Datasets:

kejian

/

sciriff-tulu-none-2000-template-1-summratio-0.85

like 0

[ { "content": "You will be presented with a citation sentence from a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\n…and Konofagou 2014; Choi et al. 2010b), chemotherapy agents (Aryal et al. 2013; Treat et al. 2007; Treat et al. 2012; Yang et al. 2012), antibodies (Kinoshita et al. 2006), magnetic nanoparticles (Fan et al. 2013), gene therapy vectors (Alonso et al. 2013), stem cells (Burgess et al. 2011) etc.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nSince deep neural networks are over-parameterized, they can memorize noisy examples.\nWe address such memorizing issue in the presence of annotation noise.\nFrom the fact that deep neural networks cannot generalize neighborhoods of the features acquired via memorization, we hypothesize that noisy examples do not consistently incur small losses on the network under a certain perturbation.\nBased on this, we propose a novel training method called Learning with Ensemble Consensus (LEC) that prevents overfitting noisy examples by eliminating them using the consensus of an ensemble of perturbed networks.\nOne of the proposed LECs, LTEC outperforms the current state-of-the-art methods on noisy MNIST, CIFAR-10, and CIFAR-100 in an efficient manner.\nDeep neural networks (DNNs) have shown excellent performance (Krizhevsky et al., 2012; He et al., 2016) on visual recognition datasets (Deng et al., 2009) .\nHowever, it is difficult to obtain highquality labeled datasets in practice (Wang et al., 2018a) .\nEven worse, DNNs could not generalize the training data in the presence of noisy examples .\nTherefore, there is an increasing demand for robust training methods.\nIn general, DNNs optimized with SGD first generalize clean examples under label noise .\nBased on this, recent studies consider examples that incur small losses on the network that does not overfit noisy examples as being clean (Han et al., 2018; Shen & Sanghavi, 2019) .\nHowever, such small-loss examples may be corrupted, particularly under a high level of noise.\nHence, choosing safe examples from the noisy dataset with small-loss criteria may be impractical.\nTo address this, we find the method of screening out noisy examples among small-loss examples by focusing on well-known observations:\n(i) noisy examples are learned via memorization rather than via generalization and\n(ii) under a certain perturbation, network predictions for memorized features easily fluctuate, while those for generalized features do not.\nBased on these two observations, we hypothesize that out of small-loss examples, training losses of noisy examples would increase by injecting certain perturbation to network parameters, while those of clean examples would not.\nThis suggests that examples that consistently incur small losses under multiple perturbations can be considered as being clean.\nSince this idea comes from an artifact of SGD optimization, it can be applied to any architecture optimized with SGD.\nIn this work, we introduce a method of perturbing parameters to filter noisy examples out of smallloss examples.\nBy embedding the filtering into training, we propose a new robust training scheme termed learning with ensemble consensus (LEC).\nIn LEC, the network is first trained on the entire training set for a while and then trained on the intersection of small-loss examples of the ensemble of perturbed networks.\nWe present three LECs with different perturbations and evaluate their effectiveness on three benchmark datasets with random label noise (Goldberger & Ben-Reuven, 2016; Ma et al., 2018) , open-set noise (Wang et al., 2018b) , and semantic noise.\nThe proposed LEC outperforms existing robust training methods by efficiently removing noisy examples from training batches.\nGeneralization of DNNs.\nAlthough DNNs are over-parameterized, they have impressive generalization ability (Krizhevsky et al., 2012; He et al., 2016) .\nSome studies argue that gradient-based optimization plays an important role in regularizing DNNs (Neyshabur et al., 2014; .\nshow that DNNs optimized with gradient-based methods generalize clean examples in the early stage of training.\nSince mislabeling reduces the correlation with other training examples, it is likely that noisy examples are learned via memorization.\nTherefore, we analyze the difference between generalized and memorized features to discriminate clean and noisy examples.\nTraining DNNs with Noisy datasets.\nLabel noise issues can be addressed by reducing negative impact of noisy examples.\nOne direction is to train with a modified loss function based on the noise distribution.\nMost studies of this direction estimate the noise distribution prior to training as it is not accessible in general (Sukhbaatar et al., 2014; Goldberger & Ben-Reuven, 2016; Patrini et al., 2017; Hendrycks et al., 2018) .\nAnother direction is to train with modified labels using the current model prediction (Reed et al., 2014; Ma et al., 2018) .\nAside from these directions, recent work suggests a method of exploiting small-loss examples (Jiang et al., 2017; Han et al., 2018; Yu et al., 2019; Shen & Sanghavi, 2019) based on the generalization ability of DNNs.\nHowever, it is still hard to find clean examples by relying on training losses.\nThis study presents a simple method to overcome such a problem of small-loss criteria.\nThis work presents the method of generating and using the ensemble for robust training.\nWe explore three simple perturbation methods to generate the ensemble and then develop the way of identifying noisy examples through ensemble consensus on small-loss examples.\nAlong with growing attention to the use of small-loss examples for robust training, we expect that our ensemble method will be useful for such training methods.", "role": "user" }, { "content": "This work presents a method of generating and using ensembles effectively to identify noisy examples in the presence of annotation noise.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Gene\"].\n\nPlease return the output as a JSON object of the format: {\"Gene\": [\"SSX\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nA new cytokine (IK) down-regulating HLA class II: monoclonal antibodies, cloning and chromosome localization. The role of HLA class II Antigens in the control of the immune response is determined not only by the genetic polymorphism of these molecules, but also by their density on the cell surface. It is therefore essential to identify the signals that modulate HLA Class II gene activity in normal and neoplastic cells. We have purified a cytokine (IK factor, 19 kDa) secreted by the leukemic cell line K562 and several cancer cells, which inhibits HLA Class II antigen induction by IFN-gamma. We produced specific mAbs which antagonize the biological effect of IK in colon carcinoma Colo 205 cells induced to express HLA-DR molecules by IFN-gamma. Moreover, in Colo 205, HLA-DR can also be induced by the protein synthesis inhibitor Cycloheximide (0.1 micrograms ml-1); and addition of IK factor almost completely abolishes HLA class II expression. We have also performed the cloning and the sequencing of a specific cDNA. This probe recognizes a 2.1 Kb mRNA in different cell types. The nucleotide sequence exhibits no homologies with known cytokines. IK gene localization shows that it maps on chromosome 2p15-p14. The transient transfection of the cDNA in COS cells induces the secretion of a biologically active 19 kDa protein which is recognized in Western blot by 1C5B11 blocking mAb. This paper reports the characterization of a new cytokine down-regulating HLA class II Antigens, whose analysis will help to better understand HLA class II gene regulation and the mechanism of escape from immunorecognition in cancer cells.", "role": "user" }, { "content": "{\"Gene\": [\"HLA-DR\", \"HLA class II\", \"IK\", \"IFN-gamma\", \"cytokine\", \"HLA Class II\", \"IK factor\", \"cytokine (IK)\"]}", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Higher-Order Oligomerization Targets Plasma Membrane Proteins and HIV Gag to Exosomes \nArticle:\nAbstract:\nExosomes are secreted organelles that have the same topology as the cell and bud outward( outward is defined as away from the cytoplasm) from endosome membranes or endosome-like domains of plasma membrane. Here we describe an exosomal protein-sorting pathway in Jurkat T cells that selects cargo proteins on the basis of both higher-order oligomerization( the oligomerization of oligomers) and plasma membrane association, acts on proteins seemingly without regard to their function, sequence, topology, or mechanism of membrane association, and appears to operate independently of class E vacuolar protein-sorting( VPS) function. We also show that higher-order oligomerization is sufficient to target plasma membrane proteins to HIV virus–like particles, that diverse Gag proteins possess exosomal-sorting information, and that higher-order oligomerization is a primary determinant of HIV Gag budding/exosomal sorting. In addition, we provide evidence that both the HIV late domain and class E VPS function promote HIV budding by unexpectedly complex, seemingly indirect mechanisms. These results support the hypothesis that HIV and other retroviruses are generated by a normal, nonviral pathway of exosome biogenesis.\nIntroduction:\nExosomes are secreted organelles that have the same topology as the cell and a diameter of approximately 50–150 nm, though larger exosomes have also been reported[1–3]. Exosome content varies considerably, but commonly includes tetraspanins, integrins, major histocompatibility complex proteins, cytosolic chaperones, cholesterol, and glycosphingolipids[2, 4]. Many animal cell types secrete exosomes, and exosome-mediated signaling has been implicated in antigen presentation, morphogenesis, sperm maturation, and cancer–host interactions[2, 4–6]. Less is known about the mechanisms of exosome biogenesis. Cells can generate exosomes by either of two modes, immediate or delayed. The immediate mode of exosome biogenesis occurs at the cell surface and involves outward vesicle budding( outward is defined as away from the cytoplasm) from endosome-like domains of the plasma membrane, domains we refer to as ELDs[3]. In contrast, the delayed mode of exosome biogenesis begins with outward vesicle budding at the limiting membrane of endosomes, generating vesicle-laden endosomes, typically referred to as multivesicular bodies( MVBs)[2, 4]. If an MVB fuses with the plasma membrane, its internal vesicles are released as exosomes. However, MVBs can also fuse with lysosomes, leading to vesicle and cargo destruction[7]. Some cell types, such as T cells, prefer to make exosomes by the immediate mode, whereas other cell types, such as macrophages, prefer to make exosomes via the delayed mode. Interestingly, human immunodeficiency virus( HIV) particles bud from these two cell types at the same sites as exosomes, have the same topology as exosomes, have a similar size as exosomes, and are enriched in the same molecules as exosomes[3, 8–13]. These and other observations indicate that there might be a mechanistic relationship between retrovirus budding and exosome biogenesis[11]. A major step in understanding the biogenesis of any organelle is to identify and characterize the cis-acting signals that target proteins to the organelle. Here we show that higher-order oligomerization and plasma membrane association target proteins to sites of exosome budding and into exosomes. Proteins can be directed into this exosomal protein sorting pathway by( 1) exposing cell surface proteins to exogenous cross-linking agents( e. g., primary and secondary antibodies),( 2) appending plasma membrane anchors to highly oligomeric cytoplasmic proteins, or( 3) adding multiple homo-oligomerization domains to intracellular acylated proteins. The class E vacuolar protein-sorting( VPS) proteins are thought to drive outward vesicle budding[14], but we find that inhibiting class E VPS function does not block exosome budding or the oligomerization-induced exosomal protein-sorting pathway. We also find that retroviral Gag proteins are sorted to ELDs and exosomes, that exosomal targeting information directs proteins to sites of HIV Gag budding and onto HIV virus–like particles( VLPs), that higher-order oligomerization is a primary determinant of HIV Gag budding, that p6-deficient HIV can bud independently of class E VPS function, and that acquisition of exosomal sorting information is sufficient to induce the budding of a yeast long terminal repeat( LTR) retrotransposon. Taken together, these results support the hypothesis that retroviral budding is a form of exosome biogenesis[11].\nDiscussion:\nOur data indicate that protein sorting to retroviral VLPs and viruses is mediated by the same signals that target proteins to exosomes. Our first evidence for this was the finding that higher-order oligomerization of CD43 is sufficient to induce its trafficking to HIV Gag VLPs. Other parallels between exosomal protein sorting and protein trafficking to VLPs/viruses include the sorting of diverse Gag proteins to ELDs and exosomes, the oligomerization-induced sorting of Gag to ELDs and exosomes, the ability to remove p6 without affecting release of HIV Gag VLPs or release of PR-deficient HIV virus, the fact that adding a plasma membrane anchor was sufficient to induce the budding of TyA( the Gag-like structural protein of a yeast LTR retrotransposon), and the fact that all budding-competent proteins were sorted to ELDs and secreted from the cell in exosomes, whether of viral origin or not. An exosomal origin of HIV is also consistent with many prior observations[11], including the secretion of amyloidogenic, exosomal proteins on retrovirus particles[56] and the interactions between HTLV-1 Gag and the exosomal proteins CD81 and CD82[57]. The primary significance of these observations is that they reveal retrovirus budding to be a manifestation of a normal, cell-encoded exosome biogenesis pathway. This has important implications for the targeting of viral and nonviral proteins to sites of retrovirus budding and onto retrovirus particles, the identification and characterization of retrovirus budding factors( and exosome biogenesis factors), and potentially for the targeting of antiretroviral agents to sites of budding and onto retroviral particles. An exosomal mechanism of retrovirus budding is also likely relevant to the evolutionary relationships between retroviruses and LTR retrotransposons[11]. For example, the ability to target TyA to ELDs and exosomes merely by adding an acylation tag indicates that acquisition of exosomal sorting information might be a critical step in the evolution of retroviruses from LTR retrotransposons, and that loss of membrane binding might mediate the reverse transition. This notion is consistent with the ability to convert the mouse LTR retrotransposon MusD from an intracellular, noninfectious transposon into a budding, infectious retrovirus merely by appending a retroviral MA domain to the N-terminus of its Gag-like protein[58]. The intracellular trafficking of HIV Gag has been studied closely. Some have concluded that retrovirus assembly initiates at endosomes and then proceeds to completion either there or at the plasma membrane[8, 10, 59–61], whereas others report that retrovirus assembly initiates at the plasma membrane and proceeds to budding either there or at endosomes[62]. To us, these pathways are all consistent with an exosomal origin for HIV, for they are each compatible with the fact that exosome budding can occur at either ELDs or endosomes. Specifically, it appears that exosomes can bud from either endosomes or from ELDs, and that ELDs might form by lateral sorting in the plasma membrane as well as by endosome–plasma membrane fusion. Our results also have some relevance for exosome morphogenesis. The varied sizes and shapes of AcylTyA-containing exosomes indicate that these characteristics are not under strict mechanistic control. This suggests a model of exosome morphogenesis in which vesicle size and shape are mediated by the cargoes themselves. This would be consistent with the highly uniform morphology of retrovirus particles[13], as well as the pronounced effects that certain Gag and PR mutations can have on virus morphology[24]. An exosomal model of retrovirus budding also offers new insights into why HIV budding is promoted by the HIV late domain. The most parsimonious interpretation of the data is that the late domain promotes virus budding indirectly. As for how, one possibility is that the late domain negatively regulates HIV PR until after budding, thereby ensuring the oligomerization-induced sorting of HIV Gag to exosomes. This hypothesis is supported by additional observations in the literature, such as the inhibitory effect of PR activity on budding[43] and the premature cleavage of the HIV Gag-Pol polyprotein in the context of an HIV late domain mutant[63]. The direct and indirect interactions between the HIV late domain and the class E VPS machinery indicate that they act together. Our data support this notion insofar as they show that class E VPS function appears to promote HIV budding via an indirect mechanism. It should be noted that our data do not exclude the possibility of more complex retrovirus budding mechanisms. For example, it is formally possible that the p6 domain and class E VPS proteins play direct, mechanistic, and essential roles in delivering HIV Gag to exosomes in some other cell types, or perhaps in a non-exosomal mechanism of budding. However, this last alternative offers no explanation for why HIV budding occurs at the same sites as exosome biogenesis or why HIV particles are enriched in exosomal markers[3, 8, 9, 11, 12, 56, 64–66].", "role": "user" }, { "content": "Exosomes are small , secreted organelles with the same topology as the cell and a similar size and composition as retrovirus particles . Based on these similarities , we proposed that retroviruses are , at their most fundamental level , exosomes . Little is known about the mechanisms of exosome biogenesis . We show here that higher-order oligomerization and plasma membrane binding are sufficient to target proteins into both exosomes and HIV virus-like particles . We also find that the HIV protein Gag , which possesses these general exosomal sorting elements , requires only these elements to bud from human cells . Others have proposed that the HIV p6 domain and the host class E vacuolar protein-sorting ( VPS ) machinery play direct , essential , and mechanistic roles in HIV budding . However , we show here that p6-deficient HIV can bud from cells at normal levels and that both p6-deficient HIV and exosomes can bud independently of class E VPS function . Thus , it appears that exosome biogenesis pathways mediate the budding of HIV from cells , whereas the HIV p6 domain and the class E VPS machinery promote budding indirectly .", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\": [\"Arsenic\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nCytotoxic constituents from the fungus Daldinia concentrica (Xylariaceae). Phytochemical study on the methanol extract of the fruit bodies of Vietnamese fungus Daldinia concentrica has led to the isolation and structural elucidation of three cytotoxic constituents, 6,8-dihydroxy-3-methyl-3,4-dihydroisocoumarin (1), (22R)-hydroxylanosta-7,9(11),24-trien-3-one (2) and ergosterol (3). Their structures were elucidated by 2D-NMR and FT-ICR-MS. All the three compounds showed moderate cytotoxicity against four cancer cells, KB (a human epidermal carcinoma), MCF7 (human breast carcinoma), SK-LU-1 (human lung carcinoma) and HepG2 (hepatocellular carcinoma). In addition, the isocoumarin (1) inhibited the growth of Staphylococcus aureus with the IC50 value of 87.81 µg mL(-1).", "role": "user" }, { "content": "{\"Chemical\": [\"(22R)-hydroxylanosta-7,9(11),24-trien-3-one\", \"isocoumarin\", \"6,8-dihydroxy-3-methyl-3,4-dihydroisocoumarin\", \"methanol\", \"ergosterol\"]}", "role": "assistant" } ]

[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nLow risk of hepatitis B virus recurrence after withdrawal of long-term hepatitis B immunoglobulin in patients receiving maintenance nucleos(t)ide analogue therapy.\nAbstract 1:\nHepatitis B virus ( HBV ) recurrence rates of 0 - 16 % had been reported in patients maintained on nucleoside analogues ( NA ) after hepatitis B immunoglobulin ( HBIG ) discontinuation after orthotopic liver transplantation ( OLT ) . However , follow-up in most studies was short . We aim ed to determine the long-term risk of HBV recurrence using this strategy . All HBV patients who received > or = 7 doses of intravenous HBIG after OLT , with no HBV recurrence while receiving HBIG , and who eventually discontinued HBIG and were maintained on NA , were included . HBV recurrence was defined as HBsAg-positive or HBV DNA > or = 5 log copies/mL on 2 consecutive occasions . Twenty-one patients met the inclusion criteria . Immediate post-OLT prophylaxis was combination HBIG and NA in 15 patients , whereas 6 patients received HBIG monotherapy for 62 - 109 months before NA was added . HBIG was discontinued a median of 26 ( range , 0.2 - 121 ) months after OLT . Median follow-up post-HBIG discontinuation was 40 ( range , 5 - 51 ) months . Only 1 patient , who had 12 months of HBIG and was noncompliant to NA therapy , had HBV recurrence , 34 months after HBIG discontinuation . One patient had HBV DNA of 3.3 log copies/mL 47 and 48 months after HBIG discontinuation but remained HBsAg-negative . Lamivudine-resistant mutations were detected in both patients . Probability of HBV recurrence was 0 % and 9 % at 2 and 4 years after HBIG discontinuation . Three patients had 1 - 2 episodes of transiently detectable HBV DNA . All were HBV DNA and HBsAg negative on repeated tests over a period of 2 - 36 months . Maintenance therapy with NA after discontinuation of long-term HBIG therapy is associated with a low risk of HBV recurrence after OLT in compliant HBV patients\n\n\nTitle 2:\nShort-Term High-Dose Followed by Long-Term Low-Dose Hepatitis B Immunoglobulin and Lamivudine Therapy Prevented Recurrent Hepatitis B After Liver Transplantation\nAbstract 2:\nHepatitis B immunoglobulin ( HBIg ) and lamivudine combination has been accepted as the best way to control hepatitis B recurrence after liver transplantation . However , the optimal dose of HBIg and the target titer of hepatitis B surface antibody ( HBsAb ) remain unclear . We report our satisfactory experience with high-dose HBIg in the early period followed by low-dose HBIg with lamivudine . Subjects comprised five patients with fulminant hepatitis ( FH ) and 18 patients with liver cirrhosis ( LC ) who underwent liver transplantation . HBIg at a dosage of 200 IU/kg per day was administered for one week postoperatively . Thereafter , HBIg was administered only for HBsAb titer < 100 IU/L. After six months , HBIg was withdrawn in FH and administered in LC only for HBsAb titer < 10 IU/L. Lamivudine was administered to two FH and all LC cases . Although two patients with LC showed transient hepatitis B surface antigen ( HBsAg ) recurrence , all patients remained HBsAg-negative at the final follow-up date . This method allows reliable and cost-effective control of hepatitis B recurrence\n\n\nTitle 3:\nThe role of entecavir in preventing hepatitis B recurrence after liver transplantation\nAbstract 3:\nOBJECTIVE : Although hepatitis B recurrence after liver transplantation has been reduced to 0%–10 % since the application of the combination therapy of hepatitis B immunoglobulin ( HBIG ) and lamivudine , the viral mutation resistance of lamivudine is still an obstacle to the outcome of liver transplantation . Here we evaluate the role of entecavir in preventing hepatitis B recurrence after liver transplantation\n\n\nTitle 4:\nA randomized study of adefovir dipivoxil in place of HBIG in combination with lamivudine as post–liver transplantation hepatitis B prophylaxis\nAbstract 4:\nPrior to effective prophylaxis , liver transplantation for hepatitis B virus (HBV)‐related disease was frequently complicated by recurrence , which could be severe and rapidly progressive . Combination hepatitis B immunoglobulin ( HBIG ) and lamivudine prophylaxis reduces this rate of recurrence to < 5 % at 5 years ; however , HBIG administration is costly and inconvenient . We conducted a multicenter r and omized study of adefovir dipivoxil substitution for low‐dose intramuscular ( IM ) HBIG in patients without HBV recurrence at least 12 months posttransplantation for HBV‐related disease . Thirty‐four patients were r and omized , 16 to adefovir ( 1 patient withdrew consent at 3 months and is not considered in the results ) and 18 to continue HBIG . All continued lamivudine . Groups were well matched by age , sex , and time since transplantation ( median , 4.5 years ) , and background virological risk for HBV recurrence ( 30 % of patients in the adefovir group , 24 % in the HBIG group having detectable HBV DNA at transplantation ) . All patients were alive at study completion without recurrence . One patient in the adefovir group became hepatitis B surface antigen – positive at 5 months but was persistently HBV DNA undetectable via polymerase chain reaction ( sensitivity 14 IU/mL ) over the following 20 months . Median creatinine was not significantly changed over the course of the study in either group . One patient in the adefovir group with a background of diabetic and hypertensive nephropathy ( baseline creatinine 150 μmol/L ) developed increased creatinine leading to dose reduction and ultimately cessation of adefovir at 15 months . Yearly cost of combination adefovir/lamivudine prophylaxis was $ 8,290 versus $ 13,718 IM HBIG/lamivudine . Conclusion : Compared with combination HBIG plus lamivudine prophylaxis , combination adefovir plus lamivudine provides equivalent protection against recurrent HBV infection but with better tolerability and less cost . ( HEPATOLOGY 2008 .\n\n\nTitle 5:\nPosttransplantation Hepatitis B Prophylaxis with Combination Oral Nucleoside and Nucleotide Analog Therapy\nAbstract 5:\nLiver transplant recipients are at risk of developing recurrent hepatitis B after liver transplantation for hepatitis B virus (HBV)‐related liver disease . We evaluated the efficacy of a new hepatitis B prophylaxis regimen involving conversion from at least 12 months of HBIg with lamivudine to combination therapy with an oral nucleoside and nucleotide analog . Between June 2008 and May 2010 , a total of 61 liver transplant recipients were converted to a combination of a nucleoside and nucleotide analog . The mean ( ±st and ard deviation ) follow‐up time after conversion was 15.0 ( ±6.1 ) months . Recurrent HBV occurred in two ( 3.3 % ) patients at 3.1 and 16.6 months after HBIg cessation . The overall person time incidence rate for HBV recurrence after HBIg cessation was 2.7 cases per 100 person‐years . The estimate of HBV recurrence was 1.7 % at 1 year after HBIg cessation . HBIg cessation a minimum of 12 months after liver transplantation with subsequent combination therapy with a nucleoside and nucleotide analog provides effective prophylaxis against recurrent HBV infection . The clinical implication s of HBsAg detection without clinical , biochemical or molecular manifestations of recurrent hepatitis B require further study\n\n\nTitle 6:\nIntramuscular hepatitis B immune globulin combined with lamivudine for prophylaxis against hepatitis B recurrence after liver transplantation.\nAbstract 6:\nImmunoprophylaxis using intravenous ( IV ) hepatitis B immune globulin ( HBIG ) decreases the recurrence of hepatitis B virus ( HBV ) infection after orthotopic liver transplantation ( OLT ) . However , IV HBIG is expensive , has significant side effects , and is inconvenient to administer . An alternative approach for prophylaxis using intramuscular ( IM ) HBIG and oral lamivudine was prospect ively evaluated in this study . Ten consecutive patients with cirrhosis with HBV infection who underwent OLT were included in this study . Nine of 10 patients received lamivudine , 150 mg/d , for an average duration of 8.6 months before OLT . Two of 10 patients with detectable HBV DNA at the time of OLT received 10,000 U ( 45 mL ) of IV HBIG daily for 7 consecutive days , followed by 5 mL of IM HBIG weekly for the next 3 weeks , then every 3 weeks . The other 8 patients were HBV DNA negative at OLT and received one dose of IV HBIG ( 45 mL ) during surgery , followed by 5 mL of IM HBIG weekly for 4 weeks , then every 3 weeks . All patients received lamivudine , 150 mg/d , after OLT . During a mean follow-up of 15.6 months , 9 of 10 patients achieved a protective hepatitis B surface antibody ( HBsAb ) titer greater than 200 IU/L and had no evidence of HBV recurrence . One patient failed to develop an adequate HBsAb titer and developed histological and virological evidence of recurrence . One patient died unrelated to HBV recurrence . Our preliminary data suggest that this combination prophylaxis with IM HBIG and lamivudine is effective and potentially cost saving\n\n\nTitle 7:\nNo hepatitis recurrence using combination prophylaxis in HBV-positive liver transplant recipients with YMDD mutants.\nAbstract 7:\nRecurrence of hepatitis B impairs the outcome of liver transplantation ( OLT ) . In serum hepatitis B virus (HBV)-DNA-positive recipients , prophylaxis using lamivudine and immunoglobulins ( HBIg ) reduces the risk of recurrence , but it is undefined whether this regimen also protects c and i date s with YMDD mutants . Seventeen OLT viraemic c and i date s received pre-emptive lamivudine followed by post-OLT prophylaxis with lamivudine and HBIg . Both sera and liver biopsies were prospect ively collected and high-sensitive polymerase chain reaction ( PCR ) assay was applied for HBV-DNA detection . Finally , the presence of YMDD mutants was explored in all PCR-positive sample s. All patients remained hepatitis B recurrence-free after a mean follow up of 32 months . By PCR , serum HBV-DNA was detectable in 64.3 % of cases at OLT-baseline , in 64.7 % under combined prophylaxis and in 58.8 % in patients ( 70.5 % of the total ) with a minimum follow up of 24 months . At OLT-baseline , YMDD mutants were found in 44.4 % of patients . After OLT , mutants were present in 50 % of patients but only in 16.6 % of cases in the long period . Although 41 % of the native livers and 42.8 % of the analysed grafts harboured HBV-DNA , YMDD mutants were detected in 57 % of the native positive livers . YMDD mutants were largely detected both at OLT-baseline and post-OLT , but their presence decreased over time . Regardless of the presence of YMDD mutants , no hepatitis B recurrence was observed in our OLT recipients using pre-emptive lamivudine followed by continuous prophylaxis with lamivudine and HBIg", "role": "user" }, { "content": "Our findings favor the use of HBIG and a hgbNA instead of HBIG and LAM combined prophylaxis against HBV recurrence after LT", "role": "assistant" } ]

[ { "content": "You will be presented with a citation segment from the section of an NLP research paper, as well as the context surrounding that citation. Classify the intent behind this citation by choosing from one of the following categories:\n- Background: provides context or foundational information related to the topic.\n- Extends: builds upon the cited work.\n- Uses: applies the methods or findings of the cited work.\n- Motivation: cites the work as inspiration or rationale for the research.\n- CompareOrContrast: compares or contrasts the cited work with others.\n- FutureWork: cites the work as a direction for future research.\n\nYour answer should be a single word from the following list of options: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. Do not include any other text in your response.\n\nSection Title:\nNone\n\nContext before the citation:\nThe UMLS – the Unified Medical Language System (UMLS) has been developed and maintained by National Library of Medicine (NLM) [17]. other attributes associated with genes and the products they encode. It records gene names, symbols, and many \u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\n\nCitation Sentence:\nThe UMLS -- the Unified Medical Language System ( UMLS ) has been developed and maintained by National Library of Medicine ( NLM ) [ 17 ] .\n\nContext after the citation:\nIt contains three knowledge sources: the Metathesaurus (META), the SPECIALIST lexicon, and the Semantic Network. The META provides a uniform, integrated platform for over 60 biomedical vocabularies and classifications, and group different names for the same concept. The SPECIALIST lexicon contains syntactic information for many terms, component words, and English words, including verbs, which do not appear in the META. The Semantic Network contains information about the types or categories (e.g., “Disease or Syndrome”, “Virus”) to which all META concepts have been assigned.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the mechanism of action of decitabine?\n\nContext: The use of the DNA methylation inhibitor decitabine (Dacogen®) has been approved in the treatment of hematological malignancies, and its clinical effects on solid tumors have gained attention.\nlow-dose decitabine and combined therapy show significant improvement in solid tumor treatment.\nHere, we demonstrate dose-dependent degradation of Dnmt1 in mouse embryonic stem (ES) cells expressing catalytic site mutant (cys-ser), confirming that the covalent bond formation between Dnmt1 and decitabine-incorporated DNA is not essential for this process.\nNMT1o, the oocyte-specific isoform that lacks the N-terminal 118-amino acid domain, did not undergo decitabine-mediated degradation, which further proves the requirement of multiple domains including nuclear localization signa\nAnalysis of glycerol density gradient fractions of micrococcal nuclease-digested nuclei showed that both nucleosomal and nucleoplasmic DNMT1 are degraded upon decitabine treatment.\nThe maximal effect caused by inhibiting protein kinase C (PKC) persuaded us to investigate further its role in decitabine-mediated DNMT1 degradation.\nThese studies provide substantial evidence that decitabine-induced degradation of the maintenance methyltransferase DNMT1 does not require covalent bond formation with the substrate and also elucidate its underlying molecular mechanism.\nDecitabine is a potent demethylating agent that exhibits clinical activity against myeloid malignancies. Numerous genes silenced by hypermethylation are reactivated by decitabine through a mechanism involving promoter demethylation with subsequent release of histone deacetylases (HDACs) and accumulation of acetylated histones. Recent studies indicating that decitabine also induces regional chromatin remodeling of some unmethylated genes suggest additional mechanisms of action.\nOur findings indicate that decitabine can relieve p21WAF1 repression in AML by a mechanism that involves release of HDAC1 without requiring promoter demethylation.\nNumerous genes silenced by hypermethylation are reactivated by decitabine through a mechanism involving promoter demethylation with subsequent release of histone deacetylases (HDACs) and accumulation of acetylated histones.\n5-Aza-2'-deoxycytidine (decitabine) can relieve p21WAF1 repression in human acute myeloid leukemia by a mechanism involving release of histone deacetylase 1 (HDAC1) without requiring p21WAF1 promoter demethylation.\nDecitabine, a demethylating drug, is the first-line treatment for myelodysplastic syndromes and gains better overall survival, which is based on epigenetic mechanism\nDemethylating agent decitabine was reported to be able to up-regulate CTAs through its hypomethylation mechanism, thus enhance the immunogenicity of leukemia cells\nHowever, further elucidation of its mechanism of action is required, as clinical response to decitabine does not correlate with demethylation of the p15 gene promoter or the repetitive DNA element LINE.\nIn the area of epigenetic therapy, the demethylating drug decitabine (5-aza-2'-deoxycytidine) is increasingly used to treat acute myelogenous leukemia and myelodysplastic syndrome, but the mechanisms of its anticancer activity have remained unclear.\nAn epigenetic approach to the treatment of advanced MDS; the experience with the DNA demethylating agent 5-aza-2'-deoxycytidine (decitabine) in 177 patients.\nNumerous genes silenced by hypermethylation are reactivated by decitabine through a mechanism involving promoter demethylation with subsequent release of histone deacetylases (HDACs) and accumulation of acetylated histones. Recent studies indicating that decitabine also induces regional chromatin remodeling of some unmethylated genes suggest additional mechanisms of action.\nHowever, further elucidation of its mechanism of action is required, as clinical response to decitabine does not correlate with demethylation of the p15 gene promoter or the repetitive DNA element LINE.", "role": "user" }, { "content": "Decitabine reactivates unmethylated p21WAF1 in some AML cell lines but the possible occurrence of p21WAF1 methylation in AML in vivo has not been studied in detail and decitabine effects on p21WAF1 chromatin remodeling have not been reported. We also discuss the following questions: What is the best administration schedule of decitabine in solid tumors? Is there tumor type specificity for decitabine-based epigenetic therapy? We found that p21WAF1 mRNA was undetectable in 6 of 24 AML patient samples and 4 of 5 AML cell lines but there was no evidence of p21WAF1 promoter methylation.", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Sleep-Dependent Reactivation of Ensembles in Motor Cortex Promotes Skill Consolidation\nArticle:\nAbstract:\nDespite many prior studies demonstrating offline behavioral gains in motor skills after sleep, the underlying neural mechanisms remain poorly understood. To investigate the neurophysiological basis for offline gains, we performed single-unit recordings in motor cortex as rats learned a skilled upper-limb task. We found that sleep improved movement speed with preservation of accuracy. These offline improvements were linked to both replay of task-related ensembles during non-rapid eye movement( NREM) sleep and temporal shifts that more tightly bound motor cortical ensembles to movements; such offline gains and temporal shifts were not evident with sleep restriction. Interestingly, replay was linked to the coincidence of slow-wave events and bursts of spindle activity. Neurons that experienced the most consistent replay also underwent the most significant temporal shift and binding to the motor task. Significantly, replay and the associated performance gains after sleep only occurred when animals first learned the skill; continued practice during later stages of learning( i. e., after motor kinematics had stabilized) did not show evidence of replay. Our results highlight how replay of synchronous neural activity during sleep mediates large-scale neural plasticity and stabilizes kinematics during early motor learning.\nIntroduction:\nThe cardinal features of motor skill learning are enhanced speed and automaticity of motor execution with preserved accuracy[1–3]. Motor learning is known to progress through a series of stages: an early stage accompanied by rapid improvements in accuracy with continued variability of movement kinematics, followed by consolidation of these processes and transition to a later stage of learning, in which kinematics are largely stabilized but slow improvements in accuracy continue to occur[4–6]. The underlying neural basis by which kinematics become stabilized during early motor learning is not well understood. Human studies suggest that non-rapid eye movement( NREM) sleep is essential for this consolidation and, in addition, results in additional gains in skilled motor performance[7–14]. Even brief naps during the day can mediate these “offline” motor improvements[11, 15, 16], including faster movements and reduced variability in timing. There is evidence that NREM sleep promotes offline gains. Prior studies have described a relationship between motor learning, local slow-wave oscillations[17], the expression of immediate-early plasticity-related genes[18] and stabilization of dendritic spines[19]. However, how large-scale patterns of neural activity drive plasticity of specific motor circuits to result in enhanced motor performance is unknown. Based primarily on studies of single-unit activity conducted during hippocampal-dependent behaviors[9, 13, 16, 17, 20–25], we hypothesized that reactivations of task-related emergent neural firing during NREM sleep may be related to subsequent neural plasticity and associated offline behavioral gains. This hypothesis is largely consistent with theoretical models for how NREM sleep promotes learning more generally[20–22, 26–29], but to our knowledge, there is little experimental support of this during procedural memory formation.\nDiscussion:\nMany previous studies have examined the role of sleep in promoting offline gains in motor skill performance, with NREM sleep in particular promoting various types of motor learning[9, 13, 14, 16, 17, 53, 54]. However, little was known about the neurophysiological processes by which NREM sleep mediated motor memory consolidation. Here we show that reactivation of task-related neural patterns during NREM sleep is explicitly related to both performance improvements and plasticity of neural responses. We specifically found that these high reactivation events were closely linked to an increase in fast spindle oscillations and became slightly phase-shifted relative to the slow oscillations. Finally, we found that neural reactivation is very specific to early motor learning, and not simply a reflection of motor practice; NREM-sleep reactivation was not evident during later stages of motor learning once kinematic patterns had been stabilized. These results suggest that task-related neural reactivation during NREM sleep plays a key role in stabilizing the basic motor pattern during motor learning, with subsequent improvements not dependent on large-scale reactivation during sleep. We show here that sleep-dependent reactivation of neural ensembles occurs in the context of procedural learning. Prior demonstrations of reactivation in cortex have been described in visual[21] and prefrontal[20, 50, 55, 56] cortex. Importantly, these studies occurred in the context of hippocampal-dependent behavior and primarily in coordination with replay events from the hippocampus[20, 21, 50, 55, 56]. Another demonstration of sleep-dependent reactivation, by our group, occurred in the context of neuroprosthetic learning[29]. While neuroprosthetic learning is beginning to be explored in more detail[57–59], it is unclear whether this learning represents declarative, procedural, or some more abstract form of learning that is fundamentally different than either of the above. We thus identify the role of neural reactivation measured at single-neuron resolution for motor memory consolidation. Prior research has divided motor learning into an early phase, associated with the establishment of gross kinematic patterns and rapid gains in motor performance, and a later phase, associated more strongly with subtle refinements of kinematic patterns and more incremental changes in skill acquisition[1, 2, 5]. We show here that large-scale reactivation of neural ensembles is associated with kinematic improvements and related changes in neural activity patterns. Indeed, our study suggests that offline processing during sleep may play a key role in the consolidation of motor memories, thus allowing animals to transition to a later phase of learning that is more strongly associated with more subtle motor refinements and increased automation[60]. We also found that after sleep there was greater temporal binding of single-unit activity in motor cortex to the initiation of the reach movement. We hypothesize that the faster activation of neurons after sleep are related to the binding of separate motor programs encoding specific parts of the complex movement( i. e., “reach, grasp, retract”), into one integrated motor program. While our evidence suggests that motor cortex is the final output of this program, it may not be where this program is ultimately “stored;” in other words, the ensembles controlling the different motor actions may be bound together by intrinsic connectivity within motor cortex or may be activated through distributed circuits that occur across cortico-striatal or prefrontal circuits[61]. It is important to point out that in hippocampal-dependent replay, systems consolidation theory would suggest that memories are being transferred from subcortical to cortical representations. In motor learning, it may well be that memories are being transferred from cortical to subcortical representations, perhaps representing a fundamentally different role for reactivation. Further research will be required to assess these ideas. Studies conducted in both rodents and humans have demonstrated that early motor learning and motor cortical activity itself involves a distributed set of circuits including attentional/prefrontal regions, as well as cerebellum and dorso-medial striatum( i. e., the associative, prefrontal-connected portions)[3, 12, 60, 62–68]. By contrast, later phases of skill learning seem to be more strongly associated with changes within motor cortex[31, 41, 64, 64] and between dorso-lateral striatum( i. e., the “motor” striatial circuit)[62, 67–68]. This suggests that ensemble reactivation during sleep, which seems to occur most strongly in association with this early learning phase, may occur through distributed reactivation across cortical and subcortical regions involved in various aspects of these motor actions. This theory that motor ensembles are being driven by large-scale distributed networks during early motor learning processes, with stabilization associated with transfer of procedural memory into motor cortex, is consistent with what is known about how hippocampal associative circuits drive cortical replay in NREM sleep following declarative memory paradigms[22–24]. Moreover, this theory is also consistent with a recently proposed “active systems consolidation theory”[26, 28] that suggests that spindle-dense Stage-2 sleep[28] serves to synchronize global cortical processes, thus mediating long-range consolidation of synaptic plasticity[18, 19] and memory transfer to distant cortical regions[26]. Further studies involving dual recordings from disparate cortical regions during early/late motor learning sessions and during sleep will be required to demonstrate that ensemble reactivation truly is associated with active consolidation across a distributed set of cortical/subcortical brain regions. Interestingly, we found a specific involvement of fast spindles occurring during slow-wave oscillations in the reactivation of task-related neural ensembles. While largely consistent with a body of work demonstrating the involvement of fast spindles in motor learning[10, 11, 51], this was quite distinct from what had been observed across the two previous studies demonstrating cortical reactivation in rodents[29, 50]. In those studies, cortical reactivations seemed to be coupled most strongly to the peak negativity of the slow-oscillation[29, 50] and in the case of prefrontal cortex, also to hippocampal sharp-wave ripples[50], which themselves occurred near the peak negativity of slow-wave oscillations and prior to spindle oscillations. By contrast, here we find that after motor learning, reactivation events seemed to be particularly time-locked to fast spindles that occur a short time after the trough of slow delta waves. This difference may represent an important and fundamental difference between motor and other forms of learning. Indeed, one recent study has demonstrated that during the trough of slow-wave oscillations, cortical neurons are driven strongly by hippocampal circuits whereas during spindle events hippocampal circuits are suppressed and processing is driven strongly by thalamo-cortical circuits[69]. Given that the bulk of non-cortical motor processing( i. e., from the cerebellum and striatum) are transmitted back to the cortex through the ventral thalamus[69], it is certainly plausible that emergent task-related ensembles during NREM sleep may be locked to spindle events, particularly if this reactivation is being driven by distributed mechanisms as previously postulated. Together, our results shed light on the neural processes associated with offline gains in skilled motor performance. We have identified a specific neural correlate of the widely observed sleep-dependent improvement in movement efficiency and linked them to sleep dependent reactivation of activity patterns established during online earning. Our results particularly emphasize the importance of sleep during early motor learning when motor sequences are initially established. This phenomenon might be most relevant to early skill building during musical or sports training, or during early child development, when essentially all skills across both sensory and motor domains are new[54, 70]. In addition, these results suggest a potential mechanism by which NREM sleep may serve to enhance plasticity and functional recovery following brain injury[71].", "role": "user" }, { "content": "Sleep has been shown to help in consolidating learned motor tasks . In other words , sleep can induce “offline” gains in a new motor skill even in the absence of further training . However , how sleep induces this change has not been clearly identified . One hypothesis is that consolidation of memories during sleep occurs by “reactivation” of neurons engaged during learning . In this study , we tested this hypothesis by recording populations of neurons in the motor cortex of rats while they learned a new motor skill and during sleep both before and after the training session . We found that subsets of task-relevant neurons formed highly synchronized ensembles during learning . Interestingly , these same neural ensembles were reactivated during subsequent sleep blocks , and the degree of reactivation was correlated with several metrics of motor memory consolidation . Specifically , after sleep , the speed at which animals performed the task while maintaining accuracy was increased , and the activity of the neuronal assembles were more tightly bound to motor action . Further analyses showed that reactivation events occurred episodically and in conjunction with spindle-oscillations—common bursts of brain activity seen during sleep . This observation is consistent with previous findings in humans that spindle-oscillations correlate with consolidation of learned tasks . Our study thus provides insight into the neuronal network mechanism supporting consolidation of motor memory during sleep and may lead to novel interventions that can enhance skill learning in both healthy and injured nervous systems .", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"RNA\", \"CellType\", \"CellLine\", \"Protein\", \"DNA\"].\n\nPlease return the output as a JSON object of the format: {\"DNA\" : [\"TAL1\", ...], \"RNA\": [\"mRNAs\", ...], \"CellLine\": [\"T cells\", ...], \"CellType\": [\"monocytes\", ...], \"Protein\": [\"IL-2\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nNF-kappaB activation is a critical regulator of human granulocyte apoptosis in vitro. During beneficial inflammation, potentially tissue-damaging granulocytes undergo apoptosis before being cleared by phagocytes in a non-phlogistic manner. Here we show that the rate of constitutive apoptosis in human neutrophils and eosinophils is greatly accelerated in both a rapid and concentration-dependent manner by the fungal metabolite gliotoxin, but not by its inactive analog methylthiogliotoxin. This induction of apoptosis was abolished by the caspase inhibitor zVAD-fmk, correlated with the inhibition of nuclear factor-kappa B (NF-kappaB), and was mimicked by a cell permeable inhibitory peptide of NF-kappaB, SN-50; other NF-kappaB inhibitors, curcumin and pyrrolidine dithiocarbamate; and the proteasome inhibitor, MG-132. Gliotoxin also augmented dramatically the early (2-6 h) pro-apoptotic effects of tumor necrosis factor-alpha (TNF-alpha) in neutrophils and unmasked the ability of TNF-alpha to induce eosinophil apoptosis. In neutrophils, TNF-alpha caused a gliotoxin-inhibitable activation of an inducible form of NF-kappaB, a response that may underlie the ability of TNF-alpha to delay apoptosis at later times (12-24 h) and limit its early killing effect. Furthermore, cycloheximide displayed a similar capacity to enhance TNF-alpha induced neutrophil apoptosis even at time points when cycloheximide alone had no pro-apoptotic effect, suggesting that NF-kappaB may regulate the production of protein (s) which protect neutrophils from the cytotoxic effects of TNF-alpha. These data shed light on the biochemical and molecular mechanisms regulating human granulocyte apoptosis and, in particular, indicate that the transcription factor NF-kappaB plays a crucial role in regulating the physiological cell death pathway in granulocytes.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"eosinophils\", \"tissue - damaging granulocytes\", \"granulocytes\", \"neutrophils\", \"eosinophil\", \"human neutrophils\"], \"DNA\": [], \"Protein\": [\"transcription factor\", \"tumor necrosis factor - alpha\", \"nuclear factor - kappa B\", \"TNF - alpha\", \"NF - kappaB\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "You will be presented with a citation sentence from a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\nSphK1 catalyzes the phosphorylation of sphingosine to sphingosine-1phosphate (S1P), thus decreasing the level of pro-apoptosis ceramide and increasing pro-survival S1P production [30].", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "You are provided with the abstract of a scientific paper and the abstracts of the papers it references. Your task is to write a Related Work section for the main paper. This section should concisely summarize and integrate the key points from the cited abstracts, reflecting how they relate to the main paper's contributions and context. In your summary, use numerical citation markers like [1], [2], etc., to refer to the corresponding papers.\n\nMain Abstract:\nRecent development of network structure analysis shows that it plays an important role in characterizing complex system of many branches of sciences. Different from previous network centrality measures, this paper proposes the notion of topological centrality (TC) reflecting the topological positions of nodes and edges in general networks, and proposes an approach to calculating the topological centrality. The proposed topological centrality is then used to discover communities and build the backbone network. Experiments and applications on research network show the significance of the proposed approach.\n\nCited Abstract(s):\n[1]: The World Wide Web provides plentiful contents for Web-based learning, but its hyperlink-based architecture connects Web resources for browsing freely rather than for effective learning. To support effective learning, an e-learning system should be able to discover and make use of the semantic communities and the emerging semantic relations in a dynamic complex network of learning resources. Previous graph-based community discovery approaches are limited in ability to discover semantic communities. This paper first suggests the semantic link network (SLN), a loosely coupled semantic data model that can semantically link resources and derive out implicit semantic links according to a set of relational reasoning rules. By studying the intrinsic relationship between semantic communities and the semantic space of SLN, approaches to discovering reasoning-constraint, rule-constraint, and classification-constraint semantic communities are proposed. Further, the approaches, principles, and strategies for discovering emerging semantics in dynamic SLNs are studied. The basic laws of the semantic link network motion are revealed for the first time. An e-learning environment incorporating the proposed approaches, principles, and strategies to support effective discovery and learning is suggested.", "role": "user" }, { "content": "Research and learning resources form a network, and the connections are the relations among resources. Different from the communities in general complex networks, semantic communities in the relational network were discovered according to the roles of relations during reasoning on relations [1] .", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\", \"Protein\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\" : [\"Dexamethasone\", ...], \"Protein\" : [\"BRCA-1\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\n3'-R/S-Hydroxyvoacamine, a potent acetylcholinesterase inhibitor from Tabernaemontana divaricata.\nGuided by the acetylcholinesterase inhibiting activity, the bisindole alkaloid 3'-R/S-hydroxyvoacamine was isolated from a stem extract of Tabernaemontana divaricata, a plant used in Thailand in traditional rejuvenation remedies for improving the memory. The structure of the alkaloid was elucidated by extensive use of NMR spectroscopy and the complete assignment of the (1)H and (13)C NMR spectra is reported. The alkaloid acted as a non-competitive inhibitor against AChE with an IC50 value of 7.00±1.99μM. An HPLC method was developed for the quantitative analysis of the AChE inhibitor. It suggested that there was 12.4% (w/w) of 3'-R/S-hydroxyvoacamine in the alkaloid enriched fraction of T. divaricata stem.", "role": "user" }, { "content": "{\"Chemical\": [\"3\\u0027-R/S-hydroxyvoacamine\", \"(13)C\", \"(1)H\", \"3\\u0027-R/S-Hydroxyvoacamine\", \"bisindole alkaloid\"], \"Protein\": [\"acetylcholinesterase\", \"AChE\"]}", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"UnapprovedDrug\", \"Brand\", \"DrugGroup\", \"Drug\"].\n\nPlease return the output as a JSON object of the format: {\"Brand\": [\"Aspirin\", ...], \"DrugGroup\": [\"Salicylate\", ...], \"Drug\": [\"Phenobarbital\", ...], \"UnapprovedDrug\": [\"Heroin\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nNo drug/drug interaction studies have been performed.", "role": "user" }, { "content": "{\"Brand\": [], \"Drug\": [], \"DrugGroup\": [], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "content": "You will be shown an excerpt from a computer science research paper, followed by a question about the paper. Please answer the question given the context. Do not include any text in your response other than the answer.\n\nContext: There has been much interest in designing robust loss functions (e.g., Huber loss [13]) that reduce the contribution of outliers by down-weighting the loss of examples with large errors (hard examples). In contrast, rather than addressing outliers, our focal loss is designed to address class imbalance by down-weighting inliers (easy examples) such that their contribution to the total loss is small even if their number is large. In other words, the focal loss performs the opposite role of a robust loss: it focuses training on a sparse set of hard examples. The CE loss can be seen as the blue (top) curve in Figure 1. One notable property of this loss, which can be easily seen in its plot, is that even examples that are easily classified (p_{\\textrm{t}}\\gg.5) incur a loss with non-trivial magnitude. When summed over a large number of easy examples, these small loss values can overwhelm the rare class. In practice we use an \\alpha-balanced variant of the focal loss:\\textrm{FL}(p_{\\textrm{t}})=-\\alpha_{\\textrm{t}}(1-p_{\\textrm{t}})^{\\gamma}\\log(p_{\\textrm{t}}).(5)We adopt this form in our experiments as it yields slightly improved accuracy over the non-\\alpha-balanced form. Finally, we note that the implementation of the loss layer combines the sigmoid operation for computing p with the loss computation, resulting in greater numerical stability. Our next attempt to improve learning involved using the \\alpha-balanced CE loss described in §3.1. Results for various \\alpha are shown in Table 1a. Setting \\alpha=.75 gives a gain of 0.9 points AP. Finally, in early experiments, we attempted to train with the hinge loss [13] on p_{\\textrm{t}}, which sets loss to 0 above a certain value of p_{\\textrm{t}}. However, this was unstable and we did not manage to obtain meaningful results. Results exploring alternate loss functions are in the appendix. In this paper, we propose a new loss function that acts as a more effective alternative to previous approaches for dealing with class imbalance. The loss function is a dynamically scaled cross entropy loss, where the scaling factor decays to zero as confidence in the correct class increases, see Figure 1. Intuitively, this scaling factor can automatically down-weight the contribution of easy examples during training and rapidly focus the model on hard examples. Experiments show that our proposed Focal Loss enables us to train a high-accuracy, one-stage detector that significantly outperforms the alternatives of training with the sampling heuristics or hard example mining, the previous state-of-the-art techniques for training one-stage detectors. Finally, we note that the exact form of the focal loss is not crucial, and we show other instantiations can achieve similar results.\n\nQuestion: What are the other loss functions experimented by the authors'?", "role": "user" }, { "content": "The main loss function used by authors is The Focal Loss. Besides this, the other loss functions experimented on are: 1) Hinge Loss 2) Dynamically scaled cross entropy loss 3) \\alpha-balanced CE loss 4) \\alpha-balanced variant of the focal loss 5) Huber loss 6) The CE loss", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\", \"Disease\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\": [\"Naloxone\", ...], \"Disease\": [\"Hypotensive\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nThe effect of treatment with gum Arabic on gentamicin nephrotoxicity in rats: a preliminary study. In the present work we assessed the effect of treatment of rats with gum Arabic on acute renal failure induced by gentamicin (GM) nephrotoxicity. Rats were treated with the vehicle (2 mL/kg of distilled water and 5% w/v cellulose, 10 days), gum Arabic (2 mL/kg of a 10% w/v aqueous suspension of gum Arabic powder, orally for 10 days), or gum Arabic concomitantly with GM (80mg/kg/day intramuscularly, during the last six days of the treatment period). Nephrotoxicity was assessed by measuring the concentrations of creatinine and urea in the plasma and reduced glutathione (GSH) in the kidney cortex, and by light microscopic examination of kidney sections. The results indicated that concomitant treatment with gum Arabic and GM significantly increased creatinine and urea by about 183 and 239%, respectively (compared to 432 and 346%, respectively, in rats treated with cellulose and GM), and decreased that of cortical GSH by 21% (compared to 27% in the cellulose plus GM group) The GM-induced proximal tubular necrosis appeared to be slightly less severe in rats given GM together with gum Arabic than in those given GM and cellulose. It could be inferred that gum Arabic treatment has induced a modest amelioration of some of the histological and biochemical indices of GM nephrotoxicity. Further work is warranted on the effect of the treatments on renal functional aspects in models of chronic renal failure, and on the mechanism(s) involved.", "role": "user" }, { "content": "{\"Chemical\": [\"gentamicin\", \"glutathione\", \"gum Arabic\", \"GM\", \"GSH\", \"urea\", \"creatinine\"], \"Disease\": [\"nephrotoxicity\", \"Nephrotoxicity\", \"acute renal failure\", \"tubular necrosis\", \"chronic renal failure\"]}", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nDecomposition of xenobiotics during visible light irradiation in the presence of immobilised photosensitisers: kinetics study The objective of this work was to study the photosensitised oxidation of the xenobiotics benzylparaben (BeP) and 2,4dichlorophenol (2,4DCP) in aqueous solutions using photosensitisers immobilised into chitosan carrier particles and visible light radiation. Zn(II) phthalocyanine tetrasulfonate tetrasodium salt and Al(III) phthalocyanine chloride tetrasulfonic acid were used as photosensitisers. The major role of the singlet oxygen during photodegradation was proven by using scavengers of reactive oxygen species. The influence of initial xenobiotic concentration and temperature on degradation rate was examined. The investigations were focused on kinetics (Langmuir-Hinshelwood model) as well as activation energy determination. Moreover, the adsorption isotherms of BeP and 2,4DCP into chitosan carrier were determined using the Brunauer-Emmett-Teller model.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"photosensitised oxidation\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"Zn(II) phthalocyanine tetrasulfonate tetrasodium salt\", \"2,4dichlorophenol\", \"singlet oxygen\", \"immobilised photosensitisers\", \"xenobiotics\", \"benzylparaben\", \"BeP\", \"2,4DCP\", \"Al(III) phthalocyanine chloride tetrasulfonic acid\", \"reactive oxygen species\", \"xenobiotic\", \"photosensitisers\", \"scavengers\", \"chitosan\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"adsorption isotherms\"], \"Food\": [], \"HealthCareActivity\": [\"determination\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"study\"], \"SpatialConcept\": [], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research paper, followed by a question about the paper. Please extract text from the paragraph to answer the question. Do not include any text in your response other than the answer.\n\nParagraph: In contrast, SARS-CoV (lineage B βCoV) and MERS-CoV (lineage C βCoV) may cause severe lower respiratory tract infection with acute respiratory distress syndrome and extrapulmonary manifestations, such as diarrhea, lymphopenia, deranged liver and renal function tests, and multiorgan dysfunction syndrome, among both immunocompetent and immunocompromised hosts with mortality rates of ∼10% and ∼35%, respectively [5, 6] . On 31 December 2019, the World Health Organization (WHO) was informed of cases of pneumonia of unknown cause in Wuhan City, Hubei Province, China [7] . Subsequent virological testing showed that a novel CoV was detected in these patients. As of 16 January 2020, 43 patients have been diagnosed to have infection with this novel CoV, including two exported cases of mild pneumonia in Thailand and Japan [8, 9] . The earliest date of symptom onset was 1 December 2019 [10] . The symptomatology of these patients included fever, malaise, dry cough, and dyspnea. Among 41 patients admitted to a designated hospital in Wuhan, 13 (32%) required intensive care and 6 (15%) died. All 41 patients had pneumonia with abnormal findings on chest computerized tomography scans [10] . We recently reported a familial cluster of 2019-nCoV infection in a Shenzhen family with travel history to Wuhan [11] . In the present study, we analyzed a 2019-nCoV complete genome from a patient in this familial cluster and compared it with the genomes of related βCoVs to provide insights into the potential source and control strategies. The complete genome sequence of 2019-nCoV HKU-SZ-005b was available at GenBank (accession no. MN975262) ( Table 1 ). The representative complete genomes of other related βCoVs strains collected from human or mammals were included for comparative analysis. These included strains collected from human, bats, and Himalayan palm civet between 2003 and 2018, with one 229E coronavirus strain as the outgroup. Phylogenetic tree construction by the neighbour joining method was performed using MEGA X software, with bootstrap values being calculated from 1000 trees [12] . The percentage of replicate trees in which the associated taxa clustered together in the bootstrap test (1000 replicates) was shown next to the branches [13] . The tree was drawn to scale, with branch lengths in the same units as those of the evolutionary distances used to infer the phylogenetic tree. The evolutionary distances were computed using the Poisson correction method and were in the units of the number of amino acid substitutions per site [14] . All ambiguous positions were removed for each sequence pair (pairwise deletion option). Evolutionary analyses were conducted in MEGA X [15] . Multiple alignment was performed using CLUSTAL 2.1 and further visualized using BOX-SHADE 3.21. Structural analysis of orf8 was performed using PSI-blast-based secondary structure PREDiction (PSIPRED) [16] . For the prediction of protein secondary structure including beta sheet, alpha helix, and coil, initial amino acid sequences were input and analysed using neural networking and its own algorithm. Predicted structures were visualized and highlighted on the BOX-SHADE alignment. Prediction of transmembrane domains was performed using the TMHMM 2.0 server (http://www.cbs.dtu.dk/services/TMHMM/). Secondary structure prediction in the 5 ′ -untranslated region (UTR) and 3 ′ -UTR was performed using the RNAfold WebServer (http://rna.tbi.univie.ac.at/cgi-bin/ RNAWebSuite/RNAfold.cgi) with minimum free energy (MFE) and partition function in Fold algorithms and Table 2 . Putative functions and proteolytic cleavage sites of 16 nonstructural proteins in orf1a/b as predicted by bioinformatics. Putative function/domain Amino acid position Putative cleave site\n\ncomplex with nsp3 and 6: DMV formation\n\ncomplex with nsp3 and 4: DMV formation\n\nshort peptide at the end of orf1a basic options. The human SARS-CoV 5 ′ -and 3 ′ -UTR were used as references to adjust the prediction results. The single-stranded RNA genome of the 2019-nCoV was 29891 nucleotides in size, encoding 9860 amino acids. The G + C content was 38%. Similar to other (Table 2 ). There are no remarkable differences between the orfs and nsps of 2019-nCoV with those of SARS-CoV (Table 3) . The major distinction between SARSr-CoV and SARS-CoV is in orf3b, Spike and orf8 but especially variable in Spike S1 and orf8 which were previously shown to be recombination hot spots. Spike glycoprotein comprised of S1 and S2 subunits. The S1 subunit contains a signal peptide, followed by an N-terminal domain (NTD) and receptor-binding domain (RBD), while the S2 subunit contains conserved fusion peptide (FP), heptad repeat (HR) 1 and 2, transmembrane domain (TM), and cytoplasmic domain (CP). We found that the S2 subunit of 2019-nCoV is highly conserved and shares 99% identity with those of the two bat SARS-like CoVs (SL-CoV ZXC21 and ZC45) and human SARS-CoV (Figure 2 ). Thus the broad spectrum antiviral peptides against S2 would be an important preventive and treatment modality for testing in animal models before clinical trials [18] . Though the S1 subunit of 2019-nCoV shares around 70% identity to that of the two bat SARS-like CoVs and human SARS-CoV (Figure 3(A) ), the core domain of RBD (excluding the external subdomain) are highly conserved (Figure 3(B) ). Most of the amino acid differences of RBD are located in the external subdomain, which is responsible for the direct interaction with the host receptor. Further investigation of this soluble variable external subdomain region will reveal its receptor usage, interspecies transmission and pathogenesis. Unlike 2019-nCoV and human SARS-CoV, most known bat SARSr-CoVs have two stretches of deletions in the spike receptor binding domain (RBD) when compared with that of human SARS-CoV. But some Yunnan strains such as the WIV1 had no such deletions and can use human ACE2 as a cellular entry receptor. It is interesting to note that the two bat SARS-related coronavirus ZXC21 and ZC45, being closest to 2019-nCoV, can infect suckling rats and cause inflammation in the brain tissue, and pathological changes in lung & intestine. However, these two viruses could not be isolated in Vero E6 cells and were not investigated further. The two retained deletion sites in the Spike genes of ZXC21 and ZC45 may lessen their likelihood of jumping species barriers imposed by receptor specificity. A novel short putative protein with 4 helices and no homology to existing SARS-CoV or SARS-r-CoV protein was found within Orf3b ( Figure 4 ). It is notable that SARS-CoV deletion mutants lacking orf3b replicate to levels similar to those of wildtype virus in several cell types [19] , suggesting that orf3b is dispensable for viral replication in vitro. But orf3b may have a role in viral pathogenicity as Vero E6 but not 293T cells transfected with a construct expressing Orf3b underwent necrosis as early as 6 h after transfection and underwent simultaneous necrosis and apoptosis at later time points [20] . Orf3b was also shown to inhibit expression of IFN-β at synthesis and signalling [21] . Subsequently, orf3b homologues identified from three bat SARSrelated-CoV strains were C-terminally truncated and lacked the C-terminal nucleus localization signal of SARS-CoV [22] . IFN antagonist activity analysis demonstrated that one SARS-related-CoV orf3b still possessed IFN antagonist and IRF3-modulating activities. These results indicated that different orf3b proteins display different IFN antagonist activities and this function is independent of the protein's nuclear localization, suggesting a potential link between bat SARS-related-CoV orf3b function and pathogenesis. The importance of this new protein in 2019-nCoV will require further validation and study. Orf8 orf8 is an accessory protein found in the Betacoronavirus lineage B coronaviruses. Human SARS-CoVs isolated from early-phase patients, all civet SARS-CoVs, and other bat SARS-related CoVs contain fulllength orf8 [23] . However, a 29-nucleotide deletion,\n\nBat SL-CoV ZXC21 2018\n\nBat which causes the split of full length of orf8 into putative orf8a and orf8b, has been found in all SARS-CoV isolated from mid-and late-phase human patients [24] . In addition, we have previously identified two bat SARS-related-CoV (Bat-CoV YNLF_31C and YNLF_34C) and proposed that the original SARS-CoV full-length orf8 is acquired from these two bat SARS-related-CoV [25] . Since the SARS-CoV is the closest human pathogenic virus to the 2019-nCoV, we performed phylogenetic analysis and multiple alignments to investigate the orf8 amino acid sequences. The orf8 protein sequences used in the analysis derived from early phase SARS-CoV that includes full-length orf8 (human SARS-CoV GZ02), the mid-and late-phase SARS-CoV that includes the split orf8b (human SARS-CoV Tor2), civet SARS-CoV (paguma SARS-CoV), two bat SARS-related-CoV containing full-length orf8 (bat-CoV YNLF_31C and YNLF_34C), 2019-nCoV, the other two closest bat SARS-related-CoV to 2019-nCoV SL-CoV ZXC21 and ZC45), and bat SARS-related-CoV HKU3-1 ( Figure 5(A) ). As expected, orf8 derived from 2019-nCoV belongs to the group that includes the closest genome sequences of bat SARS-related-CoV ZXC21 and ZC45. Interestingly, the new 2019-nCoV orf8 is distant from the conserved orf8 or Figure 5(B) ) which was shown to trigger intracellular stress pathways and activates NLRP3 inflammasomes [26] , but this is absent in this novel orf8 of 2019-nCoV. Based on a secondary structure prediction, this novel orf8 has a high possibility to form a protein with an alpha-helix, following with a betasheet(s) containing six strands ( Figure 5(C) ). The genome of 2019-nCoV has overall 89% nucleotide identity with bat SARS-related-CoV SL-CoVZXC21 (MG772934.1), and 82% with human SARS-CoV BJ01 2003 (AY278488) and human SARS-CoV Tor2 (AY274119). The phylogenetic trees constructed using the amino acid sequences of orf1a/b and the 4 structural genes (S, E, M, and N) were shown (Figure 6(A-E) ). For all these 5 genes, the 2019-nCoV was clustered with lineage B βCoVs. It was most closely related to the bat SARS-related CoVs ZXC21 and ZC45 found in Chinese horseshoe \n\nAs shown in Figure 7 (A-C), the SARS-CoV 5 ′ -UTR contains SL1, SL2, SL3, SL4, S5, SL5A, SL5B, SL5C, SL6, SL7, and SL8. The SL3 contains trans-cis motif [27] . The SL1, SL2, SL3, SL4, S5, SL5A, SL5B, and SL5C structures were similar among the 2019-nCoV, human SARS-CoV and the bat SARS-related ZC45. In the 2019-nCoV, part of the S5 found was inside Figure 7 Continued the orf1a/b (marked in red), which was similar to SARS-CoV. In bat SARS-related CoV ZC45, the S5 was not found inside orf1a/b. The 2019-nCoV had the same SL6, SL7, and SL8 as SARS-CoV, and an additional stem loop. Bat SARS-related CoV ZC45 did not have the SARS-COV SL6-like stem loop. Instead, it possessed two other stem loops in this region. All three strains had similar SL7 and SL8. The bat SARS-like CoV ZC45 also had an additional stem loop between SL7 and SL8. Overall, the 5 ′ -UTR of 2019-nCoV was more similar to that of SARS-CoV than the bat SARS-related CoV ZC 45. The biological relevance and effects of virulence of the 5 ′ -UTR structures should be investigated further. The 2019-nCoV had various 3 ′ -UTR structures, including BSL, S1, S2, S3, S4, L1, L2, L3, and HVR (Figure 7(D-F) ). The 3 ′ -UTR was conserved among 2019-nCoV, human SARS-CoV and SARS-related CoVs [27] . In summary, 2019-nCoV is a novel lineage B Betacoronavirus closely related to bat SARS-related coronaviruses. It also has unique genomic features which deserves further investigation to ascertain their roles in viral replication cycle and pathogenesis. More animal sampling to determine its natural animal reservoir and intermediate animal host in the market is important. This will shed light on the evolutionary history of this emerging coronavirus which has jumped into human after the other two zoonotic Betacoroanviruses, SARS-CoV and MERS-CoV.\n\nQuestion: What do the results indicate?", "role": "user" }, { "content": "that different orf3b proteins display different IFN antagonist activities and this function is independent of the protein's nuclear localization, suggesting a potential link between bat SARS-related-CoV orf3b function and pathogenesis.", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nMachine learning (ML) models trained by differentially private stochastic gradient descent (DP-SGD) have much lower utility than the non-private ones.\nTo mitigate this degradation, we propose a DP Laplacian smoothing SGD (DP-LSSGD) to train ML models with differential privacy (DP) guarantees.\nAt the core of DP-LSSGD is the Laplacian smoothing, which smooths out the Gaussian noise used in the Gaussian mechanism.\nUnder the same amount of noise used in the Gaussian mechanism, DP-LSSGD attains the same DP guarantee, but a better utility especially for the scenarios with strong DP guarantees.\nIn practice, DP-LSSGD makes training both convex and nonconvex ML models more stable and enables the trained models to generalize better.\nThe proposed algorithm is simple to implement and the extra computational complexity and memory overhead compared with DP-SGD are negligible.\nDP-LSSGD is applicable to train a large variety of ML models, including DNNs.\nMany released machine learning (ML) models are trained on sensitive data that are often crowdsourced or contain private information (Yuen et al., 2011; Feng et al., 2017; Liu et al., 2017) .\nWith overparameterization, deep neural nets (DNNs) can memorize the private training data, and it is possible to recover them and break the privacy by attacking the released models (Shokri et al., 2017) .\nFor example, Fredrikson et al. demonstrated that a model-inversion attack can recover training images from a facial recognition system (Fredrikson et al., 2015) .\nProtecting the private data is one of the most critical tasks in ML.\nDifferential privacy (DP) (Dwork et al., 2006 ) is a theoretically rigorous tool for designing algorithms on aggregated databases with a privacy guarantee.\nThe idea is to add a certain amount of noise to randomize the output of a given algorithm such that the attackers cannot distinguish outputs of any two adjacent input datasets that differ in only one entry.\nFor repeated applications of additive noise based mechanisms, many tools have been invented to analyze the DP guarantee for the model obtained at the final stage.\nThese include the basic and strong composition theorems and their refinements (Dwork et al., 2006; 2010; Kairouz et al., 2015) , the moments accountant (Abadi et al., 2016) , etc.\nBeyond the original notion of DP, there are also many other ways to define the privacy, e.g., local DP (Duchi et al., 2014) , concentrated/zeroconcentrated DP (Dwork & Rothblum, 2016; Bun & Steinke, 2016) , and Rényi-DP (RDP) (Mironov, 2017) .\nDifferentially private stochastic gradient descent (DP-SGD) reduces the utility of the trained models severely compared with SGD.\nAs shown in Figure 1 , the training and validation losses of the logistic regression on the MNIST dataset increase rapidly when the DP guarantee becomes stronger.\nThe convolutional neural net (CNN) 1 trained by DP-SGD has much lower testing accuracy than the non-private one on the MNIST.\nWe will discuss the detailed experimental settings in Section 4.\nA natural question raised from such performance degradations is:\nCan we improve DP-SGD, with negligible extra computational complexity and memory cost, such that it can be used to train general ML models with improved utility?\nWe answer the above question affirmatively by proposing differentially private Laplacian smoothing SGD (DP-LSSGD) to improve the utility in privacy-preserving empirical risk minimization (ERM).\nDP-LSSGD leverages the Laplacian smoothing (Osher et al., 2018) as a post-processing to smooth the injected Gaussian noise in the differentially private SGD (DP-SGD) to improve the convergence of DP-SGD in training ML models with DP guarantee.\nIn this paper, we integrated Laplacian smoothing with DP-SGD for privacy-presrving ERM.\nThe resulting algorithm is simple to implement and the extra computational cost compared with the DP-SGD is almost negligible.\nWe show that DP-LSSGD can improve the utility of the trained private ML models both numerically and theoretically.\nIt is straightforward to combine LS with other variance reduction technique, e.g., SVRG (Johoson & Zhang, 2013) .", "role": "user" }, { "content": "We propose a differentially private Laplacian smoothing stochastic gradient descent to train machine learning models with better utility and maintain differential privacy guarantees.", "role": "assistant" } ]

[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nTreatment of post-transplant premalignant skin disease: a randomized intrapatient comparative study of 5-fluorouracil cream and topical photodynamic therapy.\nAbstract 1:\nOrgan transplant recipients (OTR) are at high risk of developing nonmelanoma skin cancer and premalignant epidermal dysplasia (carcinoma in situ/ Bowen's disease and actinic keratoses). Epidermal dysplasia is often widespread and there are few comparative studies of available treatments.\n To compare topical methylaminolaevulinate (MAL) photodynamic therapy (PDT) with topical 5% fluorouracil (5-FU) cream in the treatment of post-transplant epidermal dysplasia.\n Eight OTRs with epidermal dysplasia were recruited to an open-label, single-centre, randomized, intrapatient comparative study. Treatment with two cycles of topical MAL PDT 1 week apart was randomly assigned to one area of epidermal dysplasia, and 5-FU cream was applied twice daily for 3 weeks to a clinically and histologically comparable area. Patients were reviewed at 1, 3 and 6 months after treatment. The main outcome measures were complete resolution rate (CRR), overall reduction in lesional area, treatment-associated pain and erythema, cosmetic outcome and global patient preference.\n At all time points evaluated after completion of treatment, PDT was more effective than 5-FU in achieving complete resolution: eight of nine lesional areas cleared with PDT (CRR 89%, 95% CI: 0.52-0.99), compared with one of nine lesional areas treated with 5-FU (CRR 11%, 95% CI: 0.003-0.48) (P = 0.02). The mean lesional area reduction was also proportionately greater with PDT than with 5-FU (100% vs. 79% respectively). Cosmetic outcome and patient preference were also superior in the PDT-treated group.\n Compared with topical 5-FU, MAL PDT was a more effective and cosmetically acceptable treatment for epidermal dysplasia in OTRs and was preferred by patients. Further studies are now required to confirm these results and to examine the effect of treating epidermal dysplasia with PDT on subsequent development of squamous cell carcinoma in this high risk population.\n\n\nTitle 2:\nFractionated illumination improves the outcome in the treatment of precancerous lesions with photodynamic therapy.\nAbstract 2:\nPhotodynamic therapy (PDT) is a noninvasive therapy for non-melanoma skin cancer. The aim of this study was comparison of efficacy between fractioned versus single dose illumination in photodynamic therapy (PDT) of actinic keratosis (AK) and Bowen's disease (BD). Fifty-one patients (36 AK and 15 BD) were treated with PDT They were randomly arranged in two treatment groups. Group one included 26 patients (20 AK and 6 BD) that, after five hours of incubation with 20% 5-ALA, were treated with a single illumination of 100 Jcm(-2) at fluence rate of 30 mWcm(-2). Group two included 25 patients (16 AK and 9 BD) that, after 16 hours of incubation with 20% 5-ALA, were treated with two light fractions (50 plus 50 Jcm(-2)) at same fluence rate with dark interval of two hours between fractions. Twenty-four weeks later, a treated area was incubated for four hours again with 5-ALA in order to detect occult areas of abnormal skin with possible remaining tumor tissue. In case of fluorescence, histological examination was performed. In the group one, fluorescence at the end of the session was absent in 19 (73%) or very weak in 7 (27%). Residual tumor was found in 15 (75%) AK and in 4 (66.6%) BD. In the group two, fluorescence at the end of second session was more intense; in one patient (4%) was absent, very weak in 5 (20%) and weak in 19 (76%) of patients. In this group histology revealed remaining tumor tissue in only 2 (12.5%) AK and 2 (22.2%) BD. Among the patients in the first group, the remaining tumor tissue was significantly bigger (p=0.005). The treatment response with clearing of tumor tissue was significantly higher in fractionated illumination than in a single dose illumination group. Fractionated illumination scheme with 16 hours of incubation separated by two hours dark interval significantly improves the therapeutic outcome in tumor eradication.\n\n\nTitle 3:\nResponse of Bowen disease to ALA-PDT using a single and a 2-fold illumination scheme.\nAbstract 3:\nnan\n\n\nTitle 4:\nComparison of topical methyl aminolevulinate photodynamic therapy with cryotherapy or Fluorouracil for treatment of squamous cell carcinoma in situ: Results of a multicenter randomized trial.\nAbstract 4:\nTo compare the efficacy, tolerability, and cosmetic outcome of photodynamic therapy (PDT) using topical methyl aminolevulinate with cryotherapy or topical fluorouracil for treatment of squamous cell carcinoma in situ.\n Randomized, placebo-controlled study, with follow-up at 3 and 12 months after last treatment.\n Forty outpatient dermatology centers in 11 European countries.\n Random sample of 225 patients with histologically confirmed squamous cell carcinoma in situ (lesion size, 6-40 mm) and no evidence of progression.\n Treatment with PDT with methyl aminolevulinate (160 mg/g; n = 96) or matching placebo cream (n = 17), cryotherapy (n = 82), or topical fluorouracil (5% cream; n = 30). Methyl aminolevulinate or placebo cream was applied for 3 hours before illumination with broadband red light (75 J/cm2, 570-670 nm). Treatment was repeated 1 week later. Cryotherapy was performed with liquid nitrogen spray. Fluorouracil was applied for 4 weeks. Lesions with a partial response at 3 months were re-treated.\n Clinically verified complete response of lesions; blinded and on-site assessment of cosmetic outcome (4-point rating scale).\n At 12 months, the estimated sustained lesion complete response rate with methyl aminolevulinate PDT was superior to that with cryotherapy (80% vs 67%; odds ratio, 1.77; 95% confidence interval, 1.01-3.12; P = .047), and better than that with fluorouracil (80% vs 69%; odds ratio, 1.64; 95% confidence interval, 0.78-3.45; P = .19). Cosmetic outcome at 3 months was good or excellent in 94% of patients treated with methyl aminolevulinate PDT vs 66% with cryotherapy and 76% with fluorouracil, and was maintained at 12 months.\n Methyl aminolevulinate PDT is an effective treatment option for squamous cell carcinoma in situ, with excellent cosmesis.\n\n\nTitle 5:\nComparison of red and green light in the treatment of Bowen's disease by photodynamic therapy.\nAbstract 5:\nA variety of protocols exist for the treatment of Bowen's disease by photodynamic therapy (PDT) using topical 5-aminolaevulinic acid (5-ALA).\n To determine the optimal wavelength (red or green light) for this treatment.\n A randomized comparison study of ALA-PDT using red (630 +/- 15 nm) or green (540 +/- 15 nm) light in the treatment of Bowen's disease.\n The initial clearance rate for lesions treated by red light was 94% (30 of 32) in comparison with 72% (21 of 29) for those lesions receiving green light (P = 0.002). Over the following 12 months, there were two recurrences in the red light group and seven in the green light group reducing the clearance rates to 88% and 48%, respectively. The frequency and severity of pain experienced were similar between the two treatment groups. No hyperthermia, nor significant difference in lesional temperatures, was observed between the wavelengths studied.\n Green light is less effective than red light, at a theoretically equivalent dose, in the treatment of Bowen's disease by topical ALA-PDT.\n\n\nTitle 6:\nComparison of photodynamic therapy with cryotherapy in the treatment of Bowen's disease.\nAbstract 6:\nThe efficacy and suitability of photodynamic therapy (PDT) was compared with that of cryotherapy in the treatment of 40 lesions of Bowen's disease. Lesions were randomized to receive either cryotherapy with liquid nitrogen, or PDT using a portable desktop lamp incorporating a 300 W xenon short arc discharge source. A porphyrin precursor, 5-aminolaevulinic acid (5-ALA), was applied topically 4 h before irradiation in the PDT group. Each lesion received 125 J/cm2 at a fluence rate of 70 mW/cm2. All patients were reviewed at 2-monthly intervals and treatments repeated if required. Cryotherapy produced clearance in 10 of 20 lesions after one treatment, the remaining 10 lesions requiring two or three treatment applications. PDT resulted in clearance of 15 of 20 lesions after one treatment and of the remaining five lesions after a second treatment. The probability that a lesion cleared after one treatment was greater with PDT than cryotherapy (P < 0.01). Cryotherapy was associated with ulceration (five of 20), infection (two of 20) and recurrent disease (two of 20); no such complications occurred following PDT. PDT using a non-laser light source and topical 5-ALA appears to be at least as effective as cryotherapy in the treatment of Bowen's disease with fewer adverse effects.\n\n\nTitle 7:\nImiquimod 5% cream monotherapy for cutaneous squamous cell carcinoma in situ (Bowen's disease): a randomized, double-blind, placebo-controlled trial.\nAbstract 7:\nWe conducted a double-blind, placebo-controlled, randomized trial to evaluate the preliminary efficacy and safety of imiquimod 5% cream treatment for cutaneous squamous cell carcinoma (SCC) in situ.\n In all, 31 patients with biopsy-proven cutaneous SCC in situ were randomly assigned to placebo (vehicle) (n = 16) or imiquimod 5% cream (n = 15) daily for 16 weeks. Patients were assessed at week 28 for the primary end point, resolution of cutaneous SCC in situ.\n Of the 31 patients enrolled, 3 dropped out. Intention-to-treat analysis revealed 11 of the 15 patients (73%) in the imiquimod group achieved resolution of cutaneous SCC in situ, with no relapse during the 9-month follow-up period; none in the placebo group achieved resolution (P < .001). Imiquimod 5% cream was generally well tolerated and there were no serious adverse events.\n Topical imiquimod 5% cream has proven to be an effective treatment for cutaneous SCC in situ. However, studies to define the ideal dosing regimen and cost-effectiveness are required before it can be accepted as a recognized therapy.\n In this controlled trial, patients with cutaneous SCC in situ receiving topical imiquimod 5% cream as monotherapy experienced a high degree of clinical benefit compared with placebo.\n\n\nTitle 8:\nPhotodynamic therapy of multiple nonmelanoma skin cancers with verteporfin and red light-emitting diodes: two-year results evaluating tumor response and cosmetic outcomes.\nAbstract 8:\nEfficient treatment of patients with multiple synchronous nonmelanoma skin cancers represents a therapeutic challenge.\n To study the safety and efficacy of photodynamic therapy (PDT) with verteporfin and red light in the treatment of multiple nonmelanoma skin cancers.\n Open-label, randomized, multicenter, dose-ranging phase 2 study conducted at 4 North American university-based dermatology clinics.\n Fifty-four patients with 421 multiple nonmelanoma skin cancers including superficial and nodular basal cell carcinoma and squamous cell carcinoma in situ (Bowen disease).\n A single intravenous infusion of 14 mg/m(2) of verteporfin followed 1 to 3 hours later by exposure of tumors to 60, 120, or 180 J/cm(2) of red light (688 +/- 10 nm) from a light-emitting diode panel.\n Pathologic response of treated sites was assessed at 6 months. Clinical and cosmetic responses were assessed and graded at 6 weeks, 3 months, and 6 months after verteporfin PDT, with optional follow-up visits at 12, 18, and 24 months.\n The histopathologic response, defined as absence of tumor on biopsy specimens 6 months after verteporfin PDT, ranged from 69% at 60 J/cm(2) to 93% at 180 J/cm(2). At 24 months of follow-up (276 tumors in 31 patients), the clinical complete response rate ranged from 51% at 60 J/cm(2) to 95% at 180 J/cm(2). No significant systemic adverse events were observed; most events occurred at the treated tumor sites and included events such as pain. Overall, 65% (95% confidence interval, 58%-71%) of tumors were judged to have good to excellent cosmesis at 24 months.\n A single course of verteporfin PDT showed treatment benefit for patients with multiple nonmelanoma skin cancers.", "role": "user" }, { "content": "Overall, there has been very little good-quality research on treatments for Bowen's disease. There is limited evidence from single studies to suggest MAL-PDT is an effective treatment. Although cosmetic outcomes appear favourable with PDT, five-year follow-up data are needed. Significantly more lesions cleared with MAL-PDT compared to cryotherapy. No significant difference in clearance was seen when MAL-PDT was compared with 5-FU, but one study found a significant difference in clearance in favour of ALA-PDT when compared to 5-FU. There was no significant difference in clearance when cryotherapy was compared to 5-FU.\nThe lack of quality data for surgery and topical cream therapies has limited the scope of this review to one largely about PDT studies. The age group, number, and size of lesions and site(s) affected may all influence therapeutic choice; however, there was not enough evidence available to provide guidance on this. More studies are required in the immunosuppressed populations as different therapeutic options may be preferable. Specific recommendations cannot be made from the data in this review, so we cannot give firm conclusions about the comparative effectiveness of treatments.", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research paper, followed by a question about the paper. Please extract text from the paragraph to answer the question. Do not include any text in your response other than the answer.\n\nParagraph: As an RNA-binding protein that engages the hairpin termini of the genomic segments with high affinity [49, 50] , it limits the access of the RNA to host nucleases and helps to render viral replication a closed process within the cytoplasm . It also acts as a peripheral membrane protein, as does the L protein [51] , an activity that could play a role in its presumed, but not yet demonstrated function as matrix [52] . Until recently, it had not been appreciated that N has a wide variety of other activities, some of which can be linked, not only to fundamental requirements of replication, but also to the interference with an array of the intracellular processes of the normal cell. Thus, an interaction between the amino terminus of the hantavirus N protein and the cellular protein Daxx has been proposed, with the suggestion of potential pro-apoptotic consequences [51] . N is also reported to interact with actin microfilaments, and the SUMO-1 protein [53, 54] . Using reporter-gene based assays, Connie Schmaljohn and her colleagues have reported that Hantaan virus' nucleocapsid protein has an inhibitory role in inflammatory responses mediated by NF kappa B (NF-B). The effects on NF-B expression appeared to be confined to prevention of its nuclear translocation after its attempted activation with lipopolysaccharide, LPS [55] . In the cytoplasm of infected cells, N protein can be found in cellular P bodies where it sequesters and protects 5' caps. It may locate the caps through its interaction with DCP1, a key constituent of P bodies. During hantavirus infection, the viral RNAs become concentrated in P bodies, through their interaction with N and DCP1. The N protein demonstrates preferential protection of mRNAs engineered to prematurely terminate their encoded protein in comparison to native mRNAs [56] . N protein has been increasingly linked to viral replication and translation, sometimes in previously unanticipated ways. It is among a growing family of diverse viral proteins that can serve as a nonspecific -RNA chaperone‖, an activity that should facilitate the L polymerase's access to vRNA for transcription and replication, in that it can transiently dissociate misfolded RNA structures [57] . Some of N protein's effects on translation might not immediately be recognized to be adaptive in nature. It can replace the entire EIF4F translational initiation complex, simultaneously presenting the ribosome with a replacement for the cap-binding activity of eIF 4E, binding to the 43S pre-initiation complex as does eIF 4G, while replacing the helicase activity of eIF 4A, which is presumed to be needed to dissociate higher-order RNA structure [56, 58] . These three factors normally work together to achieve translational initiation. In P bodies, N protein's ability to bind at high affinity to capped native cellular oligoribonucleotides, along with its activity in protecting capped RNAs from degradation likely facilitates the access of capped oligonucleotides for use in transcriptional initiation by L polymerase (-cap snatching‖). Trafficking of N for viral assembly: Classically, N protein in infected cells appears to be clustered or particulate in nature, with a heavy concentration at a single perinuclear location, widely considered to be the Golgi [27] . The N proteins of hantaviruses are found in association with particulate fractions, and confocal microscopy and biochemical-inhibitor studies have shown that N tracks along microtubules but not with actin filaments [52] . The ultimate destination for N, for its assembly into viral particles is the Golgi, and it traffics there via the endoplasmic reticulum-Golgi intermediate complex (ERGIC), also known as vesicular-tubular cluster [52] . A dominant negative inhibitor, dynamitin, associated with dynein-mediated transport, reduced N's accumulation in the Golgi. Later studies suggested that the specific dependence on microtubular transport is specific to Old World hantaviruses such as HTNV, but that the New World hantavirus ANDV is instead associated with actin filaments [59] . However, recent data indicates that microtubular transport is indeed utilized for the New World hantavirus SNV [60] . Hantavirus diseases of man have long been suspected of having an immunopathogenic basis in part because of their relatively long incubation period of 2-3 weeks and the observed temporal association between immunologic derangements and the first appearance of signs and symptoms of hantavirus illness. HFRS and HCPS share many clinical features, leading many investigators to consider them to be, in essence, different manifestations of a similar pathogenic process, differing mainly in the primary target organs of disease expression ( Table 2 ). The pathogenesis of hantavirus infections is the topic of a continuously-updated review in the series UpToDate [61] . By the time symptoms appear in HCPS, both strong antiviral responses, and, for the more virulent viral genotypes, viral RNA can be detected in blood plasma or nucleated blood cells respectively [63, 64] . At least three studies have correlated plasma viral RNA with disease severity for HCPS and HFRS, suggesting that the replication of the virus plays an ongoing and real-time role in viral pathogenesis [65] [66] [67] . Several hallmark pathologic changes have been identified that occur in both HFRS and HCPS. A critical feature of both is a transient (~ 1-5 days) capillary leak involving the kidney and retroperitoneal space in HFRS and the lungs in HCPS. The resulting leakage is exudative in character, with chemical composition high in protein and resembling plasma. The continued experience indicating the strong tissue tropism for endothelial cells, specifically, is among the several factors that make β3 integrin an especially attractive candidate as an important in vivo receptor for hantaviruses. It is likely that hantaviruses arrive at their target tissues through uptake by regional lymph nodes, perhaps with or within an escorting lung histiocyte. The virus seeds local endothelium, where the first few infected cells give rise, ultimately, to a primary viremia, a process that appears to take a long time for hantavirus infections [62, 63] . By the time that secondary viremia emerges, the agents of the more severe forms of HFRS and HCPS have begun to achieve sufficient mass as to induce, through PAMP-PRR interactions and other means, the expression of proinflammatory cytokines [64] . For HCPS, that expression favors the pulmonary bed and lymphoid organs, yet, for unknown reasons, spares the retroperitoneum and, in general, the kidney. In HFRS the situation is reversed, and yet it is often not appreciated that the expected preferential tissue tropism of HFRS-associated viruses and their HCPS-associated counterparts for the renal and pulmonary beds, respectively, is not as one would predict through the manifestations of the two diseases. Local elaboration of inflammatory and chemotactic mediators is considered to be a requirement for the development of systemic disease symptoms, with those abnormalities sometimes culminating in shock and death. Yet it is not hypoxemia, due to the prominent pulmonary edema, that leads to death in most fatal cases of HCPS, but rather intoxication of the heart by as-yet-undefined mediators that leads to the low cardiac output state and the associated shock syndrome [64, 65] . It is tempting to speculate that mediators produced in the lung in connection with the inflammatory infiltrate can percolate through the coronary circulation with minimal dilution in HCPS, a disadvantageous consequence of the close anatomic juxtaposition of the two organs. Thus, at least three classes of potential mechanisms, some overlapping and all certainly nonexclusive of the others, could be presumed to underlie the pathogenesis of HCPS. These include:\n\n(1) Innate immune mechanisms. The nature of interactions between hantavirus pathogen-associated molecular patterns (PAMP) with the pattern recognition receptors (PRR) of susceptible endothelial cells are beginning to be clarified. The prototypical HTNV appears to be recognized by TLR-3 [43] . Such an infection has consequences such as increased expression of HLA-DR in dendritic cells [66] and differentiation of monocytes toward dendritic cells [67] . (2) Direct viral effects. The observed correlation between viral load and disease severity leaves the possibility open that hantavirus particles or RNA can themselves have toxic effects on cells or on signaling. Some investigators have favored direct viral toxicity, acting through the inhibition of endothelial cell barrier function, as an explanation for much of the capillary leak, although there is widespread agreement that multiple mechanisms that mediate pathogenesis likely operate simultaneously in the affected patient [68] . A potentially important clue toward the mechanism by which hantavirus infections deplete blood platelets and, in some cases cause hemorrhagic manifestations, was advanced by the recent discovery that pathogenic hantaviruses are able to recruit platelets to adhere to endothelial cell surfaces, with β3 integrin used as a critical binding element [69] . (3) Pathogenic effects caused by the activities of specific viral macromolecules. We have reviewed some of the activities associated with the Gn, Gc and N, virally-encoded polypeptides in previous sections. Testing models of pathogenesis can be done more effectively when there is an animal model that mimics key aspects of the disease. There is no such model that closely mimics HFRS, but animal models exist for both the asymptomatic carriage of PUUV and SNV by their native carrier rodents, the bank vole Myodes glareolus and the deer mouse P. maniculatus; as well as a Syrian hamster model using ANDV or the related Maporal virus from Venezuela, for which an HCPS-mimetic disease is observed [70] [71] [72] [73] . The ANDV-Syrian hamster model has a number of features in common with the human disease, as well as some differences. Unlike the neurologic diseases that have been possible to elicit with HTNV, the hamster model for HCPS appears to be caused by capillary leak that results in pulmonary edema and the production of a pleural effusion with exudative characteristics. Typically the hamsters die between 11 and 14-d post-inoculation, reflecting a slightly accelerated incubation period in comparison to human infections. As with human HCPS, the microscopic examination of the lung reveals abundant fibrin deposition, thickened alveolar septa, and viral antigen expressed abundantly in the microvascular endothelium. ANDV-infected hamsters fitted with physiologic monitoring devices exhibited diminished pulse pressures, tachycardia, and hypotension that appear to closely mimic the shock that is believed to be the proximate cause of demise in patients who succumb to HCPS [65, 74] . Compared to the human disease, ANDV-infected hamsters exhibit exceptionally high titers of live ANDV in their tissues, with much of the viral replication occurring in hepatocytes, which are spared in the human disease. Titers of live ANDV in some cases exceed 10 8 /g, whereas hantavirus isolates from human tissues have been notoriously difficult to obtain. Despite the universal occurrence of mildly-elevated hepatic enzymes in patients with HCPS, hepatic enzymes do not appear to be present at elevated levels in the blood of diseased hamsters even immediately before death [75] . The protracted incubation period associated with hantavirus disease gives the host considerable time to mount a mature immune response against the virus. Thus, in contradistinction to infections of comparable severity and related symptomatology associated with arenaviruses and filoviruses, hantavirus infections of humans are associated with antibody responses of significant titer by the time symptoms commence. Despite this observation, it appears to be possible that natural variation in individual neutralizing antibody responses among patients with SNV infections can be linked to disease severity, suggesting that administration of antiviral antibodies could prove effective therapeutically [76] . In the case of ANDV infection, new evidence has emerged indicating that the apparent clearance of the virus from the blood does not result in the complete removal of antigenic stimulus by the virus, suggesting that the virus may persist, perhaps in some as-yet undetermined immunologically privileged site [77] . A role for T cell-mediated pathological responses in HFRS and HCPS has been the source of speculation for a variety of reasons. The severity of SNV-associated HCPS may have made it more apparent that the onset of pulmonary edema, tachycardia and hypertension seemed to be all but universally temporally associated with the appearance of a spectrum of highly-activated cells of the lymphoid lineage in the peripheral blood. Cells with a close morphologic similarity to these -immunoblasts‖ were detected in the congested, heavy lungs of patients who came to autopsy, as well as in lymphoid organs and in the portal triads [63, [78] [79] [80] . These observations led to speculation that some component of hantavirus pathogenesis could be linked to the appearance of antiviral T cells that could stimulate or contribute to the appearance of a -storm‖ of mediators and the associated capillary leak phenotype. Subsequent studies have borne out the expectation that a significant fraction of the immunoblast population in patients with HCPS are T cells with specificity for specific class I HLA-presented epitopes of viral antigens, including Gn, Gc and N [77, [81] [82] [83] . Presumably, the antiviral activities of such cells, manifested in part through their elaboration of mediators in the affected interstitium, can contribute to the endothelial/capillary leak that lies at the heart of hantavirus pathogenesis. Because early cases of HCPS often came to autopsy, it became possible to examine necropsied tissues for expression of cytokines. The study by Mori et al. (1999) revealed high relative expression of proinflammatory cytokines including TNF, IL-1, IL-6, providing evidence in favor of a -cytokine storm‖ model for pathogenesis [64] . The authors believed, based on the morphology of cytokine-secreting cells, that both monocytes and lymphocytes were contributing to the production of cytokines. That proinflammatory mediators are found in elevated levels in the plasma as well as the renal interstitium of patients with acute hantaviral illness has been recognized for some time as well [84, 85] . While diagnosis of HCPS as well as HFRS is best accomplished with IgM serology, in the acute stage of SNV infection, RT-PCR can also be used if blood cells or blood clot are used instead of plasma or serum, where sensitivity even using nested PCR primers drops to about 70% [86] [87] [88] . In a facility at which many cases of HCPS are treated, the University of New Mexico medical center in Albuquerque, a diagnostic service has long been offered in which the patient's hematologic findings are analyzed to establish the probability that a patient has HCPS.\n\nQuestion: As an RNA-binding protein that engages the hairpin termini of the genomic segments, what does the N-protein of hantavirus do?", "role": "user" }, { "content": "helps to render viral replication a closed process within the cytoplasm", "role": "assistant" } ]

[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is the abnormal dosage of ultraconserved elements disfavored in cancer cells?\n\nContext: Abnormal dosage of ultraconserved elements is highly disfavored in healthy cells but not cancer cells.\nWe begin by showing that depletion for UCEs characterizes the most recent large-scale human CNV datasets and then find that even newly formed de novo CNVs, which have passed through meiosis at most once, are significantly depleted for UCEs. In striking contrast, CNVs arising specifically in cancer cells are, as a rule, not depleted for UCEs and can even become significantly enriched. This observation raises the possibility that CNVs that arise somatically and are relatively newly formed are less likely to have established a CNV profile that is depleted for UCEs. Alternatively, lack of depletion for UCEs from cancer CNVs may reflect the diseased state. In support of this latter explanation, somatic CNVs that are not associated with disease are depleted for UCEs. Finally, we show that it is possible to observe the CNVs of induced pluripotent stem (iPS) cells become depleted of UCEs over time, suggesting that depletion may be established through selection against UCE-disrupting CNVs without the requirement for meiotic divisions.\nAlternatively, lack of depletion for UCEs from cancer CNVs may reflect the diseased state.", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\n1. History of colorectal surgery \n2. Suspected or known digestive tract obstruction, stricture, or perforation \n3. Serious status of illness, such as severe renal failure whose creatinine clearance<30 ml/min, New York Heart Association grade III or grade IV congestive heart failure, or hemodynamic instability, etc. \n4. Incapable of completing bowel preparation，such as dysphagia, allergy to purgatives, or impaired mental status, etc. \n5. Pregnancy or breastfeeding \n6. Incomplete colonoscopy due to causes except poor bowel preparation \n7. Unable to give informed consent \n8. Have participated in the study before.", "role": "user" }, { "content": "{\"Condition\": [\"hemodynamic instability\", \"renal failure\", \"allergy\", \"impaired mental status\", \"poor bowel preparation\", \"digestive tract obstruction\", \"digestive tract stricture\", \"Incapable of completing bowel preparation\", \"Serious status of illness\", \"Pregnancy\", \"congestive heart failure\", \"digestive tract perforation\", \"dysphagia\"], \"Device\": [], \"Drug\": [\"purgatives\"], \"Measurement\": [\"New York Heart Association\", \"creatinine clearance\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [\"except\"], \"Observation\": [\"History\", \"informed consent\", \"breastfeeding\"], \"Person\": [], \"Procedure\": [\"colonoscopy\", \"colorectal surgery\"], \"Qualifier\": [\"Incomplete\", \"severe\"], \"ReferencePoint\": [], \"Scope\": [\"severe renal failure whose creatinine clearance\\u003c30 ml/min, New York Heart Association grade III or grade IV congestive heart failure, or hemodynamic instability\", \"dysphagia, allergy to purgatives, or impaired mental status\"], \"Temporal\": [], \"Value\": [\"grade III or grade IV\", \"\\u003c30 ml/min\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nIn this paper, we propose data statements as a design solution and professional practice for natural language processing technologists, in both research and development — through the adoption and widespread use of data statements, the field can begin to address critical scientific and ethical issues that result from the use of data from certain populations in the development of technology for other populations.\nWe present a form that data statements can take and explore the implications of adopting them as part of regular practice.\nWe argue that data statements will help alleviate issues related to exclusion and bias in language technology; lead to better precision in claims about how NLP research can generalize and thus better engineering results; protect companies from public embarrassment; and ultimately lead to language technology that meets its users in their own preferred linguistic style and furthermore does not mis- represent them to others.\n\n\n** To appear in TACL **\nAs technology enters widespread societal use it is important that we, as technologists, think critically about how the design decisions we make and systems we build impact people -including not only users of the systems but also other people who will be affected by the systems without directly interacting with them.\nFor this paper, we focus on natural language processing (NLP) technology.\nPotential adverse impacts include NLP systems that fail to work for specific subpopulations (e.g. children or speakers of language varieties which are not supported by training or test data) or systems that reify and reinforce biases present in training data (e.g. a resume-review system that ranks female candidates as less qualified for computer programming jobs because of biases present in training text).\nThere are both scientific and ethical reasons to be concerned.\nScientifically, there is the issue of generalizability of results; ethically, the potential for significant real-world harms.\nWhile there is increasing interest in ethics in NLP, 1 there remains the open and urgent question of how we integrate ethical considerations into the everyday practice of our field.\nThis question has no simple answer, but rather will require a constellation of multi-faceted solutions.Toward that end, and drawing on value sensitive design BID22 , this paper contributes one new professional practicecalled data statements -which we argue will bring about improvements in engineering and scientific outcomes while also enabling more ethically responsive NLP technology.\nA data statement is a characterization of a dataset which provides context to allow developers and users to better understand how experimental results might generalize, how software might be appropriately deployed, and what biases might be reflected in systems built on the software.\nIn developing this practice, we draw on analogous practices from the fields of psychology and medicine that require some standardized information about the populations studied (e.g. APA 2009; BID41 BID26 BID40 .\nThough the construct of data statements applies more broadly, in this paper we focus specifically on data statements for NLP systems.\nData statements should be included in most writing on NLP including: papers presenting new datasets, papers reporting experimental work with datasets, and documentation for NLP systems.\nData statements should help us as a field engage with the ethical issues of exclusion, overgeneralization, and underexposure BID30 .\nFurthermore, as data statements bring our datasets and their represented populations into better focus, they should also help us as a field deal with scientific issues of generalizability and reproducibility.\nAdopting this practice will position us to better understand and describe our results and, ultimately, do better and more ethical science and engineering.\n2 We begin by defining terms ( §2), discuss why NLP needs data statements ( §3) and relate our proposal to current practice ( §4).\nNext is the substance of our contribution: a detailed proposal for data statements for NLP ( §5), illustrated with two case studies ( §6).\nIn §7 we discuss how data statements can mitigate bias and use the technique of 'value scenarios' to envision potential effects of their adoption.\nFinally, we relate data statements to similar emerging proposals ( §8), make recommendations for how to implement and promote the uptake of data statements ( §9), and lay out considerations for tech policy ( §10).\nAs researchers and developers working on technology in widespread use, capable of impacting people beyond its direct users, we have an obligation to consider the ethical implications of our work.\nThis will only happen reliably if we find ways to integrate such thought into our regular practice.\nIn this paper, we have put forward one specific, concrete proposal which we believe will help with issues related to exclusion and bias in language technology: the practice of including 'data statements' in all publications and documentation for all NLP systems.We believe this practice will have beneficial effects immediately and into the future: In the short term, it will foreground how our data does and doesn't represent the world (and the people our systems will impact).\nIn the long term, it should enable research that specifically addresses issues of bias and exclusion, promote the development of more representative datasets, and make it easier and more normative for researchers to take stakeholder values into consideration as they work.\nIn foregrounding the information about the data we work with, we can work toward making sure that the systems we build work for diverse populations and also toward making sure we are not teaching computers about the world based on the world views of a limited subset of people.Granted, it will take time and experience to develop the skill of writing carefully crafted data statements.\nHowever, we see great potential benefits: For the scientific community, researchers will be better able to make precise claims about how results should generalize and perform more targeted experiments around reproducing results for datasets that differ in specific characteristics.\nFor industry, we believe that incorporating data statements will encourage the kind of conscientious software development that protects companies' reputations (by avoiding public embarrassment) and makes them more competitive (by creating systems used more fluidly by more people).\nFor the public at large, data statements are one piece of a larger collection of practices that will enable the development of NLP systems that equitably serves the interests of users and indirect stakeholders.", "role": "user" }, { "content": "A practical proposal for more ethical and responsive NLP technology, operationalizing transparency of test and training data", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nspiral waves are characteristic structures of excitable media that have been observed in many extended systems such as reaction - diffusion media @xcite , aggregating colonies of slime mold @xcite , and heart tissues @xcite , where they are suspected to play an essential role in cardiac arrhythmia and fibrillation .\nsudden cardiac death resulting from ventricular fibrillation is generated from the fragmenting or breakup of spiral waves @xcite .\nspiral waves are prone to a variety of instabilities @xcite , one of which is meander instability @xcite , where spiral tips follow a hypocycloid trajectory instead of moving around a small circle . due to doppler effect , this spiral may undergo a transition from ordered spiral patterns to a state of defect - mediated turbulence @xcite . in the meandering regime\n, the spiral tips can be made to drift and controlled by external influences @xcite or localized inhomogeneities of defects @xcite .\nafter the concept of small - world connections was proposed by watts and strogatz @xcite , it has quickly attracted much attention because this kind of connections exists commonly in real world , such as in social systems @xcite , neural networks @xcite and epidemic problems @xcite .\ndifferent studies show that a little change of the network connections can essentially change the features of a given medium , and plays a very important role in determining the dynamic behavior of a system . in numerical simulations ,\na spatially extended system can be approximately regarded as a network consisting of a number of sites connected with certain topology . in this way\nlocalized inhomogeneities can be achieved by changing the topology of the network . in heart tissues ,\npacemakers dominate the dynamics of the travelling wave behavior and control the heart rhythm .\nwe hypothesize that this happens because the characters and the structures of the local cells are different from other cardiac muscle cells .\ncould a small - world network describe one of the characters of the pacemaker ? to answer this question , we changed the widely used regular network in spiral wave study to a small - world network in part of the system to investigate its effects . in the next section , we study the effect of a local small - world network on the behavior of spiral waves .\nwe show that this special region is a dynamic attractor for spiral tips . in section iii\n, we compare the effect of the small - world network with that of changing diffusion coefficient in the local region , and show that they are equivalent .\nwe give a discussion and conclude our study in the last section .\nthe model we used is the two - variable fitzhugh - nagumo model @xcite with local nearest - neighbor couplings in a region of @xmath0 : @xmath1 where @xmath2 , @xmath3 ; @xmath4 and @xmath5 is dimensionless excitable variable and recovery variable respectively ; @xmath6 and @xmath7 are diffusion coefficients of the two variables .\nthe laplacien in the last term can be approximated as : @xmath8 when @xmath9 , @xmath10 , @xmath11 , @xmath12 , the equation describes an excitable medium , which can be regarded as a simplified model for cardiac tissues . in the following discussion , we set the control parameters as follows : @xmath13 , @xmath14 , @xmath15 , @xmath16 , @xmath17 , @xmath18\n. no - flux boundary condition is applied in the simulation . using vertical gradient distribution initial condition\n, we first create spiral waves in regular lattices ( fig .\n1(a ) ) . in this case\n, the spiral tip follows a hypocycloid trajectory , showing a typical sign of meandering state @xcite , see fig .\nwe then create a small - world network in a small local region @xmath19 of a size @xmath20 , where the tip of spiral waves locates .\nthe small - world network is created in the following way : with the probability @xmath21 , we reconnect every edge in the region @xmath19 from one of its original vertex to another vertex chosen randomly in the region @xcite(see fig .\nthe change of connections leads to the change of `` diffusion '' mode .\nsupposing node[i][j ] is connected with node[@xmath22[@xmath23 , node[@xmath24[@xmath25 , node [ @xmath26[@xmath27 , then the `` diffusion '' term in the eqs ( 1 ) ( 2 ) becomes : @xmath28 ; ( b ) a small - world network , @xmath29 ; ( c ) spiral wave and its tip s motion in the regular network .\nthe white curve is the trajectory of the spiral tip ; ( d ) spiral wave and its tip s motion in the small - world network .\n@xmath30.,width=302 ] introducing the small - world network region in the reaction medium greatly influences the motion of the spiral tip .\nwe find that the small - world network region can attract the spiral tip as it passes through the region .\nafter that , the spiral tip rotates around its boundary , as shown in fig .\nbecause the topological structure of the local small - world network is generated randomly under the above mentioned rule , the attraction only occurs under a certain parameter range with certain probability . to characterize the attraction property of the small - world network\n, we use the attraction probability @xmath31 as an order parameter , which can be obtained by repeating ( 50 times in our work ) the simulation using the same control parameters but with different small - world network connections .\nour simulation results show that the most influential factor to @xmath31 is the small - world creation probability @xmath32 .\nas show in fig .\n2(a ) , @xmath31 increases with the increase of the small - world @xmath32 . when @xmath33 ( corresponding to a regular network ) , the spiral tip can not be attracted ; when @xmath34 ( corresponding to a random network ) , the tip can be attracted with probability 1 . between @xmath35 ,\nthere is a transition where the attraction probability @xmath31 increases rapidly .\nthe transition point @xmath36 can be defined as the value of @xmath37 when @xmath38 . as a function of @xmath32 with different @xmath39 .\nthe line is the sigmoidal fitting @xmath40 ; ( b ) transition curves of @xmath31 as a function of @xmath41 with different @xmath39 .\nthe line is the fitting of @xmath42 here @xmath43 is the critical length where @xmath44 , and @xmath45 is the transition width.,width=226 ] one of the most important characters of small - world network is the reducing of average path length while keeping the clustering coefficient almost constant @xcite . define the normalized average path length @xmath41 of small - world network as @xmath46 , where @xmath47 is the average path length of small - world network in @xmath19 @xcite and @xmath48 is the average path length of regular network in @xmath19 .\n@xmath41 will decrease from @xmath49 to @xmath50 when @xmath32 changes from 0 to 1 . from numerical simulations\n, we find the same type of transition curve of @xmath51 as a function of @xmath41 , as shown in fig .\n2(b ) , indicating that the major effect of the small - world topology to the behavior of spiral waves is the decrease of average path length .\nin addition , defining the critical length @xmath52 as the value of @xmath41 when @xmath38 , we find that the critical length decreases linearly as the increase of the size of @xmath19 , see fig .\nour simulation results suggest that the major effect of the small - world network on spiral tip movement comes from the long distance connections , which lead to shortening the average path length ( @xmath41 ) and increasing the diffusion speed .\nif the above suggestion is correct , the phenomenon of spiral tip attraction should also occur when we locally increase the diffusion constant in eqs .\n( 1 ) and ( 2 ) .\nin this part of work , we increase the diffusion coefficient in a small circular region @xmath19 by @xmath53 times and keep the system with regular connections . in the following discussion\n, we will use @xmath54 to denote the diffusion coefficient in region @xmath55 , and use @xmath56 for the region outside of @xmath55 , so that @xmath57 .\nwe find that the spiral tip can be attracted and travel around the boundary of region @xmath55 when @xmath58 is large enough and @xmath59.(@xmath60 is the radius of @xmath19 , @xmath61 is the core radius of spiral when @xmath62 ) . at a given @xmath60\n, we can define two values @xmath63 and @xmath64 : a temporal attraction occurs when @xmath65 . in that case , the tip can be trapped for a short period and then escapes ; the `` trapped '' time increases with @xmath58 . when @xmath66 , the tip can be trapped for a long enough period .\ndefine @xmath67 as the mean value of @xmath63 and @xmath64 , the plot of @xmath67 with different @xmath60 is shown in the fig .\nthe above simulation results suggest that the increase of diffusion speed in the small region is responsible for the attraction of the spiral tip .\nto quantitatively compare the two systems , we analyze the diffusion terms of the two systems . in the small - world network , because of the long distance connections , the average distance between nodes declines as @xmath32 increases from @xmath68 to @xmath49 . in a network model of a reaction - diffusion system\n, this effect can be in a sense translated from the decrease of the average path length between nodes while keeping the distance of two neighboring nodes @xmath69 constant , to the decrease of the step length @xmath69 while keeping the network regular .\nthe normalized average path length @xmath41 can also describe the relative change of @xmath69 . from this argument\n, the diffusion items of the small - world network can be expressed as : @xmath70 at the critical point , for a fixed @xmath60 , the diffusion terms in two systems should be the same .\nso that @xmath71 , which gives @xmath72 . as presented in fig .\n3(b ) , our simulation fits this analysis within the range of error .\nthis result indicates that our proposition is reasonable .\nthe attracting effect of the small - world network comes from the decline of @xmath41 inside the inhomogeneous area @xmath19 . as a function of the region s radius @xmath60 , @xmath73\n, the error bar is @xmath45,(see the caption of fig .\n2(b ) about the fitting ) ; ( b ) @xmath74 as a function of @xmath60.,width=226 ]\na question should be answered before fully understanding the effect of the small - world network in the dynamics of spiral tips : what is the mechanism for the spiral tip attraction ? in the following discussion , we give an explanation with the eikonal equation , luther equation @xcite , and the relation between diffusion coefficient and of spiral core radius . according to the analysis of the spiral tip dynamics given by hakim and karma @xcite , for the steady rotational movement of a spiral tip in an excitable medium ,\nthe core radius @xmath60 as a function of diffusion coefficient can be written as : @xmath75 where @xmath76 is the diffusion coefficient of activator ( @xmath77 ) ; @xmath78 is the speed of plane wave ; @xmath79 , @xmath80 and @xmath81 are all constants .\n@xmath82 is the constant width of the excited region . in the simulation\n, we assume that at the boundary of @xmath55 exists a `` virtual '' gradient region of @xmath6 which links the outside and inside regions . for a given @xmath60 of the region @xmath83 ,\nthe `` trapped '' motion of the spiral tip requires a specific value of @xmath76 , satisfying equation ( [ eq : g1 ] ) .\nwhen @xmath84 , the spiral tip will enter the gradient region where the system can find the required @xmath76 , so that the spiral tip will rotate around the gradient area at the boundary of @xmath19 ; on the other hand , when @xmath85 , the `` trapped '' motion can not be sustained by the central region . from this argument , at critical point , we will have @xmath86 .\nas shown in fig .\n4 , our simulation results are consistent with this analysis with the range of error .\nto prove the `` trapped '' state of tip motion is a stable state , we apply the eikonal equation , which determines the relation between the curvature of a travelling wave front and its speed in an excitable medium , and the luther relation , which describes the relation between the speed of chemical waves and the diffusion coefficient of activator @xcite .\nthe eikonal equation is : @xmath87 , where @xmath88 is the normal wave speed , @xmath89 is the local curvature of the wave front ; the luther equation is : @xmath90 where @xmath91 is a constant .\ninsert the luther equation into eikonal relation we have : @xmath92 taking partial derivative of r in eq .\n( [ eq : h1 ] ) , we get : @xmath93\\cdot \\frac{\\partial d_{u}}{\\partial r } \\label{eq : h2}\\ ] ] at the spiral tip we have @xmath94 , so that : @xmath95 in our system , assuming there exists a continuous change of @xmath76 at the boundary of region @xmath96 , we have @xmath97 .\nthus the equation ( [ eq : h3 ] ) indicates that @xmath98 .\nthat means , if we introduce a small deviation from the `` trapped '' motion of the spiral tip , the system will return to the `` trapped '' state spontaneously , because we have @xmath99 inside the region @xmath55 , and @xmath100 outside the region @xmath55.(@xmath101 points to the center of @xmath96 region ) . in conclusion\n, we find that in an excitable system local change of topological structure can trap the spiral tip .\nthis ability comes from the increase of diffusion speed .\nwe prove this by increasing the diffusion coefficient .\nwe also give a theoretical explanation using the eikonal equation , luther equation , and the relation between core radius and diffusion coefficient , which fits well with the results of simulation .\nwe should note that there are other situations where the tip of spiral waves can be trapped in a given area .\nfor example , lzr _ et al .\n_ reported that self - sustained chemical waves can rotate around a central obstacle in an annular 2-d excitable system , and the wave fronts in the case of an annular excitable region are purely involutes of the central obstacle in the asymptotic state @xcite .\nobviously this phenomenon is beyond our analysis . so that more work should be done to fully understand the attract effect of local inhomogeneities in an excitable reaction - diffusion system .", "role": "user" }, { "content": "trapping and un - trapping of spiral tips in a two - dimensional homogeneous excitable medium with local small - world connections is studied by numerical simulation . in a homogeneous medium which can be simulated with a lattice of regular neighborhood connections , \n the spiral wave is in the meandering regime . \n when changing the topology of a small region from regular connections to small - world connections , the tip of a spiral waves is attracted by the small - world region , where the average path length declines with the introduction of long distant connections . \n the `` trapped '' \n phenomenon also occurs in regular lattices where the diffusion coefficient of the small region is increased . \n the above results can be explained by the eikonal equation and the relation between core radius and diffusion coefficient .", "role": "assistant" } ]

[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nReduction of cholesterol risk factors by lecithin in patients with Alzheimer's disease.\nAbstract 1:\nnan\n\n\nTitle 2:\nIntramuscular desferrioxamine in patients with Alzheimer's disease.\nAbstract 2:\nAlthough epidemiological and biochemical evidence suggests that aluminium may be associated with Alzheimer's disease (AD), there is no convincing proof of a causal link for aluminium in disease progression. We have completed a two year, single-blind study to investigate whether the progression of dementia could be slowed by the trivalent ion chelator, desferrioxamine. 48 patients with probable AD were randomly assigned to receive desferrioxamine (125 mg intramuscularly twice daily, 5 days per week, for 24 months), oral placebo (lecithin), or no treatment. No significant differences in baseline measures of intelligence, memory, or speech ability existed between groups. Activities of daily living were assessed and videorecorded at 6, 12, 18, and 24 month intervals. There were no differences in the rate of deterioration of patients receiving either placebo or no treatment. Desferrioxamine treatment led to significant reduction in the rate of decline of daily living skills as assessed by both group means (p = 0.03) and variances (p less than 0.04). The mean rate of decline was twice as rapid for the no-treatment group. Appetite (n = 4) and weight (n = 1) loss were the only reported side-effects. We conclude that sustained administration of desferrioxamine may slow the clinical progression of the dementia associated with AD.\n\n\nTitle 3:\nLecithin administration in Alzheimer dementia.\nAbstract 3:\nnan\n\n\nTitle 4:\nA double-blind, placebo controlled trial of high-dose lecithin in Alzheimer's disease.\nAbstract 4:\nThe first long-term double-blind placebo controlled trial of high dose lecithin in senile dementia of the Alzheimer type is reported. Fifty one subjects were given 20-25 g/day of purified soya lecithin (containing 90% phosphatidyl plus lysophosphatidyl choline) for six months and followed up for at least a further six months. Plasma choline levels were monitored throughout the treatment period. There were no differences between the placebo group and the lecithin group but there was an improvement in a subgroup of relatively poor compliers. These were older and had intermediate levels of plasma choline. It is suggested that the effects of lecithin are complex but that there may be a \"therapeutic window\" for the effects of lecithin in the condition and that this may be more evident in older patients.\n\n\nTitle 5:\nAlzheimer disease: lack of effect of lecithin treatment for 3 months.\nAbstract 5:\nEleven outpatients with Alzheimer disease of moderate severity completed a double-blind placebo-controlled crossover trial of lecithin. Each patient received 10 gm three times daily of a placebo for 3 months. Plasma choline levels rose threefold and remained at that level throughout the lecithin administration period. A significant difference between mean baseline scores and treatment scores was found on tests of new learning ability, indicating a practice effect in these tests. However, there were no differences between mean placebo and lecithin scores on any of the psychological test measures.\n\n\nTitle 6:\nLecithin treatment of cognitively impaired Parkinson's patients.\nAbstract 6:\nTo test the effects of lecithin on cognitive deficits associated with Parkinson's disease, sixteen elderly and mentally-impaired outpatients with Parkinson's disease participated in a 9-week double-blind placebo-controlled study. Each patient took a daily dose of approximately 32 g of a commercial lecithin preparation containing 25% phosphatidylcholine, or an equivalent amount of powdered skim milk placebo. Marked clinical improvement was not observed, but some indications of a positive treatment effect were obtained on memory, cognition, and motility tests.\n\n\nTitle 7:\nFailure of long term high-dose lecithin to retard progression of early-onset Alzheimer's disease.\nAbstract 7:\nWe conducted a six-month, randomized, double-blind trial of lecithin therapy in early-onset Alzheimer's disease. We hypothesized that such therapy would retard the progression of the clinical and neuropsychological manifestations of this illness. Of the 73 referred patients, 37 met strict requirements for diagnosis and compliance. The 21 placebo and 16 lecithin-treated patients (mean age 63 years) had a comparable degree of severity of dementia (mean Clinical Dementia Rating 1.6). Lecithin therapy produced an increase in mean plasma choline levels from a baseline of 15.9 to 28.8 nmol/ml. Patients were evaluated by the physician using clinical assessments (CDR, Lawton ADL and other rating scales) and by the neuropsychologist who determined the outcome of therapy on a battery of tests (Mini Mental State Examination, Wepman Aphasia Screen, Verbal Fluency Test, Verbal Selective Reminding Test and Spatial Memory Test). Only 6 (37.5%) of the 16 lecithin-treated patients were considered by the neurologist to be clinically stable or improved as compared to 12 (57.1%) of the 21 patients given placebo (difference -19.6%, 95% confidence limits of -51% to 12%). The neuropsychologic scores showed no differences in the stability of the dementing process over time between the lecithin-treated (50.0%) and placebo (47.6%) groups. On the basis of these clinical and neuropsychological findings, it appears that lecithin alone has no important therapeutic effect in early-onset Alzheimer's disease.\n\n\nTitle 8:\nThe effect of long-term high dose lecithin on erythrocyte choline transport in Alzheimer patients.\nAbstract 8:\nnan\n\n\nTitle 9:\nA dose-ranging study of lecithin in the treatment of primary degenerative dementia (Alzheimer disease).\nAbstract 9:\nnan", "role": "user" }, { "content": "Evidence from randomized trials does not support the use of lecithin in the treatment of patients with dementia. A moderate effect cannot be ruled out, but results from the small trials to date do not indicate priority for a large randomized trial.", "role": "assistant" } ]

[ { "content": "You will be presented with a paragraph from a COVID-19 literature. Your task is to classify the topics of this piece of text by choosing from the following categories:\n\n- Epidemic Forecasting: The content relates to predictions about the spread of COVID-19.\n- Treatment: The paragraph discusses therapeutic methods or medication for COVID-19.\n- Prevention: The content covers measures to prevent the spread of COVID-19.\n- Mechanism: The paragraph explains the biological mechanisms of the virus.\n- Case Report: The content is a report of a COVID-19 case.\n- Transmission: The paragraph discusses how COVID-19 is transmitted.\n- Diagnosis: The content is about diagnosing COVID-19 in individuals.\n\nYour classification should be provided as an element within a JSON array. The array should be formatted with topics enclosed in double quotes and separated by commas, following the JSON format, for example: [\"Topic1\", \"Topic2\", ...]. Include all applicable categories within the array. \nYour output should be a valid JSON array, and no additional text should be included in your response.\n\nArticle:\n\nCoronavirus disease 2019 (COVID-19) is an active worldwide pandemic with diverse presentations and complications. Most patients present with constitutional and respiratory symptoms. Acute ischemic stroke remains a medical emergency even during the COVID-19 pandemic. Here we present a case of a patient with COVID-19 who presented with acute ischemic stroke in the absence of common risk factors for cerebrovascular accidents. A 70-year-old male patient, with no prior comorbidities, presented to the emergency department (ED) with fever, cough, and shortness of breath for four days, and altered level of consciousness and right-sided weakness with the sensory loss for one day. On examination, the patient had a score of 8/15 on the Glasgow coma scale (GCS). There was a right-sided sensory loss and weakness in both upper and lower limbs with a positive Babinski's sign. The pulmonary examination was remarkable for bilateral crepitation. On blood workup, there was leukocytosis and raised c-reactive protein (CRP). D-dimer, ferritin, thyroid-stimulating hormone (TSH), vitamin B12, and hypercoagulability workup were normal. Transthoracic echocardiography was also normal. COVID-19 polymerase chain reaction (PCR) detected the virus. Chest x-ray showed infiltrations in the left middle and both lower zones of the lungs in the peripheral distribution. Computed tomography (CT) scan of the chest showed peripheral and mid to basal predominant multilobar ground-glass opacities. CT scan of the head showed a large hypodense area, with a loss of gray and white matter differentiation, in the left middle cerebral artery territory. Magnetic resonance imaging (MRI) of the head showed abnormal signal intensity area in the left parietal region. It appeared isointense on T1 image and hyperintense on T2 image. It also showed diffusion restriction on the diffusion-weighted 1 (DW1) image with corresponding low signals on the apparent diffusion coefficient (ADC) map. These findings were consistent with left middle cerebral artery territory infarct due to COVID-19. The patient was intubated in the ED. He was deemed unfit for thrombolysis and started on aspirin, anti-coagulation, and other supportive measures. Patients with COVID-19 should be evaluated early for neurological signs. Timely workup and interventions should be performed in any patient suspected of having a stroke to reduce morbidity and mortality.", "role": "user" }, { "content": "[\"Case Report\"]", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\", \"Protein\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\" : [\"Dexamethasone\", ...], \"Protein\" : [\"BRCA-1\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nOccupancy of dopamine D(1), D (2) and serotonin (2A) receptors in schizophrenic patients treated with flupentixol in comparison with risperidone and haloperidol.\nRATIONALE: Flupentixol (FLX) has been used as a neuroleptic for nearly 4 decades. In vitro data show comparable affinity to dopamine D(2), D(1) and 5-HT(2A) receptors and recently, FLX showed to be not inferior to risperidone in schizophrenic patients with predominant negative symptomatology, which was implicated with flupentixol's interaction with 5-HT(2A) and/or D(1) receptors. OBJECTIVES: To assess in vivo receptor occupancy (RO) in patients clinically treated with FLX (n = 13, 5.7 +/- 1.4 mg/day) in comparison with risperidone (RIS, n = 11, 3.6 +/- 1.3 mg/day) and haloperidol (HAL, n = 11, 8.5 +/- 5.5 mg/day). MATERIALS AND METHODS: Each patient underwent two PET scans with 3-N-[(11)C]methylspiperone (target: frontal 5-HT(2A)), [(11)C]SCH23390 (striatal D(1)) or [(11)C]raclopride (striatal D(2)). RO was calculated as the percentage reduction of specific binding in comparison with healthy controls. RESULTS: D(2)-RO under FLX was between 50% and 70%, indicating an ED(50) of about 0.7 ng/ml serum. 5-HT(2A) and D(1)-RO was 20 +/- 10% and 20 +/- 5% (mean, SEM). Under HAL, D(1)-RO was 14 +/- 6% and under RIS not significantly different from zero. CONCLUSIONS: We were able to demonstrate a moderate 5-HT(2A) and D(1) occupancy under clinically relevant doses of flupentixol, albeit lower than expected from in vitro data and clearly below saturation. Therefore, if flupentixol's efficacy on negative symptoms is based on its interaction with 5-HT(2A) and/or D(1) receptors, it should be highly dependent on serum concentration and thus on dosage and metabolism. However, these data suggest that mechanisms other than D(1) or 5-HT(2A) antagonism may contribute to flupentixol's efficacy on negative symptoms.", "role": "user" }, { "content": "{\"Chemical\": [\"serotonin\", \"[(11)C]raclopride\", \"FLX\", \"dopamine\", \"Flupentixol\", \"3-N-[(11)C]methylspiperone\", \"[(11)C]SCH23390\", \"haloperidol\", \"flupentixol\", \"risperidone\"], \"Protein\": [\"dopamine D(2)\", \"D(2)\", \"5-HT(2A)\", \"D(1)\", \"D (2)\", \"serotonin (2A) receptors\", \"5-HT(2A) receptors\", \"D(1) receptors\"]}", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Molecular Basis for a Lack of Correlation between Viral Fitness and Cell Killing Capacity\nArticle:\nAbstract:\nThe relationship between parasite fitness and virulence has been the object of experimental and theoretical studies often with conflicting conclusions. Here, we provide direct experimental evidence that viral fitness and virulence, both measured in the same biological environment provided by host cells in culture, can be two unrelated traits. A biological clone of foot-and-mouth disease virus acquired high fitness and virulence( cell killing capacity) upon large population passages in cell culture. However, subsequent plaque-to-plaque transfers resulted in profound fitness loss, but only a minimal decrease of virulence. While fitness-decreasing mutations have been mapped throughout the genome, virulence determinants—studied here with mutant and chimeric viruses—were multigenic, but concentrated on some genomic regions. Therefore, we propose a model in which viral virulence is more robust to mutation than viral fitness. As a consequence, depending on the passage regime, viral fitness and virulence can follow different evolutionary trajectories. This lack of correlation is relevant to current models of attenuation and virulence in that virus de-adaptation need not entail a decrease of virulence.\nIntroduction:\nThe relationship between fitness and virulence is an unsettled question, and sometimes fitness is considered a component of the virulence phenotype of parasites. RNA viruses are ideal systems to address this important question because of their high mutability and fecundity, which result in a potential for rapid evolution, and also because of the availability of quantitative fitness and virulence assays. RNA viruses replicate as complex and dynamic mutant spectra, termed viral quasispecies. Key to quasispecies dynamics are mutation rates in the range of 10−3 to 10−5 substitutions per nucleotide copied, and competition among continuously arising variant genomes[1–4], which prompt rapid movements in sequence space, with corresponding changes of position in the fitness landscape[5]. Indeed, large population passages of RNA viruses in cell culture permit competitive optimization of mutant distributions that generally result in fitness gain[6, 7], while repeated bottleneck events( experimentally realized as plaque-to-plaque transfers) lead to random accumulation of deleterious mutations( operation of Muller's ratchet[8]) and result in average fitness decreases[9–13]. Fitness recovery of low fitness foot-and-mouth disease virus( FMDV) clones occurs mainly with introduction of mutations along the genome, with very few true reversions. An understanding of the consequences of fitness variation for viral virulence is a key question for viral pathogenesis and evolution. Here, we approach this issue with FMDV, an important viral pathogen in veterinary medicine[14], and one that fully participates of quasispecies dynamics. Our laboratory has characterized multiple FMDV variants that derive from one original biological clone, and that occupy widely different fitness levels when replicating in a defined environment in cell culture. We define fitness as the replication capacity of a mutant FMDV, relative to a reference FMDV, in direct growth-competition upon coinfection of baby hamster kidney 21( BHK-21) cells[15–17]. Fitness of FMDV in BHK-21 cells is a multigenic trait[7]. In the present study, we define virulence of FMDV as the capacity of the virus to kill BHK-21 cells under a standard set of cell culture conditions[18]. Thus, the FMDV–BHK-21 system offered a means to investigate in a direct and comparative fashion the relationship between fitness and virulence of a virus, measured in the same biological environment provided by BHK-21 cells. We describe the behavior of an FMDV clone(), which has a history of repeated serial plaque-to-plaque transfers in BHK-21 cells[11], that attained a very low fitness value relative to its parental reference virus( C-S8c1), and yet, its virulence for BHK-21 cells was significantly higher than that of C-S8c1. A comparative study of the capacity to kill BHK-21 cells of chimeric FMDVs constructed with cDNA copies of the two parental FMDVs indicates that the enhanced virulence for BHK-21 cells of the low fitness clone is a polygenic trait, with participation of the regions encoding capsid proteins and non-structural proteins 2A, 2B, and 2C as virulence determinants. Three specific amino acid replacements in 2C have been identified as redundant virulence determinants of FMDV for BHK-21 cells. Thus, while large population passages of the virus resulted in a gain of both fitness and virulence, subsequent bottleneck passages resulted in a decrease of fitness but not of virulence. The results suggest that fitness is very vulnerable to mutation in any genomic region. In contrast, because of the involvement of several( but not all) viral genes in virulence, and the redundant effect of three 2C substitutions, virulence is a more robust phenotypic trait than fitness, and less vulnerable to accumulation of mutations. Therefore, we provide direct evidence that viral fitness and capacity to kill cells can( in some cases) be unrelated traits. Furthermore, the relationship between fitness and virulence, of being either linked or unrelated traits, depends on the evolutionary history of the virus. This observation has implications for viral pathogenesis, and sheds light on models of virulence proposed on the basis of theoretical and experimental studies with cellular organisms.\nDiscussion:\nThe results with FMDV clones H5 have documented that both fitness-enhancing and virulence-enhancing mutations can be incorporated in the viral genome in such a fashion that subsequent fitness-decreasing mutations associated with bottleneck( plaque-to-plaque) transfers produce only minimal effects on virulence( Figure 2). The dissection of accompanying molecular events, achieved through quantification of virulence of recombinant and mutant genomes( Tables 2 and S1), provides an interpretation of the lack of positive correlation between virulence and fitness. Multiple fitness-decreasing mutations occur in the course of plaque-to-plaque transfers, distributed throughout the FMDV genome[11]. In contrast, determinants of virulence for BHK-21 cells are multigenic, but concentrated mainly in some FMDV genomic regions. Similar multigenic but discrete virulence determinants have been described also in other virus–host systems[42, 43]. To decrease virulence, mutations occurring randomly in the course of plaque-to-plaque transfers should affect specific genomic sites, and this will occur with a lower probability than fitness-decreasing mutations, which can hit any of the multifunctional picornaviral proteins and regulatory regions[11]. This model is reinforced by the observation that three amino acid substitutions in 2C( S80N, T256A, and Q263H) had a similar effect in enhancing FMDV virulence, and the three mutations in the same genome had an effect comparable to each mutation individually( Figure 6; Tables 2 and S1). It is not clear what the basis of the contribution of 2C to virulence for BHK-21 could be. 2C is involved in RNA synthesis and contains a nucleotide-binding domain, although none of the substitutions found in and lie within such a domain. An unlikely triple reversion would be required to eliminate the virulence-enhancing effect of the three mutations in 2C. We propose that a higher robustness of the FMDV genome with regard to virulence for BHK-21 cells, rather than to replicative fitness in the same cells, underlies the different trajectories followed by fitness and virulence upon subjecting the virus to repeated bottleneck transfers. Obviously, we cannot exclude that parameters of the virus life cycle, other than fitness as measured in our experiments, could correlate with virulence for BHK-21. The comparative analysis of FMDV clones and populations shows that shifts in virulence can occur even through the evolution of a single viral clone( C-S8c1), with its restricted genetic diversity prompted by different replication regimes in the same host cells, which also have a clonal origin( see Materials and Methods). We conjecture that the demonstration that fitness and virulence can follow different evolutionary courses has been possible thanks to the consequences of the extreme passage regimes to which the viral populations were subjected: competitive evolution of an ample mutant spectra during repeated large population passages, and accumulation of deleterious( with regard to fitness, but not with regard to virulence) mutations upon plaque-to-plaque transfers( predominance of genetic drift and operation of Muller's ratchet)[12, 15]. It must be emphasized that fitness and virulence are relative values that pertain to a defined physical and biological environment. Virulence determinants of FMDV, identified here for BHK-21 cells, need not apply to virulence for the natural animal hosts of FMDV[44]. However, the observation of a lack of correlation between fitness and virulence in a FMDV clone is relevant to current models of attenuation and virulence, since it shows that more virulent forms of a virus need not have a reproductive advantage, and that viral virulence is not necessarily a byproduct of viral fitness. Even if virulence is regarded as an unavoidable consequence of parasite adaptation[45], virus de-adaptation( fitness loss) need not entail a decrease of virulence. Most current definitions of virulence include both the ability of the pathogen to multiply and to cause harm to its host; some authors, however, assume a direct relationship between fitness and capacity to produce disease[46–48]. In relating the results with FMDV to general models of virulence in host–parasite systems, it must be considered that in the FMDV system, evolution of the host BHK-21 cells could not influence FMDV evolution, because clonal cell populations with a controlled passage history were supplied in constant numbers at each infection event( see Materials and Methods). Therefore, changes in host density, or mobility, as well as pathogen survival in the external environment, all of which are relevant parameters in virulence models[48, 49], cannot play a role in our system. A consistent finding in serial passage experiments is that virulence of a parasite increases with passage number in a new host[50]. The results with FMDV infecting BHK-21 cells cytolytically imply that the increase of virulence can be conditioned to the history of passage regimes undergone by a virus. The invariance of BHK-21 cells in the course of serial cytolytic passages of FMDV is in contrast with the parallel system consisting of BHK-21 cells persistently infected with FMDV C-S8c1[25], in which the cells are passaged and coevolve with the resident virus[51]. Host–virus coevolution has generally favored a decrease of viral virulence in the field, a classical example being myxoma virus and myxomatosis in rabbits[52]. Our comparison of FMDV clones did not provide evidence of clones with high fitness and low virulence, which, with regard to natural hosts, is an aim of biomedicine to obtain vaccine strains. Yet, the existence of specific mutations that differentially affect fitness and virulence opens the way to engineer candidate vaccine strains unable to kill the host, while maintaining replicative competence. Virulence is, however, a feature of the host–parasite relationship[46], and the mutations needed to impair virulence are expected to be host-dependent[53, 54].", "role": "user" }, { "content": "Virulence expresses the harm that parasites inflict upon their hosts . Many studies have addressed the basis of virulence and its effect on host and parasite survival . It has generally been accepted that one of the components of parasite virulence is fitness , or the capacity of the parasite to multiply in its host . Some models have equated virulence with fitness . In the present study , we use foot-and-mouth disease virus ( FMDV ) to document that virulence and fitness—measured in the same biological environment provided by cells in culture—can be unrelated traits . This has been achieved by multiplying the virus in a manner that mutations accumulated in its genome . Mutations decreased fitness dramatically , but not virulence . Chimeric and mutant viruses were constructed to show that virulence is influenced by only some of the FMDV genes , while fitness is influenced by the entire genome . For this reason , virulence is more robust ( “resistant” ) than fitness to the effects of deleterious mutations . The fact that virulence can be unrelated to fitness has implications for the design of anti-viral vaccines because it suggests that it may be possible to design high fitness , low virulence strains to stimulate the host immune response . Furthermore , in modelling studies it cannot be assumed that virulence is equal to fitness .", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: Which is the mass-tag that reveal the ubiquitination of a lysine residue?\n\nContext: antibodies that recognize the Lys-ɛ-Gly-Gly (K-ɛ-GG) remnant produced by trypsin digestion of proteins having ubiquitinated lysine side chains have markedly improved the ability to enrich and detect endogenous ubiquitination sites by mass spectrometry (MS).\nRecent publications have also highlighted the use of peptide-level immunoaffinity enrichment of K-GG modified peptides from whole cell lysates for global characterization of ubiquitination sites.\nIn this work, levels of lysine ubiquitination were quantitated using a structurally homologous label that is chemically similar to the diglycine (GlyGly) tag, which is left at the ubiquitination site upon trypsinolysis\nTandem mass spectrometry (LC-MS/MS) analysis of immunoprecipitated proteins resulted in the identification of five peptides containing ubiquitin (diglycine) modifications on eIF2Bε", "role": "user" }, { "content": "Lys-ɛ-Gly-Gly (K-ɛ-GG) is the remnant produced by trypsin digestion of proteins having ubiquitinated lysine side chains.", "role": "assistant" } ]

[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: The most common symptoms are: Respiratory illness symptoms (sore throat, cough (usually dry), shortness of breath, chest pain)\n\nAbstract:\nSince Dec 2019, a cluster of pneumonia outbreak in Wuhan, Hubei province, China, and soon spread to all province of China.\nThe pathogen was proved to be a novel betacoronavirus called 2019 novel coronavirus (officially named by the World Health Organization as COVID-19).\nThe typical clinical manifestations were fever, cough, dyspnea, and myalgia or fatigue.\nLess common symptoms included headache, diarrhea, nausea and vomiting.\nHowever diarrhea as the first symptom is rarely reported.\nHere we reported a case of 2019 novel coronavirus-infected patient (NCIP) with diarrhea as the initial symptom.\nImage of CT scan and laboratory examination and careful collected as well as detection of viral RNA in pharynx.\nThe case demonstrate that gastrointestinal symptoms ware not rare in NCIP, and diarrhea could be the initial symptom.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"The pathogen was proved to be a novel betacoronavirus called 2019 novel coronavirus (officially named by the World Health Organization as COVID-19).\", \"The typical clinical manifestations were fever, cough, dyspnea, and myalgia or fatigue.\", \"Less common symptoms included headache, diarrhea, nausea and vomiting.\"]}", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Engineering of a synthetic quadrastable gene network to approach Waddington landscape and cell fate determination\nArticle:\nAbstract:\nThe process of cell fate determination has been depicted intuitively as cells travelling and resting on a rugged landscape, which has been probed by various theoretical studies. However, few studies have experimentally demonstrated how underlying gene regulatory networks shape the landscape and hence orchestrate cellular decision-making in the presence of both signal and noise. Here we tested different topologies and verified a synthetic gene circuit with mutual inhibition and auto-activations to be quadrastable, which enables direct study of quadruple cell fate determination on an engineered landscape. We show that cells indeed gravitate towards local minima and signal inductions dictate cell fates through modulating the shape of the multistable landscape. Experiments, guided by model predictions, reveal that sequential inductions generate distinct cell fates by changing landscape in sequence and hence navigating cells to different final states. This work provides a synthetic biology framework to approach cell fate determination and suggests a landscape-based explanation of fixed induction sequences for targeted differentiation.\nIntroduction:\nMultistability is a mechanism that cells use to achieve a discrete number of mutually exclusive states in response to environmental inputs, such as the lysis/lysogeny switch of phage lambda( Arkin et al, 1998; Oppenheim et al., 2005) and sporulation/competence in Bacillus subtilis( Süel et al., 2006; Schultz et al., 2009). In multicellular organisms, multistable switches are also common in the cellular decision-making including the regulation of cell-cycle oscillator during cell mitosis( Pomerening et al., 2003), Epithelial-to-Mesenchymal transition and cancer metastasis( Jolly et al., 2016; Lee et al., 2014a), and the well-known cell differentiation process, which is a manifestation of cellular state determination in a multistable system( Laurent and Kellershohn, 1999; Guantes and Poyatos, 2008). However, loss of multistability can drive cells to acquire metastatic characteristics and stabilize highly proliferative, pathogenic cellular states in cancer( Lee et al., 2014b). C. H. Waddington hypothesized the ‘epigenetic landscape’ to explain canalization and fate determination mechanism during cell differentiation( Waddington, 1957). In this hypothesis, differentiation is depicted as a marble rolling down a landscape with multiple bifurcating valleys and eventually settles at one of the local minima, corresponding to terminally differentiated cells. More recent theoretical studies further proposed the local minima to be modeled as steady states or attractors of dynamical systems, which can be mathematically described using differential equations( Zhang and Wolynes, 2014; Li and Wang, 2013a). As such, cell differentiation can be interpreted as a state transition process on a multistable dynamic system. A myriad of theoretical analysis have investigated the functioning of such systems and quantified the Waddington landscape and developmental paths through computation of the probability landscape for the underlying gene regulatory networks( Li and Wang, 2013a; Wang et al., 2011; Li and Wang, 2013b; Ferrell, 2012; Bhattacharya et al., 2011; Macarthur et al., 2009; Huang et al., 2007). Recent studies also revealed that the potential landscape and the corresponding curl flux are crucial for determining the robustness and global dynamics of non-equilibrium biological networks( Wang, 2015; Xu et al., 2014; Wang et al., 2008). Furthermore, the multiple stable steady states have been predicted beyond the bistable switches with or without epigenetic effects, which is reflected in slow timescales( Wang, 2015; Xu et al., 2014; Li and Wang, 2013b; Feng and Wang, 2012; Wang et al., 2011; Feng et al., 2011). Experimental researches, however, mostly focus on bistable switches, involving transitions between only two states. And demonstrations, from a combination of experiments and computational modeling, for the existence and operation of such a landscape in a higher dimensional multistable system are still lacking. Moreover, it remains unknown how gene regulatory networks( GRNs), gene expression noise, and signal induction together shape the attractor landscape and determine a cell’s developmental trajectory to its final fates( Schmiedel et al., 2015; Tanouchi et al., 2015; Prindle et al., 2014; Chalancon et al., 2012; Murphy et al., 2010; Balázsi et al., 2011; Kramer and Fussenegger, 2005; Bennett et al., 2008; Maamar et al., 2007). Complex contextual connections of GRNs have impeded experimentally establishing the shape and function of the cell fate landscape. Rationally designed and tunable synthetic multistable gene networks in E. coli, however, could form well-characterized attractor landscapes to enable close experimental investigations of general principles of GRN regulated cellular state transitions. Since the functioning of these principles only requires the most fundamental aspects of gene expression regulation, they would also be applicable for cell differentiation regulations in mammalian cells. Here, we combine mathematical theory, numerical simulations, and synthetic biology to probe all possible sub-networks of mutually inhibitory network with positive autoregulations( MINPA, Figure 1A), which has been hypothesized to have multistability potentials( Guantes and Poyatos, 2008; Huang et al., 2007). Moreover, MINPA and its sub-networks are recurring motifs enriched in GRNs regulating hematopoietic development( Gata1-Pu. 1,[Graf and Enver, 2009]), trophectoderm differentiation( Oct3/4-Cdx2,[Niwa et al., 2005]), endoderm formation( Gata6-Nanog,[Bessonnard et al., 2014; Li and Wang, 2013a]), and bone, cartilage, and fat differentiation( RUNX2-SOX9-PPAR-γ,[MacArthur et al., 2008; Rabajante and Babierra, 2015]). 10. 7554/eLife. 23702. 003Figure 1. Conceptual and experimental design of MINPA and its sub-networks.( A) Abstract diagram of MINPA topology, where X and Y mutually inhibit( T-bars) each other and auto-activate( arrowheads) itself. Four inducers to regulate the four color-coded regulatory edges are also listed.( B) Molecular implementation of the MINPA network. Para/lac( purple arrow) is activated by AraC( yellow) and repressed by LacI( light green), while Plux/tet( cyan arrow) is activated by LuxR( blue) and repressed by TetR( red). Arabinose and AHL( oval) can induce AraC and LuxR activation, respectively. IPTG and aTc( hexagon) can respectively relieve LacI and TetR inhibition. GFP and mCherry serve as the readout of Para/lac and Plux/tet, respectively. Therefore, TetR and AraC collectively form the node X in( A), color-coded as purple rectangle. Similarly, LuxR and LacI collectively form the node Y in( A), color-coded as cyan rectangle. Genes, promoters and regulations are color-coded corresponding to the topology in( A).( C) List of MINPA and its 14 sub-networks. Numbering of indices is converted from topologies’ binary name( see Figure 1—figure supplement 1E for more details). T represents ‘topology’. R represents ‘repression’, and A represents ‘autoactivation’. Superscript is used to describe the number of such types of edges. Topologies with shaded background were later constructed and analyzed experimentally.( D–E) Dynamic responses for Para/lac( D) and Plux/tet( E) through induction with Arabinose( Ara) and IPTG, and AHL and aTc, respectively. Presented data was the mean value of three replicates. mCherry and GFP serves as the readout of the two promoters. DOI: http://dx. doi. org/10. 7554/eLife. 23702. 00310. 7554/eLife. 23702. 004Figure 1—figure supplement 1. Experimental design, topological hierarchy and multistability probability analysis of MINPA sub-networks.( A) Abstract diagrams and molecular implementation of the eight MINPA sub-network topologies, including tunable positive feedbacks( T6 and T9), mutual inhibition( T5), dual-positive feedbacks( T10), and their combinations( T7, T11, T13, and T14). Genes, promoters, and regulations are color-coded corresponding to the topology on the left side.( B–C) Biological devices for testing promoter Para/lac( B) and Plux/tet( C), respectively. Fluorescence was measured by flow cytometry at 12 hr and 24 hr( not shown) after adding the inducers. All the data points were averaged from three repeated experiments. Grey arrows represent constitutive promoters( BBa_K176009).( D) Principle components and optimal Hill functions fitted for hybrid promoter Para/lac and Plux/tet.( E) List of MINPA and its 14 sub-networks, which are named, and color-coded, as binary numbers based on the existence of regulatory edges.( F) Topological hierarchy of the 15 motifs.( G) Probability of multistability( tristability and quadrastability) for the nine experimentally constructed networks. SSS: stable steady states. The range for activation/repression strength is[0. 3, 0. 8], and the probability was calculated from the number of parameter sets giving rise to multistability over 2000-repeated computational simulations.( H) Histograms for parameter combination that have multistability in sub-networks of T10, T13, T14 and T15( MINPA). For each sub-network, the network activation and inhibition strength Sa, Su, St and Sl are randomly selected from given ranges and the number of corresponding SSS is recorded. We repeat this procedure for all sub-networks for 2000 times and calculate the probabilities of bistability( blue lines), tristability( black lines) and quadrastability( red lines).( I) Scatter plots for all parameter combinations that have multistability in MINPA. We generate parameters using the same approach as( H) and select the parameter combinations that can generate three or four SSS in MINPA. DOI: http://dx. doi. org/10. 7554/eLife. 23702. 004\nDiscussion:\nMultistability and the resulting landscape has long been proposed as an underlying mechanism that cells use to maintain pluripotency and guide differentiation( Kauffman, 1993; Laurent and Kellershohn, 1999; Huang et al., 2007; Guantes and Poyatos, 2008; Palani and Sarkar, 2009; Narula et al., 2010; Faucon et al., 2014). Theoretical frameworks have also been established to quantify the Waddington landscape and biological paths for cell development( Li and Wang, 2013a, 2013b; Wang et al., 2011). Experimental validation of this hypothesis and a full understanding of this mechanism will help reveal differentiation dynamics and routes for all cell types, which remains an outstanding problem in biology. In this study, we engineered the quadrastable MINPA circuit and show that it can guide cell fate choices, represented by fluorescence expression, through shaping the potential landscape. MINPA represents one of the most complicated two-node network topologies and includes four genes to implement a web of regulations. Biological complexity correlates with the number of regulatory connections( Szathmáry et al., 2001), not the number of genes. Hence, dense connectivity and complex dynamics of MINPA may provide a framework to understand similarly densely connected gene regulatory networks. Combining mathematical modeling and experimental investigation, this study serves as a proof-of-principle demonstration of the Waddington landscape. Furthermore, we used this circuit to demonstrate how different sequential inductions can change the landscape in a specific order and navigate cells to different final states. Such illustrations suggest mechanistic explanations of the need for fixed induction sequences for targeted differentiation to desired cell lineage. Overall, this study helps reveal fundamental mechanisms of cell-fate determination and provide a theoretical foundation for systematic understanding of the cell differentiation process, which will lead to development of new strategies to program cell fate.", "role": "user" }, { "content": "Cells in animals use a process called differentiation to specialize into specific cell types such as skin cells and liver cells . Proteins called transcription factors drive particular steps in differentiation by controlling the activity of specific genes . Many transcription factors interact with each other to form complex networks that regulate gene activity to determine the fate of a cell and control the whole differentiation process . Some individual gene networks can program cells to become any one of several different cell fates , a feature known as multistability . In the 1950s , a scientist called Conrad Waddington proposed the concept of an “epigenetic landscape” to describe how the fate of a cell is decided as an animal develops . The cell , depicted as a ball , rolls down a rugged landscape and has the option of taking several different routes . Each route will eventually lead to a distinct cell fate . As the ball moves down the hill , the choice of routes and final destinations becomes more limited . Theoretical approaches have been used to understand how gene regulatory networks shape the epigenetic landscape of an animal . However , few studies have experimentally tested the findings of the theoretical approaches and it is not clear how environmental inputs help to determine which path a cell will take . Although bacteria cells do not generally specialize into particular cell types , bacteria cells can use multistability in transcription factor networks to switch between different behaviors or “states” in response to cues from the environment . Wu et al . used a bacterium called E . coli as a model to investigate how a gene network called MINPA from mammals , which is involved in differentiation and is believed to show multistability , can guide cells to adopt different states . The work combined experimental and mathematical approaches to design , construct and test an artificial version of the MINPA gene network in E . coli . The experiments showed that MINPA could direct the cells to adopt four different stable states in which the cells produced fluorescent proteins of different colors . With the help of mathematical modeling , Wu et al . charted how the landscape of cell states changed when external chemical cues were applied . Exposing the cells to several cues in particular orders guided the cells to different final states . The findings of Wu et al . shed new light on how the fate of a cell is determined and provide a theoretical framework for understanding the complex networks that control cell differentiation . This could help develop new ways of directing cell fate that could ultimately be used to generate cells to treat human diseases .", "role": "assistant" } ]

[ { "content": "You will be presented with the full text of a biomedical research paper. Please write an abstract for this paper. Your response should only include the abstract and no additional text.\n\nPaper text:\nsex ratio , an important social indicator measuring extent of prevailing equity betweenmales and females in a society , is defined as number of females per 1000 males .\nthe overall sex ratio in india has increased to 940 as per 2011 census against 933 as given by 2001 census . however , the area of grave concern is that the child sex ratio plummeted to 914 from 927 in 2001 .\nfemale feticide besides skewed sex ratio and its attendant social evils has grave ethical undertones , especially for medical professionals and their commitment to save lives as per the hippocratic oath .\nthe unaffected ratio in the census of 1981 was 978 but after sex selective feticide came into practice , the ratio dropped steadily to 934 in the census of 2001 and then further to 905 in 2003 .\nthe female feticide in 1997 is estimated by different experts and the figures vary from a low of 106 thousand to half a million .\nthe worsening of the country s hugely skewed sex ratio is largely due to misuse of prenataldiagnostic techniques despite stringent laws banning their use for sex selection and consequent increase in cases of female feticide .\nthe sex selection in a globalized economy has dragged the fetus to the market place . in spite of a massive influx of legal regulations barring the female fetuses\nthe meansto showbetter off in respect to sex ratio is only through improving the child sex ratio in the next few years , so it will again reflect in future censuses in terms of better overall sex ratio . in spite of this , if the child sex ratio still remains low in next census , we have to bear its effects until the middle of 21 century as it is definitely going to reflect in long term .\nthe only means to get satisfaction in the next census in terms of sex ratio is the intensive measures directed to improve the child ( 0 - 6 ) sex ratio . a concerted effort by the medical fraternity , the lawenforcers and political leaders , ngos , media , teachers , and the community itself are essential against this social evil .\nif the doctors are willing to fight against this emerging concern , the problem could easily be curbed . to sensitize tomorrow s doctors about the ethics related to the inappropriate and indiscriminate use of technology\nis the need of the hour , so that these future doctors can join their hands to improve the status of women in india .\nhence , the present study was conducted in a medical college to assess the knowledge and attitude of interns regarding declining sex ratio and female feticide .\nacross - sectional study was conducted in a medical college in an urban area of western maharashtra from february 2013 to april 2013 .\nthe purpose of the study was explained to the participants and informed verbal consent was taken from all the participants .\nquestions were developed by reviewing relevant literature and also based on the vital statistics data of india and current prevalent practices regarding methods of sex selection and related legislationsin india .\nthe questions were both open - ended and closed - ended and related to three domains viz . , sex ratio , pre - conception and prenatal diagnostic techniques ( pcpndt ) act , female feticide and measures to combat it .\neach correct response was given the score of 1 ( one ) and each incorrect response was given 0 ( zero ) .\npercentages and proportions were estimated and chi - square tests , standard error of difference between two means ( z tests ) and kruskal - wallis tests were used to test the significance .\nacross - sectional study was conducted in a medical college in an urban area of western maharashtra from february 2013 to april 2013 .\nthe purpose of the study was explained to the participants and informed verbal consent was taken from all the participants .\nquestions were developed by reviewing relevant literature and also based on the vital statistics data of india and current prevalent practices regarding methods of sex selection and related legislationsin india .\nthe questions were both open - ended and closed - ended and related to three domains viz . , sex ratio , pre - conception and prenatal diagnostic techniques ( pcpndt ) act , female feticide and measures to combat it .\neach correct response was given the score of 1 ( one ) and each incorrect response was given 0 ( zero ) .\npercentages and proportions were estimated and chi - square tests , standard error of difference between two means ( z tests ) and kruskal - wallis tests were used to test the significance .\nin a cross - sectional study conducted among 79 medical interns , 47(59.5% ) were male and 32(40.5% ) were female .\nas revealed in table 1 , knowledge of current sex ratio was significantly better among female interns compared to male interns .\nhowever , there was no significant difference in knowledge regarding causes of declining sex ratio and its implications in male and female interns .\nknowledge regarding sex ratio a total of 61interns opined that creating awareness is the effective measure to combat declining sex ratio , while 49 interns thought that legislative measures are the useful means and only 33 interns had correct knowledge regarding all measures [ table 2 ] .\nknowledge regarding measures to combat declining sex ratio only 37.9% of interns ( 15 male and 15 female ) knew all the indications for use of prenatal diagnostic techniques mentioned under pcpndt act .\nhowever , 81% of interns were aware about punishments mentioned for violation of the act .\nalmost all interns ( 92.4% ) in our study were aware of indications for termination of pregnancy under mtp act , 1971 .\nhowever , there was no significant difference in knowledge about measures to combat declining sex ratio among male and female interns .\nknowledge of measures to reduce female feticide and responsibilities of doctors and other members was significantly better among female interns than among male interns [ table 3 ] .\nknowledge regarding measures to reduce female feticide mean score of knowledge was better among female interns and significant difference was observed after applying z test for standard error of difference between two means [ table 4 ] .\na cross - sectional study was conducted among 79 interns to assess their knowledge about sex ratio and female feticide . in our study ,\na total of 26.6% of interns knew that increase in crime and violence would be one of the implications of declining sex ratio .\na total of 41.9% of male interns and 25.7% of female interns were aware of all implications of female feticide and declining sex ratio like increase in crime , sexually transmitted diseases , effect on women s health and so forth .\n, in their study conducted among medical students reported that 43% of respondents knew about the dangers of female feticide . while in a study conducted by nath et al .\n, 57% of male interns and 43% of female interns participated in the study and 63.2% of male and 61.2% of female interns knew about implications of declining sex ratio as increase in crime and 52% reported that there will be effect on women s health .\nthe majority of interns 61(77.2% ) stated that creating awareness about declining sex ratio is an effective measure while 49(62.2% ) opined strict implementation of law is necessary to deal with this issue . in order to improve child sex ratio ,\nthe female feticide practice should be curbed , creating awareness among people against this social evil . legislative measures and raising the status of women are the strategies to reduce female feticide . in our study ,\n, mentioned that 88.3% of female and 70.2% of male interns stated raising status of women and 46% of males and 65.5% of females opined that strict and deterrent punishment of persons involved are important measures to reduce female feticide .\nthe shocking fact revealed by our study was that the majority of interns knew only one or two indications and only 37.9% interns knew all indications for correct use of prenatal diagnostic techniques .\n, mentioned that 33.69% were awareof the provisions of pcpndt act , while 31.02% were partly aware and 24.93% were not aware at all .\nsimilarly , a report from national institute of public cooperation and child development mentions that a serious knowledge gap was observed regarding mtp act and pndt act among health functionaries .\nour study revealed that medical interns had better knowledge of current sex ratio and causes of its decline as compared to other aspects of this issue .\nhowever , their knowledge regarding measures to reduce female feticide , pcpndt act was not up to the mark .\nthe findings in our study underline the need to sensitize tomorrow s doctors regarding the ethical and medicolegal aspects of pcpndt act and avoid unethical and indiscriminate use of the technology in selective fetal sex selection and female feticide .\nthis can be done by conducting regular workshops / continuing medical educationsessions and awareness campaigns among nonmedical and medical fraternities .", "role": "user" }, { "content": "background : female feticide , skewed sex ratio , and its attendant social evils have grave ethical undertones for medical professionals and our commitment to save lives . \n a concerted effort by all is essential against female feticide.aim:this study was to assess the knowledge of female feticide , declining sex ratio , and corrective measures among medical interns.materials and methods : a cross - sectional study was conducted among 79 medical interns . \n data werecollected with the help of predesigned structured questionnaire . \n chi - square tests , kruskal - wallis tests , and z tests were used to test the significance level.results:knowledge of current sex ratio was significantly better among female interns than male interns . \n majority of interns opined that creating awareness is an effective measure to combat declining sex ratio and only 33 interns had correct knowledge regarding all measures . \n only 37.9% of interns knew all the legal indications for use of prenatal diagnostic techniques . \n however , 81% of interns were aware of punishments mentioned for violation of the act . \n mean score of knowledge was 22.06 among males and 24.4 among females.conclusion:the findings in our study underline the need to sensitize doctors regardingevery aspect of pre - conception and prenatal diagnostic techniques act and selective sex determination .", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\", \"Protein\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\" : [\"Dexamethasone\", ...], \"Protein\" : [\"BRCA-1\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nCYP2J2 overexpression increases EETs and protects against angiotensin II-induced abdominal aortic aneurysm in mice.\nCytochrome P450 epoxygenase 2J2 (CYP2J2) metabolizes arachidonic acids to form epoxyeicosatrienoic acids (EETs), which possess various beneficial effects on the cardiovascular system. However, whether increasing EETs production by CYP2J2 overexpression in vivo could prevent abdominal aortic aneurysm (AAA) remains unknown. Here we investigated the effects of recombinant adeno-associated virus (rAAV)-mediated CYP2J2 overexpression on angiotensin (Ang) II-induced AAA in apoE-deficient mice. rAAV-CYP2J2 delivery led to an abundant aortic CYP2J2 expression and increased EETs generation. It was shown that CYP2J2 overexpression attenuated matrix metalloproteinase expression and activity, elastin degradation, and AAA formation, which was associated with reduced aortic inflammation and macrophage infiltration. In cultured vascular smooth muscle cells (VSMCs), rAAV-mediated CYP2J2 overexpression and EETs markedly suppressed Ang II-induced inflammatory cytokine expression. Moreover, overexpressed CYP2J2 and EETs inhibited Ang II-induced macrophage migration in a VSMC-macrophage coculture system. We further indicated that these protective effects were mediated by peroxisome proliferator-activated receptor (PPAR)γ activation. Taken together, these results provide evidence that rAAV-mediated CYP2J2 overexpression prevents AAA development which is likely via PPARγ activation and anti-inflammatory action, suggesting that increasing EETs levels could be considered as a potential strategy to prevent and treat AAA.", "role": "user" }, { "content": "{\"Chemical\": [\"epoxyeicosatrienoic acids\", \"arachidonic acids\", \"EETs\"], \"Protein\": [\"CYP2J2\", \"angiotensin II\", \"peroxisome proliferator-activated receptor (PPAR)\\u03b3\", \"angiotensin (Ang) II\", \"elastin\", \"matrix metalloproteinase\", \"cytokine\", \"Cytochrome P450 epoxygenase 2J2\", \"PPAR\\u03b3\", \"Ang II\"]}", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2020 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from the options provided. A short description of the datasets is also provided to help you.\n\nQuery: In this paper, we introduce a novel task, fact-grounded data-\n\nKeyphrases: data-to-text generation table\n\nDataset description:\nTHEODORE: Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high- resolution diversified fisheye images with 14 classes.\n30MQA: An enormous question answer pair corpus produced by applying a novel neural network architecture on the knowledge base Freebase to transduce facts into natural language questions.\nOpenBookQA: OpenBookQA is a new kind of question-answering dataset modeled after open book exams for assessing human understanding of a subject. It consists of 5,957 multiple-choice elementary-level science questions (4,957 train, 500 dev, 500 test), which probe the understanding of a small “book” of 1,326 core science facts and the application of these facts to novel situations.\nRotoWire: This dataset consists of (human-written) NBA basketball game summaries aligned with their corresponding box- and line-scores. Summaries taken from rotowire.com are referred to as the \"rotowire\" data.\n\nOptions: A: THEODORE B: 30MQA C: OpenBookQA D: RotoWire", "role": "user" }, { "content": "RotoWire", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nStaged Fowler-Stephens and Single-stage Laparoscopic Orchiopexy for Intra-abdominal Testes: Is There a Difference? A Single Institution Experience To compare single-stage laparoscopic orchiopexy (SSLO) and staged Fowler-Stephens (SFS) procedures in the management of intra-abdominal undescended testes, and to analyze postoperative atrophy and malpositioning as end points. A retrospective chart review identified laparoscopic orchiopexy patients with intra-abdominal testes between November 2006 and November 2014. Of 167 patients who had laparoscopic orchiopexy, 73 (85 testes) were identified as having laparoscopic orchiopexy. Baseline characteristics, as well as testicular scrotal position and size at follow-up, were recorded. Regression analysis was performed to compare outcomes between patients who underwent SFS and SSLO. Of the 85 laparoscopic orchiopexies, 35 underwent SFS and 50 had SSLO. Patient demographics were comparable in both groups. The median age at surgery was 12 months (5-151 months), and the average follow-up was 17.3 months. On follow-up, there were 0 recorded cases of SFS patients with abnormally positioned testes postoperatively, whereas there were 10 (20.0%) SSLO patients who had abnormally positioned testes (odds ratio: 0.05, 95% confidence interval: 0.01-0.44). Differences in atrophy rates were not significant. These results suggest that there may be no difference between the 2 approaches in terms of postoperative atrophy. However, the SFS appears to be more successful in securing a favorable scrotal position. Atrophy does not seem to be associated with other patient factors. Prospective, randomized studies are indicated to further explore outcome differences between the 2 approaches.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"intra-abdominal undescended testes\", \"testicular\", \"scrotal position\", \"testes\", \"Intra-abdominal Testes\", \"intra-abdominal testes\"], \"Bacterium\": [], \"BiologicFunction\": [\"atrophy\", \"Atrophy\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"postoperatively\", \"postoperative\", \"not significant\"], \"Food\": [], \"HealthCareActivity\": [\"laparoscopic orchiopexy\", \"Single-stage Laparoscopic Orchiopexy\", \"SSLO\", \"single-stage laparoscopic orchiopexy\", \"management\", \"follow-up\", \"laparoscopic orchiopexies\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"Regression analysis\"], \"MedicalDevice\": [], \"Organization\": [\"Single Institution Experience\"], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"retrospective chart review\", \"randomized studies\", \"Prospective\", \"analyze\"], \"SpatialConcept\": [\"malpositioning\", \"abnormally positioned\", \"size\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Stimulus salience determines defensive behaviors elicited by aversively conditioned serial compound auditory stimuli\nArticle:\nAbstract:\nAssessing the imminence of threatening events using environmental cues enables proactive engagement of appropriate avoidance responses. The neural processes employed to anticipate event occurrence depend upon which cue properties are used to formulate predictions. In serial compound stimulus( SCS) conditioning in mice, repeated presentations of sequential tone( CS1) and white noise( CS2) auditory stimuli immediately prior to an aversive event( US) produces freezing and flight responses to CS1 and CS2, respectively( Fadok et al., 2017). Recent work reported that these responses reflect learned temporal relationships of CS1 and CS2 to the US( Dong et al., 2019). However, we find that frequency and sound pressure levels, not temporal proximity to the US, are the key factors underlying SCS-driven conditioned responses. Moreover, white noise elicits greater physiological and behavioral responses than tones even prior to conditioning. Thus, stimulus salience is the primary determinant of behavior in the SCS paradigm, and represents a potential confound in experiments utilizing multiple sensory stimuli.\nIntroduction:\nLearned temporal relationships between cue stimuli and aversive events allow individuals to avoid danger. For example, progressive darkening of clouds often precedes lightning storms, and dark skies prompt evacuation from exposed spaces. Other forms of threat prediction derive not from cue timing or sequencing but rather from the intensity or salience of a stimulus, such as an entrenched soldier who uses relative volume of auditory threat stimuli( e. g. foreign vehicles or voices) to gauge proximity of an advancing enemy and determine when to retreat. Human studies indicate that the specific neural circuits engaged during prediction of event occurrence depend on which cognitive strategy is used to solve a particular task( Breska and Ivry, 2018). Thus, determination of the neural mechanisms that regulate different forms of threat prediction, and the consequences when such mechanisms are dysfunctional, requires behavioral paradigms in which the cognitive processes engaged are clearly defined. In SCS conditioning( Fadok et al., 2017), sequential presentation of two different auditory stimuli( pure tones followed by white noise, in that order) precedes delivery of an aversive unconditioned stimulus( US, footshock). Following repeated SCS-US presentations, mice exhibit distinct defensive behaviors to each SCS component: tones elicit freezing whereas white noise elicits flight. The paradigm thus appears to model natural behavioral shifts that occur as the perceived probability of directly encountering threat increases. As posited by ‘predatory imminence theory’, prey animals initially freeze( to avoid detection) when predators are present at a distance, but then switch to flight( escape) to avoid entrapment if a predator becomes close enough that avoiding detection is no longer possible( Blanchard and Blanchard, 1989; Blanchard et al., 1995; Bouton and Bolles, 1980; Fanselow, 1994; Fanselow and Lester, 1988; Perusini and Fanselow, 2015). Given the presence of a specific, repeating sequence of auditory stimuli preceding shock during conditioning, defensive behaviors elicited by individual components of the SCS could in principle be driven by learned CS-US temporal relationships. However, the form of both appetitive and aversive conditioned responses is known to vary substantially according to the particular properties of a given conditioned stimulus, even when the same underlying construct has been learned( Holland, 1977; Holland, 1979; Holland, 1980). Therefore, differences in the intrinsic properties of tone and white noise stimuli themselves, rather than their temporal relationship to the US, could underlie the distinct behaviors these stimuli evoke during SCS conditioning. To define the key factors responsible for the topography of behavioral responding in this paradigm, we systematically varied CS-US temporal relationships and properties of SCS component stimuli during or following conditioning. We found that when presented at equal sound pressure levels( SPL), white noise elicits greater active defensive behavior than tones, irrespective of stimulus order during conditioning. Following standard tone-white noise SCS conditioning, each stimulus was also capable on its own of evoking either conditioned freezing or flight, according to SPL. Furthermore, when presented at equivalent SPL, white noise promoted greater arousal and simple locomotor responding than pure tone stimuli, even in the absence of any prior conditioning. Together, these data argue that stimulus salience is the major factor determining the form of conditioned responses during SCS conditioning.\nDiscussion:\nIn conclusion, we found that audio frequency properties strongly influence the defensive behaviors elicited by SCS fear conditioned auditory stimuli. Escape behaviors were most potently triggered by stimuli that contain frequencies to which mouse hearing is most sensitive, an effect that was independent of the order in which auditory stimuli were presented during learning. In addition, pure tones that elicit freezing at typical experimental sound pressure levels can promote conditioned escape when presented at higher levels. These data argue that stimulus salience, not temporal proximity to the US, is the primary means by which mice assess imminence and engage appropriate defensive strategies in the SCS paradigm. This would appear to be similar mechanistically to how mice respond to innately threatening visual stimuli, where the probability and intensity of escape behaviors scale with visual stimulus salience( Evans et al., 2018). An implication of this work is the critical need to consider the behavioral sensitivity of experimental subjects to auditory stimuli of different frequencies. Psychophysical studies have demonstrated that all species have a particular range of frequencies that they hear well( i. e. which are audible at 10 dB); stimuli outside of this range may need to presented at substantially higher SPL in order to be efficiently detected. In addition, although most laboratory animals exhibit overlap in their hearing ranges, there can be significant differences in their sensitivity to particular frequencies, even among closely related species. For example, whereas the 10 dB threshold includes frequencies ranging from ~5–40 kHz in rats, this range is very narrow in mice and limited to frequencies close to 16 kHz( Heffner and Heffner, 2007). Differences can also exist across mouse strains and between different ages of the same strain. For example, C57BL/6J mice undergo hearing-loss induced plasticity that by 5 months of age results in loss of responsivity to high frequency tones( >20 kHz) with concomitantly enhanced behavioral sensitivity to middle( 12–16 kHz) but not low( 4–8 kHz) frequency stimuli( Carlson and Willott, 1996; Willott et al., 1994). Moreover, certain frequencies may be innately aversive in rodents: rats emit and respond defensively to alarm vocalizations near 20 kHz( Beckett et al., 1996; Blanchard et al., 1992; Cuomo et al., 1992), and 17–20 kHz ultrasonic sweeps can elicit robust freezing and flight behaviors in mice( Evans et al., 2018; Mongeau et al., 2003). White noise stimuli, which are both aperiodic and include 17–20 kHz frequencies, may thus be uniquely salient to mice under conditions of impending potential threats due to recruitment of dedicated defensive circuits tuned to innately threatening auditory stimuli. Indeed, in conventional fear conditioning to a simple CS composed of a single auditory stimulus, significantly more flight behavior was evoked by a white noise CS than a tone CS( Fadok et al., 2017). Importantly, discrimination studies that employ multiple auditory cues could be complicated both by variations in the ability of subjects to perceive different frequencies as well as potential innate valence associated with certain stimuli. For example, aversively conditioning a high intensity US with a 5 kHz CS+ followed by a generalization test using a higher salience CS- such as white noise could yield misleading conclusions if subjects exhibit escape behaviors to the CS- and, as is common, freezing is the only metric used to assess cue responsivity. Such confounds may be best avoided by assaying discrimination using tasks which measure behavioral responses to distinct patterns of a single, constant intensity sensory stimulus( e. g. drifting visual gratings of different orientation[Burgess et al., 2016]). Interpretation of discrimination studies that employ auditory stimuli would benefit from counterbalancing assignment of CS+ and CS- stimuli( Sanford et al., 2017), and also from use of stimuli at frequencies and SPL that are detectable but do not trigger active fear behaviors. Severe stress can result in persistent generalization or sensitization of threat responding, such that stimuli which normally elicit little to no response come to evoke robust defensive behaviors. For example, in the stress-enhanced fear learning( SEFL) model, exposure to inescapable shocks in the absence of auditory stimuli results in nonassociative freezing to white noise in a novel context on the following day( Perusini et al., 2016). Although we observed white noise-elicited escape behavior in group 3( ‘gap’, Figure 1F and O), these responses cannot be attributed directly to generalization as it remains possible that some CS-US association formed despite the 60 s gap( i. e. via trace conditioning). Thus, the extent to which white noise can nonassociatively elicit active defensive behavior will need to be determined in future experiments where training is performed with a US presented in the complete absence of CS stimuli, as done in the SEFL model. Previous work provided behavioral and neurophysiological evidence that SCS fear conditioned tone and white noise stimuli acutely elicit distinct defensive states indicative of different points along the threat imminence continuum( Fadok et al., 2017). We have found that these defensive states track with the frequency and intensity of the conditioned stimuli, not order of CS presentation during learning. This argues that threat imminence in this model is determined primarily via the salience of threat-predictive auditory stimuli which, together with recent experience( Mongeau et al., 2003) and current fear levels, determines the threshold for switching from freezing to flight. Our results contrast with those of another study( Dong et al., 2019), which reported that training with a ‘reversed SCS’( white noise-tone-US) reverses the behaviors elicited( i. e. mice freeze to the WN but exhibit flight to the tones). As the experimental procedures used in both studies were essentially the same, the explanation for the discrepant results is presently unclear. However, while the B6J mice used here were obtained from JAX, the mice used in Dong et al. were of undefined substrain( ‘C57Bl/6’) and obtained from a different vendor. Therefore, it is possible that different mouse strains utilize distinct neural processes to assess threat imminence. Future work will be required to determine if this is indeed the case and if so, the mechanistic underpinnings of such differences. Although reversing the order of the white noise and tone stimuli during training did not qualitatively alter the type of behaviors elicited by the CSs, this switch did have a quantitative effect. Specifically, white noise elicited significantly less escape behavior when it preceded rather than followed the tone during training( Figure 1). One potential explanation for this result is that compound stimuli which increase in salience from CS1 to CS2 are more naturalistic and produce higher arousal levels and greater learning than the reverse order. Indeed, tonal stimuli which sweep from low up to high frequencies are rated by human observers as more alarming than high to low sweeps( Catchpole et al., 2004). Similarly, frequency upsweeps are associated with elevation of attention and arousal, whereas downsweeps are thought to have a calming effect( Owren and Rendall, 2001). Use of compound stimuli that either increase or decrease in salience from CS1 to CS2 might thus have opposing influences on arousal, resulting in either optimal or suboptimal states for sensory signal processing and learning( Aston-Jones and Cohen, 2005; McGinley et al., 2015; Yerkes and Dodson, 1908). Finally, we note that conditioned responses exhibited at the onset of a CS can differ qualitatively from those displayed near CS offset( Holland, 1980). It thus remains possible that temporal factors make some contribution to defensive responding in SCS conditioning. Given the potent influence of stimulus salience, resolution of this issue will likely require the use of a SCS comprised of distinct component stimuli that can be clearly discriminated and yet are also matched for salience.", "role": "user" }, { "content": "If you notice the skies above you becoming darker , your first thought might be to seek shelter . Experience will have taught you that darkening skies are often a sign of an approaching storm . Learning to recognise changes that occur prior to an unpleasant event can help us avoid danger . But this is not the only strategy people can use to predict when something bad is about to happen . Another option is to use the intensity , or salience , of sensory information . Soldiers fighting on the front line , for example , might rely on the loudness of enemy voices or vehicles to judge how close an advancing enemy is . This information will help them decide when to retreat . Different brain processes are active when individuals use each of these two strategies to predict when an upcoming event will occur . One approach to study these processes is to use a technique called “SCS conditioning” . This involves exposing mice to two sounds , followed by a mild electric shock administered to the feet . The first sound is a pure tone; the second is a burst of white noise . After repeated trials , mice begin to show distinct responses to the two sounds . They freeze in response to the tone but run away upon hearing the white noise . These responses parallel behaviors seen in the wild . When mice detect a distant predator , they freeze to avoid detection . But if the predator comes too close for the mice to avoid being spotted , they instead try to flee . Some have argued that in the SCS task , mice learn that the white noise predicts an imminent shock . The mice therefore flee as soon as they hear it . By contrast , they learn that the tone predicts a delayed shock and therefore choose to freeze instead . However , by tweaking the SCS procedure , Hersman et al . now show that even if the white noise occurs before the tone , it is still more likely than the tone to trigger an escape response . In fact , mice are more reactive to white noise than tones even if the sounds are never paired with shocks . This suggests that mice find white noise naturally more noticeable than tones . Moreover , Hersman et al . show that tones can also trigger escape responses if they are sufficiently intense . Together these results suggest that mice use the intensity of the stimuli – rather than the length of time between each stimulus and the shock – to decide whether to freeze or flee . People with anxiety disorders often show exaggerated responses to things that do not pose a genuine threat . At present the pathways in the brain that are responsible for these excessive reactions are unclear . The results of Hersman et al . will aid research into the brain circuits that detect , assess and respond to threats . Understanding these circuits could in the future lead to better treatments for anxiety disorders .", "role": "assistant" } ]

[ { "content": "You are provided with the abstract of a scientific paper and the abstracts of the papers it references. Your task is to write a Related Work section for the main paper. This section should concisely summarize and integrate the key points from the cited abstracts, reflecting how they relate to the main paper's contributions and context. In your summary, use numerical citation markers like [1], [2], etc., to refer to the corresponding papers.\n\nMain Abstract:\nThis paper proposes an efficient method for computing selected generalized eigenpairs of a sparse Hermitian definite matrix pencil (A, B). Based on Zolotarev's best rational function approximations of the signum function and conformal mapping techniques, we construct the best rational function approximation of a rectangular function supported on an arbitrary interval. This new best rational function approximation is applied to construct spectrum filters of (A, B). Combining fast direct solvers and the shift-invariant GMRES, a hybrid fast algorithm is proposed to apply spectral filters efficiently. Compared to the state-of-the-art algorithm FEAST, the proposed rational function approximation is proved to be optimal among a larger function class, and the numerical implementation of the proposed method is also faster. The efficiency and stability of the proposed method are demonstrated by numerical examples from computational chemistry.\n\nCited Abstract(s):\n[1]: \n\n[2]: The FEAST method for solving large sparse eigenproblems is equivalent to subspace iteration with an approximate spectral projector and implicit orthogonalization. This relation allows to characterize the convergence of this method in terms of the error of a certain rational approximant to an indicator function. We propose improved rational approximants leading to FEAST variants with faster convergence, in particular, when using rational approximants based on the work of Zolotarev. Numerical experiments demonstrate the possible computational savings especially for pencils whose eigenvalues are not well separated and when the dimension of the search space is only slightly larger than the number of wanted eigenvalues. The new approach improves both convergence robustness and load balancing when FEAST runs on multiple search intervals in parallel.\n\n[3]: \n\n[4]: A new numerical algorithm for solving the symmetric eigenvalue problem is presented. The technique deviates fundamentally from the traditional Krylov subspace iteration based techniques (Arnoldi and Lanczos algorithms) or other Davidson-Jacobi techniques, and takes its inspiration from the contour integration and density matrix representation in quantum mechanics. It will be shown that this new algorithm - named FEAST - exhibits high efficiency, robustness, accuracy and scalability on parallel architectures. Examples from electronic structure calculations of Carbon nanotubes (CNT) are presented, and numerical performances and capabilities are discussed.\n\n[5]: \n\n[6]: Calculating portions of eigenvalues and eigenvectors of matrices or matrix pencils has many applications. An approach to this calculation for Hermitian problems based on a density matrix has been proposed in 2009 and a software package called FEAST has been developed. The density-matrix approach allows FEAST's implementation to exploit a key strength of modern computer architectures, namely, multiple levels of parallelism. Consequently, the software package has been well received and subsequently commercialized. A detailed theoretical analysis of Hermitian FEAST has also been established very recently. This paper generalizes the FEAST algorithm and theory, for the first time, to tackle non-Hermitian problems. Fundamentally, the new algorithm is basic subspace iteration or Bauer bi-iteration, except applied with a novel accelerator based on Cauchy integrals. The resulting algorithm retains the multi-level parallelism of Hermitian FEAST, making it a valuable new tool for large-scale computational science and engineering problems on leading-edge computing platforms.\n\n[7]: New methods are proposed for the numerical evaluation of @math or @math , where @math is a function such as @math or @math with singularities in @math and @math is a matrix with eigenvalues on or near @math . The methods are based on combining contour integrals evaluated by the periodic trapezoid rule with conformal maps involving Jacobi elliptic functions. The convergence is geometric, so that the computation of @math is typically reduced to one or two dozen linear system solves, which can be carried out in parallel.\n\n[8]: Abstract Solving (nonlinear) eigenvalue problems by contour integration, requires an effective discretization for the corresponding contour integrals. In this paper it is shown that good rational filter functions can be computed using (nonlinear least squares) optimization techniques as opposed to designing those functions based on a thorough understanding of complex analysis. The conditions that such an effective filter function should satisfy, are derived and translated in a nonlinear least squares optimization problem solved by optimization algorithms from Tensorlab. Numerical experiments illustrate the validity of this approach.", "role": "user" }, { "content": "Many rational filters in the literature were constructed by discretizing the contour integral on the complex plane, with an appropriate quadrature rule (e.g., the Gauss-Legendre quadrature rule [4] , the trapezoidal quadrature rule [6] [3] , and the Zolotarev quadrature rule [2] ). Here @math is a closed contour on the complex plane intersecting the real axis at @math and @math with all desired eigenvalues inside @math and other eigenvalues outside (See Figure (left) for an example). Suppose @math and @math are the quadrature points and weights in the discretization of the contour @math , respectively, the contour integral is discretized as a rational function where @math , and @math for @math . Some other methods advanced with conformal maps [7] [5] and optimization [8] [1] can also provide good rational filters.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"UnapprovedDrug\", \"Brand\", \"DrugGroup\", \"Drug\"].\n\nPlease return the output as a JSON object of the format: {\"Brand\": [\"Aspirin\", ...], \"DrugGroup\": [\"Salicylate\", ...], \"Drug\": [\"Phenobarbital\", ...], \"UnapprovedDrug\": [\"Heroin\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nSince Zarontin (ethosuximide) may interact with concurrently administered antiepileptic drugs, periodic serum level determinations of these drugs may be necessary (eg, ethosuximide may elevate phenytoin serum levels and valproic acid has been reported to both increase and decrease ethosuximide levels).", "role": "user" }, { "content": "{\"Brand\": [\"Zarontin\"], \"Drug\": [\"valproic acid\", \"ethosuximide\", \"phenytoin\"], \"DrugGroup\": [\"antiepileptic drugs\"], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is taxilin a cancer marker?\n\nContext: Αlpha-Taxilin (α-Taxilin) has been found as one of the novel, significantly up regulated protein in RA\nExpression of α-taxilin has been implicated in the development of human glioblastoma, hepatocellular carcinoma and renal cell carcinoma.\nα-Taxilin, a binding partner of the syntaxin family, is a candidate tumor marker.\nExpression of α-taxilin in hepatocellular carcinoma correlates with growth activity and malignant potential of the tumor.", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "content": "You will be shown an excerpt from a computer science research paper, followed by a question about the paper. Please answer the question given the context. Do not include any text in your response other than the answer.\n\nContext: Information maximization is a principal approach to learn representation and to avoid collapse.DeepInfoMax Hjelm et al. (2019) propose the MI maximization between the local and global views for representation learning; the existence of negative pairs prevents training toward the trivial solution.BarlowTwins Zbontar et al. (2021) and W-MSE Ermolov et al. (2021) address the collapsing with redundancy reduction that indirectly maximizes the content information of embedding vectors.Among clustering-based approaches, IIC Ji et al. (2019) maximizes the MI between the embedding codes to enable representation learning;similar to ours, TWIST Feng et al. (2021) proposes combining the MI between the data and class prediction as a negative loss term with an augmentation invariance consistency loss.Both IIC and TWIST use the MI as a loss function and directly optimize their model parameters with gradient descent of the loss.However, the direct optimization of MI terms by updating model parameters often leads to a sub-optimal solution Feng et al. (2021); TWIST copes with this issue by appending the normalization layer before softmax and introducing an additional self-labeling stage.In contrast, MIRA addresses the difficulty of MI maximization in a principled way via explicit optimization.\n\nQuestion: Why does the performance increase of TWIST deteriorates when the epoch further increases over 400?", "role": "user" }, { "content": "The direct optimization constraint used in TWIST can lead to sub-optimal solution", "role": "assistant" } ]

[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is tirilazad effective for treatment of aneurysmal subarachnoid haemorrhage?\n\nContext: There was no significant difference between the two groups at the end of follow up for the primary outcome, death (odds ratio (OR) 0.89, 95% confidence interval (CI) 0.74 to 1.06), or in poor outcome (death, vegetative state or severe disability) (OR 1.04, 95% CI 0.90 to 1.21). During the treatment period, fewer patients developed delayed cerebral ischaemia in the tirilazad group than in the control group (OR 0.80, 95% CI 0.69 to 0.93). Subgroup analyses did not demonstrate any significant difference in effects of tirilazad on clinical outcomes.\nAUTHORS' CONCLUSIONS: There is no evidence that tirilazad, in addition to nimodipine, reduces mortality or improves poor outcome in patients with aneurysmal SAH.\nThis clinical trial suggest that tirilazad mesylate, at a dosage of 6 mg/kg/day, improves overall outcome in aneurysmal subarachnoid hemorrhage patients.\nTirilazad is ineffective.There are many possible successful treatment options for preventing vasospasm, delayed ischemic neurologic deficits, and poor neurologic outcome following aneurysmal subarachnoid hemorrhage; however, further multicenter RCTs need to be performed to determine if there is a significant benefit from their use\nFindings from previous multicenter clinical trials have suggested that tirilazad mesylate, a synthetic nonhormonal 21-aminosteroid, might be effective in preventing delayed cerebral ischemia following subarachnoid hemorrhage (SAH).\nThis clinical trial suggest that tirilazad mesylate, at a dosage of 6 mg/kg/day, improves overall outcome in aneurysmal subarachnoid hemorrhage patients.", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "content": "You will be presented with a paragraph from a COVID-19 literature. Your task is to classify the topics of this piece of text by choosing from the following categories:\n\n- Epidemic Forecasting: The content relates to predictions about the spread of COVID-19.\n- Treatment: The paragraph discusses therapeutic methods or medication for COVID-19.\n- Prevention: The content covers measures to prevent the spread of COVID-19.\n- Mechanism: The paragraph explains the biological mechanisms of the virus.\n- Case Report: The content is a report of a COVID-19 case.\n- Transmission: The paragraph discusses how COVID-19 is transmitted.\n- Diagnosis: The content is about diagnosing COVID-19 in individuals.\n\nYour classification should be provided as an element within a JSON array. The array should be formatted with topics enclosed in double quotes and separated by commas, following the JSON format, for example: [\"Topic1\", \"Topic2\", ...]. Include all applicable categories within the array. \nYour output should be a valid JSON array, and no additional text should be included in your response.\n\nArticle:\n\nObjectives: The Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection, also known as COVID-19 pandemic has caused an alarming situation worldwide. Since the first detection, in December 2019, there have been no effective drug therapy options for treating the SARS-CoV-2 pandemic. However, healthcare professionals are using chloroquine, hydroxychloroquine, remdesivir, convalescent plasma and some other options of treatments. This study aims to compare the biological, molecular, pharmacological, and clinical characteristics of these three treatment modalities for SARS-COV-2 infections, Chloroquine and Hydroxychloroquine, Convalescent Plasma, and Remdesivir. Methods: A search was conducted in the \"Institute of Science Information (ISI)-Web of Science, PubMed, EMBASE, ClinicalTrials.gov, Cochrane Library databases, Scopus, and Google Scholar\" for peer reviewed, published studies and clinical trials through July 30, 2020. The search was based on keywords \"COVID-19\" SARS-COV-2, chloroquine, hydroxychloroquine, convalescent plasma, remdesivir and treatment modalities. Results: As of July 30, 2020, a total of 36,640 relevant documents were published. From them 672 peer reviewed, published articles, and clinical trials were screened. We selected 17 relevant published original articles and clinical trials: 05 for chloroquine and/or hydroxychloroquine with total sample size (n=220), 05 for Remdesivir (n=1,781), and 07 for Convalescent Plasma therapy (n=398), with a combined total sample size (n=2,399). Based on the available data, convalescent plasma therapy showed clinical advantages in SARS-COV-2 patients. Conclusions: All three treatment modalities have both favorable and unfavorable characteristics, but none showed clear evidence of benefit for early outpatient disease or prophylaxis. Based on the current available data, convalescent plasma therapy appears to show clinical advantages for inpatient use. In the future, ongoing large sample size randomized controlled clinical trials may further clarify the comparative efficacy and safety of these three treatment classes, to conclusively determine whom to treat with which drug and when to treat them.", "role": "user" }, { "content": "[\"Treatment\"]", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nAge greater than 18 \nPlanned thoracoscopy with low probability(by surgeon estimate) of conversion to open procedure", "role": "user" }, { "content": "{\"Condition\": [], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [\"Age\"], \"Procedure\": [\"thoracoscopy\"], \"Qualifier\": [\"low probability(by surgeon estimate) of conversion to open procedure\"], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [\"greater than 18\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nRegeneration of mandibular ameloblastoma defect with the help of autologous dental pulp stem cells and buccal pad of fat stromal vascular fraction Ameloblastoma is benign odontogenic tumor, which is locally aggressive in behavior. Till date, the treatment of choice is resection and reconstruction using a variety of modalities. Inadequate resection may lead to many complications such as bone deformity and dysfunction. This report is about a 14- year-old male with ameloblastoma treated with autologous dental pulp stem cells (DPSCs) and stromal vascular fraction (SVF) and evidence of bone regeneration. Marsupialization was performed; tooth was extracted and sent for DPSC cultivation. On the day of surgery, SVF was processed from buccal pad of fat, and platelet-rich fibrin (PRF) was prepared from patient's peripheral blood. During the procedure, labial plate resection and curating of tumor lining were done. After which, a mesh packed with SyboGraft T-plug, prepared SVF, DPSCs, and PRF were placed over lingual cortex and pressure dressing was done. After the 1(st) month of surgery the postoperative course was uneventful, the wound shrinkage led to exposure of mesh in the intraoral region. Removal of exposed mesh was done. The correction surgery with removal of part of mesh and primary closure was achieved with SyboGraft plug, SVF and PRF. Enhanced bone formation was seen in post-operative OPG and CT Scan after 10(th) month. In this article, we propose an innovative approach to manage these cases by using a combination of autologous DPSC and buccal pad of fat SVF to regenerate a mandibular defect left by the resection of an ameloblastoma with 1.5 year follow-up. We were able to demonstrate bone regeneration using this technique with no recurrence of tumor.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"dental pulp\", \"DPSCs\", \"cortex\", \"buccal pad of fat\", \"labial plate\", \"tooth\", \"stem cells\", \"lingual\", \"bone deformity\", \"DPSC\"], \"Bacterium\": [], \"BiologicFunction\": [\"mandibular ameloblastoma defect\", \"tumor lining\", \"Ameloblastoma\", \"benign odontogenic tumor\", \"bone regeneration\", \"recurrence of tumor\", \"Regeneration\", \"complications\", \"ameloblastoma\", \"regenerate\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [\"patient\\u0027s peripheral blood\", \"PRF\", \"platelet-rich fibrin\"], \"BodySystem\": [], \"Chemical\": [\"stromal vascular fraction\", \"SVF\", \"SyboGraft plug\", \"SyboGraft T-plug\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"locally aggressive in behavior\", \"Enhanced bone formation\", \"mandibular defect\"], \"Food\": [], \"HealthCareActivity\": [\"extracted\", \"primary closure\", \"reconstruction\", \"surgery\", \"OPG\", \"treatment\", \"resection\", \"procedure\", \"follow-up\", \"Marsupialization\", \"CT Scan\"], \"InjuryOrPoisoning\": [\"wound\"], \"IntellectualProduct\": [\"innovative approach\", \"report\"], \"MedicalDevice\": [\"pressure dressing\", \"mesh\", \"exposed mesh\"], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"cultivation\"], \"SpatialConcept\": [\"part of\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nPerformance of loop-mediated isothermal amplification (LAMP) for the diagnosis of malaria among malaria suspected pregnant women in Northwest Ethiopia Malaria is a major public health problem and an important cause of maternal and infant morbidity in sub-Saharan Africa, including Ethiopia. Early and accurate diagnosis of malaria with effective treatment is the best strategy for prevention and control of complications during pregnancy and infant morbidity and mortality. However, laboratory diagnosis has relied on the identification of malaria parasites and parasite antigens in peripheral blood using Giemsa-stained microscopy or rapid diagnostic tests (RDTs) which lack analytical and clinical sensitivity. The aim of this study was to evaluate the performance of loop-mediated isothermal amplification (LAMP) for the diagnosis of malaria among malaria suspected pregnant women in Northwest Ethiopia. A cross sectional study was conducted from January to April 2016. Pregnant women (n = 87) suspected of having malaria at six health centres were enrolled. A venous blood sample was collected from each study subject, and analysed for Plasmodium parasites by microscopy, RDT, and LAMP. Diagnostic accuracy outcome measures (sensitivity, specificity, predictive values, and Kappa scores) of microscopy, RDT and LAMP were compared to nested polymerase chain reaction (nPCR) as the gold standard. Specimen processing and reporting times were documented. Using nPCR as the gold standard technique, the sensitivity of microscopy and RDT was 90 and 70%, and the specificity was 98.7 and 97.4%, respectively. LAMP assay was 100% sensitive and 93.5% specific compared to nPCR. This study showed higher sensitivity of LAMP compared to microscopy and RDT for the detection of malaria in pregnancy. Increased sensitivity and ease of use with LAMP in point-of-care testing for malaria in pregnancy was noted. LAMP warrants further evaluation in intermittent screening and treatment programmes in pregnancy.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"Malaria\", \"complications\", \"pregnancy\", \"malaria\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [\"venous blood sample\", \"peripheral blood\"], \"BodySystem\": [], \"Chemical\": [\"antigens\"], \"ClinicalAttribute\": [], \"Eukaryote\": [\"Plasmodium\", \"parasites\", \"parasite\"], \"Finding\": [\"diagnosis\", \"problem\"], \"Food\": [], \"HealthCareActivity\": [\"LAMP\", \"Early\", \"treatment\", \"rapid diagnostic tests\", \"detection\", \"documented\", \"Giemsa-stained microscopy\", \"Specimen processing\", \"prevention\", \"evaluation\", \"point-of-care testing\", \"reporting\", \"RDTs\", \"screening\", \"laboratory diagnosis\", \"microscopy\", \"evaluate\", \"RDT\", \"loop-mediated isothermal amplification\", \"assay\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [\"health centres\"], \"PopulationGroup\": [\"public\", \"study subject\", \"pregnant women\", \"Pregnant women\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"clinical sensitivity\", \"nPCR\", \"analysed\", \"study\", \"nested polymerase chain reaction\", \"cross sectional study\"], \"SpatialConcept\": [\"Northwest\", \"sub-Saharan Africa\", \"Ethiopia\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "You will be shown sections from a scientific research paper, together with a question about the paper. This is an extractive question-answering task, where you must find and extract relevant text spans directly from the paper to answer the question. Your response should strictly be a `json` object with two fields:\n\n\"answer\": An array of strings extracted directly from the paper which, collectively, answer the question.\n\"evidence\": An array of strings. Each should be an excerpt from the paper, in which one or more of the extracted answers can be found.\n\nFor example, for the question \"What baselines did the authors compare against?\", a sample response might be:\n{\n \"answer\": [\"BERT\", \"RoBERTa\"],\n \"evidence\": [\"In our experiments, we compare the performance of our model against BERT and RoBERTa.\"]\n}\n\nDo not include any text in your response other than the json.\n\nIf the question is unanswerable given the provided excerpts, respond with the single word \"null\".\n\nPaper: Learning Rare Word Representations using Semantic Bridging\n\nWe propose a methodology that adapts graph embedding techniques (DeepWalk (Perozzi et al., 2014) and node2vec (Grover and Leskovec, 2016)) as well as cross-lingual vector space mapping approaches (Least Squares and Canonical Correlation Analysis) in order to merge the corpus and ontological sources of lexical knowledge. We also perform comparative analysis of the used algorithms in order to identify the best combination for the proposed system. We then apply this to the task of enhancing the coverage of an existing word embedding's vocabulary with rare and unseen words. We show that our technique can provide considerable extra coverage (over 99%), leading to consistent performance gain (around 10% absolute gain is achieved with w2v-gn-500K cf.\\S 3.3) on the Rare Word Similarity dataset.\n\nIntroduction\nThe prominent model for representing semantics of words is the distributional vector space model BIBREF2 and the prevalent approach for constructing these models is the distributional one which assumes that semantics of a word can be predicted from its context, hence placing words with similar contexts in close proximity to each other in an imaginary high-dimensional vector space. Distributional techniques, either in their conventional form which compute co-occurrence matrices BIBREF2 , BIBREF3 and learn high-dimensional vectors for words, or the recent neural-based paradigm which directly learns latent low-dimensional vectors, usually referred to as embeddings BIBREF4 , rely on a multitude of occurrences for each individual word to enable accurate representations. As a result of this statistical nature, words that are infrequent or unseen during training, such as domain-specific words, will not have reliable embeddings. This is the case even if massive corpora are used for training, such as the 100B-word Google News dataset BIBREF5 .\nRecent work on embedding induction has mainly focused on morphologically complex rare words and has tried to address the problem by learning transformations that can transfer a word's semantic information to its morphological variations, hence inducing embeddings for complex forms by breaking them into their sub-word units BIBREF6 , BIBREF7 , BIBREF8 . However, these techniques are unable to effectively model single-morpheme words for which no sub-word information is available in the training data, essentially ignoring most of the rare domain-specific entities which are crucial in the performance of NLP systems when applied to those domains.\nOn the other hand, distributional techniques generally ignore all the lexical knowledge that is encoded in dictionaries, ontologies, or other lexical resources. There exist hundreds of high coverage or domain-specific lexical resources which contain valuable information for infrequent words, particularly in domains such as health. Here, we present a methodology that merges the two worlds by benefiting from both expert-based lexical knowledge encoded in external resources as well as statistical information derived from large corpora, enabling vocabulary expansion not only for morphological variations but also for infrequent single-morpheme words. The contributions of this work are twofold: (1) we propose a technique that induces embeddings for rare and unseen words by exploiting the information encoded for them in an external lexical resource, and (2) we apply, possibly for the first time, vector space mapping techniques, which are widely used in multilingual settings, to map two lexical semantic spaces with different properties in the same language. We show that a transfer methodology can lead to consistent improvements on a standard rare word similarity dataset.\n\nMethodology\nWe take an existing semantic space INLINEFORM0 and enrich it with rare and unseen words on the basis of the knowledge encoded for them in an external knowledge base (KB) INLINEFORM1 . The procedure has two main steps: we first embed INLINEFORM2 to transform it from a graph representation into a vector space representation (§ SECREF2 ), and then map this space to INLINEFORM3 (§ SECREF7 ). Our methodology is illustrated in Figure 1.\nIn our experiments, we used WordNet 3.0 BIBREF9 as our external knowledge base INLINEFORM0 . For word embeddings, we experimented with two popular models: (1) GloVe embeddings trained by BIBREF10 on Wikipedia and Gigaword 5 (vocab: 400K, dim: 300), and (2) w2v-gn, Word2vec BIBREF5 trained on the Google News dataset (vocab: 3M, dim: 300).\n\nKnowledge Base Embedding\nOur coverage enhancement starts by transforming the knowledge base INLINEFORM0 into a vector space representation that is comparable to that of the corpus-based space INLINEFORM1 . To this end, we use two techniques for learning low-dimensional feature spaces from knowledge graphs: DeepWalk and node2vec. DeepWalk uses a stream of short random walks in order to extract local information for a node from the graph. By treating these walks as short sentences and phrases in a special language, the approach learns latent representations for each node. Similarly, node2vec learns a mapping of nodes to continuous vectors that maximizes the likelihood of preserving network neighborhoods of nodes. Thanks to a flexible objective that is not tied to a particular sampling strategy, node2vec reports improvements over DeepWalk on multiple classification and link prediction datasets. For both these systems we used the default parameters and set the dimensionality of output representation to 100. Also, note than nodes in the semantic graph of WordNet represent synsets. Hence, a polysemous word would correspond to multiple nodes. In our experiments, we use the MaxSim assumption of BIBREF11 in order to map words to synsets.\nTo verify the reliability of these vector representations, we carried out an experiment on three standard word similarity datasets: RG-65 BIBREF12 , WordSim-353 similarity subset BIBREF13 , and SimLex-999 BIBREF14 . Table TABREF5 reports Pearson and Spearman correlations for the two KB embedding techniques (on WordNet's graph) and, as baseline, for our two word embeddings, i.e. w2v-gn and GloVe. The results are very similar, with node2vec proving to be slightly superior. We note that the performances are close to those of state-of-the-art WordNet approaches BIBREF15 , which shows the efficacy of these embedding techniques in capturing the semantic properties of WordNet's graph.\n\nSemantic Space Transformation\nOnce we have the lexical resource INLINEFORM0 represented as a vector space INLINEFORM1 , we proceed with projecting it to INLINEFORM2 in order to improve the word coverage of the latter with additional words from the former. In this procedure we make two assumptions. Firstly, the two spaces provide reliable models of word semantics; hence, the relative within-space distances between words in the two spaces are comparable. Secondly, there exists a set of shared words between the two spaces, which we refer to as semantic bridges, from which we can learn a projection that maps one space into another.\nAs for the mapping, we used two techniques which are widely used for the mapping of semantic spaces belonging to different languages, mainly with the purpose of learning multilingual semantic spaces: Least squares BIBREF16 , BIBREF17 and Canonical Correlation Analysis BIBREF18 , BIBREF19 . These models receive as their input two vector spaces of two different languages and a seed lexicon for that language pair and learn a linear mapping between the two spaces. Ideally, words that are semantically similar across the two languages will be placed in close proximity to each other in the projected space. We adapt these models to the monolingual setting and for mapping two semantic spaces with different properties. As for the seed lexicon (to which in our setting we refer to as semantic bridges) in this monolingual setting, we use the set of monosemous words in the vocabulary which are deemed to have the most reliable semantic representations.\nSpecifically, let INLINEFORM0 and INLINEFORM1 be the corpus and KB semantic spaces, respectively, and INLINEFORM2 and INLINEFORM3 be their corresponding subset of semantic bridges, i.e., words that are monosemous according to the WordNet sense inventory. Note that INLINEFORM4 and INLINEFORM5 are vector matrices that contain representations for the same set of corresponding words, i.e., INLINEFORM6 . LS views the problem as a multivariate regression and learns a linear function INLINEFORM7 (where INLINEFORM8 and INLINEFORM9 are the dimensionalities of the KB and corpus spaces, respectively) on the basis of the following INLINEFORM10 -regularized least squares error objective and typically using stochastic gradient descent: DISPLAYFORM0 \nThe enriched space INLINEFORM0 is then obtained as a union of INLINEFORM1 and INLINEFORM2 . CCA, on the other hand, learns two distinct linear mappings INLINEFORM3 and INLINEFORM4 with the objective of maximizing the correlation between the dimensions of the projected vectors INLINEFORM5 and INLINEFORM6 : DISPLAYFORM0 \nIn this case, INLINEFORM0 is the union of INLINEFORM1 and INLINEFORM2 . In the next section we first compare different KB embedding and transformation techniques introduced in this section and then apply our methodology to a rare word similarity task.\n\nEvaluation benchmark\nTo verify the reliability of the transformed semantic space, we propose an evaluation benchmark on the basis of word similarity datasets. Given an enriched space INLINEFORM0 and a similarity dataset INLINEFORM1 , we compute the similarity of each word pair INLINEFORM2 as the cosine similarity of their corresponding transformed vectors INLINEFORM3 and INLINEFORM4 from the two spaces, where INLINEFORM5 and INLINEFORM6 for LS and INLINEFORM7 and INLINEFORM8 for CCA. A high performance on this benchmark shows that the mapping has been successful in placing semantically similar terms near to each other whereas dissimilar terms are relatively far apart in the space. We repeat the computation for each pair in the reverse direction.\n\nComparison Study\nFigure FIGREF1 shows the performance of different configurations on our three similarity datasets and for increasing sizes of semantic bridge sets. We experimented with four different configurations: two KB embedding approaches, i.e. DeepWalk and node2vec, and two mapping techniques, i.e. LS and CCA (cf. § SECREF2 ). In general, the optimal performance is reached when around 3K semantic bridges are used for transformation. DeepWalk and node2vec prove to be very similar in their performance across the three datasets. Among the two transformation techniques, CCA consistently outperforms LS on all three datasets when provided with 1000 or more semantic bridges (with 500, however, LS always has an edge). In the remaining experiments we only report results for the best configuration: node2vec with CCA. We also set the size of semantic bridge set to 5K.\n\nRare Word Similarity\nIn order to verify the reliability of our technique in coverage expansion for infrequent words we did a set of experiments on the Rare Word similarity dataset BIBREF6 . The dataset comprises 2034 pairs of rare words, such as ulcerate-change and nurturance-care, judged by 10 raters on a [0,10] scale. Table TABREF15 shows the results on the dataset for three pre-trained word embeddings (cf. § SECREF2 ), in their initial form as well as when enriched with additional words from WordNet.\nAmong the three initial embeddings, w2v-gn-500K provides the lowest coverage, with over 20% out-of-vocabulary pairs, whereas GloVe has a similar coverage to that of w2v-gn despite its significantly smaller vocabulary (400K vs. 3M). Upon enrichment, all the embeddings attain near full coverage (over 99%), thanks to the vocabulary expansion by rare words in WordNet. The enhanced coverage leads to consistent performance improvements according to both Pearson and Spearman correlations. The best performance gain is achieved for w2v-gn-500K (around 10% absolute gain) which proves the efficacy of our approach in inducing embeddings for rare words. The improvements are also statistically significant (p < 0.05) according to conducted one tailed t-test BIBREF20 , showing that the coverage enhancement could lead to improved performance even if lower-performing KB embedding and transformation are used.\n\nRelated Work\nThe main focus of research in embedding coverage enhancement has been on the morphologically complex forms BIBREF21 . BIBREF6 used recursive neural networks (RNNs) and neural language models in order to induce embeddings for morphologically complex words from their morphemes whereas BIBREF22 adapted phrase composition models for this purpose. BIBREF7 proposed a different model based on log-bilinear language models, mainly to have a compositional vector-based morphological representation that can be easily integrated into a machine translation decoder. These models often utilize a morphological segmentation toolkit, such as Morfessor BIBREF23 , in order to break inflected words into their morphological structures and to obtain segmentations for words in the vocabulary. BIBREF8 put forward a technique that does not rely on any external morphological analyzer and instead, induces morphological rules and transformations, represented as vectors in the same embedding space. Based on these rules a morphological graph is constructed and representations are inferred by analyzing morphological transformations in the graph. However, all these techniques fall short in inducing representations for single-morpheme words that are not seen frequently during training as they base their modeling on information available on sub-word units. In contrast, our transformation-based model can also induce embeddings for single-morpheme words that are infrequent or unseen in the training data, such as domain-specific entities.\n\nConclusions and Future Work\nWe presented a methodology for merging distributional semantic spaces and lexical ontologies and applied it to the task of extending the vocabulary of the former with the help of information extracted from the latter. We carried out an analysis for different KB embedding and semantic space mapping techniques and also showed that our methodology can lead to considerable enrichment of two standard word embedding models, leading to consistent improvements on the rare word similarity dataset. One interesting property of our approach is that it can be used in the reverse direction and for the completion of knowledge bases using the distributional information derived from text corpora. In future work, we plan to investigate this direction. We also intend to experiment with domain-specific lexical resources and measure the impact of coverage enhancement on a downstream NLP application.\n\nFigure 1: Illustration of the embedding coverage enhancement system. The dashed lines represent semantic bridges and the solid line represents a rare word that is transformed from a knowledge vector space to a corpus vector space (§2.2).\n\nTable 1: Pearson (r) and Spearman (ρ) correlation results on three word similarity datasets.\n\nFigure 2: Pearson correlation performance of four configurations: two KB embedding techniques (DeepWalk and node2vec) and two transformation approaches (LS and CCA) on three word similarity datasets.\n\nTable 2: Results on the Rare Word Similarity dataset for different word embeddings, before and after enrichment.\n\nQuestion: How are rare words defined?", "role": "user" }, { "content": "{\"answer\": [\"judged by 10 raters on a [0,10] scale\"], \"evidence\": [\"In order to verify the reliability of our technique in coverage expansion for infrequent words we did a set of experiments on the Rare Word similarity dataset BIBREF6 . The dataset comprises 2034 pairs of rare words, such as ulcerate-change and nurturance-care, judged by 10 raters on a [0,10] scale. Table TABREF15 shows the results on the dataset for three pre-trained word embeddings (cf. \\u00a7 SECREF2 ), in their initial form as well as when enriched with additional words from WordNet.\"]}", "role": "assistant" } ]

[ { "content": "You will be shown the title of a chemistry paper, together with sections excerpted from the body of the paper. The paper sections may include HTML tags like `<p>` and `</p>`; please ignore these. Your task is to write an abstract for the paper. Your response should include the abstract and no other text.\n\nTitle:\nUsing Marine Natural Products to Discover a Protease that Catalyzes Peptide Macrocyclization of Diverse Substrates\n\nPaper sections:\n\n<p>Numerous N-C terminally cyclized ribosomal peptides have been isolated from natural sources (Fig. 1), yet enzymatic routes to these peptides remain largely unknown.1-3 Cyclic peptides have structural features that make them good drug candidates, and in fact synthetic cyclic peptides are used clinically.3,4 Ribosomal peptides can be artificially cyclized using intein technology, which although groundbreaking suffers from certain sequence and mechanistic requirements.5 In principle, proteases could also catalyze this process, as exemplified by the proposed pilin cyclization catalyst, which was examined in vivo by mutagenesis6 and an artificial cyclization of a trypsin inhibitor.7 The potential synthesis of cyanobactins and cyclotides by proteases is also supported by in vivo analysis.8-11 However, no proteins have yet been characterized in vitro whose native function is to catalyze N-C cyclization.</p><p>Cyanobactins provide excellent models for the study of ribosomal N-C terminal cyclization. These compounds are synthesized as ribosomal precursor peptides that are extensively modified by enzymes to yield cyclic natural products.2 Cyanobactins are found in diverse cyanobacteria, including symbionts of marine animals. In the first report of this pathway type, a cyanobactin gene cluster, pat, was cloned from the metagenome of a coral reef animal and transferred to E. coli, leading to production in the lab of a cyclic peptide marine natural product previously attributed to an animal.8 Subsequently, each gene in the pat cluster (patA-G) was independently expressed under control of a T7 promoter to determine that patA,D,E,F,G were necessary and sufficient for cyanobactin biosynthesis and patB,C were not required.10 However, the enzymatic basis of each transformation could not be discerned because removing any essential enzyme led to a loss of detectable products.</p><p>Using this initial discovery, we proceeded to assign the function of genes in the pathway by comparing over 30 closely related pathways from the cyanobacterial symbionts that we showed earlier to be the true producers of the cyclic peptides — a novel approach to functional analysis, which we term 'deep metagenome mining'.12 This method was applied to show that cyanobactins are made by enzymes with broad substrate selectivity (Fig. 1 and Table S1).10,12 We then showed that wholly artificial cyclic peptides could be generated by this system in vivo.10 The putative cyanobactin peptide cyclase enzymes were demonstrated by these methods to be broadly substrate tolerant.</p><p>Most cyanobactin precursor peptides contain two product \"cassettes\" that are flanked by putative modifying enzyme recognition sequences (Fig. 1 and 2).2,10 Thus, the cassettes are cleaved out of the full-length precursor at both their C- and N-termini, and then cyclized to form the cyanobactin products. It seemed probable that proteases PatA and PatG could participate in these steps, but several other enzymes are also required to synthesize cyanobactin natural products.13 Although much experimental evidence indicated that PatA and PatG were involved in this process, their precise roles were not defined. Here, we report on the in vitro activity of these enzymes, defining their roles in cyclization of natural and artificial peptides and providing the first in vitro study of natural ribosomal peptide N-C cyclization.</p><p>Previously, we genetically engineered an artificial precursor peptide, PatEdm, encoding the new compound eptidemnamide.10 PatEdm encodes the sequence for the natural cyclic peptide patellamide C in cassette 1 and the sequence for the synthetic cyclic peptide eptidemnamide in cassette 2 (Fig 2). Eptidemnamide was produced by the full complement of cyanobactin biosynthetic proteins using heterologous in vivo experiments.10 Because eptidemnamide requires only cyclization, and not the other enzymatic transformations required to produce the natural products, it was used for biochemical experiments described below.</p><p>Both PatA and PatG proteases are clearly paralogous and contain homologous domains, including a subtilisin-like serine protease domain and a domain of unknown function. PatG also contains a N-terminal oxidase domain that is not involved in peptide cyclization as shown by metagenomic analysis.13 The PatA and PatG proteases contain the Asp-Ser-His catalytic triad,14 as shown by sequence alignment and protein threading (Fig. S1).</p><p>To determine the potential roles of PatA and PatG in the cyclization of ribosomal peptide, we expressed and purified several constructs of PatA, PatG, and the artificial precursor peptide, PatEdm. Subsequent biochemical analysis defined the roles of each of these proteins. Expressed PatA was isolated as the full-length product with a mixture of fragments, some of which contained only the subtilisin-like protease domain (Fig. S2). This domain was neatly cleaved at the linker region between the C-terminal protease and the domain of unknown function, as determined by tryptic-digest mass spectrometry. The protease domain could be purified to homogeneity. PatEdm was purified at high yield despite the inherent difficulties often encountered in expression of precursor peptides.</p><p>Both whole PatA, containing a mixture of fragments, and the purified protease domain of PatA were used for biochemical experiments. When incubated overnight with purified PatA or PatA protease domain, PatEdm was slowly cleaved to release first the eptidemnamide-encoding sequence, then the internally located patellamide-C sequence (Fig. 2 and Table S3). To further confirm that this protease activity originated in PatA, a Ser-Ala active-site mutant was purified and shown to be inactive in this assay. In time-course experiments, the larger fragment was clearly produced first, followed by accumulation of the shorter fragment (Fig. 2). By high-resolution mass spectrometry, we could observe the N-terminal leader sequence, the patellamide-C coding sequence, and the eptidemnamide-coding sequence (Fig. 2 and S4). A synthetic standard of the eptidemnamide-coding sequence was used to further confirm this analysis (Fig. S3). The enzyme reaction was very slow, but it led to eventual quantitative cleavage of the precursor peptide no matter what enzyme:substrate ratio was employed. This enzyme reaction is not optimal as is discussed further in the paragraphs concerning the PatG protein.</p><p>The precursor peptide, PatEdm, was cleaved neatly at the predicted N-terminal recognition sequence, G(L/V)E(A/P)S in both instances (Fig. 2 and Fig. S4). Thus, the cyanobactin cassettes fused to their conserved C-terminal recognition sequences, AYDG(E), were released upon incubation with PatA. By contrast, when incubated with PatEdm, PatG did not catalyze any detectable proteolysis in numerous different experimental conditions (Table S3). We therefore predicted that PatG would catalyze cleavage and cyclization of the C-terminal recognition sequence, and that the products of PatA would be the substrates of PatG.</p><p>To assess the PatG reaction, we used synthetic peptide substrate, QGGRGDWP-AYDGE. The substrate was identical to the product released by PatA from cassette II, as shown by high resolution LC-MS (Fig. 2, 3, S3 and S4).</p><p>Several PatG variants were used with the synthetic substrate. Wild-type PatG was expressed, and in addition we constructed a variant in which the N-terminal oxidase domain was absent. Finally, TruG is a related protein that naturally lacks the oxidase domain (Fig. S2). These three proteins were separately incubated with the synthetic substrate, either with or without the addition of PatA protease. All of these combinations led to production of cyclic eptidemnamide (Fig. 3 and S5, Table S3). The protease recognition sequence, AYDGE, was also clearly discernible in these reaction mixtures as a discrete cleavage product. Co-factors and added metals were not required to catalyze the reaction. In the absence of PatG, with PatA only or without enzyme for example, only starting synthetic peptide was observed.</p><p>The presence of eptidemnamide was confirmed by comparing diode array-HPLC and high resolution MS/MS data with an authentic standard (Fig. 3, S3, and S5). After 41 hours, approximately 1.5 μg of eptidemnamide was synthesized from 50 μg of precursor peptide, representing a ~5% yield. No linear eptidemnamide analog was detected in these experiments, although unreacted synthetic precursor was still clearly observed. This yield could be optimized by addition of more enzyme. Doubling the enzyme led to double the amount of product (~10% yield), while an increase to a 3:1 substrate:enzyme ratio led to a 75% ± 10% yield.</p><p>This process is clearly far from optimal, since only ~ 1 turnover is observed per enzyme molecule per day. Despite this slow rate, each monomeric enzyme unit turns over substrate between >2 to 3 times during the course of the experiment under current conditions. Therefore, PatG is shown to be the cyclization catalyst, as this turnover exceeds a stoichiometric reaction. There are several possibilities that could explain low turnover. The substrate is artificial, and the reaction proceeds in vitro. Many in vitro enzyme reactions require other enzyme partners or buffer optimization to achieve a maximum rate, since they are highly artificial in nature. As one of many possibilities, perhaps the proteases require partnering with an export protein, as is common in lantibiotics. Finally, it should be noted that a single 1 L expression of PatG provides enough protease to synthesize several mg of peptide even without optimization.</p><p>Previously, it was proposed that cyanobactin cyclization could proceed spontaneously.15 In this event, PatG would act merely as a protease, and the small linear product would cyclize on its own or via PatG catalysis at a non-proteolytic site. To rule out these possibilities, we obtained the linear precursor, QGGRGDWP, which lacked the AYDGE sequence. In enzyme reactions with PatG in various combinations and in comparison to a full set of control reactions, this peptide was neither modified nor cyclized (Table S3). Thus, cyclization is not spontaneous, and several lines of evidence favor a one-step transamidation mechanism to cyclization. The data currently support the mechanism shown in Fig. 4, although further experiments are required for confirmation.</p><p>From these experiments, it is clear that PatA catalyzes the proteolytic cleavage of the N-terminal recognition sequence, while PatG catalyzes cleavage of the C-terminal sequence in tandem with cyclization. No addition of energy (in the form of ATP, for example) is required to drive this process, making PatG the first natural peptide-cyclizing enzyme to be characterized as a pure protein. Aside from the lack of an energy requirement, PatG has another potential technological advantage in that it is highly tolerant of diverse substrate sequences as long as the C-terminal recognition domain is present. So far, we have identified >30 natural peptide sequences that appear to be cleaved and cyclized by PatG (Table S1).10,12 These data resemble results of alanine-scanning mutagenesis experiments, in that every amino acid position is substituted at least once by a non-conserved amino acid residue. Six, seven, and eight amino acid peptides are cyclized by PatG in vivo based upon this same analysis. In addition, close relatives of PatG catalyze the synthesis of >60 additional known natural products (Table S1). Finally, the wholly synthetic peptide, eptidemnamide, is cyclized by PatG in vivo10 and in vitro. The exact limitation of product size and sequence content are not yet known. If this enzyme process can be improved, and if broad substrate activity can be demonstrated in vitro, the enzyme could serve as a useful general catalyst for the cyclization of peptides.</p>\n\nSupporting Information Available\n<p>Experimental details, alignment data, tables, and MS data. The material is available free of charge via the Internet at http://pubs.acs.org.</p>\n\n\n<p>N-C cyclic peptides of the cyanobactin group. The partial precursor peptide sequences are shown that give rise to the cyclic products. Amide bonds formed by PatG and its relatives are shown in green, while recognition sequences are shown in bold and cassette sequences leading to products are underlined. Patellin 2, ulithiacyclamide, and trichamide are natural products that require multiple enzymatic processing steps in their synthesis, while the eptidemnamide precursor was engineered and requires only cleavage and cyclization.</p>\n\nPatA catalyzes two N-terminal cleavage reactions\n<p>(a) The precursor peptide PatEdm is cleaved by PatA at a recognition sequence to release first (5) and then (4), with free N-termini for cyclization. (b) SDS-PAGE of a time-course experiment with PatA and PatEdm shows that the first site is slowly cleaved, followed by relatively rapid proteolysis of the second site. (c) All reaction products were observed by mass spectrometry</p>\n\nPatG catalyzes cyclization by a transamidation mechanism\n<p>(a) Starting from product (5) of PatA, PatG cleaves this peptide into a cyclic compound, eptidemnamide, and a small linear fragment representing the recognition sequence. (b) High resolution mass spectrometry and comparison to authentic standards confirmed that this cyclic peptide was formed from compound (5).</p>\n\nProposed transamidation mechanism of peptide cyclization\n<p>In this simplified scheme, the active-site Ser of PatG is shown forming an enzyme-substrate tetrahedral intermediate with loss of the AYDGE recognition sequence. Subsequently, the N-terminus of the substrate attacks the activated ester bond to release a cyclic peptide and the free enzyme.</p>", "role": "user" }, { "content": "Small, N-C terminally cyclic ribosomal peptides are common in nature, yet the mechanisms underlying their biosyntheses remain largely unknown. We recently identified candidate peptide cyclase genes in the metagenomes of marine animals. Here we report that PatG, a protease discovered in this analysis, cleaves variables, short peptides out of a precursor protein and cyclizes these peptides in vivo and in vitro.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Disease\"].\n\nPlease return the output as a JSON object of the format: {\"Disease\": [\"COVID-19\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nNebulin seen in DMD males including one patient with a large DNA deletion encompassing the DMD gene. The presence of nebulin in a muscle specimen from a patient with Duchenne muscular dystrophy (DMD) due to a large deletion precludes the possibility that this protein is the DMD gene product..", "role": "user" }, { "content": "{\"Disease\": [\"Duchenne muscular dystrophy\", \"DMD\"]}", "role": "assistant" } ]

[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: having an autoimmune disorder such as lupus increase the risk for infection by COVID 19\n\nAbstract:\nThis review evaluates whether pregnancy is a risk factor for COVID-19 by looking at the expression of immune markers such as immune cells and cytokines in order to have a better understanding on the pathophysiology of the disease, thus reducing maternal deaths.\nPregnant women are more at risk of contracting COVID-19 due to their weakened immune system.\nStudies demonstrate that COVID-19 is an immune condition which is marked by reduced lymphocytes and elevated selected proinflammatory cytokines.\nSimilar immune expression has been demonstrated in pregnancy by several studies.\nIn addition, the placenta has been shown to possess ACE2 receptors on the villous cytotrophoblast and the syncytiotrophoblast and findings suggest that the coronavirus enters the host cells via these ACE2 receptors.\nThe immune response in pregnancy increases the risk of contracting COVID-19.\nBoth normal pregnancy and COVID-19 are marked by decreased lymphocytes, NKG2A inhibitory receptors, and increased ACE2, IL-8, IL-10, and IP-10 it therefore safer to conclude that pregnancy is a risk factor for COVID-19 development.\nFurthermore, the presence of the ACE2 receptors in the placenta may increase the risk of mother to baby transmission of the virus.\nTherefore, more studies investigating the link between pregnancy and COVID-19 are needed.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Pregnant women are more at risk of contracting COVID-19 due to their weakened immune system.\", \"Studies demonstrate that COVID-19 is an immune condition which is marked by reduced lymphocytes and elevated selected proinflammatory cytokines.\", \"Similar immune expression has been demonstrated in pregnancy by several studies.\"]}", "role": "assistant" } ]

[ { "content": "You will be shown an excerpt from a computer science research paper, followed by a question about the paper. Please answer the question given the context. Do not include any text in your response other than the answer.\n\nContext: [\" Second, compared to its plain counterpart, the 34-layer ResNet reduces the top-1 error by 3.5% ………. providing faster convergence at the early stage.\"]\n\nQuestion: What are the main findings of the experiments with respect to plain networks and residual networks?", "role": "user" }, { "content": "[Residual network reduce more training error than plain networks. ResNet eases the optimization by providing faster convergence at the early stage when net is not deep than plain networks. ]", "role": "assistant" } ]

[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: End-to-End Entity Resolution for Big Data: A Survey \nChapter Title: Directions for Future Work \n1. Abstract of Cited Paper (BIB001): Entity matching (EM) has been a long-standing challenge in data management. Most current EM works focus only on developing matching algorithms. We argue that far more efforts should be devoted to building EM systems. We discuss the limitations of current EM systems, then present as a solution Magellan, a new kind of EM systems. Magellan is novel in four important aspects. (1) It provides how-to guides that tell users what to do in each EM scenario, step by step. (2) It provides tools to help users do these steps; the tools seek to cover the entire EM pipeline, not just matching and blocking as current EM systems do. (3) Tools are built on top of the data analysis and Big Data stacks in Python, allowing Magellan to borrow a rich set of capabilities in data cleaning, IE, visualization, learning, etc. (4) Magellan provides a powerful scripting environment to facilitate interactive experimentation and quick \"patching\" of the system. We describe research challenges raised by Magellan, then present extensive experiments with 44 students and users at several organizations that show the promise of the Magellan approach. \n2. Abstract of Cited Paper (BIB002): Developers use cloud computing platforms to process a large quantity of data in parallel when developing big data analytics. Debugging the massive parallel computations that run in today's datacenters is time consuming and error-prone. To address this challenge, we design a set of interactive, real-time debugging primitives for big data processing in Apache Spark, the next generation data-intensive scalable cloud computing platform. This requires rethinking the notion of step-through debugging in a traditional debugger such as gdb, because pausing the entire computation across distributed worker nodes causes significant delay and naively inspecting millions of records using a watchpoint is too time consuming for an end user. First, B ig D ebug 's simulated breakpoints and on-demand watchpoints allow users to selectively examine distributed, intermediate data on the cloud with little overhead. Second, a user can also pinpoint a crash-inducing record and selectively resume relevant sub-computations after a quick fix. Third, a user can determine the root causes of errors (or delays) at the level of individual records through a fine-grained data provenance capability. Our evaluation shows that B ig D ebug scales to terabytes and its record-level tracing incurs less than 25% overhead on average. It determines crash culprits orders of magnitude more accurately and provides up to 100% time saving compared to the baseline replay debugger. The results show that B ig D ebug supports debugging at interactive speeds with minimal performance impact. \n3. Abstract of Cited Paper (BIB003): Multi-modal data is becoming more common than before because of big data issues. Finding the semantically equal or similar objects from different data sources(called entity resolution) is one of the heart problem of multi-modal task. Current models for solving this problem usually needs much paired data to find the latent correlation between multi-modal data, which is of high cost. A new kind latent correlation is proposed in this article. With the correlation, multi-modal objects can be uniformly represented in a commonly shard space. A classifying based model is designed for multi-modal entity resolution task. With the proposed method, the demand of training data can be decreased much. \n4. Abstract of Cited Paper (BIB004): A novel approach COSLAQ for cross modal similarity learning with active queries is proposed.Disagreement-based active query strategy explores the most valuable supervised information.Uncertainty of similarity learning model is utilized to avoid querying outliers and noises. In real applications, data is usually collected from heterogeneous sources and represented with multiple modalities. To facilitate the analysis of such complex tasks, it is important to learn an effective similarity across different modalities. Existing similarity learning methods usually requires a large number of labeled training examples, leading to high labeling costs. In this paper, we propose a novel approach COSLAQ for active cross modal similarity learning, which actively queries the most important supervised information based on the disagreement among different intra-modal and inter-modal similarities. Furthermore, the closeness to decision boundary of similarity is utilized to avoid querying outliers and noises. Experiments on benchmark datasets demonstrate that the proposed method can reduce the labeling cost effectively. \n5. Abstract of Cited Paper (BIB005): As machine learning (ML) systems become democratized, it becomes increasingly important to help users easily debug their models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly. This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets, and slicing allows users to analyze the model performance on a more granular-level. Unlike general techniques (e.g., clustering) that can find arbitrary slices, our goal is to find interpretable slices (which are easier to take action compared to arbitrary subsets) that are large and problematic. We propose Slice Finder, which is an interactive framework for identifying such slices using statistical techniques. Applications include diagnosing model fairness and fraud detection, where identifying slices that are interpretable to humans is crucial.\n\nLiterature Review:", "role": "user" }, { "content": "As we have just begun to realize the need for Entity Resolution Management Systems BIB002 , we next highlight few critical research directions for future work aiming to support advanced services for specifying, maintaining and making accountable complex ER workflows. Multi-modal ER. In the Big Data era, multi-modal entity descriptions are becoming more and more common. Factual, textual or image-based descriptions of the same real world entities are becoming available from different sources and at different temporal or spatial resolutions. Each modality carries a specific piece of information about an entity and offers some type of added value that cannot be obtained from any of the other modalities. Recent years have witnessed a surge of need in jointly analyzing of multi-modal descriptions BIB004 . Finding the semantically similar descriptions from different modality is one of the heart problems of multimodal learning. Most current approaches presume that there is a linear or non-linear projection between multimodal data. These methods focus on how to utilize extrinsic supervised information to project one modality to the other or map both two modalities into a commonly shared space. The performance of these methods heavily depends on the richness of training samples. However, in real-world applications, obtaining the matched data from multiple modalities is costly or even impossible BIB005 . Therefore, it is urgently needed to develop a sample-insensitive method for multi-modal ER, and in this respect, we can leverage recent advances in multi-model ML techniques . Debugging and Repairing ER workflows. Current ER research mainly focuses on developing accurate and efficient blocking and matching techniques which in reality are constrained by a number of factors, such as low quality of entity descriptions, ambiguity or domain knowledge, limited ground truth. Hence, it becomes difficult to guarantee the quality of ER workflows at specification time. To support a continuous specification of ER workflows, an iterative approach is needed to refine ER workflows by identifying and analyzing the mistakes (false matches and non-matches) of ER enactments at each iteration step. Debugging ER workflows requires to (a) understand the mistakes made by blocking or matching algorithms; (b) diagnose root-causes of these mistakes (e.g., due to dirty data, problematic feature sets, or even tuning parameters of algorithms); and (c) prioritize mistakes and take actions to fix them BIB002 . We should stress that not all categories of mistakes have the same impact on the end-to-end quality of ER workflows. For example, the removal of outliers from the input data often leads to overfitting problems of learningbased matchers. Recognizing patterns of mistakes reproduced under similar conditions can provide valuable insights in order to repair ER workflows. Clearly, the primary focus of ER work so far was in preventing rather than repaing mistakes in ER results. Recent work on debugging and repairing Big Data analytics pipelines can be leveraged in this respect BIB006 BIB001 BIB003 .", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: How many selenoproteins are encoded in the human genome?\n\nContext: The human selenoproteome consists of 25 selenoproteins.", "role": "user" }, { "content": "25", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a materials science research paper. Your task is to extract all synthesis operations described in the abstract into a structured JSON format. Your output should be a JSON array. Each entry in the array should be a JSON object describing a single synthesis operation. Your output JSON object should have the following two fields:\n\n- \"trigger\": A verbal predicate indicating a synthesis operation. This should be a string extracted directly from the abstract.\n- \"arguments\": An array of arguments specifying aspects of the synthesis operation. Each entry in the array should be a length-2 array formatted as [<argument_text>, <argument_type>]. The `argument_text` should be a string extracted directly from the abstract. The `argument_type` should be one of the following types: [\"Recipe_Precursor\", \"Solvent_Material\", \"Atmospheric_Material\", \"Participant_Material\", \"Recipe_Target\"].\n\nFor instance, suppose an excerpt from the abstract reads:\n\nTetraethoxysilane (TEOS, 98%) and cetyltrimethylammonium bromide (CTAB, 98%) were purchased from Fluka. The MTTZ-siloxy derivative (triethoxysilyl-propyl-5-mercapto-1-methyl-tetrazole) was synthesized as previously described [38].\n\nThis excerpt includes two operations, which could be annotated as follows:\n\n[{\"arguments\": [[\"Tetraethoxysilane\", \"Recipe_Precursor\"], [\"cetyltrimethylammonium bromide\", \"Recipe_Precursor\"]], \"trigger\": \"purchased\"}, {\"arguments\": [[\"MTTZ-siloxy derivative\", \"Recipe_Target\"]], \"trigger\": \"synthesized\"}]\n\nIn your response, please include the JSON and no other text.\n\nAbstract:\n10.1016/j.matchemphys.2007.10.005\nSynthesis of CuO nanocrystalline and their application as electrode materials for capacitors\n0.03 mol Cu(NO3)2*3H2O was dissolved in 750 ml distilled water under stirring (solution A). The mixture of PEG (Mw = 6000) and 0.24 mol NH3*H2O was added dropwise into solution A at 30 degC, resulting in a blue solution. The final mixture was rapidly heated to 80 degC and stirred vigorously. After 10 h, the precipitate was filtered and washed for several times with deionized water and alcohol, and then dried at 60 degC in air overnight. Product was signed as sample A.", "role": "user" }, { "content": "[{\"arguments\": [[\"water\", \"Solvent_Material\"], [\"Cu(NO3)2*3H2O\", \"Recipe_Precursor\"]], \"trigger\": \"dissolved\"}, {\"arguments\": [[\"solution A\", \"Participant_Material\"]], \"trigger\": \"stirring\"}, {\"arguments\": [[\"NH3*H2O\", \"Recipe_Precursor\"], [\"solution A\", \"Participant_Material\"], [\"PEG\", \"Recipe_Precursor\"]], \"trigger\": \"added\"}, {\"arguments\": [[\"mixture\", \"Participant_Material\"]], \"trigger\": \"heated\"}, {\"arguments\": [[\"solution\", \"Participant_Material\"]], \"trigger\": \"resulting\"}, {\"arguments\": [[\"precipitate\", \"Participant_Material\"]], \"trigger\": \"filtered\"}, {\"arguments\": [[\"water\", \"Participant_Material\"], [\"alcohol\", \"Participant_Material\"]], \"trigger\": \"washed\"}, {\"arguments\": [[\"air\", \"Atmospheric_Material\"]], \"trigger\": \"dried\"}, {\"arguments\": [[\"sample A\", \"Recipe_Target\"], [\"Product\", \"Participant_Material\"]], \"trigger\": \"signed\"}]", "role": "assistant" } ]

[ { "content": "You will be presented with a citation sentence from a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\n…August 14, 2015 10 / 21\nproxies may have difficulty evaluating the impact of conditions on dimensions of health such as pain and emotion; Tilford et al. (2005) [79] called for more research to be conducted on calculation methods for young child when discussing the issues surrounding the…", "role": "user" }, { "content": "Method", "role": "assistant" } ]

[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the mechanism of the auxin-inducible degron system?\n\nContext: Fusion of inducible degradation signals, so-called degrons, to cellular proteins is an elegant method of controlling protein levels in vivo.\nThe auxin-inducible degron (AID) system allows the rapid and reversible proteolysis of proteins of interest, and enables the generation of conditional mutants of budding yeast.\nStrategies that use ubiquitin-mediated protein degradation to eliminate the product of a gene of interest, such as heat-inducible degron (td) and auxin-inducible degron (AID), are powerful methods for constructing conditional mutants.\nAuxin-inducible degron (AID) technology allows rapid depletion of proteins in animal cells and fungi, but its application to human cells has been limited by the difficulties of tagging endogenous proteins.\nThe auxin-inducible degron harbors great potential for dynamic protein depletion in yeast. Here, we thoroughly and quantitatively characterize the auxin-inducible degron in single yeast cells. We show that an auxin concentration of 0.25 mM is necessary for fast and uniform protein depletion between single cells, and that in mother cells proteins are depleted faster than their daughters.\nwe introduce an easy and efficient method to generate conditional knockout cell lines based on combining auxin-inducible degron (AID) technology with CRISPR/Cas9 gene editing.\nPlants have evolved a unique system in which the plant hormone auxin directly induces rapid degradation of the AUX/IAA family of transcription repressors by a specific form of the SCF E3 ubiquitin ligase. Other eukaryotes lack the auxin response but share the SCF degradation pathway, allowing us to transplant the auxin-inducible degron (AID) system into nonplant cells and use a small molecule to conditionally control protein stability.\nWe constructed an auxin-inducible degron (AID) system, which utilizes auxin-dependent poly-ubiquitination of Aux/IAA proteins by SCFTIR1 in plants, in fission yeast.\nRESULTS We constructed an auxin-inducible degron (AID) system, which utilizes auxin-dependent poly-ubiquitination of Aux/IAA proteins by SCFTIR1 in plants, in fission yeast.\nTo this end, a degradation system was developed in yeast exploiting TIR1, a plant F box protein, which can recruit proteins with an auxin-inducible degron to an E3 ubiquitin ligase complex, but only in the presence of the phytohormone auxin.\nPlants have evolved a unique system in which the plant hormone auxin directly induces rapid degradation of the AUX/IAA family of transcription repressors by a specific form of the SCF E3 ubiquitin ligase.\ninducible inactivation of a protein is a powerful approach for analysis of its function within cells fission yeast is a useful model for studying the fundamental mechanisms such as chromosome maintenance and cell cycle however previously published strategies for protein depletion are successful only for some proteins in some specific conditions and still do not achieve efficient depletion to cause acute phenotypes such as immediate cell cycle arrest the aim of this work was to construct a useful and powerful protein depletion system in shizosaccaromyces pombe we constructed an auxin inducible degron aid system which utilizes auxin dependent poly ubiquitination of aux iaa proteins by scftir1 in plants in fission yeast although expression of a plant f box protein tir1 decreased mcm4 aid a component of the mcm complex essential for dna replication tagged with aux iaa peptide depletion did not result in an evident growth defect we successfully improved degradation efficiency of mcm4 aid by fusion of tir1 with fission yeast skp1 a conserved f box interacting component of scf improved aid system i aid and the cells showed severe defect in growth the i aid system induced degradation of mcm4 aid in the chromatin bound mcm complex as well as those in soluble fractions the i aid system in conjunction with transcription repression off aid system we achieved more efficient depletion of other proteins including pol1 and cdc45 causing early s phase arrest improvement of the aid system allowed us to construct conditional null mutants of s pombe we propose that the off aid system is the powerful method for in vivo protein depletion in fission yeast.\nplants have evolved a unique system in which the plant hormone auxin directly induces rapid degradation of the aux iaa family of transcription repressors by a specific form of the scf e3 ubiquitin ligase other eukaryotes lack the auxin response but share the scf degradation pathway allowing us to transplant the auxin inducible degron aid system into nonplant cells and use a small molecule to conditionally control protein stability the aid system allowed rapid and reversible degradation of target proteins in response to auxin and enabled us to generate efficient conditional mutants of essential proteins in yeast as well as cell lines derived from chicken mouse hamster monkey and human cells thus offering a powerful tool to control protein expression and study protein function.\nthe analysis of consequences resulting after experimental elimination of gene function has been and will continue to be an extremely successful strategy in biological research mutational elimination of gene function has been widely used in the fly drosophila melanogaster rna interference is used extensively as well in the fly exceptionally precise temporal and spatial control over elimination of gene function can be achieved in combination with sophisticated transgenic approaches and clonal analyses however the methods that act at the gene and transcript level cannot eliminate protein products which are already present at the time when mutant cells are generated or rna interference is started targeted inducible protein degradation is therefore of considerable interest for controlled rapid elimination of gene function to this end a degradation system was developed in yeast exploiting tir1 a plant f box protein which can recruit proteins with an auxin inducible degron to an e3 ubiquitin ligase complex but only in the presence of the phytohormone auxin here we demonstrate that the auxin inducible degradation system functions efficiently also in drosophila melanogaster neither auxin nor tir1 expression have obvious toxic effects in this organism and in combination they result in rapid degradation of a target protein fused to the auxin inducible degron.\nisolation of a tight conditional mutant of a gene of interest is an effective way of studying the functions of essential genes strategies that use ubiquitin mediated protein degradation to eliminate the product of a gene of interest such as heat inducible degron td and auxin inducible degron aid are powerful methods for constructing conditional mutants however these methods do not work with some genes here we describe an improved aid system iaid for isolating tight conditional mutants in the budding yeast saccharomyces cerevisiae in this method transcriptional repression by the tet off promoter is combined with proteolytic elimination of the target protein by the aid system to provide examples we describe the construction of tight mutants of the replication factors dpb11 and mcm10 dpb11 iaid and mcm10 iaid because dpb11 and mcm10 are required for the initiation of dna replication their tight mutants are unable to enter s phase this is the case for dpb11 iaid and mcm10 iaid cells after the addition of tetracycline and auxin both the tet off promoter and the aid system have been shown to work in model eukaryotes other than budding yeast therefore the iaid system is not only useful in budding yeast but also can be applied to other model systems to isolate tight conditional mutants.", "role": "user" }, { "content": "Fusion of inducible degradation signals, so-called degrons, to cellular proteins is an elegant method of controlling protein levels in vivo. The auxin-inducible degron (AID) system allows the rapid and reversible proteolysis of proteins of interest, and enables the generation of conditional mutants of budding yeast. Strategies that use ubiquitin-mediated protein degradation to eliminate the product of a gene of interest, such as heat-inducible degron (td) and auxin-inducible degron (AID), are powerful methods for constructing conditional mutants. Auxin-inducible degron (AID) technology allows rapid depletion of proteins in animal cells and fungi, but its application to human cells has been limited by the difficulties of tagging endogenous proteins. The auxin-inducible degron harbors great potential for dynamic protein depletion in yeast. Here, we thoroughly and quantitatively characterize the auxin-inducible degron in single yeast cells.", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nMachine learning algorithms for controlling devices will need to learn quickly, with few trials.\nSuch a goal can be attained with concepts borrowed from continental philosophy and formalized using tools from the mathematical theory of categories.\nIllustrations of this approach are presented on a cyberphysical system: the slot car game, and also on Atari 2600 games.\nThere is a growing need for algorithms that control cyberphysical systems to learn with very little data how to operate quickly in a partially-known environment.\nMany reinforcement-learning (RL) solutions using neural networks (NN) have proved to work well with emulators, for instance with the Atari 1 2600 games BID17 , or with real systems such as robots BID11 .\nHowever, these state-of-the-art approaches need a lot of training data, which may not be obtainable within the allowed time frame or budget.\nThis work thus started as an alternative approach to teach computers to learn quickly to perform as efficiently as the existing solution with approximately one percent of the training data, time, and computing resources.We first review reinforcement learning methods for Markov Decision Processes (MDP) and Partially Observable MDP (POMDP).\nWe then explain the motivation behind our continental-philosophyinspired approach.\nWe describe the two classes of problems on which we focus: the bijective case, which may lead to playing by imitating, and the category-based approach, which should lead to a more innovative behavior of the control algorithms.\nBoth approaches rely on knowledge accumulated during previous experiences, as in Lifelong Machine Learning BID6 .These\ntwo approaches are illustrated by results from both a commercial slot car game controlled by an 8-bit Arduino system, and from Atari 2600 video games running within the Arcade Learning Environment (ALE, see BID1 ).\nContinental philosophy lead us to formalize a mathematical concept to control an agent evolving in a world, whether it is simulated or real.\nThe power of this framework was illustrated by the theoretical example of the slot car on unknown circuits.\nResults from experiments with a real slot car, using real analog signals confirmed our expectations, even though it only used a basic survival approach.\nMoreover, the same basic survival strategy was applied to two Atari 2600 games and showed the same trend: even though not as skilled as, for instance, DQN-based agents trained with two hundred million frames, our AI reached in less than ten thousand frames scores that DQN met after learning with a few million frames.The next steps are to apply the transposition properties to the Atari games, as we did for the slot car, which should further decrease the learning time when playing a new game.\nMoreover, going beyond the basic survival strategy will be mandatory to reach higher scores: approaches based on Monte-Carlo Tree Search will be investigated.", "role": "user" }, { "content": "Continental-philosophy-inspired approach to learn with few data.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nReference data for jumping mechanography in Canadian children, adolescents and young adults To provide age - and sex - specific reference data for mechanography -derived parameters of muscle function in Canadian children and youth using the single two-legged jump (S2LJ) with hands-on-waist. Our sample included 2017 observations from 715 participants (9-21 years; 338 girls). Participants performed three S2LJ with hands-on-waist on a force platform (Leonardo Mechanograph, Novotec). Outcomes were maximum peak power (Pmax), Pmax / mass, peak force / body weight (Fmax / BW), force efficiency, maximum jump height (Hmax), and velocity (Vmax). We used the LMS method to construct age - and sex - specific percentile curves and mixed effects models to examine sex and ethnic differences. With the exception of Efficiency, mechanography outcomes were greater in girls (4-40%, p<0.05) than boys at age 9. Boys ' advantage in mechanography parameters emerged in adolescence (age 11-13 years; 3-65%, p<0.05) and persisted into young adulthood, except for Fmax / BW which was not greater in boys until age 17 (4-10%, p<0.05). Mechanography outcomes were 3-9% (p<0.05) greater in Asian compared with white participants. We provide the first reference data for the S2LJ using the hands-on-waist protocol in children, youth and young adults. These data support previous findings using freely moving arms and can be used when evaluating muscle function in pediatric studies.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"muscle function\", \"Fmax\", \"peak force\", \"moving arms\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"findings\", \"mass\", \"parameters\"], \"Food\": [], \"HealthCareActivity\": [\"jumping mechanography\", \"mechanography\", \"Mechanography\", \"evaluating\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"mixed effects models\", \"Novotec\"], \"MedicalDevice\": [\"Leonardo Mechanograph\"], \"Organization\": [], \"PopulationGroup\": [\"Asian\", \"participants\", \"Participants\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"Outcomes\", \"studies\", \"observations\", \"outcomes\", \"examine\"], \"SpatialConcept\": [\"curves\", \"Canadian\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nBacteriuria during urinary tract catheterization: suprapubic versus urethral route: a prospective randomized trial.\nAbstract 1:\nIn this r and omized prospect i ve trial urethral and suprapubic routes were compared in terms of tolerance and infectious potential . Daily bacteriuria determined infectious danger and patients were interrogated on the pain and discomfort induced by their catheter every day . Identical single dose pre-operative antibiotic prophylaxis was routinely applied . Patients ( n = 50 ) were divided into two similar groups ( 25 suprapubic catheters and 25 urethral catheters ) . Four patients in the suprapubic group were excluded . All specimen cultured by suprapubic catheter remained sterile . Nine patients with urethral catheterization eventually developed bacteriuria . The difference became significant on the third day of catheterization ( p < 0.05 ) and increased on days 4 and 5 ( p < 0.01 ) . Between the two groups , pain and discomfort did not achieve statistical significance . Suprapubic catheterization is preferable to the alternative using the urethral route in terms of improving urine sterility\n\n\nTitle 2:\nUrological management of the patient with spinal cord injury.\nAbstract 2:\nA total of 515 patients with spinal cord injuries were admitted to the Conradie Hospital 's Spinal Cord Injuries Centre during a 3-year period from September 1974 to September 1977 . Intermittent catheterization was used for urinary drainage in all patients with incomplete lesions as initially assessed neurologically , and indwelling catheterization in those with complete lesions . Transcutaneous suprapubic Bonnano ( stab ) continuous catheter drainage was used in a r and om group of 24 male patients with complete neurological lesions . The majority of the patients were admitted within 24 hours of injury . The follow-up period varied from 1 to 4 years . At 3 months more than 50 % of patients had a balanced neurogenic bladder and were catheter-free . At 12 months 19 % of patients were still catheter-dependent for reasons explained . Bladder outlet operations were more frequent among patients with thoracic lesions and were indicated 3 times more often in patients with complete neurological lesions . Bladder outlet operations were performed on 8.6 % of patients . Only 5 patients ( 1 % ) required permanent urinary diversion . A urodynamic work-up is no longer regarded as merely a research tool in the investigation of patients with neurogenic bladder dysfunction . Both urodynamic and videoradiological techniques are a prerequisite to proper management of the neurogenic urinary tract\n\n\nTitle 3:\nA randomised controlled trial: outcomes of bladder rehabilitation in persons with multiple sclerosis\nAbstract 3:\nObjective A stratified , r and omised , waitlist controlled study over 12 months assessed the effectiveness of a 6 week bladder rehabilitation programme in persons with multiple sclerosis ( pwMS ) in an Australian community cohort . Methods Patients with definite MS and bladder issues ( n=74 ) recruited from a tertiary hospital data base were r and omised to a treatment group ( n=40 ) for an individualised bladder rehabilitation programme or to a control waitlist group ( n=34 ) . The Urogenital Distress Inventory ( UDI6 ) , Neurological Disability Scale ( NDS ) and the American Urological Association Symptom Index ( AUA ) assessed bladder impairment and ‘ activity limitation ’ ; a single Quality of life ( QoL ) item in the AUA and the Incontinence Impact Question naire ( IIQ7 ) measured restriction in ‘ participation ’ . Primary outcome measures were assessed at baseline and at 12 months . Results Analysis of per protocol data from 58 patients ( treatment n=24 , control n=34 ) showed reduced disability in the treatment group , with significant differences ( p<0.001 ) and large effect sizes ( > 0.5 ) in post-treatment UDI6 , NDS , AUA total , AUA QoL and IIQ7 scores for the two groups . The treatment group compared with the control group showed improvement : 78 % versus 27 % for UDI6 and 59 % versus 17 % improved for IIQ7 . More patients in the control group deteriorated over the study period on the UDI6 ( 30 % vs 0 % ; p<0.001 ) and IIQ7 ( 39 vs 0 % ; p=0.001 ) . Conclusion A multifaceted , individualised bladder rehabilitation programme reduces disability and improves QoL in pwMS compared with no intervention after 12 months of follow-up . Information on specific interventions in different bladder types in MS and the impact on QoL need further evaluation . Australian Clinical trials Registry ACTRNO12605000676617\n\n\nTitle 4:\n[Urinary catheterization: transurethral or suprapubic approach?].\nAbstract 4:\n75 patients , needing a bladder drainage for nonurological indications and having sterile urines were studied after r and omization into two groups . In the first group , drained with an urethral catheter , urinary infection took place in 12 (= 30 % ) patients , while it was detected in 4 (= 11 % ) drained with a suprapubic catheter . In this latter group , patients felt more comfortable , had less pain ; the duration of urinary drainage and hospital stay was shorter\n\n\nTitle 5:\nA comparison of fine-bore suprapubic and an intermittent urethral catheterisation regime after spinal cord injury\nAbstract 5:\nA prospect i ve trial , comparing fine-bore suprapubic cathetisation and intermittent urethral catheterisation as methods of bladder drainage in the acute stage following spinal cord injury , was conducted . The results showed no important difference in either method of bladder management . Fine-bore suprapubic catheterisation is particularly suitable for young female patients , who find repeated urethral catheterisation distasteful ; in other patients it is an acceptable alternative to intermittent urethral catheterisation , particularly where economic considerations are paramount\n\n\nTitle 6:\nProportion of complications in patients practicing clean intermittent self-catheterization (CISC) vs indwelling catheter.\nAbstract 6:\nOBJECTIVE To compare the complications especially infection in two groups ; group-A : those performing clean intermittent self-catheterization ( CISC ) and group-B : patients with indwelling catheters . METHODS Comparative study , conducted at Department of Urology , Jinnah Postgraduate Medical Centre , Karachi . A total of 80 patients with ages between 15 - 80 years were studied . There were 40 patients in each group comprising of 35 males and 5 females in group-A and 38 males and 2 females in group-B. Group-A patients were mainly those with neurogenic bladder ( n = 25 ) and postoperative cases of stricture . While in indwelling group 35 patients had neurogenic bladder with the remaining ( n = 5 ) having benign prostatic hypertrophy . Group-A performed CISC 1 - 4 times/24 hours depending on the primary disease while in group-B fortnightly catheter change was done under aseptic conditions . Symptomatic infections were taken into consideration in both the groups proven by urine C/S. RESULTS Symptomatic infections as pyelonephritis , epididymorchitis and urosepsis occurred in both groups . In group-A 2 ( 5 % ) patients developed pyelonephritis as compared to 10 ( 25 % ) in group-B ( P value 0.01 ) . Epididymorchitis and urosepsis occurred in 1 ( 2.5 % ) and 0 patients in group-A while 3 ( 7 % ) and 2 ( 5 % ) patients in group-B. Statistically significant infection ( pyelonephritis ) occurred in group-B. CONCLUSION CISC is much safer practice with less complications and infection rate than indwelling catheters\n\n\nTitle 7:\nProspective randomized controlled trial of urethral versus suprapubic catheterization\nAbstract 7:\nSixty‐six patients requiring catheterization in the course of general surgical operations were r and omly allocated into two groups . Of the 34 patients catheterized urethrally 16 developed urinary tract infections whereas of the 32 suprapubically catheterized patients only 2 developed an infection ( P<0.001 ) . Five patients required recatheterization after removal of their urethral catheters . There were no major complications associated with the use of suprapubic catheters . We propose that , when catheterization is required during a general surgical procedure , the suprapubic route is to be preferred", "role": "user" }, { "content": "It was not possible to draw any conclusions regarding the use of different types of catheter in managing the neurogenic bladder", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: Which peptide plays a pivotal role in human cystatin C fibrillization?\n\nContext: Human cystatin C (HCC) is a low molecular weight member of the cystatin family (type2). HCC consists of 120 amino acids. Normally it is an inhibitor of cysteine proteases, but in pathological conditions it forms amyloid fibrils in brain arteries of young adults. An 'aggregation-prone' pentapeptide ((47)LQVVR(51)) was located within the HCC sequence using AmylPred, an 'aggregation-prone' peptide prediction algorithm developed in our lab. This peptide was synthesized and self-assembled into amyloid-like fibrils in vitro, as electron microscopy, X-ray fiber diffraction, Attenuated Total Reflectance Fourier-Transform Spectroscopy and Congo red staining studies reveal. Thus, the (47)LQVVR(51) peptide seems to have an important role in HCC fibrillization.\nThe pentapeptide LQVVR plays a pivotal role in human cystatin C fibrillization.\nthe (47)LQVVR(51) peptide seems to have an important role in HCC fibrillization.\nThus, the (47)LQVVR(51) peptide seems to have an important role in HCC fibrillization.", "role": "user" }, { "content": "LQVVR", "role": "assistant" } ]

[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: Application of Augmented Reality and Robotic Technology in Broadcasting: A Survey \nChapter Title: Monitor-Based Applications \n1. Abstract of Cited Paper (BIB001): We show how a system for video-rate parallel camera tracking and 3D map-building can be readily extended to allow one or more cameras to work in several maps, separately or simultaneously. The ability to handle several thousand features per map at video-rate, and for the cameras to switch automatically between maps, allows spatially localized AR workcells to be constructed and used with very little intervention from the user of a wearable vision system. The user can explore an environment in a natural way, acquiring local maps in real-time. When revisiting those areas the camera will select the correct local map from store and continue tracking and structural acquisition, while the user views relevant AR constructs registered to that map. The method is shown working in a progressively larger environments, from desktop to large building. \n2. Abstract of Cited Paper (BIB002): In this paper, we perform a rigorous analysis of EKF-based visual-inertial odometry (VIO) and present a method for improving its performance. Specifically, we examine the properties of EKF-based VIO, and show that the standard way of computing Jacobians in the filter inevitably causes inconsistency and loss of accuracy. This result is derived based on an observability analysis of the EKF's linearized system model, which proves that the yaw erroneously appears to be observable. In order to address this problem, we propose modifications to the multi-state constraint Kalman filter (MSCKF) algorithm [1], which ensure the correct observability properties without incurring additional computational cost. Extensive simulation tests and real-world experiments demonstrate that the modified MSCKF algorithm outperforms competing methods, both in terms of consistency and accuracy. \n3. Abstract of Cited Paper (BIB003): The transition of visual-odometry technology from research demonstrators to commercial applications naturally raises the question: “what is the optimal camera for vision-based motion estimation?” This question is crucial as the choice of camera has a tremendous impact on the robustness and accuracy of the employed visual odometry algorithm. While many properties of a camera (e.g. resolution, frame-rate, global-shutter/rolling-shutter) could be considered, in this work we focus on evaluating the impact of the camera field-of-view (FoV) and optics (i.e., fisheye or catadioptric) on the quality of the motion estimate. Since the motion-estimation performance depends highly on the geometry of the scene and the motion of the camera, we analyze two common operational environments in mobile robotics: an urban environment and an indoor scene. To confirm the theoretical observations, we implement a state-of-the-art VO pipeline that works with large FoV fisheye and catadioptric cameras. We evaluate the proposed VO pipeline in both synthetic and real experiments. The experiments point out that it is advantageous to use a large FoV camera (e.g., fisheye or catadioptric) for indoor scenes and a smaller FoV for urban canyon environments.\n\nLiterature Review:", "role": "user" }, { "content": "Monitor-based display enables augmented view through a monitor or other types of screens, which generally provides the viewers the third-person perspective in front of TV sets. Figure 2 shows a typical framework of monitor-displayed AR. Firstly, the real-world image is captured by camera as the inputs; then the obtained images are processed and merged with computer-generated virtual graphics in a back-stage process; and the final augmented view is displayed through screens. Since this approach requires registering the real-world environment for correctly rendering annotation, the final displayed augmented view is always delayed. AR is firstly used as a virtual annotation on screencast of sport competitions. Virtual 1st & 10 line inserted virtual lines to indicate the yardage in American Football broadcasting in 1998. After then, AR annotation has been frequently adopted in basketball, tennis, ice hockey, etc. BIB002 3, . Recently, this AR technique is widely used to enhance appearance of broadcasting studio. Ericsson has introduced their indoor AR systems for visualizing the statistical data of sports broadcasting. By augmenting virtual contents at the front of broadcasters, they can interact with 3D virtual models and illustrate sports competition in more detail, e.g., BBC \"Match of the Day\" and BT sports. INDE display their interactive and touchable AR effect on large screens for education, entertainment, exhibition, etc. As an innovation, some AR systems insert virtual effect on the TV terminal or user side to enable viewers to choose between ordinary image or augmented view, as well as allowed them to design their personal AR effects while watching broadcasts BIB004 BIB001 BIB003 .", "role": "assistant" } ]

[ { "content": "Given an abstract from a research paper, your task is to identify and label relationships between chemical compounds and genes mentioned in the abstract.\n\nThe relationship type must be one of ['DOWNREGULATOR', 'SUBSTRATE', 'INDIRECT-REGULATOR', 'PART-OF', 'MODULATOR-ACTIVATOR', 'REGULATOR', 'INHIBITOR', 'COFACTOR', 'UPREGULATOR', 'ACTIVATOR', 'ANTAGONIST', 'NOT', 'INDIRECT-DOWNREGULATOR', 'SUBSTRATE_PRODUCT-OF', 'INDIRECT-UPREGULATOR', 'AGONIST', 'PRODUCT-OF', 'MODULATOR', 'DIRECT-REGULATOR', 'UNDEFINED', 'AGONIST-INHIBITOR', 'AGONIST-ACTIVATOR', 'MODULATOR-INHIBITOR'].\n\nPlease format your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"]. If no relations can be found, please output an empty JSON array [].\n\nAbstract:\n\nDiclofenac inhibits proliferation and differentiation of neural stem cells. Nonsteroidal anti-inflammatory drugs (NSAIDs) are widely used in clinical situations as anti-inflammatory, analgesic and antipyretic drugs. However, it is still unknown whether NSAIDs have effects on the development of the central nervous system. In the present study, we investigated the effects of NSAIDs on neural stem cell (NSC) proliferation and differentiation into neurons. In contrast to aspirin, naproxen, indomethacin and ibuprofen, treatment with diclofenac (10 microM) for 2 days induced the death of NSCs in a concentration-dependent manner. Diclofenac also inhibited the proliferation of NSCs and their differentiation into neurons. Treatment with diclofenac resulted in nuclear condensation (a morphological change due to apoptosis of NSCs) 24hr after the treatment and activated caspase-3 after 6 hr, indicating that diclofenac may cause apoptosis of neuronal cells via activation of the caspase cascade. These results suggest that diclofenac may affect the development of the central nervous system.", "role": "user" }, { "content": "[[\"diclofenac\", \"ACTIVATOR\", \"caspase-3\"], [\"diclofenac\", \"ACTIVATOR\", \"caspase\"]]", "role": "assistant" } ]

[ { "content": "You will be shown the title of a chemistry paper, together with sections excerpted from the body of the paper. The paper sections may include HTML tags like `<p>` and `</p>`; please ignore these. Your task is to write an abstract for the paper. Your response should include the abstract and no other text.\n\nTitle:\nEnantioselective Synthesis of Indolines, Benzodihydrothiophenes, and Indanes by C\\xe2\\x80\\x93H Insertion of Donor/Donor Carbenes\n\nPaper sections:\n\n<p>The insertion of metal carbenes into otherwise unreactive C–H bonds is a powerful method for the synthesis of complex molecules. Chiral metal complexes, specifically rhodium tetracarboxylates, can induce high levels of enantioselectivity for both intra- and intermolecular reactions.[1] The asymmetric C–H insertion reactions of metal carbenes flanked by electron withdrawing groups have been well-documented since Teyssie's seminal publication in 1982.[2] Recently, our group has demonstrated the utility of metal carbenes with two pendant electron donating groups, or \"donor/donor\" metal carbenes, in the asymmetric synthesis of benzodihydrofurans (Figure 1).[3]</p><p>Moreover, the requisite diazo precursor for the donor/donor carbene can be produced in situ from the parent hydrazone. Herein, we apply our methodology to the synthesis of three new classes of products, i.e. indolines, benzodihydrothiophenes and indanes.</p><p>Indolines represent a common core structure among natural products and drug discovery candidates.[4] Although these heterocycles can be prepared by a variety of strategies, formation of the C2–C3 bond by C–H insertion offers the opportunity to create two stereogenic centers.[5] Intramolecular C–H insertion has been used previously for the synthesis of indolines, however few examples of substrates containing basic nitrogen have been shown to proceed with high levels of enantioselectivity.[6] We documented the first enantioselective synthesis of an indoline from a donor/donor carbene, albeit with modest enantioselectivity on a substrate lacking a basic nitrogen atom.[3a] Recently, Zhu et. al. reported the enantioselective synthesis of indolines from donor/donor carbenes via a non-diazo approach.[5b]</p><p>A variety of indolines were synthesized with high levels of diastereo- and enantioselectivity (Figure 2). Fused indolines derived from cyclic anilines (2a-d) were formed in good to excellent er, dr, and yield. C–H Insertion into primary centers is known to be electronically unfavorable.[2, 7] However, indoline 2e was produced in high yield and modest er. Changing from a methyl to an ethyl substituent has a drastic effect on the enantioselectivity of the reaction, as indoline 2f was produced as primarily one enantiomer. This observation suggests that increased steric bulk at the insertion center plays a role in the high degree of stereoselectivity observed. An indoline derived from an N-tosyl protected amine was also tolerated (2b) allowing for further modification after deprotection. Additionally, indoline 2g derived from a free amine was also synthesized in excellent er, dr and yield. X-ray crystallography of 2c indicated that the relative and absolute configurations of the product were consistent with the sense of induction observed for the formation of benzodihydrofurans.[3a, 8]</p><p>Over the course of our synthesis of indolines, it became apparent that unsymmetrical aniline substrates presented the opportunity to insert into two chemically different C–H bonds. X-ray crystal structures by Fürstner show that the π system of the pendant phenyl group is in conjugation with the carbene center.[9] Additionally, computational experiments in our previous work with benzodihydrofurans have demonstrated that the electron donation afforded by the phenyl ring reduces the electrophilicity of the resultant metal carbene and stabilizes its formation.[3b] These factors motivate a stepwise reaction mechanism unique to our donor/donor system. In contrast, the mechanism of donor/acceptor substituted carbenes is known to be concerted asynchronous.[10] With this mechanistic framework in mind we set out to test the effect of sterics and electronics on the regiochemistry of C–H insertion reactions to form indolines. The insertion begins with a hydride transfer followed by rapid collapse of the resultant zwitterionic intermediate II.[3b] As such, insertion is favored by substituents that stabilize cations at the insertion carbon (Scheme 1). However, steric demand near the insertion carbon can be unfavorable, especially with crowded chiral catalysts.</p><p>To study the effects of sterics and electronics on the regioselectivity of this chemistry, we synthesized two unsymmetrical hydrazones (5a, b) with both sterically and electronically favorable insertion sites (Table 1). In the presence of Rh2(OAc)4, insertion at the benzylic carbon is favorable, to form 7a (entry 1). Treatment with Rh2(Mes)4 and Rh2(R-PTAD)4, shows a decrease in selectivity for the electronically favorable center as the bulk of the catalyst increases (entries 2, 3). When methyl is contrasted with isopropyl (5b), selectivity for the less substituted carbon is modest (entry 4) and use of the Rh2(Mes)4 catalyst heavily favors methyl insertion (entry 5). Finally, the reaction of 5b with Rh2(R-PTAD)4 also favors methyl insertion to a lesser extent (entry 6). The results indicate that both steric and electronic factors compete for the most favorable insertion pathway.</p><p>Benzodihydrothiophenes form an interesting class of heterocycles for which there are currently few stereoselective synthetic methods.[11] Growing interest in sulfur-containing heterocycles as anti-tumor agents emphasizes the need for new method development in this area.[12] To date, there is only a single report of a benzodihydrothiophene synthesis employing rhodium carbenes with acceptor-substituted diazo compounds.[13] The authors of this study hypothesize that the lack of development of this methodology is due to a propensity of the highly nucleophilic sulfur atom to attack the carbene directly to form an ylide.[14] Due to the reduced electrophilicity of our donor/donor carbenes we are able to synthesize a variety of benzodihydrothiophenes with excellent stereocontrol and high yields.</p><p>Similarly to benzodihydrofurans,[3b]\n4a, b were synthesized with excellent stereoselectivity and yield (Figure 3). Hydrazone 3c was selectively oxidized to the diazo compound with MnO2 in the presence of a benzylic alcohol. Furthermore, the corresponding diazo-alcohol was tolerated well under our reaction conditions, creating a useful chemical handle for further modification without the use of a protecting group (4c). Sterically crowded insertion centers were also tolerated allowing access to novel alkyl and spirocyclic compounds 4d-f. In contrast, poor selectivity was observed with 4g. This result supports our hypothesis that the degree of stereoselectivity observed corresponds to the presence of steric bulk near the insertion center as shown with indolines. Interestingly, with sufficient activation from the neighboring acetal, six-membered ring formation (4h) was achieved in high yield and er.</p><p>Indanes are rigid carbacycles that feature prominently in both natural products and in drug discovery. Unlike their heterocyclic counterparts, the electron-neutral benzene and benzylic carbon are less easily oxidized by enzymes responsible for drug clearance.[15] Enantioselective synthesis of indanes has been achieved primarily by asymmetric reduction of indenes.[16] Hashimoto and Lei have reported the enantioselective synthesis of indanes by C–H insertion of donor/acceptor carbenes.[17] In our seminal publication, we demonstrated that the formation of indanes by C–H insertion of donor/donor metal carbenes was possible in good yield and with a modest degree of stereoselectivity.[3a] In this work, we expand the scope of this chemistry to include a variety of indanes in excellent yield and selectivity.</p><p>Aliphatic spirocyclic five- and six-membered rings were particularly effective (Figure 4A, 9a, c). Heteroatoms were also tolerated to generate the corresponding spirocycles 9d, e including a Boc-protected amine as a chemical handle.[8] Disubstitution at the inserting carbon creates a high level of steric crowding, yet stabilizes carbocation formation at the insertion center more readily. As such, these substrates react to form quaternary carbons in high yield and with high levels of stereoselectivity (9b). The absolute configuration of the new stereogenic center was shown to be S upon treatment with Rh2(R-PTAD)4, in agreement with the sense of induction for both benzodihydrofurans and indolines.</p><p>Substitution of the carbene pendant groups with halogens was also tolerated with excellent selectivity (9f, g). Furthermore, J-values of the relevant protons of these products were consistent with the cis diastereomer observed both in this and in our previous work.[3a] We envisioned 9f as the direct synthetic precursor to a class of indanes patented as an estrogen receptor agonist for the treatment of breast, prostate and ovarian cancers.[18] Treatment of substrate 9f under modified Ullman coupling conditions allowed us to access the first enantioselective synthesis of drug lead 11a[19] in 34% overall yield (Figure 4B).</p><p>In conclusion, we have expanded the C–H insertion methodology of donor/donor metal carbenes to the enantioselective synthesis of a variety of indolines, benzodihydrothiophenes, and indanes. Preliminary results suggest the regiochemistry of C–H insertions to form indolines is influenced by competition between electronics that favor carbocation stability and the steric demands of catalyst and substrate. Our methodology allows for the facile synthesis of complex and difficult-to-access benzodihydrothiophenes. Furthermore, insertion into deactivated C–H bonds was accomplished, yielding a variety of indanes. Finally, we demonstrated the utility of this chemistry by carrying out the first highly enantioselective synthesis of patented drug lead 11a in good overall yield.[19]</p>\n\nExperimental Section\n<p>Experimental procedures and compound characterization can be found in the Supporting Information (PDF). 1H and 13C NMR spectra for all new compounds and HPLC traces for all enantiomerically enriched insertion products (PDF). X-ray data for compound 2c (CIF) and 9d (CIF).</p>", "role": "user" }, { "content": "We employ a single catalyst/oxidant system to enable the asymmetric syntheses of indolines, benzodihydrothiophenes, and indanes by C\\xe2\\x80\\x93H insertion of donor/donor carbenes. This methodology enables the rapid construction of densely substituted five-membered rings that form the core of many drug targets and natural products. Furthermore, oxidation of hydrazones to the corresponding diazo compounds proceeds in situ, enabling a relatively facile one- or two-pot protocol in which isolation of potentially explosive diazo alkanes is avoided. Regioselectivity studies were performed to determine the impact of sterics and electronics in donor/donor metal carbene C\\xe2\\x80\\x93H insertions to form indolines. This methodology was applied to a variety of substrates in high yield, diastereomeric, and enantiomeric ratios and to the synthesis of a patented indane estrogen receptor agonist with anti-cancer activity.", "role": "assistant" } ]

[ { "content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the function of the protein tafazzin?\n\nContext: Tafazzin is a transacylase that transfers acyl chains with unsaturated fatty acids from phospholipids to monolysocardiolipin to generate cardiolipin with unsaturated fatty acids.\nTafazzin (EC 2.3.1.23) is a Phospholipid Transacylase involved in Cardiolipin remodeling on mitochondrial membrane and coded by TAZ gene (Cytogenetic Location: Xq28) in human.\nTafazzin is a transacylase that affects cardiolipin fatty acid composition and mitochondrial function.\nTafazzin is a mitochondrial phospholipid transacylase, and its mutations cause Barth syndrome (BTHS).\nTafazzin (TAZ) is a phospholipid transacylase that catalyzes the remodeling of cardiolipin, a mitochondrial phospholipid required for oxidative phosphorylation.\nTafazzin expression induced a new enzymatic function in Sf9 cell mitochondria, namely 1-palmitoyl-2-[14C]linoleoyl-phosphatidylcholine:monolysocardiolipin linoleoyltransferase.\nAmong the human isoforms, only full-length tafazzin (FL) and tafazzin lacking exon 5 (Delta5) had transacylase activity, and only these two isoforms were able to restore a normal cardiolipin pattern, normal respiratory activity of mitochondria, and male fertility in tafazzin-deficient flies.\nTafazzin is a mitochondrial transacylase required for cardiolipin remodeling.\nTafazzin is a putative enzyme that is involved in cardiolipin metabolism, it may carry mutations responsible for Barth syndrome.\nTafazzin is an enzyme that remodels saturated fatty acyl chains within CL to unsaturated fatty acyl chains, loss of function mutations in the TAZ gene encoding tafazzin are causal for the inherited cardiomyopathy Barth syndrome\nThe tafazzin gene encodes a phospholipid-lysophospholipid transacylase involved in cardiolipin metabolism, but it is not known why it forms multiple transcripts as a result of alternative splicing.\nFurthermore, the data show that the expression of human tafazzin in flies creates cardiolipin with a Drosophila pattern, suggesting that the characteristic fatty acid profile of cardiolipin is not determined by the substrate specificity of tafazzin.\nTafazzin is a transacylase that affects cardiolipin fatty acid composition and mitochondrial function.", "role": "user" }, { "content": "Tafazzin is a phospholipid transacylase that transfers acyl chains with unsaturated fatty acids from phospholipids to monolysocardiolipin to generate cardiolipin with unsaturated fatty acids on mitochondrial membrane.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\": [\"Arsenic\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nHerbacetin induces apoptosis in HepG2 cells: Involvements of ROS and PI3K/Akt pathway. Herbacetin (HER) is a natural flavonoid compound that can be extracted from Ramose Scouring Rush Herb, and its biological and pharmacological activities lack of corresponding attention. In this study, the apoptotic effect of HER against the human hepatoma cell line (HepG2) was investigated. The results showed that HepG2 cells apoptosis occurred in a dose-dependent manner within 48h incubated with HER, which was confirmed by DNA fragmentation, nuclear shrinkage, and poly (ADP-ribose) polymerase (PARP) cleavage. HER at 25-100μM induced a mitochondria-dependent apoptotic pathway associated with Bcl-2/Bax ratio decrease, mitochondrial membrane potential (ΔΨ) collapse, cytochrome c release, and caspase-3 activation. Increasing expression of peroxisome proliferator-activated receptor-γ coactivator 1α (PGC-1α) was also observed in HER-treated cells. Furthermore, the addition of a ROS inhibitor (N-Acetyl-l-cysteine, NAC) significantly attenuated the apoptosis induced by HER and also blocked the expression of PGC-1α protein. Additionally, HER effectively inhibited the phosphorylation of Akt and the phosphatidylinositol-3 kinase (PI3K) inhibitor LY294002 increased the inhibition effect of HER on Akt phosphorylation. These findings provide evidences that HER induces HepG2 apoptosis in a ROS-mediated mitochondria-dependent manner that correlate with the inactivation of the PI3K/Akt pathway.", "role": "user" }, { "content": "{\"Chemical\": [\"LY294002\", \"flavonoid\", \"phosphatidylinositol\", \"NAC\", \"Herbacetin\", \"poly (ADP-ribose)\", \"HER\", \"N-Acetyl-l-cysteine\"]}", "role": "assistant" } ]

[ { "content": "You will be shown an excerpt from a computer science research paper, followed by a question about the paper. Please answer the question given the context. Do not include any text in your response other than the answer.\n\nContext: For many-shot recognition, we adopt the benchmark suite proposed in the transfer learning study [28], which includes the target datasets FGVC Aircraft [38], Caltech-101 [15], Stanford Cars [29], CIFAR10 [30], CIFAR-100 [30], DTD [9], Oxford 102 Flowers [41], Food-101 [3], Oxford-IIIT Pets [43], SUN397 [59], and Pascal VOC2007 [14]. These datasets cover a wide range of classification tasks, including texture, scene and fine/coarse-grained object classification. While they are all in the ‘many-shot’ regime, they include significant variety in amount of training data (2,000-75,000 images), and cardinality of classification (10-397 classes).\n\nQuestion: [Section 4.2]: What characteristics do the aforementioned datasets in transfer learning have?", "role": "user" }, { "content": "A variety of range of classification tasks, including texture, scene", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nThis paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources.\nWe design a Dynamic Point-cloud Convolution (D-Conv) operator as the core component of CloudLSTMs, which performs convolution directly over point-clouds and extracts local spatial features from sets of neighboring points that surround different elements of the input.\nThis operator maintains the permutation invariance of sequence-to-sequence learning frameworks, while representing neighboring correlations at each time step -- an important aspect in spatiotemporal predictive learning.\nThe D-Conv operator resolves the grid-structural data requirements of existing spatiotemporal forecasting models and can be easily plugged into traditional LSTM architectures with sequence-to-sequence learning and attention mechanisms.\n \nWe apply our proposed architecture to two representative, practical use cases that involve point-cloud streams, i.e. mobile service traffic forecasting and air quality indicator forecasting.\nOur results, obtained with real-world datasets collected in diverse scenarios for each use case, show that CloudLSTM delivers accurate long-term predictions, outperforming a variety of neural network models.\nPoint-cloud stream forecasting aims at predicting the future values and/or locations of data streams generated by a geospatial point-cloud S, given sequences of historical observations (Shi & Yeung, 2018) .\nExample data sources include mobile network antennas that serve the traffic generated by ubiquitous mobile services at city scale (Zhang et al., 2019b) , sensors that monitor the air quality of a target region (Cheng et al., 2018) , or moving crowds that produce individual trajectories.\nUnlike traditional spatiotemporal forecasting on grid-structural data, like precipitation nowcasting (Shi et al., 2015) or video frame prediction (Wang et al., 2018) , point-cloud stream forecasting needs to operate on geometrically scattered sets of points, which are irregular and unordered, and encapsulate complex spatial correlations.\nWhile vanilla Long Short-term Memories (LSTMs) have modest abilities to exploit spatial features (Shi et al., 2015) , convolution-based recurrent neural network (RNN) models, such as ConvLSTM (Shi et al., 2015) and PredRNN++ (Wang et al., 2018) , are limited to modeling grid-structural data, and are therefore inappropriate for handling scattered point-clouds.\n: Different approaches to geospatial data stream forecasting: predicting over input data streams that are inherently grid-structured, e.g., video frames using ConvLSTMs (top); mapping of pointcloud input to a grid, e.g., mobile network traffic collected at different antennas in a city, to enable forecasting using existing neural network structures (middle); forecasting directly over point-cloud data streams using historical information (as above, but without pre-processing), as proposed in this paper (bottom).\npermutations for the features (Li et al., 2018) .\nThrough this, the proposed PointCNN leverages spatial-local correlations of point clouds, irrespective of the order of the input.\nNotably, although these architectures can learn spatial features of point-clouds, they are designed to work with static data, thus have limited ability to discover temporal dependencies.\nWe introduce CloudLSTM, a dedicated neural model for spatiotemporal forecasting tailored to pointcloud data streams.\nThe CloudLSTM builds upon the DConv operator, which performs convolution over point-clouds to learn spatial features while maintaining permutation invariance.\nThe DConv simultaneously predicts the values and coordinates of each point, thereby adapting to changing spatial correlations of the data at each time step.\nDConv is flexible, as it can be easily combined with various RNN models (i.e., RNN, GRU, and LSTM), Seq2seq learning, and attention mechanisms.", "role": "user" }, { "content": "This paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Finding\", \"Bacterium\", \"ProfessionalOrOccupationalGroup\", \"InjuryOrPoisoning\", \"Eukaryote\", \"BodySystem\", \"Virus\", \"ResearchActivity\", \"BodySubstance\", \"PopulationGroup\", \"Chemical\", \"AnatomicalStructure\", \"SpatialConcept\", \"HealthCareActivity\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Food\", \"ClinicalAttribute\", \"MedicalDevice\", \"BiologicFunction\", \"IntellectualProduct\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nBiological Characteristics of H9N2 Avian Influenza Viruses from Healthy Chickens in Shanghai, China BACKGROUND H9N2 avian influenza viruses that circulate in domestic poultry in eastern China pose challenges to human health. However, few studies have compared the biological characteristics of H9N2 viruses isolated from healthy chickens in Shanghai. MATERIAL AND METHODS Three H9N2 viruses - CK/SH/Y1/07, CK/SH/Y1/02, and CK/SH/23/13 - isolated from healthy chickens in Shanghai between 2002 and 2013, were selected and their biological characteristics were determined. RESULTS All 3 H9N2 viruses showed a preference for both the avian - and human-like receptors, and they replicated well in MDCK and A549 cells. All H9N2 viruses were non-pathogenic to mini-pigs and were detected in the trachea and lung tissues. The CK/SH/Y1/07 and CK/SH/Y1/02 viruses were transmitted to mini-pigs through direct-contact or respiratory droplet exposure, but CK/SH/23/13 virus was not. CONCLUSIONS These results suggest that H9N2 viruses isolated from healthy chickens in Shanghai efficiently replicate and transmit among pigs and other mammals.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"lung tissues\", \"trachea\", \"MDCK\"], \"Bacterium\": [], \"BiologicFunction\": [\"direct-contact\", \"droplet exposure\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"human-like receptors\", \"avian\"], \"ClinicalAttribute\": [], \"Eukaryote\": [\"pigs\", \"poultry\", \"mini-pigs\", \"chickens\", \"mammals\", \"Chickens\", \"human\"], \"Finding\": [\"non-pathogenic\", \"detected\"], \"Food\": [], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"studies\"], \"SpatialConcept\": [\"eastern China\", \"China\", \"Shanghai\"], \"Virus\": [\"A549 cells\", \"CK/SH/23/13\", \"CK/SH/23/13 virus\", \"H9N2 avian influenza viruses\", \"CK/SH/Y1/07\", \"H9N2 viruses\", \"H9N2 Avian Influenza Viruses\", \"CK/SH/Y1/02 viruses\", \"CK/SH/Y1/02\"]}", "role": "assistant" } ]

[ { "content": "You will be presented with a citation segment from the section of an NLP research paper, as well as the context surrounding that citation. Classify the intent behind this citation by choosing from one of the following categories:\n- Background: provides context or foundational information related to the topic.\n- Extends: builds upon the cited work.\n- Uses: applies the methods or findings of the cited work.\n- Motivation: cites the work as inspiration or rationale for the research.\n- CompareOrContrast: compares or contrasts the cited work with others.\n- FutureWork: cites the work as a direction for future research.\n\nYour answer should be a single word from the following list of options: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. Do not include any other text in your response.\n\nSection Title:\nintroduction\n\nContext before the citation:\nBut their importance has grown far beyond machine translation: for instance, transferring annotations between languages (Yarowsky and Ngai 2001; Hwa et al. 2005; Ganchev, Gillenwater, and Taskar 2009); discovery of paraphrases (Bannard and Callison-Burch 2005); and joint unsupervised POS and parser induction across languages (Snyder and Barzilay 2008). MT system combination (Matusov, Ueffing, and Ney 2006). Word alignments are used primarily for extracting minimal translation units for machine translation (MT) (e.g., phrases [Koehn, Och, and Marcu 2003] and rules [Galley et al. 2004; Chiang et al. 2005]) as well as for \u0000\u0000\u0000\u0000\u0000\u0000\n\nCitation Sentence:\nBut their importance has grown far beyond machine translation : for instance , transferring annotations between languages ( Yarowsky and Ngai 2001 ; Hwa et al. 2005 ; Ganchev , Gillenwater , and Taskar 2009 ) ; discovery of paraphrases ( Bannard and Callison-Burch 2005 ) ; and joint unsupervised POS and parser induction across languages ( Snyder and Barzilay 2008 ) .\n\nContext after the citation:\nIBM Models 1 and 2 and the HMM are simple and tractable probabilistic models, which produce the target sentence one target word at a time by choosing a source word and generating its translation. IBM Models 3, 4, and 5 attempt to capture fertility (the tendency of each source word to generate several target words), resulting in probabilistically deficient, intractable models that require local heuristic search and are difficult to implement and extend. Many researchers use the GIZA++ software package (Och and Ney 2003) as a black box, selecting IBM Model 4 as a compromise between alignment quality and efficiency. All of the models are asymmetric (switching target and source languages produces drastically different results) and the simpler models (IBM Models 1, 2, and HMM) do not enforce bijectivity (the majority of words translating as a single word).", "role": "user" }, { "content": "Motivation", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: What is the outcome of TAF10 interacting with the GATA1 transcription factor?\n\nContext: TAF10 Interacts with the GATA1 Transcription Factor and Controls Mouse Erythropoiesis.\nwe show that TAF10 interacts directly with GATA1 and that TAF10 is enriched on the GATA1 locus in human fetal erythroid cells\nTAF10 Interacts with the GATA1 Transcription Factor and Controls Mouse Erythropoiesis", "role": "user" }, { "content": "Control of Mouse Erythropoiesis", "role": "assistant" } ]

[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: mask-wearing can lessen COVID-19 severity\n\nAbstract:\nIn the context of Coronavirus Disease (2019) (COVID-19) cases globally, there is a lack of consensus across cultures on whether wearing face masks is an effective physical intervention against disease transmission.\nThis study 1) illustrates transmission routes of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2); 2) addresses controversies surrounding the mask from perspectives of attitude, effectiveness, and necessity of wearing the mask with evidence that the use of mask would effectively interrupt the transmission of infectious diseases in both hospital settings and community settings; and 3) provides suggestion that the public should wear the mask during COVID-19 pandemic according to local context.\nTo achieve this goal, government should establish a risk adjusted strategy of mask use to scientifically publicize the use of masks, guarantee sufficient supply of masks, and cooperate for reducing health resources inequities.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"This study 1) illustrates transmission routes of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2); 2) addresses controversies surrounding the mask from perspectives of attitude, effectiveness, and necessity of wearing the mask with evidence that the use of mask would effectively interrupt the transmission of infectious diseases in both hospital settings and community settings; and 3) provides suggestion that the public should wear the mask during COVID-19 pandemic according to local context.\"]}", "role": "assistant" } ]

[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Does ESN364 activate the hypothalamic-pituitary-gonadal axis?\n\nContext: Oral administration of the NK3R antagonist, ESN364, suppressed the hypothalamic-pituitary-gonadal axis in healthy volunteers by selective modulation of gonadotropin secretion, leading to a restrained decrease in ovarian hormone levels in women.", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "content": "You will be presented with a citation sentence from a research paper. Classify the intent behind this citation by choosing from one of the following categories:\n\n- Method: Cites the paper for its methodology or procedure.\n- Background: Cites the paper to provide background information.\n- Result: Cites the paper for its findings or results.\n\nYour answer should be a single word from the following list of options: [\"Method\", \"Background\", \"Result\"]. Do not include any other text in your response.\n\nCitation sentence:\n\nNowadays, there are only a few studies that have a systemic view on these accidents (Bentley 2008) and which try, by using detailed analysis (Gao and Abeysekera 2004, Leclercq and Thouy 2004, Bentley et al. 2005, 2006, Derosier 2005), to enlighten contributing factors and root causes involved in…", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: From which sequence does the Alu repeat originate from?\n\nContext: The origin of Alu-derived minisatellites appears to have been mediated by short flanking repeats, as first proposed by Haber and Louis\nFinally, we propose that the origin of Alu subfamilies in human populations may be related to evolution of chromosome Y.\nOur analysis indicates that about 60 Myr ago, before the prosimian divergence, free left and right monomers formed an Alu heterodimer connected by a 19-nucleotide-long A-rich linker.\nthe presence of Alu-like structural motifs supports the hypothesis of the monophyletic origin of Alu and B1 repeats, i.e., from a common 7SL RNA-derived retroposing monomeric element\nAlu elements are each a dimer of similar, but not identical, fragments of total size about 300 bp, and originate from the 7SL RNA gene.", "role": "user" }, { "content": "7SL RNA", "role": "assistant" } ]

[ { "content": "You will be given an abstract from a computer science research paper. Given the abstract, your task is to extract all unique relationships between entities of the following, and ONLY the following, types:\n\n- \"USED-FOR\": For instance, \"Our method models user proficiency\" -> [\"method\", \"user proficiency\", \"USED-FOR\"].\n- \"EVALUATE-FOR\": For instance, \"We evaluate our method using F1-measure\" -> [\"F1-measure\", \"method\", \"EVALUATE-FOR\"].\n- \"FEATURE-OF\": For instance, \"prior knowledge of the model\" -> [\"prior knowledge\", \"model\", \"FEATURE-OF\"].\n- \"HYPONYM-OF\": For instance, \"TUIT is a software library\" -> [\"TUIT\", \"software library\", \"HYPONYM-OF\"].\n- \"PART-OF\": For instance, \"We incorporate NLU module into the system\" -> [\"NLU module\", \"system\", \"PART-OF\"].\n- \"COMPARE\": For instance, \"Unlike the quantitative prior, the qualitative prior is often ignored\" -> [\"quantitative prior\", \"qualitative prior\", \"COMPARE\"].\n- \"CONJUNCTION\": For instance, \"obtained from human expert or knowledge base\" -> [\"human expert\", \"knowledge base\", \"CONJUNCTION\"].\n\nFormat your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<Entity_B>\", \"<RELATION_A_B>\"]. An example output might look like:\n\n[[\"neural networks\", \"classification\", \"USED-FOR\"], [\"neuron\", \"neural network\", \"PART-OF\"]].\n\nIf no relations are found, please return an empty JSON array \"[]\".\n\nAbstract:\n\nThis paper reports a completed stage of ongoing research at the University of York. Landsbergen 's advocacy of analytical inverses for compositional syntax rules encourages the application of Definite Clause Grammar techniques to the construction of a parser returning Montague analysis trees. A parser MDCC is presented which implements an augmented Friedman-Warren algorithm permitting post referencing * and interfaces with a language of intenslonal logic translator LILT so as to display the derivational history of corresponding reduced IL formulae. Some familiarity with Montague 's PTQ and the basic DCG mechanism is assumed.", "role": "user" }, { "content": "[[\"Montague \\u0027s PTQ\", \"Definite Clause Grammar techniques\", \"CONJUNCTION\"], [\"post referencing\", \"augmented Friedman-Warren algorithm\", \"FEATURE-OF\"], [\"analytical inverses\", \"compositional syntax rules\", \"USED-FOR\"], [\"derivational history\", \"intenslonal logic translator LILT\", \"USED-FOR\"], [\"Definite Clause Grammar techniques\", \"parser returning Montague analysis trees\", \"USED-FOR\"], [\"analytical inverses\", \"Definite Clause Grammar techniques\", \"USED-FOR\"], [\"reduced IL formulae\", \"derivational history\", \"FEATURE-OF\"], [\"augmented Friedman-Warren algorithm\", \"parser MDCC\", \"USED-FOR\"]]", "role": "assistant" } ]

[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: A Survey on Data Processing Methods and Cloud Computation \nChapter Title: A. Graph Theory \n1. Abstract of Cited Paper (BIB001): In this work, we developed an algorithm for the integrated analysis of multiple high-dimensional data matrices based on sparse rank-one matrix approximations. The algorithm approximates multiple data matrices with rank one outer products composed of sparse left singular-vectors that are unique to each matrix and a right singular-vector that is shared by all of the data matrices. The right-singular vector represents a signal we wish to detect in the row-space of each matrix. The non-zero components of the resulting left-singular vectors identify rows of each matrix that in aggregate provide a sparse linear representation of the shared right-singular vector. This sparse representation facilitates downstream interpretation and validation of the resulting model based on the rows selected from each matrix. False discovery rate is used to select an appropriate l1 penalty parameter that imposes sparsity on the left singular-vector but not the common right singular-vector of the joint approximation. Since a given multi-modal data set (MMDS) may contain multiple signals of interest the algorithm is iteratively applied to the residualized version of original data to sequentially capture and model each distinct signal in terms of rows from the different matrices. We show that the algorithm outperforms standard singular value decomposition over a wide range of simulation scenarios in terms of detection accuracy. Analysis of real data for ovarian and liver cancer resulted in compact gene expression signatures that were predictive of clinical outcomes and highly enriched for cancer related biology.\n\nLiterature Review:", "role": "user" }, { "content": "Graph theory, which has been used to develop networks in fields such as sociology and biology, is discussed for its application to neural networking in BIB002 . The authors contribute to the field of Integrated Information Theory of Consciousness by increasing the efficiency of calculating integrated information for neural data. They offer a Maximum Modularity Partition as opposed to comparable studies that use a Minimum Information Partition (MIP). Their method is \"based on the graph-theoretic notion of modularity\" and is an improvement over the MIP method in terms of cost efficiency and real data application. Meanwhile, authors in BIB001 focus on the management of disease through mobile health platforms by offering an improvement in \"optimal dynamic treatment regimes\" of precision medicine patients. They accommodate an infinite time scale acting as a Markov decision process, with \"minimal assumptions about the data-generating model\". Further, to increase the efficacy of mobile health (mHealth) treatment management, they create a new reinforcement learning method to accommodate data obtained from mobile technologies. Thus, they offer \"V-learning\" as an alternative to the conventional Q-learning, which requires model free reinforcement [27] , by instead selecting among a pre-specified class of policies.", "role": "assistant" } ]

[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: Respiratory failure remained the leading cause of death (69.5%), followed by sepsis/multiple organ dysfunction syndrome (MOF) (28.0%), cardiac failure (14.6%), hemorrhage (6.1%)\n\nAbstract:\nThe ongoing outbreak of COVID-19 has been expanding worldwide.\nAs of 17 April 2020, the death toll stands at a sobering 147,027 and over two million cases, this has been straining the health care systems all over.\nRespiratory failure has been cited as the major cause of death but here we present a case about a patient who instead succumbed to severe metabolic acidosis with multiple organ failure.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Respiratory failure has been cited as the major cause of death but here we present a case about a patient who instead succumbed to severe metabolic acidosis with multiple organ failure.\"]}", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: What happens to retrotransposons during ageing?\n\nContext: Senescent cells undergo dramatic alterations to their chromatin landscape that affect genome accessibility and their transcriptional program. These include the loss of DNA-nuclear lamina interactions, the distension of centromeres, and changes in chromatin composition that can lead to the activation of retrotransposons.\nRetrotransposons are activated as organisms age, based on work from several model systems.", "role": "user" }, { "content": "Activation", "role": "assistant" } ]

[ { "content": "You will be shown sections from a scientific research paper, together with a question about the paper. This is an extractive question-answering task, where you must find and extract relevant text spans directly from the paper to answer the question. Your response should strictly be a `json` object with two fields:\n\n\"answer\": An array of strings extracted directly from the paper which, collectively, answer the question.\n\"evidence\": An array of strings. Each should be an excerpt from the paper, in which one or more of the extracted answers can be found.\n\nFor example, for the question \"What baselines did the authors compare against?\", a sample response might be:\n{\n \"answer\": [\"BERT\", \"RoBERTa\"],\n \"evidence\": [\"In our experiments, we compare the performance of our model against BERT and RoBERTa.\"]\n}\n\nDo not include any text in your response other than the json.\n\nIf the question is unanswerable given the provided excerpts, respond with the single word \"null\".\n\nPaper: S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension\n\nIn this paper, we present a novel approach to machine reading comprehension for the MS-MARCO dataset. Unlike the SQuAD dataset that aims to answer a question with exact text spans in a passage, the MS-MARCO dataset defines the task as answering a question from multiple passages and the words in the answer are not necessary in the passages. We therefore develop an extraction-then-synthesis framework to synthesize answers from extraction results. Specifically, the answer extraction model is first employed to predict the most important sub-spans from the passage as evidence, and the answer synthesis model takes the evidence as additional features along with the question and passage to further elaborate the final answers. We build the answer extraction model with state-of-the-art neural networks for single passage reading comprehension, and propose an additional task of passage ranking to help answer extraction in multiple passages. The answer synthesis model is based on the sequence-to-sequence neural networks with extracted evidences as features. Experiments show that our extraction-then-synthesis method outperforms state-of-the-art methods.\n\nIntroduction\nMachine reading comprehension BIBREF0 , BIBREF1 , which attempts to enable machines to answer questions after reading a passage or a set of passages, attracts great attentions from both research and industry communities in recent years. The release of the Stanford Question Answering Dataset (SQuAD) BIBREF0 and the Microsoft MAchine Reading COmprehension Dataset (MS-MARCO) BIBREF1 provides the large-scale manually created datasets for model training and testing of machine learning (especially deep learning) algorithms for this task. There are two main differences in existing machine reading comprehension datasets. First, the SQuAD dataset constrains the answer to be an exact sub-span in the passage, while words in the answer are not necessary in the passages in the MS-MARCO dataset. Second, the SQuAD dataset only has one passage for a question, while the MS-MARCO dataset contains multiple passages.\nExisting methods for the MS-MARCO dataset usually follow the extraction based approach for single passage in the SQuAD dataset. It formulates the task as predicting the start and end positions of the answer in the passage. However, as defined in the MS-MARCO dataset, the answer may come from multiple spans, and the system needs to elaborate the answer using words in the passages and words from the questions as well as words that cannot be found in the passages or questions.\nTable 1 shows several examples from the MS-MARCO dataset. Except in the first example the answer is an exact text span in the passage, in other examples the answers need to be synthesized or generated from the question and passage. In the second example the answer consists of multiple text spans (hereafter evidence snippets) from the passage. In the third example, the answer contains words from the question. In the fourth example, the answer has words that cannot be found in the passages or question. In the last example, all words are not in the passages or questions.\nIn this paper, we present an extraction-then-synthesis framework for machine reading comprehension shown in Figure 1 , in which the answer is synthesized from the extraction results. We build an evidence extraction model to predict the most important sub-spans from the passages as evidence, and then develop an answer synthesis model which takes the evidence as additional features along with the question and passage to further elaborate the final answers.\nSpecifically, we develop the answer extraction model with state-of-the-art attention based neural networks which predict the start and end positions of evidence snippets. As multiple passages are provided for each question in the MS-MARCO dataset, we propose incorporating passage ranking as an additional task to improve the results of evidence extraction under a multi-task learning framework. We use the bidirectional recurrent neural networks (RNN) for the word-level representation, and then apply the attention mechanism BIBREF2 to incorporate matching information from question to passage at the word level. Next, we predict start and end positions of the evidence snippet by pointer networks BIBREF3 . Moreover, we aggregate the word-level matching information of each passage using the attention pooling, and use the passage-level representation to rank all candidate passages as an additional task. For the answer synthesis, we apply the sequence-to-sequence model to synthesize the final answer based on the extracted evidence. The question and passage are encoded by a bi-directional RNN in which the start and end positions of extracted snippet are labeled as features. We combine the question and passage information in the encoding part to initialize the attention-equipped decoder to generate the answer.\nWe conduct experiments on the MS-MARCO dataset. The results show our extraction-then-synthesis framework outperforms our baselines and all other existing methods in terms of ROUGE-L and BLEU-1.\nOur contributions can be summarized as follows:\n\nOur Approach\nFollowing the overview in Figure 1 , our approach consists of two parts as evidence extraction and answer synthesis. The two parts are trained in two stages. The evidence extraction part aims to extract evidence snippets related to the question and passage. The answer synthesis part aims to generate the answer based on the extracted evidence snippets. We propose a multi-task learning framework for the evidence extraction shown in Figure 15 , and use the sequence-to-sequence model with additional features of the start and end positions of the evidence snippet for the answer synthesis shown in Figure 3 .\n\nGated Recurrent Unit\nWe use Gated Recurrent Unit (GRU) BIBREF18 instead of basic RNN. Equation 8 describes the mathematical model of the GRU. $r_t$ and $z_t$ are the gates and $h_t$ is the hidden state. \n$$z_t &= \\sigma (W_{hz} h_{t-1} + W_{xz} x_t + b_z)\\nonumber \\\\\nr_t &= \\sigma (W_{hr} h_{t-1} + W_{xr} x_t + b_r)\\nonumber \\\\\n\\hat{h_t} &= \\Phi (W_h (r_t \\odot h_{t-1}) + W_x x_t + b)\\nonumber \\\\\nh_t &= (1-z_t)\\odot h_{t-1} + z_t \\odot \\hat{h_t}$$ (Eq. 8) \n\nDataset and Evaluation Metrics\nFor the MS-MARCO dataset, the questions are user queries issued to the Bing search engine and the context passages are from real web documents. The data has been split into a training set (82,326 pairs), a development set (10,047 pairs) and a test set (9,650 pairs).\nThe answers are human-generated and not necessarily sub-spans of the passages so that the metrics in the official tool of MS-MARCO evaluation are BLEU BIBREF21 and ROUGE-L BIBREF22 . In the official evaluation tool, the ROUGE-L is calculated by averaging the score per question, however, the BLEU is normalized with all questions. We hold that the answer should be evaluated case-by-case in the reading comprehension task. Therefore, we mainly focus on the result in the ROUGE-L.\n\nResult\nTable 2 shows the results on the MS-MARCO test data. Our extraction model achieves 41.45 and 44.08 in terms of ROUGE-L and BLEU-1, respectively. Next we train the model 30 times with the same setting, and select models using a greedy search. We sum the probability at each position of each single model to decide the ensemble result. Finally we select 13 models for ensemble, which achieves 42.92 and 44.97 in terms of ROUGE-L and BLEU-1, respectively, which achieves the state-of-the-art results of the extraction model. Then we test our synthesis model based on the extracted evidence. Our synthesis model achieves 3.78% and 3.73% improvement on the single model and ensemble model in terms of ROUGE-L, respectively. Our best result achieves 46.65 in terms of ROUGE-L and 44.78 in terms of BLEU-1, which outperforms all existing methods with a large margin and are very close to human performance. Moreover, we observe that our method only achieves significant improvement in terms of ROUGE-L compared with our baseline. The reason is that our synthesis model works better when the answer is short, which almost has no effect on BLEU as it is normalized with all questions.\nSince answers on the test set are not published, we analyze our model on the development set. Table 3 shows results on the development set in terms of ROUGE-L. As we can see, our method outperforms the baseline and several strong state-of-the-art systems. For the evidence extraction part, our proposed multi-task learning framework achieves 42.23 and 44.11 for the single and ensemble model in terms of ROUGE-L. For the answer synthesis, the single and ensemble models improve 3.72% and 3.65% respectively in terms of ROUGE-L. We observe the consistent improvement when applying our answer synthesis model to other answer span prediction models, such as BiDAF and Prediction.\n\nDiscussion\nWe analyze the result of incorporating passage ranking as an additional task. We compare our multi-task framework with two baselines as shown in Table 4 . For passage selection, our multi-task model achieves the accuracy of 38.9, which outperforms the pure answer prediction model with 4.3. Moreover, jointly learning the answer prediction part and the passage ranking part is better than solving this task by two separated steps because the answer span can provide more information with stronger supervision, which benefits the passage ranking part. The ROUGE-L is calculated by the best answer span in the selected passage, which shows our multi-task learning framework has more potential for better answer.\nWe compare the result of answer extraction and answer synthesis in different categories grouped by the upper bound of extraction method in Table 5 . For the question whose answer can be exactly matched in the passage, our answer synthesis model performs slightly worse because the sequence-to-sequence model makes some deviation when copying extracted evidences. In other categories, our synthesis model achieves more or less improvement. For the question whose answer can be almost found in the passage (ROUGE-L $\\ge $ 0.8), our model achieves 0.2 improvement even though the space that can be raised is limited. For the question whose upper performance via answer extraction is between 0.6 and 0.8, our model achieves a large improvement of 2.0. Part of questions in the last category (ROUGE-L $<$ 0.2) are the polar questions whose answers are “yes” or “no”. Although the answer is not in the passage or question, our synthesis model can easily solve this problem and determine the correct answer through the extracted evidences, which leads to such improvement in this category. However, in these questions, answers are too short to influence the final score in terms of BLEU because it is normalized in all questions. Moreover, the score decreases due to the penalty of length. Due to the limitation of BLEU, we only report the result in terms of ROUGE-L in our analysis.\nWe compare our extraction-then-synthesis model with several end-to-end generation models in Table 6 . S2S represents the sequence-to-sequence framework shown in Figure 3 . The difference among our synthesis model and all entries in the Table 6 is the information we use in the encoding part. The authors of MS-MACRO publish a baseline of training a sequence-to-sequence model with the question and answer, which only achieves 8.9 in terms of ROUGE-L. Adding all passages to the sequence-to-sequence model can obviously improve the result to 28.75. Then we only use the question and the selected passage to generate the answer. The only difference with our synthesis model is that we add the position features to the basic sequence-to-sequence model. The result is still worse than our synthesis model with a large margin, which shows the matching between question and passage is very important for generating answer. Next, we build an end-to-end framework combining matching and generation. We apply the sequence-to-sequence model on top of the matching information by taking question sensitive passage representation $v^P_t$ in the Equation 14 as the input of sequence-to-sequence model, which only achieves 6.28 in terms of ROUGE-L. Above results show the effectiveness of our model that solves this task with two steps. In the future, we hope the reinforcement learning can help the connection between evidence extraction and answer synthesis.\n\nAcknowledgement\nWe thank the MS-MARCO organizers for help in submissions.\n\nTable 2: The performance on the MS-MARCO test set. *Using the ensemble result of extraction models as the input of the synthesis model.\n\nTable 3: The performance on the MS-MARCO development set in terms of ROUGE-L. *Using the ensemble result of extraction models as the input of the synthesis model. +Wang & Jiang (2016b) report their Prediction with 37.3.\n\nQuestion: Which framework they propose in this paper?", "role": "user" }, { "content": "{\"answer\": [\" extraction-then-synthesis framework\"], \"evidence\": [\"In this paper, we present an extraction-then-synthesis framework for machine reading comprehension shown in Figure 1 , in which the answer is synthesized from the extraction results. We build an evidence extraction model to predict the most important sub-spans from the passages as evidence, and then develop an answer synthesis model which takes the evidence as additional features along with the question and passage to further elaborate the final answers.\"]}", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Chemical\", \"Protein\"].\n\nPlease return the output as a JSON object of the format: {\"Chemical\" : [\"Dexamethasone\", ...], \"Protein\" : [\"BRCA-1\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nCentral sympatholysis as a novel countermeasure for cocaine-induced sympathetic activation and vasoconstriction in humans.\nOBJECTIVES: The aim of this study was to determine whether cocaine's sympathomimetic actions can be reversed by a potent centrally acting alpha2 adrenergic receptor (AR) agonist (dexmedetomidine). BACKGROUND: We recently showed that cocaine stimulates the human cardiovascular system primarily by acting in the brain to increase sympathetic nerve activity (SNA), the neural stimulus to norepinephrine release. Thus, SNA constitutes a putative new drug target to block cocaine's adverse cardiovascular effects at their origin. METHODS: In 22 healthy cocaine-naive humans, we measured skin SNA (microneurography) and skin blood flow (laser Doppler velocimetry) as well as heart rate and blood pressure before and after intranasal cocaine (2 mg/kg) alone and in combination with dexmedetomidine or saline. RESULTS: During intranasal cocaine alone, SNA increased by 2-fold and skin vascular resistance increased from 13.2 +/- 2.3 to 20.1 +/- 2.2 resistance units while mean arterial pressure increased by 14 +/- 3 mm Hg and heart rate by 18 +/- 3 beats/min (p < 0.01). Dexmedetomidine abolished these increases, whereas intravenous saline was without effect. Dexmedetomidine was effective in blocking these sympathomimetic actions of cocaine even in all 7 subjects who were homozygous for the Del322-325 polymorphism in the alpha2C AR, a loss-of-function mutation that is highly enriched in blacks. CONCLUSIONS: The data advance the novel hypothesis that central sympatholysis with dexmedetomidine constitutes a highly effective countermeasure for cocaine's sympathomimetic actions on the human cardiovascular system, even in individuals carrying the alpha2CDel322-325 polymorphism. (Study to Improve Scientific Understanding of the Cardiovascular Actions of Cocaine; http://clinicaltrials.gov/ct/show/NCT00338546?order=1; NCT00338546).", "role": "user" }, { "content": "{\"Chemical\": [\"dexmedetomidine\", \"norepinephrine\", \"Dexmedetomidine\", \"cocaine\", \"Cocaine\"], \"Protein\": [\"alpha2C AR\", \"AR\", \"alpha2 adrenergic receptor\", \"alpha2C\"]}", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research paper, followed by a question about the paper. Please extract text from the paragraph to answer the question. Do not include any text in your response other than the answer.\n\nParagraph: Our methods assume that changes in the reproductive number — a measure of transmission - are an immediate response to these interventions\nbeing implemented rather than broader gradual changes in behaviour. Our model estimates these\nchanges by calculating backwards from the deaths observed over time to estimate transmission that\noccurred several weeks prior, allowing for the time lag between infection and death. One of the key assumptions of the model is that each intervention has the same effect on the\nreproduction number across countries and over time. This allows us to leverage a greater amount of\ndata across Europe to estimate these effects. It also means that our results are driven strongly by the\ndata from countries with more advanced epidemics, and earlier interventions, such as Italy and Spain. We find that the slowing growth in daily reported deaths in Italy is consistent with a significant impact\nof interventions implemented several weeks earlier. In Italy, we estimate that the effective\nreproduction number, Rt, dropped to close to 1 around the time of Iockdown (11th March), although\nwith a high level of uncertainty. Overall, we estimate that countries have managed to reduce their reproduction number. Our\nestimates have wide credible intervals and contain 1 for countries that have implemented a||\ninterventions considered in our analysis. This means that the reproduction number may be above or\nbelow this value. With current interventions remaining in place to at least the end of March, we\nestimate that interventions across all 11 countries will have averted 59,000 deaths up to 31 March\n[95% credible interval 21,000-120,000]. Many more deaths will be averted through ensuring that\ninterventions remain in place until transmission drops to low levels. We estimate that, across all 11\ncountries between 7 and 43 million individuals have been infected with SARS-CoV-Z up to 28th March,\nrepresenting between 1.88% and 11.43% ofthe population. The proportion of the population infected\n\nto date — the attack rate - is estimated to be highest in Spain followed by Italy and lowest in Germany\nand Norway, reflecting the relative stages of the epidemics. Given the lag of 2-3 weeks between when transmission changes occur and when their impact can be\nobserved in trends in mortality, for most of the countries considered here it remains too early to be\ncertain that recent interventions have been effective. If interventions in countries at earlier stages of\ntheir epidemic, such as Germany or the UK, are more or less effective than they were in the countries\nwith advanced epidemics, on which our estimates are largely based, or if interventions have improved\nor worsened over time, then our estimates of the reproduction number and deaths averted would\nchange accordingly. It is therefore critical that the current interventions remain in place and trends in\ncases and deaths are closely monitored in the coming days and weeks to provide reassurance that\ntransmission of SARS-Cov-Z is slowing. SUGGESTED CITATION\n\nSeth Flaxman, Swapnil Mishra, Axel Gandy et 0/. Estimating the number of infections and the impact of non—\npharmaceutical interventions on COVID—19 in 11 European countries. Imperial College London (2020), doi:\nhttps://doi.org/10.25561/77731\n\n1 Introduction\n\nFollowing the emergence of a novel coronavirus (SARS-CoV-Z) in Wuhan, China in December 2019 and\nits global spread, large epidemics of the disease, caused by the virus designated COVID-19, have\nemerged in Europe. In response to the rising numbers of cases and deaths, and to maintain the\ncapacity of health systems to treat as many severe cases as possible, European countries, like those in\nother continents, have implemented or are in the process of implementing measures to control their\nepidemics. These large-scale non-pharmaceutical interventions vary between countries but include\nsocial distancing (such as banning large gatherings and advising individuals not to socialize outside\ntheir households), border closures, school closures, measures to isolate symptomatic individuals and\ntheir contacts, and large-scale lockdowns of populations with all but essential internal travel banned. Understanding firstly, whether these interventions are having the desired impact of controlling the\nepidemic and secondly, which interventions are necessary to maintain control, is critical given their\nlarge economic and social costs. The key aim ofthese interventions is to reduce the effective reproduction number, Rt, ofthe infection,\na fundamental epidemiological quantity representing the average number of infections, at time t, per\ninfected case over the course of their infection. Ith is maintained at less than 1, the incidence of new\ninfections decreases, ultimately resulting in control of the epidemic. If Rt is greater than 1, then\ninfections will increase (dependent on how much greater than 1 the reproduction number is) until the\nepidemic peaks and eventually declines due to acquisition of herd immunity. In China, strict movement restrictions and other measures including case isolation and quarantine\nbegan to be introduced from 23rd January, which achieved a downward trend in the number of\nconfirmed new cases during February, resulting in zero new confirmed indigenous cases in Wuhan by\nMarch 19th. Studies have estimated how Rt changed during this time in different areas ofChina from\naround 2-4 during the uncontrolled epidemic down to below 1, with an estimated 7-9 fold decrease\nin the number of daily contacts per person.1'2 Control measures such as social distancing, intensive\ntesting, and contact tracing in other countries such as Singapore and South Korea have successfully\nreduced case incidence in recent weeks, although there is a riskthe virus will spread again once control\nmeasures are relaxed.3'4\n\nThe epidemic began slightly laterin Europe, from January or later in different regions.5 Countries have\nimplemented different combinations of control measures and the level of adherence to government\nrecommendations on social distancing is likely to vary between countries, in part due to different\nlevels of enforcement. Estimating reproduction numbers for SARS-CoV-Z presents challenges due to the high proportion of\ninfections not detected by health systems”7 and regular changes in testing policies, resulting in\ndifferent proportions of infections being detected over time and between countries. Most countries\nso far only have the capacity to test a small proportion of suspected cases and tests are reserved for\nseverely ill patients or for high-risk groups (e.g. contacts of cases). Looking at case data, therefore,\ngives a systematically biased view of trends. An alternative way to estimate the course of the epidemic is to back-calculate infections from\nobserved deaths. Reported deaths are likely to be more reliable, although the early focus of most\nsurveillance systems on cases with reported travel histories to China may mean that some early deaths\nwill have been missed. Whilst the recent trends in deaths will therefore be informative, there is a time\nlag in observing the effect of interventions on deaths since there is a 2-3-week period between\ninfection, onset of symptoms and outcome. In this report, we fit a novel Bayesian mechanistic model of the infection cycle to observed deaths in\n11 European countries, inferring plausible upper and lower bounds (Bayesian credible intervals) of the\ntotal populations infected (attack rates), case detection probabilities, and the reproduction number\nover time (Rt). We fit the model jointly to COVID-19 data from all these countries to assess whether\nthere is evidence that interventions have so far been successful at reducing Rt below 1, with the strong\nassumption that particular interventions are achieving a similar impact in different countries and that\nthe efficacy of those interventions remains constant over time. The model is informed more strongly\nby countries with larger numbers of deaths and which implemented interventions earlier, therefore\nestimates of recent Rt in countries with more recent interventions are contingent on similar\nintervention impacts. Data in the coming weeks will enable estimation of country-specific Rt with\ngreater precision. Model and data details are presented in the appendix, validation and sensitivity are also presented in\nthe appendix, and general limitations presented below in the conclusions. 2 Results\n\nThe timing of interventions should be taken in the context of when an individual country’s epidemic\nstarted to grow along with the speed with which control measures were implemented. Italy was the\nfirst to begin intervention measures, and other countries followed soon afterwards (Figure 1). Most\ninterventions began around 12th-14th March. We analyzed data on deaths up to 28th March, giving a\n2-3-week window over which to estimate the effect of interventions. Currently, most countries in our\nstudy have implemented all major non-pharmaceutical interventions. For each country, we model the number of infections, the number of deaths, and Rt, the effective\nreproduction number over time, with Rt changing only when an intervention is introduced (Figure 2-\n12). Rt is the average number of secondary infections per infected individual, assuming that the\ninterventions that are in place at time t stay in place throughout their entire infectious period. Every\ncountry has its own individual starting reproduction number Rt before interventions take place. Specific interventions are assumed to have the same relative impact on Rt in each country when they\nwere introduced there and are informed by mortality data across all countries. Figure l: Intervention timings for the 11 European countries included in the analysis. For further\ndetails see Appendix 8.6. 2.1 Estimated true numbers of infections and current attack rates\n\nIn all countries, we estimate there are orders of magnitude fewer infections detected (Figure 2) than\ntrue infections, mostly likely due to mild and asymptomatic infections as well as limited testing\ncapacity. In Italy, our results suggest that, cumulatively, 5.9 [1.9-15.2] million people have been\ninfected as of March 28th, giving an attack rate of 9.8% [3.2%-25%] of the population (Table 1). Spain\nhas recently seen a large increase in the number of deaths, and given its smaller population, our model\nestimates that a higher proportion of the population, 15.0% (7.0 [18-19] million people) have been\ninfected to date. Germany is estimated to have one of the lowest attack rates at 0.7% with 600,000\n[240,000-1,500,000] people infected. Imperial College COVID-19 Response Team\n\nTable l: Posterior model estimates of percentage of total population infected as of 28th March 2020. Country % of total population infected (mean [95% credible intervall)\nAustria 1.1% [0.36%-3.1%]\nBelgium 3.7% [1.3%-9.7%]\nDenmark 1.1% [0.40%-3.1%]\nFrance 3.0% [1.1%-7.4%]\nGermany 0.72% [0.28%-1.8%]\nItaly 9.8% [3.2%-26%]\nNorway 0.41% [0.09%-1.2%]\nSpain 15% [3.7%-41%]\nSweden 3.1% [0.85%-8.4%]\nSwitzerland 3.2% [1.3%-7.6%]\nUnited Kingdom 2.7% [1.2%-5.4%]\n\n2.2 Reproduction numbers and impact of interventions\n\nAveraged across all countries, we estimate initial reproduction numbers of around 3.87 [3.01-4.66],\nwhich is in line with other estimates.1'8 These estimates are informed by our choice of serial interval\ndistribution and the initial growth rate of observed deaths. A shorter assumed serial interval results in\nlower starting reproduction numbers (Appendix 8.4.2, Appendix 8.4.6). The initial reproduction\nnumbers are also uncertain due to (a) importation being the dominant source of new infections early\nin the epidemic, rather than local transmission (b) possible under-ascertainment in deaths particularly\nbefore testing became widespread. We estimate large changes in Rt in response to the combined non-pharmaceutical interventions. Our\nresults, which are driven largely by countries with advanced epidemics and larger numbers of deaths\n(e.g. Italy, Spain), suggest that these interventions have together had a substantial impact on\ntransmission, as measured by changes in the estimated reproduction number Rt. Across all countries\nwe find current estimates of Rt to range from a posterior mean of 0.97 [0.14-2.14] for Norway to a\nposterior mean of2.64 [1.40-4.18] for Sweden, with an average of 1.43 across the 11 country posterior\nmeans, a 64% reduction compared to the pre-intervention values. We note that these estimates are\ncontingent on intervention impact being the same in different countries and at different times. In all\ncountries but Sweden, under the same assumptions, we estimate that the current reproduction\nnumber includes 1 in the uncertainty range. The estimated reproduction number for Sweden is higher,\nnot because the mortality trends are significantly different from any other country, but as an artefact\nof our model, which assumes a smaller reduction in Rt because no full lockdown has been ordered so\nfar. Overall, we cannot yet conclude whether current interventions are sufficient to drive Rt below 1\n(posterior probability of being less than 1.0 is 44% on average across the countries). We are also\nunable to conclude whether interventions may be different between countries or over time. There remains a high level of uncertainty in these estimates. It is too early to detect substantial\nintervention impact in many countries at earlier stages of their epidemic (e.g. Germany, UK, Norway). Many interventions have occurred only recently, and their effects have not yet been fully observed\ndue to the time lag between infection and death. This uncertainty will reduce as more data become\navailable. For all countries, our model fits observed deaths data well (Bayesian goodness of fit tests). We also found that our model can reliably forecast daily deaths 3 days into the future, by withholding\nthe latest 3 days of data and comparing model predictions to observed deaths (Appendix 8.3). The close spacing of interventions in time made it statistically impossible to determine which had the\ngreatest effect (Figure 1, Figure 4). However, when doing a sensitivity analysis (Appendix 8.4.3) with\nuninformative prior distributions (where interventions can increase deaths) we find similar impact of\n\nImperial College COVID-19 Response Team\n\ninterventions, which shows that our choice of prior distribution is not driving the effects we see in the\n\nmain analysis. Figure 2: Country-level estimates of infections, deaths and Rt. Left: daily number of infections, brown\nbars are reported infections, blue bands are predicted infections, dark blue 50% credible interval (CI),\nlight blue 95% CI. The number of daily infections estimated by our model drops immediately after an\nintervention, as we assume that all infected people become immediately less infectious through the\nintervention. Afterwards, if the Rt is above 1, the number of infections will starts growing again. Middle: daily number of deaths, brown bars are reported deaths, blue bands are predicted deaths, CI\nas in left plot. Right: time-varying reproduction number Rt, dark green 50% CI, light green 95% CI. Icons are interventions shown at the time they occurred.\n\nQuestion: What is a way to measure virus transmission?", "role": "user" }, { "content": "reproductive number", "role": "assistant" } ]

[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nActive learning in a Year 2 pathology curriculum.\nAbstract 1:\nPURPOSE Team-based learning ( TBL ) has been successfully used in non-medical curricula , but its effectiveness in medical education has not been studied extensively . We evaluated the impact of TBL on the academic performance of Year 2 medical students at Wright State University by comparing this active learning strategy against a traditional method of case-based group discussion ( CBGD ) . METHODS A prospect i ve crossover design assigned 83 Year 2 medical students to either CBGD or TBL for 8 pathology modules in the systems-based curriculum . The effectiveness of both learning methods was assessed by performance on pathology-based examination questions contained in end-of-course examinations . The highest and lowest academic quartiles of students were evaluated separately . Students ' opinions of both methods were surveyed . RESULTS No significant differences in whole group performance on pathology-based examination questions were observed as a consequence of experiencing TBL versus CBGD . However , students in the lowest academic quartile showed better examination performance after experiencing TBL than CBGD in 4 of 8 modules ( P = 0.035 ) . Students perceived that the contributions of peers to learning were more helpful during TBL than CBGD ( P = 0.003 ) . CONCLUSION This study demonstrates that TBL and CBGD are equally effective active learning strategies when employed in a systems-based pre- clinical pathology curriculum , but students with lower academic performance may benefit more from TBL than CBGD", "role": "user" }, { "content": "Despite improvement in knowledge scores , there was mixed learner reaction .", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\nin classical information theory one can make ( in principle ) arbitrarily many perfect copies of any classical input . in quantum information theory ,\nthe situation is quite different .\nthe no cloning theorem @xcite prohibits exact copying of arbitrary superposition states .\nnevertheless , buek and hillery and other authors @xcite have shown that imperfect copies can be made by a universal quantum cloning machine ( uqcm ) , the outputs of which are identical .\nthe price which must be paid is that there is a difference between the original input and the copies , because of a residual entanglement between machine and copies .\nhowever not only similarity is lost during the cloning process .\nperhaps even more important than the no cloning feature of quantum mechanics is entanglement , that is a composite microsystem formed from some subsystems can be generated in a state @xmath0 , in which correlations between these subsystems are much stronger than any classical correlations .\nthis quantum entanglement feature is crucial in many applications , such as some forms of quantum cryptography @xcite , relying on correlated quantum communication @xcite and in quantum computation theory @xcite . in all these situations success\ndepends upon the strength of the non local correlations .\nif the cloning process applied to correlated subsystems is to be anything more than a basic curiosity , and is to find a practical application in the field of quantum information theory , it should be possible to obtain not only maximally accurate copies of the original state , but also copies which preserve a degree of non local correlation characteristic of the copied state .\nwe will show in this paper that entanglement is rapidly destroyed by the copying process .\nwe consider the simplest generic case of a non local system , consisting of two qubits formed in a pure entangled state . we can choose to describe this in terms of the bell state basis : @xmath1 where @xmath2 determines the amount of entanglement in the state and @xmath3 .\n( we assume , for simplicity , that both @xmath2 and @xmath4 are real . )\nthere are two possibilities : the pair of qubits can be cloned locally or non locally .\nnow we concentrate on the first case and restrict our considerations to the state @xmath5 as the results for the remaining states are entirely the same .\nwe will explain below why they are the same for different bell states .\na scheme which will achieve local cloning is described by the following@xcite : two distant parties share an entangled two qubit state @xmath6 .\neach of them perform some local transformations on the own qubit using distant quantum copying machines .\nwe assume that the two additional qubits , employed in the copying process , are initially uncorrelated .\nthe two copiers make copies of the qubits separately .\nthe result of the cloning process is an output which is no longer a pure state , but is described by the density matrix : @xmath7 @xmath8 it is quite easy to determine whether a given pure state is local or non local .\nthe situation is much more complicated for the case when a system is prepared in a mixed state .\nthere is no general method known to us which determines the degree of non locality of mixed states .\nhowever in the case of @xmath9 systems , there a is simple criterion which allows us to distinguish density matrices describing entangled mixed states @xcite .\nthe peres - horodecki separability criterion tells us that if the partially transposed density matrix of the composite system , defined by matrix elements generated in the following way @xmath10 , does not have non negative eigenvalues , then the state is separable . for a system formed from two two \nlevel subsystems opposite is also true . using the partial transposition criterion we determine for what values of the superposition parameter @xmath2 the final state of the local process is inseparable .\nthe state @xmath11 is entangled when the following condition is fulfilled : @xmath12 .\nthe state @xmath13 can also be cloned non locally @xcite . in this case\nthe entangled state of the two qubits is treated as a state in a larger hilbert space and cloned as a whole .\nthe final state of each pair of the two \nqubit copies at the output of the cloning machine is given by the density operator : @xmath14 @xmath15 now , we find the inseparability condition derived from the partial transposition criterion @xcite is the following : @xmath16 .\nthe non locality of a quantum state can manifest itself in many different ways .\nthe best known , and one which has been tested in many experiments is the manifestation of strong nonclassical correlations of quantum states , in violation of bell s inequality @xcite .\nthe bell chsh inequality @xcite under consideration has the form : @xmath17 where @xmath18\\ ] ] is the two qubit correlation function and @xmath19 are pauli spin-@xmath20 operators .\nthe quantity @xmath21 depend strongly upon vectors @xmath22 , @xmath23 , @xmath24 , @xmath25 .\nit is easy to check that for the singlet state @xmath26 optimal configuration , maximising @xmath21 is achieved by coplanar vectors @xmath22 , @xmath23 , @xmath24 , @xmath25 , where the angles between two consecutive vectors are the same and equal to @xmath27 ( fig .\nunfortunately this configuration is optimal only for the choice of an exact singlet initial state and actually does not fit our needs here . instead of looking for other optimal sets of vectors , which are necessary to calculate the quantity @xmath21\n, we employ the formula for the maximal value of @xmath21 obtained recently by horodecki _ et.al .\nthe @xmath28 can be calculated directly using the result @xmath29 , where @xmath30 , and @xmath31 are eigenvalues of the matrix @xmath32 , and @xmath33 $ ] . using this expression we investigate properties of copies produced from the pure entangled state @xmath34 .\nthese same calculations can be repeated for the other bell states , but we have found that the results are identical to the above and independent of which state was chosen .\nthis results from the fact that @xmath28 depends upon the state just by the maximum @xmath35 of sums of pairs of the eigenvalues of the matrix @xmath36 .\nclones obtained from different bell states @xmath37 or @xmath38 have the same eigenvalues @xmath39 , so @xmath35 is the same for all states from bell basis . in fig .\n[ bell_pure ] we compare the values of @xmath40 calculated employing vectors @xmath22 , @xmath23 , @xmath24 , @xmath25 taken in the configuration which is shown in fig . 1 and values of the @xmath41 , both calculated for the bell state @xmath42 . in fig . [ bell_local ] and fig\n. [ bell_non - local ] we show @xmath40 and @xmath41 calculated for states @xmath43 $ ] of a pair of qubits obtained in the cloning process , first using local copying and secondly using non local copying .\nit turns out that in both cases the pairs of qubit copies are in states which do not violate bell s inequality , even if the input state was prepared in a singlet state with maximal entanglement .\nin the previous section we have shown that during the cloning process entangled states lose so much of their entanglement that they are not able to violate bell s inequality in a state correlation experiment .\nhowever this does not mean that such states do not contain any quantum correlations .\nit is known that the violation of bell s inequality is not a wholly satisfactory measure of quantum non \nlocality@xcite : this is just not as sensitive as other measures of entanglement @xcite .\nthere are other quantities which are have been developed as measures of quantum correlations and entanglement . for the case of a pair of correlated qubits ,\none such measure is the entanglement of formation @xcite .\nthis quantity is much more sensitive to the degree of correlation than bell s inequality and more importantly , a finite , compact analytical formula for it is known .\nthe entanglement of formation @xmath44 is defined in the following way @xcite : @xmath45 where @xmath46 @xmath47 and @xmath48 .\nthe @xmath49 s in these expressions are the square roots of eigenvalues , in decreasing order , of a non - hermitian matrix @xmath50 , and @xmath51 in fig .\n5 we show the entanglement of formation calculated for the pure state @xmath42 and the two qubit states obtained as the result of both local and non local copying of the state @xmath42 . we see that non local cloning is much more efficient than the local process , in that the values of @xmath52 are much larger in the former case .\nthe entanglement of formation is in this case non \nzero for states @xmath42 , characterised by values of @xmath2 parameter , which belong to a larger subinterval of the @xmath53 $ ] interval .\none sees from the above that either local or non local copying are rather inefficient processes from the point of view of preserving entanglement . even in the case when the maximally inseparable state is the input state of the cloning process\n, only a small amount of entanglement survives the cloning .\nit is an interesting question to ask what will happen when the output state of the copier is used as an input state in the next step of a sequence of cloning processes . in particular\n, we are interested to discover how fast the entanglement decreases when the copying is iterated .\nwe restrict ourself in these considerations to the case of non local cloning , because this scheme is much more effective as we saw above , and results obtained in this case can be treated as an upper bound for all other schemes .\nthe final state of the copying process is a mixed state , described by the density matrix , eq.([non - local cloning ] ) .\nthis density matrix can not be used directly as input data in computations , because the non local copying scheme works straitforwardly only when an input state is initially in a pure , potentially entangled , state .\nthe density matrix should be first converted to a form which allows us to perform the second cloning .\nit turns out that a simple diagonalization of the density matrix is sufficient . in this new , diagonal base ,\nthe density matrix is given by the mixture of projection operators @xmath54 .\nthe weights @xmath55 in the decomposition are the eigenvalues of the density matrix @xmath56 and the vectors @xmath57 are the normalised eigenvectors of @xmath56 . each vector @xmath58 can be cloned separately .\nthe mixture of the resultant density matrices taken with the weights @xmath55 is the result of the second cloning process .\nwe repeat this procedure and investigate changes in the entanglement of formation at each stage of this procedure . in fig .\n6 we show the entanglement of formation of the clones of the states @xmath42 for the case of the first two stages of cloning . results for the maximally entangled state @xmath59 are shown in table 1 . [ cols=\"^,^,^,^,^\",options=\"header \" , ] table 1 . entanglement of formation of clones of the singlet state @xmath59 + as a function of the number of cloning steps .\none sees the entanglement decreases extremely rapidly , and after just three iterations the copy of any inseparable state the resultant entanglement of formation goes to zero .\nwe have shown that the uqcm of buek and hillery @xcite can generate copies of entangled pairs of qubits , but that the degree of entanglement of the resultant copies is substantially reduced .\nthe amount of entanglement decreases very rapidly with the number of times the copier is used .\nstates obtained as a result of either local or non local copying do not violate already bell s inequality .\nhowever the entanglement of formation of such states remains still positive .\nit is still positive after the second step of the copying process , when output states obtained in the previous step become input states of the next step .\nbut after the third step the entanglement of formation is equal to zero .\nit means that even qubits , which are copies of copies of copies of the singlet state are already in local state .\nthey do not have any nonclassical correlations and are useless as a resource in quantum computation or quantum telecommunication .\nthis reduction is of course due to a residual entanglement between the copies and the quantum copying machine .\nthis is important if the copying process is used to replicate ( albeit approximately ) copies of a quantum register , for example , in quantum computing @xcite or of a bell correlated quantum cryptography protocol @xcite .\nthis work was supported in part by the uk engineering and physical sciences research council , the royal society and the european union .\nwe would like to acknowledge fruitful discussions with daniel jonathan and martin plenio .\nwe also thank vladimir buek for many useful suggestions and comments on this paper .\nv. buek and m. hillery , _ phys .\na _ , * 54 * , 1844 , ( 1996 ) ; n. gisin and s. massar , _ phys .\n_ , * 79 * , 2153 ( 1997 ) ; v. buek , _ et .\n_ , _ phys .\na _ , * 56 * , 3446 ( 1997 ) ; d. bruss , _ et .\n_ , _ phys .\na _ , * 57 * , 2368 ( 1998 ) .", "role": "user" }, { "content": "we investigate the degree to which entanglement survives when a correlated pair of two state systems are copied using either local or non local processes . \n we show how the copying process degrades the entanglement , due to a residual correlation between the copied output and the copying machine ( itself made of qubits ) .", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: An Arabidopsis Example of Association Mapping in Structured Samples\nArticle:\nAbstract:\nA potentially serious disadvantage of association mapping is the fact that marker-trait associations may arise from confounding population structure as well as from linkage to causative polymorphisms. Using genome-wide marker data, we have previously demonstrated that the problem can be severe in a global sample of 95 Arabidopsis thaliana accessions, and that established methods for controlling for population structure are generally insufficient. Here, we use the same sample together with a number of flowering-related phenotypes and data-perturbation simulations to evaluate a wider range of methods for controlling for population structure. We find that, in terms of reducing the false-positive rate while maintaining statistical power, a recently introduced mixed-model approach that takes genome-wide differences in relatedness into account via estimated pairwise kinship coefficients generally performs best. By combining the association results with results from linkage mapping in F2 crosses, we identify one previously known true positive and several promising new associations, but also demonstrate the existence of both false positives and false negatives. Our results illustrate the potential of genome-wide association scans as a tool for dissecting the genetics of natural variation, while at the same time highlighting the pitfalls. The importance of study design is clear; our study is severely under-powered both in terms of sample size and marker density. Our results also provide a striking demonstration of confounding by population structure. While statistical methods can be used to ameliorate this problem, they cannot always be effective and are certainly not a substitute for independent evidence, such as that obtained via crosses or transgenic experiments. Ultimately, association mapping is a powerful tool for identifying a list of candidates that is short enough to permit further genetic study.\nIntroduction:\nAs sequencing and genotyping costs continue to decrease, association mapping( also known as linkage disequilibrium mapping) is emerging as a powerful, general tool for identifying alleles and loci responsible for natural variation. Although its application to human disease has received most attention[1], association mapping has tremendous potential in organisms ranging from Arabidopsis thaliana[2] to cattle[3]. Indeed, given how quickly sequencing and genotyping technology is developing, it will soon be feasible to carry out genome-wide association scans in almost any organism, including many that are not amenable to traditional mapping methods( e. g., because they cannot be crossed experimentally). A potentially serious obstacle to association mapping is confounding by population structure. It is well known that population structure may cause spurious correlations, leading to an elevated false-positive rate[4]. Whether this is likely to be a significant problem in human association studies is currently a subject of considerable debate[5–11]. Be that as it may, human association studies are typically designed as case-control studies, and the effects of confounding can thus be minimized by carefully matching cases and controls[7]. When association mapping is instead used to identify genes responsible for quantitative variation in a single population sample, there is every reason to believe that confounding will be a significant problem, especially if the trait varies geographically, as does height, skin color, or flowering time[7, 12–14]. In an earlier paper, we demonstrated that confounding can be severe in a structured sample of 95 A. thaliana accessions for which genome-wide polymorphism data are available[13]. We also showed that the two best-known statistical approaches for dealing with this type of confounding, “genomic control”[15] and “structured association”[16], were not effective, the former because it lacks power in the presence of strong confounding, the latter because it did not adequately capture the complex pattern of relatedness in the sample. Although we were able to identify several previously known loci, the false-positive rate remained sufficiently elevated to make searching for new loci infeasible. In this paper, we evaluate a wider range of methods, including the mixed-model approach of Yu et al.[14] and the principal components approach of Price et al.[17]. We first investigate how these methods perform in terms of reducing the false-positive rate in genome-wide scans for a range of flowering-related phenotypes, then examine their power using data-perturbation simulations. We find that versions of the approach of Yu et al. generally perform best, but a comparison with the results of linkage mapping indicates that some confounding still remains, and, furthermore, that correcting for population structure also introduces false negatives. Nonetheless, the false-positive rate is reduced to levels that make it possibly to use our sample for association mapping, and although our scans have low power due to insufficient marker density and small sample size, we identify a number of plausible associations.\nDiscussion:\nThere is currently great interest in applying association mapping to a wide range of organisms, many of which( e. g., maize[12] and dog[35]) have heavily structured populations. Our study provides a dramatic example of the difficulties that may be encountered. Although our example may ultimately turn out to have been extreme, we would caution against premature optimism. Indeed, there should be no reason ever to assume anything about the importance of population structure in a particular study; it is straightforward to determine the distribution of test statistics empirically by calculating them across large numbers of loci. In genome-wide scans, large numbers of loci will by definition always be available, and for candidate locus studies, our results simply illustrate the need for an appropriate genomic control. Any association result not accompanied by a demonstration that the reported significance values are actually meaningful should be treated with suspicion( unless supported by strong experimental evidence). We took advantage of our genome-wide data to evaluate published claims of association in A. thaliana. We found no evidence for association between the CRY2 polymorphism reported by Olsen et al.[32] and any of our phenotypes, while the FLC polymorphism reported by Caicedo et al.[33] is at best weakly associated with the flowering response to differences in day length after vernalization. In contrast, the PHYC polymorphism reported by Balasubramanian et al.[34] does appear to show a significant interaction with latitude in determining vernalization response, in broad agreement with the original findings. While it is of course not possible to disprove a published association using a different sample and different phenotypic measurements, it is notable that neither Olsen et al.[32] nor Caicedo et al.[33] employed an appropriate genomic control, while Balasubramanian et al.[34] based their claim on a ranking of p-values( from a small genomic control) and, more importantly, several independent sources of evidence. A number of statistical approaches for reducing confounding by population structure have been proposed. Methods, like “genomic control”[15], which simply rescale p-values without changing the rankings of loci, are not likely to be useful in genome-wide scans where the existence of true positives is not in doubt. Most biologists will simply rank the associations by nominal significance and proceed to test the most significant. Methods that attempt to separate true from spurious associations, like the ones used in this study, are of much greater interest. Our results demonstrate that such methods can be very effective at reducing( not eliminating) confounding. It is clear that this is a hard problem, and more theoretical work is certainly warranted. Comprehensive simulation studies( with known null distributions) would be required to determine how the different methods perform in terms of the false-positive rate. The mixed-model approach[14, 36] seems particularly promising, and further research would probably be worthwhile. General principles for how kinship( the K matrix) should be estimated might be attainable, whereas the utility of estimators of population structure are likely to vary greatly from case to case. The underlying structure in our sample appears to be some form of isolation-by-distance[22], and both STRUCTURE[18] and PCA[17] appear to capture the relevant aspects of this structure reasonably well( Table 1). The first two principal components from the PCA are in fact strongly correlated with longitude and latitude( Figure S11). At the same time, it is important to recognize that there are limits to what can be achieved using statistics. As noted above, any method that effectively removes confounding will also effectively remove true positives that are strongly correlated with population structure. Thus, while reducing confounding makes the common, widely distributed alleles of FRI stand out more clearly in our study, it also eliminates many of the best candidates for the extreme late-flowering phenotype characteristic of the northern accessions. Because these accessions are so distinct on a genome-wide level, any late-flowering allele shared by all or most of them would( and should) be removed by a statistical method that reduces confounding. There has to be segregation for mapping to work. Interestingly, FLC, a central regulator of flowering, may be an example of this. Allelic variation at FLC has been shown to affect flowering[37, 38], and five of our F2 crosses revealed a strong flowering QTL centered on it[28]. FLC expression is strongly correlated with flowering time( Table 1 and[39]). In our naive analysis( i. e., without correcting for population structure), FLC is one of the strongest associations for many phenotypes; however, because the significance is due to allele sharing among a large subset of northern accessions, it is down-weighted when population structure is taken into account( this can be seen in Figure 5, for example). It should be noted that the strong association we find at FLC( whether causative or spurious) does not correspond to the association previously reported by Caicedo et al.[33]. As discussed above, the polymorphism studied by these authors is also associated with several of our phenotypes( Tables S2–S4), but the associations are much weaker. In conclusion, we should emphasize that although this paper has focused on the difficulties caused by confounding, we do not mean to say that these studies are impossible, merely that caution is needed. The statistical methods we used look promising, and we did identify several interesting associations. It must be remembered that, in a small and heavily structured sample such as the one used here, we should really only expect to be able to find polymorphisms with a major effect on the phenotypic variation that segregate widely across the geographic distribution of the sample. FRI is an example, and we do indeed find it. Of the new associations we have identified( Table 4), the most promising is probably the common polymorphism at CLF, which may be a major factor in determining the differential flowering response to day length. However, the large fraction of the phenotypic variation that is due to the very late accessions probably cannot be dissected further using this sample. There is every reason to believe that genome-wide association studies involving adequate marker densities and larger samples will be very fruitful.", "role": "user" }, { "content": "There is currently tremendous interest in using association mapping to find the genes responsible for natural variation , particularly for human disease . In association mapping , researchers seek to identify regions of the genome where individuals who are phenotypically similar ( e . g . , they all have the same disease ) are also unusually closely related . A potentially serious problem is that spurious correlations may arise if the population is structured so that members of a subgroup tend to be much more closely related . We have previously demonstrated that this problem can be severe in Arabidopsis thaliana , and that established statistical methods for controlling for population structure are insufficient . Here , we evaluate a broader range of methods . We find that a recently introduced mixed-model approach generally performs best . By combining the association results with results from linkage mapping in F2 crosses , we identify one previously known true positive and several promising new associations , but also demonstrate the existence of both false positives and false negatives . Our results illustrate the potential of genome-wide association scans as a tool for dissecting the genetics of natural variation , while at the same time highlighting the pitfalls .", "role": "assistant" } ]

[ { "content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nProphylactic use of hydrochlorothiazide in pregnancy.\nAbstract 1:\nA r and omized double-blind investigation of the early , continuous , prophylactic use of hydrochlorothiazide ( 50 mg daily ) was undertaken with 1,030 obstetrical patients . Twenty-eight percent of the patients were teenagers and 39 % were nulliparas . Hypokalemia and hyperuricemia were significantly increased in the hydrochlorothiazide group , but the patients were asymptomatic . The total incidence of hypertension was 19.6 % in the hydrochlorothiazide group and 21.8 % in the placebo group . Preeclampsia occurred in 3 % of the former group and in 3.8 % of the latter . Excessive weight gain was evident in 13.9 % of the placebo group as compared to 7.7 % of the hydrochlorothiazide group ( P= 0.002 ) . The average fetal weight and the incidence of prematurity , congenital anomalies , and perinatal mortality were similar in both groups . No complications related to thiazides were encountered in the 1,040 newborns . The data demonstrated that long-term , prophylactic use of hydrochlorothiazide in pregnancy did not alter the incidence of preeclampsia , hypertension , prematurity , congenital anomalies , or perinatal mortality\n\n\nTitle 2:\nPharmacokinetics of furosemide in gestosis of pregnancy\nAbstract 2:\nSummary Furosemide 50 mg was administered orally and intravenously to twelve gestotic women for brief periods as a part of a r and omized , multicentre clinical trial comparing the efficacy of bed rest and pharmacological treatment . The pharmacokinetic profile was investigated using a gas-liquid chromatographic technique . The plasma half-life after oral and intravenous administration was 115±37.1 and 71.8±26.3 min and plasma clearance was 153±48 and 152±23 ml/min , respectively ( mean±SD ) . Comparative data from healthy pregnant women can not be obtained for ethical reasons . The results show that gestosis has only a marginal if any effect on the kinetics of furosemide in comparison with published kinetic parameters in healthy volunteers and patients with renal failure . The new-born babies where checked for side effects according to a protocol in use in a larger regional surveillance programme . No clinical side-effects were attributable to furosemide , but the small size of the group does not permit any definitive conclusions about this aspect\n\n\nTitle 3:\nOverview of randomised trials of diuretics in pregnancy.\nAbstract 3:\nOver the past 20 years at least 11 r and omised trials of the prevention with diuretics of pre-eclampsia and its sequelae have been undertaken . Nine of these were review ed . Reliable data from the remaining two were not available . The nine review ed had investigated a total of nearly 7000 people . Significant evidence of prevention of \" pre-eclampsia \" was overwhelming , even when oedema was not included as a diagnostic criterion . But as the definitions of pre-eclampsia that had been used depended heavily on increases in blood pressure this evidence may simply have reflected the well known ability of diuretics to reduce blood pressure . When the data on perinatal death were review ed a little difference was seen in postnatal survival . The incidence of stillbirths was reduced by about one third with treatment , but , perhaps owing to small numbers ( only 37 stillbirths ) , the difference was not significant . Thus these r and omised trials failed to provide reliable evidence of either the presence or the absence of any worthwhile effects of treatment with diuretics on perinatal mortality . The implication s of this for current and future trials of beta blockers and other agents in the prevention of pre-eclampsia and its sequelae are that extremely large , ultra simple r and omised trials are needed , of a size sufficient to permit direct assessment of the effects of treatment not on pre-eclampsia but on perinatal mortality itself . This may require the study of tens of thous and s of pregnancies\n\n\nTitle 4:\nThe Effects and Side Effects of Diuretics in the Prophylaxis of Toxaemia of Pregnancy\nAbstract 4:\nIn a series comprising 211 pregnant patients , the prophylactic effect of chlorthalidone on the incidence of gestosis was studied by means of a single‐blind trial . The study continued from the 16th week of pregnancy until term . No beneficial effects were observed . In addition , the maternal serum potassium and sodium levels were found to be significantly lowered in the diuretic group . This made it necessary to administer potassium perorally to most of this group and to two of them even in the form of infusions . No significant differences in the parameters of the newborn infants were observed . On the other h and , the placentae in the diuretic group were definitely larger than in the control group , a fact which may be suggestive or eventual alterations in the glycogen metabolism\n\n\nTitle 5:\nTHE EFFECT OF A LOW CALORIE DIET OR A THIAZIDE DIURETIC ON THE INCIDENCE OF PRE‐ECLAMPSIA AND ON BIRTH WEIGHT\nAbstract 5:\nA 1200 calorie diet or cyclopenthiazide with potassium was given to two groups of 51 high weight gain primigravidae and baby weight and the incidence of pre‐eclampsia were compared with those in a matched control group . There was no difference in the development of pre‐eclampsia , but the weight of babies in the control group was higher than in the treated groups . The body fat was reduced in the diet group and the total body water in the diuretic group\n\n\nTitle 6:\nA Clinical Study of the Effects of an Aldosterone Antagonist (Aldactone‐A) and a Thiazide Diuretic (Enduron) in Pregnancy\nAbstract 6:\nThe use of a diuretic is frequently advocated in pregnancies complicated by excessive weight gain , generalised oedema , hypertension , or overt pre-eclampsia . A wide range of drugs has been tried under such circumstances . One of the newer diuretic agents is Aldactone-A , a spironolactone possessing antagonistic action to aldosterone , and this drug has also been recommended for the resistant types of oedema . Since it was first described in 1957 ( Kagawa et al. , 1957 ) , conflicting reports have been received concerning its effects in normal and pre-eclamptic pregnancies . Although its clinical and pharmacological effects have been studied in the non-pregnant state , much less is known about its place during pregnancy and its effects on the feto-placental unit . Since it possesses a different mechanism of action to other diuretic agents in common use , the administration of Aldactone-A in combination with other diuretic agents may be advantageous and may reduce the incidence of undesirable pharmacological effects . The present study reports the results of a clinical therapeutic trial involving the use of an aldosterone antagonist , Aldactone-A , a st and ard thiazide diuretic agent in current use , methychlothiazide ( Enduron ) , and a combination of these two agents , in pregnancy complicated by hypertension . During the study , the effect of these agents on urinary oestriol excretion was also assessed\n\n\nTitle 7:\nEffects of diuretics on plasma volume in pregnancies with long-term hypertension.\nAbstract 7:\nThe purpose of this r and omized , prospect i ve study was to investigate the effects of diuretics on plasma volume findings and perinatal outcome in pregnancies complicated by mild long-term hypertension . Twenty patients were in their first trimester and were receiving diuretics at time of entry to the study : Ten patients were allowed to continue their diuretic medication throughout pregnancy ( diuretic group ) , whereas for the other 10 patients , diuretics were discontinued immediately . Plasma volume was serially measured throughout pregnancy with the use of the Evans blue dye-dilution technique . Initial plasma volume was similar in the two groups . However , in the diuretic group , subsequent plasma volume findings at various stages of gestation were markedly reduced when compared to respective plasma volume findings in the other group . In addition , plasma volume expansion was minimal in the diuretic group ( mean increase of 18 % ) , whereas it was normal in the other group ( mean increase of 52 % ) . Two patients in the diuretic group and one patient in the other group required other antihypertensive medication . There was no difference in perinatal outcome between the two groups . These results suggest that in hypertensive pregnancies , diuretics prevent normal plasma volume expansion without influencing perinatal outcome\n\n\nTitle 8:\nA controlled trial of hypotensive agents in hypertension in pregnancy.\nAbstract 8:\nAbstract A controlled trial of bendrofluazide and methyldopa in 100 patients with hypertension in pregnancy is reported . In patients developing hypertension before twenty weeks of pregnancy treatment seemed to improve the chances of a successful outcome to the pregnancy . In those developing late hypertension treatment was of no value in the presence of proteinuria . The presence or absence of proteinuria seemed to be of more importance than the level of the diastolic pressure", "role": "user" }, { "content": "There is insufficient evidence to draw reliable conclusions about the effects of diuretics on prevention of pre-eclampsia and its complications .\nHowever , from this review , no clear benefits have been found from the use of diuretics to prevent pre-eclampsia .", "role": "assistant" } ]

[ { "content": "You will be presented with the full text of a biomedical research paper. Please write an abstract for this paper. Your response should only include the abstract and no additional text.\n\nPaper text:\nhepatitis c virus ( hcv ) infection , the major cause of chronic liver disease , cirrhosis , and liver cancer , affects approximately 170 million individuals worldwide.1 combination therapy with pegylated interferon ( peg - ifn ) plus ribavirin has become the current standard regimen for patients with chronic hepatitis c. such therapy is associated with overall sustained virologic response rates of 75% to 90% among patients with hcv genotype 2 or 3 infection and 45% to 52% among those with genotype 1.2 recently , a new combination therapy together with thymosin alpha-1 has been investigated in difficult - to - treat patients to increase treatment response.3 the therapy is associated with various side effects , especially hematologic abnormalities .\nsome studies suggest that peg - ifn is commonly associated with a higher incidence of neutropenia compared with standard ifn therapy.4 nevertheless , it is known that neutropenia during peg - ifn therapy does not appear to be associated with serious sequela and seems to be effectively managed by dose modifications.5 neutropenic enterocolitis is a life - threatening complication of intensive chemotherapy , and remains a clinical syndrome characterized by abdominal pain and fever in neutropenic patients .\nthis disease entity has been most often described in patients with hematologic malignancies such as acute leukemia , multiple myeloma , and aplastic anemia , following chemotherapy.6 in rare cases , this complication has also been reported in the setting of solid cancer and autologous transplantation,6 but almost never documented in patients with chronic hepatitis c. in this report , we describe a rare case of fatal neutropenic enterocolitis encountered in a patient with chronic hcv infection receiving peg - ifn plus ribavirin combination therapy .\na 54-year - old man with known hcv infection was referred to our institution for treatment of chronic hepatitis c. pretreatment laboratory tests were as follows : elevated aspartate aminotransferase ( ast ) and alanine aminotransferase ( alt ) levels , 97 and 202\niu / l , respectively ; total bilirubin level , 1.9 mg / dl ; white blood cell ( wbc ) count , 5,400/mm ; platelet count , 149,000/mm ; prothrombin time ( inr ) , 1.21 ; genotype 2a ; and hcv viral load , 371,000 iu / ml . there was no history of alcohol abuse , gastrointestinal diseases , other co - infectious diseases , and metabolic diseases .\nalthough a liver biopsy was not performed , an ultrasound examination of the liver revealed a coarse echotexture of the parenchyma , an irregular nodular surface , and splenomegaly ( 13 cm ) , together highly suggestive of cirrhosis ( fig .\na 24-week course of standard combination therapy with peg - ifn alpha 2a 180 g weekly and ribavirin 800 mg daily was planned . at week 12 of treatment ,\nserum hcv rna was negative , but ast and alt levels remained elevated at approximately 2 times the upper limits of normal .\nthe therapy was continued until week 22 without serious side effects , except a sustained weight loss of 15 kg , anorexia , and general weakness . through 20 weeks of treatment\n, wbc counts of the patient were maintained between 2,000 and 2,600/mm , with absolute neutrophil counts ( anc ) ranging from 760 to 945/mm ( fig .\n2 ) . after 22 weeks of antiviral treatment , however , he complained of the sudden onset of diarrhea and abdominal pain with severe tenderness over the right side of the abdomen . on admission to the hospital ,\nhis temperature was 39.1 , the pulse was 113/min and regular , the respiratory rate was 28/min , and the blood pressure was 90/50 mmhg .\nthe laboratory findings included total wbc count , 1,000/mm ; anc , 611/mm ; platelet count , 41,000/mm ; hemoglobin , 9.8 g / dl ; and elevated liver enzymes ( ast , 217 iu / l and alt , 117 iu / l ) . a computed tomography ( ct ) scan with contrast of the patient 's abdomen was obtained and demonstrated marked edematous wall thickening of the ascending and proximal transverse colons , with pericolic strands ( fig .\nthe diagnosis of neutropenic enterocolitis was made based on the presence of fever , abdominal pain , and bowel wall thickening .\nbroad spectrum antibiotics , inotropic support , and granulocyte colony - stimulating factor were administered immediately . despite intensive antibiotic therapy and best supportive treatment , he continued to deteriorate and ultimately died from multiorgan failure on hospital day 9 .\nneutropenic enterocolitis occurs most often following treatment of hematologic malignancies and high - dose chemotherapy in solid tumors , and has a 5.3% pooled incidence rate , with high mortality rates ranging from 50% to 100%.7 neutropenia is often observed in patients with chronic hepatitis c receiving peg - ifn and ribavirin combination therapy , but is generally well - tolerated without serious morbidities.5 moreover , intestinal complications associated with the combination therapy are rare , with only a few case reports of exacerbation of ulcerative colitis and ischemic colitis.8 - 10 with regard to other intestinal events relevant to hcv therapy , a literature search found only one case of neutropenic enterocolitis which improved with empirical antibiotics and supportive care.11 thus , to the best of the authors ' knowledge , our patient is the second reported case to date and the first reported death from neutropenic enterocolitis while on hcv therapy .\nneutropenic enterocolitis is highly suspected in neutropenic patients presenting with fever and abdominal pain , especially in the right lower quadrant.6 abdominal imaging is useful in supporting a diagnosis of this disease .\nsome have suggested the criteria for the diagnosis of neutropenic enterocolitis to be fever , abdominal pain , and demonstration of the bowel wall thickening of more than 4 mm in any segment by ultrasound or ct scanning in a neutropenic state.6 our patient met all of these criteria , and the diagnosis of netropenic enterocolitis in this case was therefore definite .\nalthough the mechanism for the pathogenesis of neutropenic enterocolitis is not completely understood , it is postulated that a combination of factors , including mucosal injury by cytotoxic drugs , neutropenia , and impaired host defense to intestinal organisms progressing to bacteremia and sepsis , is responsible for the development of neutropenic enterocolitis.6,12 particularly , cirrhotic patients are at increased risk of bacterial infection because of intrinsic neutropenia , liver dysfunction , and reduced reticuloendothelial function .\nthus , neutropenia during therapy of hcv infection can intensify the risk of infection in patients with hcv - related cirrhosis .\nrecently , it has been shown that a shorter course of peg - ifn and ribavirin therapy over 12 weeks is as effective as a 24-week course for patients with hcv genotype 2 or 3 who have a virologic response at 4 weeks.13 it is unfortunate that in our case , hcv rna at 4 weeks was not tested and the patient with hcv genotype 2a adhered so closely to a strict schedule of antiviral therapy . in retrospect , the therapy could have been discontinued earlier if serum hcv rna was undetectable at week 4 of therapy , taking into consideration the significant weight loss and anorexia in our patient . in conclusion , we believe this case report contains a worthwhile clinical lesson for practitioners who manage patients with chronic hepatitis c , especially those patients with advanced fibrosis or cirrhosis . although some studies have indicated a negligible risk of infection associated with hcv treatment - related neutropenia,5 caution should be exercised against serious infections when treating cirrhotic patients who are potentially immunocompromised .\nalthough anorexia , weight loss and general weakness are non - specific adverse events of hcv combination therapy , if sustained and uncorrectable , clinicians should be aware of the potential development of neutropenic enterocolitis . furthermore , a shorter course of therapy could be considered in an effort to avoid possible severe life - threatening side effects for those with cirrhosis who have had a rapid virologic response to therapy .", "role": "user" }, { "content": "it is known that neutropenia caused by combination pegylated interferon plus ribavirin therapy for hepatitis c virus ( hcv ) infection is well tolerated and carries a negligible risk of infection . \n neutropenic enterocolitis is encountered most frequently in patients with hemato - oncologic diseases who are undergoing intensive chemotherapy . \n however , little information exists regarding this life - threatening event in the setting of hcv therapy . \n we present here an unusual case of fatal neutropenic enterocolitis in a cirrhotic patient receiving combination therapy for hcv infection . \n this is the first report of a death from neutropenic enterocolitis associated with treatment for chronic hcv infection . \n the present case suggests that caution should be exercised when continuing hcv therapy in neutropenic patients with advanced fibrosis , and the decision to maintain such therapy should be balanced against the potential for serious adverse events .", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2019 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from the options provided. A short description of the datasets is also provided to help you.\n\nQuery: I want to train a model for video summarization.\n\nKeyphrases: video summarization\n\nDataset description:\nSumMe: The SumMe dataset is a video summarization dataset consisting of 25 videos, each annotated with at least 15 human summaries (390 in total).\nConvAI2: The ConvAI2 NeurIPS competition aimed at finding approaches to creating high-quality dialogue agents capable of meaningful open domain conversation. The ConvAI2 dataset for training models is based on the PERSONA-CHAT dataset.\nViolin: Video-and-Language Inference is the task of joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip.\nOpoSum: OPOSUM is a dataset for the training and evaluation of Opinion Summarization models which contains Amazon reviews from six product domains: Laptop Bags, Bluetooth Headsets, Boots, Keyboards, Televisions, and Vacuums. The six training collections were created by downsampling from the Amazon Product Dataset introduced in McAuley et al.\n\nOptions: A: SumMe B: ConvAI2 C: Violin D: OpoSum", "role": "user" }, { "content": "SumMe", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: A quantitative approach for analyzing the spatio-temporal distribution of 3D intracellular events in fluorescence microscopy\nArticle:\nAbstract:\nAnalysis of the spatial distribution of endomembrane trafficking is fundamental to understand the mechanisms controlling cellular dynamics, cell homeostasy, and cell interaction with its external environment in normal and pathological situations. We present a semi-parametric framework to quantitatively analyze and visualize the spatio-temporal distribution of intracellular events from different conditions. From the spatial coordinates of intracellular features such as segmented subcellular structures or vesicle trajectories, QuantEv automatically estimates weighted densities that are easy to interpret and performs a comprehensive statistical analysis from distribution distances. We apply this approach to study the spatio-temporal distribution of moving Rab6 fluorescently labeled membranes with respect to their direction of movement in crossbow- and disk-shaped cells. We also investigate the position of the generating hub of Rab11-positive membranes and the effect of actin disruption on Rab11 trafficking in coordination with cell shape.\nIntroduction:\nModern light microscopy associated with fluorescence molecule tagging allows studying the spatial distribution of intracellular events. Unfortunately, fluorescent images are complex to analyze and additional software is needed to evaluate statistical differences between different conditions( Meijering et al., 2016; Tinevez et al., 2017). Automatic methods have the obvious advantage of being quicker and reproducible. However, most computational methods are based on the complex combination of heterogeneous features such as statistical, geometrical, morphological and frequency properties( Peng, 2008), which makes it difficult to draw definitive biological conclusions. Additionally, most experimental designs, especially at single-cell level, pool together data coming from replicated experiments of a given condition( Schauer et al., 2010; Merouane et al., 2015; Biot et al., 2016), neglecting the biological variability between individual cells. Micro-patterning is now a well-established strategy to reduce morphological variability by imposing constraints on adhesion sites, which has been shown to influence the cytoskeleton geometry and transport carrier localization( Théry et al., 2005; Schauer et al., 2010). This technique opened the way to pairwise comparisons of conditions with a two-sample kernel density-based test by pooling together all data from each condition( Duong et al., 2012). Unfortunately, it does not consider the sample-to-sample variability because all replicated experiments from a given condition are simply merged together. Additionally, the visualization of the kernel density maps enables to average several experiments but fails to identify specific locations of interest in the cell( e. g. docking areas). Finally, assessing the dynamical behavior of labeled membrane structures, a fundamental task for trafficking analysis, remains out of scope in this framework. In this paper, we describe a method that we call QuantEv dedicated to the analysis of the spatial distribution of intracellular events represented by any static or dynamical descriptor( e. g. detected points, segmented regions, trajectories...) provided that the descriptors are associated with spatial coordinates. QuantEv offers a unifying frame to decipher complex trafficking experiments at the scale of the whole cell. It is typically able to detect subtle global molecular mechanisms when trajectory clustering fails. An overview of the approach is presented in Figure 1. Our approach first computes 3D histograms of descriptors in a cylindrical coordinate system( parameterized by radius r, angle θ and depth z) with computational cell shape normalization, enabling comparisons between cells of different shape. Densities are obtained via adaptive kernel density estimation( Silverman, 1986; Taylor, 2008). Visualization through histograms and densities allows giving a clear biological interpretation of the experiments. We use the Earth Mover’s Distance( Rubner et al., 2000) and the Circular Earth Mover’s Distance( Rabin et al., 2011) to measure the dissimilarity between densities associated with different experimental conditions. A statistical analysis of these distances reliably takes into account the biological variability over replicated experiments. By computing weighted densities for each point in the cell as the reference center, QuantEv identifies the point that gives the most uniform angular distribution. This point may coincide with a biological structure of interest that would act as the events emitter or attractor. In the section Results, we describe the application of QuantEv to detect significant differences between molecular trafficking and phenotypes observed in cells with various shapes. The first application is concerned with the distribution of membranes labeled by GFP-Rab6 as a hallmark of vesicular carriers in unconstrained, crossbow- and disk-shaped cells. Rab6 proteins are transiently anchored to moving transport carriers from the Golgi apparatus located at the cell center to Endoplasmic Reticulum entry sites or to plasma membrane( White et al., 1999; Chavrier and Goud, 1999; Echard et al., 2000; Opdam et al., 2000; Grigoriev et al., 2007; Bardin et al., 2015), both assumed to be located at the cell periphery. Cell shape imposes constraints on the cytoskeleton and consequently influences the spatial distribution of Rab6 transport carriers, as confirmed with kernel density maps( Schauer et al., 2010). We apply QuantEv to visualize and quantify this influence and to localize regions in the cell associated with Rab6 trafficking stages. In addition, Rab6 positive membranes were reported to move from and toward the Golgi in apparent close proportions( Grigoriev et al., 2007, Grigoriev et al., 2011), and yet these membrane associated proteins are believed to traffic in majority from the Golgi located at the cell center to the cell periphery( White et al., 1999; Chavrier and Goud, 1999; Echard et al., 2000; Opdam et al., 2000; Grigoriev et al., 2007) where they should dissociate from membranes and recycle back to the cytosol. To investigate these apparently antagonist statements, we apply QuantEv on Rab6 trajectories to characterize the dynamical behaviors of these transport carriers. The second application focuses on the dynamics of mCherry-Rab11-positive membranes. Rab11 is known to be primarily localized to the Endosomal Recycling Compartment( ERC), and it organizes spatially and temporally recycling from this compartment( Ullrich et al., 1996; Gidon et al., 2012; Baetz and Goldenring, 2013; Boulanger et al., 2014). Here, we confirm by using QuantEv the hypothesis that the labeled transport intermediates are uniformly distributed around the ERC at the plasma membrane plane. Furthermore, we also investigate the progressive effect of actin disruption induced by Latrunculin A injection on the ERC localization with respect to time. We finally apply QuantEv to analyze the joined influence of actin disruption and cell shape on the radial distribution of Rab11 vesicles trafficking.\nDiscussion:\nThis article presents a computational framework taking into account cell variability to quantify the distribution of fluorescently labeled proteins. Using dynamical descriptors, detailed insight into dynamical processes is also unraveled and the uniformity analysis allows to localize an organizing region for the observed biological objects. Additionally to the input image, the user has to define three other inputs that depend on the biological application. First, the user has to decide which coordinate system to use. If the imaged cells are flat as in this study( see Appendix 1—figure 1a–c), a cylindrical coordinate system is well suited while a spherical coordinate system will fit better rounded cells. If the user is not familiar with cylindrical or spherical coordinate systems, a classical Cartesian system is also available, even though less suited to intracellular spatial distribution. Finally, QuantEv also allows to analyze the spatial distribution with respect to a reference point or to membrane borders( Heride et al., 2010). Once the reference coordinate system is chosen, the user has to define a reference point, typically the particle emitter or attractor, and a reference direction in order to fairly compare cells. For example, in this study, the direction between the Golgi and the cell center were used to define a reference direction for unconstrained and disk-shaped cells while the crossbow principal axis was used for crossbow-shaped cells. As intensity is proportional to the amount of proteins in fluorescence microscopy, using intensity observed in segmented areas is potentially more informative than binary segmentation masks. However, because of phenomena such as photobleaching, phototoxicity, shading, uneven illumination etc., appropriate normalization procedures within and between images need to be applied. If the user is able to correct for these phenomena, it is preferable to use intensity as weights in QuantEv analysis. Otherwise, intensity weights should be avoided. Given its genericity, QuantEv can easily be applied to any intracellular event and gives useful insights about their spatial distribution across conditions. From these observations, the user can then apply more sophisticated analyses such as mechanistic models of dynamics( Ponti et al., 2004; Jaqaman et al., 2008) or generative models( Li et al., 2012; Johnson et al., 2015a, Johnson et al., 2015b). QuantEv analysis conclusions can also be the starting point of a new modeling. We demonstrate with the help of QuantEv that the distributions of Rab6-positive membranes from unconstrained, crossbow- and disk-shaped cells are statistically different. QuantEv also enables to identify the locations where Rab6-positive membranes enter their docking phase. By considering the directions of the moving Rab6-positive membranes, QuantEv allows demonstrating that these membranes first move predominantly and directly toward the cell periphery before reaching their docking phase. They then go back to the cell center in an undirected and long fashion. This intriguing result showing statistically bi-directional movements of Rab6 was reported before. The Rab6-positive vesicles generated at the Golgi membranes are predestined to the cell periphery, in order to deliver their exocytic cargo( Grigoriev et al., 2007; Grigoriev et al., 2011), which should favor a centrifuge directionality. Our data reconciles this two apparently opposed observations and show for the first time, that a majority of Rab6 vesicles reverses their movement only toward close docking-fusion sites and only during this ultimate phase of docking-fusion. QuantEv also demonstrates that Rab11 positive membranes are uniformly distributed around the ERC at the plasma membrane plane. This shows that the ERC represents an organizing hub for the Rab11 carrier vesicles. By applying the QuantEv uniformity analysis along time, we exhibit how the ERC location is affected by actin disruption caused by Latrunculin A injection. The radial distribution analysis of Rab11-positive membranes combined with Latrunculin A injection reveals a dual regulation by cell shape and actin organization on Rab11 trafficking at the plasma membrane, and more generally on the exocytosis/recycling vesicle distribution. In conclusion, QuantEv has the potential to become a very popular analysis method for dynamics and intracellular event analysis as( i) it is publicly available;( ii) it is fully automated and semi-parametric;( iii) it provides results that are easy to biologically interpret;( iv) it performs a statistical analysis that takes into account the biological variability over the replicated experiments of a same condition and is efficient with small and large amounts of data. On a biological prospective beyond the two particular models presented here, QuantEv will be of great interest for studies where quantitative and statistical analysis of intracellular membrane or particle behaviors are required, depending on physical and external constraints. For instance, in single-cell experiments performed in microfluidics devices, QuantEv will efficiently provide automation and diversity of statistical analyses in ‘one shot’, for a relatively small amount of data. Applying QuantEv in multi-cellular systems, in which cell-cell constraints necessarily affect molecular distribution and particle movements will also be of great interest. Finally, in vivo imaging of single-cell intracellular processes in a very confined and constrained environment will benefit from the generic aspect of the QuantEv sensing and measuring of particle spatial distributions, dynamical measures with respect to intracellular localization and cell to cell variability. An Icy plugin and a tutorial are available at http://icy. bioimageanalysis. org/plugin/QuantEv. A QuantEv analysis module is available on TrackMate and a QuantEv track processor is available in Icy.", "role": "user" }, { "content": "Proteins are the workhorses of the body , performing a range of roles that are essential for life . Often , this requires these molecules to move from one location to another inside a cell . Scientists are interested in following an individual protein in a living cell ‘in real time’ , as this helps understand what this protein does . Scientists can track the whereabouts of a protein by ‘tagging’ it with a fluorescent molecule that emits light which can be picked up by a powerful microscope . This process is repeated many times on different samples . Finally , researchers have to analyze all the resulting images , and conduct statistical analysis to draw robust conclusions about the overall trajectories of the proteins . This process often relies on experts assessing the images , and it is therefore time-consuming and not easily scalable or applied to other experiments . To help with this , Pécot et al . have developed QuantEV , a free algorithm that can analyze proteins’ paths within a cell , and then return statistical graphs and 3D visualizations . The program also gives access to the statistical procedure that was used , which means that different experiments can be compared . Pécot et al . used the method to follow the Rab6 protein in cells of different shapes , and found that the conformation of the cell influences where Rab6 is located . For example , in crossbow-shaped cells , Rab6 is found more often toward the three tips of the crossbow , while its distribution is uniform in cells that look like disks . Another experiment examined where the protein Rab11 is normally placed , and how this changes when the cell’s skeleton is artificially disrupted . Both studies help to gain an insight into the behavior of the cellular structures in which Rab6 and Rab11 are embedded . Following proteins in the cell is an increasingly popular method , and there is therefore a growing amount of data to process . QuantEV should make it easier for biologists to analyze their results , which could help them to have a better grasp on how cells work in various circumstances .", "role": "assistant" } ]

[ { "content": "You will be presented with the full text of a biomedical research paper. Please write an abstract for this paper. Your response should only include the abstract and no additional text.\n\nPaper text:\nthyroid nodules are uncommon in children and adolescents compared with adults , but the risk of malignancy is much higher ( 14 to 40% in children compared with 5% in adults ) ( 1 - 3 ) . in adults , fine needle aspiration biopsy ( fnab ) has been used extensively for the management of thyroid disease and for patient selection for surgical exploration with a high degree of reliability ( 4,5 ) .\nhowever , fnab has not been utilized extensively for the evaluation of thyroid nodules in the young ; and relevant data in the literature are often in disagreement ( 2,6 - 10 ) . to assess the utility of fnab for the management of children and adolescents , we reviewed our experience with fnab for thyroid nodules in children and adolescents .\nthe reports of thyroid fnab performed in 51 children and adolescents at the inje university ilsan paik hospital were reviewed .\neighty one percent of the procedures were performed by three cytopathologist , using 23 gauge needles connected to 10 ml syringes . in these cases ,\ncytological material was smeared immediately onto slides . some of the slides were air dried and stained with diff - quik stain for an immediate evaluation of specimen adequacy .\nall of these slides were alcohol - fixed and sent to our laboratory for staining and evaluation .\nfnab results were classified into three categories : 1 ) malignant , when the aspirates had unequivocal cytological findings of malignancy ; 2 ) suspicious for malignancy , including follicular neoplasms and aspirates that showed some features of papillary carcinoma , e.g. , a few cells with intranuclear inclusions or nuclear grooves but without sufficient criteria for a definitive diagnosis of malignancy ; and 3 ) benign , including nodular hyperplasia , colloid cyst , and thyroiditis .\naspirates with less than at least six clusters of well preserved follicular cells on two slides were considered unsatisfactory ( 11 ) .\nfifty - one children and adolescents underwent fnab , and a total of 60 fnabs were performed on these patients .\npatients ' ages ranged from 2 to 21 yr with a mean age of 17 yr . sixteen ( 27% ) of the patients were 2 to 15 yr old .\nthirty - eight ( 75% ) were female and thirteen ( 25% ) were male .\nforty - five ( 74% ) of the aspirates were diagnosed as \" benign \" .\nfive ( 8% ) of the aspirates were diagnosed as \" suspicious for malignancy \" .\nfour of these aspirates were further diagnosed as follicular neoplasm and one was suspicious for papillary carcinoma .\nsix ( 10% ) of the aspirates were diagnosed as \" malignant \" and further diagnosed as papillary carcinoma .\nfour ( 7% ) of the aspirates were \" unsatisfactory \" ( table 1 ) .\nof 5 patients with a cytological diagnosis of \" benign \" , three had nodular hyperplasia and two follicular adenoma . of 4 patients with a cytological diagnosis of \" follicular neoplasm \" , one had nodular hyperplasia , two had follicular adenoma , and one papillary carcinoma .\none patient with a cytological diagnosis of \" suspicious for papillary carcinoma \" had papillary carcinoma .\none of 4 patients with a cytological diagnosis of \" unsatisfactory \" underwent surgery and was found to have papillary carcinoma .\nthe cases \" suspicious \" or \" malignant \" by cytological diagnosis that were found to have a malignant lesion at surgery were considered \" true positive . \" \" true negative \" cases comprised cases considered \" benign \" with a benign lesion , including follicular adenoma , on resection . using these criteria ,\nthe diagnostic accuracy of fnab was 81% with a sensitivity of 100% and a specificity of 63% .\npositive and negative predictive values were 73% and 100% , respectively , and false negative and positive values were 0% and 37% , respectively .\nthree false positive cases were diagnosed as \" follicular neoplasm \" on fnab but revealed nodular hyperplasia or follicular adenoma on surgical resection .\nthe cytological findings of these cases were the presence of syncytial fragments , a microfollicular pattern , and nuclear grooves ( fig .\n1 ) . two of 5 true negative cases revealed follicular adenoma on surgical resection .\nthese cases showed some clusters of atrophic follicular epithelial cells and a few scattered macrophages in the bloody background ( fig .\nin adults , fnab has become a part of the routine evaluation of thyroid nodules . since its introduction\n, the percentage of patients that undergo thyroidectomy has decreased by 25% to 50% with the use of fnab ( 6 ) .\nbut fnab has been underutilized for the evaluation of thyroid nodules in the young because of the possibility of complications and the need for sedation . in our practice ,\nsedation is rarely required and no complications have arisen . in our opinion , fnab is a relatively simple procedure with few complications .\ninternal and external reports of predominantly adult patients with thyroid nodules show that the sensitivity of thyroid fnab ranges from 80 - 100% with a specificity of 90 - 100% ( 3 - 5,12 - 15 ) .\ninvestigations of fnab in pediatric thyroid nodules have shown a wide range of sensitivities ( 7 - 10 ) .\n( 7 ) reported on 18 children who underwent surgery after thyroid fnab and found a sensitivity of 50% .\n8) reported on 24 children who underwent thyroidectomy for thyroid nodules , and a retrospective review of the cytological materials of 18 cases that received preoperative thyroid fnab revealed a sensitivity of 60% .\nthus , because of its apparent low sensitivity , they concluded that fnab did not have a primary role in surgeon 's decision regarding the surgical management of these patients .\n( 9 ) reported on 42 children who underwent surgery after thyroid fnab and found a sensitivity of 95% .\n( 10 ) reported a sensitivity of 100% in 218 child and adolescent thyroid aspirates . in the present study\nthese better results are similar to those obtained in adults and suggest that fnab is highly effective at selecting patients for surgery without missing malignant lesions .\nthe reported specificities of thyroid fnab in pediatric thyroid nodules ranges from 65 to 90% ( 7 - 10 ) . in our study , its specificity of 63% was lower than usual .\n10 ) suggested that because most cases with a negative fnab result were followed up clinically , it was difficult to estimate the true negative diagnosis in the follow up group .\nif this group were considered true negative in the present study , specificity increases to 94% .\nanother statistical problem concerns the precise definition of false positive and false negative . in our studies , for statistical analysis , cases with a suspicious or malignant cytological diagnosis that had a malignant lesion at surgery\nfollicular adenomas and carcinomas are both neoplastic lesions and their differentiation usually requires surgical excision and examination of entire nodules .\ntherefore , in some studies , the cases with a cytological diagnosis of suspicious or positive for malignancy and a histological diagnosis of follicular neoplasms encompassing both follicular adenoma and follicular carcinoma are considered true positive results . and , using these criteria , the sensitivity and specificity of our study would have been 83% and 75% . even if the statistical problems were considered ,\nthe reported specificities including ours had a wide range of figure and were sometimes disappointing .\nfollicular neoplasms have generally been considered a diagnostic \" gray zone \" in thyroid fnab . included in this group\nbecause of overlapping cytologic features , a diagnosis of follicular carcinoma is usually made after examining permanent sections following surgical treatment .\nthe overall rate of malignancy in nodules with cytological diagnosis of follicular neoplasm has been reported as approximately 20 - 30% ( 16 ) .\nkim et al . reported that 50% of such patients were diagnosed as malignancy , and an age below 20 yr ( 77% ) had a significant increased risk for malignancy ( 16 ) . in the present study , one of four cases with a cytological diagnosis of follicular neoplasm revealed papillary carcinoma .\nbut is similar to the overall rate of 20 - 30% . in our false positive cases ,\nthe presence of syncytial fragments , a microfollicular pattern , and nuclear grooves misled a cytological diagnosis of follicular neoplasm .\nthe nuclear grooves are a non - specific feature which can be seen in cases of hashimoto 's thyroiditis , nodular hyperplasia with oncocytes , follicular adenoma , or hurthle cell adenoma ( 5 ) .\nof five present cases with a cytological diagnosis of benign , two cases were histologically diagnosed as follicular adenoma .\nthese cases showed some clusters of atrophic follicular epithelial cells and a few scattered macrophages in the bloody background .\nyang et al . suggested the most important clue in differentiating follicular neoplasm from nodular hyperplasia was \" abundant blood containing microfollicles \" ( 17 ) .\nhowever , macrofollicular adenomas have far lower microvessel density than microfollicular nodules because the space occupied by the large colloid lakes are devoid of blood vessels .\nlikewise , a discrete but unencapsulated microfollicular nodule will be diagnosed as \" follicular neoplasm \" by fnab , resulting in the excision of nonneoplastic nodules .\nsome reports have suggested that the cases diagnosed as follicular neoplasm on thyroid can be stratified into lesions with a high risk of malignancy and with a low risk of malignancy that can be managed by clinical observation alone on the basis of clinical characteristics such as large size of the index nodule ( lesions measuring 3 cm or larger ) and male sex ( 18 ) .\nhowever , we experienced that one papillary carcinoma of a cytological diagnosis of follicular neoplasm was female and her thyroid nodule measured 1.8 cm in diameter . in another three cases revealed follicular adenoma or nodular hyperplasia , the ratio of male : female was 1:2 and their nodule measured 3.3 cm to 3.4 cm in diameter .\nalthough clinical characteristics can help in selecting patients for surgery , the final diagnosis by histological examination is needed .\nseveral reports have suggested that the use of immunohistochemical markers such as cytokeratin-19 , galectin-3 , and hbme-1 are useful in fnab specimens of the thyroid to differentiate between benign and malignant lesions ( 19 - 21 ) .\nwe concluded that fnab is a good screening test for thyroid nodules in children and adolescents because of its high sensitivity .\nhowever , the additional use of various clinical variables and immunohistochemical markers can be helpful to differentiate in follicular neoplasms in fnab .", "role": "user" }, { "content": "thyroid nodules are uncommon in children and adolescents compared with adults , but the risk of malignancy is much higher . in adults , fine needle aspiration biopsy ( fnab ) has been used extensively to select patients for surgical exploration with a high degree of reliability . \n the purpose of this study was to assess the utility of fnab for the management of thyroid nodules in children and adolescents . \n we reviewed our experience with 60 fnabs of thyroid nodules in 51 children and adolescents . \n of the 60 aspirates , 45 aspirates ( 74% ) were diagnosed as \" benign \" , 5 aspirates ( 8% ) as \" suspicious for malignancy \" , and 6 aspirates ( 10% ) as \" malignant \" , and 4 aspirates ( 7% ) as \" unsatisfactory \" . \n thyroidectomy was performed in 17 patients , and 5 with a cytological diagnosis of \" benign \" revealed nodular hyperplasia in three and follicular adenoma in two ; 5 with a cytological diagnosis of \" suspicious \" revealed nodular hyperplasia in one , follicular adenoma in two , and papillary carcinoma in two ; and 6 with a cytological diagnosis of \" malignant \" revealed papillary carcinoma . \n one patient with a cytological diagnosis of \" unsatisfactory \" revealed papillary carcinoma . \n the diagnostic accuracy was 81% with 100% sensitivity and 63% specificity . \n the positive and negative predictive values of fnab were 73% and 100% , respectively . \n we conclude that fnab is a good screening test for thyroid nodules in children and adolescents because of its high sensitivity .", "role": "assistant" } ]

[ { "content": "Below are the Abstract, Introduction, and Conclusion sections of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary sentence and no additional text.\n\nPaper text:\n\nMeta learning has been making impressive progress for fast model adaptation.\nHowever, limited work has been done on learning fast uncertainty adaption for Bayesian modeling.\nIn this paper, we propose to achieve the goal by placing meta learning on the space of probability measures, inducing the concept of meta sampling for fast uncertainty adaption.\nSpecifically, we propose a Bayesian meta sampling framework consisting of two main components: a meta sampler and a sample adapter.\nThe meta sampler is constructed by adopting a neural-inverse-autoregressive-flow (NIAF) structure, a variant of the recently proposed neural autoregressive flows, to efficiently generate meta samples to be adapted.\nThe sample adapter moves meta samples to task-specific samples, based on a newly proposed and general Bayesian sampling technique, called optimal-transport Bayesian sampling.\nThe combination of the two components allows a simple learning procedure for the\n\nmeta sampler to be developed, which can be efficiently optimized via standard back-propagation.\nExtensive experimental results demonstrate the efficiency and effectiveness of the proposed framework, obtaining better sample quality and faster\n\nuncertainty adaption compared to related methods.\nMeta learning (Schmidhuber, 1987; Andrychowicz et al., 2016) is an important topic in modern machine learning.\nThe goal is to learn some abstract concepts from different but related tasks, which can then be adapted and generalized to new tasks and environments that have never been encountered during training.\nThere has been lots of research on this topic.\nA recent review classifies the methods as metric-based, model-based and optimization-based methods (Weng, 2018) .\nAmong these methods, learning-to-learn seeks to learn a meta optimizer that can be applied to different models, with some task-specific information such as current gradients as input (Andrychowicz et al., 2016) .\nModel agnostic meta learning (MAML) aims to learn a meta parameter/model from a set of training tasks such that it can quickly adapt to models for new tasks (Finn et al., 2017) .\nMany follow-up works have been proposed recently, including but not limited to the meta network (Munkhdalai & Yu, 2017) , the meta learner (Ravi & Larochelle, 2017) , the Reptile model (Nichol et al., 2018) , and the lately extensions to an online setting (Finn et al., 2019) , to model hierarchical relation (Yao et al., 2019) and sequential strategies (Ortega et al., 2019) , and to its stable version Antoniou et al. (2019) and to some theoretical analysis (Khodak et al., 2019) .\nIt is worth noting that all the aforementioned models are designed from an optimization perspective.\nBayesian modeling, in parallel with optimization, has also been gaining increasing attention and found various applications in deep learning.\nRecent research has extended the above meta-learning methods to a Bayesian setting.\nFor example, Bayesian MAML (BMAML) replaces the stochasticgradient-descent (SGD) step with Stein variational gradient descent (SVGD) for posterior sampling (Yoon et al., 2018) .\nProbabilistic MAML (PMAML) extends standard MAML by incorporating a parameter distribution of the adapted model trained via a variational lower bound (Finn et al., 2018) .\nAmortized Bayesian Meta Learning extends the idea of MAML to amortized variational inference (Ravi & Beatson, 2019; Choi et al., 2019) .\nVERSA (Gordon et al., 2019) uses an amortization network to approximate the posterior predictive distributions.\nMeta particle flow realizes Bayes's rule based on ODE neural operator that can be trained in a meta-learning framework.\nThough methodologically elegant with many interesting applications, the above methods lack the ability to uncertainty propagation/adaption, in the sense that uncertainty is either not considered (e.g., in MAML) or only considered in the specific task level (e.g., BMAML).\nThis could slow down model adaption or even inaccurate uncertainty modeling when considering from a Bayesian modeling perspective.\nFor example, suppose one is given samples from a set of Gaussians with different mean and covariance matrices, how can she/he efficiently leverage uncertainty in these samples to generate samples from a complex yet related distribution such as a Gaussian mixture?\nTo tackle this problem, we propose to perform meta learning on the space of probability measures, i.e., instead of adapting parameters to a new task, one adapts a meta distribution to new tasks.\nWhen implementing distribution adaption in algorithms where distributions are approximated by samples, our distribution-adaptation framework becomes sample-to-sample adaption.\nIn other words, the meta parameter in standard MAML becomes meta samples in our method, where uncertainty can be well encoded.\nFor this reason, we call our framework Bayesian meta sampling.\nSpecifically, we propose a mathematically elegant framework for Bayesian meta sampling based on the theory of Wasserstein gradient flows (WGF) (Ambrosio et al., 2005) .\nOur goal is to learn a meta sampler whose samples can be fast adapted to new tasks.\nOur framework contains two main components: a meta sampler and a sample adapter.\nFor the meta sampler, we adopt the state-ofthe-art flow-based method to learn to transport noise samples to meta samples.\nOur meta sampler is parameterized by a neural inverse-autoregressive flow (NIAF), an extension of the recently developed neural autoregressive flows (NAFs) (Huang et al., 2018) .\nThe NIAF consists of a meta-sample generator and an autoregressive conditioner model, which outputs the parameters of the meta-sample generator.\nThe NIAF takes some task-specific information (such as gradients of target distributions) and random noise as input and outputs meta samples from its generator.\nThese meta samples are then quickly adapted to task-specific samples of target distributions by feeding them to the sample adapter.\nTo ensure efficient and accurate adaptations to new task distributions, a novel optimal-transport Bayesian sampling (OP-sampling) scheme, based on Wasserstein gradient flows, is proposed as the adaptation mechanism of the sample adapter.\nThe OP-sampling is general and can ensure samples to be adapted in a way that makes the sample density evolve to a target distribution optimally, thus endowing the property of fast uncertainty adaption.\nFinally, when one aims to perform specific tasks such as Bayesian classification with a task network, these samples are used to encode uncertainty into modeling.\nTo this end, we further develop an efficient learning algorithm to optimize the task network based on variational inference.\nExtensive experiments are conducted to test the advantages of the proposed meta-sampling framework, ranging from synthetic-distribution to posterior-distribution adaption and to k-shot learning in Bayesian neural networks and reinforcement learning.\nOur results demonstrate a better performance of the proposed model compared to related methods.\nWe present a Bayesian meta-sampling framework, called DAMS, consisting of a meta sampler and a sample adapter for effective uncertainty adaption.\nOur model is based on the recently proposed neural autoregressive flows and related theory from optimal transport, enabling a simple yet effective training procedure.\nTo make the proposed model scalable, an efficient uncertainty parameterization is proposed for the task network, which is trained by variational inference.\nDAMS is general and can be applied to different scenarios with an ability for fast uncertainty adaptation.\nExperiments on a series of tasks demonstrate the advantages of the proposed framework over other methods including the recently proposed meta SG-MCMC, in terms of both sample efficiency and fast uncertainty adaption.", "role": "user" }, { "content": "We proposed a Bayesian meta sampling method for adapting the model uncertainty in meta learning", "role": "assistant" } ]

[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is armodafinil used for treatment of insomnia?\n\nContext: Other therapies, such as sedative hypnotics, target daytime insomnia, while pharmacologic agents such as modafinil, armodafinil, and caffeine and non-pharmacologic approaches such as napping promote nighttime alertness.\nOther treatment options may include pharmacologic interventions such as modafinil and armodafinil, which have shown efficacy in this population.\nBACKGROUND: Armodafinil (Nuvigil(®), Cephalon, Inc., Frazer, PA, USA), the longer-lasting isomer of racemic modafinil, is a nonamphetamine, wakefulness-promoting medication. In patients with excessive sleepiness associated with shift work disorder, treated obstructive sleep apnoea, or narcolepsy, armodafinil has been found to improve wakefulness throughout the shift or day. In addition, while not approved for this indication, armodafinil has been found to improve excessive sleepiness associated with jet-lag disorder.\nSTUDY OBJECTIVES: Armodafinil is a wakefulness-promoting medication. Its efficacy and tolerability have been established in 12-week studies of patients with excessive sleepiness (ES) associated with treated obstructive sleep apnea (OSA), shift work disorder (SWD), or narcolepsy.\nArmodafinil represents an option for long-term treatment of patients with ES associated with treated OSA, SWD, or narcolepsy.\nThe wakefulness-promoting agents armodafinil and modafinil are FDA approved for the treatment of ES in patients with SWD.\nCONCLUSIONS: Armodafinil significantly improved overall clinical condition related to excessive sleepiness as rated by the CGI-C and was well tolerated in patients with treated OSA and comorbid depression.\nCONCLUSION: In patients with excessive sleepiness associated with chronic SWD of moderate or greater severity, armodafinil significantly improved wakefulness during scheduled night work, raising mean nighttime sleep latency above the level considered to indicate severe sleepiness during the daytime. Armodafinil also significantly improved measures of overall clinical condition, long-term memory, and attention.\nAdjunct treatment with armodafinil significantly improved wakefulness, long-term memory, and patients' ability to engage in activities of daily living in nCPAP-adherent individuals with ES associated with OSA.\nA number of studies have evaluated countermeasures or interventions in shift workers; proposed treatments include chronobiotic interventions, such as light exposure, melatonin, hypnotic agents, caffeine and CNS stimulants (amphetamine), and the wake-promoting agents modafinil and armodafinil.\nThese studies showed that modafinil and armodafinil significantly improve the ability to sustain wakefulness during waking activities (e.g. working, driving), overall clinical condition, and sustained attention or memory in patients with SWSD.\nCONCLUSIONS: In this selected population of patients with OSA/HS and residual ES despite effective treatment with nCPAP, armodafinil QD used as an adjunct to nCPAP treatment was associated with improved wakefulness and overall clinical condition.\nOther therapies, such as sedative hypnotics, target daytime insomnia, while pharmacologic agents such as modafinil, armodafinil, and caffeine and non-pharmacologic approaches such as napping promote nighttime alertness.\nArmodafinil represents an option for long-term treatment of patients with ES associated with treated OSA, SWD, or narcolepsy.\nOther therapies, such as sedative hypnotics, target daytime insomnia, while pharmacologic agents such as modafinil, armodafinil, and caffeine and non-pharmacologic approaches such as napping promote nighttime alertness.\nIn this selected population of patients with OSA/HS and residual ES despite effective treatment with nCPAP, armodafinil QD used as an adjunct to nCPAP treatment was associated with improved wakefulness and overall clinical condition", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "content": "You will be presented with the abstract, introduction, and discussion section from a biomedical research article. Your task is to create a summary that a layperson can understand, capturing the essence of the research article. Keep essential scientific terms, but ensure that the language remains clear and the concepts are explained in an uncomplicated manner.\n\nTitle: Temporal integration of auxin information for the regulation of patterning\nArticle:\nAbstract:\nPositional information is essential for coordinating the development of multicellular organisms. In plants, positional information provided by the hormone auxin regulates rhythmic organ production at the shoot apex, but the spatio-temporal dynamics of auxin gradients is unknown. We used quantitative imaging to demonstrate that auxin carries high-definition graded information not only in space but also in time. We show that, during organogenesis, temporal patterns of auxin arise from rhythmic centrifugal waves of high auxin travelling through the tissue faster than growth. We further demonstrate that temporal integration of auxin concentration is required to trigger the auxin-dependent transcription associated with organogenesis. This provides a mechanism to temporally differentiate sites of organ initiation and exemplifies how spatio-temporal positional information can be used to create rhythmicity.\nIntroduction:\nSpecification of differentiation patterns in multicellular organisms is regulated by gradients of biochemical signals providing positional information to cells( Rogers and Schier, 2011; Wolpert, 1969). In plants, graded distribution of the hormone auxin is not only essential for embryogenesis, but also for post-embryonic development, where it regulates the reiterative organogenesis characteristic of plants( Dubrovsky et al., 2008; Vanneste and Friml, 2009; Benková et al., 2003). Plant shoots develop post-embryonically through rhythmic organ generation in the shoot apical meristem( SAM), a specialized tissue with a stem cell niche in its central zone( CZ; Figure 1A). In Arabidopsis thaliana, as in a majority of plants, organs are initiated sequentially in the SAM peripheral zone( PZ surrounding the CZ) at consecutive relative angles of close to 137°, either in a clockwise or anti-clockwise spiral( Figure 1A; Galvan-Ampudia et al., 2016). SAM organ patterning or phyllotaxis has been extensively analyzed using mathematical models( Douady and Couder, 1996; Mitchison, 1977; Veen and Lindenmayer, 1977). A widely accepted model proposes that the time interval between organ initiations( the plastochron) and the spatial position of organ initiation emerge from the combined action of inhibitory fields emitted by pre-existing organs and the SAM center( Douady and Couder, 1996). Tissue growth then self-organizes organ patterning by moving organs away from the stem cells and leaving space for new ones. Auxin is the main signal for positional information in phyllotactic patterning( Reinhardt et al., 2003a; Reinhardt et al., 2000). Auxin, has been proposed to be transported directionally toward incipient primordia where it activates a transcriptional response leading to organ specification( Benková et al., 2003; Reinhardt et al., 2003a; Heisler et al., 2005; Vernoux et al., 2000). PIN-FORMED1( PIN1) belongs to a family of auxin efflux carriers whose polarity determines the direction of auxin fluxes( Benková et al., 2003; Gälweiler et al., 1998). PIN1 proteins are present throughout the SAM and regulate the spatio-temporal distribution of auxin cooperatively with other carriers( Reinhardt et al., 2003a; Bainbridge et al., 2008). Convergence of PIN1 carriers toward sites of organ initiation was proposed to control an accumulation of auxin that triggers organ initiation. This spatial organization of PIN1 polarities was also proposed to deplete auxin around organs, locally blocking initiation and thus establishing auxin-based inhibitory fields( Reinhardt et al., 2003a; Heisler et al., 2005; Vernoux et al., 2011; de Reuille et al., 2006; Stoma et al., 2008; Jonsson et al., 2006; Smith et al., 2006a). In addition, a reduced responsivity of the CZ to auxin has been demonstrated, providing an auxin-dependent mechanism for the inhibition of organogenesis in the CZ( Vernoux et al., 2011; de Reuille et al., 2006). Several models converge to suggest that together, these auxin-dependent regional cues determine new organ locations in the growing SAM. The genetically-encoded biosensor DII-VENUS, a synthetic protein degraded directly upon sensing of auxin, recently allowed an unprecedented qualitative visualization of spatial auxin gradients in the SAM( Vernoux et al., 2011; Brunoud et al., 2012). However, quantification of the spatio-temporal dynamics of auxin is required to fully evaluate both experimental and theoretical understanding of the action of auxin in SAM patterning. This is all the more important given that the continuous helicoidal reorganization of auxin distribution in the growing SAM, suggests that auxin might convey complex positional information. Here, we used a quantitative imaging approach to question the nature of the auxin-dependent positional information. We further investigate how efflux and biosynthesis regulate the 4D dynamics of auxin, and explore how this information is processed in the SAM to generate rhythmic patterning.\nDiscussion:\nIn a recent modeling study, a stochastic induction of organ initiation based on temporal integration of morphogenetic information was proposed( Refahi et al., 2016). Here we provide evidence that organ initiation in the SAM is indeed dependent on temporal integration of the auxin signal. Our quantitative analysis of the dynamics of auxin distribution and response supports a scenario in which rhythmic organ initiation at the SAM is driven by the combination of high-precision spatio-temporal graded distributions of auxin with the use of the duration of cell exposure to auxin, to temporally differentiate sites of organ initiation( Figure 6). Importantly our results suggest that a time integration mechanism is essential for rhythmic organ patterning in the SAM since auxin-based spatial information pre-specifies several sites of organ initiation and is thus unlikely to provide sufficient information( Video 1). Whether temporal integration of auxin information exists in other tissues remains to be established. We provide evidence that temporal integration of the auxin signal likely requires the effectors of the auxin signaling pathway. Activation of transcription downstream of auxin by ARFs relies on chromatin remodeling, increasing the accessibility of ARF targets and possibly allowing for the recruitment of histone acetyltransferases( Wu et al., 2015), together with the release of histone deacetylases( HDACs) from target loci through degradation of Aux/IAA repressors( Long et al., 2006). Chromatin state change is one mechanism that allows the temporal integration of signals in eukaryotes, including plants( Angel et al., 2011; Coda et al., 2017; Nahmad and Lander, 2011; Sun et al., 2009). It is thus plausible that time integration of the auxin signal in cells leaving the CZ is set by progressive acetylation of histones triggered by ARFs at their target loci. As chromatin deacetylation also represses auxin signaling in the CZ( Ma et al., 2019), balancing the acetylation status of ARF target loci could provide a mechanism to tightly link stem cell maintenance to differentiation by precisely positioning organ initiation at the boundary of the stem cell niche, while at the same time allowing sequential organ initiation. Temporal integration might as well rely on mechanisms that fine-tune the intracellular distribution of auxin, such as auxin metabolism but also intracellular transport( Sauer and Kleine-Vehn, 2019). Determining how different mechanisms might act in parallel to provide a capacity to activate target genes as a function of auxin concentrations over time will require further analyses. It will notably be important to determine whether other ARF than ARF3 act in the temporal integration of auxin. The existence of high definition spatio-temporal auxin gradients suggests that as for several morphogens in animals( Nahmad and Lander, 2011; Dessaud et al., 2007; Scherz et al., 2007; Maden, 2002) the robustness of SAM patterning results from highly reproducible spatio-temporal positional information. Our results indicate that auxin maxima could first emerge from the CZ at the confluence of centripetal auxin fluxes. Confluences creating auxin maxima would at the same time divert fluxes away from areas where auxin minima appear( Figure 3M). Our analysis raises the question of how auxin transport could generate this high definition signal distribution and whether the different models that have been proposed can explain this distribution( Bainbridge et al., 2008; Stoma et al., 2008; Jonsson et al., 2006; Smith et al., 2006a; van Berkel et al., 2013). Further analysis of the spatio-temporal control of auxin distribution needs also to consider that early developing flowers act as auxin production centers. These flowers could not only provide a memory of the developmental pattern through lateral inhibition but also contribute positively to a self-sustained auxin distribution pattern by providing auxin to the system( Figure 3M). Finally, our work indicates that the stem cell niche could act as a system-wide organizer of auxin transport, consistent with previous work( de Reuille et al., 2006). This could provide another layer of regulation tightly coordinating differentiation with the presence of a largely auxin-insensitive stem cell niche( Vernoux et al., 2011; Ma et al., 2019).", "role": "user" }, { "content": "Plants , like animals and many other multicellular organisms , control their body architecture by creating organized patterns of cells . These patterns are generally defined by signal molecules whose levels differ across the tissue and change over time . This tells the cells where they are located in the tissue and therefore helps them know what tasks to perform . A plant hormone called auxin is one such signal molecule and it controls when and where plants produce new leaves and flowers . Over time , this process gives rise to the dashing arrangements of spiraling organs exhibited by many plant species . The leaves and flowers form from a relatively small group of cells at the tip of a growing stem known as the shoot apical meristem . Auxin accumulates at precise locations within the shoot apical meristem before cells activate the genes required to make a new leaf or flower . However , the precise role of auxin in forming these new organs remained unclear because the tools to observe the process in enough detail were lacking . Galvan-Ampudia , Cerutti et al . have now developed new microscopy and computational approaches to observe auxin in a small plant known as Arabidopsis thaliana . This showed that dozens of shoot apical meristems exhibited very similar patterns of auxin . Images taken over a period of several hours showed that the locations where auxin accumulated were not fixed on a group of cells but instead shifted away from the center of the shoot apical meristems faster than the tissue grew . This suggested the cells experience rapidly changing levels of auxin . Further experiments revealed that the cells needed to be exposed to a high level of auxin over time to activate genes required to form an organ . This mechanism sheds a new light on how auxin regulates when and where plants make new leaves and flowers . The tools developed by Galvan-Ampudia , Cerutti et al . could be used to study the role of auxin in other plant tissues , and to investigate how plants regulate the response to other plant hormones .", "role": "assistant" } ]

[ { "content": "You will be shown the title of a chemistry paper, together with sections excerpted from the body of the paper. The paper sections may include HTML tags like `<p>` and `</p>`; please ignore these. Your task is to write an abstract for the paper. Your response should include the abstract and no other text.\n\nTitle:\nRapid and Efficient Generation of Stable Antibody–Drug Conjugates via an Encoded Cyclopropene and an Inverse‐Electron‐Demand Diels–Alder Reaction\n\nPaper sections:\n\n<p>B. Oller-Salvia, G. Kym, J. W. Chin, Angew. Chem. Int. Ed.\n2018, 57, 2831.</p><p>Enhancing the selective delivery of drugs to the desired tissues is a prime goal in the development of therapeutics. Antibody–drug conjugates (ADCs) seek to address this need by directing potent cytotoxins to specific cell types, thus minimizing the off‐target effects of traditional chemotherapy. Site‐specific conjugation of drugs to antibodies can improve the therapeutic index with respect to first‐generation heterogeneous ADCs.1 Therefore, several strategies have been reported for the selective chemical and enzymatic attachment of drugs to antibodies.1, 2 However, the positions on the antibody that can be targeted, the stability of the linkage, and/or the extent of drug conjugation are limited.</p><p>Genetic‐code expansion enables the site‐specific incorporation of non‐canonical amino acids (ncAA) into proteins in response to a target codon, commonly the amber stop codon, introduced into a gene of interest.3 Orthogonal aminoacyl‐tRNA synthetase/tRNA pairs that enable the incorporation of diverse ncAAs have been discovered,4 and the site‐specific incorporation of ncAAs bearing bioorthogonal reactive groups provides an attractive, and potentially general, strategy for generating ADCs.5 However, the ncAAs that have been incorporated into antibodies so far, which contain ketones or azides, are not optimal for bioconjugation. Ketones6 can react with endogenous amines, require low pH (4.5) and long reaction times (60 h); azides7 are prone to reduction8 and the copper species used to catalyze cycloadditions with alkynes may induce oxidative damage.9 Although alternative highly reactive ncAAs based on large, hydrophobic, carbocyclic handles have recently been encoded in an antibody,10 the expression system used suffers from very low yields (0.5 mg L−1) and these ncAAs may modify the physicochemical properties of the protein.</p><p>Here, we describe antibody‐expression systems that utilize the pyrrolysyl‐tRNA synthetase (encoded by PylS)/tRNACUA (encoded by PylT) pair to direct the incorporation of a cyclopropene derivative of lysine (CypK, Figure 1 b)11 in response to amber codons introduced into antibody genes. We apply these systems to the production of the FDA‐approved trastuzumab antibody, which targets the breast‐cancer marker HER2. We express trastuzumab with CypK at similar levels to the wild‐type antibody. CypK contains a 1,3‐disubstituted cyclopropene, which provides a minimal bioorthogonal handle that undergoes a rapid and selective inverse‐electron‐demand Diels–Alder cycloaddition with tetrazine derivatives to yield dihydropyridazines.12 We show that trastuzumab(CypK)2 can be covalently linked to monomethyl auristatin E (MMAE), the microtubule polymerization inhibitor used in Adcetris, an FDA‐approved ADC. We show that the resulting dihydropyridazine linkage is stable in serum and we demonstrate the selectivity and potency of trastuzumab(MMAE)2.</p><p>Antibody‐expression systems developed in this study. a) Relevant region of the two plasmids transfected into HEK cells for transient expression and the three components for the stable expression in CHO cells b) N\nϵ‐[((2‐methylcycloprop‐2‐en‐1‐yl)methoxy)carbonyl]‐l‐lysine (CypK) c) Expression yields in the two expression systems. Error bars represent the standard deviation from three biological replicates. d) Western blot shows that the expression of the antibody heavy chain is dependent on the addition of CypK.</p><p>To rapidly characterize antibody variants and test the conjugation conditions, we developed a transient expression system, consisting of two plasmids, one encoding trastuzumab heavy chain (HC) and the other encoding the light chain (LC) (Figure 1 a and Figure S1 in the Supporting Information). Previous approaches have relied on a separate plasmid for co‐expression of the expanded‐genetic‐code machinery, PylS/PylT.13 Here we achieve higher antibody yields by transferring PylT and PylS onto the same constructs as the HC and LC genes and reducing the number of plasmids (Figure S2).</p><p>The first position of the CH1 domain on the heavy chain was chosen to encode the ncAA (HC‐118TAG). HC‐118 is permissive for mutation and conjugation14 and because it is conserved in all IgG1s the expression system is applicable to most therapeutic monoclonal antibodies. Transfection of the transient plasmid system in Expi293 cells yielded 22±2 mg L−1 of trastuzumab(CypK)2, which approaches the wild‐type antibody level (33±3 mg L−1) (Figure 1 c). We also verified that the expression of HC‐118TAG trastuzumab is ncAA‐dependent (Figure 1 d).</p><p>Although the focus of this study was on the incorporation of two drugs per antibody, we also showed the flexibility of the expression system by adapting it to the production of trastuzumab(CypK)4. Incorporation of the amber codon at position 107 in the light chain (LC‐107TAG) in addition to HC‐118TAG resulted in trastuzumab with four CypK conjugation sites, one on each HC and LC (Figure S3). This antibody variant is expressed at 10–20 mg L−1.</p><p>In order to create a robust platform for the expression of antibodies containing ncAAs, we generated a CHO‐S stable cell line in two steps (Figure S4). First, we inserted the genetic‐code‐expansion machinery into the CHO genome by using a piggyback transposase.15 Second, we integrated the heavy and light chain genes and selected for high expression of the antibody. After optimizing the CypK concentration in this system (Figure S5), we achieved an antibody expression yield of 31±2 mg L−1, 75–80 % with respect to the wild‐type line (Figure 1 c). Prior work suggests that absolute yields can be substantially increased in optimized industrial formats.16</p><p>No aggregation products were detected by size‐exclusion chromatography after the antibody was concentrated, with protein A resin, from the supernatant. This observation is in line with the bioorthogonality and low hydrophobicity of CypK. Subsequent purification with hydrophobic‐interaction chromatography (HIC) proved sufficient to isolate the pure full‐length antibody. We confirmed incorporation of CypK at position 118 by mass spectrometry (Figure 2 d, and Figures S6 and S7).</p><p>Tetrazine‐vcMMAE conjugation to trastuzumab(CypK)2. a) Scheme of the inverse‐electron‐demand Diels–Alder reaction of tetrazine‐vcMMAE with a CypK residue. b) HIC chromatograms showing the evolution of each DAR species with time during the conjugation using five molar equivalents of tetrazine‐vcMMAE per CypK. c) Conversion with respect to maximum DAR (1.9) as measured by HIC‐HPLC. d,e) Deconvoluted mass spectra of deglycosylated trastuzumab(CypK)2 and trastuzumab(MMAE)2, respectively.</p><p>To generate the ADC trastuzumab(MMAE)2, we conjugated trastuzumab(CypK)2 with a tetrazine‐modified MMAE (tetrazine‐vcMMAE) (Figure 2 a). We included a valine–citrulline protease‐labile component in the linker between the benzyl tetrazine handle and MMAE; upon internalization of the ADC, the dipeptidyl linker is cleaved by cathepsin B in the lysosome to release the toxin.17</p><p>The cycloaddition reaction between trastuzumab(CypK)2 and tetrazine‐vcMMAE was completed within 3 h at 25 °C in phosphate‐buffered saline (PBS; pH 7.4) when five or more equivalents of the toxin per CypK were added (Figure 2 b and c). Due to the high hydrophobicity of the toxin, addition of 10 % acetonitrile is required. This result confirms that CypK allows a substantially faster conjugation than most reported bioorthogonal handles for ADCs. Alternatively, conjugation without acetonitrile and with just two equivalents of peptide per CypK resulted in a completely modified product in 20 h; the low stoichiometry could lead to substantial cost savings during ADC manufacturing in comparison with most existing ncAA‐based technologies. In all cases, a drug‐to‐antibody ratio (DAR) of >1.9 was achieved as measured by LC‐MS and HPLC‐HIC. The identity of the conjugate was verified by LC‐MS (Figure 2 e and Figure S8). Trastuzumab(CypK)2 stored for more than four months in PBS at 4 °C maintains its reactivity.</p><p>We also conjugated tetrazine‐TAMRA under the same conditions as tetrazine‐vcMMAE, reaching a DAR >1.9 (as measured by LC‐MS) within only 2 h (Figures S9 and S10). Additionally, we showed that the affinity of the antibodies for their antigen is preserved after the conjugation (Figure S11).</p><p>The stability of the linker in ADCs is critical because the premature release of the drug results in higher toxicity and lower efficacy.1,7c We assessed the integrity of the dihydropyridazine linkage in trastuzumab(TAMRA)2 in serum and plasma; since the stability of this linkage can be easily followed by fluorescence and an enzyme‐linked immunosorbent assay (ELISA), and the measurements are not complicated by the protease‐labile component of trastuzumab(MMAE)2. The payload remained attached to the immunoconjugate for greater than five days at 37 °C in human serum and plasma (Figure 3 b and Figure S12).</p><p>Stability and cytotoxicity of trastuzumab conjugates. a) Schematic of desired properties for internalizing ADCs. b) Stability in human plasma and serum as measured by ELISA. Error bars represent the standard deviation of biological triplicates. c,d) Cell‐viability assay. Data show the mean of three independent experiments and error bars represent the standard deviations.</p><p>Finally, to demonstrate the selectivity of trastuzumab(MMAE)2, we compared the potency of the ADC in breast‐cancer cell lines expressing high and low levels of HER2. As expected, trastuzuamb(MMAE)2 had dramatically increased cytotoxicity with respect to tetrazine‐vcMMAE and the unconjugated antibody in SK‐BR‐3 cells(HER2 high; Figure 3 c and Table S1). The half‐maximal effective concentration (EC50) for the MMAE ADC is 55±10 pm, which is consistent with the activity of immunoconjugates obtained using alternative conjugation methods.18 By contrast, the EC50 of trastuzumab(MMAE)2 in MCF‐7 cells, which express 15‐fold fewer HER2 receptors than SK‐BR‐3 cells,19 is at least 200 times higher (Figure 3 d and Table S1). These results demonstrate the high selectivity of the ADC for the target cells. We then showed that tetrazine‐vcMMAE and the same toxin without the linker have similar toxicity in the HER2‐high SK‐BR‐3 and the HER2‐low MCF‐7 cell lines (Figure 3 c,d and Figure S13), demonstrating that the antibody is responsible for the aforementioned selectivity. When trastuzuamb(MMAE)2 was incubated in human serum for five days prior to its use in the viability assay it retained full toxicity and selectivity, consistent with the conjugate being stable in serum (Figure S14).</p><p>In conclusion, we have engineered two mammalian‐expression systems to efficiently and site‐specifically incorporate CypK in trastuzumab. The modified IgG1 can be easily purified and rapidly conjugated with tetrazine‐containing molecules, yielding dihydropyridazine‐linked products that are stable in serum. Finally, we have demonstrated that linking trastuzumab to MMAE by using genetically encoded CypK and bioorthgonal ligation generates a potent and selective ADC. The minimal bioorthogonal handle in CypK may enable facile and rapid conjugation of diverse therapeutic antibodies with sterically hindered third‐generation ADC payloads. The genetic encoding of CypK coupled to its rapid and quantitative conjugation to generate a stable linkage may also prove useful for other protein conjugates intended for therapy and diagnosis.</p>\n\nConflict of interest\n<p>The authors declare no conflict of interest.</p>\n\n\n<p>As a service to our authors and readers, this journal provides supporting information supplied by the authors. Such materials are peer reviewed and may be re‐organized for online delivery, but are not copy‐edited or typeset. Technical support issues arising from supporting information (other than missing files) should be addressed to the authors.</p><p>Supplementary</p><p>Click here for additional data file.</p>", "role": "user" }, { "content": "AbstractHomogeneous antibody–drug conjugates (ADCs), generated by site‐specific toxin linkage, show improved therapeutic indices with respect to traditional ADCs. However, current methods to produce site‐specific conjugates suffer from low protein expression, slow reaction kinetics, and low yields, or are limited to particular conjugation sites. Here we describe high yielding expression systems that efficiently incorporate a cyclopropene derivative of lysine (CypK) into antibodies through genetic‐code expansion. We express trastuzumab bearing CypK and conjugate tetrazine derivatives to the antibody. We show that the dihydropyridazine linkage resulting from the conjugation reaction is stable in serum, and generate an ADC bearing monomethyl auristatin E that selectively kills cells expressing a high level of HER2. Our results demonstrate that CypK is a minimal bioorthogonal handle for the rapid production of stable therapeutic protein conjugates.", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nPCOS or polycystic ovary on ultrasound scan.\nModerate or severe endometriosis.\nHydrosalpinx.\nUterine abnormalities or myoma.\nPrevious uterine surgery.", "role": "user" }, { "content": "{\"Condition\": [\"PCOS\", \"endometriosis\", \"myoma\", \"polycystic ovary\", \"Hydrosalpinx\", \"Uterine abnormalities\"], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [\"ultrasound scan\", \"uterine surgery\"], \"Qualifier\": [\"Moderate\", \"severe\"], \"ReferencePoint\": [], \"Scope\": [\"Moderate or severe\", \"PCOS or polycystic ovary\"], \"Temporal\": [\"Previous\"], \"Value\": [], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "You will be shown the title of a chemistry paper, together with sections excerpted from the body of the paper. The paper sections may include HTML tags like `<p>` and `</p>`; please ignore these. Your task is to write an abstract for the paper. Your response should include the abstract and no other text.\n\nTitle:\nFluorescent Mimics of Cholesterol that Rapidly Bind Surfaces of Living Mammalian Cells\n\nPaper sections:\n\n<p>Cholesterol (1) is a critical constituent of membranes of mammalian cells. Cells acquire exogenous forms of this sterol through multiple mechanisms involving structurally distinct cell surface receptors. Lipoprotein particles such as low-density lipoprotein (LDL) and high-density lipoprotein (HDL) carry cholesteryl esters (2) and associated protein and lipid components throughout the bloodstream.1 Cells expressing LDL and HDL receptors actively internalize these natural nanoparticles via receptor-mediated endocytosis. In contrast, Niemann-Pick C1 Like 1 protein (NPC1L1) plays key roles in the cellular uptake of dietary (unesterified) cholesterol (1), as found in mixed micelles.2 This receptor was identified in 20043 as a target of ezetimibe (3), a drug used to treat hypercholesterolemia. More recent studies suggest that although NPC1L1 is a primary target of ezetimibe and its active glucuronide metabolite,4-6 other proteins, such as the HDL receptor SR-BI, can also be inhibited by this drug.7 Recent proteomics experiments have identified over 250 cholesterol-binding proteins, including receptors, channels, and enzymes.8</p><p>Derivatives of cholesterol have numerous biological applications. These compounds have been used to facilitate the delivery of small inhibitory RNA (siRNA),9 enhance DNA transfection,10 probe cellular membrane subdomains,11 and assay cholesterol transport processes.12-17 Cholesteryl carbamates have been extensively investigated, and cellular uptake of cholesteryl carbamate-conjugated siRNA has been reported to be similar to uptake of cholesteryl esters, requiring binding to HDL or LDL,9 followed by internalization via HDL or LDL receptors. This initial lipoprotein-binding step can slow cellular uptake, and the presence of high concentrations of serum (e.g. 10%) in media typically reduces the activity of these compounds, likely because of competition between serum lipoproteins and cognate cell surface receptors.</p><p>In an effort to mimic the molecular recognition properties of free cholesterol (1), we hypothesized that the protonated secondary amino group of N-alkyl-3β-cholesterylamines,18, 19 as found in compounds 4-7, might function as a bioisostere for the 3β-hydroxyl group of cholesterol. Thus, in contrast to cholesteryl esters, cholesteryl carbamates, and structurally related compounds, which may require lipoprotein-mediated cellular uptake, these compounds might bind to receptors on cell surfaces that recognize free cholesterol or structurally similar metabolites through alternative mechanisms. We further hypothesized that the addition of anionic amino acids might affect binding to serum proteins and increase the affinity of these compounds for cells.</p><p>To investigate how structural features affect recognition of cholesterol derivatives and related compounds by proteins on the surface of cells, we synthesized the fluorescent molecular probes 4-13. For probes derived from 3β-cholesterylamine, this steroid building block,20 and some cholesterylamine-derived intermediates,21 were prepared as previously reported. The novel building block 3β-sitosterylamine was prepared from sitosterol using methodology described for the synthesis of 3β-cholesterylamine.20 The 4-carboxy Pennsylvania Green fluorophore was prepared as previously described.22 Full synthetic details are provided in Scheme S1 and Scheme S2 of the supporting information. These probes were designed to systematically compare membrane anchors derived from N-alkyl-3β-cholesterylamines (4-7), a sitosteryl analogue (8), a N-acyl-3β-cholesterylamine (10), or cholesterol (9, 11–13) linked to the hydrophobic Pennsylvania Green23, 24 (PG) fluorophore through amino acid subunits. We hypothesized that the carbonyl linked to the steroid in amide 10, ester 11 or carbamates 12 and 13 would be similar to natural cholesteryl esters, and this structural modification might correspondingly affect their ability to bind cell surfaces.</p><p>As shown in Figure 1, confocal laser scanning microscopy was employed to compare living human Jurkat lymphocyte cells after treatment with 4–13. These experiments demonstrated that a brief (5 minute) treatment of cells with 4 or 5 (2 μM) at 37 °C results in robust fluorescent staining of cellular plasma membranes. Examination of these cells after 1 hour showed enhanced cellular binding, uptake of the probe, and localization in transferrin-positive early/recycling endosomes (Figure 1 and Figure S1 of the supporting information). Binding of 4 (and 5) to cell surfaces was predominantly receptor-mediated as evidenced by up to 80% inhibition upon coaddition with excess (200 μM) ezetimibe (3, Compare Figure 1A and 1C, and see Figure S3 of the supporting information). This inhibition indicates that proteins on cell surfaces may recognize these compounds as mimics of free cholesterol or related cholesterol metabolites. These metabolites might include structurally related cholesterol sulfate25 and cholesterol glucuronide,26 which are present in micromolar concentrations in the bloodstream of animals. Comparison of 4 with 6 lacking the glutamic acid residue in the linker region revealed that the anionic moiety of 4 is critical for rapid high affinity/efficacy binding to cells (Figure 1, compare panels B and G). Moreover, despite the presence of a structurally analogous glutamic acid, the cholesteryl carbamate 12 showed low cellular binding and cellular uptake compared with 4, supporting the hypothesis that carbamates engage a mechanistically distinct cellular uptake pathway. However, this loss of activity of 12 could be at least partially rescued by addition of a second glutamic acid, as found in 13.</p><p>Using ezetimibe (3, 200 μM, 0.2% DMSO) as a specific competitor, we quantified the relative affinities (Kd, app) and efficacies (Bmax) of rapid binding of 4-13 to Jurkat lymphocytes in media containing 10% serum. Data from saturation binding experiments after treatment for five minutes, designed to limit cellular uptake by endocytosis, are shown in Figure 2, Table 1, and the supporting information. The high affinity and efficacy of binding of 4 and 5 to cell surfaces compared to 6-12 revealed that N-alkyl cholesterylamines bearing an anionic functional group and a spacer residue such as β-alanine most efficiently bind cell surfaces, a critical initial step for initiation of endocytosis and delivery of linked agents. The absence of substantial cellular binding of the sitosterolamine analogue (8), differing from 4 by the presence of an additional ethyl group in the tail of the sterol, further supports a specific receptor-mediated uptake mechanism. This result is consistent with limited receptor-mediated27, 28 uptake of phytosterols such as sitosterol by mammalian cells.</p><p>To investigate whether other cell types show differential effects, we examined rapid (5 min) binding of 4, 5, 8, and 13 to three different human cell lines. Human Jurkat cells, grown in suspension were compared with the human cell lines HeLa and HEK-293, which were suspended in media prior to treatment. As shown in Figure 3, HeLa cells bound the fluorescent cholesterol mimics to the greatest extent. Comparison of HeLa with Jurkat and HEK-293 cells revealed 3.3-fold to 8.1-fold more specific binding to HeLa cell surfaces compared to the other cell lines. These results might be explained by higher expression by HeLa cells of a specific receptor that interacts with these compounds.</p><p>For these assays, cellular fluorescence was converted to molecules of equivalent fluorescein (MEFL) using fluorescent bead standards. For the Jurkat cell line, this analysis indicated that treatment with 4 or 5 at a concentration of 2 μM for 5 minutes loads 0.5–1.5 × 106 molecules into the plasma membrane of individual cells. This rapid and massive increase in cellular fluorescence suggested that an enzyme may be actively inserting these compounds into the cellular plasma membrane. Further analysis of time-dependent fluorescence resulting from treatment with 4, 5, 8, and 13 using the Mechaelis-Menten model of enzyme kinetics is shown in Figure 4. These studies revealed that the cellular uptake of 4, 5, and to a lesser extent 13, is highly efficient, with 1.8–5.0 × 105 molecules incorporated per minute per cell, consistent with a catalytic process. Kinetic values of KM and Vmax from this analysis are shown in Table 1.</p><p>In conclusion, we identified novel structure-activity relationships that govern binding of fluorescent cholesterol mimics to the surface of living mammalian cells. New cholesterol-mimetic membrane anchor motifs of 4, 5, and 13 were identified that engage a rapid cellular uptake pathway, consistent with a receptor-mediated process, that catalytically inserts these compounds into the plasma membrane. Although the receptor or enzyme targeted by these compounds has not yet been identified, it is unlikely to be NPC1L1, the classical pharmacological target of ezetimibe, because this protein is not highly expressed outside of the liver and intestine,29 and the active metabolite ezetimibe-glucuronide, prepared as previously reported,30 does not inhibit binding of 4 to Jurkat cell surfaces (data shown in Figure S2 of the supporting information). Given that cholesterol trafficking and distribution involves dynamic receptor-mediated and vesicular processes that are not completely understood,31 these compounds have potential as novel probes and tools for the delivery of impermeable molecules into mammalian cells.</p>", "role": "user" }, { "content": "Mammalian cells acquire cholesterol, a critical membrane constituent, through multiple mechanisms. We synthesized mimics of cholesterol, fluorescent N-alkyl-3\\xce\\xb2-cholesterylamine-glutamic acids, that are rapidly incorporated into cellular plasma membranes compared with analogous cholesteryl amides, ethers, esters, carbamates, and a sitosterol analogue. This process was inhibited by ezetimibe, indicating a receptor-mediated uptake pathway.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nPlease return the output as a JSON object of the format: {\"Participant\": [\"patients with COPD\", ...], \"Intervention\": [\"Atenolol\", ...], \"Outcome\": [\"blood pressure\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nVideotaped training in alcohol counseling for obstetric care practitioners : a randomized controlled trial . OBJECTIVE To determine the feasibility of videotaped training for obstetric care practitioners in motivational interviewing skills that could be used in brief patient consultations on problem drinking . METHODS Thirty health care practitioners participated in a clinical trial using a 20-minute videotape to instruct them in motivational interviewing . Participants engaged in a pretest roleplay with an actress playing a drinking pregnant woman . Those randomly assigned to the experimental condition watched the motivational interviewing videotape . Control condition participants watched a 20-minute docudrama of a pregnant problem drinker . Both groups then engaged in a post-test roleplay similar to the pretest . Behavioral ratings of the roleplays and participant evaluations of the motivational interviewing video constituted the outcome measures . RESULTS Participant evaluations indicated that the training video was clear in explaining and demonstrating the principles and skills of motivational interviewing . Change in behavioral ratings from pretest to post-test showed significant differences in motivational interviewing skills between the experimental and control groups . Obstetric care practitioners who viewed the training video were rated as showing greater empathy , minimizing patient defensiveness , and supporting women 's beliefs in their ability to change . CONCLUSION Obstetric care practitioners can improve their alcohol intervention skills through the use of a 20-minute videotaped instruction in motivational interviewing . Clinicians who improve their skills in motivational interviewing can intervene more effectively with their drinking pregnant patients . Using motivational interviewing with this population holds promise for helping prevent alcohol-related health problems .", "role": "user" }, { "content": "{\"Intervention\": [\"Videotaped training in alcohol counseling\", \"videotaped training for obstetric care practitioners in motivational interviewing skills\", \"20-minute docudrama\", \"training video\", \"Control\", \"motivational interviewing videotape\", \"20-minute videotape\", \"videotaped instruction in motivational interviewing .\", \"motivational interviewing\"], \"Outcome\": [\"Behavioral ratings of the roleplays\", \"empathy\", \"supporting women \\u0027s beliefs in their ability to change\", \"patient defensiveness\", \"participant evaluations of the motivational interviewing video\"], \"Participant\": [\"obstetric care practitioners\", \"obstetric care practitioners :\"]}", "role": "assistant" } ]

[ { "content": "You are presented with multiple paper abstracts, a literature review title, and a specific chapter title. Your task is to write a focused literature review chapter that aligns with the given chapter title. The review should synthesize the content from the provided abstracts, draw connections between different works, highlight major findings, and identify any gaps in the existing research.\nLiterature Review Title: Survey on Prediction Algorithms in Smart Homes \nChapter Title: Survey on Prediction Algorithms in Smart Homes \n1. Abstract of Cited Paper (BIB001): The goal of the MavHome (Managing An Intelligent Versatile Home) project is to create a home that acts as an intelligent agent. In this paper we introduce the MavHome architecture. The role of prediction algorithms within the architecture is discussed, and a meta-predictor is presented which combines the strengths of multiple approaches to inhabitant action prediction. We demonstrate the effectiveness of these algorithms on smart home data. \n2. Abstract of Cited Paper (BIB002): In this work, a system for recognizing activities in the home setting using a set of small and simple state-change sensors is introduced. The sensors are designed to be “tape on and forget” devices that can be quickly and ubiquitously installed in home environments. The proposed sensing system presents an alternative to sensors that are sometimes perceived as invasive, such as cameras and microphones. Unlike prior work, the system has been deployed in multiple residential environments with non-researcher occupants. Preliminary results on a small dataset show that it is possible to recognize activities of interest to medical professionals such as toileting, bathing, and grooming with detection accuracies ranging from 25% to 89% depending on the evaluation criteria used. \n3. Abstract of Cited Paper (BIB003): A smart home is an application of ubiquitous computing in which the home environment is monitored by ambient intelligence to provide context-aware services and facilitate remote home control. This paper presents an overview of previous smart home research as well as the associated technologies. A brief discussion on the building blocks of smart homes and their interrelationships is presented. It describes collective information about sensors, multimedia devices, communication protocols, and systems, which are widely used in smart home implementation. Special algorithms from different fields and their significance are explained according to their scope of use in smart homes. This paper also presents a concrete guideline for future researchers to follow in developing a practical and sustainable smart home. \n4. Abstract of Cited Paper (BIB004): Recently, bio-signal based control has been gradually deployed in biomedical devices and assistive robots for improving the quality of life of disabled and elderly people, among which electromyography (EMG) and electroencephalography (EEG) bio-signals are being used widely. This paper reviews the deployment of these bio-signals in the state of art of control systems. The main aim of this paper is to describe the techniques used for (i) collecting EMG and EEG signals and diving these signals into segments (data acquisition and data segmentation stage), (ii) dividing the important data and removing redundant data from the EMG and EEG segments (feature extraction stage), and (iii) identifying categories from the relevant data obtained in the previous stage (classification stage). Furthermore, this paper presents a summary of applications controlled through these two bio-signals and some research challenges in the creation of these control systems. Finally, a brief conclusion is summarized.\n\nLiterature Review:", "role": "user" }, { "content": "is an intelligent control, or an interface that allows for management of the system. The final component is home automation, where any product contained in the home is connected in some way to a service or system from an outside source BIB004 . In this type of smart home, the main point of emphasis is the use of remote access to activate or control a part of the smart home. However, what about having a smart home that can act on its own? This is the direction that researchers have been leaning toward, so there must be some way to allow the smart home to think for itself in order to complete certain tasks. When smart homes were first introduced, the idea was to have a system in place for a resident to interact with the system through an interface to change some aspect according to their own preference. Though this is still a key component for a smart home, progress continues to be made to make the system more automated. This has led to researchers trying to implement an artificial intelligence into the environment to make decisions based on previously gathered information or prior inputs from the resident . With artificial intelligence in play, this should allow a smart home to act on its own. This all seems ideal, but there still needs to be a way for the smart home to make suitable decisions. To do so, prediction algorithms have been introduced in many smart home systems to analyze information and make a choice that is appropriate for situation at hand. One example of a smart home that has been developed to act more or less independently is the managing an adaptive versatile home (MavHome) BIB002 , BIB001 . The researchers at the University of Texas at Arlington created this smart home project to have the home act as a \"rational agent,\" meaning that the MavHome wants to make the resident as comfortable as possible while operating at maximally efficiency. The MavHome architecture is similar to many other smart homes in that it employs four layers: decision, information, communication, and physical layers. The decision layer uses knowledge given to it from the information layer to select what action needs to take place. The information layer gathers and stores all data pertinent to any decision making process. The communication layer enables the flow of information or request between any two parts of the system. Lastly, the physical layer is all the hardware that is included within the smart home environment. MavHome uses this structure, along with prediction algorithms, to enable the smart home to be a more automated space. Some other work on this interest can be found in BIB003 - BIB005 . This paper is a survey on several different prediction algorithms that have been or are being used at smart homes. It will discuss the different areas within the home environment that use prediction algorithms. It will also compare the merits and flaws of the algorithms presented and possible adaptations to enhance the overall quality of the prediction algorithms used in smart homes. This paper is organized as follows. We first introduce the background of prediction algorithms, including system models and data in Section II. Then, Section III extensively reviews the literature prediction algorithms, compares them upon their features and models. Next, Section IV discusses the enhancements and variants of the prediction algorithms. Finally, this paper is concluded by Section V.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"AnatomicalEntity\"].\n\nPlease return the output as a JSON object of the format: {\"AnatomicalEntity\": [\"tumor cells\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be an empty JSON array \"[]\".\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nAtypical mycobacteriosis of the larynx: an unusual clinical presentation secondary to steroids inhalation.\nVocal cords stiffness can be associated with a variety of etiologic agents, but it is rarely seen with atypical mycobacteria, for example, Mycobacterium avium complex. We report a case of a 35-year-old white woman who is and was maintained on inhaled steroids. She presented with hoarseness and low-grade fever, but her medical history was otherwise unremarkable. Laryngoscopy revealed bilateral scarring of the vocal cords. Vocal cord biopsies were performed. Histologic examination revealed unremarkable laryngeal mucosa, except for abundant subepithelial non-necrotizing granulomata. The differential diagnosis included sarcoid, Klebsiella scleroma, and tuberculosis. Special stains reviewed abundant acid-fast bacilli, later confirmed by a DNA assay on induced deep sputum, consistent with M avium complex. Subsequently, steroids were withdrawn, and the patient was treated with a multiple-drug antituberculous regimen and had a full recovery. This unusual clinical presentation of the atypical mycobacteriosis may be encountered by otolaryngologists and pathologists, and it is critical to recognize it in patients immunocompromised because of steroids.", "role": "user" }, { "content": "{\"AnatomicalEntity\": [\"larynx\", \"Vocal cords\", \"Vocal cord\", \"sputum\", \"sarcoid\", \"Klebsiella scleroma\", \"vocal cords\", \"laryngeal mucosa\", \"subepithelial non-necrotizing granulomata\"]}", "role": "assistant" } ]

[ { "content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Person\", \"Condition\", \"Value\", \"ReferencePoint\", \"Temporal\", \"Qualifier\", \"Observation\", \"Visit\", \"Measurement\", \"Mood\", \"Device\", \"Scope\", \"Negation\", \"Drug\", \"Procedure\", \"Multiplier\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\": [\"breast cancer\", ...], \"Device\": [\"ports\", ...], \"Drug\": [\"Atenolol\", ...], \"Measurement\": [\"blood pressure\", ...], \"Mood\": [\"suspected\", ...], \"Multiplier\": [\"more than two\", ...], \"Negation\": [\"no\", ...], \"Observation\": [\"history\", ...], \"Person\": [\"male\", ...], \"Procedure\": [\"surgery\", ...], \"Qualifier\": [\"severe\", ...], \"ReferencePoint\": [\"enrollment\", ...], \"Scope\": [\"infection\", ...], \"Temporal\": [\"one day\", ...], \"Value\": [\"50%\", ...], \"Visit\": [\"ICU\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nParticipation in another clinical trial.\nKnown or suspected (or history of) malignancy or chronic illness.\nSerious organic or mental disease diagnosed by a psychiatrist (e.g., major depression currently treated with antidepressant medication) suspected on the basis of the medical history and/or clinical examination.\nConditions that may affect the compliance to the study.\nContraindications to therapy with the study drug or hypersensitivity to the study drug (active ingredient or excipients of the formulation).", "role": "user" }, { "content": "{\"Condition\": [\"mental disease\", \"malignancy\", \"ganic o sease d\", \"major depression\", \"chronic illness\"], \"Device\": [], \"Drug\": [\"antidepressant medication\"], \"Measurement\": [], \"Mood\": [\"Known\", \"suspected\"], \"Multiplier\": [], \"Negation\": [], \"Observation\": [\"history of\", \"medical history\"], \"Person\": [], \"Procedure\": [\"clinical examination\", \"treated\"], \"Qualifier\": [\"diagnosed by a psychiatrist\"], \"ReferencePoint\": [], \"Scope\": [\"malignancy or chronic illness\", \"organic or mental disease diagnosed by a psychiatrist\", \"organic or mental disease\", \"Known or suspected (or history of)\", \"medical history and/or clinical examination\"], \"Temporal\": [\"currently\"], \"Value\": [], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "You will be shown a claim about public health and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: Though vitamin C supplements are considered safe, according to the CDC, it's easy to consume all the vitamin C you need through your diet.\n\nAbstract:\nBACKGROUND The coronavirus disease 2019 (COVID-19) is a pandemic caused by coronavirus with mild to severe respiratory symptoms.\nThis paper aimed to investigate the effect of nutrients on the immune system and their possible roles in the prevention, treatment, and management of COVID-19 in adults.\nMETHODS This Systematic review was designed based on the guideline of the Preferred Reporting for Systematic Reviews (PRISMA).\nThe articles that focussed on nutrition, immune system, viral infection, and coronaviruses were collected by searching databases for both published papers and accepted manuscripts from 1990 to 2020.\nIrrelevant papers and articles without English abstract were excluded from the review process.\nRESULTS Some nutrients are actively involved in the proper functioning and strengthening of the human immune system against viral infections including dietary protein, omega-3 fatty acids, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B6, vitamin B12, vitamin C, iron, zinc, and selenium.\nFew studies were done on the effect of dietary components on prevention of COVID-19, but supplementation with these nutrients may be effective in improving the health status of patients with viral infections.\nCONCLUSION Following a balanced diet and supplementation with proper nutrients may play a vital role in prevention, treatment, and management of COVID-19.\nHowever, further clinical trials are needed to confirm these findings and presenting the strong recommendations against this pandemic.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"RESULTS Some nutrients are actively involved in the proper functioning and strengthening of the human immune system against viral infections including dietary protein, omega-3 fatty acids, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B6, vitamin B12, vitamin C, iron, zinc, and selenium.\", \"Few studies were done on the effect of dietary components on prevention of COVID-19, but supplementation with these nutrients may be effective in improving the health status of patients with viral infections.\"]}", "role": "assistant" } ]