Datasets:

kejian

/

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

like 0

[ { "content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: We propose Random Erasing, a simple yet powerful data augmentation method that improves the generalization ability of the CNN\n\nKeyphrases: image classification\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.\nDocBank: A benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the \\LaTeX{} documents available on the arXiv.com.\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\nCUHK03: The CUHK03 consists of 14,097 images of 1,467 different identities, where 6 campus cameras were deployed for image collection and each identity is captured by 2 campus cameras. This dataset provides two types of annotations, one by manually labelled bounding boxes and the other by bounding boxes produced by an automatic detector.\nDukeMTMC-reID: The DukeMTMC-reID (Duke Multi-Tracking Multi-Camera ReIDentification) dataset is a subset of the DukeMTMC for image-based person re-ID. The dataset is created from high-resolution videos from 8 different cameras.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nReCoRD: Reading Comprehension with Commonsense Reasoning Dataset (ReCoRD) is a large-scale reading comprehension dataset which requires commonsense reasoning. ReCoRD consists of queries automatically generated from CNN/Daily Mail news articles; the answer to each query is a text span from a summarizing passage of the corresponding news.\n\nOptions:- A: THEODORE B: DocBank C: CIFAR-10 D: CUHK03 E: DukeMTMC-reID F: ImageNet G: ReCoRD", "role": "user" }, { "content": "[\"CIFAR-10\", \"CUHK03\", \"DukeMTMC-reID\", \"ImageNet\"]", "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:\nDevelopment of a fluorogenic sensor for activated Cdc42\n\nPaper sections:\n\n<p>Fluorescent probes have been used to monitor a variety of dynamic signaling interactions, including protein-protein interactions, enzyme activation, and changes in protein conformation.1, 2 In addition to enabling biochemical studies in real-time, these tools have been utilized in high-thoughput assays to screen for new small molecule drugs and inhibitors.3, 4 These methods generally rely on a change in a fluorescent read out, such as FRET, anisotropy, fluorescence lifetime, quantum yield, or emission wavelength.5 Solvatochromic fluorophores, which have emissive properties that are dependent on the nature of the solvent environment, are ideal for measuring these interactions because they are capable of providing information on even subtle changes in protein conformation.2 While many such fluorophores are commercially available, we have been particularly interested in the development and application of those derived from the dimethylaminonaphthalimide family.6–9 Specifically, 4-N,N-dimethylamino-1,8-naphthalimide (4-DMN) has recently been demonstrated to be a powerful probe of protein binding interactions.10 When the fluorophore is in an unbound, water-exposed state, the quantum yields of fluorescence are exceedingly low. However, upon exposure to a hydrophobic environment, such as that at the interface of a protein-protein interaction, increases in fluorescence can exceed 100-fold. Thus, when the fluorophore is appropriately positioned in a sensor protein, it behaves as an \"off-on\" switch to indicate a binding event. The 4-DMN chromophore can be readily incorporated into peptides and proteins either as an amino acid building block10 or through cysteine labeling with maleimide or α-bromoacetamide derivatives.11 Herein, we exploit the unique properties of this fluorophore to generate a sensor for the Rho GTPase Cdc42 (Figure 1).</p><p>Rho GTPases are small proteins central to the regulation of the actin cytoskeleton and cell migration. Alternating between an inactive GDP-bound and active GTP-bound state, these proteins function as molecular switches through transient interactions with effector proteins.12 One prominent member of the Rho GTPases is Cdc42, which is responsible for the reorganization of actin filaments into parallel bundles for filopodial protrusions. Additionally, Cdc42 activation generates cell polarity, a critical step in cell migration.13 Due to the fundamental role of Cdc42 in migratory processes, methods to monitor the real-time activity of the protein in vitro and in cells are essential.</p><p>Although FRET-based sensors have been developed for cellular applications, these methods use recombinant Cdc4214 or require overexpression of the protein.15 However, a particularly elegant sensor, generated by incorporating an environment sensitive fluorophore onto a protein fragment known to bind only the activated conformation of Cdc42, is capable of probing endogenous levels of wild-type Cdc42. This sensor, which was derived from the Cdc42/Rac interactive binding (CRIB) domain of the Wiscott-Aldrich syndrome protein (WASP), was modified with a merocyanine dye and exhibited a 3-fold increase in fluorescence intensity in the presence of activated Cdc42 compared to incubation with the inactive form of the protein.16 Due to the long excitation and emission wavelengths and high extinction coefficient of the merocyanine fluorophore, this sensor has been successfully used in live cell imaging studies and has been applied in combination with FRET-based sensors of the RhoA and Rac GTPases to interrogate activity at cell protrusions.17 To extend these studies and to exploit the high environment sensitivity of the 4-DMN fluorophore, we developed a complementary sensor for Cdc42 with 4-DMN and used it to monitor in vitro Cdc42 activity. We anticipated that the 4-DMN fluorophore would provide advantages for in vitro studies due to excellent signal-to-noise ratios and could be readily adapted for high-throughput screening.</p><p>The Cdc42 sensor was based on the CRIB domain of the WASP protein (residues 230–277) and incorporates the 4-DMN fluorophore in place of phenylalanine at position 271, a site previously reported to undergo changes in solvent environment upon interaction with Cdc42(GTP) due to exposure to hydrophobic interactions at the binding interface.16, 18 To increase heterologous expression levels and protein stability, the GB1 protein19 was fused to the N-terminus of the sensor, and to facilitate purification, a hexahistidine tag was incorporated at the C-terminus. Because the length of the linker tethering the fluorophore to the protein can significantly affect the fluorescent properties of the sensor,11 we tested a panel of five analogs, which append the 4-DMN fluorophore to the sensor with varying linker lengths, ranging from no linker to chains between 4 and 9 Å. We developed two complementary approaches for the site-specific incorporation of 4-DMN into the WASP fragment (Figure 2). In the first strategy, we examined a cysteine-labeling method using previously reported 4-DMN-modified α-bromoacetamide and maleimide reagents,11 and in an alternative approach, we exploited protein semisynthesis to incorporate the 4-N,N-dimethylamino-1,8-naphthalimido-alanine amino acid (4-DMNA), which eliminates the need for a linker.10 Because this amino acid derivative is similar in size to tryptophan, this route introduces a more conservative mutation, and potential structural perturbations are minimized. We then compared the fluorescence intensities of the sensors in the presence of inactive GDP-bound and active GTP-γS-bound Cdc42.</p><p>With the 4-DMN labeling strategy, we expressed the GB1-WASP protein with a Phe271Cys mutation to enable selective labeling of the protein sensor with 4-DMN thiol-reactive reagents (Figure 2a). Following expression in E. coli and purification by Ni-NTA affinity chromatography, the protein was labeled through an overnight incubation with a 20-fold excess of the cysteine-modifying reagent in the presence of TCEP. Purification of the labeling reactions from excess fluorophore by desalting yielded 1, 2, 3, and 4. Labeling efficiencies for all derivatives routinely reached around 60–70% (Figure S1).</p><p>The second approach to incorporation of the 4-DMN chromophore utilized expressed protein ligation, in which the N-terminal portion of the protein was prepared as a thioester, and the C-terminal fragment of the sensor containing the 4-DMNA amino acid was synthesized by Fmoc-based solid phase peptide synthesis (Figure 2b). The recombinant fragment (GB1-WASP(230–268)) was expressed as a fusion to intein and chitin binding domains to enable on-resin cleavage with sodium 2-mercaptoethanesulfonate to yield the corresponding thioester. Native chemical ligation between this thioester and the N-terminal cysteine of the synthetic peptide furnished the full-length sensor at about 60% conversion relative to unligated protein (Figure S2). The sensor was then purified from the unligated protein by Ni-NTA affinity chromatography, and excess peptide was eliminated by size exclusion chromatography. In addition to incorporation of the 4-DMNA residue, this approach offers the ability to integrate other functional handles into the C-terminal region of the sensor.</p><p>We next examined the fluorescent responses of the 4-DMN-based sensors to Cdc42 (Figures 3, S3). We expressed Cdc42 heterologously in E. coli, and loaded the purified protein with either GDP or GTP-γS, a non-hydrolyzable analog of GTP. Incubation of each 4-DMN sensor with the inactive GDP-bound form of the protein resulted in a negligible 1.1 – 1.9-fold increase in fluorescence over that of the sensor alone. However, dramatic increases in fluorescence, ranging from 11- to 32-fold, were observed in the presence of the active GTP-γS-bound Cdc42 compared to incubation with the inactive form of the protein (Figure 3a). Thus, the sensor readily discriminates between the two states of the protein and effectively acts as a signal of Cdc42 activation. Concurrent with the increase in fluorescence intensity was a hypsochromic shift in the emission maximum from 534 nm in the absence of Cdc42 to 514 nm in the presence of the activated protein.</p><p>Whereas the fluorescence of all five sensors was similarly low in the presence of the inactive GDP-bound protein, deviations in fluorescence intensities appeared upon Cdc42 activation. Of all the derivatives, probe 3 exhibited the most promising properties with a 32-fold increase in emission intensity and the strongest fluorescence signal upon binding activated Cdc42 (Figure 3b). In this construct, the long 9-Å linker provides the greatest flexibility for the 4-DMN fluorophore, likely allowing it to better embed within the hydrophobic interface of the two proteins. Importantly, because signal from the sensor alone or in the presence of Cdc42(GDP) is extremely low, background fluorescence is virtually non-existent. This switch-like property of the 4-DMN sensor is particularly useful because significant fluorescence differences can be observed without removing excess, unbound sensor before analysis. Additionally, we examined a double mutant of the sensor (His246Asp, His249Asp), which cannot bind Cdc42. This labeled mutant did not demonstrate fluorescence increases, even in the presence of Cdc42(GTP-γS), confirming that the fluorescence differences with 1 – 5 resulted from the sensor recognizing activated Cdc42 (Figure S4).</p><p>After demonstrating that the sensors exhibit excellent fluorescent responses to activated Cdc42, we explored the use of these tools to monitor nucleotide exchange and GTPase activity in real-time. We envisioned that this would provide a convenient method to measure the in vitro activity of Cdc42 and interactions with guanine nucleotide exchange factors (GEFs), which activate Cdc42 by exchanging GDP for GTP, and GTPase activating proteins (GAPs), which accelerate the rate of GTP hydrolysis. In the case of nucleotide exchange, the addition of GTP-γS to a solution of Cdc42 pre-equilibrated with GDP resulted in a continuous increase in the fluorescence of 3, while addition of GDP did not change the signal (Figure 4). Thus, the nucleotide exchange promoted by GEFs can be easily monitored, allowing convenient characterization of these regulating proteins or rapid screens of GEF inhibitors. Alternatively, the probe can be used to monitor GTP hydrolysis. For this assay, Cdc42 is pre-loaded with GTP, and in the presence of the sensor, a decrease in fluorescence is observed as the nucleotide is hydrolyzed (Figure S5). However, because the WASP fragment has been shown to inhibit the intrinsic rate of GTP hydrolysis,20 this application may be best suited for comparing relative rates of hydrolysis. The tool provides advantages over current approaches for evaluating Cdc42 activity, which include discontinuous radioactive filter binding approaches,21 because dynamic activity can be monitored directly in a continuous fashion with a simple fluorescence plate reader. Additionally, with a high signal-to-noise ratio, the probe exhibits great sensitivity and can be readily adapted for high-throughput screening of small molecule modulators of Cdc42 or associated regulatory proteins.</p><p>Finally, we measured the dissociation constant of the 4-DMN sensor with GTP-γS-bound Cdc42 to demonstrate the utility of the probe in quantifying bimolecular interactions and to ensure that incorporation of the fluorophore does not significantly alter binding. To eliminate complicating effects resulting from the presence of unmodified GB1-WASP in samples obtained through the cysteine-labeling approach, the sensor generated by expressed protein ligation was initially employed for these studies. Fluorescence spectra from titrations in which Cdc42(GTP-γS) was added to 5 were fit to a 1:1 binding model, which yielded an observed KD of 385 ± 9 nM (Figure S6). Similarly, the observed KD for sensor 3 was 341 ± 22 nM. These values agree well with the dissociation constants of similar WASP fragments, which lie within the mid-nanomolar range.22</p><p>In summary, we have developed a powerful probe for detecting the activated form of Cdc42 by incorporation of the 4-DMN solvatochromic fluorophore into the WASP binding domain. Cysteine labeling of the WASP fragment or protein semisynthesis furnishes a sensor that discriminates between the inactive and active conformations of Cdc42 through dramatic increases in fluorescence. These remarkable properties can be exploited to monitor the nucleotide exchange and GTPase activities of Cdc42 as well as the influence of regulatory proteins. By offering a large dynamic range and high sensitivity, this 4-DMN-based sensor promises to be valuable in the study of Cdc42 and represents another example of the versatility of the 4-DMN fluorophore as a probe of important protein binding interactions.</p>", "role": "user" }, { "content": "Cdc42, a member of the Rho GTPase family, is a fundamental regulator of the actin cytoskeleton during cell migration. To generate a sensor for Cdc42 activation, we employed a multi-pronged approach, utilizing cysteine labeling and expressed protein ligation, to incorporate the environment sensitive fluorophore 4-N,N-dimethylamino-1,8-naphthalimide (4-DMN) into the GTPase binding domain of the WASP protein. These constructs bind only the active, GTP-bound conformation of Cdc42 to produce a fluorescence signal. Studies with a panel of five sensor analogs revealed a derivative that exhibits a 32-fold increase in fluorescence intensity in the presence of activated Cdc42 compared to incubation with the inactive GDP-bound form of the protein. We demonstrate that this sensor can be exploited to monitor Cdc42 nucleotide exchange and GTPase activity in a continuous, fluorescence assay.", "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:\nThus, the second class of SBD systems employs machine learning techniques such as decision tree classifiers (Riley 1989), neural networks (Palmer and Hearst 1994), and maximum-entropy modeling (Reynar and Ratnaparkhi 1997). Automatically trainable software is generally seen as a way of producing systems that are quickly retrainable for a new corpus, for a new domain, or even for another language. Another well-acknowledged shortcoming of rule-based systems is that such systems are usually closely tailored to a particular corpus or sublanguage and are not easily portable across domains.\n\nCitation Sentence:\nThus , the second class of SBD systems employs machine learning techniques such as decision tree classifiers ( Riley 1989 ) , neural networks ( Palmer and Hearst 1994 ) , and maximum-entropy modeling ( Reynar and Ratnaparkhi 1997 ) .\n\nContext after the citation:\nMachine learning systems treat the SBD task as a classification problem, using features such as word spelling, capitalization, suffix, and word class found in the local context of a potential sentence-terminating punctuation sign. Although training of such systems is completely automatic, the majority of machine learning approaches to the SBD task require labeled examples for training. This implies an investment in the data annotation phase.", "role": "user" }, { "content": "Background", "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:\nThe compact conformation of the Plasmodium knowlesi myosin tail interacting protein MTIP in complex with the C-terminal helix of myosin A\n\nPaper sections:\n1. Introduction\n<p>The machinery used by malaria parasites for the invasion of host cells is currently the subject of intense investigations (for recent reviews see [1,2]), which reflects the crucial importance of this machinery in understanding the biology of the parasite. Such studies can at the same time yield possible starting points for the design of molecules which interfere with the invasion process and which might be developed into novel anti-malarials [3–7]. Key proteins such as TRAP, aldolase, actin, myosin A, MTIP, GAP40, GAP45, GAP50 and others have been identified as crucial components of the invasion machinery, also called the glideosome. We have previously been successful in determining crystal structures of several proteins of this system. These include (i) Plasmodium falciparum aldolase in complex with the TRAP tail [8]; (ii) the soluble domain of GAP50 from P. falciparum [7]; (iii) ligand-free Plasmodium knowlesi MTIP (PknoMTIP) and the complex of PknoMTIP with the MyoA tail peptide (PknoMTIP•MyoA) [9]; (iv) P. falciparum MTIP in complex with the MyoA tail peptide (PfalMTIP•MyoA) [10]; and (v) the structure of the C-terminal domain of PfalMTIP in complex with a nanobody (Khamrui et al., accompanying paper). Here we focus on MTIP from P. knowlesi. MTIP interacts with the C-terminal helix of myosin A and with GAP45. In doing so, MTIP performs a crucial role in the chain of proteins leading from TRAP interacting with a human cell surface protein to the inner membrane complex of the malaria parasite.</p><p>MTIP is a three-domain protein where the first domain (D1) is involved in interactions with GAP45 as observed in the closely related Apicomplexan parasite Toxoplasma gondii [11]. The second domain (D2) interacts with the MyoA tail helix in the compact PfalMTIP•MyoA complex but not in the extended PknoMTIP•MyoA complex [9,10]. The third domain (D3) interacts with the MyoA tail in both reported PfalMTIP•MyoA and PknoMTIP•MyoA complexes [9,10]. The D3 domain undergoes substantial conformational changes when binding to the MyoA tail helix ([9,10]; Khamrui et al., accompanying paper).</p><p>The relative position and orientation of D2 and D3 in the PknoMTIP•MyoA complex appeared to be dramatically different from that in the PfalMTIP•MyoA complex. In the PknoMTIP•MyoA complex, MTIP is extended with domains D2 and D3 far apart, connected by an essentially straight central helix while only D3 interacts with the MyoA tail helix. In contrast, the conformation of MTIP in PfalMTIP•MyoA is compact with domains D2 and D3 much closer together, connected by a kinked central helix while both domains interact with the MyoA tail helix [9,10]. We previously suggested that both the pH and the length of the construct used could be a crucial factor in determining the conformation of MTIP in complex with the MyoA tail helix. Here we provide evidence that PknoMTIP can adopt an extended as well as a compact conformation when binding the MyoA tail helix, with a higher pH the crucial factor in making the compact PfalMTIP•MyoA complex possible.</p><p>The protein preparation and structure determination of the new PknoMTIP•MyoA complex is described in Table 1, which also contains statistical parameters regarding X-ray diffraction data and model quality. Since full length MTIP resisted all crystallization attempts so far, all MTIP structures presented here and reported previously are from variants with the D1 domain deleted. The PknoMTIP variant described here contains residues K79 to C135 of D2, the hinge region V136-N141, and D3 residues M142-S205. The crystals of the PknoMTIP•MyoA complex obtained appeared to contain three copies of the PknoMTIP•MyoA complex in the asymmetric unit (Fig. 1A). The three complexes are similar in structure, with complexes A and B differing by an rmsd of 1.06 Å, complexes A and C by 0.87 Å, and complexes B and C by 0.63 Å. Since complex C has the lowest average B-factor, this complex will be used for further description and comparison. In the new PknoMTIP•MyoA structure each of the three PknoMTIP molecules surrounds the MyoA tail helix with both domains 2 and 3 engaging in contact with the MyoA helix. The solvent accessible surface area buried between PknoMTIP-D2 and MyoA is 728 Å2, and between PknoMTIP-D3 and MyoA 1451 Å2, as calculated by PISA [12].</p><p>The conformation of MTIP in the new PknoMTIP•MyoA complex differs considerably from that seen in the previous PknoMTIP•MyoA crystal structure (Fig. 1B). While both structures contain three chains per asymmetric unit, previously the three subunits adopted three distinctly different conformations, all with an extended connecting helix, despite the fact that subunits A and B contained no MyoA, and subunit C did [9]. In contrast, in the current structure, the three MTIP molecules are all essentially the same, with the connecting helix kinked, resulting, in each instance, in a compact PknoMTIP conformation. Clearly, PknoMTIP is able to adopt two very different conformations even when in complex with the MyoA tail helix.</p><p>The interactions between MTIP and MyoA consists of a mainly hydrophilic interface between MyoA and PknoMTIP-D2 (Fig. 2A), an interface with D3 which is a combination of hydrophobic and hydrophilic interactions (Fig. 2B), and one PknoMTIP•MyoA interaction between MyoA-R806 and PknoMTIP-D140 from the central hinge region. In the D2•MyoA interface, the carbonyl O of A106 is interacting with the guanidinium group of R806. In this interface, the Cβ, Cγ and Cδ atoms of MyoA-K813 engage in hydrophobic interactions with the peptide units of PknoMTIP-L105 and PknoMTIP-G104. In the PknoMTIP-D3•MyoA interface, the side chains of three aliphatic residues of MyoA, L804, V807 and I811 are buried in hydrophobic pockets of D3 formed by residues L145, M148, F149, I168, L169, W172, L176, A184, L185, F199, C200 and I203 (Fig. 2B). The imidazole ring of MyoA-H810 plays a critical role as will be discussed below. Its Nδ1 is forming a 2.9 Å hydrogen bond with the side chain amino group of MyoA-K813, and its Nε2 is engaged in a hydrogen bond of equal length with the carboxylate of PknoMTIP-D140 of the hinge region (Fig. 2A).</p><p>When comparing the compact and the extended PknoMTIP conformations, it appears that MTIP-D2 rotates considerably (117°, based on the superposition of α6-loop-α7 of D3 from subunits C in both crystal structures) with respect to MTIP-D3. Residues V136-N141 in the central part of the connecting helix adopt very different conformations in these two complexes (Fig. 1B). The conformations of MTIP-D2 in the two complexes are very similar with an rmsd of 0.45 Å. The MTIP-D3 domains in the two structures differ more, however, and superimpose with an rmsd of 1.06 Å as explained further in the accompanying paper (Khamrui et al., accompanying paper). It appears therefore that, upon forming a complex with MyoA, PknoMTIP-D3 adopts a conformation with a wide groove to accommodate the MyoA helix. Another change is a major bending of the connecting helix, turning residues V136-N141 into a non-helical conformation, thereby allowing D2, which remains essentially unaltered, to contact the MyoA helix from \"above\".</p><p>The conformation of P. falciparum MTIP in the previously reported PfalMTIP•MyoA complex appeared to be compact with a kinked connecting helix and both PfalMTIP-D2 and PfalMTIP-D3 interacting with the MyoA tail helix [10]. The rmsd of MTIP in the PknoMTIP•MyoA and PfalMTIP•MyoA complexes after superposition is 1.06 Å for 121 amino acids with a sequence identity of 80%, with the individual domains D2 and D3 differing by 0.30 and 0.32 Å, respectively. The buried solvent accessible surface areas of D3 in the PfalMTIP•MyoA and PknoMTIP•MyoA complexes with the MyoA helix are remarkably similar with 2139 and 2063 Å2, of which 1478 and 1451 Å2 buried in the interface between MTIP-D3 and the MyoA helix, respectively. The side chains of PknoMTIP and PfalMTIP contacting MyoA are identical in the two complexes, except for the C-terminal S204 which is a glutamine in PfalMTIP.</p><p>Previously it was suggested [10] that two factors might play a role determining whether the MTIP•MyoA complex adopts an extended or a compact conformation. One putative factor was a lower pH in the crystals with the extended PknoMTIP•MyoA structure, and a second potential factor the slightly longer version, starting 20 residues closer to the N-terminus of the full length protein, of P. falciparum MTIP used for the PfalMTIP•MyoA studies compared to the PknoMTIP variant used for the PknoMTIP•MyoA structure. In the current compact PknoMTIP structure we used precisely the same variant of PknoMTIP as in the previous study which yielded the extended structures [9]. Hence, the length difference between the P. falciparum and P. knowlesi MTIP variants used is not the cause of the difference between compact and extended conformations.</p><p>The current compact structure was solved from crystals grown out of a solution with pH 7.0, while the previous structure yielding the extended PknoMTIP conformation was obtained from crystals grown at pH 5.3. The key interface residue which differs in protonation state at these pH values is MyoA-H810. In the compact PknoMTIP conformation (Fig. 2A), the imidazole of this residue interacts with the Nε of MyoA-K813 and with an Oδ of PknoMTIP-D140. The latter interaction requires a proton on one imidazole nitrogen, but, in order to form a hydrogen bond with the Nε of MyoA-K813, the second ring nitrogen of MyoA-H810 needs to be unprotonated. At the pH 7.0 in the current PknoMTIP•MyoA structure, the imidazole is uncharged thereby allowing favorable interactions with the negatively charged Asp carboxylate oxygen and the positively charged Lys side chain nitrogen to take place simultaneously (Fig. 2A). But at the lower pH 5.3 of the crystals used for the previous PknoMTIP•MyoA structure determination, the imidazole ring of MyoA-H810 is charged and repulsion with the Lys side chain nitrogen prevents the tight interactions in the compact MTIP•MyoA complex, resulting in an extended MTIP conformation.</p>\n\n2. Concluding remarks\n<p>The new crystal structure of the PknoMTIP•MyoA complex shows, in triplicate (Fig. 1A), that PknoMTIP is able to adopt a compact conformation where PknoMTIP-D2 and PknoMTIP-D3 surround the MyoA tail helix, different from the extended PknoMTIP conformations observed before. The four conformations of PknoMTIP now available indicate that PknoMTIP is a highly flexible protein able to adopt different extended conformations in the absence of the MyoA tail (i.e. subunits A and B of [9]), an extended conformation in complex with the MyoA tail (subunit C of [9]), and a compact conformation in complex with the MyoA tail (Fig. 1). In addition, the third domain can adopt different conformations in the absence and presence of the MyoA tail helix ([9]; Khamrui et al., accompanying paper). This spectrum of conformations indicates a considerable mobility of liganded and ligand-free MTIP in solution. The importance of this flexibility under physiological conditions still needs to be established with further investigations.</p>", "role": "user" }, { "content": "The myosin motor of the malaria parasite\\xe2\\x80\\x99s invasion machinery moves over actin fibers while it is making critical contacts with the myosin-tail interacting protein (MTIP). Previously, in a \\xe2\\x80\\x9ccompact\\xe2\\x80\\x9d Plasmodium falciparum MTIP\\xe2\\x80\\xa2MyoA complex, MTIP domains 2 (D2) and 3 (D3) make contacts with the MyoA helix, and the central helix is kinked, but in an \\xe2\\x80\\x9cextended\\xe2\\x80\\x9d Plasmodium knowlesi MTIP\\xe2\\x80\\xa2MyoA complex only D3 interacts with the MyoA helix, and the central helix is fully extended. Here we report the crystal structure of the compact P. knowlesi MTIP\\xe2\\x80\\xa2MyoA complex. It appears that, depending on the pH, P. knowlesi MTIP can adopt either the compact or the extended conformation to interact with MyoA. Only at pH values above ~7.0, can key hydrogen bonds can be formed by the imidazole group of MyoA His810 with an aspartate carboxylate from the hinge of MTIP and a lysine amino group of MyoA simultaneously.", "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\n[ The effects of antidepressant treatment on efficacy of antihypertensive therapy in elderly hypertension ] . OBJECTIVE To explore the effect of antidepressant treatment on antihypertensive therapy of senile hypertension . METHODS 138 cases of senile hypertension complicating with depression were studied . 103 senile hypertensive patients without depression in the same period served as controls . The patients were randomly divided into 3 groups as A , B and C for study . 12.5 mg/d hydrochlorothiazide and 30 mg/d release-controlling tablets of nifedipine were orally administrated as basic antihypertensive medication each group . Besides , 20 mg/d fluoxetine was additionally given to groups A and one tablet of almitrine l/d and 20 mg oryzanol 3/d were given to group B . The treatment lasted 12 weeks . RESULTS In comparison with pre-treatment , the blood pressure at base line in sitting position and the average circadian SBP and DBP monitored with 24-hour ambulatory blood pressure monitoring ( ABPM ) was remarkably decreased in group A with statistical significance ( P < 0.01 ) . These blood pressure parameters in group B were also decreased as compared ith the pretreatment level brt with less statistical significance ( P > 0.05 ) . It was also noted tha with the addition of antidepressant fluoxetine , the manifestations of depression ere alleviated as shown by Hamilton depression ( HAMD ) scale . untoward reactions such as nausea , perspiration and skin rash were noted in a few patients , but none withdrew from the study . CONCLUSIONS Antidepressant and antianxiety treatment is of benefit to the antihypertensive therapy in senile hypertensive patients with complications of depression and/or anxiety neurosis . Based on the results of this study , it is suggested that routine administration of antidepressants and antianxiety drugs should be carried out in senile hypertensive patients complicating with depression or anxiety .", "role": "user" }, { "content": "{\"Intervention\": [\"fluoxetine\", \"almitrine l/d\", \"nifedipine\", \"oryzanol 3/d\", \"hydrochlorothiazide\", \"antidepressant treatment\"], \"Outcome\": [\"efficacy\", \"nausea , perspiration and skin rash\", \"Hamilton depression ( HAMD ) scale\", \"blood pressure parameters\", \"depression\", \"blood pressure\", \"average circadian SBP and DBP monitored with 24-hour ambulatory blood pressure monitoring ( ABPM )\", \"hypertension\"], \"Participant\": [\"senile hypertension\", \"103\", \"senile hypertensive patients\", \"elderly\", \"depression\", \"senile hypertensive patients without depression\", \"138\", \"hypertension\"]}", "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 delivery system is used for the Fluzone Intradermal vaccine?\n\nContext: On May 9 2011, the US FDA approved Sanofi Pasteur's Fluzone(®) Intradermal influenza vaccine, the first influenza vaccine licensed in the USA that uses a new microinjection system for intradermal delivery of vaccines (Soluvia™, Becton Dickinson).", "role": "user" }, { "content": "Microinjection system for intradermal vaccine delivery", "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\nUtility of the bladder flap at cesarean delivery : a randomized controlled trial . OBJECTIVE To test the hypothesis that omission of the bladder flap in primary and repeat cesarean deliveries shortens operating time without increasing intraoperative and postoperative complications . METHODS We randomized 258 women undergoing primary and repeat cesarean deliveries at 32 weeks of gestation or more to creation ( n=131 ) or omission ( n=127 ) of the bladder flap . Emergency cesarean deliveries , planned vertical uterine incisions , and previous abdominal surgeries besides cesarean deliveries were excluded . The primary outcome measure was total operating time . Secondary outcomes were bladder injury , incision-to-delivery time , incision-to-fascial closure time , estimated blood loss , postoperative microhematuria , postoperative pain , hospital days , endometritis , and urinary tract infection . Analysis followed the intention-to-treat principle . RESULTS The median skin incision to delivery interval was shorter with omission of the bladder flap ( 9 [ range 1-43 ] compared with 10 [ range 2-70 ] minutes ; P=.04 ) , but there was no difference in total operating time ( 51 [ range 18-124 ] minutes compared with 51 [ range 16-178 ] ; P=.10 ) . No bladder injuries occurred in either group and there were no significant differences in estimated blood loss , change in hemoglobin level , postoperative microhematuria , postoperative pain , hospital days , endometritis , or urinary tract infection . CONCLUSION Omission of the bladder flap at primary and repeat cesarean deliveries does not increase intraoperative or postoperative complications . Incision-to-delivery time is shortened but total operating time appears unchanged . CLINICAL TRIAL REGISTRATION ClinicalTrials.gov , www.ClinicalTrials.gov , NCT00918996 . LEVEL OF EVIDENCE I .", "role": "user" }, { "content": "{\"Intervention\": [\"cesarean deliveries\", \"cesarean delivery\", \"creation\", \"abdominal surgeries\", \"bladder flap\", \"omission of the bladder flap\", \"primary and repeat cesarean deliveries\", \"omission\"], \"Outcome\": [\"bladder injuries\", \"incision-to-delivery time\", \"estimated blood loss\", \"postoperative microhematuria\", \"incision-to-fascial closure time\", \"bladder injury\", \"postoperative pain\", \"total operating time\", \"endometritis\", \"median skin incision to delivery interval\", \"hospital days\", \"change in hemoglobin level\", \"total operating time .\", \"urinary tract infection\"], \"Participant\": [\"n=131\", \"258\", \"n=127\", \"primary and repeat cesarean deliveries\", \"women\"]}", "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\nAge and renal clearance of cimetidine. In 35 patients (ages 20 to 86 yr) receiving cimetidine therapeutically two serum samples and all urine formed in the interim were collected for analysis of cimetidine by high-pressure liquid chromatography and for creatinine. Cimetidine clearance decreased with age. The extrapolated 6-hr serum concentration of cimetidine per unit dose, after intravenous cimetidine, increased with age of the patients. The ratio of cimetidine clearance to creatinine clearance (Rc) averaged 4.8 +/- 2.0, indicating net tubular secretion for cimetidine. Rc seemed to be independent of age and decreased with increasing serum concentration of cimetidine, suggesting that secretion of cimetidine is a saturable process. There was only one case of dementia possibly due to cimetidine (with a drug level of 1.9 microgram/ml 6 hr after a dose) in a group of 13 patients without liver or kidney disease who had cimetidine levels above 1.25 microgram/ml. Thus, high cimetidine levels alone do not always induce dementia.", "role": "user" }, { "content": "{\"Chemical\": [\"Cimetidine\", \"creatinine\", \"cimetidine\"], \"Disease\": [\"kidney disease\", \"liver disease\", \"liver or kidney disease\", \"dementia\"]}", "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: Loss of RMI2 Increases Genome Instability and Causes a Bloom-Like Syndrome\nArticle:\nAbstract:\nBloom syndrome is a recessive human genetic disorder with features of genome instability, growth deficiency and predisposition to cancer. The only known causative gene is the BLM helicase that is a member of a protein complex along with topoisomerase III alpha, RMI1 and 2, which maintains replication fork stability and dissolves double Holliday junctions to prevent genome instability. Here we report the identification of a second gene, RMI2, that is deleted in affected siblings with Bloom-like features. Cells from homozygous individuals exhibit elevated rates of sister chromatid exchange, anaphase DNA bridges and micronuclei. Similar genome and chromosome instability phenotypes are observed in independently derived RMI2 knockout cells. In both patient and knockout cell lines reduced localisation of BLM to ultra fine DNA bridges and FANCD2 at foci linking bridges are observed. Overall, loss of RMI2 produces a partially active BLM complex with mild features of Bloom syndrome.\nIntroduction:\nBloom syndrome( BS) is a very rare genetic disorder with features of significant growth deficiency, hypo- and hyperpigmented skin, sun-sensitive facial skin lesions, cancer predisposition in early life and male infertility[1, 2]. Early cytogenetic experiments revealed clues about the underlying mechanism with patient chromosomes exhibiting hyper-recombination and genome instability[3]. The only known gene, BLM, associated with BS was identified in 1995[4]. The gene encodes for the BLM protein that is a member of the RecQ DNA helicase family of proteins. RecQ helicases are essential for genome maintenance and are conserved across evolution. Protein interaction studies have shown that the BLM protein is a member of a four-subunit complex that includes topoisomerase III alpha( TOP3A)[5, 6] and RecQ-mediated genome instability proteins 1[7–9] and 2[10, 11]( RMI1 & 2), collectively known as the BTR complex. The BTR promotes the dissolution of double Holliday junctions that can be formed during DNA replication into non-crossover products in a two-step process: 1) by pushing the Holliday junctions together by the helicase activity of BLM, and 2) the dissolution of hemi-catenated DNA by the cleavage and joining activities of TOP3A[12]. Crossover events between homologs in somatic cells can be detrimental to a cell’s survival as they lead to loss of heterozygosity( LOH)[13, 14, 15]. Notably LOH is elevated in BLM deficient cells[16]. Moreover, unresolved recombination intermediates that persist into mitosis lead to bridging and are a source of genomic instability[17]. Structure and function studies have shown that RMI1 and 2 form a heterodimer that is important in stabilising the BTR[18, 19]. The BTR complex has been proposed to localise to stalled replication forks via interactions with Fanconi anaemia( FANC) subunits and Replication Protein A[20]. This super-complex is also known as BRAFT. Similar to BS, Fanconi anemia patients exhibit growth deficiencies, chromosomal breaks, heightened genomic instability and cancer predisposition[21]. Further evidence to support this connection is through structural analyses with a FANCM peptide and the RMI1-RMI2 heterodimer[22]. The FANC core complex consists of eight subunits that promote the monoubiquitination of FANCD2 and FANCI in response to sites of DNA damage where replication forks are obstructed[23, 24]. FANCD2 acts at stalled replication forks to remove interstrand cross-links( ICLs) and additionally regulates homologous recombination proteins including BRCA2/FANCD1[25–27]. BLM is known to cooperate with FANCD2 during S phase to restart stalled replication forks while also suppressing the firing of new replication origins; an activity that is independent of FANCI[28]. During mitosis, FANCD2 and FANCI subunits frequently appear at the sister chromatid anchor sites that link DAPI-negative chromatin threads also known as ultra fine bridges( UFBs) and also occasionally along the UFBs during anaphase[29, 30]. FANCI/D2 sister foci in mitosis appear at chromosome arms and not centromeres and their localisation corresponds to fragile sites in the genome[29]. The foci that link UFBs during chromosome segregation imply a tethering or loading function for proteins that coat UFBs such as BLM and PICH[31, 32], but this is yet to shown. BLM, TOP3A and RMI1 are highly conserved in most eukaryotes but RMI2 is absent in some lineages including invertebrates and yeasts, suggesting that it is needed in organisms with higher genome complexity[11]. Further evidence to support RMI2’s functional role in higher eukaryotes was shown in chicken DT40 RMI2 null cells which display elevated levels of sister chromatid exchanges( SCEs). At a cellular level, whether RMI2 is required during mitosis and at an organism level, its role during development and disease predisposition are all outstanding questions. Here, we show a homozygous deletion of RMI2 in two siblings with milder clinical features of Bloom syndrome. We have additionally mutated RMI2 using CRISPR-Cas9 gene-editing to further confirm the hyper-recombination and mitotic defect phenotypes observed in the patients’ cells.\nDiscussion:\nWe have identified a homozygous deletion of the RMI2 gene that results in a Bloom-like phenotype from a consanguineous kindred. The two affected siblings exhibit a variable phenotype with some overlapping features of Bloom syndrome. Sibling, S2, presented with growth deficiency and gastro-esophageal reflux, traits commonly found in Bloom syndrome children. Curiously, these indicators were absent in sibling S1( Table 1). It is too early to tell whether homozygous deletion of RMI2 is associated with elevated risk of cancer in late childhood or adulthood. Consistent with the clinical presentation, our cell biology analyses also indicated sibling S2 was slightly more affected with mitotic assays for chromosome bridges in mitosis, bridges persisting between interphase nuclei and micronuclei all elevated compared to sibling S1. The striking feature consistent with a Bloom syndrome phenotype, is both children display café-au-lait macules( Fig 1A). These dermatological findings are often associated with childhood cancer syndromes[37]. Loss of RMI2 should therefore be added to the differential diagnosis of children presenting with multiple café-au-lait macules. Cytogenetic investigation into genome instability showed a higher rate of SCEs and chromatid breaks( Fig 2). BLM null individuals have a 10-fold elevation in the rate of SCEs when compared to wild-type cells[3]. By contrast, we have observed a slightly lower rate at seven- to eight-fold above wild-type. This is consistent with a similar decrease when SCE rates are compared between BLM and RMI2 knockout chicken DT40 cells[11]. These data suggest that the BLM helicase displays partial activity in dissolving catenated DNA in the absence of RMI2. Indeed, in vitro addition of RMI2 to BLM-TopoIIIα-RMI1 caused a statistically significant increase in the rate and overall level of dissolution of radiolabelled double Holliday junction substrates[10]. The same study found the BLM-TopoIIIα-RMI1 complex alone still possesses significant dissolution activity; suggesting RMI2 enhances but is not essential to the enzymatic capability of the BTR complex. However, we note our in vivo analyses show removal of RMI2 has a profound affect on the stability of BLM on UFBs that likely represent a range of replication intermediates. Understanding the DNA structure of UFBs remains an important task that will provide insight into why and how UFB-associated proteins act. The notion that BLM-TopoIIIα-RMI1 alone can still dissolve double Holliday junctions is consistent with the observation that BLM patients show a more noticeable clinical presentation compared to RMI2 affected individuals. Additionally, BLM has activities that are independent of RMI2. For instance, it is known BLM stimulates the resection activity of human exonuclease 1[38]. It is therefore also likely that with the increase in DNA analysis capabilities and also clinical awareness that further RMI1 and also RMI2 affected individuals will be identified in the population. The failure to dissolve catenated DNA in the affected siblings is the main trigger for downstream mitotic errors such as DNA anaphase bridges and micronuclei( Fig 3 and Fig 4). These perturbations in mitosis are thought to have an impact on the cell proliferation rate. We have investigated whether there was any link between mitotic errors and growth rates in the affected siblings but no consistent association could be found. Homozygous knockout of the RMI2 gene in HCT-116 cells showed a noticeable slowing down in cell proliferation and the ability to form colonies from single cells( Fig 4B and S5E and S5F Fig). This is in contrast to the chicken DT40 RMI2 knockout cell lines that did not display any reduction in cellular growth rate, although colony forming assays were not performed[11]. Correspondingly, one of the affected siblings showed prenatal and postnatal growth deficiency( Table 1). The variability in cell proliferation rates and impact on development is most likely to be dependent on genetic background. Furthermore, the growth deficiency phenotype observed in sibling S2 may be due to a co-existing disorder associated with the parents’ consanguinity. RMI2 mouse knockout studies will hopefully shed some light on these differences between model systems. DNA repair disorders are commonly associated with sensitivity to DNA-damaging agents such as chemical mutagens or short wave radiation such as UV light. Bloom syndrome affected individuals are mildly sensitive to sunlight where they display sun-sensitive lesions on exposed areas such as the face[1]. However, there are conflicting reports in the literature whether BLM null cells are sensitive to UV light in vitro[4, 39, 40]. The affected siblings did not show any signs of sun-sensitive skin lesions on exposed areas. HCT-116 RMI2 null cells also did not show any consistent reduction in the number or size of colonies after being exposed to short-wave UV light or hydroxyurea when compared to parental wild-type cells( Fig 4). Similar results were observed in chicken DT40 RMI2 null cells when challenged with DNA-damaging chemicals such as cisplatin or methyl methanesulfonate[11]. Taken together, these data support that the BLM helicase can perform some of its DNA repair functions without the participation of RMI2. Earlier experiments on the knockdown of RMI2 from vertebrate cells had not examined its role during chromosome segregation. Examination of RMI2 null cells in fibroblasts and HCT-116 lines has shown hallmarks of mitotic errors in the form of DNA bridges and micronuclei( Fig 3 and Fig 4). Were these chromosome entanglements due to the lack of the BTR complex localising to UFBs? We have shown both BLM( Fig 6) and TopoIIIα( Fig 7) localisation is disrupted when RMI2 is removed. Our data however show that BLM still can localise to UFBs, albeit at a significantly lower intensity. Together, this evidence supports our hypothesis that the BTR is functionally impaired during mitosis without RMI2. Further evidence of this partial activity is illustrated with localisation experiments of FANCD2 in RMI2 null cells. Like BLM, FANCD2 sister chromatid foci are reduced in frequency and intensity, suggesting that BTR instability impacts upon important DNA repair complexes such as FANC( Fig 8). This is not without precedent as it is known that BLM co-immunoprecipitates with FANCD2 in human cells[41], and mechanistically FANCD2 and the BTR complex cooperate to restart stalled replication forks[28, 42]. These studies suggest a physical and mechanistic interplay between BTR and FANCD2 in S phase under replication stress and the dependencies seemingly persist through to M phase. Curiously ours( Fig 8 and S9 Fig) and another study[29] observed FANCD2 coated UFBs. The nature of FANCD2 UFBs has not been fully explored, but it is possible they exist as backup or additional activity in resolving catenated DNA structures during anaphase. The BLM Bloom syndrome gene was first identified over 20 years ago. Our report shows that this is the first clinical description of individuals with Bloomoid features of non-BLM subunit. Although producing a clinical presentation similar to Bloom syndrome, the hallmark features are not as severe. Independent studies using cell lines derived from homozygous affected siblings and also HCT-116 cells deleted of RMI2 both show overlapping defects with marked increase in DNA bridges during the later stages of cell division. Our data show removing RMI2 affects the stability of interacting partners in the BRAFT super complex with BLM and FANCD2 reduced on chromosomes during chromosome segregation. Significantly, those cells without RMI2 that displayed BLM fibers in anaphase showed a marked drop in signal intensity, suggesting RMI2 stabilises or activates the complex. Whether there is any residual activity of BLM and how the overall subunit composition and architecture of the BTR and BRAFT complexes is affected is not yet clear. These will be important questions for future studies. Our current study suggest both at the patient and cell biology level the effects are not as severe as lacking BLM altogether.", "role": "user" }, { "content": "Cells contain specific protein complexes that are needed to correct errors during the replication and segregation of DNA . Impairment in the activity of these proteins can be detrimental to the viability of the cell and organism development . Bloom syndrome is an example of a genome instability disorder where cells cannot efficiently untangle DNA after replication . The only gene that is known to cause Bloom syndrome is the BLM helicase . In this article , we describe two affected individuals with Bloom-like features with a homozygous deletion of the RMI2 gene . The RMI2 protein has previously been shown to form a complex with BLM , topoisomerase III alpha and RMI1 . Deletion of RMI2 in patient and unrelated cell lines show hyper-recombination and chromosome entanglements during cell division . Furthermore , we show that the BLM and FANCD2 proteins are diminished in the binding of DNA bridges that need to be dissolved during the late stages of cell division . Therefore , loss of RMI2 produces a milder Bloom phenotype and impairs the full activity of the BLM complex .", "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\nCXCR4 by various receptor tyrosine kinases has been linked to both normal and disease-related signaling in multiple cell types.(16-19) This transactivation often involves a physical association between receptors and site-specific phosphorylation of CXCR4 that activates various signaling outcomes.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2018 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 am trying to implement a framework for knowledge representation learning based on Generative Adversarial Networks.\n\nKeyphrases: knowledge representation learning\n\nDataset description:\nWN18: The WN18 dataset has 18 relations scraped from WordNet for roughly 41,000 synsets, resulting in 141,442 triplets. It was found out that a large number of the test triplets can be found in the training set with another relation or the inverse relation.\nSWAG: Given a partial description like \"she opened the hood of the car,\" humans can reason about the situation and anticipate what might come next (\"then, she examined the engine\"). SWAG (Situations With Adversarial Generations) is a large-scale dataset for this task of grounded commonsense inference, unifying natural language inference and physically grounded reasoning.\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.\nCommonsenseQA: The CommonsenseQA is a dataset for commonsense question answering task. The dataset consists of 12,247 questions with 5 choices each.\n\nOptions: A: WN18 B: SWAG C: ConvAI2 D: CommonsenseQA", "role": "user" }, { "content": "WN18", "role": "assistant" } ]

[ { "content": "You will be shown a claim related to the COVID-19 pandemic, 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\".\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract.\n\nFor instance, if the model were given the claim \"the COVID vaccine is safe for healthy adults\", the output might be:\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that the risks of severe COVID vaccine side effects are low for healthy adults.\"]\n}\n\nClaim: Surgical mask partition reduces the risk of noncontact transmission in a golden syrian hamster model for coronavirus disease 2019\n\nAbstract:\nBACKGROUND: Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is believed to be mostly transmitted by medium-to large-sized respiratory droplets, although airborne transmission may be possible in healthcare settings involving aerosol-generating procedures.\nExposure to respiratory droplets can theoretically be reduced by surgical mask usage.\nHowever, there is a lack of experimental evidence supporting surgical mask usage for prevention of COVID-19.\nMETHODS: We used a well-established golden Syrian hamster SARS-CoV-2 model.\nWe placed SARS-CoV-2-challenged index hamsters and naive hamsters into closed system units each comprising 2 different cages separated by a polyvinyl chloride air porous partition with unidirectional airflow within the isolator.\nThe effect of a surgical mask partition placed between the cages was investigated.\nBesides clinical scoring, hamster specimens were tested for viral load, histopathology, and viral nucleocapsid antigen expression.\nRESULTS: Noncontact transmission was found in 66.7% (10/15) of exposed naive hamsters.\nSurgical mask partition for challenged index or naive hamsters significantly reduced transmission to 25% (6/24, P = .018).\nSurgical mask partition for challenged index hamsters significantly reduced transmission to only 16.7% (2/12, P = .019) of exposed naive hamsters.\nUnlike the severe manifestations of challenged hamsters, infected naive hamsters had lower clinical scores, milder histopathological changes, and lower viral nucleocapsid antigen expression in respiratory tract tissues.\nCONCLUSIONS: SARS-CoV-2 could be transmitted by respiratory droplets or airborne droplet nuclei which could be reduced by surgical mask partition in the hamster model.\nThis is the first in vivo experimental evidence to support the possible benefit of surgical mask in prevention of COVID-19 transmission, especially when masks were worn by infected individuals.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Exposure to respiratory droplets can theoretically be reduced by surgical mask usage.\", \"Surgical mask partition for challenged index or naive hamsters significantly reduced transmission to 25% (6/24, P = .018).\", \"Surgical mask partition for challenged index hamsters significantly reduced transmission to only 16.7% (2/12, P = .019) of exposed naive hamsters.\"]}", "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\nPhotosensitized protein damage by dimethoxyphosphorus(V) tetraphenylporphyrin. For the purpose of the basic study of photodynamic therapy, the activity of the water-soluble P(V)porphyrin, dimethoxyP(V)tetraphenylporphyrin chloride (DMP(V)TPP), on photosensitized protein damage was examined. The quantum yield of singlet oxygen generation by DMP(V)TPP (0.64) was comparable with that of typical porphyrin photosensitizers. Absorption spectrum measurement demonstrated the binding interaction between DMP(V)TPP and human serum albumin, a water-soluble protein. Photo-irradiated DMP(V)TPP damaged the amino acid residue of human serum albumin, resulting in the decrease of the fluorescence intensity from the tryptophan residue of human serum albumin. A singlet oxygen quencher, sodium azide, could not completely inhibit the damage of human serum albumin, suggesting that the electron transfer mechanism contributes to protein damage as does singlet oxygen generation. The decrease of the fluorescence lifetime of DMP(V)TPP by human serum albumin supported the electron transfer mechanism. The estimated contribution of the electron transfer mechanism is 0.64. These results suggest that the activity of DMP(V)TPP can be preserved under lower oxygen concentration condition such as tumor.", "role": "user" }, { "content": "{\"Chemical\": [\"dimethoxyphosphorus(V) tetraphenylporphyrin\", \"DMP(V)TPP\", \"oxygen\", \"amino acid\", \"sodium azide\", \"tryptophan\", \"porphyrin\", \"dimethoxyP(V)tetraphenylporphyrin chloride\", \"P(V)porphyrin\"]}", "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 liquid liquid phase transition?\n\nContext: engaged in or are at least related to the physiological liquid-liquid phase transitions (LLPTs) leading to the formation of various proteinaceous membrane-less organelles (PMLOs), both normal and pathological.\nThe influence of membrane-free microcompartments resulting from crowding-induced liquid/liquid phase separation (LLPS) on the dynamic spatial organization of FtsZ, the main component of the bacterial division machinery, has been studied using several LLPS systems.\nwe hypothesize that intrinsically disordered proteins (IDPs) serve as important drivers of the intracellular liquid-liquid phase separations that generate various membrane-less organelles", "role": "user" }, { "content": "membrane-free microcompartments", "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. Male and female subjects must be 18 years of age or older and ambulatory. \n2. Females of child-bearing potential (FOCP) must have a negative serum beta human chorionic gonadotropin (HCG) pregnancy test. \n3. A documented history of severe Symptomatic Orthostatic Hypotension (SOH) that, in the judgment of the treating physician, has required treatment with midodrine HCl , and has been at a stable dose for at least 3 months. \n4. The subject has manifested at least 1 of the following symptoms while standing or had a medical history of 1 of the following when not treated for orthostatic hypotension (OH): dizziness, lightheadedness, feeling faint, or feeling like they might black out.", "role": "user" }, { "content": "{\"Condition\": [\"Symptomatic Orthostatic Hypotension (SOH)\", \"orthostatic hypotension (OH)\", \"feeling like they might black out\", \"lightheadedness\", \"dizziness\", \"child-bearing potential\", \"feeling faint\"], \"Device\": [], \"Drug\": [\"midodrine HCl\"], \"Measurement\": [\"serum beta human chorionic gonadotropin (HCG) pregnancy test\"], \"Mood\": [], \"Multiplier\": [\"1\", \"at least 1\"], \"Negation\": [\"not\"], \"Observation\": [], \"Person\": [\"female\", \"Females\", \"Male\", \"age\"], \"Procedure\": [\"treated\"], \"Qualifier\": [\"stable dose\", \"severe\"], \"ReferencePoint\": [], \"Scope\": [\"dizziness, lightheadedness, feeling faint, or feeling like they might black out\", \"Females of child-bearing potential\"], \"Temporal\": [\"for at least 3 months\"], \"Value\": [\"18 years or older\", \"negative\"], \"Visit\": [\"ambulatory\"]}", "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:\nCommon test generators fall into two categories. Generating test inputs at the unit level is fast, but can lead to false alarms when a function is called with inputs that would not occur in a system context. If a generated input at the system level causes a failure, this is a true alarm, as the input could also have come from the user or a third party; but system testing is much slower. In this paper, we introduce the concept of a test generation bridge, which joins the accuracy of system testing with the speed of unit testing. A Test Generation Bridge allows to combine an arbitrary system test generator with an arbitrary unit test generator. It does so by carving parameterized unit tests from system (test) executions. These unit tests run in a context recorded from the system test, but individual parameters are left free for the unit test generator to systematically explore. This allows symbolic test generators such as KLEE to operate on individual functions in the recorded system context. If the test generator detects a failure, we lift the failure-inducing parameter back to the system input; if the failure can be reproduced at the system level, it is reported as a true alarm. Our BASILISK prototype can extract and test units out of complex systems such as a Web Python SQLite C stack; in its evaluation, it achieves a higher coverage than a state-of-the-art system test generator.\n\nCited Abstract(s):\n[1]: The following section describes the tools we built to test the utilities. These tools include the fuzz (random character) generator, ptyjig (to test interactive utilities), and scripts to automate the testing process. Next, we will describe the tests we performed, giving the types of input we presented to the utilities. Results from the tests will follow along with an analysis of the results, including identification and classification of the program bugs that caused the crashes. The final section presents concluding remarks, including suggestions for avoiding the types of problems detected by our study and some commentary on the bugs we found. We include an Appendix with the user manual pages for fuzz and ptyjig.", "role": "user" }, { "content": "The idea of is an old one: To test a program @math , a producer @math will generate inputs for @math with the intent to cause it to fail. To find bugs, a producer need not be very sophisticated; as shown in the famous fuzzing'' paper of 1989, simple random strings can quickly crash programs [1] .", "role": "assistant" } ]

[ { "content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: We propose a deep attention-based framework to learn local appearance representations for person re-identification.\n\nKeyphrases: person re-identification images\n\nDataset description:\nVeRi-776: VeRi-776 is a vehicle re-identification dataset which contains 49,357 images of 776 vehicles from 20 cameras. The dataset is collected in the real traffic scenario, which is close to the setting of CityFlow.\nPRID2011: PRID 2011 is a person reidentification dataset that provides multiple person trajectories recorded from two different static surveillance cameras, monitoring crosswalks and sidewalks. The dataset shows a clean background, and the people in the dataset are rarely occluded.\nCUHK-PEDES: The CUHK-PEDES dataset is a caption-annotated pedestrian dataset. It contains 40,206 images over 13,003 persons.\nSYSU-MM01: The SYSU-MM01 is a dataset collected for the Visible-Infrared Re-identification problem. The images in the dataset were obtained from 491 different persons by recording them using 4 RGB and 2 infrared cameras.\nCUHK03: The CUHK03 consists of 14,097 images of 1,467 different identities, where 6 campus cameras were deployed for image collection and each identity is captured by 2 campus cameras. This dataset provides two types of annotations, one by manually labelled bounding boxes and the other by bounding boxes produced by an automatic detector.\nMarket-1501: Market-1501 is a large-scale public benchmark dataset for person re-identification. It contains 1501 identities which are captured by six different cameras, and 32,668 pedestrian image bounding-boxes obtained using the Deformable Part Models pedestrian detector.\n\nOptions:- A: VeRi-776 B: PRID2011 C: CUHK-PEDES D: SYSU-MM01 E: CUHK03 F: Market-1501", "role": "user" }, { "content": "[\"CUHK03\", \"Market-1501\"]", "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\nPolymorphisms of the CYP2D6 gene increase susceptibility to ankylosing spondylitis. Ankylosing spondylitis (AS) is a common and highly familial rheumatic disorder. The sibling recurrence risk ratio for the disease is 63 and heritability assessed in twins > 90%. Although MHC genes, including HLA-B27, contribute only 20-50% of the genetic risk for the disease, no non-MHC gene has yet been convincingly demonstrated to influence either susceptibility to the disease or its phenotypic expression. Previous linkage and association studies have suggested the presence of a susceptibility gene for AS close to, or within, the cytochrome P450 2D6 gene (CYP2D6, debrisoquine hydroxylase) located at chromosome 22q13.1. We performed a linkage study of chromosome 22 in 200 families with AS affected sibling-pairs. Association of alleles of the CYP2D6 gene was examined by both case-control and within-family means. For case-control studies, 617 unrelated individuals with AS (361 probands from sibling-pair and parent-case trio families and 256 unrelated non-familial sporadic cases) and 402 healthy ethnically matched controls were employed. For within-family association studies, 361 families including 161 parent-case trios and 200 affected sibling-pair families were employed. Homozygosity for poor metabolizer alleles was found to be associated with AS. Heterozygosity for the most frequent poor metabolizer allele (CYP2D6*4) was not associated with increased susceptibility to AS. Significant within-family association of CYP2D6*4 alleles and AS was demonstrated. Weak linkage was also demonstrated between CYP2D6 and AS. We postulate that altered metabolism of a natural toxin or antigen by the CYP2D6 gene may increase susceptibility to AS.", "role": "user" }, { "content": "{\"Disease\": [\"rheumatic disorder\", \"ankylosing spondylitis\", \"AS\", \"Ankylosing spondylitis\"]}", "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: We perform the same design one more time to predict boxes for the final scale. Thus our predictions for the 3rd scale benefit from all the prior computation as well as fine-grained features from early on in the network. In the past YOLO struggled with small objects. However, now we see a reversal in that trend. With the new multi-scale predictions we see YOLOv3 has relatively high AP{}_{S} performance. However, it has comparatively worse performance on medium and larger size objects. More investigation is needed to get to the bottom of this.\n\nQuestion: In paper authors make the predictions at three different scales, but what is advantage of making object detections at different scales?", "role": "user" }, { "content": "By using multi-scaled prediction, YOLOv3 has improved performance for small objects. Also, the subsequent scales benefit from previous scales and the previous features from earlier layers.", "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 supervised model for image classification.\n\nKeyphrases: image classification images\n\nDataset description:\nSNIPS: The SNIPS Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity: SearchCreativeWork (e.g. Find me the I, Robot television show), GetWeather (e.g.\nDCASE 2014: DCASE2014 is an audio classification benchmark.\nI-HAZE: The I-Haze dataset contains 25 indoor hazy images (size 2833×4657 pixels) training. It has 5 hazy images for validation along with their corresponding ground truth images.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\n\nOptions: A: SNIPS B: DCASE 2014 C: I-HAZE D: ImageNet", "role": "user" }, { "content": "ImageNet", "role": "assistant" } ]

[ { "content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: The dataset bias is the main cause of performance degradation of facial expression recognition algorithms\n\nKeyphrases: facial expression recognition images lab-controlled real-world\n\nDataset description:\nAffectNet: AffectNet is a large facial expression dataset with around 0.4 million images manually labeled for the presence of eight (neutral, happy, angry, sad, fear, surprise, disgust, contempt) facial expressions along with the intensity of valence and arousal.\nFRGC: The data for FRGC consists of 50,000 recordings divided into training and validation partitions. The training partition is designed for training algorithms and the validation partition is for assessing performance of an approach in a laboratory setting.\nSFEW: The Static Facial Expressions in the Wild (SFEW) dataset is a dataset for facial expression recognition. It was created by selecting static frames from the AFEW database by computing key frames based on facial point clustering.\nMegaFace: MegaFace was a publicly available dataset which is used for evaluating the performance of face recognition algorithms with up to a million distractors (i.e., up to a million people who are not in the test set). MegaFace contains 1M images from 690K individuals with unconstrained pose, expression, lighting, and exposure.\nFERG: FERG is a database of cartoon characters with annotated facial expressions containing 55,769 annotated face images of six characters. The images for each character are grouped into 7 types of cardinal expressions, viz.\nExpW: The Expression in-the-Wild (ExpW) dataset is for facial expression recognition and contains 91,793 faces manually labeled with expressions. Each of the face images is annotated as one of the seven basic expression categories: “angry”, “disgust”, “fear”, “happy”, “sad”, “surprise”, or “neutral”.\n\nOptions:- A: AffectNet B: FRGC C: SFEW D: MegaFace E: FERG F: ExpW", "role": "user" }, { "content": "[\"AffectNet\", \"SFEW\"]", "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:\nThe effect of acupuncture in chronic intractable epilepsy.\nAbstract 1:\nWe examined the effect of acupuncture on epileptic seizures in humans in a controlled clinical setting. Treatment was administered by two Chinese professors of acupuncture. Effect was measured by change in seizure frequency. Twenty-nine patients with chronic intractable epilepsy completed the study. They were randomized in two groups; 15 were given classical acupuncture and 14 were given sham acupuncture. There was a reduction in seizure frequency in both groups, which did not reach a level of statistical significance. There was also an increase in the number of seizure-free weeks in both groups, which reached a level of significance in the sham group. Thus, we have not been able to prove a beneficial effect of acupuncture in chronic intractable epilepsy.\n Copyright 1999 BEA Trading Ltd.\n\n\nTitle 2:\n[Clinical observation on catgut implantation at acupoint for treatment of general paroxysmal epilepsy].\nAbstract 2:\nTo search for an effective method for treatment of general paroxysmal epilepsy.\n One hundred cases were randomly divided into a treatment group of 50 cases treated with catgut implantation at Dazhui (GV 14), Jinsuo (GV 8), Fenglong (ST 40), etc., and a control group of 50 cases treated with oral administration of sodium valproate.\n The scores for epilepsy after treatment significantly improved in the both groups (P<0.05); the total effective rate was 94.0% in the treatment group and 82.0% in the control group with a significant difference between the two groups (P<0.05).\n Catgut implantation at acupoint has a definite therapeutic effect on general paroxysmal epilepsy with no adverse effect.", "role": "user" }, { "content": "The current evidence does not support acupuncture for treating epilepsy.", "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\nDynamics of NO rebinding to the heme domain of NO synthase-like proteins from bacterial pathogens.\nSome Gram-positive bacterial pathogens harbor a gene that encodes a protein (HNS, Heme domain of NO Synthase-like proteins) with striking sequence identity to the oxygenase domain of mammalian NO synthases (NOS). However, they lack the N-terminal and the Zn-cysteine motif participating to the stability of an active dimer in the mammalian isoforms. The unique properties of HNS make it an excellent model system for probing how the heme environment tunes NO dynamics and for comparing it to the endothelial NO synthase heme domain (eNOS(HD)) using ultrafast transient spectroscopy. NO rebinding in HNS from Staphylococcus aureus (SA-HNS) is faster than that measured for either Bacillus anthracis (BA-HNS) or for eNOS(HD) in both oxidized and reduced forms in the presence of arginine. To test whether these distinct rates arise from different energy barriers for NO recombination, we measured rebinding kinetics at several temperatures. Our data are consistent with different barriers for NO recombination in SA-HNS and BA-HNS and the presence of a second NO-binding site. The hypothesis that an additional NO-binding cavity is present in BA-HNS is also consistent with the effect of the NO concentration on its rebinding. The lack of the effect of NO concentration on the geminate rebinding in SA-HNS could be due to an isolated second site. We confirm the existence of a second NO site in the oxygenase domain of the reduced eNOS as previously hypothesized [A. Slama-Schwok, M. Negrerie, V. Berka, J.C. Lambry, A.L. Tsai, M.H. Vos, J.L. Martin, Nitric oxide (NO) traffic in endothelial NO synthase. Evidence for a new NO binding site dependent on tetrahydrobiopterin? J. Biol. Chem. 277 (2002) 7581-7586]. This site requires the presence of arginine and BH(4); and we propose that NO dynamic and escape from eNOS is regulated by the active site H-bonding network connecting between the heme, the substrate, and cofactor.", "role": "user" }, { "content": "{\"Chemical\": [\"NO\", \"H\", \"BH(4)\", \"N\", \"tetrahydrobiopterin\", \"Zn-cysteine\", \"Nitric oxide\", \"arginine\"], \"Protein\": [\"endothelial NO synthase\", \"eNOS(HD)\", \"BA-HNS\", \"N-terminal and the Zn-cysteine motif\", \"eNOS\", \"heme domain of NO synthase-like proteins\", \"oxygenase domain\", \"HNS\", \"reduced eNOS\", \"NOS\", \"SA-HNS\", \"endothelial NO synthase heme domain\", \"Heme domain of NO Synthase-like proteins\", \"mammalian NO synthases\"]}", "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\nNext, we applied a method based on previously published literature by Aloy and Russell [38], in which they derived Su et al.", "role": "user" }, { "content": "Method", "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: When someone who has COVID-19 coughs, sneezes, or talks, they send tiny droplets with the coronavirus into the air. That's where a mask can help.\n\nAbstract:\nThe COVID‐19 pandemic caused by the novel coronavirus SARS‐CoV‐2 has claimed many lives worldwide.\nWearing medical masks or N95 masks (namely N95 respirators) can slow the virus spread and reduce the infection risk.\nReuse of these masks can minimize waste, protect the environment, and help to solve the current imminent shortage of masks.\nDisinfection of used masks is needed for reuse of them with safety, but improper decontamination can damage the blocking structure of masks.\nIn this study, we demonstrated, using avian coronavirus of infectious bronchitis virus to mimic SARS‐CoV‐2, that medical masks and N95 masks remained their blocking efficacy after being steamed on boiling water even for 2 hours.\nWe also demonstrated that three brands of medical masks blocked over 99% viruses in aerosols.\nThe avian coronavirus was completely inactivated after being steamed for 5 minutes.\nTogether, this study suggested that medical masks are adequate for use on most social occasions, and both medical masks and N95 masks can be reused for a few days with steam decontamination between use.\nThis article is protected by copyright.\nAll rights reserved.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Wearing medical masks or N95 masks (namely N95 respirators) can slow the virus spread and reduce the infection risk.\", \"We also demonstrated that three brands of medical masks blocked over 99% viruses in aerosols.\", \"The avian coronavirus was completely inactivated after being steamed for 5 minutes.\", \"Together, this study suggested that medical masks are adequate for use on most social occasions, and both medical masks and N95 masks can be reused for a few days with steam decontamination between use.\"]}", "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\nImproved local control of invasive bladder cancer by concurrent cisplatin and preoperative or definitive radiation . The National Cancer Institute of Canada Clinical Trials Group . PURPOSE A prospective randomized trial was conducted to determine whether the addition of concurrent cisplatin to preoperative or definitive radiation therapy in patients with muscle-invasive bladder cancer improved local control or survival . PATIENTS AND METHODS Ninety-nine eligible patients with T2 to T4b transitional cell bladder cancer participated , 64 % with cT3b or cT4 . Patients and their physicians selected either definitive radiotherapy or precystectomy radiotherapy ; patients were then randomly allocated to receive intravenous cisplatin 100 mg/m2 at 2-week intervals for three cycles concurrent with pelvic radiation , or to receive radiation without chemotherapy . Patients were stratified by clinical tumor stage and by radiation plan . The median follow-up duration is 6.5 years . RESULTS The occurrence of distant metastases was the same in both study arms . However , 25 of 48 control patients have had a first recurrence in the pelvis , compared with 15 of 51 cisplatin-treated patients ( P = .036 ) . The pelvic relapse rate in the two groups was significantly reduced by concurrent cisplatin ( P = .038 , log-rank test ) and this effect was preserved in a stepwise Cox regression model of prognostic factors ( hazards ratio , 0.50 ; 90 % confidence interval [ CI ] , 0.29 to 0.86 ; P = .036 ) . The hazard reduction was similar for both radiation plans . Pretreatment leukocytosis and high clinical stage were independent adverse factors in a Cox model of overall survival , but the effect of cisplatin was not significant . CONCLUSION Concurrent cisplatin may improve pelvic control of locally advanced bladder cancer with preoperative or definitive radiation , but has not been shown to improve overall survival . The use of concurrent cisplatin had no detectable effect on distant metastases .", "role": "user" }, { "content": "{\"Intervention\": [\"preoperative\", \"and\", \"cisplatin\", \"radiotherapy\", \"Concurrent cisplatin\", \"preoperative or definitive radiation\", \"cisplatin-treated\", \"intravenous cisplatin\", \"definitive radiation\", \"precystectomy radiotherapy\", \"concurrent with pelvic radiation\", \"concurrent cisplatin\", \"receive radiation without chemotherapy\", \"concurrent cisplatin to preoperative\"], \"Outcome\": [\"occurrence of distant metastases\", \"overall survival\", \"first recurrence\", \"hazard reduction\", \"pelvic relapse rate\", \"pelvic control\", \"local control or survival\"], \"Participant\": [\"muscle-invasive bladder cancer\", \"64 %\", \"Ninety-nine\", \"T2 to T4b transitional cell bladder cancer\"]}", "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\nTransparent nanostructured cellulose acetate films based on the self assembly of PEO-b-PPO-b-PEO block copolymer In this study fabrication and characterization of transparent nanostructured composite films based on cellulose triacetate (CTA) and poly(ethylene oxide)-b-poly(propylene oxide)-b-poly(ethylene oxide) (EPE) triblock copolymer were presented. The effect of the addition of EPE triblock copolymer on the thermal stability, morphology, and mechanical properties of cellulose triacetate films was investigated. The triblock EPE was chosen since PEO blocks interact favorably with CTA, whereas, PPO blocks remain immiscible which provokes a microphase separation. This allows to obtain EPE / CTA composite films with ordered microphase-separated structures where PPO spherical microdomains are well-dispersed in PEO / CTA matrix by simple solvent - evaporation process. During this process, PEO block chains selectively interact with CTA by strong interpolymer hydrogen-bonding while PPO block microseparated. The addition even 40wt% of EPE leads to nanostructured EPE / CTA composite. The cytotoxicity assay of CTA and EPE / CTA composite films confirm non-toxic character of designed transparent nanostructured composites based on sustainable matrices.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"cellulose acetate\", \"poly(ethylene oxide)-b-poly(propylene oxide)-b-poly(ethylene oxide) (EPE) triblock copolymer\", \"films\", \"PPO blocks\", \"PEO\", \"interpolymer\", \"matrix\", \"PPO\", \"PPO block\", \"EPE triblock copolymer\", \"cellulose triacetate\", \"PEO blocks\", \"triblock EPE\", \"CTA\", \"solvent\", \"matrices\", \"PEO-b-PPO-b-PEO block copolymer\", \"EPE\", \"PEO block chains\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [], \"Food\": [], \"HealthCareActivity\": [\"cytotoxicity assay\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"spherical\", \"structures\"], \"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:\nShort-term recovery after subtotal and total abdominal hysterectomy--a randomised clinical trial.\nAbstract 1:\nTo determine whether the day-by-day postoperative recovery differs between women undergoing subtotal and total abdominal hysterectomy, and to analyse factors associated with postoperative recovery and sick leave.\n A prospective, open, randomised multicentre trial.\n Seven hospitals and one private clinic in the south-east of Sweden.\n Two-hundred women scheduled for hysterectomy for benign conditions were enrolled in the study, and 178 women completed the study. Ninety-four women were randomised to subtotal abdominal hysterectomy; 84 women were randomised to total abdominal hysterectomy.\n The day-by-day recovery of general wellbeing was measured on a visual analogue scale in a diary 7 days preoperatively and 35 days postoperatively. Psychometric measurements included depression, anxiety and general psychological wellbeing.\n Effects of operating method and preoperative wellbeing on the day-by-day recovery and duration of sick leave.\n No significant difference was found in the day-by-day recovery between operating methods. The day-by-day recovery of general wellbeing and duration of sick leave was strongly associated with the occurrence of minor complications, but not with major complications. The level of psychological wellbeing preoperatively was strongly associated with the day-by-day recovery of general wellbeing and duration of sick leave.\n Day-by-day recovery of general wellbeing is no faster in subtotal versus total abdominal hysterectomy. Independent of operation method there is an interaction between preoperative psychological wellbeing, postoperative recovery of general wellbeing and the duration of sick leave. Postoperative complications and preoperative psychological wellbeing are strong determinants for the duration of sick leave. There is a need for intervention studies with a focus on complications and preoperative wellbeing.\n\n\nTitle 2:\nRandomised controlled trial of total compared with subtotal hysterectomy with one-year follow up results.\nAbstract 2:\nTo compare total abdominal hysterectomy and subtotal abdominal hysterectomy performed for benign uterine diseases.\n Randomised, controlled, unblinded trial with central, computer-generated randomisation.\n Danish trial performed in 11 departments of gynaecology.\n Women referred for benign uterine diseases were randomised to total abdominal hysterectomy (n = 158) or subtotal abdominal hysterectomy (n = 161). One-year follow up questionnaires had a response rate of 87%.\n Patients were followed by strict data collection procedures, including postal questionnaires. The results after one year of follow up were analysed by intention-to-treat analyses.\n (1) Primary: urinary incontinence and (2) secondary: post-operative complications, quality of life (SF-36), constipation, prolapse of the vaginal vault/cervical stump, satisfaction with sexual life, pelvic pain and vaginal bleeding.\n A significantly (P = 0.043) smaller proportion of women had urinary incontinence one year after total abdominal hysterectomy compared with subtotal abdominal hysterectomy [9% vs 18% (OR 2.08, 95% CI 1.01-4.29)]. The lower proportion of incontinent women in the total abdominal hysterectomy group was a result of a higher proportion of symptom relief (total abdominal hysterectomy: 20/140, subtotal abdominal hysterectomy: 14/136) as well as a lower proportion of women with new symptoms (total abdominal hysterectomy: 3/140, subtotal abdominal hysterectomy: 10/137). Twenty-seven women (20%) from the subtotal abdominal hysterectomy group had vaginal bleeding and two of them had to have their cervix removed. No other clinically important differences were found between the two hysterectomy methods.\n A smaller proportion of women suffered from urinary incontinence after total abdominal hysterectomy than after subtotal abdominal hysterectomy one year post-operatively.\n\n\nTitle 3:\nA randomized trial comparing changes in sexual health and psychological well-being after subtotal and total hysterectomies.\nAbstract 3:\nTo evaluate changes in sexual health and psychological well-being one year after subtotal and total hysterectomies.\n Prospective randomized controlled trial.\n One hundred and thirty-two premenopausal patients scheduled for hysterectomy without planned oophorectomy for benign disorders and without a history of cervical dysplasia or symptomatic prolapse were randomized to total (n = 66) or subtotal hysterectomy (n = 66). The McCoy Female Sexuality Questionnaire was used to evaluate changes in sexual health and the Psychological General Well-Being index was used to evaluate changes in psychological well-being. Differences in outcome before and one year after the hysterectomy were calculated for each individual, and changes compared between the groups.\n Women who had subtotal hysterectomy (SH) reported a significantly greater positive change in frequency of orgasm and sexual pleasure as compared with women who had total hysterectomy (TH) (mean values +/- standard deviation (SD), orgasm: SH: 0.4 +/- 1.1; TH: -0.2 +/- 0.9, p = 0.012, sexual enjoyment: SH 0.3 +/- 1.5; TH: -0.3 +/- 1.3, p = 0.039). There was a significantly greater general health gain for the women who underwent subtotal hysterectomy as compared with total hysterectomy (mean values +/- SD SH: 1.2 +/- 2.3; TH: 0.3 +/- 1.6, p = 0.03). The total score did not show a difference.\n Women undergoing subtotal hysterectomy experience a greater positive change in the frequency of orgasm and extent of sexual pleasure after surgery than women undergoing total hysterectomy, but the results must be interpreted with caution.\n\n\nTitle 4:\nA randomized comparison of total or supracervical hysterectomy: surgical complications and clinical outcomes.\nAbstract 4:\nTo compare surgical complications and clinical outcomes after total versus supracervical abdominal hysterectomy for control of abnormal uterine bleeding, symptomatic uterine leiomyomata, or both.\n We conducted a randomized intervention trial in four US clinical centers among 135 patients who had abdominal hysterectomy for symptomatic uterine leiomyomata, abnormal uterine bleeding refractory to hormonal treatment, or both. Patients were randomly assigned to receive a total or supracervical hysterectomy performed using the surgeon's customary technique. Using an intention-to-treat approach, we compared surgical complications and clinical outcomes for 2 years after randomization.\n Sixty-eight participants were assigned to supracervical hysterectomy (SCH) and 67 to total abdominal hysterectomy (TAH). Hysterectomy by either technique led to statistically significant reductions in most symptoms, including pelvic pain or pressure, back pain, urinary incontinence, and voiding dysfunction. Patients randomly assigned to (SCH) tended to have more hospital readmissions than those randomized to TAH, but this difference was not statistically significant. There were no statistically significant differences in the rate of complications, degree of symptom improvement, or activity limitation. Participants weighing more than 100 kg at study entry were twice as likely to be readmitted to the hospital during the 2-year follow-up period (relative risk [RR] 2.18, 95% confidence interval [CI] 1.06, 4.48, P=.034).\n We found no statistically significant differences between (SCH) and TAH in surgical complications and clinical outcomes during 2 years of follow-up.\n\n\nTitle 5:\nThe psychosocial outcomes of total and subtotal hysterectomy: A randomized controlled trial.\nAbstract 5:\nCurrent controversies involve the adverse effects of hysterectomy on women's psychosocial functioning and whether subtotal as opposed to total hysterectomy mitigates these effects.\n To investigate the psychosocial effects of hysterectomy by examining sexual, pain, and psychological outcomes of total vs. subtotal hysterectomy in a randomized controlled trial.\n Patients suffering from benign gynecological conditions were randomly assigned to one of two groups: (i) total hysterectomy, that is, laparoscopic assisted vaginal hysterectomy (TOT, N = 32); or (ii) subtotal hysterectomy, that is, supracervical laparoscopic hysterectomy (SUB, N = 31). Both groups were premenopausal and underwent hysterectomy without concurrent oophorectomy. Two premenopausal control groups: (i) minor gynecological surgery (SURG-CON, N = 30); and (ii) healthy nonsurgical controls (NORM-CON, N = 40), were also tested. All surgical groups were assessed 2-3 weeks before surgery and then 6-7 months afterward; the nonsurgical control group was assessed at the time of recruitment and 6-7 months later.\n Assessments included semistructured interviews, standardized questionnaires, and standardized gynecological examinations.\n For the TOT group, sexual drive, arousal, and sexual behavior significantly improved postoperatively. For the SUB group, sexual behavior and overall sexual functioning significantly improved. For both TOT and SUB groups, unprovoked pain in the abdomen and pain in the abdomen during gynecological examinations was significantly reduced. For both TOT and SUB groups, overall psychological functioning did not significantly change postoperatively. Although between 3% and 16% of women undergoing hysterectomy reported adverse changes in psychosocial well-being after surgery, similar percentages of women in the control groups reported such effects.\n Hysterectomy resulted in a consistent reduction in abdominal pain, some improvement in sexual functioning, but no change in overall psychological functioning. There was no evidence supporting the idea that subtotal hysterectomy produced more favorable psychosocial outcomes than total hysterectomy nor was there any evidence that either type of hysterectomy resulted in adverse effects.\n\n\nTitle 6:\nOutcomes of total versus subtotal abdominal hysterectomy.\nAbstract 6:\nThere is still controversy about the best technique for hysterectomy to reduce postoperative adverse effects. This randomized clinical study in Babol, Islamic Republic of Iran, compared some clinical complications and sexual functioning following subtotal (SAH) and total abdominal hysterectomy (TAH). A total of 150 women (50 allocated to SAH and 100 to TAH) were followed up at 6 months postoperatively. Length of hospitalization was 4.40 (SD 1.90) days after SAH and 4.48 (SD 1.67) days after TAH. Haemoglobin level, postoperative fever, symptoms of dyspareunia and frequency of sexual intercourse were not significantly different between the 2 groups of women. SAH did not show any significant benefits over TAH.\n\n\nTitle 7:\nHysterectomy and women satisfaction: total versus subtotal technique.\nAbstract 7:\nThe impact of different surgical procedures on women's satisfaction after hysterectomy is a topical issue. The aim of this study was to investigate the impact of sub-total and total hysterectomy on women's satisfaction, evaluated with questionnaire assessment of sexual activity, body image, and health status.\n A prospective, randomized, non-blind study was conducted. In the study period of 3 years, 105 women were enrolled and completed the questionnaires [EuroQol (EQ-5D), body image scale (BIS), sexual activity questionnaire] 2 weeks before and 1 year after surgery.\n Both total and sub-total hysterectomy resulted with improvements in the women's sexual satisfaction (1 year after surgery), but no statistically significant differences were reached between the two groups. A highly significant difference (P < 0.001) in the perception of the body image between total and sub-total hysterectomy, at 1 year after surgery, was underlined. The health-related quality of life resulted significantly better in the \"sub-total hysterectomy\" group 1 year after surgery (P < 0.05).\n Considering these results, why should a total hysterectomy be performed, if the women's satisfaction seems to be higher using the sub-total technique? In our opinion, the woman undergoing hysterectomy for benign conditions must be counseled regarding the differences between the two techniques and, when possible, a choice must be offered to the woman.\n\n\nTitle 8:\nOutcomes after total versus subtotal abdominal hysterectomy.\nAbstract 8:\nIt is uncertain whether subtotal abdominal hysterectomy results in better bladder, bowel, or sexual function than total abdominal hysterectomy.\n We conducted a randomized, double-blind trial comparing total and subtotal abdominal hysterectomy in 279 women referred for hysterectomy because of benign disease; most of the women were premenopausal. The main outcomes were measures of bladder, bowel, and sexual function at 12 months. We also evaluated postoperative complications.\n The rates of urinary frequency (urination more than seven times during the day) were 33 percent in the subtotal-hysterectomy group and 31 percent in the total-hysterectomy group before surgery, and they fell to 24 percent and 20 percent, respectively, at 12 months (P=0.03 for the change over time within each group; P=0.84 for the interaction between the treatment assignment and time). The reduction in nocturia and stress incontinence and the improvement in bladder capacity were similar in the two groups. The frequency of bowel symptoms (as indicated by reported constipation and use of laxatives) and measures of sexual function (including the frequency of intercourse and orgasm and the rating of the sexual relationship with a partner) did not change significantly in either group after surgery. The women in the subtotal-hysterectomy group had a shorter hospital stay (5.2 days, vs. 6.0 in the total-hysterectomy group; P=0.04) and a lower rate of fever (6 percent vs. 19 percent, P<0.001). After subtotal abdominal hysterectomy, 7 percent of women had cyclical bleeding and 2 percent had cervical prolapse.\n Neither subtotal nor total abdominal hysterectomy adversely affects pelvic organ function at 12 months. Subtotal abdominal hysterectomy results in more rapid recovery and fewer short-term complications but infrequently causes cyclical bleeding or cervical prolapse.\n Copyright 2002 Massachusetts Medical Society", "role": "user" }, { "content": "This review has not confirmed the perception that subtotal hysterectomy offers improved outcomes for sexual, urinary or bowel function when compared with total abdominal hysterectomy. Women are more likely to experience ongoing cyclical bleeding up to a year after surgery with subtotal hysterectomy compared to total hysterectomy.", "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:\nTrapping the Transition State in a [2,3]-Sigmatropic Rearrangement by Applying Pressure\n\nPaper sections:\n\n<p>The rearrangement of allylic sulfoxides to allylic sulfenate esters is a popular example of [2,3]sigmatropic rearrangements. [1][2][3] This type of reaction is also known as Mislow-Evans rearrangement [4][5][6][7][8][9][10][11] and is widely used in asymmetric synthesis due to the possibility of chirality transfer from the carbon bearing the sulfoxide group to the alcohol resulting from a subsequent reaction with an appropriate thiophile (Figure 1A). Hence, the Mislow-Evans rearrangement is a popular tool in the synthesis of bioactive substances and natural products like terpenes, [12] vernolepin, [13,14] amphidinol 3, [15] and pyrenolide D. [16] The transition state of the Mislow-Evans rearrangement has attracted considerable attention, because it determines the stereochemistry of the reaction. [17] It has been found that the Mislow-Evans rearrangement proceeds via a five-membered cyclic transition state (Figure 1A). [6,11,[17][18][19] By using quantum chemical methods, we here demonstrate that the cyclic transition state of the Mislow-Evans rearrangement becomes a minimum under pressures between 100 and 150 GPa, which is a pressure range that is accessible with modern diamond-anvil cell technology. [20] While the \"trapping\" of a transition state has been achieved before with mechanical force, [21] to the best of our knowledge this is the first time that hydrostatic pressure has been used for this purpose. The possibility of transforming a transition state into a minimum on the potential energy surface paves the way for isolating and characterizing this transient chemical species and will more broadly open up new possibilities in chemical synthesis.</p><p>Several quantum chemical methods for the application of hydrostatic pressure to molecules during geometry optimizations have been reported. [22][23][24][25][26][27][28][29] We apply the eXtended Hydrostatic Compression Force Field (X-HCFF) approach [28] in this paper, since this method has been used successfully to predict structural parameters and chemical reactions in the GPa regime.</p><p>Furthermore, Born-Oppenheimer Molecular Dynamics (BOMD) simulations can be conducted at a user-defined pressure with X-HCFF. B3LYP [30][31][32] /6-31G(d) [33] is used as the electronic structure method throughout. Further computational details can be found in the Supporting Information.</p><p>While, according to our calculations, the cyclic transition state of the model Mislow-Evans reaction considered in this paper (Figure 1B) lies 12.0 kcal/mol above the educt, geometry optimization with X-HCFF at a pressure of 120 GPa yields a five-membered cyclic structure (Figure 1C). This compressed geometry is remarkably close to the pressure-free transition state, with a mean RMSD of only 0.3 Å between the ring atoms in the compressed and the pressure-free geometries (Table S1). While transition states have been found to disappear under pressure, [27] leading to the formation of the product of a chemical reaction with no further energy input, our calculations demonstrate that pressure can be used to transform a transition state into a minimum on the potential energy surface. Despite the intriguing notion that a transition state can be isolated, this finding is intuitive, since the transition state of the Mislow-Evans rearrangement has a more condensed geometry than both the educt and the product. A preference of the transition state geometry is therefore expected at elevated pressures.</p><p>To investigate the formation of the five-membered ring in the model Mislow-Evans reaction under pressure more closely, we conducted ten individual BOMD simulations, in which we increased the pressure in increments of 10 GPa every 96.8 fs. Two representative distances, S2).</p><p>The possibility to either form the product or to recover the educt is the expected behavior for a system that is held artificially at the transition state, since it can move in either direction when the constraint is lifted, depending on the instantaneous nuclear velocities that are present upon decompression. In seven out of the ten simulations, the formation of the product is observed, whereas the educt is recovered in the remaining three simulations. This observation lends further evidence that a transition state was isolated using pressure. The pressure required to form the five-membered ring ranges between 100 and 150 GPa, depending on the trajectory.</p><p>Details on each individual trajectory are given in the Supporting Information (Table S2).</p><p>The formation of the five-membered ring and its transformation to either the product or the educt of the Mislow-Evans rearrangement upon decompression can also be understood in terms of changes in Mayer bond orders [34,35] throughout the BOMD simulations (Figure 4). Analogous effects can be observed in the propagation of electron densities at the bond critical points throughout the BOMD trajectories (Figure S3): In addition to an overall increase in electron density with increasing pressure, which is due to the compressed nuclear scaffold and the shortened bonds, shifts in electron density mark the formation of the five-membered cyclic structure at high pressure and its transformation to either the product or the educt of the Mislow-Evans rearrangement upon decompression.</p><p>The quantum chemical calculations and BOMD simulations presented in this study demonstrate that the five-membered cyclic transition state of a model Mislow-Evans rearrangement can be \"trapped\" by applying hydrostatic pressures in the range between 100 and 150 GPa.</p><p>Decompression leads to the formation of the product of the rearrangement in seven out of ten trajectories, whereas the educt is recovered in the remaining three simulations. Our future studies will focus on the influence of environmental factors like chemical substitution [36] or the solvent in a multiscale simulation setup. We hope that our calculations spark the interest in experimental studies on the barochemical isolation of transitory species in sigmatropic rearrangements and other chemical reactions. We speculate that transition states can generally be isolated by using pressure if the transition state geometries are more condensed than both the educt and the product of the reaction.</p>", "role": "user" }, { "content": "Transition states are of central importance in chemistry. While they are, by definition, transient species, it has been shown before that it is possible to \"trap\" transition states by applying stretching forces. We here demonstrate that the task of transforming a transition state into a minimum on the potential energy surface can be achieved by using hydrostatic pressure. We apply the computational eXtended Hydrostatic Compression Force Field (X-HCFF) approach to the educt of a [2,3]-sigmatropic rearrangement in both static and dynamic calculations and find that the five-membered cyclic transition state of this reaction becomes a minimum at pressures in the range between 100 and 150 GPa. Slow decompression leads to a 70:30 mix of the product and the educt of the sigmatropic rearrangement. Our findings are discussed in terms of geometric parameters and electronic rearrangements throughout the reaction. We speculate that the trapping of transition states by using pressure is generally possible if the transition state of a chemical reaction has a more condensed geometry than both the educt and the product, which paves the way for new ways of initiating chemical reactions.", "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\nHypertensive crises have resulted when sympathomimetic amines have been used concomitantly within14 days following use of monoamine oxidase inhibitors. DIDREX should not be used concomitantly with other CNS stimulants. Amphetamines may decrease the hypotensive effect of antihypertensives. Amphetamines may enhance the effects of tricyclic antidepressants. Urinary alkalinizing agents increase blood levels and decrease excretion of amphetamines. Urinary acidifying agents decrease blood levels and increase excretion of amphetamines.", "role": "user" }, { "content": "{\"Brand\": [\"DIDREX\"], \"Drug\": [\"Urinary acidifying\"], \"DrugGroup\": [\"monoamine oxidase inhibitors\", \"CNS stimulants\", \"tricyclic antidepressants\", \"Amphetamines\", \"sympathomimetic amines\", \"antihypertensives\", \"amphetamines\"], \"UnapprovedDrug\": []}", "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:\nw uma type binary systems are cool short - period binary systems in which both of its two components fill the critical roche lobes and share a common convective envelope .\ntheir ew - type light curves vary continuously and the depths of the primary and secondary minima are almost equal . it is found that about @xmath8 of the eclipsing binaries around the solar system are w uma type contact binary systems @xcite .\n@xcite divided the w uma type binary systems into two subclasses : a - subtype and w - subtype .\nthe a - subtype w uma systems are also called early - type contact binaries with their spectral types usually earlier than f0 and the more massive stars are the hotter ones .\nthe w - subtype systems are also called late type contact binaries with their spectral types to be f and g type or even later .\nthe less massive components are the hotter ones in the w - subtype systems .\nthe formation and evolutionary theories of contact binaries are still open issues .\nw uma type systems are very important targets in this research field .\ntherefore , more and more fundamental information about w uma type systems , both photometric and spectroscopic analysis , are urgently needed . , also named or ,\nis a newly discovered w uma type contact binary system detected in the field of view of v563 lyr .\nthere is neither photometric solution nor spectroscopic observation about this target published before . in the present work , @xmath0 @xmath1 @xmath2 and @xmath3 bands light curves of are analyzed with the wilson - devinney ( w - d ) code for the first time .\nthe basic physical parameters of this system is obtained and its formation and evolutionary scenario are figured out , which will improve our understanding on the w uma type binary systems .\nthe ccd photometric observations of the eclipsing binary were carried out over 7 nights on september and october 2012 ( hjd 2456199 to hjd 2456207 ) using an sbig st-10xme ccd camera attached to the 0.4 m cassegrain reflecting telescope in the university of athens observatory , greece @xcite . during the observations , the broadband johnson - cousins @xmath0 @xmath1 @xmath2 @xmath3 filters were used . was chosen as the comparison star .\na total of 358 points in @xmath0 filter , 395 in @xmath1 filter , 383 in @xmath9 filter and 417 in @xmath10 filter were collected , respectively . the coordinates and brightness ( in @xmath1 band ) of the variable ,\nthe comparison stars are listed in table [ coordinates ] .\nthe identification map of in the field of view of is shown in fig . 1 . .\ncoordinates of and the comparison star [ cols=\"^,^,^,^,^\",options=\"header \" , ] and @xmath11 for light curves of .\n@xmath12 is the resulting sum of weighted square deviations .\nit is shown that the minimum is obtained at q = 2.65.,width=453 ] @xmath1 @xmath2 and @xmath3 bands of .\nthe standard deviation of the fitting residuals is 0.069 mag for @xmath0 band , 0.052 mag for @xmath1 band , 0.040 mag for @xmath2 band and 0.036 mag for @xmath3 band , respectively.,width=377 ]\nthe ccd photometric light curves of in @xmath0 @xmath1 @xmath2 @xmath3 bands are analyzed simultaneously with the w - d code ( version 2013 ) .\nour solutions suggest that is a w - subtype shallow contact ( @xmath6 ) binary system with its mass ratio to be @xmath4 , where shallow \" is defined when the degree of contact is lower than @xmath13 @xcite .\nthe temperature difference between its two components is @xmath5 which may imply that is a newly formed contact binary system .\nit is just under geometrical contact and will evolve to be a thermal contact binary system .\nthe less massive star contributes about @xmath14 of the total luminosity in the binary system . during the calculations\n, we also set @xmath15 as an adjustable parameter in the w - d code .\nhowever , we havent detected the contribution of the third light in the light curves .\nthe high orbital inclination ( @xmath7 ) implies that is a total eclipsing binary system and the photometric parameters obtained by us are quite reliable . by assuming that the primary star in is a normal main sequence star , we estimate the mass of the primary star to be @xmath16 @xcite . considering the mass ratio of @xmath4 derived by us , the mass of the secondary star is calculated to be @xmath17 .\nthe radii and luminosity of the two components are determined to be : @xmath18 , @xmath19 , @xmath20 and @xmath21 .\nthe orbital semi - major axis of is calculated to be @xmath22 .\nthe formation and evolutionary theories of contact binaries are still unclear .\nthe most possible scenario is that they are formed from initially detached binary systems through the angular momentum loss ( aml ) via the magnetic wind @xcite .\na late type star component may have played an important role in the formation process @xcite .\ntherefore , the w uma type systems are ideal targets to test this theory and the photometric analyses of the w uma type systems will provide invaluable information on the research of star formation and evolution . as for\n, the temperature difference between its two components suggest that the system is under poor thermal contact\n. it may be a newly formed contact binary system .\n@xcite pointed out that the majority of w - subtype contact binaries are shallow contact systems .\nour results for confirm the conclusion and imply that may be undergoing the thermal relaxation oscillation ( tro ; @xcite ) .\nthe orbit of the binary system will shrink and expand under the control of the angular momentum loss ( aml ) and the thermal relaxation oscillation ( tro ) .\nthe degree of contact will increase and the system will evolve into a fully thermal contact configuration as the increasing times of oscillating circles @xcite .\nwe thank k. gazeas in department of astrophysics , astronomy and mechanics , national and kapodistrian university of athens for the data observed in university of athens observatory , greece .\nthis work is supported by the chinese natural science foundation ( grant no . 11133007 , 11325315 and 11203066 ) , the strategic priority research program `` the emergence of cosmological structure '' of the chinese academy of sciences ( grant no .\nxdb09010202 ) and the science foundation of yunnan province ( grant no .\n2012hc011 ) .\nthis research has made use of the fourth us naval observatory ccd astrograph catalog ( ucac4 ) .\nbinnendijk , l. 1970 , vistas in astronomy , 12 , 217 cox , a. n. 2000 , allen@xmath23s astrophysical quantities ( 4th ed . ; newyork : springer ) flannery , b. p. 1976 ,\napj , 205 , 217 gazeas , k. 2015 , information bulletin on variable stars , 6199 liu , l. , qian , s. b. , he , j. j. , et al . 2016 , new a , 43 , 1 lucy , l. b. 1967 , zap , 65 , 89 lucy , l. b. 1976 , apj , 205 , 208 qian , s. 2001a , mnras , 328 , 635 qian , s. 2001b , mnras , 328 , 914 robertson , j. a. , & eggleton , p. p. 1977 , mnras , 179 , 359 ruciski , s. m. 1969 , aca , 19 , 245 shapley , h. 1948 , harvard observatory monographs , 7 , 249 van hamme , w. 1993 , aj , 106 , 2096 van hamme , w. , & wilson , r. e. 2007 , apj , 661 , 1129 wilson , r. e. , devinney e.j . 1971 ,\napj , 166 , 605 wilson , r. e. , van , hamme . w. , terrell , d. , 2010 , apj , 723 , 1469 yildiz , m. , & doan , t. 2013 , mnras , 430 , 2029 yildiz , m. 2014 , mnras , 437 , 185 zhou , x. , qian , s .- b . , zhang , j. , et al .\n2016 , apj , 817 , 133 zhu , l. , qian , s .- b .\n, mikulek , z. , et al .\n2010 , aj , 140 , 215", "role": "user" }, { "content": "the @xmath0 @xmath1 @xmath2 @xmath3 bands light curves of the newly discovered binary system are obtained and analyzed using the wilson - devinney ( w - d ) code . \n the solutions suggest that the mass ratio of the binary system is @xmath4 and the less massive component is @xmath5 hotter than the more massive one . \n we conclude that is a w - subtype shallow contact ( with a contact degree of @xmath6 ) binary system . \n it may be a newly formed contact binary system which is just under geometrical contact and will evolve to be a thermal contact binary system . \n the high orbital inclination ( @xmath7 ) implies that is a total eclipsing binary system and the photometric parameters obtained by us are quite reliable . \n we also estimate the absolute physical parameters of the two components in , which will provide fundamental information for the research of contact binary systems . \n the formation and evolutionary scenario of is discussed . \n stars : binaries : close ; stars : binaries : eclipsing ; stars : individual :", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research article. Your task is to extract all drug combinations appearing in a specific sentence within the paragraph. Each drug combination should be assigned to one of the following three categories:\n\n- POS: Indicates a positive interaction between the drugs in the combination; for instance, drugs that have an additive or synergistic effect.\n- NEG: Indicates a negative interaction between the drugs in the combination; for instance, combining these drugs might result in adverse side effects, or might reduce their efficacy.\n- COMB: Indicates that the drugs are given in combination, but the type of interaction between the drugs cannot be determined based on the provided context.\n\nPlease format your answer as a JSON array. Each entry in the array should itself be an array formatted as [<drug_1>, <drug_2>, ..., <drug_n>, <category>] where <category> is one of the three categories listed above and <drug_1>, ..., <drug_n> are drug names copied verbatim from the input sentence. Different combinations may involve different numbers of drugs; in other words, the `n` in <drug_n> may vary.\n\nAs an example, the following output describes two extracted drug combinations; one between two drugs, and one between three drugs:\n\n[[\"artesunate\", \"artemether\", \"COMB\"], [\"Nifedipine\", \"Labetalol\", \"Prazosin\", \"POS\"]]\n\nThe paragraph and specific sentence are below. You should only extract relationships expressed in the specific sentence; the paragraph is provided for context.\n\nIn your output, return only the JSON array and no other text. If no drug combinations appear, return an empty array `[]`.\n\nparagraph: Efficacy and tolerability of IV doripenem versus meropenem in adults with complicated intra-abdominal infection: a phase III, prospective, multicenter, randomized, double-blind, noninferiority study. Complicated intra-abdominal infections (cIAIs) require surgical intervention and empiric antibacterial therapy. doripenem, a broad-spectrum carbapenem, provides coverage of key gram-negative and -positive aerobes and anaerobes encountered in cIAI. ### objective This study was designed to compare the efficacy and safety profile of doripenem and meropenem in hospitalized adult patients with cIAI. ### methods In this prospective, multicenter, doubleblind, noninferiority study, hospitalized adults with cIAI were randomly assigned to receive doripenem 500 mg IV q8h or meropenem 1 g IV q8h. After a minimum of 9 doses and adequate clinical improvement (relative to before the start of IV study drug, decreased body temperature and white blood cell count, improved or absent signs and symptoms of cIAI, and return of normal bowel function), patients could be switched to oral amoxicillin/clavulanate. Antibacterial therapy (IV plus subsequent oral) was given for a total of 5 to 14 days. The coprimary efficacy end points were the clinical cure rate (complete resolution or significant improvement of signs or symptoms of the index infection) in patients microbiologically evaluable (>or=1 baseline pathogen isolated from an intra-abdominal culture that was susceptible to both IV study drug therapies) at the test-of-cure (TOC) visit (21-60 days after the completion of study drug therapy) and the clinical cure rate in the microbiological modified intent-to-treat (mMITT) population (a bacterial pathogen identified at baseline, regardless of its susceptibility to the study drug). Noninferiority was concluded if the lower limit of the 2-sided 95 % CI for the difference ( doripenem minus meropenem ) in the proportion of patients classified as clinical cures was > or=-15 % . ### results A total of 476 patients were enrolled. The microbiologically evaluable population (319 patients) was 62.7% male and 67.7% white, with a mean age and weight of 46.7 years and 77.2 kg, respectively. In this population, doripenem and meropenem were associated with clinical cure rates at the TOC visit of 85.9% and 85.3%, respectively. The corresponding treatment difference was 0.6% (95% CI, -7.7% to 9.0%); this difference was not statistically significant. Similarly, in the mMITT population (385 patients), the clinical cure rates were 77.9% and 78.9%, respectively, and the corresponding 1.0% treatment difference was not statistically significant (95% CI, -9.7% to 7.7%). Clinical cure rates were not significantly different between the 2 treatment arms in key subgroups (eg, age, sex, race, baseline Acute Physiology and Chronic Health Evaluation II score, primary infection site). Microbiological eradication rates for common pathogens isolated at study entry were not significantly different between the 2 treatment groups. doripenem was well tolerated in the population studied. In the intent-to-treat population (471 patients), 83.0% and 78.0% of patients experienced >or=1 adverse event (AE) and 13.2% and 14.0% experienced >or=1 serious AE in the doripenem and meropenem treatment arms, respectively. In the doripenem and meropenem treatment arms, AEs resulted in study drug discontinuation in 5.1% and 2.1% of patients and death in 2.1% and 3.0% of patients, respectively. ### conclusions The present study found that doripenem (500 mg q8h) was effective in the treatment of cIAI, was therapeutically noninferior to meropenem (1 g q8h), with a safety profile not significantly different from that of meropenem in this selected population of patients with cIAI.\n\nsentence: Noninferiority was concluded if the lower limit of the 2-sided 95 % CI for the difference ( doripenem minus meropenem ) in the proportion of patients classified as clinical cures was > or=-15 % .", "role": "user" }, { "content": "[]", "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\nThe most common prebiotics used in humans are fructo-oligosaccharides (FOS) of different polymerization degrees (Guerreiro et al., 2016), either obtained from vegetables by hydrolysis or enzymatically synthesized (Flores-Maltos et al., 2014).", "role": "user" }, { "content": "Method", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2015 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: We propose to learn deep convolutional features for patch-level descriptors for image retrieval. The proposed Patch\n\nKeyphrases: patch image retrieval images\n\nDataset description:\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\nABC Dataset: The ABC Dataset is a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction.\nHPatches: The HPatches is a recent dataset for local patch descriptor evaluation that consists of 116 sequences of 6 images with known homography. The dataset is split into two parts: viewpoint - 59 sequences with significant viewpoint change and illumination - 57 sequences with significant illumination change, both natural and artificial.\nSEN12MS: A dataset consisting of 180,662 triplets of dual-pol synthetic aperture radar (SAR) image patches, multi-spectral Sentinel-2 image patches, and MODIS land cover maps.\n\nOptions: A: ImageNet B: ABC Dataset C: HPatches D: SEN12MS", "role": "user" }, { "content": "ImageNet", "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\nBACKGROUND: Long-term care facilities are high-risk settings for severe outcomes from outbreaks of Covid-19, owing to both the advanced age and frequent chronic underlying health conditions of the residents and the movement of health care personnel among facilities in a region. METHODS: After identification on February 28, 2020, of a confirmed case of Covid-19 in a skilled nursing facility in King County, Washington, Public Health-Seattle and King County, aided by the Centers for Disease Control and Prevention, launched a case investigation, contact tracing, quarantine of exposed persons, isolation of confirmed and suspected cases, and on-site enhancement of infection prevention and control. RESULTS: As of March 18, a total of 167 confirmed cases of Covid-19 affecting 101 residents, 50 health care personnel, and 16 visitors were found to be epidemiologically linked to the facility. Most cases among residents included respiratory illness consistent with Covid-19; however, in 7 residents no symptoms were documented. Hospitalization rates for facility residents, visitors, and staff were 54.5%, 50.0%, and 6.0%, respectively. The case fatality rate for residents was 33.7% (34 of 101). As of March 18, a total of 30 long-term care facilities with at least one confirmed case of Covid-19 had been identified in King County. CONCLUSIONS: In the context of rapidly escalating Covid-19 outbreaks, proactive steps by long-term care facilities to identify and exclude potentially infected staff and visitors, actively monitor for potentially infected patients, and implement appropriate infection prevention and control measures are needed to prevent the introduction of Covid-19.", "role": "user" }, { "content": "[\"Case Report\"]", "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\nRufinamide attenuates mechanical allodynia in a model of neuropathic pain in the mouse and stabilizes voltage-gated sodium channel inactivated state. BACKGROUND: Voltage-gated sodium channels dysregulation is important for hyperexcitability leading to pain persistence. Sodium channel blockers currently used to treat neuropathic pain are poorly tolerated. Getting new molecules to clinical use is laborious. We here propose a drug already marketed as anticonvulsant, rufinamide. METHODS: We compared the behavioral effect of rufinamide to amitriptyline using the Spared Nerve Injury neuropathic pain model in mice. We compared the effect of rufinamide on sodium currents using in vitro patch clamp in cells expressing the voltage-gated sodium channel Nav1.7 isoform and on dissociated dorsal root ganglion neurons to amitriptyline and mexiletine. RESULTS: In naive mice, amitriptyline (20 mg/kg) increased withdrawal threshold to mechanical stimulation from 1.3 (0.6-1.9) (median [ 95% CI ]) to 2.3 g (2.2-2.5) and latency of withdrawal to heat stimulation from 13.1 (10.4-15.5) to 30.0 s (21.8-31.9), whereas rufinamide had no effect. Rufinamide and amitriptyline alleviated injury-induced mechanical allodynia for 4 h (maximal effect: 0.10 + /- 0.03 g (mean + /- SD) to 1.99 + /- 0.26 g for rufinamide and 0.25 + /- 0.22 g to 1.92 + /- 0.85 g for amitriptyline). All drugs reduced peak current and stabilized the inactivated state of voltage-gated sodium channel Nav1.7, with similar effects in dorsal root ganglion neurons. CONCLUSIONS: At doses alleviating neuropathic pain, amitriptyline showed alteration of behavioral response possibly related to either alteration of basal pain sensitivity or sedative effect or both. Side-effects and drug tolerance/compliance are major problems with drugs such as amitriptyline. Rufinamide seems to have a better tolerability profile and could be a new alternative to explore for the treatment of neuropathic pain.", "role": "user" }, { "content": "[[\"Rufinamide\", \"REGULATOR\", \"voltage-gated sodium channel\"]]", "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:\nexperiments\n\nContext before the citation:\nAn off-the-shelf speech recognition device, a Nippon Electric Corporation DP-200, was added to an existing natural language processing system, the Natural Language Computer (NLC) (Ballard 1979, Biermann and Ballard 1980). The usefulness of the methodology described above was tested in the implementation of a connected speech understanding system.\n\nCitation Sentence:\nAn off-the-shelf speech recognition device , a Nippon Electric Corporation DP-200 , was added to an existing natural language processing system , the Natural Language Computer ( NLC ) ( Ballard 1979 , Biermann and Ballard 1980 ) .\n\nContext after the citation:\nThe expectation system provided the intermediate processing between the errorful output of the speech recognizer and the deep semantics of NLC. The resulting speech understanding system is called the Voice Natural Language Computer with Expectation (VNLCE, Fink 1983). [The current system should be distinguished from an earlier voice system (VNLC, Biermann et al. 1985), which had no expectation and which handled discrete speech where a 300 millisecond pause must follow each word.] It should be emphasized, of course, that the central issue here is the study of expectation mechanisms and the details of the design decisions could have been made in rather different ways.", "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\nWe present a large-scale empirical study of catastrophic forgetting (CF) in modern Deep Neural Network (DNN) models that perform sequential (or: incremental) learning.\n\nA new experimental protocol is proposed that takes into account typical constraints encountered in application scenarios.\n\nAs the investigation is empirical, we evaluate CF behavior on the hitherto largest number of visual classification datasets, from each of which we construct a representative number of Sequential Learning Tasks (SLTs) in close alignment to previous works on CF.\n\nOur results clearly indicate that there is no model that avoids CF for all investigated datasets and SLTs under application conditions.\nWe conclude with a discussion of potential solutions and workarounds to CF, notably for the EWC and IMM models.\nThis article is in the context of sequential or incremental learning in Deep Neural Networks (DNNs).\nEssentially, this means that a DNN is not trained once, on a single task D, but successively on two or more sub-tasks D 1 , . . . , D n , one after another.\nLearning tasks of this type, which we term Sequential Learning Tasks (SLTs) (see FIG0 ), are potentially very common in real-world applications.\nThey occur wherever DNNs need to update their capabilities on-site and over time: gesture recognition, network traffic analysis, or face and object recognition in mobile robots.\nIn such scenarios, neural networks have long been known to suffer from a problem termed \"catastrophic forgetting\"(CF) (e.g., BID7 ) which denotes the abrupt and near-complete loss of knowledge from previous subtasks D 1 , . . . , D k−1 after only a few training iterations on the current sub-task D k (see FIG0 compared to FIG0 ).\nWe focus on SLTs from the visual domain with two sub-tasks each, as DNNs show pronounced CF behavior even when only two sub-tasks are involved.\nThe sequential learning tasks used in this study only have two sub-tasks: D1 and D2.\nDuring training (white background) and re-training (gray background), test accuracy is measured on D1 (blue, ), D2 (green, ) and D1 ∪ D2 (red, ).\nThe blue curve allows to determine the presence of CF by simple visual inspection: if there is significant degradation w.r.t. the red curve, then CF has occurred.\nDISPLAYFORM0\nThe field of incremental learning is large, e.g., BID20 and BID8 .\nRecent systematic comparisons between different DNN approaches to avoid CF are performed in, e.g., BID23 or .\nPrincipal recent approaches to avoid CF include ensemble methods BID22 BID6 , dual-memory systems BID24 BID11 BID21 BID9 and regularization approaches.\nWhereas BID10 suggest Dropout for alleviating CF, the EWC method BID14 proposes to add a term to the energy function that protects weights that are important for the previous sub-task (s) .\nImportance is determined by approximating the Fisher information matrix of the DNN.\nA related approach is pursued by the Incremental Moment Matching technique (IMM) (see ), where weights from DNNs trained on a current and a past sub-tasks are \"merged\" using the Fisher information matrix.\nOther regularization-oriented approaches are proposed in BID2 ; BID25 and BID13 which focus on enforcing sparsity of neural activities by lateral interactions within a layer.Number of tested datasets In general, most methods referenced here are evaluated only on a few datasets, usually on MNIST BID16 and various derivations thereof (permutation, rotation, class separation).\nSome studies make limited use of CIFAR10, SVHN, the Amazon sentiment analysis problem, and non-visual problems such as data from Q-learning of Atari games.\nA largescale evaluation on a huge number of qualitatively different datasets is still missing 1 .\nModel selection and prescience Model selection (i.e., selecting DNN topology and hyperparameters) is addressed in some approaches BID10 but on the basis of a \"prescient\" evaluation where the best model is selected after all tasks have been processed, an approach which is replicated in BID14 .\nThis amounts to a knowledge of future sub-tasks which is problematic in applications.\nMost approaches ignore model selection BID25 BID2 BID13 , and thus implicitly violate causality.\nStorage of data from previous sub-tasks From a technical point of view, DNNs can be retrained without storing training data from previous sub-tasks, which is done in BID10 and BID25 .\nFor regularization approaches, however, there are regularization parameters that control the retention of previous knowledge, and thus must be chosen with care.\nIn BID14 , this is λ, whereas two such quantities occur in : the \"balancing\" parameter α and the regularization parameter λ for L2-transfer.\nThe only study where regularization parameters are obtained through cross-validation (which is avoided in other studies) is BID2 (for λ SN I and λ Ω ) but this requires to store all previous training data.This review shows that enormous progress has been made, but that there are shortcomings tied to applied scenarios which need to be addressed.\nWe will formalize this in Sec. 1.2 and propose an evaluation strategy that takes these formal constraints into account when testing CF in DNNs.\nThe original contributions of our work can be summarized as follows:• We propose a training and evaluation paradigm for incremental learning in DNNs that enforces typical application constraints, see Sec. 1.2.\nThe importance of such an applicationoriented paradigm is underlined by the fact that taking application constraints into account leads to radically different conclusions about CF than those obtained by other recent studies on CF (see Sec. 1.1).•\nWe investigate the incremental learning capacity of various DNN approaches (Dropout, LWTA, EWC and IMM) using the largest number of qualitatively different classification datasets so far described. We\nfind that all investigated models are afflicted by catastrophic forgetting, or else in violation of application constraints and discuss potential workarounds.• We\nestablish that the \"permuted\" type of SLTs (e.g., \"permuted MNIST\") should be used with caution when testing for CF.• We\ndo not propose a method for avoiding CF in this article. This\nis because avoiding CF requires a consensus on how to actually measure this effect: our novel contribution is a proposal how to do just that.\nThe primary conclusion from the results in Sec. 4 is that CF still represents a major problem when training DNNs.\nThis is particularly true if DNN training happens under application constraints as outlined in Sec. 1.2.\nSome of these constraints may be relaxed depending on the concrete application: if some prior knowledge about future sub-task exists, it can be used to simplify model selection and improve results.\nIf sufficient resources are available, a subset of previously seen data may be kept in memory and thus allow a \"best\" type evaluation/stopping criterion for re-training, see Alg.\n1.Our evaluation approach is similar to , and we adopt some measures for CF proposed there.\nA difference is the setting of up to 10 sub-tasks, whereas we consider only two of them since we focus less on the degree but mainly on presence or absence of CF.\nAlthough comparable both in the number of tested models and benchmarks, BID23 uses a different evaluation methodology imposing softer constraints than ours, which is strongly focused on application scenarios.\nThis is, to our mind, the reason why those results differ significantly from ours and underscores the need for a consensus of how to measure CF.In general application scenarios without prior knowledge or extra resources, however, an essential conclusion we draw from Sec. 4 is that model selection must form an integral part of training a DNN on SLTs.\nThus, a wrong choice of hyper-parameters based on D 1 can be disastrous for the remaining sub-tasks, which is why application scenarios require DNN variants that do not have extreme dependencies on hyper-parameters such as layer number and layer sizes.Lastly, our findings indicate workarounds that would make EWC or IMM practicable in at least some application scenarios.\nIf model selection is addressed, a small subset of D 1 may be kept in memory for both methods: to determine optimal values of α for IMM and to determine when to stop re-training for EWC.\nFIG7 shows that small changes to α do not dramatically impact final accuracy for IMM, and FIG4 indicates that accuracy loss as a function of re-training time is gradual in most cases for EWC.\nThe inaccuracies introduced by using only a subset of D 1 would therefore not be very large for both algorithms.To conclude, this study shows that the consideration of applied scenarios significantly changes the procedures to determine CF behavior, as well as the conclusions as to its presence in latestgeneration DNN models.\nWe propose and implement such a procedure, and as a consequence claim that CF is still very much of a problem for DNNs.\nMore research, either on generic solutions, or on workarounds for specific situations, needs to be conducted before the CF problem can be said to be solved.\nA minor but important conclusion is that results obtained on permutation-type SLTs should be treated with caution in future studies on CF.", "role": "user" }, { "content": "We check DNN models for catastrophic forgetting using a new evaluation scheme that reflects typical application conditions, with surprising results.", "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\nAround-the-clock intraocular pressure reduction with once-daily application of latanoprost by itself or in combination with timolol . OBJECTIVE To determine whether once-daily , in the morning , topical application of the new ocular hypotensive prostaglandin analogue , latanoprost , yields nocturnal intraocular pressure ( IOP ) reduction similar to its diurnal IOP reducing efficacy . STUDY DESIGN AND PATIENTS Placebo- controlled , randomized , and double-masked study on hospitalized patients with ocular hypertension or glaucoma . Patients in group 1 ( n=9 ) were maintained on twice-daily applications of 0.5 % timolol maleate . Patients in group 2 ( n=10 ) terminated their timolol treatment 3 weeks before the beginning of the study . In both groups the test drug ( 0.005 % latanoprost ) and its vehicle ( placebo ) was applied by hospital staff every morning for 9 days . MEASUREMENTS After 4 days of ambulatory treatment , patients were hospitalized , and IOP values were obtained in the supine and sitting positions with a handheld electronic tonometer ( Tono-Pen XL , Bio-Rad , Glendale , Calif ) and a Goldmann 's applanation tonometer , covering every 2-hour interval , around the clock , but not more than at four time points per day during a 5-day period . RESULTS The mean nocturnal IOPs ( Goldmann 's applanation tonometer ) collected for 5 days were mean +/-SEM 17.9+/-0.6 vs 20.2+/-0.6 mm Hg and 16.8+/-0.3 vs 20.6+/-0.5 mm Hg for the study vs the control eyes in group 1 and group 2 , respectively . These nocturnal IOP reductions were statistically significant ( P < .001 , two-tailed paired Student 's t test ) . The differences between diurnal and nocturnal IOP reductions ( handheld electronic or Goldmann 's applanation tonometer ) were minimal ( > 0.3 mm Hg ) and statistically not significant ( P > .31 , two-tailed paired Student 's t test ) . CONCLUSION Once-daily latanoprost treatment provides uniform circadian ( around-the-clock ) IOP reduction by itself , or in combination with timolol .", "role": "user" }, { "content": "{\"Intervention\": [\"latanoprost\", \"timolol maleate\", \"timolol\", \"combination with timolol\", \"placebo\"], \"Outcome\": [\"intraocular pressure reduction\", \"nocturnal IOP reductions\", \"IOP values\", \"nocturnal intraocular pressure ( IOP ) reduction\", \"diurnal and nocturnal IOP reductions\", \"mean nocturnal IOPs ( Goldmann \\u0027s applanation tonometer\", \"IOP reduction\"], \"Participant\": [\"hospitalized patients with ocular hypertension or glaucoma . Patients in group 1 ( n=9 )\"]}", "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:\nDevelopmental intervention for low birth weight infants: improved early development outcome.\nAbstract 1:\nThis prospect i ve longitudinal study was design ed to evaluate the effects of a multidisciplinary infant development program ( IDP ) on the mental and physical development of low birth weight infants ( less than 1,800 g ) . Infants in the neonatal intensive care were r and omly assigned to the IDP or to traditional care ( control group ) . IDP infants received developmental interventions in the hospital and at home through the first 2 years of life . Counseling and parenting education were provided to their parents during this same period . The control group received all the postnatal care and referrals customarily given in traditional care . Both IDP and control infants were enrolled in an independent follow-up program , which used the Bayley Scales of Infant Development in a blind evaluation design . The IDP group had a significantly lower incidence of developmental delay ( P less than .05 ) and scored significantly higher than the control group ( P less than .05 ) on mean mental and physical indices at 12 and 24 months of adjusted age\n\n\nTitle 2:\nA cognitive approach to child mistreatment prevention among medically at-risk infants.\nAbstract 2:\nThe authors assessed the effectiveness of a home visitation program in enhancing the early parenting history of infants born at medical risk -- a population that is at risk for mistreatment . A r and omized clinical trial design was used to compare the effects of a cognitively based extension of the Healthy Start home visitation program ( HV+ ) with a visitation condition that did not include this component ( HV ) . In the HV+ condition , they observed ( a ) a lower use of corporal punishment , ( b ) greater safety maintenance in the home , and ( c ) fewer reported child injuries . The sample ( N = 102 ) was primarily Latino ; however , the effects of the intervention were not qualified by ethnicity , maternal education , or immigration status\n\n\nTitle 3:\nAn intervention program for mothers of low-birthweight infants: preliminary results.\nAbstract 3:\nMothers of low-birthweight babies born at the Medical Center Hospital of Vermont during a 21-month period were r and omly assigned to experimental ( N = 34 ) and control ( N = 40 ) groups . Forty-one normal-birthweight controls were also recruited . Experimental mothers received an 11-session intervention program which emphasized maternal sensitivity and responsiveness to infant social signals . This paper analyzes the impact of the program , by 6 months , on maternal adaptation and psychopathology , and on infant cognitive development and temperament\n\n\nTitle 4:\nMinimizing adverse effects of low birthweight: four-year results of an early intervention program.\nAbstract 4:\nThe outcome of an early intervention program for low-birthweight ( LBW ) infants was examined in this study . The intervention consisted of 11 sessions , beginning during the final week of hospitalization and extending into the home over a 3-month period . The program aim ed to facilitate maternal adjustment to the care of a LBW infant , and , indirectly , to enhance the child 's development . Neonates weighing less than 2,200 grams and under 37 weeks gestational age were r and omly assigned to experimental or control conditions . A full-term , normal birthweight ( NBW ) group served as a second control . 6-month analyses of dyads who completed all assessment s over a 4-year period ( N 's = 25 LBW experimental , 29 LBW control , and 28 NBW infant-mother dyads ) showed that the experimental group mothers reported significantly greater self-confidence and satisfaction with mothering , as well as more favorable perception of infant temperament than LBW control group mothers . A progressive divergence between the LBW experimental and LBW control children on cognitive scores culminated in significant group differences on the McCarthy GCI at ages 36 and 48 months , when the LBW experimental group caught up to the NBW group . Possible explanations for the observed delay in the emergence of intervention effects on cognitive development and the mediating role of favorable mother-infant transactional patterns are discussed in light of recent evidence from the literature\n\n\nTitle 5:\nMaternal holding of preterm infants during the early weeks after birth and dyad interaction at six months.\nAbstract 5:\nOBJECTIVE To examine whether a supportive nursing intervention that promoted kangaroo holding of healthy preterm infants by their mothers during the early weeks of the infant 's life facilitated coregulation between mother and infant at 6 months of age . DESIGN R and omized controlled trial . PARTICIPANTS Sixty-five mother/infant dyads with mean gestational age at birth of 33 weeks . Fifty percent of infants were male , and 50 % were non-White . INTERVENTIONS An 8-week home intervention encouraged daily 1-hour , uninterrupted holding with either blanket ( baby wrapped in blanket and held in mother 's arms ) or the kangaroo ( baby in skin-to-skin contact on mother 's chest ) method . In both conditions , weekly home visits by an experienced RN included encouragement to hold the infant , emotional support , and information about infant behavior and development . A control group received brief social visits , had no holding constraints , and participated in all assessment s. MAIN OUTCOME MEASURES When infants were 6 months of age , the Still-Face Paradigm was used to assess mother/infant interaction . Outcome measures were coregulation of the dyad 's responses during the play episodes of the Still-Face Paradigm and vitality in infant efforts to reengage the mother during the neutral face portion of the Still-Face Procedure . RESULTS Significant differences among groups were found in mother/infant coregulation . Post hoc analysis showed that dyads who were supported in kangaroo holding displayed more coregulation behavior during play than dyads in the blanket-holding group . No differences were found between groups in infant vitality during the neutral face portion of the Still-Face Procedure . CONCLUSION Dyads supported in practicing kangaroo holding in the early weeks of life may develop more coregulated interactional strategies than other dyads\n\n\nTitle 6:\nLow Birth Weight and Home Intervention Strategies: Preterm Infants\nAbstract 6:\nABSTRACT . We investigated the effects of a 1 -year home intervention on premature infants with low ( < 1500 g ) and higher ( 1500–2000 g ) birth weights . Infants from each weight condition were block r and omly assigned to a control or to one of two treatment groups . One treatment group focused on the development of the infant ; the other treatment group focused on the parent-infant interaction . The low birth weight infants obtained significantly lower Bayley mental and motor scores , and were more passive and less intense than the higher birth weight infants . However , the low birth weight infants and their parents were more responsive to the home intervention than were the higher birth weight infants , as demonstrated by changes in the Bayley mental scores and the Home Observation for Measurement of the Environment ( HOME ) inventory . These findings exemplify the reciprocal relationship between the child 's characteristics and parental responding . The importance of selecting the most high-risk premature infants for early home intervention is outlined\n\n\nTitle 7:\nEarly home intervention with low-birth-weight infants and their parents.\nAbstract 7:\nWe investigated the effects of a year-long home intervention with a sample of preterm infants r and omly assigned to 1 of 3 groups : a developmental intervention , a parent-infant intervention , and a no-treatment control group . A full-term no-treatment control was also used . Both intervention approaches focused on the parent-child unit , providing training for parents to improve observational skills , emotional support , and information about community re sources . However , whereas specific tasks to facilitate the child 's development were provided in the developmental intervention group , the quality of the parent-infant interaction was the target for treatment in the other group . All infants were assessed at 4 , 8 , 12 , and 16 months of age corrected for prematurity . The results suggest that although both intervention approaches were effective in modifying some aspects of the home environment and , to a lesser degree , in improving infants ' cognitive development , the parent-infant interaction approach seemed to have the greater impact . These findings confirm previous observations regarding the cognitive development of preterm and full-term infants during the first 18 months of life and demonstrate changes in behavior and behavior styles in both pre- and full-term infants as they become older\n\n\nTitle 8:\nNine-year outcome of the Vermont intervention program for low birth weight infants.\nAbstract 8:\nTwenty-four low birth weight children who had received an experimental intervention ( LBWE ) during the neonatal period , 31 control children who had received no treatment ( LBWC ) , and 36 normal birth weight children were compared . The intervention involved seven hospital sessions and four home sessions in which a nurse helped mothers adapt to their LBW babies . At age 9 , LBWE children scored significantly higher than LBWC children on the Kaufman Mental Processing Composite , Sequential , Simultaneous , Achievement , Arithmetic , and Riddles scales , after statistical adjustments for socioeconomic status . The LBWE children had also advanced more rapidly in school than had LBWC children . Parent ( Child Behavior Checklist ) and teacher ( Teacher 's Report Form ) ratings of school functioning were more favorable for LBWE than LBWC children , with especially strong effects on Teacher 's Report Form scores for academic performance and the attention problems syndrome . At age 9 , LBWE children were not significantly inferior to normal birth weight children on any measure . These results bear out a progressive divergence between the LBWE and LBWC children that first became statistically significant in cognitive scores at age 3 . The findings suggest that the intervention prevented cognitive lags among LBW children and that this eventually had a favorable effect on academic achievement , behavior , and advancement in school . The progression from no significant differences between LBWE and LBWC children on early cognitive and achievement scores to significant and pervasive differences in later functioning argues for long-term follow-up periods to evaluate properly the power of behavioral interventions to compensate for biological risks\n\n\nTitle 9:\nPreterm infant follow-up project: a multi-site field experiment of hospital and home intervention programs for mothers and preterm infants.\nAbstract 9:\nThis study was design ed as a multi-site field experiment to test the efficacy of hospital and home visit interventions to improve interaction between mothers and preterm infants . Hospital intervention consisted of State Modulation ( SM ) treatment , which focused on teaching mothers to read the behavioral cues and modulate the states of consciousness of preterm infants during feedings . Home visit intervention was a field-tested program , Nursing Systems for Effective Parenting-Preterm ( NSTEP-P ) , implemented during the first five months after the infant 's hospital discharge . A hospital program on car seats ( CS ) and st and ard public health nursing home visits ( PHN ) served as comparison treatments . The sample consisted of 327 mothers and their preterm infants who were less than 36 weeks of gestational age at hospital discharge . Mothers were r and omly assigned to intervention groups on the basis of their education . High education ( HE ) was > or = 13 years of education , while low education ( LE ) was < or = 12 years of education . HE mothers were only assigned to hospital programs , while LE mothers were assigned to combinations of hospital and home visit programs . Evaluations were conducted at 40 weeks conceptual age ( expected date of birth ) , at 46 weeks conceptual age ( 1.5-months-corrected age ) , and 60 weeks conceptual age ( 5-months-corrected age ) . Comparisons were made within each educational group . For HE groups , SM infants gave significantly more clear cues during observations of feeding interactions at 1.5-months-corrected age and teaching interactions at 5-months-corrected age than infants in the CS group . During the teaching interaction , well-educated SM mothers provided significantly more social-emotional and cognitive stimulation than CS mothers . For LE groups , infants in the SM group combined with either PHN or NSTEP-P exhibited significantly more responsive behavior during feeding observations than those infants in the CS/PHN group at 1.5-months-corrected age . LE mothers in the SM/NSTEP-P group demonstrated more sensitivity and more stimulation during teaching interactions at 5-months-corrected age than mothers in the SM/PHN or CS/PHN groups . Findings suggest that State Modulation treatment is effective in influencing positive social interaction of infants regardless of the level of maternal education . State modulation treatment combined with NSTEP-P is most effective in improving the social interaction between preterm infants and mothers with limited formal education . Such treatment-specific programs suggest avenues for providing cost-effective care that complements the changing transactional needs of mothers and preterm infants\n\n\nTitle 10:\nEffects of parent training on teenage mother and their infants.\nAbstract 10:\nParent training was provided for 80 low-income , black teenage mothers during their infants ' first six months . Half of the mothers were visited biweekly in their homes to be instructed in caregiving and in sensorimotor and interaction exercises , and half were trained as CETA ( Comprehensive Employment Training ACT)-paid , teacher 's aides in a medical school infant nursery that provided care for their infants and infants of medical faculty . Growth and development during the first two years were superior for the infants whose mothers received training , particularly those who received paid parent training as teacher 's aides in the infant nursery . Repeat pregnancy rates were lower and return to work/school rates were higher for the infant nursery mothers , most of whom subsequently pursued nurse 's aide training", "role": "user" }, { "content": ": Review ed studies suggest that home visiting for preterm infants promotes improved parent-infant interaction .", "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\nMechanical activation of CaO-based adsorbents for CO(2) capture. The reversible cycling of CaO adsorbents to CaCO(3) for high-temperature CO(2) capture is substantially improved by mechanical treatment. The mechanical milling intensity and conditions of grinding (e.g., wet vs. dry, planetary vs. vibratory milling) were determined to be the main factors that control the effectiveness of the mechanochemical synthesis to enhance the recycling stability of the sorbents prepared. In addition, MgO was used as an example of an inert binder to help mitigate CaCO(3) sintering. Wet planetary milling of MgO into CaCO(3) allowed efficient particle size reduction and the effective dispersion of MgO throughout the particles. Wet planetary milling yielded the most stable sorbents during 50 cycles of carbonation-calcination.", "role": "user" }, { "content": "{\"Chemical\": [\"CaO\", \"CaCO(3)\", \"CO(2)\", \"MgO\"]}", "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\nMales and females with confirmed disease: Fabry (by GLA enzymes and/or DNA testing) naïve and on ERT, Mitochondrial diseases (electron transport chain and/or DNA testing) or connective tissue diseases (clinical criteria and/or DNA testing when available) \nConsenting adults (18 years and older) who agrees and consents to skin biopsy and QSART procedure", "role": "user" }, { "content": "{\"Condition\": [\"connective tissue diseases\", \"confirmed disease\", \"Mitochondrial diseases\"], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [\"clinical criteria\"], \"Person\": [\"Males\", \"females\"], \"Procedure\": [\"ERT\", \"DNA testing\", \"GLA enzymes\", \"electron transport chain\"], \"Qualifier\": [\"Fabry na\\u00efve\"], \"ReferencePoint\": [], \"Scope\": [\"Fabry (by GLA enzymes and/or DNA testing) na\\u00efve and on ERT\", \"Fabry (by GLA enzymes and/or DNA testing) na\\u00efve and on ERT, Mitochondrial diseases (electron transport chain and/or DNA testing) or connective tissue diseases (clinical criteria and/or DNA testing when available)\", \"clinical criteria and/or DNA testing\", \"GLA enzymes and/or DNA testing\", \"electron transport chain and/or DNA testing\"], \"Temporal\": [], \"Value\": [], \"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: [\"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\nObstructed Diffusion in Silica Colloidal Crystals. The hindered diffusion in silica colloidal crystals was studied experimentally, both by fluorescence recovery after photobleaching and by measurement of ionic conductivity. Particle size was varied to include 120, 220, 470, and 1300 nm, and the porosities were determined by flow measurements. For fluorescein, the results showed that the obstruction factor, which is the ratio of the diffusion coefficients inside the media and in open solution, is equal to the porosity within experimental error. For proteins, the same conclusion is made after correction for size exclusion of the pores. The obstruction factors for these media are 2-fold lower than those measured for chromatographic media, 60% higher than theoretical predictions, and equal to what is assumed for electrophoretic sieving in random fibers.", "role": "user" }, { "content": "{\"Chemical\": [\"fluorescein\"]}", "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\nA field trial of production and financial consequences of helminthosis control in sheep production in Ethiopia . We used a partial-budget analysis to evaluate profitability of different management strategies of three genotypes of sheep in a 2 x 2 x 3 factorial experiment conducted at Debre Berhan research station in the central highlands of Ethiopia . This involved two anthelmintic-treatment levels ( treated vs. non-treated ) , two supplementary nutrition levels ( protein-energy supplementation yes/no ) and three genotypes : indigenous Menz ( n=40 ) , 50 % Awassi x 50 % Menz crosses ( n=38 ) and 75 % Awassi x 25 % Menz crosses ( n=31 ) . All sheep were exposed to natural sub-clinical helminthosis challenge . Supplemented sheep were offered a concentrate mix daily on an individual basis . Anthelmintic-treated sheep were drenched with fenbendazole against nematodes and with triclabendazole against trematodes . Data were collected during the experimental period ( for 10 months from approximately 1 year of age ) on feed intake , live weight , eggs per gram ( EPG ) of faeces , packed-cell volume ( PCV ) , wool weight , and adult-worm burden . Actual market input and output prices were recorded . Supplemented sheep had significantly higher marginal profit ( MP ) per sheep than non-supplemented sheep ( ETB 33 vs. 4 ) . Likewise , anthelmintic treated sheep performed significantly better than their non-treated contemporaries ( MP=ETB 28 vs. 8 ) . The 75 % Awassi crosses were least profitable .", "role": "user" }, { "content": "{\"Intervention\": [\"two anthelmintic-treatment levels ( treated vs. non-treated )\", \"two supplementary nutrition levels ( protein-energy supplementation yes/no )\", \"concentrate mix daily\", \"fenbendazole against nematodes and with triclabendazole against trematodes\", \"different management strategies of three genotypes of sheep\"], \"Outcome\": [\"market input and output prices\", \"adult-worm burden\", \"live weight\", \"wool weight\", \"profitability\", \"performed\", \"feed intake\", \"profitable\", \"marginal profit ( MP )\", \"eggs per gram ( EPG ) of faeces\", \"packed-cell volume ( PCV )\"], \"Participant\": [\"central highlands of Ethiopia\", \"n=31\", \"sheep production in Ethiopia .\", \"n=40\"]}", "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 visual planning (VP), an agent learns to plan goal-directed behavior from observations of a dynamical system obtained offline, e.g., images obtained from self-supervised robot interaction.\nVP algorithms essentially combine data-driven perception and planning, and are important for robotic manipulation and navigation domains, among others.\nA recent and promising approach to VP is the semi-parametric topological memory (SPTM) method, where image samples are treated as nodes in a graph, and the connectivity in the graph is learned using deep image classification.\nThus, the learned graph represents the topological connectivity of the data, and planning can be performed using conventional graph search methods.\nHowever, training SPTM necessitates a suitable loss function for the connectivity classifier, which requires non-trivial manual tuning.\nMore importantly, SPTM is constricted in its ability to generalize to changes in the domain, as its graph is constructed from direct observations and thus requires collecting new samples for planning.\nIn this paper, we propose Hallucinative Topological Memory (HTM), which overcomes these shortcomings.\nIn HTM, instead of training a discriminative classifier we train an energy function using contrastive predictive coding.\nIn addition, we learn a conditional VAE model that generates samples given a context image of the domain, and use these hallucinated samples for building the connectivity graph, allowing for zero-shot generalization to domain changes.\nIn simulated domains, HTM outperforms conventional SPTM and visual foresight methods in terms of both plan quality and success in long-horizon planning.\nFor robots to operate in unstructured environments such as homes and hospitals, they need to manipulate objects and solve complex tasks as they perceive the physical world.\nWhile task planning and object manipulation have been studied in the classical AI paradigm [20, 9, 30, 10] , most successes have relied on a human-designed state representation and perception, which can be challenging to obtain in unstructured domains.\nWhile high-dimensional sensory input such as images can be easy to acquire, planning using raw percepts is challenging.\nThis has motivated the investigation of datadriven approaches for robotic manipulation.\nFor example, deep reinforcement learning (RL) has made impressive progress in handling high-dimensional sensory inputs and solving complex tasks in recent years [7, 4, 15, 23] .\nOne of the main challenges in deploying deep RL methods in human-centric environment is interpretability.\nFor example, before executing a potentially dangerous task, it would be desirable to visualize what the robot is planning to do step by step, and intervene if necessary.\nAddressing both data-driven modeling and interpretability, the visual planning (VP) paradigm seeks to learn a model of the environment from raw perception and then produce a visual plan of solving a task before actually executing a robot action.\nRecently, several studies in manipulation and navigation [13, 29, 5, 22] have investigated VP approaches that first learn what is possible to do in a particular environment by self-supervised interaction, and then use the learned model to generate a visual plan from the current state to the goal, and finally apply visual servoing to follow the plan.\nOne particularly promising approach to VP is the semi-parametric topological memory (SPTM) method proposed by Savinov et al. [22] .\nIn SPTM, images collected offline are treated as nodes in a graph and represent the possible states of the system.\nTo connect nodes in this graph, an image classifier is trained to predict whether pairs of images were 'close' in the data or not, effectively learning which image transitions are feasible in a small number of steps.\nThe SPTM graph can then be used to generate a visual plan -a sequence of images between a pair of start and goal images -by directly searching the graph.\nSPTM has several advantages, such as producing highly interpretable visual plans and the ability to plan long-horizon behavior.\nHowever, since SPTM builds the visual plan directly from images in the data, when the environment changes -for example, the lighting varies, the camera is slightly moved, or other objects are displaced -SPTM requires recollecting images in the new environment; in this sense, SPTM does not generalize in a zero-shot sense.\nAdditionally, similar to [5] , we find that training the graph connectivity classifier as originally proposed by [22] requires extensive manual tuning.\nFigure 1 : HTM illustration.\nTop left: data collection.\nIn this illustration, the task is to move a green object between gray obstacles.\nData consists of multiple obstacle configurations (contexts), and images of random movement of the object in each configuration.\nBottom left: the elements of HTM.\nA CVAE is trained to hallucinate images of the object and obstacles conditioned on the obstacle image context.\nA connectivity energy model is trained to score pairs of images based on the feasibility of their transition.\nRight: HTM visual planning.\nGiven a new context image and a pair of start and goal images, we first use the CVAE to hallucinate possible images of the object and obstacles.\nThen, a connectivity graph (blue dotted lines) is computed based on the connectivity energy, and we plan for the shortest path from start to goal on this graph (orange solid line).\nFor executing the plan, a visual servoing controller is later used to track the image sequence.\nIn this work, we propose to improve both the robustness and zero-shot generalization of SPTM.\nTo tackle the issue of generalization, we assume that the environment is described using some context vector, which can be an image of the domain or any other observation data that contains enough information to extract a plan (see Figure 1 top left) .\nWe then train a conditional generative model that hallucinates possible states of the domain conditioned on the context vector.\nThus, given an unseen context, the generative model hallucinates exploration data without requiring actual exploration.\nWhen building the connectivity graph with these hallucinated images, we replace the vanilla classifier used in SPTM with an energy-based model that employs a contrastive loss.\nWe show that this alteration drastically improves planning robustness and quality.\nFinally, for planning, instead of connecting nodes in the graph according to an arbitrary threshold of the connectivity classifier, as in SPTM, we cast the planning as an inference problem, and efficiently search for the shortest path in a graph with weights proportional to the inverse of a proximity score from our energy model.\nEmpirically, we demonstrate that this provides much smoother plans and barely requires any hyperparameter tuning.\nWe term our approach Hallucinative Topological Memory (HTM).\nA visual overview of our algorithm is presented in Figure 1 .\nWe evaluate our method on a set of simulated VP problems of moving an object between obstacles, which require long-horizon planning.\nIn contrast with prior work, which only focused on the success of the method in executing a task, here we also measure the interpretability of visual planning, through mean opinion scores of features such as image fidelity and feasibility of the image sequence.\nIn both measures, HTM outperforms state-of-the-art data-driven approaches such as visual foresight [4] and the original SPTM.\nWe propose a method that is visually interpretable and modular -we first hallucinate possible configurations, then compute a connectivity between them, and then plan.\nOur HTM can generalize to unseen environments and improve visual plan quality and execution success rate over state-of-the-art VP methods.\nOur results suggest that combining classical planning methods with data-driven perception can be helpful for long-horizon visual planning problems, and takes another step in bridging the gap between learning and planning.\nIn future work, we plan to combine HTM with Visual MPC for handling more complex objects, and use object-oriented planning for handling multiple objects.\nAnother interesting aspect is to improve planning by hallucinating samples conditioned on the start and goal configurations, which can help reduce the search space during planning.", "role": "user" }, { "content": "We propose Hallucinative Topological Memory (HTM), a visual planning algorithm that can perform zero-shot long horizon planning in new environments.", "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\nSubchondral bone microarchitecture and failure mechanism under compression: A finite element study Subchondral bone (SCB) microdamage is commonly observed in traumatic joint injuries and has been strongly associated with post-traumatic osteoarthritis (PTOA). Knowledge of the three-dimensional stress and strain distribution within the SCB tissue helps to understand the mechanism of SCB failure, and may lead to an improved understanding of mechanisms of PTOA initiation, prevention and treatment. In this study, we used high-resolution micro-computed tomography (µCT)-based finite element (FE) modelling of cartilage-bone to evaluate the failure mechanism and the locations of SCB tissue at high-risk of initial failure under compression. The µCT images of five cartilage-bone specimens with an average SCB thickness of 1.23±0.20mm were used to develop five µCT-based FE models. The FE models were analysed under axial compressions of approximately 30MPa applied to the cartilage surface while the bone edges were constrained. Strain and stress-based failure criteria were then applied to evaluate the failure mechanism of the SCB tissue under excessive compression through articular cartilage. µCT-based FE models predicted two locations in the SCB at high-risk of initial failure: (1) the interface of the calcified - uncalcified cartilage due to excessive tension, and (2) the trabecular bone beneath the subchondral plate due to excessive compression. µCT-based FE models of cartilage-bone enabled us to quantify the distribution of the applied compression which was transferred through the articular cartilage to its underlying SCB, and to investigate the mechanism and the mode of SCB tissue failure. Ultimately, the results will help to understand the mechanism of injury formation in relation to PTOA.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"SCB\", \"subchondral plate\", \"cartilage-bone\", \"SCB tissue\", \"cartilage\", \"trabecular bone\", \"Subchondral bone\", \"bone\", \"articular cartilage\"], \"Bacterium\": [], \"BiologicFunction\": [\"PTOA\", \"post-traumatic osteoarthritis\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"high-risk of\", \"improved\", \"stress-based\", \"stress\", \"strain\", \"Strain\"], \"Food\": [], \"HealthCareActivity\": [\"\\u00b5CT-based\", \"high-resolution micro-computed tomography\", \"\\u00b5CT\"], \"InjuryOrPoisoning\": [\"traumatic joint injuries\", \"injury\"], \"IntellectualProduct\": [\"finite element (FE) modelling\", \"FE models\", \"\\u00b5CT images\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"analysed\", \"finite element study\", \"study\"], \"SpatialConcept\": [\"edges\", \"cartilage surface\", \"axial\", \"locations\", \"three-dimensional\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: We develop a new method for 3D human body reconstruction from a monocular image\n\nKeyphrases: 3d human body reconstruction images\n\nDataset description:\nPeople Snapshot Dataset: Enables detailed human body model reconstruction in clothing from a single monocular RGB video without requiring a pre scanned template or manually clicked points.\nMPII: The MPII Human Pose Dataset for single person pose estimation is composed of about 25K images of which 15K are training samples, 3K are validation samples and 7K are testing samples (which labels are withheld by the authors). The images are taken from YouTube videos covering 410 different human activities and the poses are manually annotated with up to 16 body joints.\nAIST++: AIST++ is a 3D dance dataset which contains 3D motion reconstructed from real dancers paired with music. The AIST++ Dance Motion Dataset is constructed from the AIST Dance Video DB.\nExPose: Curates a dataset of SMPL-X fits on in-the-wild images.\nDeep Fashion3D: A novel benchmark and dataset for the evaluation of image-based garment reconstruction systems. Deep Fashion3D contains 2078 models reconstructed from real garments, which covers 10 different categories and 563 garment instances.\nCOCO: The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.\n\nOptions:- A: People Snapshot Dataset B: MPII C: AIST++ D: ExPose E: Deep Fashion3D F: COCO", "role": "user" }, { "content": "[\"MPII\", \"COCO\"]", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research article. Your task is to extract all drug combinations appearing in a specific sentence within the paragraph. Each drug combination should be assigned to one of the following three categories:\n\n- POS: Indicates a positive interaction between the drugs in the combination; for instance, drugs that have an additive or synergistic effect.\n- NEG: Indicates a negative interaction between the drugs in the combination; for instance, combining these drugs might result in adverse side effects, or might reduce their efficacy.\n- COMB: Indicates that the drugs are given in combination, but the type of interaction between the drugs cannot be determined based on the provided context.\n\nPlease format your answer as a JSON array. Each entry in the array should itself be an array formatted as [<drug_1>, <drug_2>, ..., <drug_n>, <category>] where <category> is one of the three categories listed above and <drug_1>, ..., <drug_n> are drug names copied verbatim from the input sentence. Different combinations may involve different numbers of drugs; in other words, the `n` in <drug_n> may vary.\n\nAs an example, the following output describes two extracted drug combinations; one between two drugs, and one between three drugs:\n\n[[\"artesunate\", \"artemether\", \"COMB\"], [\"Nifedipine\", \"Labetalol\", \"Prazosin\", \"POS\"]]\n\nThe paragraph and specific sentence are below. You should only extract relationships expressed in the specific sentence; the paragraph is provided for context.\n\nIn your output, return only the JSON array and no other text. If no drug combinations appear, return an empty array `[]`.\n\nparagraph: Modified magrath regimens for adults with Burkitt and Burkitt-like lymphomas: preserved efficacy with decreased toxicity. Burkitt and Burkitt-like lymphomas are rapidly growing tumors which require specialized therapy. Although intensive, multi-agent regimens have been effective in children, results are more variable in adults. Magrath et al. previously described a regimen that was highly effective in children and young adults. This phase II study of a modified Magrath regimen was designed to assess its efficacy in older adults and reduce treatment-related toxicity. Fourteen patients with Burkitt/Burkitt-like lymphoma and median age of 47 years were stratified into two categories: low-risk (normal LDH and a single focus of disease measuring less than 10 cm, 3 patients) and high risk (all other, 11 patients). Low-risk patients received three cycles of modified CODOX-M ( cyclophosphamide , doxorubicin , adriamycin , vincristine with intrathecal methotrexate and cytarabine followed by high-dose systemic methotrexate , regimen A ) . High-risk patients received four alternating cycles of regimens A and B (A-B-A-B). Regimen B consisted of ifosfamide, cytarabine, etoposide and intrathecal methotrexate (IVAC). The modified treatment regimen was associated with no grade 3/4 neuropathy and only one episode of grade 3/4 mucositis. All patients completed protocol therapy and there were no treatment-related deaths. Twelve patients (86%, 90% CI: 61 97%) achieved a complete response; 1 patient achieved a PR and 1 patient died of progressive disease. Nine patients (64%) are alive and disease free at a median follow-up of 29 months. This modified Magrath regimen is effective and well-tolerated in a representative group of older adult patients.\n\nsentence: Low-risk patients received three cycles of modified CODOX-M ( cyclophosphamide , doxorubicin , adriamycin , vincristine with intrathecal methotrexate and cytarabine followed by high-dose systemic methotrexate , regimen A ) .", "role": "user" }, { "content": "[[\"cyclophosphamide\", \"doxorubicin\", \"vincristine\", \"methotrexate\", \"cytarabine\", \"adriamycin\", \"POS\"]]", "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 hypersensitivity to DNA crosslinking agents a hallmark of Fanconi anemia?\n\nContext: The Fanconi anemia (FA) core complex plays a central role in the DNA damage response network\nFAAP100-deficient cells display hallmark features of FA cells, including defective FANCD2 monoubiquitination, hypersensitivity to DNA crosslinking agents, and genomic instability.\nFanconi anemia (FA) is a rare genetic disorder characterized by aplastic anemia, cancer/leukemia susceptibility and cellular hypersensitivity to DNA crosslinking agents, such as cisplatin.\nFanconi anemia (FA) is an inherited chromosomal recessive syndrome characterized by cellular hypersensitivity to DNA crosslinking agents and bone marrow failure, which cause aplastic anemia, and an increased incidence of malignancy.\nFeatures of chromosomal aberrations, hypersensitivity to DNA crosslinking agents, and predisposition to malignancy have suggested a fundamental anomaly of DNA repair in Fanconi anemia.\nFanconi anemia (FA) is one of several genetic diseases with characteristic cellular hypersensitivity to DNA crosslinking agents which suggest that FA proteins may function as part of DNA repair processes.\nFanconi anemia (FA) is characterized by cellular hypersensitivity to DNA crosslinking agents, but how the Fanconi pathway protects cells from DNA crosslinks and whether FA proteins act directly on crosslinks remain unclear.\nFanconi Anemia (FA) is a rare genetic disorder associated with a bone-marrow failure, cancer predisposition and hypersensitivity to DNA crosslinking agents.\nFanconi anemia (FA) is a heterogeneous disease associated with a bone marrow failure, cancer predisposition and hypersensitivity to DNA crosslinking agents.\nFanconi anemia (FA) is an inherited disorder characterized by defective DNA repair and cellular sensitivity to DNA crosslinking agents.\nFanconi anemia (FA) is an inherited disease characterized by bone marrow failure, increased cancer risk and hypersensitivity to DNA cross-linking agents, implying a role for this pathway in the maintenance of genomic stability.\nGenetic or epigenetic inactivation of the pathway formed by the Fanconi Anemia (FA) proteins occurs in several cancer types, including head and neck squamous cell carcinomas (HNSCC), rendering the affected tumors potentially hypersensitive to DNA crosslinking agents.\nFanconi Anemia (FA) is a rare autosomic recessive and X-linked disease with chromosomal instability after exposure to crosslinking agents as the hallmark.\nFanconi Anemia (FA) is an autosomal recessive disease characterized by chromosome instability, cellular hypersensitivity to DNA cross-linking agents, and increased predisposition to malignancies.\nThe Bloom protein (BLM) and Topoisomerase IIIalpha are found in association with proteins of the Fanconi anemia (FA) pathway, a disorder manifesting increased cellular sensitivity to DNA crosslinking agents.\nUsing siRNA depletion and gene knockout techniques, we show that FAAP100-deficient cells display hallmark features of FA cells, including defective FANCD2 monoubiquitination, hypersensitivity to DNA crosslinking agents, and genomic instability.\nFanconi anemia (FA) is a recessive human cancer prone syndrome featuring bone marrow failure, developmental abnormalities and hypersensitivity to DNA crosslinking agents exposure.\nFA is a chromosome instability syndrome characterized by childhood-onset aplastic anemia, cancer or leukemia susceptibility, and cellular hypersensitivity to DNA crosslinking agents.\nFunctional defects in the Fanconi pathway can result in a marked hypersensitivity to interstrand crosslinking agents, such as mitomycin C.\nAt the cellular level, hypersensitivity to DNA interstrand crosslinks is the defining feature in Fanconi anemia.\nDNA crosslinking agents may led to DNA cross-linking lesion, and Fanconi anemia pathway plays a key role in repairing its cross-linking.\nFanconi anemia (FA), an autosomal recessive disorder of children, is characterized by congenital or childhood aplastic anemia, multiple developmental anomalies, increased incidence of myeloid leukemia, increased spontaneous chromosome breakage, and cellular and chromosomal hypersensitivity to DNA bifunctional crosslinking and alkylating agents.\nelegans provides an excellent model system for the study of the Fanconi Anemia (FA), one of the hallmarks of which is sensitivity to interstrand crosslinking agents\nUsing siRNA depletion and gene knockout techniques, we show that FAAP100-deficient cells display hallmark features of FA cells, including defective FANCD2 monoubiquitination, hypersensitivity to DNA crosslinking agents, and genomic instability\nOne of the hallmark phenotypes of FA is cellular hypersensitivity to agents that induce DNA interstrand crosslinks (ICLs), such as mitomycin C (MMC)\nFurthermore, the cytological hallmark of FA, the DNA crosslink-induced radial chromosome formation, exemplifies an innate impairment in the repair of these particularly cytotoxic DNA lesions [A.D\nFanconi anemia (FA) is characterized by cellular hypersensitivity to DNA crosslinking agents, but how the Fanconi pathway protects cells from DNA crosslinks and whether FA proteins act directly on crosslinks remain unclear\nFeatures of chromosomal aberrations, hypersensitivity to DNA crosslinking agents, and predisposition to malignancy have suggested a fundamental anomaly of DNA repair in Fanconi anemia\nFanconi anemia (FA) is an inherited chromosomal recessive syndrome characterized by cellular hypersensitivity to DNA crosslinking agents and bone marrow failure, which cause aplastic anemia, and an increased incidence of malignancy\nGenetic or epigenetic inactivation of the pathway formed by the Fanconi Anemia (FA) proteins occurs in several cancer types, including head and neck squamous cell carcinomas (HNSCC), rendering the affected tumors potentially hypersensitive to DNA crosslinking agents\nFanconi anemia (FA) is a human autosomal disorder characterized by cancer susceptibility and cellular sensitivity to DNA crosslinking agents such as mitomycin C and diepoxybutane\nThe Fanconi anemia pathway promotes DNA glycosylase-dependent excision of interstrand DNA crosslinks.\nDNA crosslinking agents may led to DNA cross-linking lesion, and Fanconi anemia pathway plays a key role in repairing its cross-linking\nFA is a chromosome instability syndrome characterized by childhood-onset aplastic anemia, cancer or leukemia susceptibility, and cellular hypersensitivity to DNA crosslinking agents\nThe disease is manifested by defects in DNA repair, hypersensitivity to DNA crosslinking agents, and a high degree of chromosomal aberrations", "role": "user" }, { "content": "yes", "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:\na 2-month - old girl was brought to us with haziness of both eyes for the past 20 days .\nshe was a full - term baby delivered by cesarean section with a birth weight of 2.75 kg .\nthe parents denied any history of trauma and the child was otherwise healthy . on examination ( under general anesthesia ) , she was noted to have conjunctival hyperemia , increased corneal diameter ( 13.5 mm od , 11 mm os ) , corneal haze with small blood clots in the anterior chamber of both eyes .\nintraocular pressure ( iop ) was noted to be 20 mm hg od and 8 mm hg os by perkin 's tonometer .\na few yellowish - orange skin nodules were noted on the forehead and neck [ fig .\n2 ] , that progressively increased on follow - up . remainder of her systemic and neurological examination was normal .\nexcision biopsy of a forehead skin lesion was performed under general anesthesia and histopathological examination of the specimen showed non - langerhans histiocytic proliferation [ fig . 3 ] .\nimmunohistochemistry was negative for cd1a and cytokeratin ; positive for cd68 . with the above clinical picture and laboratory finding\nleft , corneal edema right eye ; top right : hyphema after resolution of corneal edema left eye ; bottom left : development of cataract ; bottom right : after cataract extraction resolution of skin lesion over the period of 1 year histopathology of skin lesion .\nlow power ( 100 ) : structure of acanthotic skin with sub epidermal infiltration of xanthomatous cells ( arrow ) and inflammatory cells with encircling adnexal structure and extending into subcutaneous zone .\nhigh power ( 1000 ) : sheets of foamy histiocytes ( arrow ) with interspersed multinucleated giant cells ( block arrow ) she was started on a topical antibiotic steroid combination , cycloplegic and dorzalamide ou . on her review visits , she developed posterior synechiae and a few iris nodules in the left eye , which resolved with intensive topical steroids .\nshe maintained a steady central fixation throughout her treatment and was also on regular review with a pediatrician .\nfour months after her first presentation , she developed bilateral anterior subcapsular cataract , which gradually progressed .\ntopical prednisolone acetate 4 times a day was added to topical antibiotics a day before surgery .\nafter peritomy , the bleeders were cauterized and a limbal groove made with a blade breaker .\nthe anterior chamber was entered by deepening the groove and trypan blue was injected under an air bubble .\nthe anterior capsule was punctured by a bent 26 g needle and capsulorhexis done with a utrata forceps .\nthe bottle height was raised to increase pressure in the anterior chamber and tamponade any bleeding .\nsubsequently , the posterior capsule was punctured by a bent 26 g needle in a sideways fashion and capsulorhexis completed by an utrata forceps .\nan intraocular lens ( iol ) was not implanted given the age of the patient ( < 1 year ) .\nafter surgery , she was started on topical steroid antibiotic combination and cycloplegics , which were tapered over 6 weeks .\nthe right eye cataract surgery was done 6 weeks after the left eye surgery and a similar procedure was followed .\n1 year after surgery , the child was comfortable with aphakic correction and the visual axis was clear .\nthe iop was noted to be normal on all occasions and no antiglaucoma medications were needed .\ntouton 's giant cells were absent in our patient ; however , she had features suggestive of a non - langerhan 's cell histiocytosis as suggested by the absence of a cd1a and cytokeratin .\nocular involvement in jxg is in the form of diffuse or discrete vascular iris nodules , which may bleed , resulting in spontaneous hyphema and secondary glaucoma .\nthe condition may also involve the ciliary body , anterior choroid , cornea , lids , limbus , orbit , retina , optic nerve and optic nerve , but intraocular involvement is rare ( < 1% of cases ) .\nindeed jxg should be included in the differential diagnosis of spontaneous hyphema in this age group and one should make a careful evaluation to detect skin nodules , which can be difficult to detect early in dark skinned individuals .\nthis could be because patient was taken up for surgery once the iris nodules and hyphema had resolved and patient was continued on topical steroids .\nit is likely that the use of intracameral adrenaline , raising the bottle height and a tight wound closure reduced the risk of bleeding in our patient . in general ,\nbimanual anterior limbal vitrectomy is preferred over a pars plana vitrectomy after primary posterior capsulotomy in pediatric cataract surgery .\nthis is because the technique is simpler and most cataract surgeons are comfortable with an anterior approach .\nan iol was not implanted in our patient considering the anterior segment inflammation and the bilaterality .\nfurthermore , the safety and benefits of iol implantation in infancy is not well - established .\nmanagement as detailed above may reduce the risk of bleeding and improve the visual outcome .", "role": "user" }, { "content": "there is limited literature on the management of cataracts in juvenile xanthogranuloma ( jxg ) . \n a 2-month - old girl presented to us with hyphema , secondary glaucoma ou and skin nodules suggestive of jxg . \n she developed bilateral cataracts during her follow - up and was treated successfully with cataract surgery and aphakic rehabilitation .", "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\nVariant ventricular tachycardia in desipramine toxicity. We report a case of variant ventricular tachycardia induced by desipramine toxicity. Unusual features of the arrhythmia are repetitive group beating, progressive shortening of the R-R interval, progressive widening of the QRS complex with eventual failure of intraventricular conduction, and changes in direction of the QRS axis. Recognition of variant ventricular tachycardia is important because therapy differs from that of classic ventricular tachycardia.", "role": "user" }, { "content": "{\"Chemical\": [\"desipramine\"], \"Disease\": [\"arrhythmia\", \"ventricular tachycardia\", \"toxicity\"]}", "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: In the past YOLO struggled with small objects. However, now we see a reversal in that trend. With the new multi-scale predictions we see YOLOv3 has relatively high AP{}_{S} performance. However, it has comparatively worse performance on medium and larger size objects. More investigation is needed to get to the bottom of this.\n\nQuestion: YoloV3 is most suited for small, medium or large size objects?", "role": "user" }, { "content": "YOLOv3 now struggles more with medium and larger size objects, i.e., performs worse than before. On the other hand, it is more succesful for smaller objects.", "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: Char-RNN and Active Learning for Hashtag Segmentation\n\nWe explore the abilities of character recurrent neural network (char-RNN) for hashtag segmentation. Our approach to the task is the following: we generate synthetic training dataset according to frequent n-grams that satisfy predefined morpho-syntactic patterns to avoid any manual annotation. The active learning strategy limits the training dataset and selects informative training subset. The approach does not require any language-specific settings and is compared for two languages, which differ in inflection degree.\n\nNeural Model for Hashtag Segmentation ::: Sequence Labeling Approach\nWe treat hashtag segmentation as a sequence labeling task. Each character is labeled with one of the labels $\\mathcal {L} = \\lbrace 0, 1\\rbrace $, (1) for the end of a word, and (0) otherwise (Table TABREF9 and TABREF9). Given a string $s = {s_1, \\ldots , s_n}$ of characters, the task is to find the labels $Y^* = {y_1^*. \\ldots , y_n^*}$, such that $ Y^* = \\arg \\max _{Y \\in \\mathcal {L} ^n} p(Y | s).$\nThe neural model for hashtag segmentation consists of three layers.\nThe embedding layer is used to compute the distributed representation of input characters. Each character $c_i$ is represented with an embedding vector $e_i \\in \\mathbb {R}^{d_e}$, where $d_e$ is the size of the character embedding. $E$ is the look up table of size $|V| \\times d_e$, where $V$ is the vocabulary, i.e. the number of unique characters.\nThe feature layer is used to process the input. We use a bi-directional recurrent layer with LSTM units to process the input in forward and backward directions. The LSTM units we use are default keras LSTM units as introduced by Hochreiter.\nThe inference layer is used to predict the labels of each character. We use a single dense layer as f or inference and $softmax$ to predict the probabilities of the labels $\\mathcal {L} = \\lbrace 0, 1\\rbrace $.\nEach character is assigned with the most probable label.\nThe parameters of the char-RNN are the following:\nEmbedding layer = 50 input dimensions;\nFeature layer = 64 bidirectional LSTM units;\nInference layer = 2 output neurons with softmax activation function mapped to each of 64 outputs.\n\nDataset ::: Russian dataset\nTo our knowledge there is no available dataset for hashtag segmentation in Russian, so we faced the need to create our own dataset. Our approach to the dataset creation was twofold: the training data was created from social network texts by selecting frequent $n$-grams and generating hashtags following some hashtag patterns. The test dataset consists of real hashtags collected from vk.com (a Russian social network) and were segmented manually.\nWe followed the same strategy to create an English language dataset.\n\nDataset ::: Russian dataset ::: Training Dataset Generation\nWe scraped texts from several pages about civil services from vk.com. Next we extracted frequent $n$-grams that do not contain stopwords and consist of words and digits in various combinations (such as word + 4 digits + word or word + word + 8 digits). We used several rules to merge these $n$-grams so that they resemble real hashtags, for example:\nremove all whitespace: wordwordworddigits\nExamples: ЁлкаВЗазеркалье, нескольколетназад\nreplace all whitespace with an underscore: word_word_digits\nExamples: увд_юга_столицы\nremove some whitespace and replace other spaces with an underscore: word_worddigits.\nExamples: ищусвоегогероя_уфпс\nA word here might be a word in lower case, upper case or capitalized or an abbreviation. There might be up to four digits.\nIn general, we introduced 11 types of hashtags, which contain simply constructed hashtags as well as the complex ones. Here are a couple of examples:\nThe hashtag consists of two parts: the word/abbreviation in the first part and the number or word in the second. The underscore is a delimiter.\nExamples: word_2017, NASA_2017, word_word\nTwo or three words, which are separated by an underscore.\nExamples: Word_Word, word_word_word\n\nDataset ::: Russian dataset ::: Test Dataset Annotation\nWe segmented manually 2K the most frequent hashtags, extracted from the same collection of the scraped texts.\nThe resulting size of the Russian dataset is 15k hashtags for training and 2k hashtags for testing.\n\nDataset ::: English dataset\nWe used the dataset, released by BIBREF0. This dataset consists of:\na collection of tweets, which we used to generate the synthetic training hashtags according to the same rules as for Russian;\na collection of annotated and separated hashtags, which we used as a testing set. From this test set we excluded ambiguous hashtags, annotated with several possible segmentations.\nThe resulting size of the English dataset is 15k hashtags for training and 1k hashtags for testing.\n\nExperiments ::: Baseline\nAs for baseline algorithm, we consider the BIBREF0 system architecture as a state-of-the-art algorithm. Unfortunately, their approach is not straightforwardly applicable to our synthetic Russian dataset, because it requires twofold input: a hashtag and a corresponding tweet or a text from any other social media, which is absent in our task setting due to synthetic nature of the training dataset.\nFor this reason as a baseline algorithm for English dataset we refer to results from BIBREF0, and as for Russian dataset, we used the probabilistic language model, described in BIBREF8. The probability of a sequence of words is the product of the probabilities of each word, given the word’s context: the preceding word. As in the following equation:\nwhere\nIn case there is no such a pair of words $(w_{i-1}, w_i)$ in the set of bigrams, the probability of word $w_i$ is obtained as if it was only an unigram model:\nwhere $V$ – vocabulary, $f(w_{i})$ – frequency of word $w_{i}$, and $\\alpha $ = 1.\nIn Table TABREF30 we present three baseline results: LM BIBREF8 for Russian and English datasets; context-based LM BIBREF0 for English dataset only. We treat a segmentation as correct if prediction and target sequences are the same.\n\nExperiments ::: Neural Model\nIn our experiments we used 5 epochs to train the char-RNN with LSTM units. For each language we observed three datasets with different number of hashtags. In case of Russian language, the more data we use while training, the higher the accuracy. As for English, the highest accuracy score was achieved on a set of 10k hashtags (Table TABREF32). Due to it's lower morphological diversity and complexity the model starts to overfit on training sets with large sizes. The training showed that mostly the model makes wrong predictions of segmentation on hashtags of complex types, such as “wordword_worddigits”.\nOur results outperform all choosen baseline both for Russian and English datasets. Note, that we have two baselines for the English dataset: one is purely frequency-based, another is cited from BIBREF0, where external resources are heavily used. We show that using significantly less amount of training data, we achieve a boost in quality by switching from statistical word language models to char-RNN. As expected, the results on Russian dataset are higher than for the English dataset due to higher inflection degree in Russian as opposed to English.\n\nExperiments ::: Visualization\nIn order to see if embeddings of similar characters, in terms of string segmentation, appear near each-other in their resulting 50-dimensional embedding space, we have applied one technique for dimensionality reduction: SVD to character embeddings to plot them on 2D space. For both languages meaningful and interpretable clusters can be extracted: capital letters, letters in lower case, digits and underscore, as shown below.\n\nRelated Work\nThe problem of word segmentation has received much attention in Chinese and German NLP for word segmentation and compound splitting BIBREF10, respectively. The major techniques for word segmentation exploit string matching algorithms BIBREF11, language models BIBREF12, BIBREF0 and sequence labeling methods BIBREF10. Recent trend of deep learning as a major approach for any NLP task in general and sequence labeling in particular resulted in using various RNN-based models and CNN-based model for Chinese word segmentation BIBREF10, BIBREF13, BIBREF14.\nSince BIBREF10 Chinese word segmentation is addressed as a character labeling task: each character of the input sequence is labeled with one of the four labels $\\mathcal {L} = \\lbrace B, M, E, S\\rbrace $, which stand for character in Begin, Middle or End of the word or Single character word. BIBREF10 uses a maximum entropy tagger to tag each character independently. This approach was extended in BIBREF15 to the sequence modeling task, and linear conditional random fields were used to attempt it and receive state of the art results. A neural approach to Chinese segmentation mainly uses various architectures of character level recurrent neural networks BIBREF16, BIBREF17, BIBREF18 and very deep constitutional networks BIBREF19. Same architectures are used for dialectal Arabic segmentation BIBREF20.\nThe evolution of German compound splitters is more or less similar to Chinese word segmentation systems. The studies of German compound splitting started with corpus- and frequency-based approaches BIBREF13, BIBREF14 and are now dominated with neural-based distributional semantic models. However, German compound splitting is rarely seen as sequence modeling task.\nThe problem of hashtag segmentation, analysis and usage in English has been approached by several research groups. As it was shown by BIBREF12 hashtag segmentation for TREC microblog track 2011 BIBREF21 improves the quality of information retrieval, while BIBREF0 shows that hashtag segmentation improves linking of entities extracted from tweets to a knowledge base. Both BIBREF12, BIBREF0 use Viterbi-like algorithm for hashtag segmentation: all possible segmentations of hashtag are scored using a scoring function:\nwhere $P_{Unigram}$ are probabilities, computed according to the unigram model based on a large enough corpus or any N-gram service.\nFollowing the idea of scoring segmentation candidates, BIBREF11 introduces other scoring functions, which include a bigram model (2GM) and a Maximum Unknown Matching (MUM), which is adjustable to unseen words.\nBIBREF22 attempt to split camel-cased hashtags using rule-based approach and POS-tagging for further semantic classification. WordSegment has been used for sentiment analysis BIBREF23, BIBREF24 and other applications.\nTo our knowledge there has been little work done for word or hashtag segmentation in Russian.\n\nConclusions\nIn this paper we approach the problem of hashtag segmentation by using char-RNNs. We treat the problem of hashtag segmentation as a sequence labeling task, so that each symbol of a given string is labeled with 1 (there should be a whitespace after this symbol) or 0 (otherwise). We use two datasets to test this approach in English and in Russian without any language-specific settings. We compare char-RNN to traditional probabilistic algorithms. To interpret the results we use a few visualization techniques and the strategy of active learning to evaluate the complexity of training data, since we use synthetically generated hashtags for training.\nThe results show that:\nWhen approached on character level, hashtag segmentation problem can be solved using relatively small and simple recurrent neural network model without usage of any external corpora and vocabularies. Such char-RNN not only outperforms significantly traditional frequency-based language models, but also can be trained on synthetic data generated according to morpho-syntactic patterns, without any manual annotation and preprocessing.\nIn languages with high inflection (such as Russian) the char-RNN achieves higher results than in languages with little inflections (such as English) due to the ability of the char-RNN to capture and memorize word boundary patterns, especially word ending patterns (i.e. adjective endings “ый”,“ая”,“ое” or verbal endings “ать”,“еть” in Russian).\nThe amount of generated synthetic training data can be limited by using techniques for active learning which allows to select sufficient training subset without any loss of quality.\n\nTable 2. Illustration of sequence labeling for segmentation \"#photooftheday\" [photo of the day]\n\nFig. 1. Neural model for hashtag segmentation\n\nTable 5. Accuracy of LSTM char-RNN on both Russian and English datasets\n\nFig. 3. Accuracy obtained on English Dataset\n\nQuestion: Which languages are used in the paper?", "role": "user" }, { "content": "{\"answer\": [\"English\", \"Russian\"], \"evidence\": [\"For this reason as a baseline algorithm for English dataset we refer to results from BIBREF0, and as for Russian dataset, we used the probabilistic language model, described in BIBREF8. The probability of a sequence of words is the product of the probabilities of each word, given the word\\u2019s context: the preceding word. As in the following equation:\"]}", "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\nFK506 and ciclosporin: molecular probes for studying intracellular signal transduction. The immunosuppressants ciclosporin and FK506 block the Ca (2 +) -dependent signal-transduction pathway emanating from the T-cell receptor, thereby inhibiting the activation of helper T cells. Using these drugs as probes, chemists and biologists have uncovered several intracellular signalling molecules bridging the generation of second-messenger Ca2 + ions and the transcriptional activation of IL-2, among which are calmodulin, calcineurin and the nuclear factor of activated T cells (NF-AT). Hence, Ca2 + binds to calmodulin, leading to the binding of calmodulin to calcineurin; the activated calcineurin, in turn, may dephosphorylate the cytoplasmic subunit of NF-AT, resulting in its translocation from the cytoplasm into the nucleus to form a competent transcriptional activator. As described by Jun Liu, these drugs manifest their effects in an unprecedented fashion. They do not directly intercept intracellular signalling molecules. Instead, they form tight complexes with two different classes of abundant cytosolic receptors called immunophilins upon entering the cell, and consequently inhibit their peptidyl prolyl cis-trans isomerase activities. The two structurally distinct immunophilin-drug complexes bind to, and inhibit, the phosphatase activity of calcineurin.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"helper T cells\", \"activated T cells\", \"T cells\"], \"DNA\": [], \"Protein\": [\"T - cell receptor\", \"nuclear factor of activated T cells\", \"peptidyl prolyl cis - trans isomerase\", \"immunophilin - drug complexes\", \"calcineurin\", \"cytoplasmic subunit of NF - AT\", \"immunophilins\", \"IL - 2\", \"phosphatase\", \"Jun\", \"competent transcriptional activator\", \"cytosolic receptors\", \"NF - AT\", \"calmodulin\"], \"RNA\": []}", "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\nDNA methylation detection at single base resolution using targeted next generation bisulfite sequencing and cross validation using capillary sequencing With a purpose of accurate and simultaneous determination of DNA methylation from multiple loci in multiple samples, here, we are demonstrating a method to aid rapid DNA methylation detection of genomic sequences. Using genomic DNA of peripheral blood from 14 healthy individuals, DNA methylation in 465 CpG sites from 12 loci of genes (ADAM22, ATF2, BCR, CD83, CREBBP, IL12B, IL17RA, MAP2K2, RBM38, TGFBR2, TGFBR3, and WNT5A) was analysed by targeted next generation bisulfite sequencing. Analysed region for three genes, BCR, IL17RA and RBM38 showed an absolute mean DNA methylation of 25.6%, 89.2% and 38.9% respectively. Other nine gene loci were unmethylated and exhibited <10% absolute mean DNA methylation. Two genes, IL17RA and RBM38 were technically validated using direct capillary sequencing and results were comparable with positive correlation (P=0.0088 & P<0.0001 respectively) in the CpG sites for DNA methylation. All CpG sites analysed from RBM38 genes locus displayed 95% limits of agreement for DNA methylation measurements from the two methods. The present approach provides a fast and reliable DNA methylation quantitative data at single base resolution with good coverage of the CpG sites under analysis in multiple loci and samples simultaneously. Use of targeted next generation bisulfite sequencing may provide an opportunity to explore genes in the discovery panel for biomarker identification and facilitate functional validation.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"loci of genes\", \"samples\", \"loci\", \"ADAM22\", \"ATF2\", \"IL12B\", \"IL17RA\", \"RBM38\", \"gene loci\", \"CD83\", \"CREBBP\", \"MAP2K2\", \"TGFBR2\", \"BCR\", \"WNT5A\", \"genes\", \"genomic\", \"TGFBR3\"], \"Bacterium\": [], \"BiologicFunction\": [\"DNA methylation\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [\"peripheral blood\"], \"BodySystem\": [], \"Chemical\": [\"CpG sites\", \"genomic DNA\"], \"ClinicalAttribute\": [\"biomarker\"], \"Eukaryote\": [], \"Finding\": [\"positive\", \"resolution\", \"unmethylated\"], \"Food\": [], \"HealthCareActivity\": [\"determination\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"method\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"individuals\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"capillary sequencing\", \"Analysed\", \"analysed\", \"direct capillary sequencing\", \"validation\", \"cross validation\", \"technically validated\", \"next generation bisulfite sequencing\"], \"SpatialConcept\": [\"sequences\", \"locus\", \"single base\"], \"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: [\"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\nRecycling factors for ribosome disassembly in the apicoplast and mitochondrion of Plasmodium falciparum. The reduced genomes of the apicoplast and mitochondrion of the malaria parasite Plasmodium falciparum are actively translated and antibiotic-mediated translation inhibition is detrimental to parasite survival. In order to understand recycling of organellar ribosomes, a critical step in protein translation, we identified ribosome recycling factors (RRF) encoded by the parasite nuclear genome. Targeting of PfRRF1 and PfRRF2 to the apicoplast and mitochondrion respectively was established by localization of leader sequence-GFP fusions. Unlike any RRF characterized thus far, PfRRF2 formed dimers with disulphide interaction(s) and additionally localized in the cytoplasm, thus suggesting adjunct functions for the factor. PfRRF1 carries a large 108-amino-acid insertion in the functionally critical hinge region between the head and tail domains of the protein, yet complemented Escherichia coli RRF in the LJ14frr(ts) mutant and disassembled surrogate E. coli 70S ribosomes in the presence of apicoplast-targeted EF-G. Recombinant PfRRF2 bound E. coli ribosomes and could split monosomes in the presence of the relevant mitochondrial EF-G but failed to complement the LJ14frr(ts) mutant. Although proteins comprising subunits of P. falciparum organellar ribosomes are predicted to differ from bacterial and mitoribosomal counterparts, our results indicate that the essential interactions required for recycling are conserved in parasite organelles.", "role": "user" }, { "content": "{\"Chemical\": [\"disulphide\", \"amino-acid\"]}", "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 antiepileptic drug is most strongly associated with spina bifida? \n\nContext: The teratogenicity of antiepilepsy drug valproic acid (VPA) mostly is found in genetic and somatic levels, causing teratogenesis involving neurotubular defects (NTDs), anencephaly, lumbosacral meningomyelocele, and leg dysfunction due to spina bifida aperta.\nThe summary odds ratio estimate for the association between valproic acid and spina bifida was 11.9 (95% uncertainty interval (UI): 4.0-21.2); for valproic acid and cleft palate 5.8 (95% UI: 3.3-9.5); for carbamazepine and spina bifida 3.6 (95% UI: 1.3-7.8); and for carbamazepine and cleft palate 2.4 (95% UI: 1.1-4.5) in the United States.\nIncreased risk for MCMs could be demonstrated only for exposure to valproate (5.6%, p = 0.005) and AED polytherapy (6.1%, p = 0.02). Neonatal spina bifida was not significantly increased, but was a major indication for elective pregnancy termination among women with epilepsy.\nValproic acid, a drug commonly used to treat seizures and other psychiatric disorders, causes neural tube defects (NTDs) in exposed fetuses at a rate 20 times higher than in the general population. Failure of the neural tube to close during development results in exencephaly or anencephaly, as well as spina bifida.\nAssociations were found for spina bifida with valproic acid.\nFetal exposure to valproic acid or carbamazepine increases the risk of neural tube defect (NTD)\nWomen with epilepsy giving birth during 1973 to 1991 were identified by record linkage of Swedish health registries. Among 3,625 identified infants, 9 had spina bifida. A nested case-control study was performed, comparing drugs used in early pregnancy in the 9 cases and in 18 controls, matched for year of delivery, maternal age, and parity. Six of the spina bifida mothers had used carbamazepine and two had used valproic acid. Among the controls, 5 women used carbamazepine and one valproic acid. There is an apparent excess risk for spina bifida after use of either of these two drugs, but it is not statistically significant when the analysis is restricted to drug-using women. T\nA significant association was seen between maternal use of valproic acid and spina bifida, and a weaker, non-significant one between carbamazepine and spina bifida.\nA statistically significant association between Spina Bifida and Valproic Acid (odds ratio 22.7; Fisher p value = 0.0364) was observed: no other anticonvulsant tested showed any association with any type of malformation.", "role": "user" }, { "content": "Valproate", "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: In many patients hospitalized with the coronavirus, the immune system is threatened by a depletion of certain essential cells, suggesting eerie parallels with H.I.V.\n\nAbstract:\nThe outbreak of the 2019 Novel Coronavirus (SARS-CoV-2) rapidly spread from Wuhan, China to more than 150 countries, areas or territories, causing staggering number of infections and deaths.\nA systematic profiling of the immune vulnerability landscape of SARS-CoV-2, which can bring critical insights into the immune clearance mechanism, peptide vaccine development, and antiviral antibody development, is lacking.\nIn this study, we investigated the potential of the SARS-CoV-2 viral proteins to induce class I and II MHC presentation and to form linear antibody epitopes.\nWe created an online database to broadly share the predictions as a resource for the research community.\nUsing this resource, we showed that genetic variations in SARS- CoV-2, though still few for the moment, already follow the pattern of mutations in related coronaviruses, and could alter the immune vulnerability landscape of this virus.\nImportantly, we discovered evidence that SARS-CoV-2, along with related coronaviruses, used mutations to evade attack from the human immune system.\nOverall, we present an immunological resource for SARS-CoV-2 that could promote both therapeutic development and mechanistic research.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "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: We used an innovative combination of in vitro experimentation and within-host modeling to explore the impact of unique bat immunity on virus dynamics. Critically, we found that bat cell lines demonstrated a signature of enhanced interferon-mediated immune response, of either constitutive or induced form, which allowed for establishment of rapid within-host, cell-to-cell virus transmission rates (b). These results were supported by both data-independent bifurcation analysis of our mean field theoretical model, as well as fitting of this model to viral infection time series established in bat cell culture. Additionally, we demonstrated that the antiviral state induced by the interferon pathway protects live cells from mortality in tissue culture, resulting in in vitro epidemics of extended duration that enhance the probability of establishing a long-term persistent infection. Our findings suggest that viruses evolved in bat reservoirs possessing enhanced IFN capabilities could achieve more rapid within-host transmission rates without causing pathology to their hosts. Such rapidly-reproducing viruses would likely generate extreme virulence upon spillover to hosts lacking similar immune capacities to bats. To achieve these results, we first developed a novel, within-host, theoretical model elucidating the effects of unique bat immunity, then undertook bifurcation analysis of the model's equilibrium properties under immune absent, induced, and constitutive assumptions. We considered a cell line to be constitutively immune if possessing any number of antiviral cells at disease-free equilibrium but allowed the extent of constitutive immunity to vary across the parameter range for \", the constitutive rate of antiviral acquisition. In deriving the equation for R 0 , the basic reproduction number, which defines threshold conditions for virus invasion of a tissue (R 0 >1), we demonstrated how the invasion threshold is elevated at high values of constitutive antiviral acquisition, \". Constitutive immune processes can thus prohibit pathogen invasion, while induced responses, by definition, can only control infections post-hoc. Once thresholds for pathogen invasion have been met, assumptions of constitutive immunity will limit the cellular mortality (virulence) incurred at high transmission rates. Regardless of mechanism (induced or constitutive), interferon-stimulated antiviral cells appear to play a key role in maintaining longer term or persistent infections by safeguarding susceptible cells from rapid infection and concomitant cell death. Fitting of our model to in vitro data supported expected immune phenotypes for different bat cell lines as described in the literature. Simple target cell models that ignore the effects of immunity best recapitulated infectious time series derived from IFN-deficient Vero cells, while models assuming induced immune processes most accurately reproduced trials derived from RoNi/7.1 (Rousettus aegyptiacus) cells, which possess a standard virusinduced IFN-response. In most cases, models assuming constitutive immune processes best recreated virus epidemics produced on PaKiT01 (Pteropus alecto) cells, which are known to constitutively express the antiviral cytokine, IFN-a (Zhou et al., 2016) . Model support for induced immune assumptions in fits to rVSV-MARV infections on PaKiT01 cells suggests that the constitutive IFN-a expression characteristic of P. alecto cells may represent more of a constitutive immune priming process than a perpetual, functional, antiviral defense. Results from mean field model fitting were additionally confirmed in spatially explicit stochastic simulations of each time series. As previously demonstrated in within-host models for HIV (Coffin, 1995; Perelson et al., 1996; Nowak et al., 1995; Bonhoeffer et al., 1997; Ho et al., 1995) , assumptions of simple target-cell depletion can often provide satisfactory approximations of viral dynamics, especially those reproduced in simple in vitro systems. Critically, our model fitting emphasizes the need for incorporation of top-down effects of immune control in order to accurately reproduce infectious time series derived from bat cell tissue cultures, especially those resulting from the robustly antiviral PaKiT01 P. alecto cell line. These findings indicate that enhanced IFN-mediated immune pathways in bat reservoirs may promote elevated within-host virus replication rates prior to cross-species emergence. We nonetheless acknowledge the limitations imposed by in vitro experiments in tissue culture, especially involving recombinant viruses and immortalized cell lines. Future work should extend these cell culture studies to include measurements of multiple state variables (i.e. antiviral cells) to enhance epidemiological inference. The continued recurrence of Ebola epidemics across central Africa highlights the importance of understanding bats' roles as reservoirs for virulent zoonotic disease. The past decade has born witness to emerging consensus regarding the unique pathways by which bats resist and tolerate highly virulent infections (Brook and Dobson, 2015; Xie et al., 2018; Zhang et al., 2013; Ahn et al., 2019; Zhou et al., 2016; Ng et al., 2015; Pavlovich et al., 2018) . Nonetheless, an understanding of the mechanisms by which bats support endemic pathogens at the population level, or promote the evolution of virulent pathogens at the individual level, remains elusive. Endemic maintenance of infection is a defining characteristic of a pathogen reservoir (Haydon et al., 2002) , and bats appear to merit such a title, supporting long-term persistence of highly transmissible viral infections in isolated island populations well below expected critical community sizes (Peel et al., 2012) . Researchers debate the relative influence of population-level and within-host mechanisms which might explain these trends (Plowright et al., 2016) , but increasingly, field data are difficult to reconcile without acknowledgement of a role for persistent infections (Peel et al., 2018; Brook et al., 2019) . We present general methods to study cross-scale viral dynamics, which suggest that within-host persistence is supported by robust antiviral responses characteristic of bat immune processes. Viruses which evolve rapid replication rates under these robust antiviral defenses may pose the greatest hazard for cross-species pathogen emergence into spillover hosts with immune systems that differ from those unique to bats. All experiments were carried out on three immortalized mammalian kidney cell lines: Vero (African green monkey), RoNi/7.1 (Rousettus aegyptiacus) (Kühl et al., 2011; Biesold et al., 2011) and PaKiT01 (Pteropus alecto) (Crameri et al., 2009) . The species identifications of all bat cell lines was confirmed morphologically and genetically in the publications in which they were originally described (Kühl et al., 2011; Biesold et al., 2011; Crameri et al., 2009) . Vero cells were obtained from ATCC. Monolayers of each cell line were grown to 90% confluency (~9Â10 5 cells) in 6-well plates. Cells were maintained in a humidified 37˚C, 5% CO 2 incubator and cultured in Dulbecco's modified Eagle medium (DMEM) (Life Technologies, Grand Island, NY), supplemented with 2% fetal bovine serum (FBS) (Gemini Bio Products, West Sacramento, CA), and 1% penicillin-streptomycin (Life Technologies). Cells were tested monthly for mycoplasma contamination while experiments were taking place; all cells assayed negative for contamination at every testing. Previous work has demonstrated that all cell lines used are capable of mounting a type I IFN response upon viral challenge, with the exception of Vero cells, which possess an IFN-b deficiency (Desmyter et al., 1968; Rhim et al., 1969; Emeny and Morgan, 1979) . RoNi/7.1 cells have been shown to mount idiosyncratic induced IFN defenses upon viral infection (Pavlovich et al., 2018; Kuzmin et al., 2017; Arnold et al., 2018; Kühl et al., 2011; Biesold et al., 2011) , while PaKiT01 cells are known to constitutively express the antiviral cytokine, IFN-a (Zhou et al., 2016) . This work is the first documentation of IFN signaling induced upon challenge with the particular recombinant VSVs outlined below. We verified known antiviral immune phenotypes via qPCR. Results were consistent with the literature, indicating a less pronounced role for interferon defense against viral infection in RoNi/7.1 versus PaKiT01 cells. Replication-capable recombinant vesicular stomatitis Indiana viruses, expressing filovirus glycoproteins in place of wild type G (rVSV-G, rVSV-EBOV, and rVSV-MARV) have been previously described (Wong et al., 2010; Miller et al., 2012) . Viruses were selected to represent a broad range of anticipated antiviral responses from host cells, based on a range of past evolutionary histories between the virus glycoprotein mediating cell entry and the host cell's entry receptor. These interactions ranged from the total absence of evolutionary history in the case of rVSV-G infections on all cell lines to a known receptor-level cell entry incompatibility in the case of rVSV-MARV infections on PaKiT01 cell lines. To measure infectivities of rVSVs on each of the cell lines outlined above, so as to calculate the correct viral dose for each MOI, NH 4 Cl (20 mM) was added to infected cell cultures at 1-2 hr postinfection to block viral spread, and individual eGFP-positive cells were manually counted at 12-14 hr post-infection. Previously published work indicates that immortalized kidney cell lines of Rousettus aegyptiacus (RoNi/7.1) and Pteropus alecto (PaKiT01) exhibit different innate antiviral immune phenotypes through, respectively, induced (Biesold et al., 2011; Pavlovich et al., 2018; Kühl et al., 2011; Arnold et al., 2018) and constitutive (Zhou et al., 2016 ) expression of type I interferon genes. We verified these published phenotypes on our own cell lines infected with rVSV-G, rVSV-EBOV, and rVSV-MARV via qPCR of IFN-a and IFN-b genes across a longitudinal time series of infection. Specifically, we carried out multiple time series of infection of each cell line with each of the viruses described above, under mock infection conditions and at MOIs of 0.0001 and 0.001-with the exception of rVSV-MARV on PaKiT01 cell lines, for which infection was only performed at MOI = 0.0001 due to limited viral stocks and the extremely low infectivity of this virus on this cell line (thus requiring high viral loads for initial infection). All experiments were run in duplicate on 6well plates, such that a typical plate for any of the three viruses had two control (mock) wells, two MOI = 0.0001 wells and two MOI = 0.001 wells, excepting PaKiT01 plates, which had two control and four MOI = 0.0001 wells at a given time. We justify this PaKiT01 exemption through the expectation that IFN-a expression is constitutive for these cells, and by the assumption that any expression exhibited at the lower MOI should also be present at the higher MOI. For these gene expression time series, four 6-well plates for each cell line-virus combination were incubated with virus for one hour at 37˚C. Following incubation, virus was aspirated off, and cell monolayers were washed in PBS, then covered with an agar plaque assay overlay to mimic conditions under which infection trials were run. Plates were then harvested sequentially at timepoints of roughly 5, 10, 15, and 20 hr post-infection (exact timing varied as multiple trials were running simultaneously). Upon harvest of each plate, agar overlay was removed, and virus was lysed and RNA extracted from cells using the Zymo Quick RNA Mini Prep kit, according to the manufacturer's instructions and including the step for cellular DNA digestion. Post-extraction, RNA quality was verified via nanodrop, and RNA was converted to cDNA using the Invitrogen Superscript III cDNA synthesis kit, according to the manufacturer's instructions. cDNA was then stored at 4˚C and as a frozen stock at À20˚C to await qPCR. We undertook qPCR of cDNA to assess expression of the type I interferon genes, IFN-a and IFNb, and the housekeeping gene, b-Actin, using primers previously reported in the literature (Supplementary file 6) . For qPCR, 2 ml of each cDNA sample was incubated with 7 ml of deionized water, 1 ml of 5 UM forward/reverse primer mix and 10 ml of iTaq Universal SYBR Green, then cycled on a QuantStudio3 Real-Time PCR machine under the following conditions: initial denaturation at 94 C for 2 min followed by 40 cycles of: denaturation at 95˚C (5 s), annealing at 58˚C (15 s), and extension at 72˚C (10 s). We report simple d-Ct values for each run, with raw Ct of the target gene of interest (IFN-a or IFN-b) subtracted from raw Ct of the b-Actin housekeeping gene in Figure 1 -figure supplement 6. Calculation of fold change upon viral infection in comparison to mock using the d-d-Ct method (Livak and Schmittgen, 2001) was inappropriate in this case, as we wished to demonstrate constitutive expression of IFN-a in PaKiT01 cells, whereby data from mock cells was identical to that produced from infected cells. After being grown to~90% confluency, cells were incubated with pelleted rVSVs expressing eGFP (rVSV-G, rVSV-EBOV, rVSV-MARV). Cell lines were challenged with both a low (0.0001) and high (0.001) multiplicity of infection (MOI) for each virus. In a cell monolayer infected at a given MOI (m), the proportion of cells (P), infected by k viral particles can be described by the Poisson distribution: P k ð Þ ¼ e Àm m k k! , such that the number of initially infected cells in an experiment equals: 1 À e Àm . We assumed that a~90% confluent culture at each trial's origin was comprised of~9x10 5 cells and conducted all experiments at MOIs of 0.0001 and 0.001, meaning that we began each trial by introducing virus to, respectively,~81 or 810 cells, representing the state variable 'E' in our theoretical model.\n\nQuestion: How was the modeling carried out?", "role": "user" }, { "content": "an innovative combination of in vitro experimentation and within-host modeling to explore the impact of unique bat immunity on virus dynamics.", "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\nHuman mRNA polyadenylate binding protein: evolutionary conservation of a nucleic acid binding motif. We have isolated a full length cDNA (cDNA) coding for the human poly(A) binding protein. The cDNA derived 73 kd basic translation product has the same Mr, isoelectric point and peptidic map as the poly(A) binding protein. DNA sequence analysis reveals a 70,244 dalton protein. The N terminal part, highly homologous to the yeast poly(A) binding protein, is sufficient for poly(A) binding activity. This domain consists of a four-fold repeated unit of approximately 80 amino acids present in other nucleic acid binding proteins. In the C terminal part there is, as in the yeast protein, a sequence of approximately 150 amino acids, rich in proline, alanine and glutamine which together account for 48% of the residues. A 2,9 kb mRNA corresponding to this cDNA has been detected in several vertebrate cell types and in Drosophila melanogaster at every developmental stage including oogenesis.", "role": "user" }, { "content": "{\"Gene\": [\"nucleic acid binding proteins\", \"nucleic acid binding motif\", \"mRNA polyadenylate binding protein\", \"poly(A) binding protein\"]}", "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\nIn vivo assessment of periodontal structures and measurement of gingival sulcus with Optical Coherence Tomography: a pilot study There has been increasing interest on the development of clinically acceptable, more sensitive and specific methods for non-invasive diagnosis in Periodontics. In this pilot study, the performance of an Optical Coherence Tomography (OCT) system in imaging periodontal structures in humans was evaluated. Gingival sulcus depth measurements were obtained and compared with traditional probes. In total, 445 sites of 23 periodontally healthy individuals were measured by 3 instruments: North Carolina manual probe, Florida automated probe and OCT at 1325 nm. To obtain quantitative measurements from OCT images, the gingival refractive index was also determined. Discomfort / pain perception and the duration of examinations were compared among the instruments. The analysis of OCT images allowed the identification of relevant anatomic dental and periodontal regions. The average sulcus depth measured by OCT, 0.85 ± 0.27 mm and 0.87 ± 0.28 mm, was lower than the values obtained by manual and automated probing. Discomfort / pain were prevalent for traditional probes, which are invasive methods, than for the non-invasive OCT technique. OCT has the potential to be a reliable tool for in vivo periodontal tissues evaluation and for reproducible sulcus depth measurements in healthy sites. Further technological advances are required to reduce the procedure time and promote evaluation of posterior oral regions. Photonic assessment of periodontal tissue with OCT (top) in a clinical environment, showing tooth / gingiva features (bottom).", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"tooth\", \"periodontal tissues\", \"periodontal\", \"periodontal tissue\", \"gingiva\"], \"Bacterium\": [], \"BiologicFunction\": [\"perception\"], \"BiomedicalOccupationOrDiscipline\": [\"Periodontics\"], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [\"humans\"], \"Finding\": [\"Discomfort\", \"diagnosis\", \"pain\"], \"Food\": [], \"HealthCareActivity\": [\"evaluated\", \"OCT\", \"probing\", \"examinations\", \"imaging\", \"evaluation\", \"procedure\", \"assessment\", \"Optical Coherence Tomography\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"Photonic\"], \"MedicalDevice\": [\"Florida automated probe\", \"North Carolina manual probe\", \"instruments\", \"probes\"], \"Organization\": [], \"PopulationGroup\": [\"individuals\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"pilot study\"], \"SpatialConcept\": [\"gingival\", \"posterior\", \"gingival sulcus\", \"in vivo\", \"oral regions\", \"depth\", \"In vivo\", \"sites\", \"top\", \"environment\", \"bottom\", \"Gingival sulcus\", \"sulcus\", \"regions\", \"structures\"], \"Virus\": []}", "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:\nover last three decades , the role of hematopoietic stem cell transplant ( hsct ) in chronic myeloid leukemia ( cml ) has seen several phases and continues to be defined . in 1980 's ,\nhsct came as a revolutionary concept that offered cure from cml . in 1990 's ,\ntransplant methodologies were refined , which resulted in increased cure rates and decreased transplant - related mortality .\nsurvival outcomes improved significantly in chronic phase patients with 3 years survival rate of more than 80% .\nthirty years later , it is still the only treatment that offers cure in cml .\nthe ability of allogeneic hsct to cure cml is related to the antileukemic effects of both the conditioning regimen and the graft versus leukemia ( gvl ) effect of the donor lymphocytes . however , with the advent of imatinib in early 2000 's the natural history of cml was changed and so did the way we treated cml . with the excellent response rates and minimal toxicity imatinib soon became the treatment of choice for chronic phase cml , and it was thought that hsct was no longer needed at least in chronic phase . however , as our experience with imatinib increased , issues of resistance / intolerance in chronic phase emerged . at 18 months of treatment , imatinib resistance\nalso , the treatment of advanced phase disease ( accelerated and blast phases ) with imatinib proved to be inadequate .\nsecond - generation tyrosine kinase inhibitors ( tkis ) including dasatinib and nilotinib were able to achieve < 50% complete cytogenetic response ( ccyr ) in imatinib resistant / intolerant cases .\nthus , transplantation still has a definite , though more limited , role in the treatment of cml .\nin advanced phase disease , treatment with tkis can achieve initial good response ( second chronic phase ) .\nhowever , such responses are usually short lived and do not appear to be associated with long - term survival . in one study ,\nthe rate of major cyr and ccyr in accelerated phase patients treated with imatinib at 600 mg / day was only 24% and 17% , respectively . in another analysis of three phase ii studies of cml patients in blast crisis treated with 600 mg / day imatinib , at 36 months only 7% were disease free and only 14% were alive .\nhowever , it would be prudent to start the patient on a tki for two reasons .\nfirst , it tides over the time period required to find human leukocyte antigen ( hla ) matched unrelated donor if hla - matched sibling is not available .\nsecond , cure rates in advanced phase disease are better if transplanted in second chronic phase . among patients in chronic phase treated with imatinib as first line tki therapy , approximately 20% will fail primary therapy , either from intolerance , relapse or progression to advanced phase disease .\nit is reasonable to consider hsct at the time of first - line failure . however ,\nsecondary tki therapy should be started at the time of resistance for two reasons - first , a ccyr on secondary therapy is achieved in approximately 50% patients second , a donor search may take months .\npatients who relapse with a t315i mutation should proceed to transplant at the earliest , given the low - response rate to secondary therapy .\nsimilarly , those who have a mutation within the p loop region , which is known to be associated with an increased risk of progression to advance phase disease , transplant is a reasonable option .\nthus , current indications for transplant in cml include [ figure 1 ] : \n advanced phase disease ( accelerated phase and blast crisis)resistance / intolerance to tkisrelapse on tkis . \n \nadvanced phase disease ( accelerated phase and blast crisis ) resistance / intolerance to tkis algorithm for consideration of hematopoietic stem cell transplant in chronic myeloid leukemia\nseveral factors influence the outcome of allogeneic hsct in cml , most importantly the phase of the disease , but also , the type of donor used , the nature of the stem cell product , and the age of the patient .\nthe european group for blood and marrow transplantation ( ebmt ) devised a risk score based on five separate characteristics , which predicted treatment - related mortality and 5 years overall survival following allogeneic hematopoietic cell transplantation .\nthis system uses hla matching , stage , age , sex of donor / recipient and time from diagnosis to transplant as risk factors .\nsurvival at 5 years varied from 72% for the best score to 22% for the worst score .\nthe ebmt risk score was later validated using separate data from the international bone marrow transplant registry . however , the value of this prognostic scoring system is largely for prognostication rather than decision - making .\nfive years disease - free survival varies from 90% in chronic phase to 40 - 50% in accelerated phase to 10 - 20% in blast crisis .\noutcome of patients in blast crisis who achieve a second chronic phase with tki therapy is similar to that of patients in accelerated phase .\nadvances in hla typing and graft versus host disease ( gvhd ) therapy has improved transplant outcomes in cml .\nresults with a fully matched unrelated donor are quite similar to that achieved with a matched - related donor .\nbone marrow harvest has been replaced by peripheral blood mobilization for stem cell collection making the procedure more donor compliant .\ntwo randomized trials involving patients with various hematologic malignancies , including cml , concluded that use of granulocyte colony - stimulating factor mobilized peripheral blood stem cells lead to faster myeloid and platelet recovery , no significant difference in acute or chronic gvhd and an overall survival advantage compared with bone marrow .\nhowever , another study in chronic phase cml showed no significant difference in the outcome between the bone marrow and peripheral blood groups . in earlier studies , younger age has been shown to improve survival after hsct in cml , however , better supportive care , better donor selection and use of reduced intensity conditioning regimens have dampened the effect of age on survival outcome .\nsome studies had suggested that increased interval from diagnosis to transplant was associated with a worse transplant outcome , higher relapse rate and an increase in nonrelapse mortality .\nthis was attributed to the development of resistant clones associated with a longer delay to transplantation .\nanother factor implicated in affecting outcome in earlier studies was the use of prior imatinib , which was shown to be associated with an increase in regimen - related toxicity and mortality , especially from hepatic causes .\nhowever , larger studies have shown that there is no deleterious effect of the pretransplant imatinib on outcome .\nfurthermore , patients with abl mutations have similar outcomes compared with those with no mutations following transplantation .\non average 5 - 20% of the chronic phase patients and 30 - 60% of advanced phase patients relapse following allo - hsct . increased incidence of relapse is seen with hsct strategies involving t - cell depletion and use of reduced intensity conditioning regimens .\nan increasing level of bcr - abl transcript measured by quantitative polymerase chain reaction is predictive of impending disease relapse and needs intervention .\nmodalities available to prevent and/or treat posttransplant relapse include donor lymphocyte infusion ( dli ) therapy , tki therapy , interferon therapy and infusion of in vitro stimulated cd8 t cells .\ndli have been very effective ( 70 - 90% complete remission rate ) for patients who relapse with chronic phase .\nthe efficacy of dli is the result of gvl effect which is highly pronounced in cml .\nhowever , the drawbacks of dli are ( 1 ) advanced phases of the disease are least responsive to dlis , ( 2 ) effect of dli may last for few months and repeat dli may be required and ( 3 ) it may be complicated by life - threatening gvhd . tki therapy with imatinib\nis highly effective in treatment of posttransplant relapse . in a study of 28 cml patients who were treated with imatinib for posttransplant relapse ,\nlonger follow - up of similar patients had shown that these responses are quite durable .\nresponse rates are higher in patients who relapse in chronic phase compared to those who relapse in advanced phase disease .\nfurthermore , there is some evidence that imatinb maintenance therapy posttransplant is effective in preventing relapse in high - risk cases .\nhowever , considering the morbidity and mortality associated with hsct and efficacy and favorable toxicity profile of tkis , cml chronic phase patients should be initially treated with tki . for patients with advanced phase disease and those with chronic phase disease who are resistant or intolerant to tki or relapse on tki ,", "role": "user" }, { "content": "indications for hematopoietic stem cell transplant ( hsct ) in chronic myeloid leukemia ( cml ) have changed over time . \n this change has largely been influenced by the advent of tyrosine kinase inhibitors , increased understanding of the mechanisms underlying disease phase progression as well as drug resistance , refinement of transplant techniques and exploitation of graft versus leukemia effect in this disease . here , we have discussed the status of hsct in cml in the present era with regards to the current indications , factors determining outcome and management strategies for posttransplant relapse .", "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:\nPatient-reported treatment satisfaction with oral rivaroxaban versus standard therapy in the treatment of acute symptomatic deep-vein thrombosis.\nAbstract 1:\nRivaroxaban , an oral , direct factor Xa inhibitor , has been approved for the treatment of deep-vein thrombosis ( DVT ) and pulmonary embolism ( PE ) and the prevention of recurrent DVT and PE as a fixed-dose , single-drug regimen that does not require initial heparinisation , routine coagulation monitoring or dose adjustment . This study evaluated patient-reported treatment satisfaction in EINSTEIN DVT -- a large , open-label , r and omised study that compared rivaroxaban with enoxaparin/vitamin K antagonist ( VKA ) therapy in patients with acute symptomatic DVT without PE . As part of EINSTEIN DVT , a total of 1,472 patients in seven countries were asked to complete a new , vali date d measure of treatment satisfaction -- the Anti-Clot Treatment Scale (ACTS)--at scheduled visits throughout 12 months of treatment . ACTS scores were compared between study groups in the intention-to-treat population . Patients reported greater satisfaction in the rivaroxaban group compared with the enoxaparin/VKA group , with higher mean ACTS scores across visits . Mean ACTS Burdens scores were 55.2 vs 52.6 ( p<0.0001 ) in favour of rivaroxaban , equivalent to a moderate effect size of 0.42 . The treatment effect was consistent over time , with the mean score difference ranging from 2.18 ( month 2 ) to 3.18 ( month 12 ) . Overall mean ACTS Benefits scores were 11.7 vs 11.5 in favour of rivaroxaban ( p=0.006 ) . This was associated with a small overall effect size of 0.12 . The improvement in ACTS Benefits for rivaroxaban became apparent at month 2 and subsequent visits . Rivaroxaban results in improved treatment satisfaction compared with enoxaparin/VKA among patients with DVT , particularly in reducing patient-reported anticoagulation burden\n\n\nTitle 2:\nDoes treatment guided by vitamin K in the diet alter the quality of life of anticoagulated patients?\nAbstract 2:\nPURPOSE To compare whether health-related quality of life ( HRQoL ) is altered in patients undergoing a treatment strategy guided by changes in dietary vitamin K. METHODS This study is a r and omized clinical trial carried out with chronic oral anticoagulation out patients r and omized into a control group ( conventional dose adjustment of oral anticoagulants ) ( n = 66 ) and an intervention group ( strategy based on changes in dietary vitamin K intake ) ( n = 66 ) . HRQoL was measured using the Duke Anticoagulation Satisfaction Scale ( DASS ) at baseline and 90 days of follow-up . RESULTS Patients with worse HRQoL were younger ( p = 0.005 ) and were using a higher dose of baseline oral anticoagulants ( p = 0.008 ) , while those with better HRQoL scores had a higher level of education ( p = 0.01 ) . Both groups had significant improvements in HRQoL from baseline to 90 days in the global DASS score ( p < 0.001 ) , as well as in the negative and positive psychological impact ( p < 0.001 ) domains . We did not observe differences in the variations of HRQoL scores in any of the DASS domains ( p values > 0.05 ) between groups of interventions . Patients who achieved oral anticoagulation stability ( n = 23 ) had significantly better HRQoL scores than patients who did not achieve stability ( p = 0.003 ) . CONCLUSION Patients receiving the treatment strategy based on changes in dietary vitamin K intake did not have better HRQoL scores ; however , both treatment approaches to manage oral anticoagulation improved HRQoL. Patients with greater oral anticoagulation stability had better HRQoL scores\n\n\nTitle 3:\nPatient-reported treatment satisfaction with oral rivaroxaban versus standard therapy in the treatment of pulmonary embolism; results from the EINSTEIN PE trial.\nAbstract 3:\nINTRODUCTION Rivaroxaban is an oral , direct Factor Xa inhibitor , approved for the treatment of pulmonary embolism ( PE ) and deep vein thrombosis ( DVT ) and the secondary prevention of recurrent PE and DVT as a fixed-dose , monotherapy regimen that does not require initial heparinisation , routine coagulation monitoring or dose adjustment . Approval in this indication was supported by results from EINSTEIN PE , a large , r and omised , open-label study that compared rivaroxaban with enoxaparin/vitamin K antagonist ( VKA ) therapy in patients with acute symptomatic PE with or without DVT . MATERIAL S AND METHODS Patient-reported treatment satisfaction was evaluated in a predefined sub analysis of EINSTEIN PE to enable monitoring and optimisation of patient-reported outcomes and , therefore , patient compliance . As part of EINSTEIN PE , 2,397 patients in seven countries were asked to complete a vali date d measure of treatment satisfaction , the Anti-Clot Treatment Scale ( ACTS ) throughout the duration of treatment ( up to 12 months ) . RESULTS Patients reported greater satisfaction in the rivaroxaban treatment arm as compared with the enoxaparin/VKA treatment arm . Treatment with rivaroxaban was reported as being significantly less burdensome than enoxaparin/VKA therapy , and the benefits of treatment were significantly greater . CONCLUSION Rivaroxaban treatment result ed in improved treatment satisfaction compared with enoxaparin/VKA in PE patients , particularly in reducing patient-reported anticoagulation burden\n\n\nTitle 4:\nThe Anti-Clot Treatment Scale (ACTS) in clinical trials: cross-cultural validation in venous thromboembolism patients\nAbstract 4:\nBackground The Anti-Clot Treatment Scale ( ACTS ) is a 15-item patient-reported instrument of satisfaction with anticoagulant treatment . It includes a 12-item ACTS Burdens scale and a 3-item ACTS Benefits scale . Its role in clinical trials and other setting s should be supported by evidence that it is both clinical ly meaningful and scientifically sound . The aim of the study was to evaluate the measurement performance of the ACTS ( Dutch , Italian , French , German and English language versions ) in patients with venous thromboembolism based on traditional psychometric methods . Methods ACTS Burdens and Benefits scale data from a large clinical trial ( EINSTEIN DVT ) involving 1336 people with venous thromboembolism were analysed at both the scale and item level . Five key psychometric properties were examined using traditional psychometric methods : acceptability , scaling assumptions , reliability ( including internal consistency reliability , test-retest reproducibility ) ; validity ( including known groups and discriminant validity ) ; and responsiveness . These methods of examination underpin the US Food and Drug Administration recommendations for patient-reported outcome instrument evaluation . Results Overall , the 12-item ACTS Burdens scale and 3-item ACTS Benefits scale met the psychometric criteria evaluated at both item and scale levels , with the exception of some relatively minor issues in the Dutch language version , which were just below reliability criteria ( i.e. alpha = 0.72 , test-retest intraclass correlation = 0.79 ) . A consistent finding from item-level evaluations of aggregate endorsement frequencies and skewness suggested that response scales may be improved by reducing the number of response options from five to four . Conclusions Both the ACTS Burdens and ACTS Benefits scales consistently satisfied traditional reliability and validity criteria across multiple language data sets , supporting it as a clinical ly useful patient-reported instrument of satisfaction with anticoagulant treatment in clinical trials . Trial registration\n\n\nTitle 5:\nDevelopment and testing of the Hill-Bone Compliance to High Blood Pressure Therapy Scale.\nAbstract 5:\nThe Hill-Bone Compliance to High Blood Pressure Therapy Scale assesses patient behaviors for three important behavioral domains of high blood pressure treatment : 1 ) reduced sodium intake ; 2 ) appointment keeping ; and 3 ) medication taking . This scale is comprised of 14 items in three subscales . Each item is a four point Likert type scale . The content validity of the scale was assessed by a relevant literature review and an expert panel , which focused on cultural sensitivity and appropriateness of the instrument for low literacy . Internal consistency reliability and predictive validity of the scale were evaluated using two community based sample s of hypertensive adults enrolled in clinical trials of high blood pressure care and control . The st and ardized alpha for the total scale were 0.74 and 0.84 , and the average interitem correlations of the 14 items were 0.18 and 0.28 , respectively . The construct and predictive validity of the scale was assessed by factor analysis and by testing of theoretically derived hypotheses regarding whether the scale demonstrated consistent and expected relationships with related variables . In this study , high compliance scale scores predicted significantly lower levels of blood pressure and blood pressure control . Moreover , high compliance scale scores at the baseline were significantly associated with blood pressure control at both baseline and at follow up in the two independent sample s. This brief instrument provides a simple method for clinicians in various setting s to use to assess patients ' self reported compliance levels and to plan appropriate interventions\n\n\nTitle 6:\nImpact of a new method of warfarin management on patient satisfaction, time, and cost.\nAbstract 6:\nSTUDY OBJECTIVE International normalized ratio self-testing with online remote monitoring and management ( STORM₂ ) is an alternative to anticoagulation clinic management , but the patient 's perspective of this method has not been evaluated in the United States ; thus we sought to evaluate the impact of STORM₂ on patient satisfaction , time , and cost . DESIGN Prospect i ve pre- and postintervention study . SETTING Freest and ing clinical research center . PATIENTS Forty-three patients treated with long-term warfarin therapy and monitored initially in the anticoagulation clinic setting and then with STORM₂ , referred from 11 medical practice s. INTERVENTION Patients were asked to complete a survey and the Duke Anticoagulation Satisfaction Scale ( DASS ) before ( at baseline ) and after at least 3 months of STORM₂ ( at follow-up ) . MEASUREMENTS AND MAIN RESULTS Patient satisfaction and time were assessed by survey and the DASS . Costs were measured from the patient 's perspective . Overall 90 % of responders preferred STORM₂ to traditional clinic management . The DASS questions indicated that patients were more satisfied with their anticoagulation treatment and more likely to recommend oral anticoagulation to a friend after experiencing STORM₂. In addition , patients found STORM₂ to be less complicated and more convenient than traditional clinic management . For each traditional monthly visit , patients drove 20 miles and expended a total of 1.8 hours ; using 55¢/mile for mileage reimbursement and $ 15/hour for lost wages , the cost for each visit was $ 38 . The total cost for four STORM₂ visits per month was $ 10 , for a net savings of $ 28 per patient per month . A total of 76 % of patients were willing to pay additional money to eliminate a monthly clinic visit . CONCLUSION STORM₂ is more convenient , less complicated , preferred by patients , and saves patients time and money compared with clinic management\n\n\nTitle 7:\nPatient satisfaction with extended-interval warfarin monitoring\nAbstract 7:\nExtended-interval monitoring of warfarin has been proposed to reduce follow-up burden and improve patient satisfaction . We aim ed to make an initial assessment of anticoagulation satisfaction before and after an extended-interval warfarin monitoring intervention . We conducted a translational prospect i ve single-arm pilot study of extended-interval warfarin monitoring in five pharmacist-managed anticoagulation clinics . Patients meeting CHEST guideline criteria for extended-interval warfarin monitoring began progressive extended-interval follow-up ( 6 , 8 , and 12 weeks thereafter ) . The Duke Anticoagulation Satisfaction Scale ( DASS ) was administered at baseline and at end-of- study or study removal ( in patients no longer appropriate for extended interval follow-up ) . Forty-six patients had evaluable pre- and post-intervention DASS survey data . Mean age of patients was 66.5 years , 74 % were non-Hispanic whites , and 48 % were men . Patients completed a mean ± SD of 34 ± 22 weeks of follow-up . Mean ± SD total DASS score at baseline was 45.2 ± 14.2 versus 49.1 ± 14.9 at end-of- study ( mean change , + 3.9 [ 95 % CI −0.6–8.4 ; p = 0.09 ] ) , indicating no benefit— and trending toward decrement — to anticoagulation satisfaction . Change in anticoagulation satisfaction varied substantially following extended-interval monitoring , with no evidence of improved satisfaction . Plausible reasons for patients not preferring extended-interval monitoring include increased anxiety and disengagement from self-management activities , both potentially related to less frequent feedback and reassurance during extended interval-monitoring . Additional research is needed to identify who is likely to benefit most from extended-interval monitoring . Anticoagulation satisfaction should be considered with clinical factors and shared-decision making when implementing extended-interval warfarin monitoring", "role": "user" }, { "content": "Generic question naires and those specific to adherence to hypertension treatment are the most numerous .", "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 SATB1 positioned close to AT-rich sequences?\n\nContext: Tryptic cleavage and peptide sequence analysis demonstrated that the 98-kD protein is identical to a recently cloned protein, special A-T-rich binding protein 1 (SATB1)\nSpecial AT-rich sequence-binding protein 1 (SATB1), a DNA-binding protein expressed predominantly in thymocytes, recognizes an ATC sequence context that consists of a cluster of sequence stretches with well-mixed A's, T's, and C's without G's on one strand.\nWe have purified and identified one of the core factors as the matrix attachment region (MAR) binding protein, SATB1, which is known to bind to AT-rich sequences with a high propensity to unwind\nSATB1 (special AT-rich sequence-binding protein-1) provides a key link between DNA loop organization, chromatin modification/remodeling, and association of transcription factors at matrix attachment regions (MARs).\nOver-expression of the special AT rich sequence binding protein 1 (SATB1) promotes the progression of nasopharyngeal carcinoma: association with EBV LMP-1 expression.\npecial AT rich sequence binding protein 1 (SATB1) plays a crucial role in the biology of various types of human cancer.\nLoss of special AT-rich sequence-binding protein 1 (SATB1)\nSpecial AT-rich sequence-binding protein 1 (SATB1) is a cell type-specific matrix attachment region binding protein, functioning as a global genome organizer.\nSATB1 (special AT-rich binding protein 1) is a global chromatin organizer regulating the expression of a large number of genes\nSpecial AT-rich Sequence-binding Protein 1 (SATB1) Functions as an Accessory Factor in Base Excision Repair.\nRearrangement of the Chromatin Organizer Special AT-rich Binding Protein 1 Gene\nThe Special AT-rich Sequence Binding Protein 1 (SATB1) exerts multiple functions, by influencing the structural organization of chromatin and interacting with several co-activators and co-repressors of transcription.\nThe Special AT-rich Sequence Binding Protein 1 (SATB1) and its role in solid tumors.", "role": "user" }, { "content": "yes", "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\nBystander fatigue and CPR quality by older bystanders: a randomized crossover trial comparing continuous chest compressions and 30:2 compressions to ventilations This study sought to measure bystander fatigue and cardiopulmonary resuscitation (CPR) quality after five minutes of CPR using the continuous chest compression (CCC) versus the 30:2 chest compression to ventilation method in older lay persons, a population most likely to perform CPR on cardiac arrest victims. This randomized crossover trial took place at three tertiary care hospitals and a seniors' center. Participants were aged ≥55 years without significant physical limitations (frailty score ≤3/7). They completed two 5-minute CPR sessions (using 30:2 and CCC) on manikins; sessions were separated by a rest period. We used concealed block randomization to determine CPR method order. Metronome feedback maintained a compression rate of 100/minute. We measured heart rate (HR), mean arterial pressure (MAP), and Borg Exertion Scale. CPR quality measures included total number of compressions and number of adequate compressions (depth ≥5 cm). Sixty-three participants were enrolled: mean age 70.8 years, female 66.7%, past CPR training 60.3%. Bystander fatigue was similar between CPR methods: mean difference in HR -0.59 (95% CI -3.51-2.33), MAP 1.64 (95% CI -0.23-3.50), and Borg 0.46 (95% CI 0.07-0.84). Compared to 30:2, participants using CCC performed more chest compressions (480.0 v. 376.3, mean difference 107.7; p<0.0001) and more adequate chest compressions (381.5 v. 324.9, mean difference. 62.0; p=0.0001), although good compressions/minute declined significantly faster with the CCC method (p=0.0002). CPR quality decreased significantly faster when performing CCC compared to 30:2. However, performing CCC produced more adequate compressions overall with a similar level of fatigue compared to the 30:2 method.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"cardiac arrest\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [\"heart rate\", \"HR\"], \"Eukaryote\": [], \"Finding\": [\"mean arterial pressure\", \"Borg 0.46\", \"Bystander fatigue\", \"ventilation method\", \"ventilations\", \"bystander fatigue\", \"frailty score\", \"level of fatigue\", \"MAP\"], \"Food\": [], \"HealthCareActivity\": [\"cardiopulmonary resuscitation\", \"CPR training\", \"CPR sessions\", \"CPR\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"Borg Exertion Scale\"], \"MedicalDevice\": [], \"Organization\": [\"seniors\\u0027 center\", \"tertiary care hospitals\"], \"PopulationGroup\": [\"population\", \"older bystanders\", \"participants\", \"Participants\"], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"block randomization\", \"randomized crossover trial\"], \"SpatialConcept\": [], \"Virus\": []}", "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:\nthe kondo effect @xcite in samples with reduced dimensions ( thin films , narrow wires ) is one of the most challenging problems in the field .\nmost of the experiments @xcite have shown that the kondo contribution to the resistivity is suppressed when the sample size is reduced or the disorder in the sample is increased .\nin addition the different thermopowers of samples with different thickness gave further evidences for the existence of size dependence @xcite .\nthe previously examined samples were au(fe ) , cu(fe ) , and cu(cr ) alloys , i.e. , alloys with integer spin impurities .\nsurprisingly , however , very weak size dependence has been found recently in cu(mn ) alloys @xcite . the first possible explanation related to the size of the kondo screening cloud @xcite\nwas ruled out both theoretically @xcite and experimentally @xcite . in the limit of strong disorder the experiments\nmight be well explained with the theory of phillips and co - workers based on weak localization @xcite . in the dilute limit\nthe theory of the spin - orbit - induced magnetic anisotropy proposed by the authors @xcite was able to explain every experiment in samples with reduced dimensions , small disorder and integer spin impurities for thin layers @xcite .\nrecently an elegant method was developed by fomin and co - workers @xcite which can be applied for a general geometry . according to this theory\n@xcite the spin - orbit interaction of the conduction electrons on the non - magnetic host atoms can result in a magnetic anisotropy for the magnetic impurity .\nthis anisotropy can be described by the hamiltonian @xmath3 where @xmath4 is the normal direction of the experienced surface element , @xmath5 is the spin of the impurity , and @xmath6 is the anisotropy constant which is always positive and inversely proportional to the distance of the impurity from the surface . due to this\nanisotropy the spin multiplet splits according to the value of @xmath7 . in the case of integer spin ( e.g. , @xmath1 for fe ) ,\nthe lowest level is a singlet with @xmath8 thus at a given temperature the impurities close enough to the surface , where the splitting is greater than @xmath9 , can not contribute to the kondo resistivity .\nwhen the sample size becomes smaller , more and more impurity spins freeze out , reducing the amplitude of the kondo resistivity @xcite .\nthe theory predicts , however , different behavior for samples with half - integer impurity spin ( e.g. , @xmath0 for mn ) which is recently in the center of interest . in the one - half case when the anisotropy looses its meaning @xcite , in fact\nno anomalous size dependence has been found for ce impurities by roth and co - workers @xcite . in half - integer @xmath10 case\nthe lowest level is a doublet ( @xmath11 ) thus even an impurity close to the surface ( large anisotropy ) has a contribution to the kondo resistivity . even accepting that the surface anisotropy reduces the free spin of the manganese to a doublet , it is far from trivial that in this case the size dependence is drastically suppressed , therefore an elaborate theory is required . in this paper\nwe calculate the kondo resistivity in thin films of magnetic alloys with @xmath0 impurity with helps of the simple model and mrg calculation of ref .\nfitting to the kondo resistivity the @xmath12 function , we calculate the coefficient @xmath13 in terms of the film thickness which is quite different from the @xmath1 case .\nthese results will be compared to the recent experiment by jacobs and giordano @xcite presented in thin cu(mn ) films and we compare also the case of alloys with different kondo temperatures .\nin the presence of the spin - orbit - induced surface anisotropy the kondo hamiltonian is @xmath14 where @xmath15 ( @xmath16 ) creates ( annihilates ) a conduction electron with momentum @xmath17 , spin @xmath18 and energy @xmath19 measured from the fermi level . the conduction electron band is taken with constant energy density @xmath20 for one spin direction , with a sharp and symmetric bandwidth cutoff @xmath21 .\n@xmath22 stands for the pauli matrices , @xmath23 s are the effective kondo couplings and @xmath24 is the anisotropy hamiltonian when the quantization axis is parallel to @xmath4 . applying the callan - symantzik multiplicative renormalization group ( mrg ) method to the problem , the next to leading logarithmic scaling equations for the dimensionless couplings @xmath25 were calculated for any impurity spin in ref .\nthere was a multiple step scaling performed , corresponding to the freezing out of different intermediate states due to the surface anisotropy .\nafter exploiting the @xmath26 symmetries of the problem , the scaling equations ( see eq . ( 20 ) and ( 21 ) in ref .\n@xcite ) were solved numerically in terms of the scaling parameter @xmath27 .\nthe results for @xmath0 , @xmath28 , and @xmath29k , i.e. , @xmath30k for cu(mn ) , can be seen in fig .\nwe can see from the plot that , when @xmath31 is large enough , at @xmath32 every coupling can be neglected , except the @xmath33 and @xmath34 . this corresponds to the freezing out of the given higher @xmath7 states , but it can be seen well that the two lowest energy states are still significant even for large anisotropy . the kondo resistivity calculated from the running couplings at @xmath32 by solving the boltzmann equations ( see ref .\n@xcite ) is @xmath35 where @xmath36 is the impurity concentration , @xmath37 is the fermi energy , @xmath38 is the electron distribution function in the absence of an electric field , and @xmath39 is a function of the running couplings at @xmath32 , spin factors , the strength of the anisotropy @xmath40 , and the temperature , defined in ref . @xcite . for thin films the kondo resistivity calculated in the frame of a simple model where the two surfaces contribute to the anisotropy constant in an additive way as\n@xmath41 is @xmath42 where @xmath43 is the proportionality factor of the spin - orbit - induced surface anisotropy , @xmath44 is the thickness of the film and we have used the fact that the kondo contribution to the resistivity is smaller by a factor of @xmath45 than the residual normal impurity contribution ( see for the details ref .\n@xcite ) . in fig .\n[ fig2 ] the resistivity as a function of @xmath46 can be seen for different @xmath47 for @xmath0 , @xmath28 , and @xmath29k , i.e. , @xmath30k as for cu(mn ) . thus reducing the thickness of the film for given @xmath43 , the kondo contribution to the resistivity\nis reduced comparing to the bulk value , but for given thickness there is a temperature below that the reduction turns into an increase . fitting the logarithmic function @xmath48 to the kondo resistivity\n, the plots of the coefficient @xmath49 as a function of the thickness can be seen in fig .\nhere we can better see this very different behavior from the @xmath1 case ( cf .\nfirst of all , the kondo amplitude is reduced comparing to the bulk value , but the dependence on the thickness is much weaker than for @xmath1 .\nsecondly , for small @xmath47 s the coefficient does not go to zero as for @xmath1 , but has a minima at @xmath50 and then changes sign , begins to increase .\nthis corresponds to that for an @xmath0 impurity in the presence of the anisotropy , the lowest energy states are the @xmath51 doublet which give a contribution to the resistivity even for large anisotropy ( small distance from the surface ) and which can also be larger than the bulk value as a consequence of the spin factors in the scaling equations . because of the large domain of the microscopic estimation of the anisotropy constant ( @xmath52 ) , we can not give a precise microscopic prediction for the place of the minima . according to the the fits on the experimental results on au(fe ) @xcite and cu(fe ) @xcite , @xmath53\nfrom which we can obtain a rough estimation for the place of the minima as @xmath54 .\nhowever , the theoretical calculation is not reliable in that region where @xmath33 is already in the strong coupling limit .\nthus the minima may be a sign of the breakdown of the weak coupling calculation .\nwe have fitted in the @xmath55 k temperature regime , thus below @xmath56k where the electron - phonon interaction can still be neglected @xcite and well above the kondo temperature where the weak coupling approximation is justified , thus our perturbative calculation and the logarithmic function for the kondo resistivity is valid .\nthese results are in good agreement with the recent experiments of jacobs and giordano @xcite on thin films of cu(mn ) . in fig .\n[ fig4 ] we have examined what like is the function @xmath57 for different kondo temperatures corresponding to different @xmath58-spin alloys .\nit can be seen from the figure that a minima in the @xmath59 function for small @xmath47 s is present at pretty much the same place ( i.e. , @xmath60 ) .\nthe character of the @xmath13 coefficient comparing to @xmath61 would roughly the same , but the absolute measure of the thickness dependence and the reduction from the bulk value become larger for larger @xmath2 when we fit in the same temperature regime corresponding to the larger bulk value ( see the figure caption of fig . [ fig4 ] ) .\nin this paper we have reexamined our previous calculation @xcite about the kondo resistivity in thin films of alloys with @xmath0 impurities in the presence of spin - orbit - induced surface anisotropy .\nfirst we presented our results on kondo resistivity for @xmath0 and @xmath30k , i.e. , for cu(mn ) , and fitted the @xmath48 function on it .\nthe @xmath13 function in terms of the film thickness is plotted in fig .\n[ fig3 ] from which we can see that there is a reduction in resistivity comparing to the bulk value , but the @xmath13 coefficient depends much weaker on the thickness than in case of @xmath1 , and for small @xmath47 s @xmath13 does not go to zero , but it has a minima at ca .\n@xmath62 below that it increases which may be only a sign of the breakdown of the weak coupling calculation .\nthese results are in good agreement with the recent experiment on cu(mn ) films @xcite .\nwe do not get , however , their factor of 30 difference from the bulk value .\nthen we have examined what like is the @xmath57 coefficient for different kondo temperatures , i.e. , for different @xmath58-spin alloys .\nwe have find that the character of the @xmath57 function is the same , but the reduction from the bulk value and the thickness dependence is somewhat stronger for larger @xmath2 .\nsummarizing , the level structure of the impurity is very different for integer and half - integer spin and at the surface the spin has a degenerate ground state in the latter case , but we obtained an essentially suppressed size dependence which is far from being trivial .\nthe actually dependence is an interplay between different effects as the strength of the anisotropy and the different amplitudes and temperature dependence of coupling strength of the electron induced transitions between levels .\nthe drastically different behavior for the integer and half - integer cases found experimentally and determined theoretically provides a further support of the surface anisotropy as the origin of the size dependence .\nwe would like to thank n. giordano for helpful discussions .\nthis work was supported by grant otka @xmath63 and @xmath64 .\none of us ( a.z . ) benefited from the hospitality of the meissner institute and the lmu in munich and supported by the humboldt foundation .\n99 j. kondo , prog .\n* 32 * , 37 ( 1964 ) .\nsee for a review m. a. blachly and n. giordano , phys .\n* b * * 51 * , 12537 ( 1995 ) ; j. f. ditusa , k. lin , m. park , m. s. isaacson , and j. m. parpia , phys . rev . lett .\n* 68 * , 678 ( 1992 ) ; g. neuttiens , j. eom , c. strunk , v. chandrasekhar , c. van haesendonck , and y. bruynserade , europhys .\n* 34 * , 623 ( 1996 ) . c. strunk , m. henny , and c. schnenberger , g. neuttiens and c. van haesendonck , phys .\n* 81 * , 2982 ( 1998 ) . t. m. jacobs and n. giordano , europhys .\nlett . * 44 * , 74 ( 1998 ) .\ng. bergmann , phys .\n* 67 * , 2545 ( 1991 ) .\nv. barzykin and i. affleck , phys .\nlett . * 76 * , 4959 ( 1996 ) .\nm. a. blachly and n. giordano , phys . rev .\n* b * * 49 * , 6788 ( 1994 ) .\ni. martin , yi wan , and philip phillips , phys .\nlett . * 78 * , 114 ( 1997 ) .\no. jsghy , a. zawadowski , and b. l. gyorffy , phys .\nlett . * 76 * , 2378 ( 1996 ) ; o. jsghy and a. zawadowski , phys . rev . * b * * 57 * , 11598 ( 1998 ) . o. jsghy and a. zawadowski , phys . rev .\n* b * * 57 * , 11609 ( 1998 ) .\nl. borda and a. zawadowski , cond - mat/9903054 , submitted to phys . rev . * b*. v. m. fomin , v. n. gladilin , j. t. devreese , c. van haesendonck , and g. neuttiens , solid state commun . * 106 * , 293 ( 1998 ) .\nc. roth , c. srgersand , and h. v. lhneysen , phys . rev .\n* b * * 54 * , 534 ( 1996 ) .\no. jsghy and a. zawadowski , unpublished .", "role": "user" }, { "content": "recently , for spin @xmath0 impurities quite different size dependence of the kondo contribution to the resistivity was found experimentally than for @xmath1 . therefore previous calculation about the effect of the spin - orbit - induced magnetic anisotropy on the kondo amplitude of the resistivity \n is extended to the case of @xmath0 impurity spin which differs from the integer spin case as the ground state is degenerated . in this case \n the kondo contribution remains finite when the sample size goes to zero and the thickness dependence in the kondo resistivity is much weaker for cu(mn ) . \n the behavior of the kondo coefficient as a function of the thickness depends on the kondo temperature , that is somewhat stronger for larger @xmath2 . comparing our results with a recent experiment in thin cu(mn ) films , we find a good agreement .", "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:\nThe cost-effectiveness of nivolumab monotherapy for the treatment of advanced melanoma patients in England\nAbstract 1:\nBackground Nivolumab was the first programmed death receptor 1 ( PD-1 ) immune checkpoint inhibitor to demonstrate long-term survival benefit in a clinical trial setting for advanced melanoma patients . Objective To evaluate the cost effectiveness of nivolumab monotherapy for the treatment of advanced melanoma patients in Engl and . Methods A Markov state-transition model was developed to estimate the lifetime costs and benefits of nivolumab versus ipilimumab and dacarbazine for BRAF mutation-negative patients and versus ipilimumab , dabrafenib , and vemurafenib for BRAF mutation-positive patients . Covariate-adjusted parametric curves for time to progression , pre-progression survival , and post-progression survival were fitted based on patient-level data from two trials and long-term ipilimumab survival data . Indirect treatment comparisons between nivolumab , ipilimumab , and dacarbazine were informed by these covariate-adjusted parametric curves , controlling for differences in patient characteristics . Kaplan – Meier data from the literature were digitised and used to fit progression-free and overall survival curves for dabrafenib and vemurafenib . Patient utilities and re source use data were based on trial data or the literature . Patients are assumed to receive nivolumab until there is no further clinical benefit , assumed to be the first of progressive disease , unacceptable toxicity , or 2 years of treatment . Results Nivolumab is the most cost-effective treatment option in BRAF mutation-negative and mutation-positive patients , with incremental cost-effectiveness ratios of £ 24,483 and £ 17,362 per quality -adjusted life year , respectively . The model results are most sensitive to assumptions regarding treatment duration for nivolumab and the parameters of the fitted parametric survival curves . Conclusions Nivolumab is a cost-effective treatment for advanced melanoma patients in Engl and\n\n\nTitle 2:\nCost Effectiveness of Pembrolizumab for Advanced Melanoma Treatment in Portugal.\nAbstract 2:\nBACKGROUND The aim of this study was to assess the cost-effectiveness of pembrolizumab in treating patients with ipilimumab-naïve advanced melanoma in Portugal . METHODS A cost-effectiveness model was developed to analyze the costs and consequences of treatment with pembrolizumab compared to treatment with ipilimumab in patients with advanced melanoma not previously treated with ipilimumab . The model was parameterized by using data from a head-to-head phase III r and omized clinical trial , KEYNOTE-006 . Extrapolation of long-term outcomes was based on approaches previously applied , combining ipilimumab data and melanoma patients ' registry data . The analysis was conducted from the perspective of the Portuguese National Health Service , and a lifetime horizon ( 40 years ) was used . Portugal-specific disease management costs were estimated by convening a panel of six clinical experts to derive health state re source use and multiplying the results by national unit costs . To test for the robustness of the conclusions , we conducted deterministic and probabilistic sensitivity analyses . RESULTS Pembrolizumab increases life expectancy in 1.57 undiscounted life-years ( LYs ) and is associated with an increase in costs versus that of ipilimumab . The estimated incremental cost-effectiveness ratio is € 47,221 per quality -adjusted life-year ( QALY ) and € 42,956 per LY . Deterministic sensitivity analysis showed that the results were robust to the change of most input values or assumptions and were sensitive to time on treatment scenarios . According to the probabilistic sensitivity analysis performed , pembrolizumab is associated with a cost per QALY gained inferior to € 50,000 in 75 % of the cases . CONCLUSIONS Considering the usually accepted thresholds in oncology , pembrolizumab is a cost-effective alternative for treating patients with advanced melanoma in Portugal\n\n\nTitle 3:\nCost-Effectiveness of Pembrolizumab Versus Ipilimumab in Ipilimumab-Naïve Patients with Advanced Melanoma in the United States.\nAbstract 3:\nBACKGROUND Recent clinical trials have shown that pembrolizumab significantly prolonged progression-free survival and overall survival compared with ipilimumab in ipilimumab-naïve patients with unresectable or metastatic melanoma . However , there has been no published evidence on the cost-effectiveness of pembrolizumab for this indication . OBJECTIVE To assess the long-term cost-effectiveness of pembrolizumab versus ipilimumab in ipilimumab-naïve patients with unresectable or meta-static melanoma from a U.S. integrated health system perspective . METHODS A partitioned-survival model was developed , which divided overall survival time into progression-free survival and postprogression survival . The model used Kaplan-Meier estimates of progression-free survival and overall survival from a recent r and omized phase 3 study ( KEYNOTE-006 ) that compared pembrolizumab and ipilimumab . Extrapolation of progression-free survival and overall survival beyond the clinical trial was based on parametric functions and literature data . The base-case time horizon was 20 years , and costs and health outcomes were discounted at a rate of 3 % per year . Clinical data -including progression-free survival and overall survival data spanning a median follow-up time of 15 months , as well as quality of life and adverse event data from the ongoing KEYNOTE-006 trial- and cost data from public sources were used to populate the model . Costs included those of drug acquisition , treatment administration , adverse event management , and disease management of advanced melanoma . The incremental cost-effectiveness ratio ( ICER ) expressed as cost difference per quality -adjusted life-year ( QALY ) gained was the main outcome , and a series of sensitivity analyses were performed to test the robustness of the results . RESULTS In the base case , pembrolizumab was projected to increase the life expectancy of U.S. patients with advanced melanoma by 1.14 years , corresponding to a gain of 0.79 discounted QALYs over ipilimumab . The model also projected an average increase of $ 63,680 in discounted perpatient costs of treatment with pembrolizumab versus ipilimumab . The corresponding ICER was $ 81,091 per QALY ( $ 68,712 per life-year ) over a 20-year time horizon . With $ 100,000 per QALY as the threshold , when input parameters were varied in deterministic one-way sensitivity analyses , the use of pembrolizumab was cost-effective relative to ipilimumab in most ranges . Further , in a comprehensive probabilistic sensitivity analysis , the ICER was cost-effective in 83 % of the simulations . CONCLUSIONS Compared with ipilimumab , pembrolizumab had higher expected QALYs and was cost-effective for the treatment of patients with unresectable or metastatic melanoma from a U.S. integrated health system perspective . DISCLOSURES This study was supported by funding from Merck & Co. , which review ed and approved the manuscript before journal su bmi ssion . Wang , Pellissier , Xu , Stevinson , and Liu are employees of , and own stock in , Merck & Co. Chmielowski has served as a paid consultant for Merck & Co. and received a consultant fee for clinical input in connection with this study . Chmielowski also reports receiving advisory board and speaker bureau fees from multiple major pharmaceutical companies . Wang led the modeling and writing of the manuscript . Chmielowski , Xu , Stevinson , and Pellissier contributed substantially to the modeling design and methodology . Liu led the data collection work and contributed substantially to writing the manuscript . In conducting the analysis and writing the manuscript , the authors followed Merck publication polices and the \" cost-effectiveness analysis alongside clinical trials-good research practice s and the CHEERS reporting format as recommended by the International Society for Pharmacoeconomics and Outcomes Research\n\n\nTitle 4:\nCost-Effectiveness of Immune Checkpoint Inhibition in BRAF Wild-Type Advanced Melanoma.\nAbstract 4:\nPurpose Patients who are diagnosed with stage IV metastatic melanoma have an estimated 5-year relative survival rate of only 17 % . R and omized controlled trials of recent US Food and Drug Administration-approved immune checkpoint inhibitors-pembrolizumab ( PEM ) , nivolumab ( NIVO ) , and ipilumumab (IPI)-demonstrate improved patient outcomes , but the optimal treatment sequence in patients with BRAF wild-type metastatic melanoma remains unclear . To inform policy makers about the value of these treatments , we developed a Markov model to compare the cost-effectiveness of different strategies for sequencing novel agents for the treatment of advanced melanoma . Material s and Methods We developed Markov models by using a US-payer perspective and lifetime horizon to estimate costs ( 2016 US$ ) and quality -adjusted life years ( QALYs ) for treatment sequences with first-line NIVO , IPI , NIVO + IPI , PEM every 2 weeks , and PEM every 3 weeks . Health states were defined for initial treatment , first and second progression , and death . Rates for drug discontinuation , frequency of adverse events , disease progression , and death obtained from r and omized phase III trials were used to determine the likelihood of transition between states . Deterministic and probabilistic sensitivity analyses were conducted to evaluate model uncertainty . Results PEM every 3 weeks followed by second-line IPI was both more effective and less costly than dacarbazine followed by IPI then NIVO , or IPI followed by NIVO . Compared with the first-line dacarbazine treatment strategy , NIVO followed by IPI produced an incremental cost effectiveness ratio of $ 90,871/QALY , and first-line NIVO + IPI followed by carboplatin plus paclitaxel chemotherapy produced an incremental cost effectiveness ratio of $ 198,867/QALY . Conclusion For patients with treatment-naive BRAF wild-type advanced melanoma , first-line PEM every 3 weeks followed by second-line IPI or first-line NIVO followed by second-line IPI are the most cost-effective , immune-based treatment strategies for metastatic melanoma", "role": "user" }, { "content": "Changes to key parameters were unlikely to change the conclusions of the CEA when the cost-effectiveness threshold was considered .\nWhen parameter inputs are not exactly aligned , conclusions may still be comparable across jurisdictions .", "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 Uhl's anomaly?\n\nContext: Uhl's anomaly is an extremely rare cardiac defect characterized by absence of the myocardium of the right ventricle.\nUhl's anomaly is an evolutive disease leading to terminal right ventricular failure\nUhl anomaly is a rare form of congenital hypoplasia of the right ventricular myocardium.\nUhl's anomaly was first reported by Uhl in 1952 and is characterized by congenital partial or complete absence of right ventricular myocardium.\nUhls anomaly was first reported by Uhl in 1952 and is characterized by congenital partial or complete absence of right ventricular myocardium", "role": "user" }, { "content": "Uhl's anomaly is an extremely rare cardiac defect characterized by absence of the myocardium of the right ventricle. Uhl's anomaly is an evolutive disease leading to terminal right ventricular failure.", "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:\nExercise training in pregnancy reduces offspring size without changes in maternal insulin sensitivity.\nAbstract 1:\nEpidemiological studies have identified the importance of the in utero environment in providing a healthy start to life. Previous studies have suggested that the maternal environment, in particular a reduction in maternal insulin sensitivity, contributes significantly to fetal growth. Regular aerobic exercise, through an effect on maternal insulin sensitivity, may influence offspring size by regulating nutrient supply to the fetus.\n The aim of the study was to determine the effects of aerobic exercise training in the second half of pregnancy on maternal insulin sensitivity and neonatal outcomes.\n We conducted a community-based, randomized, controlled trial of exercise in pregnancy.\n Eighty-four healthy nulliparous women (mean +/- sd, age, 30 +/- 4 yr; body mass index, 25.5 +/- 4 kg/m(2)) participated in the study.\n Subjects participated in a home-based stationary cycling program from 20 wk gestation to delivery.\n Maternal insulin sensitivity, neonatal auxology, body composition, and growth-related peptides in cord blood were measured.\n Offspring of exercisers had lower birth weight (sd score, control, 0.23 +/- 0.8; exercise, -0.19 +/- 0.9; P = 0.03) and body mass index at birth (sd score, control, 0.40 +/- 0.9; exercise, -0.01 +/- 0.09; P = 0.04). The reduction in maternal insulin sensitivity in late gestation was not affected by exercise (P = 0.45) and was unrelated to offspring size. Exercise offspring had lower cord serum IGF-I (P = 0.03) and IGF-II (P = 0.04).\n Regular exercise was associated with lower birth weights and reduced cord concentrations of growth-related peptides, suggesting an influence of exercise on endocrine regulation of fetal growth. These effects on offspring growth were not associated with an exercise training effect on maternal insulin sensitivity.\n\n\nTitle 2:\nExercise during pregnancy improves maternal glucose screen at 24-28 weeks: a randomised controlled trial.\nAbstract 2:\nThe influence of an exercise programme performed by healthy pregnant women on maternal glucose tolerance was studied.\n A physical activity (PA, land/aquatic activities) programme during the entire pregnancy (three sessions per week) was conducted by a qualified instructor. 83 healthy pregnant women were randomly assigned to either an exercise group (EG, n=40) or a control (CG, n=43) group. 50 g maternal glucose screen (MGS), maternal weight gain and several pregnancy outcomes were recorded.\n Significant differences were found between study groups on the 50 g MGS. Values corresponding to the EG (103.8 ± 20.4 mg/dl) were better than those of the CG (126.9 ± 29.5 mg/dl), p=0.000. In addition, no differences in maternal weight gain and no cases of gestational diabetes in EG versus 3 in CG (7%) (p>0.05) were found.\n A moderate PA programme performed during pregnancy improves levels of maternal glucose tolerance.\n\n\nTitle 3:\nSupervised home-based exercise may attenuate the decline of glucose tolerance in obese pregnant women.\nAbstract 3:\nThe significant deterioration of insulin sensitivity and glucose tolerance during pregnancy can have serious health implications for both the pregnant woman and her baby. Although it is well established that regular exercise benefits insulin sensitivity in the nonpregnant population, the effect on glucose tolerance in obese pregnant women is not known. The purpose of this study was to investigate the effect of a supervised 10-week, home-based, exercise programme, beginning at week 18 of gestation, on glucose tolerance and aerobic fitness in previously sedentary obese women.\n Twelve sedentary obese women were randomized into an exercise (EX; n=6) or control (CON; n=6) group at 18 weeks of gestation. Those randomized to EX engaged in 10 weeks of supervised home-based exercise (three sessions a week of stationary cycling), while those in the CON group maintained their usual daily activity. Their glucose and insulin responses to an oral glucose tolerance test (OGTT), as well as their aerobic fitness, were assessed both pre- and postintervention.\n Reduced glucose tolerance in the CON, but not EX, group was indicated by a tendency postintervention towards higher blood glucose levels at 1h of the OGTT (P=0.072). Furthermore, at 2h of the postintervention OGTT, blood glucose tended to remain elevated from baseline in the CON (P=0.077). There was also a trend towards increased fitness in the EX (P=0.064), but not the CON group.\n Regular aerobic exercise begun during pregnancy may have favourable effects on glucose tolerance and fitness in obese women, and warrants further investigation in a larger sample population.\n\n\nTitle 4:\nRegular exercise during pregnancy to prevent gestational diabetes: a randomized controlled trial.\nAbstract 4:\nTo assess whether exercise during pregnancy can prevent gestational diabetes and improve insulin resistance.\n A total of 855 women in gestational week 18-22 were randomly assigned to receiving a 12-week standard exercise program (intervention group) or standard antenatal care (control group). The exercise program followed standard recommendations and included moderate-intensity to high-intensity activity 3 or more days per week. Primary outcomes were gestational diabetes and insulin resistance estimated by the homeostasis model assessment method. For the power calculation, we assumed a gestational diabetes prevalence of 9% in the control group and a prevalence of 4% in the exercise group (risk difference of 5%). Under these assumptions, a two-sample comparison with a 5% level of significance and power of 0.80 gave a study population of 381 patients in each group.\n At 32-36 weeks of gestation there were no differences between groups in prevalence of gestational diabetes: 25 of 375 (7%) in the intervention group compared with 18 of 327 (6%) in the control group (P=.52). There were no differences in insulin resistance between groups when adjusting for baseline values. Only 55% of women in the intervention group managed to follow the recommended exercise protocol. No serious adverse events related to physical exercise were seen, and the outcomes of pregnancy were similar in the two groups.\n There was no evidence that offering women a 12-week standard exercise program during the second half of pregnancy prevents gestational diabetes or improves insulin resistance in healthy pregnant women with normal body mass indexes.\n : ClinicalTrials.gov, www.clinicaltrials.gov, NCT00476567.\n\n\nTitle 5:\nPrevention of gestational diabetes: feasibility issues for an exercise intervention in obese pregnant women.\nAbstract 5:\nTo examine the feasibility of an individualized exercise program to prevent gestational diabetes mellitus (GDM) in obese pregnant women.\n The study was a pilot randomized controlled trial with obese pregnant women (intervention group, individualized exercise program [n = 25]; control group, usual care [n = 25]). Average weekly energy expenditure (MET hours per week and kilocalories per week) of exercise-specific activity was assessed during pregnancy using the Pregnancy Physical Activity Questionnaire. Fasting glucose and insulin and homeostasis model assessment of insulin resistance (HOMA-IR) were assessed at baseline and 20, 28, and 36 weeks' gestation.\n Of the women in the intervention group, 16 of 22 (73%) achieved more than 900 kcal/week of exercise-based activity at 28 weeks compared with 8 of 19 women in the control group (42%), P = 0.047. However, insulin resistance (HOMA-IR) did not differ between the groups.\n This intervention was feasible and prompted a modest increase in physical activity. However, we are not confident that this intervention would be sufficient to prevent GDM.", "role": "user" }, { "content": "There is limited randomised controlled trial evidence available on the effect of exercise during pregnancy for preventing pregnancy glucose intolerance or GDM. Results from three randomised trials with moderate risk of bias suggested no significant difference in GDM incidence between women receiving an additional exercise intervention and routine care.\nBased on the limited data currently available, conclusive evidence is not available to guide practice. Larger, well-designed randomised trials, with standardised behavioural interventions are needed to assess the effects of exercise on preventing GDM and other adverse pregnancy outcomes including large-for-gestational age and perinatal mortality. Longer-term health outcomes for both women and their babies and health service costs should be included. Several such trials are in progress. We identified another seven trials which are ongoing and we will consider these for inclusion in the next update of this review.", "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:\nCatalytic Synthesis of Nonracemic Azaproline Derivatives by Cyclization of \\xce\\xb2-Alkynyl Hydrazines under Kinetic Resolution Conditions**\n\nPaper sections:\n\n<p>Heteroatom additions to unactivated alkynes are thought to be best mediated by transition metal catalysts such as palladium[1] and gold.[2] Recent reports by Hammond[3] and others[4] demonstrate that cyclizations of alkynes with nitrogen and oxygen nucleophiles are possible using stoichiometric tetrabutylammonium fluoride. However, these several examples appear to be limited to aryl or α,α-difluoro-alkynes. As described below, we have discovered by serendipity a non-metal catalyzed addition of amine to unactivated alkynes in a cyclic context to yield azaproline derivatives (scheme 1). Although the nature of this catalysis reaction is not clear, these reactions proceed in excellent yields and lead to enantio-enriched azaprolines under kinetic resolution conditions using ammonium phase transfer catalysts.</p><p>We decided to further investigate this cyclization reaction partly out of mechanistic curiosity but also mindful that azaprolines have taken on an increasingly important role in bioorganic[5] and medicinal chemistry investigations.[6] Indeed, there has been a great deal of interest in the synthesis of azaproline derivatives over the last decade. The earliest approach pioneered by Carreira involved diastereoselective [3+2] additions of diazoalkanes with α,β-unsaturated chiral esters.[7] More recently this method has been expanded to include other dipolar diazo reactions[8] including those catalyzed by chiral magnesium bisoxazole[9] and titanium BINOL-ate[10] and Lewis acids. The pyrazolidine ring of azaprolines has also been prepared via palladium catalyzed cyclizations of optically active allenylic hydrazines[11] or hydrazine adducts produced from racemic allenyl phosphine oxides.[12] However, in the present communication, we report related cyclization reactions catalyzed by non-metal cations which have allowed for an exciting class of chiral ammonium phase transfer catalysts to be brought to bear to produce non-racemic azaproline derivatives (scheme 1).</p><p>Based on our previous experience with γ-silyl allenyl esters,[13] we hypothesized that base catalyzed addition of dinitrogen electrophiles such as azidodicarboxylates should lead to β-alkynyl hydrazine intermediates. Indeed, with substrates 1 and 2 (EWG = CO2But and CO2Et) DBU catalyzed this transformation but the reactions were sluggish especially with larger α-substituents (table 1). Following a procedure similar to one we had previously reported,[14] γ-silyl allenyl and propargyl thioesters (EWG = COSBut) were prepared and, as expected, these substrates underwent rapid addition to azidodicarboxylates with DBU even at −20 °C. Less basic amines failed to give hydrazine products even with these thioesters except with DMF as the reaction solvent. This solvent gave no enantioselectivity when chiral amine catalysts such as quinine were used to catalyze the addition reaction to give 4.</p><p>For improved characterization, we thought it useful to remove the silyl group from product 4. However, we were surprised to discover that the desilylation of 4 using tetrabutylammonium fluoride (TBAF) led to dehydro-azaproline 5 in nearly quantitative yields. Our subsequent studies of this system revealed that the ammonium salt acts catalytically to form the heterocycle and that the reaction appears to tolerate a variety of substituents at the quaternary carbon center (table 2). We note that the TBAF used was a commercially available THF solution containing up to 5% dissolved water, likely the stoichiometric agent responsible for silyl group removal. While the present TBAF catalyzed cyclization step is unprecedented, a literature report details the cyclization of aryl alkynes with nitrogen and oxygen nucleophiles mediated by stoichiometric TBAF.[4] In addition, Hammond and co-workers describe a cyclization with a nitrogen nucleophile with an alkyne flanked with an α,α-difluoro methylene requiring two equivalents of TBAF.[3]</p><p>To better understand the role of the non-metal catalyst in the present reaction, several factors were examined. To separate issues of desilylation versus cyclization, we prepared silyl-free substrate 6 using stoichiometric TBAF in isopropanol (alcohol solvents do not lead to cyclization products). Now, using TBAF as the catalyst (0.1 eq), the cyclization reaction of 6 gives excellent yields in THF, DCM, and toluene. The use of tetrabutylammonium bromide (TBAB) as a catalyst gave no cyclization product except with the addition of CsF (table 3, entry 3). However, the anion need not be fluoride as added carbonate leads to the same result with TBAB (entry 6). Interestingly, tetrabutylphosphonium bromide (TBPB) also effectively catalyzes the cyclization[15] with either fluoride or carbonate additives. Clearly, neither ammonium nor fluoride are strictly required to catalyze this cyclization reaction.</p><p>The discovery that the present cyclization reaction is mediated by catalytic non-metal cations suggested that kinetic resolution might be possible. Our initial experiments with α-benzyl ester and chiral ammonium bromides 7 and 8 (table 4, entries 1–2) gave no reaction. However, less steric bulk at the quaternary carbon leads to a successful reactions (entries 4–7) which proceed fairly rapidly to approximately 50% conversion with catalysts 7 and 8. Importantly, this reaction leads to products (and remaining starting materials) of high enantioselectivities. Catalysts containing the bromide counter ion required added CsF to achieve product. This cyclization reaction is particularly sensitive to steric crowding. Thus with allyl substitution at α-position, catalyst 7 proved ineffective whereas the much smaller 8 leads to product with good resolution (table 4, entries 6–7). As expected, recovered starting material from a kinetic resolution reaction (entry 7) led to cyclization product 5 using catalytic TBAF in high enantiomeric excess (entry 8).</p><p>It appears that a modestly basic counteranion (F− or CO32−) is required for this cyclization reaction presumably to deprotonate the attacking carbamate nitrogen. Hiroya and Sakamoto have proposed an ammonium cation activation of alkynes in cycloaddition reactions involving aryl alkynes.[4a] While additional theoretical and physical investigations are needed to substantiate these claims, we remain intrigued by the possibility that the carbamate nitrogen nucleophile in our case attacks the alkyne group similarly activated by an ammonium or phosphonium catalyst. In this manner, the catalyzing ability of a chiral organic cation is expected to be influenced by the configuration of the quaternary center immediately adjacent to the alkyne perhaps explaining our successful kinetic resolution in this cyclization reaction.</p><p>The main thrust of this project was to develop a kinetic resolution technique to take advantage of an unprecedented non-metal catalyzed cyclic heteroatom addition mentioned above. Nevertheless we briefly explored asymmetric phase-transfer catalyzed additions of azidodicarboxylates to our γ-silyl allenyl ester system following a recent precedent by Maruoka involving carbon electrophiles.[16] While aqueous-organic biphasic systems resulted in no reaction with allenyl oxy-esters, we observed that CsOH•H2O in toluene led to their successful hydrazination. However, this solid-liquid phase reaction led to entirely racemic product when a variety of commercially available phase transfer catalysts (PTC) we employed.[17] We returned to the organic-aqueous systems with thioester substrates and observed addition products in good yields and moderate enantioselectivities (eq. 1). For this study we employed only several commercially available PTCs including cinchona-based catalysts and Maruoka catalyst 7. These results suggest that a suitable catalyst can be engineered for higher selectivities.</p><p>In conclusion, a robust α-selective hydrazination of allenyl esters has been developed. This reaction was also expanded to include asymmetric catalysis conditions using chiral phase transfer catalysts leading to promising results. Importantly, these hydrazino adducts underwent ammonium and phosphonium catalyzed cyclization to afford dehydro-azaproline derivatives. This amine addition to unactivated alkynes is uniquely mediated by non-metal cation catalysts. While the precise mechanism of this cyclization reaction is not yet understood, highly enantio-enriched azaproline derivatives have been prepared using readily available chiral ammonium salts as catalysts. Further mechanistic studies and exploration of the reactivity of the dehydro-azaproline system are currently underway.</p>\n\nExperimental Section\n<p>Neutral base catalyzed α-amination: Allene/alkyne mixture (1 mmol) was added to a round bottom flask which was then charged with solvent (5 mL). The reaction was cooled to the required temperature followed by addition of base (20 mol%). After 5 min of stirring, azidodicarboxylate (1.2 equiv) was slowly added and the reaction was allowed to stir. Reaction was monitored by thin layer chromatography and, upon completion, the reaction was quenched with aqueous HCl (1 M). The organic layer was removed and the aqueous layer was extracted twice with ether. All organic layers were combined, concentrated in vacuo, and purified by silica gel flash chromatography.</p><p>TBAF catalyzed cyclization: The substrate (0.5 mmol) was dissolved in THF (2 mL), followed by addition of TBAF (1 M THF, 20mol %). The reaction was stirred for 30 min, quenched with aqueous HCl (1 M) and extracted with ether. The organic layer was removed and the aqueous layer was extracted twice with ether. All organic layers were combined, concentrated in vacuo, and purified by silica gel flash chromatography to give nearly quantitative yield of product.</p><p>General procedure for kinetic resolution with ammonium fluoride catalysts: substrate (0.5 mmol) was added to a round bottom flask which was then charged with toluene (5 mL). Catalyst (10 mol%) was then added followed by stirring for the required time. The reaction was quenched with aqueous HCl (1 M) and extracted with ether. All organic layers were combined, concentrated in vacuo, and purified by silica gel flash chromatography. The separated products and starting materials were then analyzed by chiral HPLC for enantiomeric excess.</p><p>For spectroscopic data on all products see Supporting Information.</p>\n\n\n<p>The work was supported by the National Institutes of of Mental Health (087932-01) and NSF (0311369).</p><p>Supporting information for this article is available on the WWW under http://www.angewandte.org or from the author.</p><p>One phosphonium catalyzed carbocyclization was reported recently: HuJWuLYWangXCHuYYNiuYNLiuXYYangSLiangYMAdv Synth Catal2010352351</p><p>This suggests that the addition reactions may be occurring at the toluene/KOH interface without the intermediacy of the chiral PTC.</p><p>Catalytic generation of azaprolines via cyclization of β-alkynyl hydrazines.</p><p>DBU catalyzed additions of allenyl esters to azidodicarboxylates.</p><p>Isolated yields. With thioester substrates <5% of γ-addition hydrazine products (allenes) were also observed.</p><p>TBAF catalyzed cyclization of β-alkynyl hydrazines.</p><p>Isolated yields.</p><p>Starting with non-racemic 4 leads to product with the same ee.</p><p>Amide of pyrrolidine</p><p>Role of cation and anion in catalyzed cyclization of 4.</p><p>tetratbutylammonium bromide.</p><p>tetrabutylphosphonium bromide</p><p>Non-racemic azaproline products via kinetic resolution.</p><p>Based on chiral HPLC analysis of remaining starting material.</p><p>Recovered starting material from previous reaction (entry 7) was utilized.</p><p>Amide of pyrrolidine.</p><p>Recovered 25% starting material.</p>", "role": "user" }, { "content": "Cyclic addition of a hydrazine nitrogen to unactivated alkynes catalyzed by non-metals. Starting from readily accessible \\xce\\xb3-silyl allenyl esters, \\xce\\xb2-alkynyl hydrazines are prepared in one step and subsequently undergo unprecedented cyclization reactions in the presence of ammonium and phosphonium catalysts leading to dehydro-azaproline products. These heterocycles are also produced in high enantiomeric excesses using chiral ammonium phase transfer catalysts via a kinetic resolution pathway.", "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\nThe selected journals were based on those used in the earlier studies by Kohl and Davis (1985) and by Nisonger and Davis (2005), additional ones suggested by participants in the latter study, and the 20 journals with the highest JIF in the Information Science and Library Science category of the…", "role": "user" }, { "content": "Method", "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: Anti-inflammatory drugs, which includes steroids such as prednisone and non-steroidal drugs like ibuprofen, work by decreasing inflammation\n\nAbstract:\nIbuprofen is an over-the-counter medication that is used widely for the treatment of pain and fever during COVID-19 pandemic.\nA concern was raised regarding the safety of ibuprofen use because of its role in increasing ACE2 levels within the Renin-Angiotensin-Aldosterone system.\nACE2 is the coreceptor for the entry of SARS-CoV-2 into cells, and so, a potential increased risk of contracting COVID-19 disease and/or worsening of COVID-19 infection was feared with ibuprofen use.\nHowever, available data from limited studies show administration of recombinant ACE2 improves lung damage caused by respiratory viruses, suggesting ibuprofen use may be beneficial in COVID-19 disease.\nAt this time, there is no supporting evidence to discourage the use of ibuprofen.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Ibuprofen is an over-the-counter medication that is used widely for the treatment of pain and fever during COVID-19 pandemic.\", \"However, available data from limited studies show administration of recombinant ACE2 improves lung damage caused by respiratory viruses, suggesting ibuprofen use may be beneficial in COVID-19 disease.\", \"At this time, there is no supporting evidence to discourage the use of ibuprofen.\"]}", "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: Simian Varicella Virus Infection of Rhesus Macaques Recapitulates Essential Features of Varicella Zoster Virus Infection in Humans\nArticle:\nAbstract:\nSimian varicella virus( SVV), the etiologic agent of naturally occurring varicella in primates, is genetically and antigenically closely related to human varicella zoster virus( VZV). Early attempts to develop a model of VZV pathogenesis and latency in nonhuman primates( NHP) resulted in persistent infection. More recent models successfully produced latency; however, only a minority of monkeys became viremic and seroconverted. Thus, previous NHP models were not ideally suited to analyze the immune response to SVV during acute infection and the transition to latency. Here, we show for the first time that intrabronchial inoculation of rhesus macaques with SVV closely mimics naturally occurring varicella( chickenpox) in humans. Infected monkeys developed varicella and viremia that resolved 21 days after infection. Months later, viral DNA was detected only in ganglia and not in non-ganglionic tissues. Like VZV latency in human ganglia, transcripts corresponding to SVV ORFs 21, 62, 63 and 66, but not ORF 40, were detected by RT-PCR. In addition, as described for VZV, SVV ORF 63 protein was detected in the cytoplasm of neurons in latently infected monkey ganglia by immunohistochemistry. We also present the first in depth analysis of the immune response to SVV. Infected animals produced a strong humoral and cell-mediated immune response to SVV, as assessed by immunohistology, serology and flow cytometry. Intrabronchial inoculation of rhesus macaques with SVV provides a novel model to analyze viral and immunological mechanisms of VZV latency and reactivation.\nIntroduction:\nVaricella zoster virus( VZV), a neurotropic alpha herpesvirus, is the etiological agent of varicella( chickenpox). VZV establishes latency in ganglia and can reactivate to produce herpes zoster( shingles), a debilitating disease for the elderly and immunocompromised. Studies of VZV pathogenesis have been hampered by the lack of an animal model that consistently recapitulates both the virological and immunological hallmarks of both acute and latent VZV infection. Experimental inoculation of mice, rats and nonhuman primates( NHP) with VZV results in seroconversion but not varicella[1],[2],[3]. In weanling guinea pigs, seroconversion, viremia, an exanthem and animal-to-animal spread after VZV infection have been found[4]. Although humoral and cellular immune responses have been briefly characterized in the guinea pig model, the scarcity of immunological tools specific for this species have precluded in depth analysis[5],[6]. Further, VZV does not reactivate in any of these models. A SCID-humanized( SCID-hu) mouse model was developed in which co-implants of human fetal thymus/liver tissue were introduced under the kidney capsule. Fetal skin was then introduced subcutaneously as full thickness dermal grafts and later infected by injection of VZV-infected cells into the implanted tissue[7]. Further studies showed that the skin implants can also be infected and display hallmarks of VZV lesions following intravenous transfer of VZV infected tonsilar T cells[8]. Although this model contributed significantly to our understanding of VZV dissemination and pathogenesis, the chimeric and partially immunodeficient status of the host coupled with the need for fetal liver, thymus, tonsils and skin, precluded in depth studies of the role of the host immune response in the establishment and maintenance of VZV latency. Simian varicella virus( SVV) produces a naturally occurring exanthematous disease in NHP that mimics human varicella[9]. Both virus genomes have been sequenced and are colinear, sharing up to 75% DNA similarity[10],[11],[12]. Furthermore, SVV and VZV encode antigenically related polypeptides[13],[14],[15]. Like VZV, SVV becomes latent in ganglionic neurons[16],[17],[18],[19] and reactivates after environmental stress or immune suppression[9],[20],[21],[22]. However, although intratracheal inoculation of African green or Cynomolgus monkeys with SVV produces clinical and pathological features in monkeys similar to those seen in humans infected with VZV[9],[23], the animals remain persistently viremic for years[24],[25]. Thus, it is not ideal to use these models to characterize immunological control of VZV infection. To address this limitation and study VZV latency, a model of natural SVV infection was developed whereby African Green or Cynomolgus monkeys were exposed to cage-mates that had been experimentally inoculated with SVV[21],[26]. While natural infection resulted in rash and SVV DNA was detected only in ganglia and not in liver or lung, features consistent with varicella latency, seroconversion was random, and viremia was not found in most animals. These observations, coupled with an unknown dose and exact time of infection, make it difficult to study the kinetics of the host immunological response to virus infection[21]. The goal of this study was to investigate whether intrabronchial inoculation of rhesus macaques with SVV would provide a more suitable model of VZV pathogenesis and latency. In this manuscript, we report that intrabronchial infection of rhesus macaques with SVV reproduced all of the cardinal features of primary VZV infection in humans.\nDiscussion:\nIn this study, we show for the first time that intrabronchial infection of rhesus macaques with SVV results in viremia and varicella rash followed by resolution of viremia and establishment of SVV latency in ganglionic neurons. The incubation period for SVV( 7–10 days) seems to be slightly shorter than that of VZV, which has been estimated at 14 days. As early as 2 months after varicella, SVV DNA was found exclusively in ganglia and not in any of multiple visceral tissues examined. Transcripts corresponding to SVV ORFs 21, 61, 62, 63 and 66, but not 40 or 29, were also found in latently infected ganglia( Table 3). Except for ORF 61, the SVV transcripts found in ganglia are the same as those detected in latently infected human ganglia[27]. The detection of SVV ORF 61 RNA in latently infected monkey ganglia suggests that it should be searched for in human ganglia latently infected with VZV. Finally, like VZV, SVV ORF 63 protein was seen exclusively in the cytoplasm of neurons in latently infected monkey ganglia. Two different NHP models of SVV infection have been developed. African green or Cynomolgus monkeys inoculated intratracheally with SVV develop viremia followed by varicella and an antibody response[23],[40],[41]. Unfortunately, this model does not results in latency but rather the persistence of SVV DNA in blood, lung and liver for months to years after experimental infection[24],[25]. More recently, Mahalingam et al., developed a natural infection model whereby naïve African green or Cynomolgus monkeys were exposed to experimentally inoculated cage mates[21],[26]. Although naturally infected animals developed varicella followed by the establishment of latency, viremia and seroconversion were not consistently observed[21],[26]. Thus, in our initial experiments we inoculated two rhesus macaques intravenously. The first monkey developed persistent viremia. The second monkey was re-challenged with SVV 4 months later, at which point it did not show any signs of disease and SVV DNA was detected only on 4 dpi, indicative of subclinical infection. These data suggested that the immune response generated after primary infection protects against subsequent exposures. Encouraged by the results in the latter monkey and the fact that varicella virus is naturally transmitted through inhaled aerosolized viral droplets, we redesigned our strategies to deliver virus by the intrabronchial route. This strategy led to viremia, varicella, the establishment of latency in sensory ganglia, and the development of SVV-specific cellular and humoral immune responses. Although the difference in the route of infection( intratracheal versus intrabronchial) cannot be discounted, it is very likely that the change in nonhuman primate species is the main reason for resolution of viremia. For example, African green monkeys infected with simian immunodeficiency virus( SIV) show high levels of viremia without signs of simian AIDS. In contrast, rhesus macaques infected with SIV develop a profound loss of CD4 T cells and simian AIDS[42],[43]. As described for VZV[44],[45],[46], SVV infection resulted in viremia and in the detection of SVV DNA in T cells( CD4, CD8 and γδ), B cells, macrophages and dendritic cells( data not shown). The increased levels of SVV DNA in BAL cells compared to PBMCs are consistent with the severity of VZV infection seen in lungs of humans with varicella[47],[48],[49],[50]. The presence of SVV ORF61 transcripts was the only difference between VZV and SVV latency. SVV ORF 61 protein shares 37% amino acid identity with that of VZV ORF 61 protein with highly conserved domains[51]. Transcripts associated with VZV ORF61 have not been reported in latently infected human ganglia. Nevertheless, given parallels between varicella latency in humans and monkeys, a more aggressive search for VZV ORF 61 transcripts in humans is indicated. Interestingly SVV ORF 61 protein was detected only sparingly despite the presence of a high level of transcripts. It is unlikely that the low level detection of SVV ORF61 is due to poor sensitivity of the antibody used. Rather, the high number of antisense transcripts detected in same ganglia could be inhibiting protein translation. The kinetics of the immune response to SVV in rhesus macaques also parallel findings in humans infected with VZV. In humans, antibodies are detected at about 6 days after the onset of varicella rash, and we found peak SVV-specific IgG titers about 8 days after rash( 18 dpi). VZV-specific T cells are present at 3 days after the onset of varicella in humans[52]. We detected T cell proliferation after SVV infection at 7 dpi, with a peak at 14 dpi, i. e., at about 4 days post-rash, and SVV-specific IFNγ-secreting T cells were also first detected at 7 dpi and peaked at 14 dpi. We also detected an increase in granzyme B+ T cells indicative of a cytotoxic T cell response as described for VZV[53]. In peripheral blood, the peak of the proliferative burst occurred 14 dpi with 23986 displaying the highest level of proliferation in all T cell subsets analyzed. Interestingly, 23986 displayed the most extensive rash and the highest viral load in ganglia. On the other hand, monkey 25043, which had the least amount of rash, viral DNA and minimal virus transcription in latently infected ganglia, also had a low proliferative T cell response. The kinetics of T cell proliferation in BAL correlated with the onset of the rash, with T cells form 24953/25043, which showed signs of varicella on day 7, proliferating earlier( 7 dpi) that T cells from 23942/23986, which showed sings of varicella on day 10. These data suggest a correlation between the extent of rash, the development of the T cell response and the extent of viral load and expression in latently infected ganglia. Overall, SVV-infected rhesus macaques develop an adaptive immune response to virus with kinetics like those seen in humans after primary infection with VZV. Together, our data indicate that SVV infection of rhesus macaques provides a robust animal model that recapitulates clinical, virological and immunological hallmarks of VZV infection in humans. This model will provide unique opportunities to define host and viral factors needed to maintain latency and to characterize immune correlates needed for protection against VZV infection. Future studies will dissect the antiviral functions of the antibody response( neutralization, complement fixation, ADCC). It will also be important to characterize the specificity and function of SVV-specific CD4 and CD8 T cells, and to determine if the SVV homologues of VZV ORFs 4, 10, 29, 62, 63, gI and gE are also immunogenic in rhesus macaques[39],[54],[55],[56],[57].", "role": "user" }, { "content": "Varicella zoster virus ( VZV ) is a ubiquitous herpesvirus that causes chickenpox ( varicella ) and establishes a life-long latent infection in humans . VZV can then reactivate causing herpes zoster , commonly known as shingles , a painful and debilitating disease that can be life-threatening in elderly and immunocompromised individuals . Our understanding of immunological factors that control VZV replication is limited due to the fact that VZV causes disease only in humans . Simian varicella virus ( SVV ) is a simian counterpart of VZV that infects nonhuman primates . Our study showed for the first time that infection of rhesus macaques with SVV recapitulates key aspects of VZV infection from chickenpox and the resolution of acute viremia to the establishment of latency in ganglia , and the development of B and T cell responses to virus . This model will allow us to improve our understanding of the immune response to varicella virus , and to develop and test vaccines and antiviral drugs that can reduce the incidence of shingles and its attendant neurological complications .", "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\nThe drug interaction data described in this section were obtained from controlled clinical trials and studies involving otherwise healthy adults with epilepsy. Use in Conjunction with Other Antiepileptic Drugs: The addition of Felbatol to antiepileptic drugs (AEDs) affects the steady-state plasma concentrations of AEDs. The net effect of these interactions is summarized in the following table: AED AED Felbatol Coadministered Concentration Concentration Phenytoin Valproate ** Carbamazepine (CBZ) *CBZ epoxide Phenobarbital *Not administered, but an active metabolite of carbamazepine. **No significant effect. Specific Effects of Felbatol on Other Antiepileptic Drugs Phenytoin: Felbatol causes an increase in steady-state phenytoin plasma concentrations. In 10 otherwise healthy subjects with epilepsy ingesting phenytoin, the steadystate trough (Cmin) phenytoin plasma concentration was 17 5 micrograms/mL. The steady-state Cmin increased to 21 5 micrograms/mL when 1200 mg/day of felbamate was coadministered. Increasing the felbamate dose to 1800 mg/day in six of these subjects increased the steady-state phenytoin Cmin to 25 7 micrograms/mL. In order to maintain phenytoin levels, limit adverse experiences, and achieve the felbamate dose of 3600 mg/day, a phenytoin dose reduction of approximately 40% was necessary for eight of these 10 subjects. In a controlled clinical trial, a 20% reduction of the phenytoin dose at the initiation of Felbatol therapy resulted in phenytoin levels comparable to those prior to Felbatol administration. Carbamazepine: Felbatol causes a decrease in the steady-state carbamazepine plasma concentrations and an increase in the steady-state carbamazepine epoxide plasma concentration. In nine otherwise healthy subjects with epilepsy ingesting carbamazepine, the steady-state trough (Cmin) carbamazepine concentration was 8 2 micrograms/mL. The carbamazepine steady-state Cmin decreased 31% to 5 1 micrograms/mL when felbamate (3000 mg/day, divided into three doses) was coadministered. Carbamazepine epoxide steady-state Cmin concentrations increased 57% from 1.0 0.3 to 1.6 0.4 micrograms/mL with the addition of felbamate. In clinical trials, similar changes in carbamazepine and carbamazepine epoxide were seen. Valproate: Felbatol causes an increase in steady-state valproate concentrations. In four subjects with epilepsy ingesting valproate, the steady-state trough (Cmin) valproate plasma concentration was 63 16 micrograms/mL. The steady-state Cmin increased to 78 14 micrograms/mL when 1200 mg/day of felbamate was coadministered. Increasing the felbamate dose to 2400 mg/day increased the steadystate valproate Cmin to 96 25 micrograms/mL. Corresponding values for free valproate Cmin concentrations were 7 3, 9 4, and 11 6 micrograms/mL for 0, 1200, and 2400 mg/day Felbatol , respectively. The ratios of the AUCs of unbound valproate to the AUCs of the total valproate were 11.1 %, 13.0%, and 11.5%, with coadministration of 0, 1200, and 2400 mg/day of Felbatol , respectively. Phenobarbital: Coadministration of felbamate with phenobarbital causes an increase in phenobarbital plasma concentrations, In 12 otherwise healthy male volunteers ingesting phenobarbital, the steady-state trough (Cmin) phenobarbital concentration was 14.2 micrograms/mL. The steady-state Cmin concentration increased to 17.8 micrograms/mL when 2400 mg/day of felbamate was coadministered for one week. Effects of Other Antiepileptic Drugs on Felbatol Phenytoin: Phenytoin causes an approximate doubling of the clearance of Felbatol (felbamate) at steady state and, therefore, the addition of phenytoin causes an approximate 45% decrease in the steady-state trough concentrations of Felbatol as compared to the same dose of Felbatol given as monotherapy. Carbamazepine: Carbamazepine causes an approximate 50% increase in the clearance of Felbatol at steady state and, therefore, the addition of carbamazepine results in an approximate 40% decrease in the steady-state trough concentrations of Felbatol as compared to the same dose of Felbatol given as monotherapy. Valproate: Available data suggest that there is no significant effect of valproate on the clearance of Felbatol at steady state, Therefore, the addition of valproate is not expected to cause a clinically important effect on Felbatol (felbamate) plasma concentrations. Phenobarbital: It appears that phenobarbital may reduce plasma felbamate concentrations. Steady-state plasma felbamate concentrations were found to be 29% lower than the mean concentrations of a group of newly diagnosed subjects with epilepsy also receiving 2400 mg of felbamate a day. Effects of Antacids on Felbatol The rate and extent of absorption of a 2400 mg dose of Felbatol as monotherapy given as tablets was not affected when coadministered with antacids. Effects of Erythromycin on Felbatol The coadministration of erythromycin (1000 mg/day) for 10 days did not alter the pharmacokinetic parameters of Cmax, Cmin, AUC, CI/kg or tmax at felbamate daily doses of 3000 or 3600 mg/day in 10 otherwise healthy subjects with epilepsy. Effects of Felbatol on Low-Dose Combination Oral Contraceptives A group of 24 nonsmoking, healthy white female volunteers established on an oral contraceptive regimen containing 30 mg ethinyl estradiol and 75 mg gestodene for at least 3 months received 2400 mg/day of felbamate from midcycle (day 15) to midcycle (day 14) of two consecutive oral contraceptive cycles. Felbamate treatment resulted in a 42% decrease in the gestodene AUC 0-24, but no clinically relevant effect was observed on the pharmacokinetic parameters of ethinyl estradiol. No volunteer showed hormonal evidence of ovulation, but one volunteer reported intermenstrual bleeding during felbamate treatment.", "role": "user" }, { "content": "{\"Brand\": [\"Felbatol\"], \"Drug\": [\"Felbamate\", \"CBZ\", \"erythromycin\", \"Erythromycin\", \"gestodene\", \"ethinyl estradiol\", \"Phenytoin\", \"phenytoin\", \"valproate\", \"felbamate\", \"Phenobarbital\", \"Carbamazepine\", \"carbamazepine\", \"Valproate\", \"phenobarbital\"], \"DrugGroup\": [\"AED\", \"Combination Oral Contraceptives\", \"contraceptive\", \"antacids\", \"Antacids\", \"antiepileptic drugs\", \"Antiepileptic Drugs\", \"AEDs\"], \"UnapprovedDrug\": [\"Carbamazepine epoxide\", \"carbamazepine epoxide\"]}", "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: There is absolutely no evidence that ACE-inhibitors or ARBs increase the risk of COVID-19 infection or severe consequences from it\n\nAbstract:\nThe effects of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs) on the risk of COVID-19 infection and disease progression are yet to be investigated.\nThe relationship between ACEI/ARB use and COVID-19 infection was systematically reviewed.\nTo identify relevant studies that met predetermined inclusion criteria, unrestricted searches of the PubMed, Embase, and Cochrane Library databases were conducted.\nThe search strategy included clinical date published until May 9, 2020.\nTwelve articles involving more than 19,000 COVID-19 cases were included.\nTo estimate overall risk, random-effects models were adopted.\nOur results showed that ACEI/ARB exposure was not associated with a higher risk of COVID-19 infection (OR = 0.99; 95 % CI, 0-1.04; P = 0.672).\nAmong those with COVID-19 infection, ACEI/ARB exposure was also not associated with a higher risk of having severe infection (OR = 0.98; 95 % CI, 0.87-1.09; P = 0.69) or mortality (OR = 0.73, 95 %CI, 0.5-1.07; P = 0.111).\nHowever, ACEI/ARB exposure was associated with a lower risk of mortality compared to those on non-ACEI/ARB antihypertensive drugs (OR = 0.48, 95 % CI, 0.29-0.81; P = 0.006).\nIn conclusion, current evidence did not confirm the concern that ACEI/ARB exposure is harmful in patientswith COVID-19 infection.\nThis study supports the current guidelines that discourage discontinuation of ACEIs or ARBs in COVID-19 patients and the setting of the COVID-19 pandemic.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"In conclusion, current evidence did not confirm the concern that ACEI/ARB exposure is harmful in patientswith COVID-19 infection.\", \"This study supports the current guidelines that discourage discontinuation of ACEIs or ARBs in COVID-19 patients and the setting of the COVID-19 pandemic.\"]}", "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:\nSome well-known approaches include rule-based models (Brill and Resnik 1994), backed-off models (Collins and Brooks 1995), and a maximumentropy model (Ratnaparkhi 1998). Researchers have proposed many computational models for resolving PPattachment ambiguities. One common source of structural ambiguities arises from syntactic constructs in which a prepositional phrase might be equally likely to modify the verb or the noun preceding it.\n\nCitation Sentence:\nSome well-known approaches include rule-based models ( Brill and Resnik 1994 ) , backed-off models ( Collins and Brooks 1995 ) , and a maximumentropy model ( Ratnaparkhi 1998 ) .\n\nContext after the citation:\nFollowing the tradition of using learning PPattachment as a way to gain insight into the parsing problem, we first apply sample selection to reduce the amount of annotation used in training a PP-attachment model. We use the Collins-Brooks model as the basic learning algorithm and experiment with several evaluation functions based on the types of predictive criteria described earlier. Our experiments show that the best evaluation function can reduce the number of labeled examples by nearly half without loss of accuracy.", "role": "user" }, { "content": "Background", "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:\nrelated work\n\nContext before the citation:\n(Davis and Ogden, 1997; Ballesteros and Croft, 1997; Hull and (3refenstette, 1996). Another common approach is term translation, e.g., via a bilingual lexicon. Our focus is on languages where no MT exists, but a bilingual dictionary may exist or may be derived.\n\nCitation Sentence:\n( Davis and Ogden , 1997 ; Ballesteros and Croft , 1997 ; Hull and ( 3refenstette , 1996 ) .\n\nContext after the citation:\nWhile word sense disambiguation has been a central topic in previous studies for cross-lingual IR, our study suggests that using multiple weighted translations and compensating for the incompleteness of the lexicon may be more valuable. Other studies on the value of disambiguation for cross-lingual IR include Hiemstra and de Jong, 1999; Hull, 1997. Sanderson, 1994 studied the issue of disambiguation for mono-lingual M. The third approach to cross-lingual retrieval is to map queries and documents to some intermediate representation, e.g latent semantic indexing (LSI) (Littman et al, 1998), or the General Vector space model (GVSM), (Carbonell et al, 1997).", "role": "user" }, { "content": "CompareOrContrast", "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 role of Tcf3 in the maintenance of pluripotency?\n\nContext: Accordingly, the transcripts of the pluripotency genes Esrrb, Tfcp2l1, and Klf2, repressed by TCF3 in mESCs, are increased in TERRA-overexpressing cells.\nFurther studies revealed that T cell factor 3 ( TCF3) is a potential downstream target of TERRA and mediates the effect of TERRA in mESC maintenance.\nOne of these encodes T-cell factor 3 (TCF3), a transcription factor that plays important roles in ESC differentiation.\nImportantly, hnRNP H/F knockdown not only recapitulated the switch in TCF3 AS but also destabilized hESC colonies and induced differentiation. Providing an explanation for this, we show that expression of known TCF3 target E-cadherin, critical for maintaining ESC pluripotency, is repressed by E47 but not by E12.\nthe transcription factor T-cell factor-3 (Tcf3), co-occupies promoters throughout the genome in association with the pluripotency regulators Oct4 and Nanog.\nTcf3 is an integral component of the core regulatory circuitry of ES cells, which includes an autoregulatory loop involving the pluripotency regulators.\nOur results suggest that the Wnt pathway, through Tcf3, brings developmental signals directly to the core regulatory circuitry of ES cells to influence the balance between pluripotency and differentiation.\nTcf3 localizes to many pluripotency genes in embryonic stem cells\nTcf3 acts as a transcriptional repressor and reveal that β-catenin directly abrogates Tcf3 function.\nInhibition of glycogen synthase kinase-3 (Gsk3) supports mouse embryonic stem cells (ESCs) by modulating Tcf3, but the critical targets downstream of Tcf3 are unclear.\nConversely, forced expression phenocopied Gsk3 inhibition or Tcf3 deletion by suppressing differentiation and sustaining self-renewal.\nWnt signaling regulates the lineage differentiation potential of mouse embryonic stem cells through Tcf3 down-regulation.\nWe found that down-regulation of Tcf3, a member of the Tcf/Lef family and a key player in the control of self-renewal and pluripotency, represents a specific and primary response to Wnt activation in ESCs\nescuing Tcf3 expression partially restored the neural defects observed in Apc-mutant ESCs, suggesting that Tcf3 down-regulation is a necessary step towards Wnt-mediated suppression of neural differentiation.\nTcf3 down-regulation in the context of constitutively active Wnt signaling does not result from promoter DNA methylation but is likely to be caused by a plethora of mechanisms at both the RNA and protein level as shown by the observed decrease in activating histone marks (H3K4me3 and H3-acetylation) and the upregulation of miR-211, a novel Wnt-regulated microRNA that targets Tcf3 and attenuates early neural differentiation in mouse ESCs.\nWnt signaling down-regulates Tcf3 expression, possibly at both the transcriptional and post-transcriptional levels, and thus highlight a novel mechanism through which Wnt signaling inhibits neuro-ectodermal lineage differentiation in mouse embryonic stem cells.\ntranscription factor 3 (TCF3), a target of miR-449a, could downregulate Nanog expression, and restoring TCF3 expression in miR-449a-expressing Nanog-negative cells abrogated cellular stemness.\ndepletion of both Tcf3 and Lef1 enables maintenance of undifferentiated mouse ESCs", "role": "user" }, { "content": "Tcf3 is an integral component of the core regulatory circuitry of ES cells, which includes an autoregulatory loop involving the pluripotency regulators. Tcf3 co-occupies promoters throughout the genome in association with the pluripotency regulators Oct4 and Nanog. Tcf3 down-regulation modulates the lineage differentiation potential of mouse embryonic stem cells through Wnt signaling. Tcf3 down-regulation is a necessary step towards Wnt-mediated suppression of differentiation. Depletion of Tcf3 enables the maintenance of undifferentiated mouse ESCs.", "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: Nicotine may play an indirect role that makes it harder for the virus to gain to access cells\n\nAbstract:\nSome comorbidities are associated with severe coronavirus disease (Covid-19) but it is unclear whether some increase susceptibility to Covid-19.\nIn this case-control Mexican study we found that obesity represents the strongest predictor for Covid-19 followed by diabetes and hypertension in both sexes and chronic renal failure in females only.\nActive smoking was associated with decreased odds of Covid-19.\nThese findings indicate that these comorbidities are not only associated with severity of disease but also predispose for getting Covid-19.\nFuture research is needed to establish the mechanisms involved in each comorbidity and the apparent \"protective\" effect of cigarette smoking.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Active smoking was associated with decreased odds of Covid-19.\"]}", "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 are the main characteristics/symptoms of the \"Brugada\" syndrome\n\nContext: In 1992, Brugada and Brugada first described a new entity, which became known as Brugada syndrome, that is associated with a high risk of ventricular arrhythmias and sudden cardiac death in patients without structural heart disease. This syndrome is characterized by a distinct electrocardiographic phenotype, type 1 Brugada pattern, consisting of a coved ST-segment elevation (≥0.2 mV) followed by a negative T wave in more than one right precordial lead.\nBrugada syndrome predisposes individuals to ventricular arrhythmias and sudden cardiac death, in the absence of structural heart disease. The typical Brugada electrocardiogram (ECG) phenotype is often concealed in affected population\nBrugada syndrome is a rare cardiac arrhythmia characterized by electrocardiographic right bundle branch block and persistent ST-segment elevation in the right precordial leads.\nBrugada syndrome is a genetically determined familial disease with autosomal dominant transmission and variable penetrance, conferring a predisposition to sudden cardiac death due to ventricular arrhythmias.\nBrugada syndrome (BrS)\nBrS is considered to be a primary inherited channelopathy often involving the inward sodium current and the diagnosis has traditionally required the exclusion of overt structural heart disease.\nBrugada syndrome (BrS) primarily associates with the loss of sodium channel function.\nPKP2 mutations may be a molecular substrate leading to the diagnosis of BrS.\nBrugada syndrome is an inherited arrhythmia syndrome predisposing to sudden cardiac death.\nthe first mutations in SCN5A encoding the cardiac sodium channel Nav1.5 were reported.\nBrugada syndrome is characterized by typical ECG features, ventricular arrhythmias and sudden cardiac death (SCD), more frequent during nighttime.\nBrugada syndrome (BrS) is an inherited cardiac disease characterized by ST segment elevation in V1-V3 ECG leads. Mutations SCN5A gene encoding for the cardiac voltage-gated Na(+) channel are found in some BrS patients, but also in family members with isolated conduction disturbances.\nBrugada syndrome (BrS), one of the most frequently diagnosed inherited arrhythmogenic syndromes, is responsible for more than 4% of all sudden deaths and at least 20% of sudden deaths in patients with structurally normal hearts.\nBrugada syndrome is a major cause of sudden death in young adults.\nBrugada's syndrome is one of the main causes of sudden death in young adults without a structural heart disease\nThe Brugada syndrome is a clinical-electrocardiographic diagnosis characterized by syncopal episodes or sudden death (caused by ventricular tachycardia and ventricular fibrillation) in patients with a structurally normal heart with a characteristic electrocardiographic pattern consisting of ST segment elevation in precordial leads (Vl-V3) and a morphology of the QRS complex resembling right bundle branch block (the latter can transiently disappear). Timely diagnosis and adequate treatment may essentially decrease mortality of this disease.\nBrugada syndrome\nIn 1992 we described a new syndrome consisting of syncopal episodes and/or sudden death in patients with a structurally normal heart and a characteristic electrocardiogram displaying a pattern resembling right bundle branch block with an ST segment elevation in leads V1 to V3. In 1998 it was described that the disease is genetically determined with an autosomal dominant pattern of transmission. Three different mutations have been identified. All three mutations affect the structure and the function of the sodium channel SCN5A.\nThe diagnosis is easily made by means of the electrocardiogram (ECG). The presence of concealed and intermittent forms, however, makes the diagnosis difficult in some patients.\nThe Brugada syndrome is a clinical-electrocardiographic diagnosis characterised by syncopal or sudden death episodes in patients with a structurally normal heart with a characteristic electrocardiographic pattern consisting of ST segment elevation in the precordial leads V1 to V3 and a morphology of the QRS complex resembling a right bundle branch block. In many patients with the Brugada syndrome, the electrocardiographic manifestations transiently normalize; leading to underdiagnosis of the syndrome.\nThe incidence of sudden death in this syndrome is very high and can only be prevented by implanting a cardioverter-defibrillator.", "role": "user" }, { "content": "In 1992, Brugada and Brugada first described a new entity, which became known as Brugada syndrome, that is associated with a high risk of ventricular arrhythmias and sudden cardiac death in patients without structural heart disease. This syndrome is characterized by a distinct electrocardiographic phenotype, type 1 Brugada pattern, consisting of a coved ST-segment elevation (≥0.2 mV) followed by a negative T wave in more than one right precordial lead. The typical Brugada electrocardiogram (ECG) phenotype is often concealed in affected population. Brugada syndrome is a genetically determined familial disease with autosomal dominant transmission and variable penetrance, conferring a predisposition to sudden cardiac death due to ventricular arrhythmias. Brugada syndrome (BrS)is considered to be a primary inherited channelopathy often involving the inward sodium current and the diagnosis has traditionally required the exclusion of overt structural heart disease. Brugada syndrome (BrS) is an inherited cardiac disease characterized by ST segment elevation in V1-V3 ECG leads. Mutations SCN5A gene encoding for the cardiac voltage-gated Na(+) channel are found in some BrS patients, but also in family members with isolated conduction disturbances.", "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 effect of grapefruit juice on CYP3A4?\n\nContext: The inhibition of CYP3A by grapefruit juice was significantly attenuated by processing particularly with γCD.\nThe encapsulation of BG and DHBG by γCD and the resulting attenuation of the inhibition of CYP3A activity by grapefruit juice may be applicable to juice processing for preventing drug-grapefruit juice interactions.", "role": "user" }, { "content": "Inhibitory", "role": "assistant" } ]

[ { "content": "You will be shown a paragraph from a biomedical research article. Your task is to extract all drug combinations appearing in a specific sentence within the paragraph. Each drug combination should be assigned to one of the following three categories:\n\n- POS: Indicates a positive interaction between the drugs in the combination; for instance, drugs that have an additive or synergistic effect.\n- NEG: Indicates a negative interaction between the drugs in the combination; for instance, combining these drugs might result in adverse side effects, or might reduce their efficacy.\n- COMB: Indicates that the drugs are given in combination, but the type of interaction between the drugs cannot be determined based on the provided context.\n\nPlease format your answer as a JSON array. Each entry in the array should itself be an array formatted as [<drug_1>, <drug_2>, ..., <drug_n>, <category>] where <category> is one of the three categories listed above and <drug_1>, ..., <drug_n> are drug names copied verbatim from the input sentence. Different combinations may involve different numbers of drugs; in other words, the `n` in <drug_n> may vary.\n\nAs an example, the following output describes two extracted drug combinations; one between two drugs, and one between three drugs:\n\n[[\"artesunate\", \"artemether\", \"COMB\"], [\"Nifedipine\", \"Labetalol\", \"Prazosin\", \"POS\"]]\n\nThe paragraph and specific sentence are below. You should only extract relationships expressed in the specific sentence; the paragraph is provided for context.\n\nIn your output, return only the JSON array and no other text. If no drug combinations appear, return an empty array `[]`.\n\nparagraph: A case of delivery of healthy infant in breast cancer patient incidentally treated with goserelin acetate and tamoxifen during pregnancy . In September 2000, a 32-year-old woman presented to our hospital with a right breast mass. In September 2000, she underwent pectoral muscle-preserving mastectomy for the treatment of right breast cancer. Pathologyy results revealed a mucinous carcinoma 27 × 20 × 18 mm in size accompanied by an extensive intraductal component. The tumor was staged as T2 N1M0 stage IIB and found to be estrogen receptor-positive, and 6 cycles of postoperative adjuvant chemotherapy consisting of 5-fluorouracil, epirubicin, and cyclophosphamide were carried out. goserelin acetate plus tamoxifen was prescribed from April 2001 to March 2005. Since the patient received tamoxifen from April 2005 and eumenorrhea started in June 2006, goserelin acetate plus tamoxifen was started in August 2006. The patient was determined to be 25 weeks pregnant by abdominal ultrasonography in February 2007. This meant that she had been taking goserelin acetate plus tamoxifen for 6 months without realizing she was pregnant. She gave birth to a girl by cesarean section in May 2007. No abnormalities, including anomaly of the genitalia, were seen, and the subsequent growth of the infant was also satisfactory. We here report this case and a brief review of the literature.\n\nsentence: A case of delivery of healthy infant in breast cancer patient incidentally treated with goserelin acetate and tamoxifen during pregnancy .", "role": "user" }, { "content": "[[\"goserelin acetate\", \"tamoxifen\", \"POS\"]]", "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\nEmerging treatment of acute coronary syndromes with platelet glycoprotein IIB/IIIA inhibitors .", "role": "user" }, { "content": "{\"Intervention\": [\"platelet glycoprotein IIB/IIIA inhibitors .\"], \"Outcome\": [], \"Participant\": [\"acute coronary syndromes\"]}", "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\nBlock of human NaV1.5 sodium channels by novel alpha-hydroxyphenylamide analogues of phenytoin. Voltage-gated sodium (Na) channels are a critical component of electrically excitable cells. Phenytoin (diphenylhydantoin, DPH) is an established sodium channel blocker and is a useful anticonvulsant and class 1b antiarrhythmic, and has been effectively used in the treatment of neuropathic pain. In this study, we have synthesized novel alpha-hydroxyphenylamide analogues of diphenylhydantoin and examined their ability to inhibit human Na (V) 1.5 sodium channels expressed in Chinese Hamster Ovary (CHO-K1) cells. Phenyl ring substitutions were examined including para-methyl, para-fluoro, para-chloro, ortho-chloro and meta-chloro. We have found that phenyl ring substitutions with electron withdrawing properties resulted in compounds with greater activity. In comparison to diphenylhydantoin, the novel chloro-substituted alpha-hydroxyphenylamide compounds produced as much as a 20-fold greater tonic and frequency-dependent blockade of Na (V) 1.5 channels with an IC (50) value of 14.5 microM. In addition, the chloro-substitutions have position specific state dependent blocking properties. The ortho-, meta- and para-chloro substitutions have an 8-, 13- and 3-fold increased affinity for the inactivated state, respectively. Molecular modeling suggests that these differences in affinity are due to a direct interaction with the receptor. Comparing models of diphenylhydantoin to the novel alpha-hydroxyphenlyamide compound suggests that the increased activity may be due to an optimized phenyl ring position and increased molecular volume. This information may be useful in the development of more potent sodium channel blockers.", "role": "user" }, { "content": "[[\"alpha-hydroxyphenylamide\", \"INHIBITOR\", \"Na (V) 1.5\"], [\"sodium\", \"SUBSTRATE\", \"human NaV1.5\"], [\"Na\", \"SUBSTRATE\", \"Voltage-gated sodium (Na) channels\"], [\"alpha-hydroxyphenylamide\", \"INHIBITOR\", \"human NaV1.5\"], [\"diphenylhydantoin\", \"INHIBITOR\", \"human Na (V) 1.5\"], [\"sodium\", \"SUBSTRATE\", \"sodium channels\"], [\"diphenylhydantoin\", \"INHIBITOR\", \"sodium channels\"], [\"phenytoin\", \"INHIBITOR\", \"human NaV1.5\"], [\"alpha-hydroxyphenylamide\", \"INHIBITOR\", \"sodium channels\"], [\"sodium\", \"SUBSTRATE\", \"human Na (V) 1.5\"], [\"sodium\", \"SUBSTRATE\", \"Voltage-gated sodium (Na) channels\"], [\"sodium\", \"SUBSTRATE\", \"sodium channel\"], [\"diphenylhydantoin\", \"INHIBITOR\", \"Na (V) 1.5\"], [\"DPH\", \"INHIBITOR\", \"sodium channel\"], [\"Phenytoin\", \"INHIBITOR\", \"sodium channel\"], [\"diphenylhydantoin\", \"INHIBITOR\", \"sodium channel\"], [\"alpha-hydroxyphenylamide\", \"INHIBITOR\", \"human Na (V) 1.5\"], [\"phenytoin\", \"INHIBITOR\", \"sodium channels\"]]", "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 humans, MERS is mostly known as a lower respiratory tract (LRT) disease involving fever, cough, breathing difficulties and pneumonia that may progress to acute respiratory distress syndrome, multiorgan failure and death in 20 % to 40 % of those infected. However, MERS-CoV has also been detected in mild and influenza-like illnesses and in those with no signs or symptoms. Older males most obviously suffer severe disease and MERS patients often have comorbidities. Compared to severe acute respiratory syndrome (SARS), another sometimes- fatal zoonotic coronavirus disease that has since disappeared, MERS progresses more rapidly to respiratory failure and acute kidney injury (it also has an affinity for growth in kidney cells under laboratory conditions), is more frequently reported in patients with underlying disease and is more often fatal. Most human cases of MERS have been linked to lapses in infection prevention and control (IPC) in healthcare settings, with approximately 20 % of all virus detections reported among healthcare workers (HCWs) and higher exposures in those with occupations that bring them into close contact with camels. Sero-surveys have found widespread evidence of past infection in adult camels and limited past exposure among humans. Sensitive, validated reverse transcriptase real-time polymerase chain reaction (RT-rtPCR)-based diagnostics have been available almost from the start of the emergence of MERS. While the basic virology of MERS-CoV has advanced over the past three years, understanding of the interplay between camel, environment, and human remains limited. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1186/s12985-015-0439-5) contains supplementary material, which is available to authorized users. Text: An email from Dr Ali Mohamed Zaki, an Egyptian virologist working at the Dr Soliman Fakeeh Hospital in Jeddah in the Kingdom of Saudi Arabia (KSA) announced the first culture of a new coronavirus to the world. The email was published on the website of the professional emerging diseases (ProMED) network on 20 th September 2012 [1] (Fig. 1) and described the first reported case, a 60 year old man from Bisha in the KSA. This information led to the rapid discovery of a second case of the virus, this time in an ill patient in the United Kingdom, who had been transferred from Qatar for care [2] . The new virus was initially called novel coronavirus (nCoV) and subsequentlty entitled the Middle East respiratoy syndrome coronavirus (MERS-CoV). As of 2 nd of September 2015, there have been 1,493 detections of viral RNA or virus-specific antibodies across 26 countries (Additional file 1: Figure S1 ) confirmed by the World Health Organization (WHO), with over a third of the positive people dying (at least 527, 35 %) [3] . Since that first report, a slow discovery process over the following two to three years revealed a virus that had infected over 90 % of adult dromedary camels (DC; Camelus dromedarius) in the KSA [4] , also DCs across the Arabian Peninsula and parts of Africa that are a source of DC imports for the KSA [5] . To date, MERS-CoV has not been detected in DCs tested in zoos or herds from other parts of the world [6] [7] [8] [9] . Occasionally, virus is transmitted from infected DCs to exposed humans. Subsequent transmission to other humans requires relatively close and prolonged exposure [10] . The first viral isolate was patented and concerns were raised that this would restrict access to both the virus and to viral diagnostics [11, 12] . However, sensitive, validated reverse transcriptase real-time polymerase chain reaction (RT-rtPCR)-based diagnostics were quickly described and virus was made freely available subject to routine biosafety considerations [13] . Subsequent epidemiology and research has identified the cell receptor as exopeptidase dipeptidyl peptidase 4 (DPP4; also called CD26); that MERS-CoV has a broad tropism, replicating better in some cells lines and eliciting a more proinflammatory response than SARS-CoV; is widespread in DCs; has the potential to infect other animals and that MERS kills its human host more often than SARS did (20-40 % versus 9 % for SARS [14] ) [15] [16] [17] [18] [19] . In humans, overt disease was given the name Middle East respiratory syndrome, with the acronym MERS. From intermittent animal-to-human spill-over events, the MERS-CoV spreads sporadically among people, causing more severe disease among older adults, especially males, with pre-existing diseases. The spread of MERS-CoV among humans has often been associated with outbreaks in hospitals, with around 20 % of all cases to date involving healthcare workers (HCWs). Although DCs appear to suffer the equivalent of a 'common cold' from MERS-CoV infection, in humans, the virus can be a more serious and opportunistic pathogen associated with the death of up to 40 % of reported cases. It has yet to be established whether infections thought to have been acquired from an animal source produce a more severe outcome than those spread between humans [20] . Studies have established that the mean incubation period for MERS is five to six days, ranging from two to 16 days, with 13 to 14 days between when illness begins in one person and subsequently spreads to another [21] [22] [23] [24] . Among those with progressive illness, the median time to death is 11 to 13 days, ranging from five to 27 days [23, 24] . Fever and gastrointestinal symptoms may form a prodrome, after which symptoms decline, only to be followed by a more severe systemic and respiratory syndrome [25, 26] . The first WHO case definition [27] defined probable cases of MERS based on the presence of febrile illness, cough and requirement for hospitalization with suspicion of lower respiratory tract (LRT) involvement. It also included roles for contact with a probable or confirmed case or for travel or residence within the Arabian Peninsula. If strictly adhered to, only the severe syndrome would be subject to laboratory testing, which was the paradigm early on [21] . From July 2013, the revised WHO case definition included the importance of seeking out and understanding the role of asymptomatic cases and from June 2014, the WHO definition more clearly stated that a confirmed case included any person whose sample was RT-PCR positive for MERS-CoV, or who produced a seroconversion, irrespective of clinical signs and symptoms. [28] [29] [30] Apart from the WHO and the KSA Ministry of Health reports, asymptomatic or subclinical cases of MERS-CoV infection were documented in the scientific literature although not always as often as occurred early on [31, 32] . The KSA definition of a case became more strict on 13 th May 2014, relying on the presence of both clinical features and laboratory confirmation [33] . Testing of asymptomatic people was recommended against from December 2014 [34] , reinforced by a case definition released by the KSA Ministry of Health in June 2015 [35] . The KSA has been the source of 79 % of human cases. Severe MERS is notable for its impact among older men with comorbid diseases including diabetes mellitus, cirrhosis and various lung, renal and cardiac conditions [36] [37] [38] . Interestingly in June 2015, an outbreak in South Korea followed a similar distribution [39, 40] . Among laboratory confirmed cases, fever, cough and upper respiratory tract (URT) signs and symptoms usually occur first, followed within a week by progressive LRT distress and lymphopaenia [37] . Patients often present to a hospital with pneumonia, or worse, and secondary bacterial infections have been reported [37, 41] . Disease can progress to acute respiratory distress syndrome and multiorgan system failure [37] . MERS has reportedly killed approximately 35 % of all reported cases, 42 % of cases in the KSA, yet only 19 % of cases in South Korea, where mortality ranged from 7 % among younger age groups to 40 % among those aged 60 years and above [42] ; all may be inflated values with asymptomatic or mild infections sometimes not sought or not reported [34] . General supportive care is key to managing severe cases [43] . Children under the age of 14 years are rarely reported to be positive for MERS-CoV, comprising only 1.1 % (n = 16) of total reported cases. Between 1 st September 2012 and 2 nd December 2013, a study described the then tally of paediatric cases in the KSA, which stood at 11 (two to 16 years of age; median 13 years); nine were asymptomatic (72 %) and one infant died [44] . In Amman, Jordan, 1,005 samples from hospitalized children under the age of two years with fever and/or respiratory signs and symptoms were tested but none were positive for MERS-CoV RNA, despite being collected at a similar time to the first known outbreak of MERS-CoV in the neighbouring town of Al-Zarqa [45] . A second trimester stillbirth occurred in a pregnant woman during an acute respiratory illness and while not RT-rtPCR positive, the mother did subsequently develop antibodies to MERS-CoV, suggestive of recent infection [46] . Her exposure history to a MERS-CoV RT-rtPCR positive relative and an antibody-reactive husband, her incubation period and her symptom history met the WHO criteria for being a probable MERS-CoV case [46] . Diagnostic methods were published within days of the ProMED email announcing the first MERS case [47] , including several now gold standard in-house RT-rtPCR assays (Fig. 2 ) as well as virus culture in Vero and LLC-MK2 cells [18, 47, 48] . A colorectal adenocarcinoma (Caco-2) epithelial cell line has since been recommended for isolation of infections MERS-CoV [49] . We previously [18] . ). Open reading frames are indicated as yellow rectangles bracketed by terminal untranslated regions (UTR; grey rectangles). FS-frame-shift. Predicted regions encompassing recombination break-points are indicated by orange pills. Created using Geneious v8.1 [211] and annotated using Adobe Illustrator. Beneath this is a schematic depicting the location of RT-PCR primers (blue arrows indicate direction) and oligoprobes (green rectangles) used in the earliest RT-rtPCR screening assays and conventional, semi-nested (three primers) RT-PCR confirmatory sequencing assays [47, 48] . Publication order is noted by first [27 th September 2012; red] and second [6 th December 2012; orange] coloured rectangles; both from Corman et al. [47, 48] Those assays recommended by the WHO are highlighted underneath by yellow dots [53] . The NSeq reverse primer has consistently contained one sequence mismatch with some MERS-CoV variants. An altered version of that from Mackay IM, Arden KE. Middle East respiratory syndrome: An emerging coronavirus infection tracked by the crowd. Virus Res 2015 Vol 202:60-88 with permission from Elsevier [5] reviewed the broad tropism of MERS-CoV [5] . However, as is well described, cell culture is a slow, specialised and insensitive method [50] while PCR-based techniques are the preferred method for MERS-CoV detection. The first open reading frames (ORF 1a and 1b; Fig. 2 ) have become a key diagnostic and taxonomic target for CoV species identification. With less than 80 % identity between the amino acid sequence of MERS ORF 1ab and betacoronavirus relatives, Tylonycteris bat HKU4 and Pipistrellus bat HKU5, it can be concluded that it is a novel and distinct virus. MERS-CoV is predicted to encode ten open reading frames with 5' and 3' untranslated regions [51] . The structural proteins include the spike (S), envelope (E), membrane (M) and nucleocapsid (N) [52] . The products of ORF1a and ORF1b are predicted to encode nonstructural proteins. The majority of specimen testing to date has employed validated RT-rtPCR assays shown to be sensitive and specific [47, 48, 53] . The RealStar® kit uses these WHOrecommended assays [54] . The target sequences of these screening assays have not changed among genomes examined until at least mid-2015 (IMM observation). Other RT-rtPCR assays have been developed and validated for use as laboratory-based diagnostic tools [55] [56] [57] . Additionally, loop-mediated [58, 59] or recombinase polymerase [60] isothermal assays have been designed for field deployment. The detection of MERS-CoV antigen has not been common to date but the combination of short turnaround time from test to result, high throughput and identification of viral proteins makes this an attractive option. Detection of viral proteins rather than viral RNA indicates the likely presence of infectious virus. The first rapid immunochromatographic tool described could detect recombinant MERS-CoV nucleocapsid protein from DC nasal swabs with 94 % sensitivity and 100 % specificity compared to RT-rtPCR [61] . A different approach used a monoclonal antibody-based capture ELISA targeting the MERS-CoV nucleocapsid protein with a sensitivity of 10 3 TCID 50 and 100 % specificity [62] . Demonstration of a seroconversion to a MERS-CoV infection meets the current WHO definition of a case so optimized and thoroughly validated sero-assays employed alongside good clinical histories are useful to both identify prior MERS-CoV infection and help support transmission studies. Because serology testing is, by its nature, retrospective, it is usual to detect a viral footprint, in the form of antibodies, in the absence of any signs or symptoms of disease and often in the absence of any viral RNA [63] . Strategic, widespread sero-surveys of humans using samples collected after 2012 are infrequent. Much of the Arabian Peninsula and all of the Horn of Africa lack baseline data describing the proportion of the community who may have been infected by a MERS-CoV. However, sero-surveys have had widespread use in elucidating the role of DCs as a transmission source for MERS-CoV. Because of the identity shared between DC and human MERS-CoV (see Molecular epidemiology: using genomes to understand outbreaks), serological assays for DC sero-surveys should be transferrable to human screening with minimal re-configuration.\n\nQuestion: What does the MERS LRT disease involve?", "role": "user" }, { "content": "fever, cough, breathing difficulties and pneumonia that may progress to acute respiratory distress syndrome, multiorgan failure and death in 20 % to 40 % of those infected.", "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\nGenistein protection against acetaminophen-induced liver injury via its potential impact on the activation of UDP-glucuronosyltransferase and antioxidant enzymes. The purpose of this study was to investigate genistein's influence on the relationship between the activation of uridine diphosphate glucuronosyltransferase (UGTs) and the protection against acetaminophen-induced liver toxicity. Animal experimental results revealed that genistein (50, 100 or 200mg/BWkg) significantly ameliorated the biomarkers alanine aminotransferase, alanine aminotransferase, lactate dehydrogenase and malondialdehyde, as indicators of acute liver damage caused by APAP (200mg/BWkg). The level of GSH declined sharply after treatment with APAP within 1h in both the liver and blood with and without genistein. However, after 16h, the levels approached or returned to the original level. Genistein may accelerate and promote APAP glucuronidation as the results showed that APAP-glucuronide increased by 18.44%, 46.79%, and 66.49% for 4h of treatment with genistein dosages of 50, 100 or 200mg/BWkg, respectively, compared with the APAP-only treatment. The activation of UGTs and glutathione peroxidase and the inhibition of CYP2E1 by genistein were observed, and UGTs mRNA expression level with genistein was measured. These findings suggest that genistein can prevent and protect against APAP-induced liver toxicity due to the inhibition of APAP biotransformation and the resistance to oxidative stress via the modulation of the activities of metabolism and the antioxidant enzyme.", "role": "user" }, { "content": "{\"Chemical\": [\"uridine diphosphate\", \"genistein\", \"glucuronide\", \"glutathione\", \"UDP\", \"lactate\", \"acetaminophen\", \"alanine\", \"malondialdehyde\", \"GSH\", \"APAP\", \"Genistein\"]}", "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 target of tanezumab?\n\nContext: Nerve growth factor inhibition with tanezumab influences weight-bearing and subsequent cartilage damage in the rat medial meniscal tear model.\nOBJECTIVE: To investigate whether the effects of nerve growth factor (NGF) inhibition with tanezumab on rats with medial meniscal tear (MMT) effectively model rapidly progressive osteoarthritis (RPOA) observed in clinical trials.\nCurrent research focuses on the development of new OA drugs (such as sprifermin/recombinant human fibroblast growth factor-18, tanezumab/monoclonal antibody against β-nerve growth factor), which aims for more effectiveness and less incidence of adverse effects than the traditional ones.\nAreas covered: This manuscript is a review that examines both the pharmacological properties and clinical studies of tanezumab, the most widely studied antibody to NGF, for management of osteoarthritis (OA) and low back pain.\nOBJECTIVE: Evaluate efficacy and safety of tanezumab, a humanized monoclonal antibody against nerve growth factor, in neuropathic pain.\nIn preclinical studies, tanezumab, and its murine precursor muMab-911, effectively targeted the NGF pathway in various chronic and inflammatory pain models.\nTanezumab (RN-624), a first-in-class recombinant humanized mAb targeting NGF, is being developed by Pfizer Inc for the potential treatment of pain associated with several conditions.\nGiven that tanezumab is an antibody, the drug demonstrates the general advantages of this class of products (including good specificity and favorable pharmacokinetics), and also appears to be particularly well suited for targeting the chronic and inflammatory-mediating pain actions of NGF and its receptor system.\nIn this randomized, double-blind, placebo controlled phase 2 study we investigated tanezumab, a humanized monoclonal antibody that specifically inhibits nerve growth factor as a treatment for interstitial cystitis pain.Patients with interstitial cystitis received a single intravenous dose of 200 μg/kg tanezumab or placebo\nNerve safety of tanezumab, a nerve growth factor inhibitor for pain treatment.\nIn preclinical studies, tanezumab, and its murine precursor muMab-911, effectively targeted the NGF pathway in various chronic and inflammatory pain models.\nTanezumab (RN-624), a first-in-class recombinant humanized mAb targeting NGF, is being developed by Pfizer Inc for the potential treatment of pain associated with several conditions.\nGiven that tanezumab is an antibody, the drug demonstrates the general advantages of this class of products (including good specificity and favorable pharmacokinetics), and also appears to be particularly well suited for targeting the chronic and inflammatory-mediating pain actions of NGF and its receptor system..", "role": "user" }, { "content": "nerve growth factor", "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\nSurface-modified HK:siRNA nanoplexes with enhanced pharmacokinetics and tumor growth inhibition.\nWe characterized in this study the pharmacokinetics and antitumor efficacy of histidine-lysine (HK):siRNA nanoplexes modified with PEG and a cyclic RGD (cRGD) ligand targeting αvβ3 and αvβ5 integrins. With noninvasive imaging, systemically administered surface-modified HK:siRNA nanoplexes showed nearly 4-fold greater blood levels, 40% higher accumulation in tumor tissue, and 60% lower luciferase activity than unmodified HK:siRNA nanoplexes. We then determined whether the surface-modified HK:siRNA nanoplex carrier was more effective in reducing MDA-MB-435 tumor growth with an siRNA targeting Raf-1. Repeated systemic administration of the selected surface modified HK:siRNA nanoplexes targeting Raf-1 showed 35% greater inhibition of tumor growth than unmodified HK:siRNA nanoplexes and 60% greater inhibition of tumor growth than untreated mice. The improved blood pharmacokinetic results and tumor localization observed with the integrin-targeting surface modification of HK:siRNA nanoplexes correlated with greater tumor growth inhibition. This investigation reveals that through control of targeting ligand surface display in association with a steric PEG layer, modified HK: siRNA nanoplexes show promise to advance RNAi therapeutics in oncology and potentially other critical diseases.", "role": "user" }, { "content": "{\"Chemical\": [\"histidine\", \"PEG\", \"lysine\"], \"Protein\": [\"RGD\", \"\\u03b1v\\u03b23\", \"\\u03b1v\\u03b25 integrins\", \"Raf-1\", \"integrin\", \"cRGD\"]}", "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 winter can spread the coronavirus transmission as in winter months, people may cluster together more indoors, increasing the number of folks at risk of becoming infection by someone who's contagious.\n\nAbstract:\nThe coronavirus disease 2019 (COVID-19) outbreak has become a severe public health issue.\nThe novelty of the virus prompts a search for understanding of how ecological factors affect the transmission and survival of the virus.\nSeveral studies have robustly identified a relationship between temperature and the number of cases.\nHowever, there is no specific study for a tropical climate such as Brazil.\nThis work aims to determine the relationship of temperature to COVID-19 infection for the state capital cities of Brazil.\nCumulative data with the daily number of confirmed cases was collected from February 27 to April 1, 2020, for all 27 state capital cities of Brazil affected by COVID-19.\nA generalized additive model (GAM) was applied to explore the linear and nonlinear relationship between annual average temperature compensation and confirmed cases.\nAlso, a polynomial linear regression model was proposed to represent the behavior of the growth curve of COVID-19 in the capital cities of Brazil.\nThe GAM dose-response curve suggested a negative linear relationship between temperatures and daily cumulative confirmed cases of COVID-19 in the range from 16.8 °C to 27.4 °C.\nEach 1 °C rise of temperature was associated with a -4.8951% (t = -2.29, p = 0.0226) decrease in the number of daily cumulative confirmed cases of COVID-19.\nA sensitivity analysis assessed the robustness of the results of the model.\nThe predicted R-squared of the polynomial linear regression model was 0.81053.\nIn this study, which features the tropical temperatures of Brazil, the variation in annual average temperatures ranged from 16.8 °C to 27.4 °C.\nResults indicated that temperatures had a negative linear relationship with the number of confirmed cases.\nThe curve flattened at a threshold of 25.8 °C.\nThere is no evidence supporting that the curve declined for temperatures above 25.8 °C.\nThe study had the goal of supporting governance for healthcare policymakers.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Results indicated that temperatures had a negative linear relationship with the number of confirmed cases.\"]}", "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: Applications of group theoretical methods to non-newtonian fluid flow models: survey of results \nChapter Title: Symmetry Reductions of a Flow with Power-Law Fluid \n1. Abstract of Cited Paper (BIB001): Solar power plants with surface receivers have low overall energy conversion efficiencies due to large emissive losses at high temperatures. Alternatively, volumetric receivers promise increased performance because solar radiation can be transferred into a fluid medium, which subsequently reduces the concentrated heat at the surface. Copper nanofluid-based direct solar receivers, where nanoparticles in a liquid medium can scatter and absorb solar radiation, have recently received interest to efficiently distribute and store the thermal energy. The objective of the present work is to investigate theoretically the unsteady Hiemenz flow of an incompressible viscous Cu-nanofluid past a porous wedge due to solar energy (incident radiation). The partial differential equations governing the problem under consideration are transformed by a special form of Lie symmetry group transformations viz. one-parameter group of transformation into a system of ordinary differential equations which are solved numerically using Runge Kutta Gill based shooting method. The conclusion is drawn that the flow field and temperature are significantly influenced by magnetic strength, convective radiation, thermal stratification, buoyancy force and porosity of the wedge sheet.\n\nLiterature Review:", "role": "user" }, { "content": "and Contaminant-Modified Viscosity BIB001 . Moitsheki et al. BIB001 have analyzed a system dealing with nonreactive pollutant transport along a single channel. Constitutive equations obeying a power-law fluid are utilized in the description of the mathematical problem. Invariant solutions which satisfy physical boundary conditions have been constructed using the Lie group approach. The dimensionless governing equations that describe the flow model are BIB001 = + [ ( ) Here is the Schmidt number and is the imposed constant pressure axial gradient. The Lie point symmetries of the above system corresponding to different forms of the source term ( , ) are given in Table 1 of BIB001 . The invariant solutions of system BIB002 found in BIB001 are of the form . An analysis has been conducted to study the problem of heat transfer of a power-law fluid over a vertical stretching sheet with slip boundary condition by Mutlag et al. . The partial differential equations governing the physical model have been converted into a set of nonlinear coupled ordinary differential equations using scaling group of transformations. These reduced equations are then solved numerically using the Runge-Kutta-Fehlberg fourthfifth order numerical method.", "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:\nSchool-Based Secondary Prevention for Children with Disruptive Behavior: Initial Outcomes\nAbstract 1:\nFirst through fourth grade rs from 22 suburban elementary schools were screened for cross- setting disruptive behavior as eligibility criteria for participation in a longitudinal secondary prevention study aim ed at reducing the risk for serious externalizing behavioral disorders . Three hundred nine subjects participated in either a multicomponent competence enhancement intervention ( MCEI ) or an information/attention control ( IAC ) condition over a 2-year period . Following baseline measurements , initial intervention effects were assessed at the end of intervention Year 1 , at the beginning of intervention Year 2 ( fall of the next school year ) , and at the end of intervention Year 2 . Multi source assessment s were not supportive of the efficacy of the MCEI over the IAC condition . Children in both groups rated themselves as improved over time in terms of increased adaptive skills and decreased school problems and internalizing symptoms . Teacher and parent ratings of externalizing behavior did not yield evidence of positive change , but teachers noted improved problem solving and observers noted a decrease in behavioral interference in both groups over time , possibly as a result of maturation\n\n\nTitle 2:\nAn attributional intervention to reduce peer-directed aggression among African-American boys.\nAbstract 2:\nAn attributional intervention was design ed to reduce aggressive males ' tendency to attribute hostile intentions to peers following ambiguously caused peer provocations . African-American elementary school boys ( N = 101 ) , aggressive and nonaggressive , were r and omly assigned to the attributional intervention , an attention training program , or a no-treatment control group . Data were collected on subjects ' attributions about hypothetical and laboratory simulations of peer provocation , disciplinary referrals to the school office , and teacher ratings of aggressive behavior . Aggressive subjects in the attributional intervention were less likely to presume hostile intent by peers in hypothetical and laboratory simulations of ambiguous provocation . They were also less likely to endorse hostile retaliation on judgment measures and to engage in verbally hostile behaviors in the laboratory task . Further , intervention subjects were rated as less aggressive by their teachers following the treatment . Both the benefits of attributional change and its limitations in the African-American population are discussed\n\n\nTitle 3:\nModification of anger in children by affective imagery training\nAbstract 3:\nFrom a school population of normal children third through fifth grade s ) , thirty children initially identified as “ angry”were r and omly assigned to either an affective imagery training group , an attention group , or a control group . The treatment group received three sessions of affective imagery in which they focused on physiological changes and on their thoughts associated with prior emotional experiences . Teachers recorded pre- , post- , and short term follow-up aggressive behaviors for all thirty children . Cognitive perceptions and attributions were recorded at the same three occasions on the Affect Question naire . Results suggested that , as a result of affective imagery training , angry children 's perceptions and cognitions shifted from “ angry ” towards “ sad , ” and there was a concomitant decrease in observed aggressive classroom behavior\n\n\nTitle 4:\nPreventing school vandalism and improving discipline: a three-year study.\nAbstract 4:\nV and alism is a major problem facing educators and taxpayers alike . The present investigation analyzed how v and alism costs and student disruption were related to the implementation of a training and consultation package design ed to increase the reinforcing ambience of the school . A positive environment , it was posited , would displace previous events that may have set the occasion for v and alism , with cues to promote productive school performance . Eighteen elementary and junior high schools were involved over a 3-year period . Using a delayed treatment control design , treatment was delivered following either 4 or 13 months of baseline . During treatment , teams of school personnel attended training workshops in behavioral strategies for reducing v and alism and disruption by students in school . Each team also met regularly on its campus to plan and implement programs on a schoolwide basis . To demonstrate that reinforcing procedures were actually implemented and accompanied by change in student performance , these variables were periodically probed throughout the study . Project staff also provided consultation . V and alism costs decreased significantly ( p less than .05 ) more in treatment than control schools , with an average reduction of 78.5 % for all project schools . Rates of praise delivered by project teachers and other r and omly selected teachers in the school increased significantly ( p less than .05 ) , and rates of off-task behavior by students decreased significantly ( p less than .05 ) following treatment . The staff development model used in this study appeared to be both feasible and economical", "role": "user" }, { "content": "School-based violence prevention programs may produce reductions in aggressive and violent behaviors in children who already exhibit such behavior .", "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:\nAdvanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of encoder and decoder are leveraged in the subsequent process, which misses the opportunity to exploit the useful information embedded in other layers. In this work, we propose to simultaneously expose all of these signals with layer aggregation and multi-layer attention mechanisms. In addition, we introduce an auxiliary regularization term to encourage different layers to capture diverse information. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation data demonstrate the effectiveness and universality of the proposed approach.\n\nCited Abstract(s):\n[1]: Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference. Also, most NMT systems have difficulty with rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using attention and residual connections. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units (\"wordpieces\") for both input and output. This method provides a good balance between the flexibility of \"character\"-delimited models and the efficiency of \"word\"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60 compared to Google's phrase-based production system.\n\n[2]: The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.\n\n[3]: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.", "role": "user" }, { "content": "Concerning machine translation, and have shown that deep networks with advanced connecting strategies outperform their shallow counterparts. Due to its simplicity and effectiveness, skip connection becomes a standard component of state-of-the-art NMT models [1] [2] [3] . In this work, we prove that deep representation exploitation can further improve performance over simply using skip connections.", "role": "assistant" } ]

[ { "content": "You will be presented with a sentence from biomedical research text. Extract all terms that correspond to chemical entities of biological interest (ChEBI).\nReturn your identified terms in a JSON array, formatted like this: [\"Entity1\", \"Entity2\", ...].\nIf no such entities are detected, respond by providing an empty JSON array [].\n\nBiomedical context:\nFirst,itispossiblethatexercisegeneratesorincreasesendogenousligandsforPPARdeltaastissuesareundergoingsubstantialincreasesinfatty-acidinternalizationandburning.", "role": "user" }, { "content": "[\"fatty - acid\"]", "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\nhas shown distractor suppression to have a much larger effect on capacity than target selection processes (Bettencourt & Somers, 2009; Pylyshyn, 2006; Vogel et al., 2005; Zanto & Gazzaley, 2009), and as the effect on capacity of increasing the number of distractors is correlated between VSTM and MOT tasks, we believe that the resources consumed by", "role": "user" }, { "content": "Background", "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: Revealing the structure of information flows discriminates similar animal social behaviors\nArticle:\nAbstract:\nBehavioral correlations stretching over time are an essential but often neglected aspect of interactions among animals. These correlations pose a challenge to current behavioral-analysis methods that lack effective means to analyze complex series of interactions. Here we show that non-invasive information-theoretic tools can be used to reveal communication protocols that guide complex social interactions by measuring simultaneous flows of different types of information between subjects. We demonstrate this approach by showing that the tandem-running behavior of the ant Temnothorax rugatulus and that of the termites Coptotermes formosanus and Reticulitermes speratus are governed by different communication protocols. Our discovery reconciles the diverse ultimate causes of tandem running across these two taxa with their apparently similar signaling mechanisms. We show that bidirectional flow of information is present only in ants and is consistent with the use of acknowledgement signals to regulate the flow of directional information.\nIntroduction:\nSocial interactions among individuals unfold across different scales of space and time( Flack, 2012). At short time scales, causal relationships can often be captured by experiments that manipulate an immediate stimulus to reveal its causal connection( s) to a stereotyped response, or fixed action pattern. In herring gulls, for example, the feeding behavior of chicks is visually triggered by a red spot on the lower bill of adult gulls—a causal relationship revealed through experiments in which changes in the color of this spot were shown to affect the likelihood that chicks will engage in feeding behavior( Tinbergen, 1953). However, interactions are often more complex than this because they follow a protocol where rules are conditionally applied over time contingent upon the outcome of previous interactions. In these cases, where short-term histories may affect longer-term outcomes, the ability to make testable predictions requires quantitative tools that can capture the dynamics of the interaction protocol at an intermediate time scale. Considering only short-term interactions, like the stimulus-and-response of herring-gull parent and chick, might not explain functional differences observed at long time scales in otherwise similar behaviors. Consider the tandem-running behavior of many ants and termites, in which one individual leads a follower through their environment, the follower walking closely behind the leader throughout the run.( Figure 1A). At short time scales, tandem runs in the ant Temnothorax rugatulus appear identical to those in the termites Coptotermes formosanus and Reticulitermes speratus. They use similar signaling mechanisms, in which the leader releases a short-range pheromone that attracts the follower( Möglich et al., 1974; Bordereau and Pasteels, 2010), while the follower taps the leader’s body with its antennae to indicate its continued presence( Möglich et al., 1974; Franks and Richardson, 2006; Nutting, 1969; Vargo and Husseneder, 2009). Upon removal of the follower, the leader stops and waits for the follower to resume contact both in ants( Möglich et al., 1974; Franks and Richardson, 2006) and in termites( Mizumoto and Dobata, 2019). At long time scales, however, there exist clear functional differences in these seemingly similar behaviors. Leaders in T. rugatulus use tandem runs as a recruitment mechanism that allows followers to learn a route and acquire navigational information necessary to later repeat the same journey independently of the leader( Figure 1B). In contrast, termites usually use tandem runs during mating, except for one example of recruitment in a basal termite( Sillam-Dussès et al., 2007). In a mated pair, the male follows the female leader only to maintain spatial cohesion when searching for a new home; once a suitable location is found, the termites remain there to start a new colony, and neither partner ever retraces the route of their tandem run. Short-term signaling mechanisms( i. e., their stimulus and response dynamics) are similar between ants and termites and cannot explain species differences in the function of tandem runs( i. e., route learning versus spatial cohesion). These differences are likely encoded at intermediate time scales, where it becomes possible in principle to detect the communication protocol( i. e., set of interaction rules) that describes how and when leader and follower use each short-term signaling mechanism. However, experimental manipulations that operate at intermediate time scales also interfere with and constrain normal patterns of behavior over time. As we show in this study, information-theoretic methods can reveal the structure of information flow between subjects based only on observational data from many repeated interactions. Moreover, these model-free methods do not rely on a priori assumptions and can be applied over different ecological scenarios allowing for comparisons across a wide taxonomic range( McCowan et al., 1999). Information theory provides a model-free formalism to explicitly quantify the effects of the interaction between individuals across space and time( Cover and Thomas, 2005; Lizier et al., 2008). Whereas the generic concept of entropy quantifies the uncertainty in a distribution of outcomes, the derived construct of transfer entropy quantifies the reduction of uncertainty about the future state of a putative receiver given knowledge of the present state of the corresponding sender( Schreiber, 2000). Transfer entropy is well suited for studying message passing; it naturally incorporates temporal ordering, from the sender’s present to the receiver’s future, and quantifies the additional predictive power gained from the sender beyond what is contained in the receiver’s past. In this way, it accounts for autocorrelations that might otherwise affect behavioral data( Mitchell et al., 2019). Previous studies have used symbolic transfer entropy( Staniek and Lehnertz, 2008) to reveal whether one animal is influencing another on the basis of a single symbolic representation of behavioral data( Orange and Abaid, 2015; Butail et al., 2016; Kim et al., 2018; Ward et al., 2018; Porfiri et al., 2019; Ray et al., 2019). We extend these methods by applying transfer entropy to different symbolic representations of the same data to capture parallel information flows within the same behavior( e. g., patterns embedded in symbols representing the direction of motion or the speed of motion as shown in Figure 1C and D). Using different symbolic representations of the same raw data allows us to uncover the complex, multi-layered structure of causal relationships between subjects. Following this approach, we provide evidence that the communication protocol used by leaders and followers over intermediate time scales explains the functional differences between the tandem runs of ants and termites despite their using similar signaling mechanisms at short time scales.\nDiscussion:\nTemporal correlations manifesting over intermediate time scales represent an important but often neglected aspect in behavioral ecology( Mitchell et al., 2019). Complex spatiotemporal interactions among individuals( i. e., those interactions evolving over intermediate time scales) are difficult to study by direct manipulation in highly controlled laboratory settings. Instead, quantitative and non-interventional methods applied over longer observational periods can be used to capture the dynamical aspect of social interactions, but these methods are generally underdeveloped and sporadically used in behavioral ecology. As we have shown in this study, information theory offers tools such as transfer entropy that can disentangle the temporal structure of the interaction between individuals. Whereas the construct of transfer entropy has seen extensive applications in the neurosciences, particularly to study effective connectivity in the brain( Vicente et al., 2011), its application in the field of animal behavior is less frequent and has focused primarily on revealing leader–follower relationships in fish( Butail et al., 2016; Kim et al., 2018; Ward et al., 2018) and bats( Orange and Abaid, 2015), with more recent applications in the study of decision-making in humans( Grabow et al., 2016; Porfiri et al., 2019) and slime molds( Ray et al., 2019). These previous applications set out to answer the generic question of whether one subject is influencing another on the basis of a single symbolic representation of raw data( e. g., a single encoding that carries information only about the direction of motion). Such uses of transfer entropy and other information-theoretic measures( McCowan et al., 1999) cannot disentangle the complex structure of information flow between subjects when simultaneous aspects of their interaction carry different forms of information transmitted in different directions and at different time scales. By quantifying multiple, concurrent symbolic patterns( i. e., variation over time in both direction and speed) and subsequently relating the structure of information flows latent in these data to each other, we have shown how to uncover more complex communication protocols as opposed to simply identifying distinct individuals within a social interaction. The methodology we put forward, which applies advanced information-theoretic measures to different symbolic representations of the same dataset, has allowed us to show differences in the communication protocol used by tandem-running ants and termites, and to explain the disparity in their function. Our approach is sufficiently generic to enable the discovery of cryptic signaling behaviors in other taxa and to provide deeper insights into behaviors whose function is poorly or partially understood( e. g., turn-taking[Flack, 2013; Pika et al., 2018] and complex coordinated dances in birds[Ota et al., 2015]). Furthermore, we have shown how the generality of this approach can extend traditional information-theoretic analysis from a mechanistic focus on one species toward a comparison across a wide taxonomic range. Such a common language of information processing can enable the posing of new questions, hypotheses, and predictions for the evolution of information processing itself.", "role": "user" }, { "content": "Social animals continuously influence each other’s behavior . Most of these interactions simply consist in an individual immediately responding to the behavior of another in a predictable way . Still , when the same individuals interact over long periods , complex social interactions can arise . These can be difficult for scientists to study , because how animals behave at a given moment depends on their shared history . Certain species of ants and termites use smell and touch to do ‘tandem runs’ and move in pairs through the environment . Only ants , however , can learn a new route from their running partner . Understanding how this difference arises means examining how the animals interact and communicate over longer time scales . This requires new approaches to capture how information flows between the insects . Here , Valentini et al . used a scientific methodology known as information theory to study tandem running in one species of ants and two species of termites . Information theory provides a framework to quantify how information is shared , processed and stored . The flow of information between individuals was measured separately for different aspects of tandem running . At small time scales , ant and termite behavior appeared identical , but over longer periods , it was possible to distinguish between the two types of insects . In termites , only one individual in a pair sent information to the other to instruct the second termite where to go . By contrast , in ants , both members of the tandem communicated with each other in a way that was consistent with how humans acknowledge information they receive from other individuals . The approach used by Valentini et al . will be useful to researchers who study how complex and often cryptic social interactions develop over extended periods in social animals . This framework could also be applied in other systems such as groups of cells , or economic networks .", "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: We demonstrate the application of the u-net to three different segmentation tasks. The first task is the segmentation of neuronal structures in electron microscopic recordings. An example of the data set and our obtained segmentation is displayed in Figure 2. We provide the full result as Supplementary Material. The data set is provided by the EM segmentation challenge [14] that was started at ISBI 2012 and is still open for new contributions. The training data is a set of 30 images (512x512 pixels) from serial section transmission electron microscopy of the Drosophila first instar larva ventral nerve cord (VNC). Each image comes with a corresponding fully annotated ground truth segmentation map for cells (white) and membranes (black). The test set is publicly available, but its segmentation maps are kept secret. An evaluation can be obtained by sending the predicted membrane probability map to the organizers. The evaluation is done by thresholding the map at 10 different levels and computation of the “warping error”, the “Rand error” and the “pixel error” [14].\n\nQuestion: What is electron microscopic recordings used for ?", "role": "user" }, { "content": "Electron microscopic recordings can be used to highlight neuronal structures.", "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\nConcomitant downregulation of IgH 3'enhancer activity and c-myc expression in a plasmacytoma x fibroblast environment: implications for dysregulation of translocated c-myc. Regulation of immunoglobulin heavy chain (IgH) gene expression is controlled by a B cell-specific promoter, intronic enhancer and additional B cell-specific enhancer elements identified recently in the 3' end of the IgH locus. One of the latter elements, the IgH 3' enhancer, is of particular interest: (1) it is B cell-specific and active only in late B cell development; (2) in rodent plasmacytomas and in some human Burkitt's lymphomas it is part of a locus control region (LCR) that is involved in deregulation of the c-myc oncogene as a result of translocation into the IgH locus; and (3) it has been implicated in the mechanisms that control Ig gene class switch recombination. We have used a somatic cell hybridization approach to genetically analyse regulation of the activity of the IgH 3' enhancer. When mouse MPC11 plasmacytoma cells, in which the IgH 3' enhancer is active, are fused with fibroblasts, Ig expression is extinguished at the level of transcription. Here we show that in a MPC11 plasmacytoma x fibroblast environment, the IgH 3' enhancer is transcriptionally inactive. Furthermore, we demonstrate that binding of several B cell-specific transcription factors, essential for IgH 3' enhancer activity, is lacking, which may explain 3' enhancer inactivity, although the binding of repressors can not be excluded. Moreover, the high expression level of c-myc, characteristic of the parental MPC11 cells carrying the t (12;15) translocation, is down-regulated in the hybrids to that in unfused fibroblasts. Therefore, inactivation of the IgH 3' enhancer is a multifactorial process affecting several transcription factors that control the cell-specific and developmental activity of the enhancer.", "role": "user" }, { "content": "{\"CellLine\": [\"mouse MPC11 plasmacytoma cells\", \"MPC11 plasmacytoma x fibroblast environment\", \"MPC11 cells\"], \"CellType\": [\"fibroblasts\"], \"DNA\": [\"c - myc oncogene\", \"t (12;15) translocation\", \"LCR\", \"intronic enhancer\", \"IgH locus\", \"enhancer\", \"IgH 3\\u0027 enhancer\", \"B cell - specific promoter\", \"Ig gene class\", \"B cell - specific enhancer elements\", \"locus control region\", \"immunoglobulin heavy chain (IgH) gene\", \"c - myc\"], \"Protein\": [\"transcription factors\", \"B cell - specific transcription factors\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: I am building a landmark localization network based on DDN.\n\nKeyphrases: landmark localization images\n\nDataset description:\nCelebA: CelebFaces Attributes dataset contains 202,599 face images of the size 178×218 from 10,177 celebrities, each annotated with 40 binary labels indicating facial attributes like hair color, gender and age.\nAFW: AFW (Annotated Faces in the Wild) is a face detection dataset that contains 205 images with 468 faces. Each face image is labeled with at most 6 landmarks with visibility labels, as well as a bounding box.\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.\nDeepLoc: DeepLoc is a large-scale urban outdoor localization dataset. The dataset is currently comprised of one scene spanning an area of 110 x 130 m, that a robot traverses multiple times with different driving patterns.\nUniversity-1652: Contains data from three platforms, i.e., synthetic drones, satellites and ground cameras of 1,652 university buildings around the world. University-1652 is a drone-based geo-localization dataset and enables two new tasks, i.e., drone-view target localization and drone navigation.\nOxford5k: Oxford5K is the Oxford Buildings Dataset, which contains 5062 images collected from Flickr. It offers a set of 55 queries for 11 landmark buildings, five for each landmark.\n\nOptions:- A: CelebA B: AFW C: ConvAI2 D: DeepLoc E: University-1652 F: Oxford5k", "role": "user" }, { "content": "[\"CelebA\", \"AFW\"]", "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\nThe spatial distribution of human immunoglobulin genes within the nucleus: evidence for gene topography independent of cell type and transcriptional activity. The three-dimensional positioning of immunoglobulin (Ig) genes within the nucleus of human cells was investigated using in situ hybridization and confocal microscopy. The visualization of heavy and light chain genes in B-lymphoid cells showed that the three Ig genes are differentially and nonrandomly distributed in different nuclear subvolumes: the kappa genes were found to be preferentially confined to an outer nuclear volume, whereas the gamma and lambda genes consistently occupied more central positions within the nucleus, the lambda genes being more interior when compared with the gamma genes. The data further show that these overall topographical distributions are independent of gene transcriptional activity and are conserved in different cell types. Although subtle gene movements within those defined topographical regions can not be excluded by this study, the results indicate that tissue specificity of gene expression is not accompanied by drastic changes in gene nuclear topography, rather suggesting that gene organization within the nucleus may be primarily dependent on structural constraints imposed on the respective chromosomes.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"different cell types\", \"human cells\", \"B - lymphoid cells\"], \"DNA\": [\"human immunoglobulin genes\", \"kappa genes\", \"Ig genes\", \"heavy and light chain genes\", \"gamma and lambda genes\", \"immunoglobulin (Ig) genes\", \"gamma genes\", \"the three Ig genes\", \"chromosomes\", \"lambda genes\"], \"Protein\": [], \"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\nIdentity begins to take shape during adolescence, but, with the incorporation of new life experiences, is continually modified throughout adulthood (McLean, 2008). Theories of identity maintain that individuals engage in particular actions to confirm their own identities and that social role expectations are internalized and demonstrated through behavior (Stryker & Burke, 2000). Most historical models of adult development that are discussed in the literature are based on research with all-male subjects or were written from a male vantage point (Caffarella & Olson, 1993). Factors that most meaningfully impact the identities of older women are unacknowledged in these models (Price, 1998). Such models, including work by Erikson (1982), stress D ow nl oa de d by [ M cG ill U ni ve rs ity L ib ra ry ] at 2 0: 35 0 5 Fe br ua ry 2 01 5", "role": "user" }, { "content": "Background", "role": "assistant" } ]