Datasets:

kejian

/

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

like 0

[ { "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 COVID crisis has created mental health issues that cannot be ignored.\n\nAbstract:\nPublic mental health response to coronavirus disease is essential.\nAfter reviewing systemic and local efforts in China, we found efficient coordination and human resources.\nWe recommend better symptom assessment, monitoring of organizations, and basic needs protection.\nThis recommendation can inform how other countries can overcome mental health challenges during this pandemic.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Public mental health response to coronavirus disease is essential.\", \"This recommendation can inform how other countries can overcome mental health challenges during this pandemic.\"]}", "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: In vitro combination studies of tenofovir and other nucleoside analogues with ribavirin against HIV-1. In patients coinfected and treated for both HIV-1 and hepatitis C virus ( HCV ) , administration of ribavirin ( RBV ) may result in altered intracellular drug levels of nucleoside reverse transcriptase inhibitors through inhibition of inosine 5'-monophosphate dehydrogenase . Drug interactions between tenofovir and RBV were studied in vitro in order to provide insights into the safety of co-administration of tenofovir disoproxil fumarate (DF) and RBV in HCV/HIV-1-coinfected patients. In accordance with previous in vitro studies, strongly increased anti-HIV activity was observed when RBV was combined with didanosine (ddl). In contrast, low-level anti-HIV antagonism was observed when RBV was combined with either tenofovir or abacavir. Significantly stronger anti-HIV antagonism was observed when RBV was combined with either zidovudine, stavudine, emtricitabine or lamivudine. Thus, although tenofovir and ddl are both adenosine analogues, their in vitro interactions with RBV are markedly different. These results suggest a low potential for increased toxicity upon co-administration of tenofovir DF with RBV in patients.\n\nsentence: In patients coinfected and treated for both HIV-1 and hepatitis C virus ( HCV ) , administration of ribavirin ( RBV ) may result in altered intracellular drug levels of nucleoside reverse transcriptase inhibitors through inhibition of inosine 5'-monophosphate dehydrogenase .", "role": "user" }, { "content": "[]", "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 want to train a supervised model for visual question answering from images.\n\nKeyphrases: visual question answering image\n\nDataset description:\nGQA: The GQA dataset is a large-scale visual question answering dataset with real images from the Visual Genome dataset and balanced question-answer pairs. Each training and validation image is also associated with scene graph annotations describing the classes and attributes of those objects in the scene, and their pairwise relations.\nVisual Genome: Visual Genome contains Visual Question Answering data in a multi-choice setting. It consists of 101,174 images from MSCOCO with 1.7 million QA pairs, 17 questions per image on average.\nCOCO-QA: COCO-QA is a dataset for visual question answering. It consists of: 123287 images 78736 train questions 38948 test questions 4 types of questions: object, number, color, location Answers are all one-word.\nVQA-E: VQA-E is a dataset for Visual Question Answering with Explanation, where the models are required to generate and explanation with the predicted answer. The VQA-E dataset is automatically derived from the VQA v2 dataset by synthesizing a textual explanation for each image-question-answer triple.\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.\nTextVQA: TextVQA is a dataset to benchmark visual reasoning based on text in images. TextVQA requires models to read and reason about text in images to answer questions about them.\nBookCorpus: BookCorpus is a large collection of free novel books written by unpublished authors, which contains 11,038 books (around 74M sentences and 1G words) of 16 different sub-genres (e.g., Romance, Historical, Adventure, etc. ).\n\nOptions:- A: GQA B: Visual Genome C: COCO-QA D: VQA-E E: COCO F: TextVQA G: BookCorpus", "role": "user" }, { "content": "[\"COCO\", \"BookCorpus\"]", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2017 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 an action progress prediction model. We evaluate our model on the UCF-10\n\nKeyphrases: action progress prediction video\n\nDataset description:\nUCF101: UCF101 dataset is an extension of UCF50 and consists of 13,320 video clips, which are classified into 101 categories. These 101 categories can be classified into 5 types (Body motion, Human-human interactions, Human-object interactions, Playing musical instruments and Sports).\nUCF Sports: The UCF Sports dataset consists of a set of actions collected from various sports which are typically featured on broadcast television channels such as the BBC and ESPN. The video sequences were obtained from a wide range of stock footage websites including BBC Motion gallery and GettyImages.\nReCAM: Tasks Our shared task has three subtasks. Subtask 1 and 2 focus on evaluating machine learning models' performance with regard to two definitions of abstractness (Spreen and Schulz, 1966; Changizi, 2008), which we call imperceptibility and nonspecificity, respectively.\nBDD100K: Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities.\n\nOptions: A: UCF101 B: UCF Sports C: ReCAM D: BDD100K", "role": "user" }, { "content": "UCF101", "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:\nCopyright violation of predators in scientific publishing - Biochemia Medica’s harmful experience and proposed solution\n\nPaper sections:\n\n<p>It is well known that predatory journals do not follow standard polices proposed by the World Association of Medical Editors (WAME). Predatory journals are usually newly established journals that spread their \"call for papers\" worldwide and charge the publication in open access journals (1). It is clear that predatory journals are those who serve for their own financial profit (2).</p><p>Biochemia Medica is an open access journal that does not charge manuscript processing or publishing. All editorial staff are continuously educated and directed to follow the highest ethical and scholarly publishing standards in all steps of the manuscript processing. They are all laboratory medicine professionals, who apart from their regular jobs, are in charge of different phases in Journal processing as volunteers. The publisher of the Journal is scientific and professional association of laboratory medicine professionals, Croatian Society of Medical Biochemistry and Laboratory medicine (CSMBLM).</p><p>In practice, each manuscript submitted to the Journal passes several phases during editorial, peer reviewing and publishing process. The steps between the first online submission and the first Editor-in-Chief's decision are schematically presented in Figure 1. Every publisher, editor, reviewer and author knows that these phases require respectable time and that that time depends on Journal's policy. The time that passes between online submission of the manuscript and the first Editor-in-Chief's decision that is made after checking for research integrity issues and peer-review is between 6 to 8 weeks. The rest of the period, prior to manuscript acceptance in the overall timeline depends on the authors. They should, in a timely manner, properly answer to reviewers' recommendations.</p><p>Workflow of the editorial and peer review process for the manuscripts submitted to Biochemia Medica.</p><p>Research integrity checkup of the manuscript consists of text similarity analysis using Crosscheck plagiarism detection service provided by CrossRef (3). Apart from that, research integrity editors also analyze the manuscript for potential salami publication (4). Furthermore, each manuscript is evaluated regarding ethical aspects of conducted and presented work (5). The final report gives the recommendation whether to proceed with editorial process, to return to the author for smaller corrections and explanation or to reject the manuscript for some of the major breaches of research integrity.</p><p>Every editor worldwide knows that the quality of the journal must be continuously improved to be in accordance with recommendations related to ethics, peer-review, online submission system, technical issues, journal web page demands and many others. Every year the editors of Biochemia Medica try to identify as many issues to be corrected or improved in order to maintain certain quality level.</p><p>In October 2018, after two-year preparation, editorial-publishing office of the journal Biochemia Medica has launched new web page because the old one could not compete with modern demands. We have fully transferred all previous, old and recent issues to the new web page. Due to new web page requirements, we changed our server provider and registrar of the domain Biochemia-medica.com. The journal remained open access and free of charge, with copyright transferred to the CSMBLM and with the open-access license under the Creative Commons Attribution 4.0 International License. Biochemia Medica's impact factor for 2017 was 3.653 and the journal was in the Q1 in the category of Medical Laboratory Technology according to Web of science Journal citation reports (JCR).</p><p>During November and December 2018, without knowledge of the editorial staff, unknown perpetrator(s) downloaded a respectable number of articles published in Biochemia Medica in portable document format (PDF) and launched an illegal web page under the same journal name with downloaded articles. They represented themselves as Journal published by CSMBLM and used the name of Editor-in-Chief to send \"call for paper\" e-mails with all other relevant information they gathered from our web page in order to get potential authors' interest. They stated that the journal covered wide area of natural science and biomedicine to attract wider range of authors from different areas. They promised fast peer-review and publication in just a few days from submission. The first suspicion was raised by Journal's Editor-in-Chief based on the e-mail received at the end of December during Christmas holidays (Figure 2). The day after, one of the Chinese authors who wanted to submit the manuscript to Biochemia Medica send an e-mail addressed to the correct e-mail address of the Editorial office with the question about the true domain of Biochemia Medica. He wanted to know which of the two, \"com\" or \"org\", was the correct Journal's web page. Furthermore, he sent us the e-mail received as invitation \"call for papers\" e-mail with listed contacts. It was obvious that the listed contacts were very similar but not identical to the true Editor-in-Chief's and Journal's contacts. As correct suffix was and still is \"com\", Senior Editor opened the web page with suffix \"org\" and revealed the existence of the web page that violated copyright of the Biochemia Medica.</p><p>An example of fraudulent e-mail sent to potential authors around the world. The content of the invitation letter was information stolen from Biochemia Medica's web page and therefore violated copyright. E-mail was also sent to the Biochemia Medica's Editor-in-Chief and several editorial-board members.</p><p>We contacted immediately our server provider and web page designer who in short time identified the server that hosted the illegal web page and its location in Turkey. They also advised us to contact the Turkish server provider and to inform them about copyright violation by the web page they had hosted. We have kindly asked them to remove illegal web page immediately. In very short time, Turkish server provider did so. We have also contacted the Department for Cyber Criminal of the Ministry of the Interior of the Republic of Croatia and National Computer Emergency Response Team (CERT), an expert group that handles computer security incidents. Furthermore, we have contacted staff from Portal of Croatian Professional and Scientific Journals (HRČAK). All of them advised us how to collect and how to save \"original e-mail headers\" received from cyber criminals and from the authors who might collaborate with them. As one of the Biochema Medica's Editorial Board member is a professor from one of the Turkish University, we have asked him to help us contact the Turkish Cyber police and Turkish national CERT. Previously listed activities resulted favorable for our Journal because the first server host and illegal web page were removed in two days. However, few hours after that we have noticed that the illegal web page became available again and was hosted by another server provider.</p><p>We have contacted again Croatian National CERT, Croatian server provider, our Turkish collaborators and HRČAK. All of them agreed that it will not be enough to contact server providers because it seemed that cyber criminals have a strategy to move from one server provider to another and that we have to contact Registrar which was localized somewhere in India. HRČAK staff helped us to compose a report on our Journal's copyright violation for acquiring financial gain. In two weeks' time from the first notification about violation, Registrar blocked the illegal web page.</p><p>During this process and later, many potential authors found our original web page and contacts surfing the internet. Some of them were confused by existence of two different Journal web pages and later they were confused when the illegal one terminated but they submitted their manuscripts through contacts available on this web page. All those manuscripts were out of scope and not in compliance with Biochemia Medica's Instructions for authors. Some of the authors sent more than one manuscript. Editor-in Chief answered to each e-mail and informed authors that unknown Cyber criminals deceived them. Some of the authors sent us e-mails received from Cyber criminals including \"e-mail headers\" as well as the acceptance decision and invoices (Figure 3). Prices were different with the opportunity to arrange a better price deal depending on the author.</p><p>An example of acceptance letter that authors have received few days after manuscript submission. It also included \"the invoice\". Received by courtesy of anonymous author.</p><p>Although this was a very harmful experience, we have learned a lot from it and we would like to share this with scientific journals' community. Therefore, we present a short workflow on how to manage situations like this if it will be necessary in the future (Table 1 and Table 2).</p>", "role": "user" }, { "content": "Biochemia Medica is an open access journal that does not charge manuscript processing or publishing. All editorial staff are continuously educated and directed to follow the highest ethical and scholarly publishing standards in all steps of the manuscript processing. They are all laboratory medicine professionals, who apart from their regular jobs, are in charge of different phases in Journal processing as volunteers. The publisher of the Journal is scientific and professional association of laboratory medicine professionals, Croatian Society of Medical Biochemistry and Laboratory medicine (CSMBLM). During November and December 2018, without knowledge of the editorial staff, unknown perpetrator(s) downloaded a respectable number of articles published in Biochemia Medica as PDF and launched an illegal web page under the same journal name with downloaded articles. Although this was a very harmful experience, we have learned a lot from it and we would like to share this with scientific journals’ community. Therefore, we would like to share this harmful experience, and to present a short workflow on how to manage situations like this if it will be necessary for any scientific journal in the future.", "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\nIn vitro inhibitory effects of non-steroidal anti-inflammatory drugs on 4-methylumbelliferone glucuronidation in recombinant human UDP-glucuronosyltransferase 1A9--potent inhibition by niflumic acid. The inhibitory potencies of non-steroidal anti-inflammatory drugs (NSAIDs) on UDP-glucuronosyltransferase (UGT) 1A9 activity were investigated in recombinant human UGT1A9 using 4-methylumbelliferone (4-MU) as a substrate for glucuronidation. 4-MU glucuronidation (4-MUG) showed Michaelis-Menten kinetics with a Km value of 6.7 microM. The inhibitory effects of the following seven NSAIDs were investigated: acetaminophen, diclofenac, diflunisal, indomethacin, ketoprofen, naproxen and niflumic acid. Niflumic acid had the most potent inhibitory effect on 4-MUG with an IC50 value of 0.0341 microM. The IC50 values of diflunisal, diclofenac and indomethacin were 1.31, 24.2, and 34.1 microM, respectively, while acetaminophen, ketoprofen and naproxen showed less potent inhibition. Niflumic acid, diflunisal, diclofenac and indomethacin inhibited 4-MUG competitively with Ki values of 0.0275, 0.710, 53.3 and 69.9 microM, respectively, being similar to each IC50 value. In conclusion, of the seven NSAIDs investigated, niflumic acid was the most potent inhibitor of recombinant UGT1A9 via 4-MUG in a competitive manner.", "role": "user" }, { "content": "[[\"niflumic acid\", \"INHIBITOR\", \"human UDP-glucuronosyltransferase 1A9\"], [\"niflumic acid\", \"INHIBITOR\", \"UGT1A9\"]]", "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\nNovel High-grade Endometrial Stromal Sarcoma: A Morphologic Mimicker of Myxoid Leiomyosarcoma Endometrial stromal sarcomas (ESS) are often underpinned by recurrent chromosomal translocations resulting in the fusion of genes involved in epigenetic regulation. To date, only YWHAE-NUTM2 rearrangements are associated with distinctive high-grade morphology and aggressive clinical behavior. We identified 3 ESS morphologically mimicking myxoid leiomyosarcoma of the uterus and sought to describe their unique histopathologic features and identify genetic alterations using next-generation sequencing. All cases displayed predominantly spindled cells associated with abundant myxoid stroma and brisk mitotic activity. Tumors involved the endometrium and demonstrated tongue-like myometrial infiltration. All 3 were associated with an aggressive clinical course, including multisite bony metastases in 1 patient, progressive peritoneal disease after chemotherapy in another, and metastases to the lung and skin in the last patient. All 3 ESS were found to harbor ZC3H7B - BCOR gene fusions by targeted sequencing and fluorescence in situ hybridization. On the basis of the review of these cases, we find that ESS with ZC3H7B - BCOR fusion constitutes a novel type of high-grade ESS and shares significant morphologic overlap with myxoid leiomyosarcoma.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"endometrium\", \"stroma\", \"lung\", \"ZC3H7B\", \"BCOR\", \"spindled cells\", \"uterus\", \"YWHAE-NUTM2\"], \"Bacterium\": [], \"BiologicFunction\": [\"metastases\", \"epigenetic regulation\", \"genetic alterations\", \"Endometrial stromal sarcomas\", \"high-grade ESS\", \"High-grade Endometrial Stromal Sarcoma\", \"chromosomal translocations\", \"Myxoid Leiomyosarcoma\", \"myxoid leiomyosarcoma\", \"bony metastases\", \"peritoneal disease\", \"rearrangements\", \"ESS\", \"myometrial infiltration\", \"Tumors\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [\"skin\"], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"morphologic overlap\", \"morphologically mimicking\", \"aggressive clinical course\", \"Morphologic Mimicker\", \"aggressive clinical behavior\", \"mitotic activity\"], \"Food\": [], \"HealthCareActivity\": [\"targeted sequencing\", \"chemotherapy\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"fusion of genes\", \"gene fusions\", \"fluorescence in situ hybridization\", \"fusion\", \"next-generation sequencing\"], \"SpatialConcept\": [\"myometrial\"], \"Virus\": []}", "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 consider tackling a single-agent RL problem by distributing it to $n$ learners.\nThese learners, called advisors, endeavour to solve the problem from a different focus.\nTheir advice, taking the form of action values, is then communicated to an aggregator, which is in control of the system.\nWe show that the local planning method for the advisors is critical and that none of the ones found in the literature is flawless: the \\textit{egocentric} planning overestimates values of states where the other advisors disagree, and the \\textit{agnostic} planning is inefficient around danger zones.\nWe introduce a novel approach called \\textit{empathic} and discuss its theoretical aspects.\nWe empirically examine and validate our theoretical findings on a fruit collection task.\nWhen a person faces a complex and important problem, his individual problem solving abilities might not suffice.\nHe has to actively seek for advice around him: he might consult his relatives, browse different sources on the internet, and/or hire one or several people that are specialised in some aspects of the problem.\nHe then aggregates the technical, ethical and emotional advice in order to build an informed plan and to hopefully make the best possible decision.\nA large number of papers tackle the decomposition of a single Reinforcement Learning task (RL, Sutton & Barto, 1998) into several simpler ones.\nThey generally follow a method where agents are trained independently and generally greedily to their local optimality, and are aggregated into a global policy by voting or averaging.\nRecent works BID12 BID30 prove their ability to solve problems that are intractable otherwise.\nSection 2 provides a survey of approaches and algorithms in this field.Formalised in Section 3, the Multi-Advisor RL (MAd-RL) partitions a single-agent RL into a MultiAgent RL problem BID22 , under the widespread divide & conquer paradigm.\nUnlike Hierarchical RL BID2 BID19 BID4 , this approach gives them the role of advisor: providing an aggregator with the local Q-values for all actions.\nThe advisors are said to have a focus: reward function, state space, learning technique, etc.\nThe MAd-RL approach allows therefore to tackle the RL task from different focuses.When a person is consulted for an advice by a enquirer, he may answer egocentrically: as if he was in charge of next actions, agnostically: anticipating any future actions equally, or empathically: by considering the next actions of the enquirer.\nThe same approaches are modelled in the local advisors' planning methods.\nSection 4 shows that the egocentric planning presents the severe theoretical shortcoming of inverting a max into a max in the global Bellman equation.\nIt leads to an overestimation of the values of states where the advisors disagree, and creates an attractor phenomenon, causing the system to remain static without any tie-breaking possibilities.\nIt is shown on a navigation task that attractors can be avoided by lowering the discount factor γ under a given value.\nThe agnostic planning BID30 has the drawback to be inefficient in dangerous environments, because it gets easily afraid of the controller performing a bad sequence of actions.\nFinally, we introduce our novel empathic planning and show that it converges to the global optimal Bellman equation when all advisors are training on the full state space.van BID29 demonstrate on a fruit collection task that a distributed architecture significantly speeds up learning and converges to a better solution than non distributed baselines.\nSection 5.2 extends those results and empirically validates our theoretical analysis: the egocentric planning gets stuck in attractors with high γ values; with low γ values, it gets high scores but is also very unstable as soon as some noise is introduced; the agnostic planning fails at efficiently gathering the fruits near the ghosts; despite lack of convergence guarantees with partial information in advisors' state space, our novel empathic planning also achieves high scores while being robust to noise.\nThis article presented MAd-RL, a common ground for the many recent and successful works decomposing a single-agent RL problem into simpler problems tackled by independent learners.\nIt focuses more specifically on the local planning performed by the advisors.\nThree of them -two found in the literature and one novel -are discussed, analysed and empirically compared: egocentric, agnostic, and empathic.\nThe lessons to be learnt from the article are the following ones.The egocentric planning has convergence guarantees but overestimates the values of states where the advisors disagree.\nAs a consequence, it suffers from attractors: states where the no-op action is preferred to actions making progress on a subset of subtasks.\nSome domains, such as resource scheduling, are identified as attractor-free, and some other domains, such as navigation, are set conditions on γ to guarantee the absence of attractor.\nIt is necessary to recall that an attractor-free setting means that the system will continue making progress towards goals as long as there are any opportunity to do so, not that the egocentric MAd-RL system will converge to the optimal solution.The agnostic planning also has convergence guarantees, and the local agnostic planning is equivalent to the global agnostic planning.\nHowever, it may converge to bad solutions.\nFor instance, in dangerous environments, it considers all actions equally likely, it favours staying away from situation where a random sequence of actions has a significant chance of ending bad: crossing a bridge would be avoided.\nStill, the agnostic planning simplicity enables the use of general value functions BID28 BID30 .The\nempathic planning optimises the system according to the global Bellman optimality equation, but without any guarantee of convergence, if the advisor state space is smaller than the global state.In our experiments, we never encountered a case where the convergence was not obtained, and on the Pac-Boy domain, it robustly learns a near optimal policy after only 10 epochs. It\ncan also be safely applied to Ensemble RL tasks where all learners are given the full state space.", "role": "user" }, { "content": "We consider tackling a single-agent RL problem by distributing it to $n$ learners.", "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: CONCLUSIONS: HAdV-55 may cause severe ARDS in immunocompetent young men. Persistent high fever, dyspnea and rapid progression to respiratory failure within 2 weeks, together with bilateral consolidations and infiltrates , are the most frequent clinical manifestations of HAdV-55-induced severe ARDS. Viral load monitoring may help predict disease severity and outcome. The NPPV and IMV failure rates were very high, but ECMO may still be the respiratory support therapy of choice. TRIAL REGISTRATION: Clinicaltrials.gov NCT01585922. Registered 20 April 2012\n\nText: Human adenoviruses (HAdVs) are notorious pathogens in people with compromised immune function and a frequent cause of outbreaks of acute respiratory disease among young children. Life-threatening adenoviral pneumonia has previously been documented among military trainees, patients with AIDS and transplant recipients [1] [2] [3] [4] [5] . Human adenovirus type 55 (HAdV-55), which is emerging as a highly virulent pathogen for acute fatal adenoviral pneumonia among immunocompetent adults in China, has gained increasing attention [6] . HAdV-55 is a newly identified, emergent acute respiratory disease pathogen causing two recent outbreaks in China in 2006 [7] and in Singapore in 2005 [8] . In 2011, this pathogen apparently re-emerged in Beijing, China, causing several cases of severe community-acquired pneumonia [9] . This pathogen was fully characterized by whole-genome sequencing [10] . Comparative studies showed that the ability of HAdV to cause severe disease may relate to the serotypes of HAdVs. Severe adenoviral pneumonia induced by HAdV-55 has been reported to be more closely related to severe cases compared to other serotypes (HAdV-3, HAdV-7 and HAdV-14) [6] . Current knowledge of HAdV-55-induced severe acute respiratory distress syndrome (ARDS) requiring invasive mechanical ventilation and/or extracorporeal membrane oxygenation (ECMO) support in immunocompetent adults is derived from single case reports or relatively small, single-center series. As a result, little information is available on HAdV-55 pneumonia complicated with severe ARDS, the frequency of which is expected to increase in the coming years. Here we describe the clinical features and outcomes of five prospective cases of HAdV-55 pneumonia complicated with severe ARDS in immunocompetent adults in our ICU. Beginning in May 2012, a randomized trial of noninvasive positive pressure ventilation (NPPV) in ARDS patients was carried out in our center (ClinicalTrials.gov ID: NCT01585922). From May 2012 to April 2014, all adult patients with ARDS caused by pneumonia who were admitted to the respiratory ICU of Beijing Chao-Yang Hospital were prospectively enrolled. Severe ARDS was diagnosed according to the Berlin definition: (1) developing within 1 week of a known clinical insult or new or worsening respiratory symptoms; (2) bilateral opacities not fully explained by effusions, lobar and/or lung collapse, or nodules; (3) respiratory failure not fully explained by cardiac failure or fluid overload; (4) partial oxygen pressure/ fraction of inspired oxygen (PaO 2 /FiO 2 ) ≤100 mmHg with positive end-expiratory pressure (PEEP) ≥5 cmH 2 O; and (5) a chest radiograph with three or four quadrants with opacities. Patients with HAdV-55 infection and severe ARDS who failed conventional NPPV and invasive mechanical ventilation (IMV) were included in the analysis. This study was approved by the Institutional Review Board of Beijing Chao-Yang Hospital (LLKYPJ2012031). Data were analyzed anonymously. Each patient gave written informed consent for their data to be used for research and publication. Clinical information collected by investigators with a standardized data form included the following: demographic characteristics (age and sex), comorbidities, clinical symptoms (fever, cough, sputum, dyspnea, chest pain, rash, nausea, vomiting, abdominal pain, diarrhea and headache), signs (body temperature, heart rate, respiratory frequency, blood pressure and crackles in the lungs), laboratory tests (whole-blood cell count and blood chemistry) and microbiological findings and images of the lung (chest X-ray (CXR) and computed tomography). Concomitant medications, respiratory support, complications and outcomes were also recorded. Patients' specimens, including sputum, whole blood and serum samples, were collected upon admission and during hospitalization. Microbiological tests were performed at the Department of Infectious Disease and Clinical Microbiology in our center, and the detection methods used were described in our previous report [6] . Common viruses causing respiratory illness were screened using a kit with 15 different viral assays. Serum samples were used for Mycoplasma pneumoniae, Chlamydia pneumoniae and Legionella pneumophila antibodies. All patients had their HAdV-55 infection confirmed by RT-PCR assay. Partial sequences of the hexon gene were analyzed to type the phylogeny of HAdV-55 strains. The adenoviral load was also performed on both respiratory specimens and blood by multiplex RT-PCR assay. Viral pneumonia was diagnosed based on the presence of HAdV detected in sputum or throat swab samples by molecular methods. Continuous variables were summarized as mean ± standard deviation (SD) or median (interquartile range). During the study period, a total of eight patients diagnosed with HAdV infection and respiratory failure were admitted to our ICU, and seven of them received a diagnosis of ARDS. Five consecutive patients with severe ARDS with confirmed HAdV-55 infection were admitted to our ICU between April and July 2013. They were included in the analysis. The other two patients had mild ARDS and were infected with other types of HAdVs. All five patients were immunocompetent young men with a median age of 32 years (range, 28 to 40 years). All of the patients shared a B blood type and came from the same city: Baoding city, Hebei province, northern China. All patients had no exposure to farm animals, corn or hay. Patient 3 had tuberculosis pleuritis and received antituberculosis therapy at ICU admission. His blood tests, including the T-SPOT tuberculosis assay (Oxford Immunotec, Marlborough, MA, USA) and antibody of Mycobacterium tuberculosis, were negative. Flulike symptoms, such as fever, cough and little sputum, were commonly observed at the onset of illness. All patients presented with a high fever, with a mean body temperature of 39.5°C (range, 39.0°C to 40.0°C), which persisted for 8 days (range, 6 to 11 days). Productive cough was observed in two patients. Dull substernal chest pain and rash were also observed in two patients. All patients had dyspnea. The mean time from onset to dyspnea was 5 days (range, 1 to 10 days). After the onset of dyspnea, patients usually progressed to respiratory failure or hypoxemia. The mean time from onset to ICU admission was 9.6 days (range, 8 to 11 days) ( Table 1) . All patients had tachypnea when admitted to the ICU, with a mean rate of 43 breaths per minute (range = 38 to 52). Arterial blood gas analysis at ICU admission revealed profound hypoxia, with a mean PaO 2 /FiO 2 of 58.1 (range = 49 to 62.5). White blood cell counts were low or in the normal range. All patients had elevated serum aspartate aminotransferase (AST), lactate dehydrogenase (LDH) and hydroxybutyrate dehydrogenase (HBDH) ( Table 1) . At admission, all patients' levels of immunoglobulin (serum immunoglobulins G and M) and components C3 and C4 were in the normal range. Four patients had lower than normal T-cell subset counts (Table 2) . CXRs revealed multiple bilateral lobar or segment consolidation in the lungs of all five patients, and radiographic lesions progressed rapidly after ICU admission ( Figure 1 ). Three patients were examined by highresolution computed tomography (HRCT). Unilateral or bilateral consolidations and infiltrates were found on HRCT scans of all three of these patients. Consolidations within a single lobe or several lobes with a clear border and air bronchogram were the most common findings on HRCT scans. Nodules, patches, pleural effusion, abscess and a cavity were also seen visualized by HRCT (Figure 2 ). The mean duration from onset to a single-lobe consolidation on CXRs was 2 days (range = 1 to 5 days). The mean duration from the first positive CXR to bilaterally multilobar lung infiltrates was 4.8 days (range = 4 to 7 days). All patients had HAdV-55 viremia. In four of the five patients, it was first detected in endotracheal aspirate (ETA) samples. The time between initial ETA sample collection of adenoviruses and positive results for HAdV-55 nucleic acid in the blood was 1 to 10 days (Table 3) . Virus DNA copies in ETAs were determined for all patients during their ICU stay. The viral load was higher than 1 × 10 8 copies in three patients and 1 × 10 4 in one patient. The viral load became negative in the only patient who survived. In the four patients who did not survive, DNA copies did not decrease, even with antiviral therapy (Figure 3 ). Oxygenation was not maintained with conventional NPPV or IMV support in any of the patients. The mean duration until NPPV failure was 30.8 hours (range = 22 to 48 hours), and the mean time until IMV failure was 6.2 days (range 2 = to 13 days) ( Table 1) . Four patients received venovenous ECMO to maintain oxygen saturation, and one patient refused ECMO support and received high-frequency oscillatory ventilation instead. Table 4 gives the oxygenation data of patients before and after venovenous ECMO support. All patients received antiviral therapy, including acyclovir (10 mg/kg, every 8 hours, intravenous drip), ganciclovir (5 mg/kg, every 12 hours, intravenous drip) and ribavirin (250 mg, twice daily, intravenous drip). Considering that bacterial coinfection may combine with a severe viral infection, broad-spectrum intravenous antibiotics were given to all patients. Tests for bacterial pathogens were negative for only one patient (Table 3) . Four (80%) of the five patients died. Among the four patients receiving venovenous ECMO, only one patient survived. The other four patients died due to ARDS, Aspergillus fumigatus coinfection, septic shock and catheter-related bloodstream infection due to Acinetobacter baumannii, respectively. To the best of our knowledge, this is the first cohort observational study on the clinical characteristics of patients with severe ARDS caused by emergent HAdV-55 infection and also the first on the evaluation of a viral load test for monitoring the reaction to therapy and for prediction of patient outcome. The following are the main findings of this study. (1) HAdV-55 may cause severe ARDS in immunocompetent young men with blood type B. All of our patients were from the same city of Hebei province, northern China. (2) at the same time, are the most frequent clinical manifestations of severe HAdV-55induced ARDS. (3) Viral load monitoring may help predict disease severity and patient outcome. (4) The NPPV and IMV failure rates were very high, and ECMO may be the last support method for this group of patients. (5) HAdV-55-induced severe ARDS has a very high mortality rate (80%) despite appropriate respiratory support. Sporadic severe adenoviral infection in healthy adults has historically been described for serotype 4 [11] , serotype 7 [4, 12] and, more recently, serotype 14 in the general population and in military trainees [13, 14] . HAdV-55 was first completely characterized in Shaanxi, China [7] and then reemerged in Hebei, a province close to Beijing, where it caused several cases of acute respiratory disease [9] . It was presumed that HAdV-55 was a recombinant form of the B2 species of HAdV-14 and HAdV-11 [7, 15] due to its sharing a hexon gene with the HAdV-11 and HAdV-14 chassis [16] . The results of our study show that HAdV-55, as an emerging pathogen among immunocompetent adults, may cause severe ARDS. The prevalence of severe fatal adenoviral pneumonia induced by HAdV-55 in our study is somewhat similar to that described by Cao and colleagues [6] . All cases of reported HAdV-55 in our study were from the same city: Baoding, Hebei province, northern China. They occurred between April and July 2013, just partly overlapping or following the influenza epidemic. The patients with severe disease also came from the same region and were treated during a similar time period, which suggests that HAdV-55 may be an important viral pathogen derived from this region. Our study results suggest that the following may be clinical features of ARDS caused by HAdV-55: persistent high fever, rapid progression of dyspnea, need for mechanical ventilation support, elevated AST level and rapid progression from unilateral infiltrates to bilateral consolidations. These clinical features are highly similar to those of ARDS caused by other types of HAdV described in previous reports [6, 9] . Recent studies have shown that the immune system plays a crucial role in the clearance of HAdV viremia and survival of the host [17] . Chen et al. reported that, in the acute phase of HAdV-55 infection, patients with severe disease may have high levels of dendritic cells and Th17 cells [18] . In our study, the only patient who recovered from severe infection had higher T-cell counts. Three of the five patients had relatively low T-cell counts when admitted. Our results suggest that these three patients may have been relatively immunocompromised and that a lower T-cell count may be a risk factor for HAdV-55 infection in young adults. HAdV-55 DNA was previously reported in 41.2% of patients with severe infection [18] . In our study, HAdV-55 DNA was detected and monitored in all patients with severe ARDS. The initial, and trend of, viral load that presented as HAdV-55 DNA copies in the respiratory tract samples and blood may suggest the severity of infection and may predict both the reaction to therapy and patient outcome.\n\nQuestion: What are the most frequent clinical manifestations of human adenovirus type 55 (HAdV-55) induced ARDS?", "role": "user" }, { "content": "Persistent high fever, dyspnea and rapid progression to respiratory failure within 2 weeks, together with bilateral consolidations and infiltrates", "role": "assistant" } ]

[ { "content": "You will be given an abstract from a computer science research paper. Given the abstract, your task is to extract all unique relationships between entities of the following, and ONLY the following, types:\n\n- \"USED-FOR\": For instance, \"Our method models user proficiency\" -> [\"method\", \"user proficiency\", \"USED-FOR\"].\n- \"EVALUATE-FOR\": For instance, \"We evaluate our method using F1-measure\" -> [\"F1-measure\", \"method\", \"EVALUATE-FOR\"].\n- \"FEATURE-OF\": For instance, \"prior knowledge of the model\" -> [\"prior knowledge\", \"model\", \"FEATURE-OF\"].\n- \"HYPONYM-OF\": For instance, \"TUIT is a software library\" -> [\"TUIT\", \"software library\", \"HYPONYM-OF\"].\n- \"PART-OF\": For instance, \"We incorporate NLU module into the system\" -> [\"NLU module\", \"system\", \"PART-OF\"].\n- \"COMPARE\": For instance, \"Unlike the quantitative prior, the qualitative prior is often ignored\" -> [\"quantitative prior\", \"qualitative prior\", \"COMPARE\"].\n- \"CONJUNCTION\": For instance, \"obtained from human expert or knowledge base\" -> [\"human expert\", \"knowledge base\", \"CONJUNCTION\"].\n\nFormat your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<Entity_B>\", \"<RELATION_A_B>\"]. An example output might look like:\n\n[[\"neural networks\", \"classification\", \"USED-FOR\"], [\"neuron\", \"neural network\", \"PART-OF\"]].\n\nIf no relations are found, please return an empty JSON array \"[]\".\n\nAbstract:\n\nThe PRC Adaptive Knowledge-based Text Understanding System (PAKTUS) has been under development as an Independent Research and Development project at PRC since 1984. The objective is a generic system of tools, including a core English lexicon, grammar, and concept representations, for building natural language processing (NLP) systems for text understanding. Systems built with PAKTUS are intended to generate input to knowledge based systems ordata base systems. Input to the NLP system is typically derived from an existing electronic message stream, such as a news wire. PAKTUS supports the adaptation of the generic core to a variety of domains: JINTACCS messages, RAINFORM messages, news reports about a specific type of event, such as financial transfers or terrorist acts, etc., by acquiring sublanguage and domain-specific grammar, words, conceptual mappings, and discourse patterns. The long-term goal is a system that can support the processing of relatively long discourses in domains that are fairly broad with a high rate of success.", "role": "user" }, { "content": "[[\"financial transfers\", \"terrorist acts\", \"CONJUNCTION\"], [\"event\", \"news reports\", \"FEATURE-OF\"], [\"concept representations\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"PART-OF\"], [\"JINTACCS messages\", \"RAINFORM messages\", \"CONJUNCTION\"], [\"conceptual mappings\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"USED-FOR\"], [\"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"news reports\", \"USED-FOR\"], [\"words\", \"conceptual mappings\", \"CONJUNCTION\"], [\"RAINFORM messages\", \"news reports\", \"CONJUNCTION\"], [\"natural language processing (NLP) systems\", \"text understanding\", \"USED-FOR\"], [\"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"knowledge based systems\", \"USED-FOR\"], [\"words\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"USED-FOR\"], [\"conceptual mappings\", \"discourse patterns\", \"CONJUNCTION\"], [\"sublanguage and domain-specific grammar\", \"words\", \"CONJUNCTION\"], [\"sublanguage and domain-specific grammar\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"USED-FOR\"], [\"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"JINTACCS messages\", \"USED-FOR\"], [\"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"natural language processing (NLP) systems\", \"USED-FOR\"], [\"grammar\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"PART-OF\"], [\"core English lexicon\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"PART-OF\"], [\"news wire\", \"electronic message stream\", \"HYPONYM-OF\"], [\"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"RAINFORM messages\", \"USED-FOR\"], [\"financial transfers\", \"event\", \"HYPONYM-OF\"], [\"electronic message stream\", \"natural language processing (NLP) systems\", \"USED-FOR\"], [\"discourse patterns\", \"PRC Adaptive Knowledge-based Text Understanding System (PAKTUS)\", \"USED-FOR\"], [\"terrorist acts\", \"event\", \"HYPONYM-OF\"]]", "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\nLocally administered prostaglandin E2 prevents aeroallergen-induced airway sensitization in mice through immunomodulatory mechanisms. Prostaglandin E2 attenuates airway pathology in asthmatic patients and exerts a protective effect in antigen-sensitized mice when administered systemically. We aimed to establish the consequences of intranasal PGE2 administration on airway reactivity to aeroallergens in mice and reveal the underlying immunoinflammatory mechanisms. PGE2 was administered either daily during a 10-day exposure to house dust mite (HDM) extracts or for limited intervals. Airway hyperreactivity was measured by whole-body and invasive plethysmography. The phenotypes of lung immune cells and cytokine production were analysed by flow cytometry and ELISA, respectively. Airway hyperreactivity was sustainably reduced only when PGE2 administration was restricted to the initial 5 days of exposure to HDM. Lung inflammation, IL-4 production, and airway mast cell activity were also prevented under this early short-term treatment with PGE2. Interestingly, a Th2 response was already committed on day 5 of exposure to HDM. This was paralleled by GM-CSF and osteopontin upregulation and a decreased number of plasmacytoid dendritic and T regulatory cells, as well as a trend towards reduced IL-10 expression. Local PGE2 administration prevented the increase of airway IL-13 and osteopontin and kept lung plasmacytoid dendritic cell counts close to baseline. GM-CSF and Tregs were unaffected by the treatment. These findings suggest that the protection provided by PGE2 is a result of the modulation of early lung immunomodulatory mechanisms, and possibly a shift in the balance of dendritic cells towards a tolerogenic profile.", "role": "user" }, { "content": "[[\"PGE2\", \"INHIBITOR\", \"osteopontin\"], [\"PGE2\", \"INHIBITOR\", \"IL-13\"], [\"PGE2\", \"INHIBITOR\", \"IL-4\"]]", "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: Transcriptomic correlates of neuron electrophysiological diversity\nArticle:\nAbstract:\nHow neuronal diversity emerges from complex patterns of gene expression remains poorly understood. Here we present an approach to understand electrophysiological diversity through gene expression by integrating pooled- and single-cell transcriptomics with intracellular electrophysiology. Using neuroinformatics methods, we compiled a brain-wide dataset of 34 neuron types with paired gene expression and intrinsic electrophysiological features from publically accessible sources, the largest such collection to date. We identified 420 genes whose expression levels significantly correlated with variability in one or more of 11 physiological parameters. We next trained statistical models to infer cellular features from multivariate gene expression patterns. Such models were predictive of gene-electrophysiological relationships in an independent collection of 12 visual cortex cell types from the Allen Institute, suggesting that these correlations might reflect general principles relating expression patterns to phenotypic diversity across very different cell types. Many associations reported here have the potential to provide new insights into how neurons generate functional diversity, and correlations of ion channel genes like Gabrd and Scn1a( Nav1. 1) with resting potential and spiking frequency are consistent with known causal mechanisms. Our work highlights the promise and inherent challenges in using cell type-specific transcriptomics to understand the mechanistic origins of neuronal diversity.\nIntroduction:\nA major goal of neuroscience has been to understand the mechanistic origins of neuronal electrophysiological phenotypes. Such electrical features help define the computational functions of each neuron[1, 2], and further, specific electrophysiological deficits contribute to brain disorders such as epilepsy, ataxia, and autism[3–5]. The molecular basis of neuron electrophysiology is complex. There are over 200 mammalian ion channel and transporter genes whose products influence a neuron’s electrophysiological phenotype[6–9]. Numerous additional genes regulate channel functional expression through initiating gene transcription and alternative splicing, post-translational modifications, and trafficking channels to and from the membrane surface[10–12]. Even morphological features contribute to cellular electrophysiology[13]. Recent genetic studies in human epileptic and neuropsychiatric patients provide convergent evidence, as mutations in many genes reflecting multiple functional pathways are associated with these disorders[4, 14–16]. In light of this complexity, the gold standard employed by neurophysiologists is to use gene knockouts or pharmacology to assay how electrophysiological function changes following protein disruption[7, 8]. However, these single-gene focused methods are relatively low-throughput and many potentially relevant genes have yet to be studied for their electrophysiological function. Cell type-specific transcriptomics, enabling genome-wide assay of quantitative mRNA expression levels, provides a lucrative avenue for discovering novel genes that might contribute to specific aspects of cellular physiology[17, 18]. Correlation-based approaches have been proposed that pair single-cell expression profiling with patch-clamp electrophysiology[19–21]. These approaches leverage the biological variability observed across a collection of cells to identify gene expression patterns correlated with cellular phenotypic differences. Generalizing from these studies has proven challenging however, since they typically have been focused on a limited number of cell types. Similarly, and perhaps more critically, there are typically hundreds to thousands of genes correlated with electrophysiological variability[22]. Thus it has been difficult from this data to pin down how individual genes might shape specific cellular phenotypes. Though making use of larger and more diverse collections of cell types could provide a potential solution, collecting such reference data is immensely resource- and labor-intensive. Here, we present an approach for correlating cell type-specific transcriptomics with neuronal electrophysiological features. We leverage neuroinformatics methods to build a novel reference dataset on brain-wide neuronal gene expression and intrinsic electrophysiological feature diversity. The compiled dataset reflects the neuronal characterization efforts of hundreds of investigators as well as our efforts to compile and normalize these data for unified mega-analysis[23–25]. From this data, we identified hundreds of genes whose expression levels significantly correlate with specific electrophysiological features( e. g., resting potential or maximum spiking frequency). Illustrating the generalizability of these results, we could use these correlations to predict the ephys parameters of an independent neocortex-specific dataset from the Allen Institute. In addition, many of these genes have been further found to directly regulate neuronal electrophysiology, suggesting that some of the correlations reported here likely reflect novel causal relationships. Our findings present a major step for understanding how a multitude of genes contribute to cell type-specific phenotypic diversity.\nDiscussion:\nThe results presented here are restricted to a limited range of situations. First, we can only identify genes where mRNA, as measured in dissociated cells[59], is an adequate readout of a gene’s functional activity at the protein level. Future datasets employing RNA-seq, proteomics, or techniques to capture non-somatic mRNA will likely be able to identify more genes where alternative splicing and post-translational modifications are essential for understanding gene function[10–12]. Second, the univariate approach that forms the majority of our study assumes a gene’s contribution to electrophysiology is similar and monotonic across cell types. This single-gene focused analysis likely misses genes that contribute to complex ephys features in ways that are biologically degenerate and are highly non-linear or combinatorial[28, 29]. For example, Kv3-family ion channels, including Kcnc1/Kv3. 1, have been implicated in helping fast-spiking cells maintain narrow spike widths[32, 60], but we did not identify Kcnc1 as correlated with AP width in our analysis. Further utilizing multivariate approaches( like shown in Fig 3) and incorporating other information sources, such as how proteins interact to form functional complexes, might reveal additional signals and help mitigate spurious correlations. However, pursuing such approaches will likely necessitate larger datasets than are currently available. Third, the focus of our analysis is to explain how ephys differences across cell types emerge through gene expression. It remains an open question whether the same genes driving large across cell type differences would also be the same genes that are defining subtler within cell type differences, like amongst olfactory bulb mitral cells or CA1 pyramidal cells[1, 2, 58]. As the patch-seq methodology, enabling transcriptomic and ephys characterization from the same single-cell[19, 20], is further developed and applied, we eagerly anticipate testing these hypotheses. However, small changes in expression of individual genes, as expected within a single cell type, are difficult to reliably detect using current technologies, in part, due to relatively limited sample sizes and technical challenges like “dropouts”[18]. Indeed, while these patch-seq studies have demonstrated their utility in classifying individual cells into types[19, 20], how variance in expression of specific genes gives rise to within cell type ephys differences remains largely unaddressed. Fourth, ephys property correlations and gene co-expression limits the potential specificity of any causal prediction made here. For example, some pairs of ephys properties, like AHPamp and Rin, are correlated but probably do not share common biophysical underpinnings( S3B Fig). Because of this common correlation, genes significantly associated with one ephys feature are more likely to be also associated with other ephys features, potentially spuriously. Similarly, many pairs of genes show correlated expression across samples( i. e., gene co-expression). Gene co-expression often reflects biologically meaningful signals, such as co-regulation by common transcription factors or shared membership in biological pathways and cellular compartments[61]. However, co-expression makes interpreting individual gene-ephys associations difficult and likely contributes to why we found many more genes for some ephys properties than we would naively expect, such as Vrest and AHPamp. Future analysis approaches that explicitly consider co-expression might prove useful[62]. Lastly, the heterogeneous nature of the compiled NeuroExpresso/NeuroElectro dataset[23, 25, 59] might limit our power to see possible biologically relevant signals and could explain our failure to find genes for some ephys features. For example, because data in NeuroElectro are compiled from different studies collected in the absence of standards for how some ephys properties are defined[24, 63], this likely limits our downstream attempts at normalization. Similarly, the cell types reflected in the aggregated dataset are likely composed of multiple transcriptomic or morphologically-defined subtypes[27, 64]. However, the overall consistency with the AIBS Cell Types dataset, where data were collected using standardized conditions and protocols, suggests that the results shown here are not entirely the result of technical artefacts due to data compilation. Our findings suggest a number of directions for future study. Can specific gene-ephys relationships be used as biomarkers to detect electrophysiological changes in a disease or treatment context? For example, if Scn1a/Nav1. 1 is upregulated in a cell type, does that serve as a reliable indicator of hyper-excitability? Given the relative ease and growing popularity of single-cell transcriptomics on dissociated cells and nuclei[18, 27], could the multivariate gene expression-based statistical models we developed be useful in imputing ephys phenotypes from transcriptomic signatures alone? Lastly, are the gene-ephys correlations reported here predictive of cell-to-cell variability reported within the same cell type? In summary, our results suggest that large-scale transcriptomics can prove useful in helping elucidate the biophysical basis for the rich electrophysiological diversity seen amongst neuron types throughout the brain.", "role": "user" }, { "content": "Brain cell types have different electrical features , determined by the genes that each cell expresses . By combining data from hundreds of articles studying individual cell types in isolation , we developed a dataset that combines neuron gene expression patterns with their electrical characteristics . We asked if patterns of gene expression could predict a neuron’s electrical features; for example , if a neuron that expresses more of a sodium channel also tends to fire action potentials more frequently . We found hundreds of such statistical correlations that also replicated across brain cell types and regions . These relationships provide a starting point for understanding how alterations in the gene expression result in alterations in electrical functioning of neurons and brain circuits .", "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: This amplifies the basal type 2 inflammation resulting in a greater release of IL-4, IL-5, IL-13, RANTES and eotaxin and a further increase in eosinophilia, a key pathological driver of asthma and CRSwNP (Wark and Gibson, 2006; Singh et al., 2010; Chung et al., 2015; Dunican and Fahy, 2015) . Increased eosinophilia, in turn, worsens the classical symptoms of disease and may further lead to life-threatening conditions due to breathing difficulties. On the other hand, patients with COPD and patients with CRS without nasal polyp (CRSsNP) are more neutrophilic in nature due to the expression of neutrophil chemoattractants such as CXCL9, CXCL10, and CXCL11 (Cukic et al., 2012; Brightling and Greening, 2019) . The pathology of these airway diseases is characterized by airway remodeling due to the presence of remodeling factors such as matrix metalloproteinases (MMPs) released from infiltrating neutrophils (Linden et al., 2019) . Viral infections in such conditions will then cause increase neutrophilic activation; worsening the symptoms and airway remodeling in the airway thereby exacerbating COPD, CRSsNP and even CRSwNP in certain cases (Wang et al., 2009; Tacon et al., 2010; Linden et al., 2019) . An epithelial-centric alarmin pathway around IL-25, IL-33 and thymic stromal lymphopoietin (TSLP), and their interaction with group 2 innate lymphoid cells (ILC2) has also recently been identified (Nagarkar et al., 2012; Hong et al., 2018; Allinne et al., 2019) . IL-25, IL-33 and TSLP are type 2 inflammatory cytokines expressed by the epithelial cells upon injury to the epithelial barrier (Gabryelska et al., 2019; Roan et al., 2019) . ILC2s are a group of lymphoid cells lacking both B and T cell receptors but play a crucial role in secreting type 2 cytokines to perpetuate type 2 inflammation when activated (Scanlon and McKenzie, 2012; Li and Hendriks, 2013) . In the event of viral infection, cell death and injury to the epithelial barrier will also induce the expression of IL-25, IL-33 and TSLP, with heighten expression in an inflamed airway (Allakhverdi et al., 2007; Goldsmith et al., 2012; Byers et al., 2013; Shaw et al., 2013; Beale et al., 2014; Jackson et al., 2014; Uller and Persson, 2018; Ravanetti et al., 2019) . These 3 cytokines then work in concert to activate ILC2s to further secrete type 2 cytokines IL-4, IL-5, and IL-13 which further aggravate the type 2 inflammation in the airway causing acute exacerbation (Camelo et al., 2017) . In the case of COPD, increased ILC2 activation, which retain the capability of differentiating to ILC1, may also further augment the neutrophilic response and further aggravate the exacerbation (Silver et al., 2016) . Interestingly, these factors are not released to any great extent and do not activate an ILC2 response during viral infection in healthy individuals (Yan et al., 2016; Tan et al., 2018a) ; despite augmenting a type 2 exacerbation in chronically inflamed airways (Jurak et al., 2018) . These classical mechanisms of viral induced acute exacerbations are summarized in Figure 1 . As integration of the virology, microbiology and immunology of viral infection becomes more interlinked, additional factors and FIGURE 1 | Current understanding of viral induced exacerbation of chronic airway inflammatory diseases. Upon virus infection in the airway, antiviral state will be activated to clear the invading pathogen from the airway. Immune response and injury factors released from the infected epithelium normally would induce a rapid type 1 immunity that facilitates viral clearance. However, in the inflamed airway, the cytokines and chemokines released instead augmented the inflammation present in the chronically inflamed airway, strengthening the neutrophilic infiltration in COPD airway, and eosinophilic infiltration in the asthmatic airway. The effect is also further compounded by the participation of Th1 and ILC1 cells in the COPD airway; and Th2 and ILC2 cells in the asthmatic airway. \n\nFrontiers in Cell and Developmental Biology | www.frontiersin.org mechanisms have been implicated in acute exacerbations during and after viral infection (Murray et al., 2006) . Murray et al. (2006) has underlined the synergistic effect of viral infection with other sensitizing agents in causing more severe acute exacerbations in the airway. This is especially true when not all exacerbation events occurred during the viral infection but may also occur well after viral clearance (Kim et al., 2008; Stolz et al., 2019) in particular the late onset of a bacterial infection (Singanayagam et al., 2018 (Singanayagam et al., , 2019a . In addition, viruses do not need to directly infect the lower airway to cause an acute exacerbation, as the nasal epithelium remains the primary site of most infections. Moreover, not all viral infections of the airway will lead to acute exacerbations, suggesting a more complex interplay between the virus and upper airway epithelium which synergize with the local airway environment in line with the \"united airway\" hypothesis (Kurai et al., 2013) . On the other hand, viral infections or their components persist in patients with chronic airway inflammatory disease (Kling et al., 2005; Wood et al., 2011; Ravi et al., 2019) . Hence, their presence may further alter the local environment and contribute to current and future exacerbations. Future studies should be performed using metagenomics in addition to PCR analysis to determine the contribution of the microbiome and mycobiome to viral infections. In this review, we highlight recent data regarding viral interactions with the airway epithelium that could also contribute to, or further aggravate, acute exacerbations of chronic airway inflammatory diseases. Patients with chronic airway inflammatory diseases have impaired or reduced ability of viral clearance (Hammond et al., 2015; McKendry et al., 2016; Akbarshahi et al., 2018; Gill et al., 2018; Wang et al., 2018; Singanayagam et al., 2019b) . Their impairment stems from a type 2-skewed inflammatory response which deprives the airway of important type 1 responsive CD8 cells that are responsible for the complete clearance of virusinfected cells (Becker, 2006; McKendry et al., 2016) . This is especially evident in weak type 1 inflammation-inducing viruses such as RV and RSV (Kling et al., 2005; Wood et al., 2011; Ravi et al., 2019) . Additionally, there are also evidence of reduced type I (IFNβ) and III (IFNλ) interferon production due to type 2-skewed inflammation, which contributes to imperfect clearance of the virus resulting in persistence of viral components, or the live virus in the airway epithelium (Contoli et al., 2006; Hwang et al., 2019; Wark, 2019) . Due to the viral components remaining in the airway, antiviral genes such as type I interferons, inflammasome activating factors and cytokines remained activated resulting in prolong airway inflammation (Wood et al., 2011; Essaidi-Laziosi et al., 2018) . These factors enhance granulocyte infiltration thus prolonging the exacerbation symptoms. Such persistent inflammation may also be found within DNA viruses such as AdV, hCMV and HSV, whose infections generally persist longer (Imperiale and Jiang, 2015) , further contributing to chronic activation of inflammation when they infect the airway (Yang et al., 2008; Morimoto et al., 2009; Imperiale and Jiang, 2015; Lan et al., 2016; Tan et al., 2016; Kowalski et al., 2017) . With that note, human papilloma virus (HPV), a DNA virus highly associated with head and neck cancers and respiratory papillomatosis, is also linked with the chronic inflammation that precedes the malignancies (de Visser et al., 2005; Gillison et al., 2012; Bonomi et al., 2014; Fernandes et al., 2015) . Therefore, the role of HPV infection in causing chronic inflammation in the airway and their association to exacerbations of chronic airway inflammatory diseases, which is scarcely explored, should be investigated in the future. Furthermore, viral persistence which lead to continuous expression of antiviral genes may also lead to the development of steroid resistance, which is seen with RV, RSV, and PIV infection (Chi et al., 2011; Ford et al., 2013; Papi et al., 2013) . The use of steroid to suppress the inflammation may also cause the virus to linger longer in the airway due to the lack of antiviral clearance (Kim et al., 2008; Hammond et al., 2015; Hewitt et al., 2016; McKendry et al., 2016; Singanayagam et al., 2019b) . The concomitant development of steroid resistance together with recurring or prolong viral infection thus added considerable burden to the management of acute exacerbation, which should be the future focus of research to resolve the dual complications arising from viral infection. On the other end of the spectrum, viruses that induce strong type 1 inflammation and cell death such as IFV (Yan et al., 2016; Guibas et al., 2018) and certain CoV (including the recently emerged COVID-19 virus) (Tao et al., 2013; Yue et al., 2018; Zhu et al., 2020) , may not cause prolonged inflammation due to strong induction of antiviral clearance. These infections, however, cause massive damage and cell death to the epithelial barrier, so much so that areas of the epithelium may be completely absent post infection (Yan et al., 2016; Tan et al., 2019) . Factors such as RANTES and CXCL10, which recruit immune cells to induce apoptosis, are strongly induced from IFV infected epithelium (Ampomah et al., 2018; Tan et al., 2019) . Additionally, necroptotic factors such as RIP3 further compounds the cell deaths in IFV infected epithelium . The massive cell death induced may result in worsening of the acute exacerbation due to the release of their cellular content into the airway, further evoking an inflammatory response in the airway (Guibas et al., 2018) . Moreover, the destruction of the epithelial barrier may cause further contact with other pathogens and allergens in the airway which may then prolong exacerbations or results in new exacerbations. Epithelial destruction may also promote further epithelial remodeling during its regeneration as viral infection induces the expression of remodeling genes such as MMPs and growth factors . Infections that cause massive destruction of the epithelium, such as IFV, usually result in severe acute exacerbations with non-classical symptoms of chronic airway inflammatory diseases. Fortunately, annual vaccines are available to prevent IFV infections (Vasileiou et al., 2017; Zheng et al., 2018) ; and it is recommended that patients with chronic airway inflammatory disease receive their annual influenza vaccination as the best means to prevent severe IFV induced exacerbation. Another mechanism that viral infections may use to drive acute exacerbations is the induction of vasodilation or tight junction opening factors which may increase the rate of infiltration. Infection with a multitude of respiratory viruses causes disruption of tight junctions with the resulting increased rate of viral infiltration. This also increases the chances of allergens coming into contact with airway immune cells. For example, IFV infection was found to induce oncostatin M (OSM) which causes tight junction opening (Pothoven et al., 2015; Tian et al., 2018) . Similarly, RV and RSV infections usually cause tight junction opening which may also increase the infiltration rate of eosinophils and thus worsening of the classical symptoms of chronic airway inflammatory diseases (Sajjan et al., 2008; Kast et al., 2017; Kim et al., 2018) . In addition, the expression of vasodilating factors and fluid homeostatic factors such as angiopoietin-like 4 (ANGPTL4) and bactericidal/permeabilityincreasing fold-containing family member A1 (BPIFA1) are also associated with viral infections and pneumonia development, which may worsen inflammation in the lower airway Akram et al., 2018) . These factors may serve as targets to prevent viral-induced exacerbations during the management of acute exacerbation of chronic airway inflammatory diseases. Another recent area of interest is the relationship between asthma and COPD exacerbations and their association with the airway microbiome. The development of chronic airway inflammatory diseases is usually linked to specific bacterial species in the microbiome which may thrive in the inflamed airway environment (Diver et al., 2019) . In the event of a viral infection such as RV infection, the effect induced by the virus may destabilize the equilibrium of the microbiome present (Molyneaux et al., 2013; Kloepfer et al., 2014; Kloepfer et al., 2017; Jubinville et al., 2018; van Rijn et al., 2019) .\n\nQuestion: What is the effect of the inflammation of the airway?", "role": "user" }, { "content": "However, in the inflamed airway, the cytokines and chemokines released instead augmented the inflammation present in the chronically inflamed airway, strengthening the neutrophilic infiltration in COPD airway, and eosinophilic infiltration in the asthmatic airway. The effect is also further compounded by the participation of Th1 and ILC1 cells in the COPD airway; and Th2 and ILC2 cells in the asthmatic airway.", "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\nAltered vasoreactivity to angiotensin II in experimental diabetic neuropathy: role of nitric oxide.\nWe evaluated the effects of angiotensin II and an angiotensin-converting enzyme inhibitor (cilazapril) on nerve blood flow (NBF) and electrophysiology in control and diabetic rats. When applied locally to the sciatic nerve, the dose-response curve of angiotensin II was more potent in experimental diabetic neuropathy (EDN) than control rats. No difference existed in plasma angiotensin II levels between EDN and controls. The rats were given typical rat pellets or pellets treated with 10 mg/kg per day cilazapril for 4 weeks. Diabetes caused a significant reduction in NBF, nerve conduction velocity, and compound muscle action potential (CMAP) amplitudes. NBF was significantly increased in diabetic rats supplemented with cilazapril diet, and nerve conduction velocity and amplitudes of the CMAP were also improved after 4 weeks on this diet. Direct application 10(-3) mol/L cilazapril on sciatic nerve did not increase NBF in normal and EDN rats. We topically applied the nitric oxide synthase (NOS) inhibitor, NG-nitro-L-arginine, on sciatic nerve and observed reduced inhibition of NBF in EDN, which was correctable with a cilazapril diet. These results suggest that diabetic neuropathy may have an increasing vasopressor action with angiotensin II and this is likely to be the mechanism of NOS inhibition. Angiotensin II-converting enzyme inhibitors may have potential in the treatment of diabetic neuropathy.", "role": "user" }, { "content": "{\"Chemical\": [\"angiotensin II\", \"nitric oxide\", \"Angiotensin II\", \"NG-nitro-L-arginine\", \"angiotensin\", \"cilazapril\"], \"Protein\": [\"nitric oxide synthase\", \"angiotensin II\", \"Angiotensin II-converting enzyme\", \"NOS\", \"angiotensin-converting enzyme\"]}", "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: Two-component spike nanoparticle vaccine protects macaques from sars-cov-2 infection\n\nAbstract:\nThe severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic is continuing to disrupt personal lives, global healthcare systems, and economies.\nHence, there is an urgent need for a vaccine that prevents viral infection, transmission, and disease.\nHere, we present a two-component protein-based nanoparticle vaccine that displays multiple copies of the SARS-CoV-2 spike protein.\nImmunization studies show that this vaccine induces potent neutralizing antibody responses in mice, rabbits, and cynomolgus macaques.\nThe vaccine-induced immunity protects macaques against a high-dose challenge, resulting in strongly reduced viral infection and replication in the upper and lower airways.\nThese nanoparticles are a promising vaccine candidate to curtail the SARS-CoV-2 pandemic.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Here, we present a two-component protein-based nanoparticle vaccine that displays multiple copies of the SARS-CoV-2 spike 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: [\"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\nTranscriptional regulation of T lymphocyte development and function. The development and function of T lymphocytes are regulated tightly by signal transduction pathways that include specific cell-surface receptors, intracellular signaling molecules, and nuclear transcription factors. Since 1988, several families of functionally important T cell transcription factors have been identified. These include the Ikaros, LKLF, and GATA3 zinc-finger proteins; the Ets, CREB / ATF, and NF-kappa B / Rel / NFAT transcription factors; the Stat proteins; and HMG box transcription factors such as LEF1, TCF1, and Sox4. In this review, we summarize our current understanding of the transcriptional regulation of T cell development and function with particular emphasis on the results of recent gene targeting and transgenic experiments. In addition to increasing our understanding of the molecular pathways that regulate T cell development and function, these results have suggested novel targets for genetic and pharmacological manipulation of T cell immunity.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"T lymphocytes\"], \"DNA\": [], \"Protein\": [\"NF - kappa B / Rel / NFAT transcription factors\", \"Ikaros\", \"cell - surface receptors\", \"Sox4\", \"Stat proteins\", \"intracellular signaling molecules\", \"T cell transcription factors\", \"LKLF\", \"LEF1\", \"CREB / ATF\", \"GATA3 zinc - finger proteins\", \"TCF1\", \"Ets\", \"HMG box transcription factors\", \"nuclear transcription factors\"], \"RNA\": []}", "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: Are there lncRNAs that control the extent of neuronal outgrowth?\n\nContext: Regulation of Neuroregeneration by Long Noncoding RNAs.\nHere, we profiled gene expression following sciatic nerve crush in mice and identified long noncoding RNAs (lncRNAs) that act in the regenerating neurons and which are typically not expressed in other contexts. We show that two of these lncRNAs regulate the extent of neuronal outgrowth. We then focus on one of these, Silc1, and show that it regulates neuroregeneration in cultured cells and in vivo, through cis-acting activation of the transcription factor Sox11.", "role": "user" }, { "content": "yes", "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: Marijuana and COVID-19: What a Doctor Wants You to Know\n\nAbstract:\nThe recently discovered novel coronavirus, SARS-CoV-2 (COVID-19 virus), has brought the whole world to standstill with critical challenges, affecting both health and economic sectors worldwide.\nAlthough initially, this pandemic was associated with causing severe pulmonary and respiratory disorders, recent case studies reported the association of cerebrovascular-neurological dysfunction in COVID-19 patients, which is also life-threatening.\nSeveral SARS-CoV-2 positive case studies have been reported where there are mild or no symptoms of this virus.\nHowever, a selection of patients are suffering from large artery ischemic strokes.\nAlthough the pathophysiology of the SARS-CoV-2 virus affecting the cerebrovascular system has not been elucidated yet, researchers have identified several pathogenic mechanisms, including a role for the ACE2 receptor.\nTherefore, it is extremely crucial to identify the risk factors related to the progression and adverse outcome of cerebrovascular-neurological dysfunction in COVID-19 patients.\nSince many articles have reported the effect of smoking (tobacco and cannabis) and vaping in cerebrovascular and neurological systems, and considering that smokers are more prone to viral and bacterial infection compared to non-smokers, it is high time to explore the probable correlation of smoking in COVID-19 patients.\nHerein, we have reviewed the possible role of smoking and vaping on cerebrovascular and neurological dysfunction in COVID-19 patients, along with potential pathogenic mechanisms associated with it.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Given a short query with keyphrases about a research idea in 2016 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 develop a system that can predict human activities and use that information to react accordingly\n\nKeyphrases: anticipation human activities video\n\nDataset description:\nCAD-120: The CAD-60 and CAD-120 data sets comprise of RGB-D video sequences of humans performing activities which are recording using the Microsoft Kinect sensor. Being able to detect human activities is important for making personal assistant robots useful in performing assistive tasks.\nJIGSAWS: The JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS) is a surgical activity dataset for human motion modeling. The data was collected through a collaboration between The Johns Hopkins University (JHU) and Intuitive Surgical, Inc. (Sunnyvale, CA.\nIITB Corridor: An abnormal activity data-set for research use that contains 4,83,566 annotated frames.\nGENIA: The GENIA corpus is the primary collection of biomedical literature compiled and annotated within the scope of the GENIA project. The corpus was created to support the development and evaluation of information extraction and text mining systems for the domain of molecular biology.\n\nOptions: A: CAD-120 B: JIGSAWS C: IITB Corridor D: GENIA", "role": "user" }, { "content": "CAD-120", "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: Genotoxic effects of topoisomerase poisoning and PARP inhibition on zebrafish embryos. Topoisomerase poisons are known to stabilize covalent enzyme-DNA intermediates forming covalent cleavage complexes, which are highly cytotoxic especially for dividing cells and thus, make topoisomerases targets for cancer therapy. Topoisomerases have been extensively studied in mammalian model systems, whereas in other vertebrate models including zebrafish, they still remain less characterized. Here we show similarities in the genotoxic effects of zebrafish and mammalian systems towards topoisomerase I (Top1) poisons and PARP inhibitor - olaparib. On the other hand we observed that topoisomerase II ( Top2 ) poisons ( doxorubicin and etoposide ) did not affect 1 day post fertilization embryo viability , however in cells isolated from Top2 drug treated embryos the formation of DNA cleavage complexes was observed by comet assay . We explain this by cellular drug uptake limitation in live zebrafish embryos versus unimpeded drug influx in cells isolated from Top2 poisons pre-treated embryos. We also demonstrate that EDTA facilitates the extraction of Top2 from zebrafish nuclei and recovers both, basal and Top2 poison induced DNA damage.\n\nsentence: On the other hand we observed that topoisomerase II ( Top2 ) poisons ( doxorubicin and etoposide ) did not affect 1 day post fertilization embryo viability , however in cells isolated from Top2 drug treated embryos the formation of DNA cleavage complexes was observed by comet assay .", "role": "user" }, { "content": "[]", "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\nActivated platelets induce monocyte chemotactic protein-1 secretion and surface expression of intercellular adhesion molecule-1 on endothelial cells [ see comments ] BACKGROUND: Platelet / endothelium interaction plays an important role in the pathophysiology of inflammation and atherosclerosis. The role of platelets for monocyte chemotactic protein-1 (MCP-1) secretion and surface expression of intercellular adhesion molecule-1 (ICAM-1) on endothelial cells has been assessed. METHODS AND RESULTS: Monolayers of human umbilical vein endothelial cells were incubated with nonstimulated or ADP-activated platelets for 6 hours, and secretion of MCP-1 and surface expression of ICAM-1 were determined by ELISA and flow cytometry, respectively. In the presence of ADP-activated platelets, both MCP-1 secretion and ICAM-1 surface expression were significantly increased compared with nonstimulated platelets (P < 0. 02). Activation of the transcription factor nuclear factor-kappaB (NF-kappaB) determined by electrophoretic mobility shift assay and kappaB-dependent transcriptional activity was enhanced in the presence of activated platelets. In addition, ADP-activated platelets induced MCP-1 and ICAM-1 promoter-dependent transcription. Liposomal transfection of a double-stranded kappaB phosphorothioate oligonucleotide, but not of the mutated form, inhibited MCP-1 secretion and surface expression of ICAM-1 on activated endothelium (P < 0. 05). CONCLUSIONS: The present study indicates that activated platelets modulate chemotactic (MCP-1) and adhesive (ICAM-1) properties of endothelial cells via an NF-kappaB-dependent mechanism. Platelet-induced activation of the NF-kappaB system might contribute to early inflammatory events in atherogenesis.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"Activated platelets\", \"human umbilical vein endothelial cells\", \"endothelial cells\", \"intercellular adhesion molecule - 1\", \"activated platelets\", \"ADP - activated platelets\", \"nonstimulated platelets\"], \"DNA\": [], \"Protein\": [\"transcription factor nuclear factor - kappaB\", \"ICAM - 1\", \"monocyte chemotactic protein - 1\", \"MCP - 1\", \"kappaB\", \"NF - kappaB\"], \"RNA\": []}", "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: Bio-Mimic Optimization Strategies in Wireless Sensor Networks: A Survey \nChapter Title: GA in WSN Data Aggregation \n1. Abstract of Cited Paper (BIB001): Abstract — A Genetic Algorithm based multi-objective methodology was implemented for a self-organizing wireless sensor network. Design parameters such as network density, connectivity and energy consumption are taken into account for developing the fitness function. The genetic algorithm optimizes the operational modes of the sensor nodes along with clustering schemes and transmission signal strengths. The algorithm has been implemented in MATLAB using its Genetic Algorithm toolbox along with custom codes. The optimal designs so achieved by the algorithm conform to all the design parameters. Index Terms – Genetic Algorithms, Network Configuration , Sensor Placement, Wireless Sensor Networks. I. I NTRODUCTION A dvancements in technologies such as Sensing, Electronics and Computing have attracted tremendous research interest in the field of Wireless Sensor Networks (WSNs), apart from their enormous potential for both commercial and military applications. A WSN generally consists of a large number of low-cost, low-power, multifunctional, energy constrained sensor nodes with limited computational and communication capabilities [1]. In WSNs sensors may be deployed either randomly or deterministically depending upon the application [2]. Deployment in a battlefield or hazardous areas is generally random, whereas a deterministic deployment is preferred in amicable environments. In general a deterministic placement requires fewer sensor nodes than the random deployment to perform the same task. Network lifetime is one of the important parameters to optimize as energy resources in a WSN are limited due to operation on battery. Replacing or recharging of battery in the network may be infeasible. Though the overall function of the \n2. Abstract of Cited Paper (BIB002): Energy is one of the most important items to determine the network lifetime due to low power energy nodes included in the network. Generally, data aggregation tree concept is used to find an energy efficient solution. However, even the best aggregation tree does not share the load of data packets to the transmitting nodes fairly while it is consuming the lowest possible energy of the network. Therefore, after some rounds, this problem causes to consume the whole energy of some heavily loaded nodes and hence results in with the death of the network. In this paper, by using the Genetic Algorithm (GA), we investigate the energy efficient data collecting spanning trees to find a suitable route which balances the data load throughout the network and thus balances the residual energy in the network in addition to consuming totally low power of the network. Using an algorithm which is able to balance the residual energy among the nodes can help the network to withstand more and consequently extend its own lifetime. In this work, we calculate all possible routes represented by the aggregation trees through the genetic algorithm. GA finds the optimum tree which is able to balance the data load and the energy in the network. Simulation results show that this balancing operation practically increases the network lifetime. \n3. Abstract of Cited Paper (BIB003): A fundamental challenge in the design of Wireless Sensor Networks (WSNs) is to maximize their lifetimes especially when they have a limited and non replenishable energy supply. To extend the network lifetime, power management and energy-efficient communication techniques at all layers become necessary. In this paper, we present solutions for the data gathering and routing problem with in-network aggregation in WSNs. Our objective is to maximize the network lifetime by utilizing data aggregation and in- network processing techniques. We particularly focus on the joint problem of optimal data routing with data aggregation en route such that the above mentioned objective is achieved. We present Grid-based Routing and Aggregator Selection Scheme (GRASS), a scheme for WSNs that can achieve low energy dissipation and low latency without sacrificing quality. GRASS embodies optimal (exact) as well as heuristic approaches to find the minimum number of aggregation points while routing data to the Base Station (BS) such that the network lifetime is maximized. Our results show that, when compared to other schemes, GRASS improves system lifetime with acceptable levels of latency in data aggregation and without sacrificing data quality.\n\nLiterature Review:", "role": "user" }, { "content": "As we discussed previously, the fundamental challenge in the design of WSNs is to maximize their lifetimes especially when they have a limited energy supply, so a good data aggregation scheme can change the scenario immensely. In BIB001 the authors present a genetic algorithm-based approach to generate balanced and energy efficient data aggregation spanning trees for WSNs. In the algorithm, the gene index determines a node and the gene's value identifies the parent node. In the data gathering round, a single best tree consumes the lowest energy among all nodes but assigns more load to selected sensors. The chromosome fitness is determined by four factors: residual energy, transmission, received load, and the distribution of load. Results showed that proposed GA outperforms a few other data aggregation tree-based approaches in terms of extending network lifetime. In BIB004 , Al Karaki et al. presented Grid-based Routing and Aggregator Selection Scheme (GRASS). GRASS is said to provide good solutions for the data gathering and routing problem with in-network aggregation in WSNs with a focus on the joint problem of optimal data routing with data aggregation. They claim that the method can achieve low energy dissipation and low latency without sacrificing quality. GRASS embodies optimal approaches as well as heuristic approaches like Clustering-Based Aggregation Heuristic (CBAH). These algorithms are used to find the minimum number of aggregation points while routing data to the BS. When compared to other schemes, GRASS improves system lifetime with acceptable levels of latency in data aggregation without sacrificing data quality. With 100 nodes CBAH provides almost two times better performance then PEGASIS and almost 1.5 times better performance then LEACH when aggregation is used. Without aggregation the performance of CBAH slightly decreases. Results also demonstrate that the CBAH can increase the system lifetime of large WSNs. Commonly, the data aggregation tree concept is used to find an energy efficient solution and is largely accepted by the researchers in this area, but fair load sharing is missing in most of these works. To address this issue Norouzi et al. BIB003 presented a method that utilizes genetic algorithm to find routes which balance energy and data load in a network. In this study, nodes monitor the area to aggregate data and then remove the redundant nodes in order to aggregate them according to the data aggregation spanning tree. GA is used here to create an efficient data aggregation tree in which any node has a value property. Like some other methods, the fitness function is determined on the basis of residual energy, number of transmission, and received data packets from individual nodes. The technique is suitable for a homogeneous WSN environment monitoring. Simulation results indicated that this method practically increases the network lifetime compared to other works BIB002 .", "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:\nINTRAMUSCULAR OXYTOCICS AND CORD TRACTION IN THIRD STATE OF LABOUR.\nAbstract 1:\nnan\n\n\nTitle 2:\nOXYTOCIC DRUGS IN FOURTH STAGE OF LABOR.\nAbstract 2:\nnan\n\n\nTitle 3:\nEffect of oxytocics on prostaglandin levels in the third stage of labour.\nAbstract 3:\nThe levels of prostaglandin F2 alpha metabolites (PGFM) in the peripheral blood were measured during third stage in a group of patients not given any oxytocic and this was compared with the levels produced in other groups given different oxytocics. There was a significant rise in PGFM within 5 min of delivery in all groups but there was no statistical difference in the serum concentrations of PGFM between the different groups. This suggests that oxytocics given during third stage do not act through release of prostaglandins.\n\n\nTitle 4:\nA placebo-controlled trial of oral ergometrine to reduce postpartum hemorrhage.\nAbstract 4:\nActive management with oral ergometrine 0.4 mg was compared with expectant management for the control of blood loss in the third stage of labor in women at low risk of postpartum hemorrhage (PPH).\n A three-arms randomized trial in which 0.4 mg ergometrine (2 tablets of 0.2 mg) was set off against placebo, both groups allowing comparison with a standard oxytocin regimen of 5 IU. Women at low risk for PPH. Of 367 parturients, 146 were randomised to ergometrine 0.4 mg, 143 to placebo and 78 to intramuscular oxytocin in a 2:2:1 design.\n Compared with placebo, ergometrine reduced blood loss with 5% (-5%; Confidence interval: -20% to +13%). Oxytocin reduced blood loss with 9% (-9%; Confidence interval: -26% to +12%) versus placebo.\n Oral ergometrine has too little effect on blood loss after childbirth in order to be a good alternative to parenteral prophylactic management.\n\n\nTitle 5:\nCLINICAL EXPERIENCE WITH SIMULTANEOUS INTRAMUSCULAR INJECTION OF OXYTOCIN AND METHYLERMETRINE.\nAbstract 5:\nnan\n\n\nTitle 6:\nA comparison of oxytocic drugs in the management of the placental stage.\nAbstract 6:\nnan\n\n\nTitle 7:\nCLINICAL TRIAL OF AN OXYTOCIN-ERGOMETRINE MIXTURE.\nAbstract 7:\nnan\n\n\nTitle 8:\nA randomized comparison of oxytocin, sulprostone and placebo in the management of the third stage of labour.\nAbstract 8:\nTo compare the effect on post partum bloodloss of the postpartum prophylactic administration of oxytocin or sulprostone in low risk women having an expectant management of the third stage.\n Randomized, placebo controlled, double-blind trial.\n Radboud University Hospital, Nijmegen (67 women) and Lievensberg Hospital, Bergen op Zoom (10 women).\n 77 women entered the trial (three were excluded).\n The intramuscular injection, immediately after the birth of the baby, of either oxytocin 5 IU, sulprostone 500 micrograms or 0.9% saline.\n Quantitative postpartum blood loss and length of third stage.\n Postpartum blood loss was reduced almost equally, by about 35%, by oxytocin (P = 0.02), or sulprostone (P = 0.05). The mean length of the third stage was shorter in both groups receiving the active treatment, this effect was significant in the sulprostone group (P = 0.01).\n Prophylactic administration of oxytocin or sulprostone directly after delivery followed by expectant management of the third stage reduces post partum blood loss and shortens the third stage.\n\n\nTitle 9:\nRoutine oxytocin in the third stage of labour: a placebo controlled randomised trial.\nAbstract 9:\nTo compare intravenous oxytocin administration (Partocon 10 IU) with saline solution in the management of postpartum haemorrhage in the third stage of labour.\n A double-blind, randomised controlled trial involving 1000 parturients with singleton fetuses in cephalic presentation and undergoing vaginal delivery, randomly allocated to treatment with oxytocin (n = 513) or 0.9% saline solution (n = 487).\n Labour ward at a central county hospital.\n Mean blood loss (total, and before and after placenta delivery); frequencies of blood loss > 800 mL, need of additional oxytocic treatment, postpartum haemoglobin < 10 g/dL; and duration of postpartum hospitalisation.\n As compared with saline solution, oxytocin administration was associated with significant reduction in mean total blood loss (407 versus 527 mL), and in frequencies of postpartum haemorrhage > 800 mL (8.8% versus 5.2%), additional treatment with metylergometrine (7.8% versus 13.8%), and postpartum Hb < 10 g/dL (9.7% versus 15.2%), and a nonsignificant increase in the frequency of manual placenta removal (3.5% versus 2.3%). There was no group difference in the mean duration of postpartum hospitalisation (4.6 versus 4.5 days, respectively).\n Administration of intravenous oxytocin in the third stage of labour is associated with an approximately 22% reduction in mean blood loss, and approximately 40% reductions in frequencies of postpartum haemorrhage (> 500 mL or > 800 mL) and of postpartum haemoglobin < 10 g/dL. Identification of risk groups for oxytocin treatment does not seem worthwhile. Oxytocin is a cheap atoxic drug and should be given routinely after vaginal delivery.", "role": "user" }, { "content": "Oxytocin appears to be beneficial for the prevention of postpartum haemorrhage. However, there is insufficient information about other outcomes and side-effects hence it is difficult to be confident about the trade-offs for these benefits. There seems little evidence in favour of ergot alkaloids alone compared to either oxytocin alone, or to ergometrine-oxytocin, but the data are sparse. More trials are needed in domiciliary deliveries in developing countries, which shoulder most of the burden of third stage complications.\n[Note: The ten citations in the awaiting classification section of the review may alter the conclusions of the review once assessed.]", "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\nLone atrial fibrillation associated with creatine monohydrate supplementation. Atrial fibrillation in young patients without structural heart disease is rare. Therefore, when the arrhythmia is present in this population, reversible causes must be identified and resolved. Thyroid disorders, illicit drug or stimulant use, and acute alcohol intoxication are among these causes. We report the case of a 30-year-old Caucasian man who came to the emergency department in atrial fibrillation with rapid ventricular response. His medical history was unremarkable, except for minor fractures of the fingers and foot. Thyroid-stimulating hormone, magnesium, and potassium levels were within normal limits, urine drug screen was negative, and alcohol use was denied. However, when the patient was questioned about use of herbal products and supplements, the use of creatine monohydrate was revealed. The patient was admitted to the hospital, anticoagulated with unfractionated heparin, and given intravenous diltiazem for rate control and intravenous amiodarone for rate and rhythm control. When discharged less than 24 hours later, he was receiving metoprolol and aspirin, with follow-up plans for echocardiography and nuclear imaging to assess perfusion. Exogenous creatine is used by athletes to theoretically improve exercise performance. Vegetarians may also take creatine to replace what they are not consuming from meat, fish, and other animal products. Previous anecdotal reports have linked creatine to the development of arrhythmia. Clinicians must be diligent when interviewing patients about their drug therapy histories and include questions about their use of herbal products and dietary supplements. In addition, it is important to report adverse effects associated with frequently consumed supplements and herbal products to the Food and Drug Administration and in the literature.", "role": "user" }, { "content": "{\"Chemical\": [\"amiodarone\", \"alcohol\", \"potassium\", \"metoprolol\", \"magnesium\", \"creatine\", \"heparin\", \"aspirin\", \"diltiazem\"], \"Disease\": [\"Thyroid disorders\", \"atrial fibrillation\", \"heart disease\", \"Atrial fibrillation\", \"fractures\", \"arrhythmia\", \"acute alcohol intoxication\"]}", "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 causes Katayama Fever?\n\nContext: The laboratory diagnosis of schistosomiasis and Katayama syndrome in returning travellers is difficult because the number of excreted eggs is often very limited.\nEosinophilia (sometimes exceeding 50%) is often present in patients with acute schistosomiasis (Katayama fever), but may be limited or absent in late fibrotic manifestations of the disease.\nLaboratory diagnosis of schistosomiasis and Katayama syndrome in returning travellers\nThe specific diagnosis of early schistosomiasis and Katayama fever relies essentially on serologic tests or preferably on PCR (if available).\nBACKGROUND: Katayama fever is an acute clinical condition characterised by high fever, dry cough and general malaise occurring during early Schistosoma spp. infection.\nSchistosomiasis is a helminthic infection that is endemic in tropical and subtropical regions.\nIn Africa, it predominantly manifests as urogenital disease, and the main infective agent is Schistosoma hematobium.\nHis symptoms were caused by acute invasive schistosomiasis, also known as Katayama fever.\nOBJECTIVES: To investigate the characteristics of imported Katayama fever (acute schistosomiasis) as well as evolution and outcome under treatment.\nRESULTS: Twenty-three patients were diagnosed with Katayama fever by Schistosoma egg detection and/or by seroconversion.\nThe best therapeutic approach to acute schistosomiasis (Katayama fever) is still unsettled.\nKatayama fever is an acute clinical condition characterised by high fever, dry cough and general malaise occurring during early Schistosoma spp.\nAcute schistosomiasis, called safari's fever in Africa and Katayama fever in Japan, is an immunoallergic reaction due to transcutaneous penetration of infective cercaria.\n[Acute schistosomiasis (Katayama fever)].\nAcute schistosomiasis (Katayama fever): corticosteroid as adjunct therapy.\nKatayama fever or acute schistosomiasis probably occurs more commonly than is recorded.\nHis symptoms were caused by acute invasive schistosomiasis, also known as Katayama fever.\nThree distinct syndromes caused by schistosomiasis have been described: cercarial dermatitis or swimmer's itch, acute schistosomiasis or Katayama fever, and chronic schistosomiasis.\nThree well-defined syndromes caused by schistosomiasis mansoni have been described: the stage of invasion, acute schistosomiasis (Katayama fever), and chronic schistosomiasis.\nEarly detection of circulating anodic antigen (CAA) in a case of acute schistosomiasis mansoni with Katayama fever.\nA 35-year-old man presented with fever and severe urticaria after visiting Uganda. His symptoms were caused by acute invasive schistosomiasis, also known as Katayama fever.\nHis symptoms were caused by acute invasive schistosomiasis, also known as Katayama fever. .\nThree well-defined syndromes caused by schistosomiasis mansoni have been described: the stage of invasion, acute schistosomiasis (Katayama fever), and chronic schistosomiasis.\nThree distinct syndromes caused by schistosomiasis have been described: cercarial dermatitis or swimmer&apos;s itch, acute schistosomiasis or Katayama fever, and chronic schistosomiasis.\nTo investigate the characteristics of imported Katayama fever (acute schistosomiasis) as well as evolution and outcome under treatment. Between April 2000 and September 2004, we included prospectively all patients with confirmed diagnosis of Katayama fever.\nA 35-year-old man presented with fever and severe urticaria after visiting Uganda. His symptoms were caused by acute invasive schistosomiasis, also known as Katayama fever.\nTo investigate the characteristics of imported Katayama fever (acute schistosomiasis) as well as evolution and outcome under treatment. Between April 2000 and September 2004, we included prospectively all patients with confirmed diagnosis of Katayama fever.", "role": "user" }, { "content": "Schistosoma spp", "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:\nAs in (Lee et al., 2003), we used unsupervised training data which is automatically segmented to discover previously unseen stems. We seeked to exploit this ability to generalize to improve the dictionary based model. However, an analysis of the errors indicated that the character based model is more effective at segmenting words that do not appear in the training data.\n\nCitation Sentence:\nAs in ( Lee et al. , 2003 ) , we used unsupervised training data which is automatically segmented to discover previously unseen stems .\n\nContext after the citation:\nIn our case, the character n-gram model is used to segment a portion of the Arabic Gigaword corpus. From this, we create a vocabulary of stems and affixes by requiring that tokens appear more than twice in the supervised training data or more than ten times in the unsupervised, segmented corpus. The resulting vocabulary, predominately of word stems, is 53K words, or about six times the vocabulary observed in the supervised training data. This represents about only 18% of the total number of unique tokens observed in the aggregate training data.", "role": "user" }, { "content": "Uses", "role": "assistant" } ]

[ { "content": "You will be presented with a citation segment from the section of an NLP research paper, as well as the context surrounding that citation. Classify the intent behind this citation by choosing from one of the following categories:\n- Background: provides context or foundational information related to the topic.\n- Extends: builds upon the cited work.\n- Uses: applies the methods or findings of the cited work.\n- Motivation: cites the work as inspiration or rationale for the research.\n- CompareOrContrast: compares or contrasts the cited work with others.\n- FutureWork: cites the work as a direction for future research.\n\nYour answer should be a single word from the following list of options: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. Do not include any other text in your response.\n\nSection Title:\nintroduction\n\nContext before the citation:\nThis includes work on generalized expectation (Mann and McCallum, 2010), posterior regularization (Ganchev et al., 2010) and constraint driven learning (Chang et al., 2007; Chang et al., 2010). There have been a number of efforts to exploit weak or external signals of quality to train better prediction models. We call our algorithm augmented-loss training as it optimizes multiple losses to augment the traditional supervised parser loss.\n\nCitation Sentence:\nThis includes work on generalized expectation ( Mann and McCallum , 2010 ) , posterior regularization ( Ganchev et al. , 2010 ) and constraint driven learning ( Chang et al. , 2007 ; Chang et al. , 2010 ) .\n\nContext after the citation:\nThe work of Chang et al. (2007) on constraint driven learning is perhaps the closest to our framework and we draw connections to it in Section 5. In these studies the typical goal is to use the weak signal to improve the structured prediction models on the intrinsic evaluation metrics. For our setting this would mean using weak application specific signals to improve dependency parsing. Though we explore such ideas in our experiments, in particular for semi-supervised domain adaptation, we are primarily interested in the case where the weak signal is precisely what we wish to optimize, but also desire the benefit from using both data with annotated parse structures and data specific to the task at hand to guide parser training.", "role": "user" }, { "content": "CompareOrContrast", "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\nConstruction and biological characterization of an interleukin-12 fusion protein (Flexi-12): delivery to acute myeloid leukemic blasts using adeno-associated virus. Interleukin-12 (IL-12) is a cytokine that exhibits pleiotropic effects on lymphocytes and natural killer cells and has been shown to have promise for the immunotherapy of cancer. The combination of the immune costimulatory molecule B7. 1 and IL-12 has been shown to be synergistic for T cell activation. By transfecting tumor cells with both IL-12 and B7. 1 cDNAs, it may be possible to use these modified targets as vaccines. A major obstacle in designing a vector to deliver these genes results from the structure of IL-12. Functional IL-12 is a heterodimer composed of two distinct subunits that are encoded by separate genes on different chromosomes. Production of functional IL-12 requires the coordinated expression of both genes. This presents several problems in vectors, particularly those in which additional genes, either a co-stimulatory gene or a selectable marker, are inserted. Therefore, we have constructed a single cDNA that encodes a single-chain protein, called Flexi-12, which retains all of the biological characteristics of recombinant IL-12 (rIL-12). The monomeric polypeptide Flexi-12 is able to induce the proliferation of phytohemagglutinin (PHA) blasts, induce PHA blasts to secrete interferon-gamma (IFN-gamma) and additionally, by preincubation, enhance the killing of K562 targets by PBLs. These phenomena are in a dose-dependent manner comparable to that seen with rIL-12. We have also shown that tyrosine phosphorylation of the STAT 4 transcription factor, which has been shown to be unique to the IL-12 signaling pathway, occurs with Flexi-12 at levels similar to those seen with rIL-12. We have packaged Flexi-12 into a recombinant adeno-associated virus (AAV) and used this vector to infect acute myeloid leukemic (AML) blasts. Infected AML blasts produced between 2 and 6 ng of IL-12 / 10 (6) cells per ml per 48 hr. These studies also confirm that AAV is an efficient delivery vehicle for cytokines to leukemic cells. Direct analysis of these modified cells acting as tumor vaccines is underway.", "role": "user" }, { "content": "{\"CellLine\": [\"PHA blasts\", \"phytohemagglutinin (PHA) blasts\"], \"CellType\": [\"natural killer cells\", \"lymphocytes\", \"PBLs\", \"acute myeloid leukemic blasts\", \"acute myeloid leukemic (AML) blasts\", \"AML blasts\"], \"DNA\": [\"IL - 12 and B7 . 1 cDNAs\", \"co - stimulatory gene\", \"cDNA\"], \"Protein\": [\"Interleukin - 12\", \"phytohemagglutinin\", \"STAT 4 transcription factor\", \"cytokines\", \"functional IL - 12\", \"Flexi - 12\", \"IL - 12\", \"PHA\", \"immune costimulatory molecule\", \"B7 . 1\", \"heterodimer\", \"interferon - gamma\", \"cytokine\", \"interleukin - 12 fusion protein\", \"rIL - 12\", \"IFN - gamma\", \"single - chain protein\"], \"RNA\": []}", "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:\nNodifferenceswereobservedintheabilityoftheAbcg8-/-micetosecretebilesalts(paneld),butthereisamarkedinabilityoftheknockoutmicetosecretesterols(panele)andatrendtowardsareducedabilitytosecretephospholipid(panelf)comparedtowildtype.", "role": "user" }, { "content": "[\"bile salts\", \"sterols\", \"phospholipid\"]", "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\nCaged CO(2) for the direct observation of CO(2)-consuming reactions. CO(2)-consuming reactions, in particular carboxylations, play important roles in technical processes and in nature. Their kinetic behavior and the reaction mechanisms of carboxylating enzymes are difficult to study because CO(2) is inconvenient to handle as a gas, exists in equilibrium with bicarbonate in aqueous solution, and typically yields products that show no significant spectroscopic differences from the reactants in the UV/Vis range. Here we demonstrate the utility of 3-nitrophenylacetic acid and related compounds (caged CO(2)) in conjunction with infrared spectroscopy as widely applicable tools for the investigation of such reactions, permitting convenient measurement of the kinetics of CO(2) consumption. The use of isotopically labeled caged CO(2) provides a tool for the assignment of infrared absorption bands, thus aiding insight into reaction intermediates and mechanisms.", "role": "user" }, { "content": "{\"Chemical\": [\"3-nitrophenylacetic acid\", \"CO(2)\", \"bicarbonate\"]}", "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\nArylsulfonamide inhibitors of aggrecanases as potential therapeutic agents for osteoarthritis: Synthesis and biological evaluation. Aggrecanases, in particular aggrecanase-2 (ADAMTS-5), are considered the principal proteases responsible for aggrecan degradation in osteoarthritis. For this reason, considerable effort has been put on the discovery and development of aggrecanase inhibitors able to slow down or halt the progression of osteoarthritis. We report herein the synthesis and biological evaluation of a series of arylsulfonamido-based hydroxamates as aggrecanase inhibitors. Compound 18 was found to have a nanomolar activity for ADAMTS-5, ADAMTS-4 and MMP-13 and high selectivity over MMP-1 and MMP-14. Furthermore, this compound proved to be effective in blocking ex vivo cartilage degradation without having effect on cell cytotoxicity.", "role": "user" }, { "content": "{\"Chemical\": [\"Arylsulfonamide\", \"hydroxamates\", \"arylsulfonamido\"]}", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"AnatomicalEntity\"].\n\nPlease return the output as a JSON object of the format: {\"AnatomicalEntity\": [\"tumor cells\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be an empty JSON array \"[]\".\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nFormation of new bone during vertical distraction osteogenesis of the human mandible is related to the presence of blood vessels.\nWe examined the effect of distraction rate on blood vessel growth in intramembraneous ossification after vertical distraction osteogenesis in the human mandible. Six edentulous patients (aged 60+/-9 years) with a severely atrophic mandible underwent bone augmentation with distraction osteogenesis. Two distraction rates (0.5 and 1 mm/day) were compared and for each group three patients were analyzed. Vascular histomorphometry was carried out in two different areas in the distraction gap: (1) in the first and (2) in the second 1 mm area from the osteotomy line, representing the oldest and younger new-bone area, respectively. Correlation analysis was performed between blood vessel parameters and the amount of new bone formed during distraction. Histological analysis demonstrated the presence of blood vessels throughout the soft connective tissue in the distraction gap. The volume density of blood vessels between the two investigated areas was significantly lower in the 1 mm/day groups, suggesting a delay in angiogenesis in this group of patients. A positive correlation between blood vessel volume and bone volume density was found in the younger new-bone area but not in the oldest new-bone area. This correlation was due to a higher number of blood vessels rather than to a larger size of the blood vessels. Our data suggest that the lower blood vessel density found in the patients with 1 mm/day distraction rate may be related to disruption of angiogenesis in the soft connective tissue of the gap or to a less optimal mechanical stimulation of cells involved in angiogenesis. This probably results in the slower rate of osteogenesis seen at the 1 mm/day distraction rate compared with the 0.5 mm/day distraction rate. The data support the concept that a positive relationship exists between the density of blood vessels and the formation of bone. For distraction of the human mandible in elderly patients, a distraction rate of 0.5 mm/day seems beneficial.", "role": "user" }, { "content": "{\"AnatomicalEntity\": [\"mandible\", \"cells\", \"area\", \"soft connective tissue\", \"Vascular\", \"areas\", \"blood vessel\", \"blood vessels\", \"new-bone area\", \"bone\"]}", "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\nNew progestagens for contraceptive use.\nThe progestins have different pharmacologic properties depending upon the parent molecule, usually testosterone or progesterone (P), from which they are derived. Very small structural changes in the parent molecule may induce considerable differences in the activity of the derivative. In hormonal contraceptives, progestins represent the major agent designed for suppressing ovulation and are used in combination with estrogen (E) usually ethinyl-estradiol (EE). The development of new generations of progestins with improved selectivity profiles has been a great challenge. Steroidal and nonsteroidal progesterone receptor (PR) agonists have been synthesized as well, although the latter are still in a very early stage of development. Several new progestins, have been synthesized in the last two decades. These include dienogest (DNG), drospirenone (DRSP), Nestorone (NES), nomegestrol acetate (NOMAc) and trimegestone (TMG). These new progestins have been designed to have no androgenic or estrogenic actions and to be closer in activity to the physiological hormone P. DRSP differs from the classic progestins as it is derived from spirolactone. It is essentially an antimineralocorticoid steroid with no androgenic effect but a partial antiandrogenic effect. The antiovulatory potency of the different progestins varies. TMG and NES are the most potent progestins synthesized to date, followed by two of the older progestins, keto-desogestrel (keto-DSG) and levonorgestrel (LNG). The new molecules TMG, DRSP and DNG also have antiandrogenic activity. Striking differences exist regarding the side effects among the progestins and the combination with EE leads to other reactions related to the E itself and whether the associated progestin counterbalances, more or less, the estrogenic action. The 19-norprogesterone molecules and the new molecules DRSP and DNG are not androgenic and, therefore, have no negative effect on the lipid profile. Given their pharmacological properties, it is likely that the new progestins may have neutral effects on metabolic or vascular risks. However, this hypothesis must be confirmed in large clinical trials.", "role": "user" }, { "content": "{\"Chemical\": [\"trimegestone\", \"levonorgestrel\", \"TMG\", \"testosterone\", \"DRSP\", \"keto-DSG\", \"ethinyl-estradiol\", \"NOMAc\", \"nomegestrol acetate\", \"spirolactone\", \"EE\", \"progestin\", \"19-norprogesterone\", \"dienogest\", \"progestagens\", \"NES\", \"LNG\", \"keto-desogestrel\", \"Steroidal\", \"progesterone\", \"estrogen\", \"Nestorone\", \"progestins\", \"steroid\", \"DNG\", \"drospirenone\"], \"Protein\": [\"progesterone receptor\", \"PR\"]}", "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 interest toward spin systems , and more in particular toward spin dynamics in semiconductor structures , has remarkably increased in the last few years also in connection with new emerging areas of physics such as quantum information and computation . in this framework\nit becomes a relevant subject to analyze the entanglement behavior in spin systems in order to assess the performance of applications for example in quantum information processing .\nquite recently it has been shown that entanglement in two qubits system can experience sudden death and sudden birth .\nthis phenomenon @xcite,@xcite deserve a great attention also in applicative contexts from quantum optical to condensed matter systems and has been observed in laboratory in experiments with entangled photon pairs @xcite and atomic ensembles @xcite . in this paper\nwe demonstrate the possibility of realizing such a behavior in a system of two uncoupled spins in a common environment .\nlet s consider a bipartite system constituted by two spins @xmath0 and @xmath1 , hereafter called central spins , that interact , with the same coupling constants @xmath2 , with a system of @xmath3 uncoupled spins .\nthe hamiltonian model that describes such a physical situation is @xmath4 with @xmath5 where @xmath6 and @xmath7 are spin operators acting on the hilbert space of the central system and @xmath8 and @xmath9 are the collective operators describing the others @xmath3 spins . in solid state physics , for example\n, this model can effectively describe many physical systems such as quantum dots @xcite , two - dimensional electron gases @xcite and optical lattices @xcite .\nthe time - dependent schrdinger equation has been already solved for an arbitrary initial condition @xcite , @xcite . in what follows\nwe analyze the dynamics of the entanglement in the central system when the surrounding spins are prepared in specific initial conditions .\nsuppose that the @xmath3 uncoupled spins around the central system are prepared in a linear superposition , with binomial weight , of eigenstates @xmath10 of @xmath11 and @xmath12 with @xmath13 .\nthe two central spins @xmath0 and @xmath1 are instead prepared in the state @xmath14 that is a maximally entangled state .\nthe initial condition we are considering can be thus written as @xmath15 where @xmath16^{\\frac{1}{2}},\\qquad p\\in[0,1].\\ ] ] at a time instant @xmath17 we can write @xcite @xmath18 with @xmath19 where @xmath20 . exploiting eqs.([psit])-([ab ] ) it is possible to prove that at any time instant @xmath17 the reduced density matrix of the central system in the two - spin standard basis @xmath21 , has the following quite simple structure @xmath22 where @xmath23 to estimate the entanglement in the central system we adopt the well - known concurrence function c @xcite that in our case can be simply expressed as @xmath24\\equiv\\max\\left[0,\\ \\sum_{j=0}^{n/2}(b_0^{j})^2\\left(1 - 2(\\delta s_z(t))^2\\right)\\right],\\ ] ] where @xmath25 . the presence of entanglement in the two central spins thus is strictly related to the behavior of observable of clear physical meaning .\nit is interesting to underline that for @xmath26 and @xmath27 , it s possible to find the following closed form of @xmath28 @xmath29.\\ ] ] in function of @xmath30 for @xmath31 with @xmath32 fig.@xmath33 displays the behavior of the exact concurrence function @xmath28 as given by eq.([exact ] ) ( continous line ) and its approximation , eq.([approximation ] ) , ( dot line ) .\nas expected the agreement is excellent at least for @xmath26 .\nmoreover the figure puts into light an interesting behavior in the time evolution of the entanglement present in the central spins .\nstarting , indeed , by construction from @xmath34 , the concurrence function evolves showing collapses and revivals phenomena . on the other hand ,\nit is possible to prove that during the plateau of @xmath28 ( that is when @xmath28 maintains the zero value ) the two spins are in a separable state described by the following density matrix @xmath35 that describes a system characterized by an equal probability of finding all the states @xmath36 . after the plateau of the entanglement the concurrence function suddenly grows up reaching values near to @xmath33 .\nthis behavior periodically appears .\nthe collapses and revivals of @xmath28 shown in fig.@xmath33 recalls those we have in the dynamical behavior of the two - photon jaynes - cummings model @xcite,@xcite described by the following hamiltonian model @xmath37 where @xmath38 is the annihilation operator of the single cavity mode .\nthe analogy between our spin star system and the two - photon j - c model can be better brought to light following the suggestion of ref@xcite , that is putting @xmath39 exploiting indeed such a correspondence the interaction hamiltonian ( [ interaction ] ) assumes the form @xmath40 in this section we analyze a different initial condition for the @xmath3 spins around the central system that is the well know _ atomic coherent state _\n, introduced in @xmath41 by arecchi in analogy with the coherent states of the radiation @xcite .\nthe central system is instead once again in the state @xmath42 .\na coherent state of @xmath3 spins is a linear superposition of states @xmath43 obtained fixing @xmath44 and varying @xmath45 .\nin particular , putting @xmath46 , the initial state of the global system is the following @xmath47 where @xmath48^{\\frac{1}{2}},\\qquad p\\in[0,1].\\ ] ] starting from @xmath49 at time instant @xmath17 we have @xcite @xmath50 with @xmath51 @xmath52 where @xmath53 in this case the concurrence function becomes @xmath54.\\ ] ] the dynamical evolution of @xmath28 against @xmath30 is shown in fig.@xmath55 . in function of @xmath30 for @xmath31 with @xmath56\nwe observe that in this case the situation is quite different from the situation previously examined : the entanglement initially present in the central system sudden dies after some oscillations and , after a period of time in which it is absent , lives again .\nhowever in this case the concurrence function does not reach values near @xmath33 assuming values less than @xmath57 .\nonce again it s possible to make a parallel between the j - c model and the spin star system exploiting the holstein - primakoff transformations @xcite @xmath58 that are valid in a subspace with @xmath44 fixed .\noperating such a transformation the interaction hamiltonian ( [ interaction ] ) becomes @xmath59,\\ ] ] that in the limit of a large number @xmath3 of spins in the environment , that is @xmath60 , reduces to an hamiltonian of the j - c type .\nsummarizing in this paper we have focused our attention on a system constituted by two uncoupled spins embedded in a common environment composed by @xmath3 spins .\nwe have proved the possibility of realizing periodic sudden death and birth of the entanglement in the two not interacting spins appropriately choosing the initial condition of the environment . generally speaking sudden death and sudden birth of the entanglement\nprovides an interesting resource for creation on demand of entanglement between two qubits .\n32 m. yna , t. yu , j.h .\neberly , j. phys .\nb : at . mol .\nphys . @xmath61\n( 2006 ) s621-s625 t. yu , j.h .\neberly , phys .\n@xmath62 , 140404 ( 2004 ) m.p .\nalmeida et al . , science @xmath63 , 579 ( 2007 ) j. laurat et al . , phys .\n@xmath64 , 180504 ( 2007 ) a. imamoglu , d.d .\nawschalom , g. burkand , d.p .\ndivincenzo , d. loss , m. scherwin , a. smale , phys .\n@xmath65 , 4204 ( 1999 ) v. privman , i. d. vagner , and g. kventsel , phys .\na 239 , 141 ( 1998 ) a. sorensen and k. molmer , phys .\n83 , 2274 ( 1999 ) .\nf. palumbo , a. napoli , a. messina , open sys . and information dyn .\n( 2006 ) @xmath66 : 309 - 314 a. napoli , f. palumbo , a. messina , j. phys . : conference series , a. shumovsky , m. manko , s. wallentovitz eds . ,\n@xmath67 , ( 2006 ) 154 - 158 w. k. wootters , phys .\nlett @xmath68 , 2245 ( 1998 ) a. joshi , r.r .\npuri , phys .\na @xmath69 , 5056 ( 1991 ) a. joshi , r.r .\npuri , journal of modern optics @xmath67 , 557 - 570 ( 1989 ) c. gerry , phys .\na @xmath70 , 2683 ( 1988 ) f. t. arecchi , e. courtens , r. gilmore , h. thomas , phys .\na @xmath71 , 2211 ( 1972 ) t. holstein , h. primakoff , phys .\n@xmath72 , 1098 ( 1940 )", "role": "user" }, { "content": "we investigate the entanglement evolution of two qubits interacting with a common environment trough an heisenberg xx mechanism . \n we reveal the possibility of realizing the phenomenon of entanglement sudden death as well as the entanglement sudden birth acting on the environment . \n such analysis is of maximal interest at the light of the large applications that spin systems have in quantum information theory .", "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: Ear Biometrics: A Survey on Ear Image Databases and Techniques for Ear Detection and Recognition \nChapter Title: Gabor Filters \n1. Abstract of Cited Paper (BIB001): This paper investigates a new approach for human ear identification using holistic ::: grey-level information. We employ Log-Gabor wavelets to extract the phase ::: information, i.e. ear-codes, from the 1D gray-level signals. Thus each ear is ::: represented by a unique ear code or (phase template). The query ear images are ::: compared with those in the database using Hamming distance. The minimum ::: Hamming distance obtained from the rotation of ear template is used to authenticate ::: the user. Our experiments on two different public ear databases achieve promising ::: results and suggest its utility in ear-based authentication. This paper also illustrates ::: that the phase information extracted from ear images can achieve significant ::: performance improvement as compared to appearance-based approach employed in ::: the literature.\n\nLiterature Review:", "role": "user" }, { "content": "To extract ear codes from one dimensional gray-level signals, BIB002 used LogGabor wavelets. They used unique code or phase template for each ear. For the classification they used Hamming distance for comparison of input image and the database. On UND collection E database of 113 subjects, they achieved 90% recognition rate. 6. 3D Ear BIB001 represented 3D ear recognition using Iterative Closest Point (ICP) algorithm. They used UND collection F database. They used two-line landmark for segmentation and achieved 98.8 recognition rates. used the ICP for implementation of completely automatic 3D ear recognition system. They used 2D Haar feature for detection of ear and then cropped corresponding 3D segment. They achieved 93% recognition rate on UND collection F database images.", "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 disease is treated with ZMapp?\n\nContext: Gene Transfer of ZMapp Antibodies Mediated by Recombinant Adeno-Associated Virus Protects Against Ebola Infections.\nVectored delivery of the ZMapp antibody cocktail (c2G4, c4G7, and c13C6) by using recombinant adeno-associated viruses (rAAVs) could be useful for preventive immunization against Ebola virus infections because rAAVs can generate long-term antibody expression.\nZMapp Reinforces the Airway Mucosal Barrier Against Ebola Virus.\nAddition of ZMapp, a cocktail of Ebola-binding immunoglobulin G antibodies, effectively reduced mobility of Ebola pseudovirus in the same mucus secretions. Topical delivery of ZMapp to the mouse airways also facilitated rapid elimination of Ebola pseudovirus.\nSeveral strategies have been developed in the past to treat EBOV infection, including the antibody cocktail ZMapp, which has been shown to be effective in nonhuman primate models of infection 1 and has been used under compassionate-treatment protocols in humans 2\nAntibody therapy has been used to treat a variety of diseases and the success of ZMapp and other monoclonal antibody-based therapies during the 2014-2016 West African Ebola outbreak has shown this countermeasure can be a successful therapy for Ebola hemorrhagic fever.\nOnly recently have vaccine or drug regimens for the Ebola virus been developed, including Zmapp and peptides.\nNumerous therapeutics were explored or developed during the outbreak, including repurposed drugs, nucleoside and nucleotide analogues (BCX4430, brincidofovir, favipiravir, and GS-5734), nucleic acid-based drugs (TKM-Ebola and AVI-7537), and immunotherapeutics (convalescent plasma and ZMapp).\nThe patient was treated with monoclonal antibodies (ZMapp), a buffy coat transfusion from an Ebola survivor, and the broad-spectrum antiviral GS-5734.\nHowever, during the recent outbreak, monoclonal antibody cocktails such as ZMapp, ZMAb and MB-003 were either tested in a human clinical safety and efficacy trial or provided to some based on compassionate grounds.\nCocktails of inhibitory monoclonal antibodies (MAbs), such as ZMAb, MB-003, and in particular ZMapp, have demonstrated in animal models some of the most significant therapeutic potential for treating EVD, and in 2014, 15 patients were treated with ZMapp or ZMAb under compassionate-use protocols.\nBACKGROUND Data from studies in nonhuman primates suggest that the triple monoclonal antibody cocktail ZMapp is a promising immune-based treatment for Ebola virus disease (EVD).\nFor example, several patients of the present Ebola virus outbreak in West Africa were treated with ZMapp, a cocktail of three monoclonal antibodies which are expressed in Nicotiana benthamiana.\nThe patient was treated with monoclonal antibodies (ZMapp), a buffy coat transfusion from an Ebola survivor, and the broad-spectrum antiviral GS-5734.\nData from studies in nonhuman primates suggest that the triple monoclonal antibody cocktail ZMapp is a promising immune-based treatment for Ebola virus disease ( EVD ) .\nSeveral patients with Ebola virus disease ( EVD ) managed in the United States have received ZMapp monoclonal antibodies , TKM-Ebola small interfering RNA , brincidofovir , and/or convalescent plasma as investigational therapeutics .\nBACKGROUND Data from studies in nonhuman primates suggest that the triple monoclonal antibody cocktail ZMapp is a promising immune-based treatment for Ebola virus disease (EVD).\nMETHODS Beginning in March 2015, we conducted a randomized, controlled trial of ZMapp plus the current standard of care as compared with the current standard of care alone in patients with EVD that was diagnosed in West Africa by polymerase-chain-reaction (PCR) assay.\nDuring the 2014 Ebola outbreak, an experimental drug named ZMapp was administered on an emergency basis to seven patients of which five were recovered.\nBACKGROUND: Data from studies in nonhuman primates suggest that the triple monoclonal antibody cocktail ZMapp is a promising immune-based treatment for Ebola virus disease (EVD).\nData from studies in nonhuman primates suggest that the triple monoclonal antibody cocktail ZMapp is a promising immune-based treatment for Ebola virus disease (EVD).\nDuring the latest outbreak of Ebola virus disease in West Africa, monoclonal antibody therapy (e.g., ZMapp) was utilized to treat patients.\nThis includes agents belonging to various therapeutic classes, namely direct antiviral agents (favipiravir and BCX4430), a combination of antibodies (ZMapp), type I interferons, RNA interference-based drugs (TKM-Ebola and AVI-7537), and anticoagulant drugs (rNAPc2).\nDuring the latest outbreak of Ebola virus disease in West Africa, monoclonal antibody therapy (e.g., ZMapp) was utilized to treat patients.\nRecent successes with monoclonal antibody cocktails ZMapp(TM) and MIL77 against Ebola virus (EBOV) infections have reignited interest in antibody-based therapeutics.\nThe human-mouse chimeric monoclonal antibody (mAb) cocktail ZMapp, previously shown to be efficacious in EBOV (variant Kikwit) lethally infected nonhuman primates (NHPs) when administration was initiated up to 5 days, was used in some patients during the outbreak. We show that a two-antibody cocktail, MIL77E, is fully protective in NHPs when administered at 50 mg/kg 3 days after challenge with a lethal dose of EBOV variant Makona, the virus responsible for the ongoing 2014-2015 outbreak, whereas a similar formulation of ZMapp protected two of three NHPs.\nThe growing promise of plant-made biologics is highlighted by the success story of ZMapp™ as a potentially life-saving drug during the Ebola outbreak of 2014-2016.\nReversion of advanced Ebola virus disease in nonhuman primates with ZMapp.\nBackground Data from studies in nonhuman primates suggest that the triple monoclonal antibody cocktail ZMapp is a promising immune-based treatment for Ebola virus disease (EVD).\nSeveral patients with Ebola virus disease (EVD) managed in the United States have received ZMapp monoclonal antibodies, TKM-Ebola small interfering RNA, brincidofovir, and/or convalescent plasma as investigational therapeutics.\nAlso there is no specific vaccine and treatment for Ebola virus; however, many candidate vaccines and antiviral-drugs such as ZMapp and TKM-Ebola are being developed for Ebola virus disease.\nA Randomized, Controlled Trial of ZMapp for Ebola Virus Infection.\nELISA and neutralizing antibody assays indicate that ZMapp is cross-reactive with the Guinean variant of Ebola.\nGoing forward, this work now provides a basis for strategic selection of next-generation antibody cocktails against Ebola and related viruses and a model for predicting the impact of ZMapp on potential escape mutations in ongoing or future Ebola outbreaks.\nSome potential therapeutic materials including ZMapp were supplied and the treated people got over the EVD.\nCocktails of inhibitory monoclonal antibodies (MAbs), such as ZMAb, MB-003, and in particular ZMapp, have demonstrated in animal models some of the most significant therapeutic potential for treating EVD, and in 2014, 15 patients were treated with ZMapp or ZMAb under compassionate-use protocols.\nThis review explores some of the more prominent recent advances in the biofarming of viral vaccines and therapies, including the recent use of ZMapp for Ebolavirus infection, and explores some possible future applications of the technology.\nELISA and neutralizing antibody assays indicate that ZMapp is cross-reactive with the Guinean variant of Ebola.\nCocktails of inhibitory monoclonal antibodies (MAbs), such as ZMAb, MB-003, and in particular ZMapp, have demonstrated in animal models some of the most significant therapeutic potential for treating EVD, and in 2014, 15 patients were treated with ZMapp or ZMAb under compassionate-use protocols.\nFor example, several patients of the present Ebola virus outbreak in West Africa were treated with ZMapp, a cocktail of three monoclonal antibodies which are expressed in Nicotiana benthamiana.\nReversion of advanced Ebola virus disease in nonhuman primates with ZMapp.", "role": "user" }, { "content": "Ebola virus infection", "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\nIncreased frequency of venous thromboembolism with the combination of docetaxel and thalidomide in patients with metastatic androgen-independent prostate cancer. STUDY OBJECTIVE: To evaluate the frequency of venous thromboembolism (VTE) in patients with advanced androgen-independent prostate cancer who were treated with docetaxel alone or in combination with thalidomide. DESIGN: Retrospective analysis of a randomized phase II trial. SETTING: National Institutes of Health clinical research center. PATIENTS: Seventy men, aged 50-80 years, with advanced androgen-independent prostate cancer. INTERVENTION: Each patient received either intravenous docetaxel 30 mg/m2/week for 3 consecutive weeks, followed by 1 week off, or the combination of continuous oral thalidomide 200 mg every evening plus the same docetaxel regimen. This 4-week cycle was repeated until there was evidence of excessive toxicity or disease progression. MEASUREMENTS AND MAIN RESULTS: None of 23 patients who received docetaxel alone developed VTE, whereas 9 of 47 patients (19%) who received docetaxel plus thalidomide developed VTE (p=0.025). CONCLUSION: The addition of thalidomide to docetaxel in the treatment of prostate cancer significantly increases the frequency of VTE. Clinicians should be aware of this potential complication when adding thalidomide to chemotherapeutic regimens.", "role": "user" }, { "content": "{\"Chemical\": [\"docetaxel\", \"thalidomide\"], \"Disease\": [\"VTE\", \"venous thromboembolism\", \"toxicity\", \"prostate cancer\"]}", "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:\nSustained Weight Loss with Vagal Nerve Blockade but Not with Sham: 18-Month Results of the ReCharge Trial\nAbstract 1:\nBackground / Objectives . Vagal block therapy ( vBloc ) is effective for moderate to severe obesity at one year . Subjects/ Methods . The ReCharge trial is a double-blind , r and omized controlled clinical trial of 239 participants with body mass index ( BMI ) of 40 to 45 kg/m or 35 to 40 kg/m with one or more obesity-related conditions . Interventions were implantation of either vBloc or Sham devices and weight management counseling . Mixed models assessed percent excess weight loss ( % EWL ) and total weight loss ( % TWL ) in intent-to-treat analyses . At 18 months , 142 ( 88 % ) vBloc and 64 ( 83 % ) Sham patients remained enrolled in the study . Results . 18-month weight loss was 23 % EWL ( 8.8 % TWL ) for vBloc and 10 % EWL ( 3.8 % TWL ) for Sham ( P < 0.0001 ) . vBloc patients largely maintained 12-month weight loss of 26 % EWL ( 9.7 % TWL ) . Sham regained over 40 % of the 17 % EWL ( 6.4 % TWL ) by 18 months . Most weight regain preceded unblinding . Common adverse events of vBloc through 18 months were heartburn/dyspepsia and abdominal pain ; 98 % of events were reported as mild or moderate and 79 % had resolved . Conclusions . Weight loss with vBloc was sustained through 18 months , while Sham regained weight between 12 and 18 months . vBloc is effective with a low rate of serious complications\n\n\nTitle 2:\nSelection of electrical algorithms to treat obesity with intermittent vagal block using an implantable medical device.\nAbstract 2:\nBACKGROUND A laparoscopically implantable electrical device that intermittently blocks both vagi near the esophagogastric junction led to significant excess weight loss ( EWL ) in an initial clinical trial in obese patients . The study objective was to optimize therapy algorithms and determine the EWL achieved with a second-generation device at university hospitals in Australia , Norway , and Switzerl and . METHODS Data acquired during the initial clinical trial were analyzed and subsequently used to select alternative electrical algorithms . In the second trial , vagal blocking using one selected therapy algorithm was initiated 2 weeks after implanting the second-generation device . The patients were followed up for 6 months to assess the EWL and safety , including adverse events . RESULTS In the initial clinical trial , vagal blocking algorithm duration s of 90 - 150 s were associated with greater EWL compared with either shorter or longer algorithm duration s ( P<.01 ) . The second trial enrolled 27 patients ( mean body mass index 39.3+/-.8 kg/m2 ) to evaluate a 120-s blocking algorithm . At 6 months , greater EWL was achieved ( 22.7%+/-3.1 % , n=24 ) compared with the initial study and first-generation device ( 14.2%+/-2.2 % , n=29 , P=.03 ) . In both trials , an association was found between the number of 90 - 150-s algorithms delivered daily and greater EWL ( P=.03 ) . No deaths , unanticipated device-related adverse events , or medically serious adverse events were associated with the device . CONCLUSION This second-generation vagal blocking device , using a therapy algorithm of 120-s duration , result ed in a clinical ly acceptable safety profile and significantly greater EWL compared with the first-generation device delivering a wider range of therapy algorithm duration\n\n\nTitle 3:\nIntra-abdominal vagal blocking (VBLOC therapy): clinical results with a new implantable medical device.\nAbstract 3:\nBACKGROUND A new medical device uses high-frequency electrical algorithms to create intermittent vagal blocking ( VBLOC therapy ) . The aim is to assess the effects of vagal blocking on excess weight loss ( EWL ) , safety , dietary intake , and vagal function . METHODS An open-label , 3-center study was conducted in obese subjects ( body mass index [ BMI ] 35 - 50 kg/m(2 ) ) . Electrodes were implanted laparoscopically on both vagi near the esophagogastric junction to provide electrical block . Patients were followed for 6 months for body weight , safety , electrocardiogram , dietary intake , satiation , satiety , and plasma pancreatic polypeptide ( PP ) response to sham feeding . To specifically assess device effects alone , no diet or exercise programs were instituted . RESULTS Thirty-one patients ( mean BMI , 41.2 + /- 1.4 kg/m(2 ) ) received the device . Mean EWL at 4 and 12 weeks and 6 months after implant was 7.5 % , 11.6 % , and 14.2 % , respectively ( all P < .001 ) ; 25 % of patients lost > 25 % EWL at 6 months ( maximum , 36.8 % ) . There were no deaths or device-related serious adverse events ( AEs ) . Calorie intake decreased by > 30 % at 4 and 12 weeks and 6 months ( all P < or= .01 ) , with earlier satiation ( P < .001 ) and reduced hunger ( P = .005 ) . After 12 weeks , plasma PP responses were suppressed ( 20 + /- 7 vs 42 + /- 19 pg/mL ) . Average percent EWL in patients with PP response < 25 pg/mL was double that with PP response > 25 pg/mL ( P = .02 ) . Three patients had serious AEs that required brief hospitalization , 1 each for lower respiratory tract , subcutaneous implant site seroma , and Clostridium difficile diarrhea . CONCLUSIONS Intermittent , intra-abdominal vagal blocking is associated with significant EWL and a desirable safety profile\n\n\nTitle 4:\nBladder voiding by combined high frequency electrical pudendal nerve block and sacral root stimulation.\nAbstract 4:\nAIMS Uncoordinated contraction of the external urethral sphincter is prevalent in individuals with spinal cord injury and can prevent bladder voiding . The aim of this study was to demonstrate that complete and reversible sinusoidal high frequency alternating current ( HFAC ) conduction block of the pudendal nerves ( PN ) can eliminate external urethral sphincter activation and produce low residual bladder voiding . METHODS In four cats , tripolar nerve cuff electrodes were implanted bilaterally on both pudendal nerves and on both extradural S2 roots . Bladder and urethral pressures , bladder volumes and flow were recorded . Bilateral HFAC was applied to determine voltage and frequency parameters result ing in bilateral PN conduction block . Sacral root stimulation provided bladder activation . R and omized sets of voiding trials were conducted with and without HFAC PN block . Additional voiding trials were conducted following bilateral PN neurotomy to eliminate somatic sphincter resistance and provide an estimate of voiding with complete block . RESULTS Effective bilateral PN block and voiding was obtained in three of four animals . Application of bilateral PN HFAC stimulation improved voiding from 2 + /- 4 % to 77 + /- 18 % of the initial bladder volume and significantly ( P < 0.001 ) reduced maximum bladder pressure during voiding . Voiding in trials with PN block was not significantly different from voiding following PN neurotomy ( 82 + /- 19 % , P = 0.51 ) . CONCLUSIONS These results demonstrate that bilateral HFAC block of the PN can produce effective voiding . Neural prostheses using this approach may provide an alternative method for producing micturition for people with spinal cord injury\n\n\nTitle 5:\nEffect of Unmodulated 5-kHz Alternating Currents Versus Transcutaneous Electrical Nerve Stimulation on Mechanical and Thermal Pain, Tactile Threshold, and Peripheral Nerve Conduction: A Double-Blind, Placebo-Controlled Crossover Trial.\nAbstract 5:\nOBJECTIVE To investigate the effect of unmodulated 5-kHz alternating current on mechanical pain threshold ( MPT ) , heat pain threshold ( HPT ) , tactile threshold ( TT ) , and peripheral nerve conduction ( PNC ) compared with transcutaneous electrical nerve stimulation ( TENS ) and sham stimulation . SETTING National referral center . DESIGN R and omized , double-blind , placebo-controlled crossover trial . PARTICIPANTS Healthy volunteers ( N=38 ) . No dropouts or adverse events were reported . INTERVENTION TENS , unmodulated 5-kHz currents , and sham stimulation were applied on the radial nerve for 20 minutes with a 24-hour washout period between them and concealed intervention allocation . MAIN OUTCOME MEASURES Four measures were taken : before , during , and 2 after the interventions . Algometry was used to assess MPT , a Peltier thermode for HPT using the method of limits , Von Frey filaments for TT , and radial nerve compound action potential . RESULTS No differences were observed on MPT , HPT , and PNC when 5-kHz current and TENS were compared . However , TT increased 56.2mN ( 95 % confidence interval [ CI ] , 28.8 - 83.6 ) in the TENS group compared with the 5-kHz current group during intervention . Compared with sham stimulation during intervention , MPT increased 4.7N ( 95 % CI , 0.3 - 9.2 ) using 5-kHz current and 10.4N ( 95 % CI , 3.5 - 17.3 ) with TENS . TT increased 17.2mN ( 95 % CI , 4.7 - 29.7 ) with 5-kHz current and 73.4mN ( 95 % CI , 47.5 - 99.2 ) with TENS . However , HPT increased 1.0 ° C ( 95 % CI , 0.2 - 2.0 ) only with TENS . For the PNC , no differences were found among the 3 groups . CONCLUSIONS Unmodulated 5-kHz current produced an increase in somatosensory thresholds that was greater than placebo but not when compared with TENS ; however , participants perceived 5-kHz currents to be more comfortable and showed more habituation to them\n\n\nTitle 6:\nThe EMPOWER Study: Randomized, Prospective, Double-Blind, Multicenter Trial of Vagal Blockade to Induce Weight Loss in Morbid Obesity\nAbstract 6:\nBackground Intermittent , reversible intraabdominal vagal blockade ( VBLOC ® Therapy ) demonstrated clinical ly important weight loss in feasibility trials . EMPOWER , a r and omized , double-blind , prospect i ve , controlled trial was conducted in USA and Australia . Methods Five hundred three subjects were enrolled at 15 centers . After informed consent , 294 subjects were implanted with the vagal blocking system and r and omized to the treated ( n = 192 ) or control ( n = 102 ) group . Main outcome measures were percent excess weight loss ( percent EWL ) at 12 months and serious adverse events . Subjects controlled duration of therapy using an external power source ; therapy involved a programmed algorithm of electrical energy delivered to the subdiaphragmatic vagal nerves to inhibit afferent/efferent vagal transmission . Devices in both groups performed regular , low-energy safety checks . Data are mean ± SEM . Results Study subjects consisted of 90 % females , body mass index of 41 ± 1 kg/m2 , and age of 46 ± 1 years . Device-related complications occurred in 3 % of subjects . There was no mortality . 12-month percent EWL was 17 ± 2 % for the treated and 16 ± 2 % for the control group . Weight loss was related linearly to hours of device use ; treated and controls with ≥12 h/day use achieved 30 ± 4 and 22 ± 8 % EWL , respectively . Conclusions VBLOC ® therapy to treat morbid obesity was safe , but weight loss was not greater in treated compared to controls ; clinical ly important weight loss , however , was related to hours of device use . Post- study analysis suggested that the system electrical safety checks ( low charge delivered via the system for electrical impedance , safety , and diagnostic checks ) may have contributed to weight loss in the control group", "role": "user" }, { "content": "High-frequency alternating currents using frequencies of > 4–5 kHz effectively block nerve conduction .\nThere is no consensus about the block mechanism , although it has been showed that the frequency is a key factor to produce K+ channels activation or Na+ channels inactivation .\nThe nerve block produced by currents quickly reverts without causing further damage to the nerve .", "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: Can Panitumumab cause trichomegaly?\n\nContext: Xerosis was present in two cases, and paronychia, pyogenic granuloma, trichomegaly, and madarosis were observed in one patient each.\nEyelash trichomegaly is an uncommon drug-associated sequelae experienced during treatment with epidermal growth factor receptor (EGFR) inhibitors. Elongation of the eyelashes induced by these agents has predominantly been observed in oncology patients with either colorectal or lung cancer. It is most frequently associated with cetuximab and erlotinib; however, it has also been described in individuals treated with gefitinib or panitumumab.\nTrichomegaly of the eyelashes during therapy with epidermal growth factor receptor inhibitors: report of 3 cases.\nTrichomegaly of the eyelashes is a rare adverse effect of EGFR inhibitor therapy and is characterized by a paradoxical overgrowth of eyelashes.", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "content": "You will be presented with a citation segment from the section of an NLP research paper, as well as the context surrounding that citation. Classify the intent behind this citation by choosing from one of the following categories:\n- Background: provides context or foundational information related to the topic.\n- Extends: builds upon the cited work.\n- Uses: applies the methods or findings of the cited work.\n- Motivation: cites the work as inspiration or rationale for the research.\n- CompareOrContrast: compares or contrasts the cited work with others.\n- FutureWork: cites the work as a direction for future research.\n\nYour answer should be a single word from the following list of options: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. Do not include any other text in your response.\n\nSection Title:\nintroduction\n\nContext before the citation:\nIn practical context, German, English, and Japanese HPSG-based grammars are developed and used in the Verbmobil project (Kay et al., 1994). Stanford University is developing the English Resource Grammar, an HPSG grammar for English, as a part of the Linguistic Grammars Online (LinGO) project (Flickinger, 2000). There are a variety of works on efficient parsing with HPSG, which allow the use of HPSGbased processing in practical application contexts (Flickinger et al., 2000).\n\nCitation Sentence:\nIn practical context , German , English , and Japanese HPSG-based grammars are developed and used in the Verbmobil project ( Kay et al. , 1994 ) .\n\nContext after the citation:\nOur group has developed a wide-coverage HPSG grammar for Japanese (Mitsuishi et al., 1998), which is used in a high-accuracy Japanese dependency analyzer (Kanayama et al., 2000). \u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000", "role": "user" }, { "content": "Background", "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:\nANTIBIOTIC ELIMINATION OF GROUP-B STREPTOCOCCI IN URINE IN PREVENTION OF PRETERM LABOUR\nAbstract 1:\nThe presence of group-B streptococci in the urine of pregnant women seems to be associated with preterm labour . Urine sample s from 4122 women at 27 - 31 weeks ' gestation were examined for bacteria . Group-B streptococci were found in the urine of 69 women . In a double-blind , controlled study these patients were given either penicillin ( 10(6 ) IU three times daily for 6 days ; 37 patients ) or placebo ( 32 patients ) . The rates of primary rupture of the membranes ( 11 % v 53 % ; p less than 0.001 ) and preterm labour ( 5.4 % v 38 % ; p less than 0.002 ) were significantly lower in the penicillin group than in the placebo group . These results suggest that treatment and follow-up to prevent recolonisation in pregnant women with group-B streptococci in the urine may reduce the frequency of preterm labour in these patients\n\n\nTitle 2:\nMaternal and neonatal consequences of treated and untreated asymptomatic bacteriuria in pregnancy: a prospective cohort study with an embedded randomised controlled trial.\nAbstract 2:\nBACKGROUND Existing approaches for the screening and treatment of asymptomatic bacteriuria in pregnancy are based on trials that were done more than 30 years ago . In this study , we reassessed the consequences of treated and untreated asymptomatic bacteriuria in pregnancy . METHODS In this multicentre prospect i ve cohort study with an embedded r and omised controlled trial , we screened women ( aged ≥18 years ) at eight hospitals and five ultrasound centres in the Netherl and s with a singleton pregnancy between 16 and 22 weeks ' gestation for asymptomatic bacteriuria . Screening was done with a single dipslide and two culture media . Dipslides were judged positive when the colony concentration was at least 1 × 10(5 ) colony-forming units ( CFU ) per mL of a single microorganism or when two different colony types were present but one had a concentration of at least 1 × 10(5 ) CFU per mL. Asymptomatic bacteriuria-positive women were eligible to participate in the r and omised controlled trial comparing nitrofurantoin with placebo treatment . In this trial , participants were r and omly assigned 1:1 to receive either nitrofurantoin 100 mg or identical placebo tablets , and were instructed to self-administer these tablets twice daily for 5 consecutive days . R and omisation was done by a web-based application with a computer-generated list with r and om block sizes of two , four , or six participants rendered by an independent data manager . 1 week after the end of treatment , they provided us with a follow-up dipslide . Women , treating physicians , and research ers all remained unaware of the bacteriuria status and treatment allocation . Women who refused to participate in the r and omised controlled trial did not receive any antibiotics , but their outcomes were collected for analysis in the cohort study . We compared untreated and placebo-treated asymptomatic bacteriuria-positive women with asymptomatic bacteriuria-negative women and nitrofurantoin-treated asymptomatic bacteriuria-positive women . The primary endpoint was a composite of pyelonephritis with or without preterm birth at less than 34 weeks , analysed by intention to treat at 6 weeks post-partum . This trial is registered with the Dutch Trial Registry , number NTR3068 . FINDINGS Between Oct 11 , 2011 , and June 10 , 2013 , we enrolled 5621 women into our screening cohort , of whom 5132 were eligible for screening . After exclusions for contaminated dipslides and patients lost to follow-up , in our final cohort of 4283 women , 248 were asymptomatic bacteriuria positive , of whom 40 were r and omly assigned to nitrofurantoin and 45 to placebo for the r and omised controlled trial , whereas the other 163 asymptomatic bacteriuria-positive women were followed without treatment . The proportion of women with pyelonephritis , preterm birth , or both did not differ between untreated or placebo-treated asymptomatic bacteriuria-positive women and asymptomatic bacteriuria-negative women ( 6 [ 2·9 % ] of 208 vs 77 [ 1·9 % ] of 4035 ; adjusted odds ratio [ OR ] 1·5 , 95 % CI 0·6 - 3·5 ) nor between asymptomatic bacteriuria-positive women treated with nitrofurantoin versus those who were untreated or received placebo ( 1 [ 2·5 % ] of 40 vs 6 [ 2·9 % ] of 208 ; risk difference -0·4 , 95 % CI -3·6 to 9·4 ) . Untreated or placebo-treated asymptomatic bacteriuria-positive women developed pyelonephritis in five [ 2·4 % ] of 208 cases , compared with 24 [ 0·6 % ] of 4035 asymptomatic bacteriuria-negative women ( adjusted OR 3·9 , 95 % CI 1·4 - 11·4 ) . INTERPRETATION In women with an uncomplicated singleton pregnancy , asymptomatic bacteriuria is not associated with preterm birth . Asymptomatic bacteriuria showed a significant association with pyelonephritis , but the absolute risk of pyelonephritis in untreated asymptomatic bacteriuria is low . These findings question a routine screen-treat-policy for asymptomatic bacteriuria in pregnancy . FUNDING ZonMw ( the Netherl and s Organisation for Health Research and Development )\n\n\nTitle 3:\nUrinary antiseptics in asymptomatic bacteriuria of pregnancy.\nAbstract 3:\nA screening programme for the detection of asymptomatic bacteriuria in patients attending an antenatal clinic is described . The results obtained from the use of urinary antiseptics in a controlled trial over a period of two years are presented . The number of patients developing clinical pyelonephritis , fetal maturity at delivery and birth weight were recorded for treatment and control groups and compared with the equivalent results obtained from the total population of patients seen at the clinic\n\n\nTitle 4:\n[Importance of systematic research of urinary infection in pregnant women and the cost of its detection. Proposal for a practical approach].\nAbstract 4:\nThe first part consisted of a prospect i ve study dealing with a series of 170 pregnancies during which cyto-bacteriological examination of urine was carried out in the 3rd , 5th , 7th and 9th months of pregnancy . Whenever bacteriuria was found it was treated . Those women found to be infected in pregnancy were re-examined bacteriologically and radiologically after delivery . A control series consisted of 200 pregnant women whose urines were not examined in this way unless they had clinical signs . In the first series 39 out of 170 women had at least one positive cyto-bacteriological test . 56 out of 638 examinations were abnormal . 50 had asymptomatic bacteriuria . No patient had any sign of acute pyelonephritis . In the control series 16 of the women had at least one positive cyto-bacteriological test . In all 21 tests were carried out ( 18 before signs of cystitis developed and 3 before symptoms of acute pyelonephritis ) . Treating asymptomatic bacteriuria is worth while because it helps to lower the incidence of pyelonephritis . There did not seem to be any relationship between premature labour , fetal mortality and maternal urinary pathology . Tests carried out at two definite intervals in pregnancy would seem to be a sufficient screening for preventing pyelonephritis and would be acceptable from the cost angle\n\n\nTitle 5:\nScreening and treatment of asymptomatic bacteriuria in pregnancy prevent pyelonephritis.\nAbstract 5:\nAlthough asymptomatic bacteriuria during pregnancy is associated with an increased risk of developing pyelonephritis , the effectiveness of screening programs to reduce this risk is controversial . A sharp reduction in the annual incidence of pyelonephritis ( 1.8 % to 0.6 % , P < .001 ) occurred after the introduction of a program to screen and treat asymptomatic bacteriuria among pregnant women followed at a large teaching hospital . The data provide retrospective and prospect i ve evidence that screening and treatment programs for asymptomatic bacteriuria during pregnancy reduce the risk of pyelonephritis in a population with a moderate to high prevalence of bacteriuria\n\n\nTitle 6:\nUrinary Concentrating Ability in Women with Asymptomatic Bacteriuria in Pregnancy\nAbstract 6:\nThe incidence of impaired renal concentrating ability in pregnant women with asymptomatic significant bacteriuria is significantly less than previously reported when osmolality readings are performed on every urine specimen obtained during the 24 hours ' deprivation of fluids . The concentrating defect is more considerable as pregnancy progresses . The lower the maximum urinary osmolality the more difficult is the treatment of the patient , and the higher the incidence of acute pyelonephritis\n\n\nTitle 7:\nBacteriuria of pregnancy: results of treatment.\nAbstract 7:\nAlthough it has been shown that bacteriuria of pregnancy can be eradicated by keeping patients on antibacterial agents throughout pregnancy [ 1 ] , this regimen of treatment would be unacceptable to most individuals , particularly when asymptomatic ; and there are many who would question the ethical justification for such prolonged antibacterial therapy in pregnancy . This paper presents the results of a study design ed to determine whether antibacterial therapy of limited duration would eradicate", "role": "user" }, { "content": "Women have conflicting opinions about antibiotic use during pregnancy .\nAntibiotic treatment for women having significant bacteriuria likely reduces the incidence of pyelonephritis and low birth weight , but we are uncertain about the magnitude of the effect and about the extent to which we can apply these results to asymptomatic population s and screening programmes .", "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 disease is the drug aducanumab targeting?\n\nContext: Most importantly, recent trials of three different Aβ antibodies (solanezumab, crenezumab, and aducanumab) have suggested a slowing of cognitive decline in post hoc analyses of mild AD subjects.\necent results from trials of agents such as aducanumab are encouraging but must also be interpreted with caution. Such medicines could potentially delay the onset of dementia and would therefore markedly reduce its prevalence.\nAducanumab is an anti-Aβ antibody being developed for the treatment of AD, and interim analyses of a phase 1b clinical trial have suggested potential beneficial effects on the amyloid pathology and the cognitive status in patients treated with aducanumab\nThe antibody aducanumab reduces Aβ plaques in Alzheimer's disease.", "role": "user" }, { "content": "Alzheimer's disease", "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\": [\"IGF\", ...]}. 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\nDoxycycline attenuates breast cancer related inflammation by decreasing plasma lysophosphatidate concentrations and inhibiting NF-κB activation. BACKGROUND: We previously discovered that tetracyclines increase the expression of lipid phosphate phosphatases at the surface of cells. These enzymes degrade circulating lysophosphatidate and therefore doxycycline increases the turnover of plasma lysophosphatidate and decreases its concentration. Extracellular lysophosphatidate signals through six G protein-coupled receptors and it is a potent promoter of tumor growth, metastasis and chemo-resistance. These effects depend partly on the stimulation of inflammation that lysophosphatidate produces. METHODS: In this work, we used a syngeneic orthotopic mouse model of breast cancer to determine the impact of doxycycline on circulating lysophosphatidate concentrations and tumor growth. Cytokine/chemokine concentrations in tumor tissue and plasma were measured by multiplexing laser bead technology. Leukocyte infiltration in tumors was analyzed by immunohistochemistry. The expression of IL-6 in breast cancer cell lines was determined by RT-PCR. Cell growth was measured in Matrigel™ 3D culture. The effects of doxycycline on NF-κB-dependent signaling were analyzed by Western blotting. RESULTS: Doxycycline decreased plasma lysophosphatidate concentrations, delayed tumor growth and decreased the concentrations of several cytokines/chemokines (IL-1β, IL-6, IL-9, CCL2, CCL11, CXCL1, CXCL2, CXCL9, G-CSF, LIF, VEGF) in the tumor. These results were compatible with the effects of doxycycline in decreasing the numbers of F4/80(+) macrophages and CD31(+) blood vessel endothelial cells in the tumor. Doxycycline also decreased the lysophosphatidate-induced growth of breast cancer cells in three-dimensional culture. Lysophosphatidate-induced Ki-67 expression was inhibited by doxycycline. NF-κB activity in HEK293 cells transiently expressing a NF-κB-luciferase reporter vectors was also inhibited by doxycycline. Treatment of breast cancer cells with doxycycline also decreased the translocation of NF-κB to the nucleus and the mRNA levels for IL-6 in the presence or absence of lysophosphatidate. CONCLUSION: These results contribute a new dimension for understanding the anti-inflammatory effects of tetracyclines, which make them potential candidates for adjuvant therapy of cancers and other inflammatory diseases.", "role": "user" }, { "content": "{\"Gene\": [\"CXCL2\", \"IL-9\", \"G-CSF\", \"CCL2\", \"VEGF\", \"CXCL9\", \"NF-\\u03baB\", \"CXCL1\", \"Ki-67\", \"IL-1\\u03b2\", \"CCL11\", \"LIF\", \"IL-6\"]}", "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\nIn this experiment, we compare our results with one of the most related exsiting works [31] using data mining method, in which the dynamics of information diffusion are predicted by", "role": "user" }, { "content": "Method", "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\nLearning effective text representations is a key foundation for numerous machine learning and NLP applications.\nWhile the celebrated Word2Vec technique yields semantically rich word representations, it is less clear whether sentence or document representations should be built upon word representations or from scratch.\nRecent work has demonstrated that a distance measure between documents called \\emph{Word Mover's Distance} (WMD) that aligns semantically similar words, yields unprecedented KNN classification accuracy.\nHowever, WMD is very expensive to compute, and is harder to apply beyond simple KNN than feature embeddings.\nIn this paper, we propose the \\emph{Word Mover's Embedding } (WME), a novel approach to building an unsupervised document (sentence) embedding from pre-trained word embeddings.\nOur technique extends the theory of \\emph{Random Features} to show convergence of the inner product between WMEs to a positive-definite kernel that can be interpreted as a soft version of (inverse) WMD.\nThe proposed embedding is more efficient and flexible than WMD in many situations.\nAs an example, WME with a simple linear classifier reduces the computational cost of WMD-based KNN \\emph{from cubic to linear} in document length and \\emph{from quadratic to linear} in number of samples, while simultaneously improving accuracy.\nIn experiments on 9 benchmark text classification datasets and 22 textual similarity tasks the proposed technique consistently matches or outperforms state-of-the-art techniques, with significantly higher accuracy on problems of short length.", "role": "user" }, { "content": "A novel approach to building an unsupervised document (sentence) embeddings from pre-trainedword embeddings", "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\nPolymorphisms of ADORA2A modulate psychomotor vigilance and the effects of caffeine on neurobehavioural performance and sleep EEG after sleep deprivation . BACKGROUND AND PURPOSE Prolonged wakefulness impairs sustained vigilant attention , measured with the psychomotor vigilance task ( PVT ) , and induces a compensatory increase in sleep intensity in recovery sleep , quantified by slow-wave activity ( SWA ) in the sleep electroencephalogram ( EEG ) . These effects of sleep deprivation are counteracted by the adenosine receptor antagonist caffeine , implying involvement of the adenosine neuromodulator/receptor system . To examine a role for adenosine A ( 2A ) receptors , we investigated whether variation of the A ( 2A ) receptor gene ( ADORA2A ) modified effects of caffeine on PVT and SWA after sleep deprivation . EXPERIMENTAL APPROACH A haplotype analysis of eight single-nucleotide polymorphisms of ADORA2A was performed in 82 volunteers . In 45 young men carrying five different allele combinations , we investigated the effects of prolonged waking and 2 × 200 mg caffeine or 2 × 100 mg modafinil on psychomotor vigilance , sleepiness , and the waking and sleep EEG . KEY RESULTS Throughout extended wakefulness , the carriers of haplotype HT4 performed faster on the PVT than carriers of non-HT4 haplotype alleles . In haplotype HT4 , caffeine failed to counteract the waking-induced impairment of PVT performance and the rebound of SWA in recovery sleep . However , caffeine was effective in non-HT4 allele carriers , and modafinil reduced the consequences of prolonged waking , independently of ADORA2A haplotype . CONCLUSIONS AND IMPLICATIONS Common genetic variation of ADORA2A is an important determinant of psychomotor vigilance in rested and sleep-deprived state . It also modulates individual responses to caffeine after sleep deprivation . These findings demonstrate a role for adenosine A ( 2A ) receptors in the effects of prolonged wakefulness on vigilant attention and the sleep EEG .", "role": "user" }, { "content": "{\"Intervention\": [\"caffeine\", \"sleep deprivation\"], \"Outcome\": [\"psychomotor vigilance task ( PVT )\", \"neurobehavioural performance and sleep EEG\", \"slow-wave activity ( SWA )\", \"vigilant attention\", \"sleep electroencephalogram ( EEG )\", \"SWA\", \"PVT\"], \"Participant\": [\"men\", \"82\", \"prolonged waking and 2 \\u00d7 200 mg caffeine or 2 \\u00d7 100 mg modafinil on psychomotor\", \"young\", \"Polymorphisms of ADORA2A modulate psychomotor vigilance\", \"five different allele combinations\", \"45\"]}", "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 pierre auger observatory measures cosmic rays within an area of 3000 @xmath0 .\nthe design calls for 1660 water - cherenkov detectors , arranged on a triangular grid , with the sides of the triangles measuring 1.5 @xmath1 , overlooked by four optical stations , each containing six telescopes , designed to detect air - fluorescence light ( fig .\n1 ) . the water - tanks(stations ) respond to the particle component ( mainly muons , electrons and positrons ) and the fluorescence cameras measure the emission from atmospheric nitrogen that is excited by the charged particles of the shower as they traverse the atmosphere .\nboth techniques , already used for many years to study extensive air showers , are brought together in a ` hybrid ' detector to observe showers simultaneously with different techniques[1 ] .\nthe array of water - tanks is known as the surface detector ( sd ) while the optical stations form the fluorescence detector , are known as fluorescence detector ( fd ) .\n+ * figure 1 . * representation of air - shower and current status of the pierre auger observatory .\nthe goal of this work is to observe the effects of direct light in the tanks which conform the sd , as well as their evolution as a function of time .\nthe change in time could provide information on the physical state of each tank .\nsuch information can be also used for studying possible systematic effects in the measurements made by the sd .\neach sd is a cylindrical water tank with @xmath2 of pure water .\nit has a cross section of @xmath3 , a diameter of @xmath4 and a depth of @xmath5 ( see figures 2 and 3 ) . the @xmath6 tanks of the sd are separated 1.5 km from each other . when an ultra - relativistic cr crosses the tank , it produces cherenkov light , that is measured by three photomultipliers ( pmts ) located on the top of each tank .\neach pmt has @xmath7 of diameter , these are photonis xp1805 .\nthe pmts are looking to the water , separated a distance of @xmath8 from the center of the tank , having a @xmath9 of difference in azimuthal angle from each other ( see figure 4 ) .\nthe direct light coming to each pmt is conditioned by the azimuthal angle of the arrival direction the particle which produced the light has . if the light arrives with the same azimuthal angle as the one a certain pmt has , then , the measurement made by that pmt will be higher than the one made by the other two .\nsuch effect can be observed in a graph showing the signal as a function of azimuthal angle , which present a different maximum and phase for each pmt , as is shown in graphs 1 to 4 [ 2 ] .\n+ * figure 4 . * pmt positions on the top of the tank .\na selection of tanks which have been working properly and more or less continuously over time , during the period from 2004 to 2013 , has been made .\nalso quality cuts for events detected are requested to guarantee that the measurement corresponds to a well reconstructed event .\nthe results shown in this document are obtained from the analysis of a tank named `` mariana '' with number i d 338 , which presented an event amount of 5673 .\n+ each pmt data is plotted as a function of azimuth angle , and an approximation of the signal from each pmt is performed by adjusting a sine function of the azimuth angle with the form : @xmath10 with @xmath11 for the pmt1 .\n@xmath12 for pmt2 and @xmath13 for pmt3 .\n+ * graph 1 .\n* amplitude 0@xmath14 - 60@xmath14 .\nthree zenith angle ranges , having the same solid angle , are considered : @xmath15 .\nthe corresponding results , showing the azimuthal effect are shown in graphs 2 to 4 .\n+ * graph 2 . * amplitude 0@xmath14 - 34@xmath14 .\n+ + * graph 4 .\n* amplitude 48@xmath14 - 60@xmath14 .\nthe amplitudes of each pmt are plotted as a function of zenith angle .\nthe corresponding line is fitted with a function of the form : @xmath16 results for pmt 1 , pmt 2 and pmt 3 are shown in graphs 5 -7 .\n* graph 5 .\n* amplitude adjustment for the pmt1 .\n+ + * graph 7 . * amplitude adjustement for the pmt3 . in order to obtain only one characteristic line for each detector ,\nthe amplitudes for each pmt at a certain zenith angle are averaged and plotted as shown in graph 8 .\nthen a new linear fit is performed resulting in the corresponding characteristic line .\n+ * graph 8 .\ncharacteristic line of the station .\n* once the characteristic line of the station was obtained for the whole period of time , its change in time is to be explored .\nthe same study has to be done for three different periods in order to compare the corresponding characteristic lines .\nthis is work in progress .\nfrom graphs 1 - 4 , it can be seen that the effect of direct light is effectively present for each pmt of of one station in the sd . a characteristic line ,\nfor the station studied was found .\nthe next step is to explore signals of the same tank for different time periods in order to study a possible change of the characteristic line as a function of time . if some change is found , its impact in the measured signal has to be studied .\nthe same kind of study must also be performed for other tanks .\n* to conacyt for the support given by the project cb 243290 .\n* to loral mexico , conacyt , unesco , conalmex and amc fort the support granted through the fellowship for women in science 2014 to karen salom caballero mora .\n* the pierre auger collaboration , arxiv:1604.03637v1 , astroph - im , the pierre auger observatory upgrade preliminary design report ( 2016 ) . * k.s .\ncaballero - mora , l. nellen and j.f .\nvaldes - galicia .\n_ azimuthal signal variations in the engineering array of the pierre auger observatory_. revista mexicana de fsica ag 2008 54 ( 4 ) 306 - 313", "role": "user" }, { "content": "cosmic rays ( cr ) are particles which come to the earth from universe \n . their origin and production mechanisms are still unknown . \n the pierre auger observatory is located in mendoza , argentina . \n it is dedicated to the study of cr . \n when cr arrive to the earth s atmosphere they produce a shower of secondary particles called _ air shower_. the surface detector ( sd ) of the pierre auger observatory consists of tanks full of pure water , where cr produce _ cherenkov radiation _ , when going through them . \n this light is detected by three photomultiplier tubes ( pmt ) located on the top of each tank . \n depending of the angle of arrival direction of the primary cr , each pmt is able to register different signal than the other . \n the goal of this study is to look at these effects of direct light on the pmt s to explore if they change in time . \n the obtained results may give information about the physical status of the tanks in order to monitor the work of the sd , and to estimate possible systematic effects on the measurements . \n the current results of this study are shown .", "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:\nModern microarchitectures are some of the world's most complex man-made systems. As a consequence, it is increasingly difficult to predict, explain, let alone optimize the performance of software running on such microarchitectures. As a basis for performance predictions and optimizations, we would need faithful models of their behavior, which are, unfortunately, seldom available. In this paper, we present the design and implementation of a tool to construct faithful models of the latency, throughput, and port usage of x86 instructions. To this end, we first discuss common notions of instruction throughput and port usage, and introduce a more precise definition of latency that, in contrast to previous definitions, considers dependencies between different pairs of input and output operands. We then develop novel algorithms to infer the latency, throughput, and port usage based on automatically-generated microbenchmarks that are more accurate and precise than existing work. To facilitate the rapid construction of optimizing compilers and tools for performance prediction, the output of our tool is provided in a machine-readable format. We provide experimental results for processors of all generations of Intel's Core architecture, i.e., from Nehalem to Coffee Lake, and discuss various cases where the output of our tool differs considerably from prior work.\n\nCited Abstract(s):\n[1]: We describe LLVM (low level virtual machine), a compiler framework designed to support transparent, lifelong program analysis and transformation for arbitrary programs, by providing high-level information to compiler transformations at compile-time, link-time, run-time, and in idle time between runs. LLVM defines a common, low-level code representation in static single assignment (SSA) form, with several novel features: a simple, language-independent type-system that exposes the primitives commonly used to implement high-level language features; an instruction for typed address arithmetic; and a simple mechanism that can be used to implement the exception handling features of high-level languages (and setjmp longjmp in C) uniformly and efficiently. The LLVM compiler framework and code representation together provide a combination of key capabilities that are important for practical, lifelong analysis and transformation of programs. To our knowledge, no existing compilation approach provides all these capabilities. We describe the design of the LLVM representation and compiler framework, and evaluate the design in three ways: (a) the size and effectiveness of the representation, including the type information it provides; (b) compiler performance for several interprocedural problems; and (c) illustrative examples of the benefits LLVM provides for several challenging compiler problems.", "role": "user" }, { "content": "The instruction scheduling components of LLVM [1] for the Sandy Bridge, Haswell, Broadwell, and Skylake microarchitecture were recently updated and extended with latency and port usage information that was, according to the commit message ( https: reviews.llvm.org rL307529 ), provided by the architects of these microarchitectures. The resulting models are available in the LLVM repository.", "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\nThe goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks.\nHowever, despite the proliferation of such methods there is currently no study of their robustness to adversarial attacks.\nWe provide the first adversarial vulnerability analysis on the widely used family of methods based on random walks.\nWe derive efficient adversarial perturbations that poison the network structure and have a negative effect on both the quality of the embeddings and the downstream tasks.\nWe further show that our attacks are transferable since they generalize to many models, and are successful even when the attacker is restricted.\nUnsupervised node embedding (network representation learning) approaches are becoming increasingly popular and achieve state-of-the-art performance on many network learning tasks BID5 .\nThe goal is to embed each node in a low-dimensional feature space such that the graph's structure is captured.\nThe learned embeddings are subsequently used for downstream tasks such as link prediction, node classification, community detection, and visualization.\nAmong the variety of proposed approaches, techniques based on random walks (RWs) (Perozzi et al.; Grover & Leskovec) are highly successful since they incorporate higher-order relational information.\nGiven the increasing popularity of these method, there is a strong need for an analysis of their robustness.\nIn particular, we aim to study the existence and effects of adversarial perturbations.\nA large body of research shows that traditional (deep) learning methods can easily be fooled/attacked: even slight deliberate data perturbations can lead to wrong results BID17 BID28 BID6 BID12 BID26 BID10 .So\nfar, however, the question of adversarial perturbations for node embeddings has not been addressed. This\nis highly critical, since especially in domains where graph embeddings are used (e.g. the web) adversaries are common and false data is easy to inject: e.g. spammers might create fake followers on social media or fraudsters might manipulate friendship relations in social networks. Can\nnode embedding approaches be easily fooled? The\nanswer to this question is not immediately obvious. On\none hand, the relational (non-i.i.d.) nature of the data might improve robustness since the embeddings are computed for all nodes jointly rather than for individual nodes in isolation. On\nthe other hand, the propagation of information might also lead to cascading effects, where perturbations in one part of the graph might affect many other nodes in another part of the graph.Compared to the existing works on adversarial attacks our work significantly differs in various aspects. First\n, by operating on plain graph data, we do not perturb the features of individual instances but rather their interaction/dependency structure. Manipulating\nthe structure (the graph) is a highly realistic scenario. For example,\none can easily add or remove fake friendship relations on a social network, or write fake reviews to influence graph-based recommendation engines. Second, the\nnode embedding works are typically trained in an unsupervised and transductive fashion. This means\nthat we cannot rely on a single end-task that our attack might exploit to find appropriate perturbations, and we have to handle a challenging poisoning attack where the model is learned after the attack. That is, the\nmodel cannot be assumed to be static as in most other adversarial attack works. Lastly, since\ngraphs are discrete classical gradient-based approaches BID28 for finding adversarial perturbations that were designed for continuous data are not well suited. Particularly\nfor RW-based methods, the gradient computation is not directly possible since they are based on a non-differentiable sampling procedure. How to design\nefficient algorithms that are able to find adversarial perturbations in such a challenging -discrete and combinatorial -graph domain?We propose a principled\nstrategy for adversarial attacks on unsupervised node embeddings. Exploiting results from\neigenvalue perturbation theory BID35 we are able to efficiently solve a challenging bi-level optimization problem associated with the poisoning attack. We assume an attacker with\nfull knowledge about the data and the model, thus, ensuring reliable vulnerability analysis in the worst case. Nonetheless, our experiments\non transferability demonstrate that our strategy generalizes -attacks learned based on one model successfully fool other models as well.Overall, we shed light on an important problem that has not been studied so far. We show that node embeddings\nare sensitive to adversarial attacks. Relatively few changes are needed\nto significantly damage the quality of the embeddings even in the scenario where the attacker is restricted. Furthermore, our work highlights\nthat more work is needed to make node embeddings robust to adversarial perturbations and thus readily applicable in production systems.\nWe demonstrate that node embeddings are vulnerable to adversarial attacks which can be efficiently computed and have a significant negative effect on node classification and link prediction.\nFurthermore, successfully poisoning the system is possible with relatively small perturbations and under restriction.\nMore importantly, our attacks generalize -the adversarial edges are transferable across different models.\nFuture work includes modeling the knowledge of the attacker, attacking other network representation learning methods, and developing effective defenses against such attacks.", "role": "user" }, { "content": "Adversarial attacks on unsupervised node embeddings based on eigenvalue perturbation theory.", "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: Hand dryers, a hot bath, and cold weather or snow are not effective in killing the new coronavirus.\n\nAbstract:\nThe spatial distribution of the COVID-19 infection in China cannot be explained solely by geographical distance and regulatory stringency.\nIn this research we investigate how meteorological conditions and air pollution, as concurring factors, impact COVID-19 transmission, using data on new confirmed cases from 219 prefecture cities from January 24 to February 29, 2020.\nResults revealed a kind of nonlinear dose-response relationship between temperature and coronavirus transmission.\nWe also found that air pollution indicators are positively correlated with new confirmed cases, and the coronavirus further spreads by 5-7% as the AQI increases by 10 units.\nFurther analysis based on regional divisions revealed that in northern China the negative effects of rising temperature on COVID-19 is counteracted by aggravated air pollution.\nIn the southern cities, the ambient temperature and air pollution have a negative interactive effect on COVID-19 transmission, implying that rising temperature restrains the facilitating effects of air pollution and that they jointly lead to a decrease in new confirmed cases.\nThese results provide implications for the control and prevention of this disease and for the anticipation of another possible pandemic.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "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:\nToresolvethisquestion,wehavenowknockedouttheCapn2geneencodingthem-80ksubunitinmice.", "role": "user" }, { "content": "[]", "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 want to train a supervised model for multi-person 2D human pose\n\nKeyphrases: 2d human pose estimation video\n\nDataset description:\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.\nLIP: The LIP (Look into Person) dataset is a large-scale dataset focusing on semantic understanding of a person. It contains 50,000 images with elaborated pixel-wise annotations of 19 semantic human part labels and 2D human poses with 16 key points.\nMuPoTS-3D: MuPoTs-3D (Multi-person Pose estimation Test Set in 3D) is a dataset for pose estimation composed of more than 8,000 frames from 20 real-world scenes with up to three subjects. The poses are annotated with a 14-point skeleton model.\nMannequinChallenge: The MannequinChallenge Dataset (MQC) provides in-the-wild videos of people in static poses while a hand-held camera pans around the scene. The dataset consists of three splits for training, validation and testing.\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.\nPoseTrack: The PoseTrack dataset is a large-scale benchmark for multi-person pose estimation and tracking in videos. It requires not only pose estimation in single frames, but also temporal tracking across frames.\n\nOptions:- A: COCO B: LIP C: MuPoTS-3D D: MannequinChallenge E: Market-1501 F: PoseTrack", "role": "user" }, { "content": "[\"COCO\", \"Market-1501\"]", "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: Sensitivity Analysis of Intracellular Signaling Pathway Kinetics Predicts Targets for Stem Cell Fate Control\nArticle:\nAbstract:\nDirecting stem cell fate requires knowledge of how signaling networks integrate temporally and spatially segregated stimuli. We developed and validated a computational model of signal transducer and activator of transcription-3( Stat3) pathway kinetics, a signaling network involved in embryonic stem cell( ESC) self-renewal. Our analysis identified novel pathway responses; for example, overexpression of the receptor glycoprotein-130 results in reduced pathway activation and increased ESC differentiation. We used a systematic in silico screen to identify novel targets and protein interactions involved in Stat3 activation. Our analysis demonstrates that signaling activation and desensitization( the inability to respond to ligand restimulation) is regulated by balancing the activation state of a distributed set of parameters including nuclear export of Stat3, nuclear phosphatase activity, inhibition by suppressor of cytokine signaling, and receptor trafficking. This knowledge was used to devise a temporally modulated ligand delivery strategy that maximizes signaling activation and leads to enhanced ESC self-renewal.\nIntroduction:\nSelf-renewal is one of the defining characteristics of embryonic stem cells( ESCs)[1]. This fate choice is influenced by ligand–receptor-mediated activation of intracellular signaling pathways. Significant work is being done to understand the signaling proteins and pathways that control self-renewal of ESCs, and an emerging picture is that these pathways influence self-renewal in a context-dependent and temporally modulated manner[2–4]. One such pathway is the Jak/Stat3( Janus kinase / signal transducer and activator of transcription-3) pathway[5]. Activation of Stat3 by phosphorylation at Tyr-705 results in induction of genetic programs that are sufficient for maintenance of self-renewal in mouse ESCs[6–8]. Understanding how Stat3 activation is controlled may be useful for controlling ESC self-renewal. Stat3 is activated by a variety of ligands from the interlukin-6( IL-6) –type family[9]. In mouse ESCs, Stat3 activation results from binding of leukemia inhibitor factor( LIF) to the LIF receptor and glycoprotein-130( GP130), forming a heterodimeric receptor complex[10, 11]. Jak-mediated Src homology-2( SH2) –domain phosphorylation of receptors leads to Stat3 recruitment to the receptor complex[12], and its Tyr-705 phosphorylation and subsequent nuclear accumulation[13–25]. This pathway is under control of three main inhibitors, protein inhibitor of activated Stat3( PIAS3), Src-2 homology containing phosphotyrosine phosphatase( SHP2), and suppressor of cytokine signaling( SOCS3). PIAS3 and SHP2 work to reduce Stat3 availability[26] and receptor activation[21, 24–26], respectively, and SOCS3, which is under transcription control of Stat3, inactivates activated receptors by binding to GP130[26, 27]. Activation of Stat3 is therefore influenced by a variety of intrinsic pathway components as well as receptor trafficking[28, 29]. Understanding how this signaling is controlled presents a challenge which may be best addressed by mathematical modeling[30]. Previous attempts to model the Jak/Stat pathway have either focused on steady state responses or on capturing the transient activation profile of the pathway to understand its kinetics[31–35]. Examining the transient activation profile provides a larger dynamic range of signal activation, and is therefore more amenable to experimental investigation. Although several models have made predictions about the role of different signaling processes in Stat activation, little work has been done to systematically understand how different signaling events contribute to pathway control, and to experimentally validate model predictions. Furthermore, a lack of computationally feasible algorithms for assessing the importance of pathway structure on signaling behavior has prevented an examination of the signaling consequences of all possible intrapathway interactions. To address this limitation, we developed an in silico model of the Jak/Stat3 pathway to computationally screen and classify parameter interactions for their effects on the transient activation profile of Stat3. In performing this global sensitivity analysis, we were able to predict and experimentally verify novel pathway dynamics such as a receptor-concentration–dependent switch in ligand sensitivity. Moreover, this approach allowed us to group pathway interactions into stimulatory- and inhibitory-signaling modules. By focusing our computational analysis on signaling kinetics, we were able to examine the consequence of pathway structure on the kinetics of ligand desensitization. These results led to predictive control of ESC self-renewal by modulating the frequency of ligand stimulation.\nDiscussion:\nThe Jak/Stat3 pathway, which is required for self-renewal of mouse ESCs, was modeled using a deterministic, lumped-parameter, differential-equation–based representation of mass action kinetics. Model-predicted trends of Stat3 activation and nuclear accumulation as well as Jak activation and SOCS3 expression were verified experimentally by quantitative imaging of adherent mouse ESCs. These results provided evidence for biological relevance of model predictions, and led to further investigation of pathway control. Transient Stat3 activation was used to understand how different signaling events influence pathway kinetics, and grouping of model parameter interactions determined the important intracellular signaling control modules. Sensitivity analysis of model parameters in isolation predicted that significant GP130 overexpression should reduce Stat3 activation. Experimental results of GP130 overexpressing cell lines confirmed predictions, showing decreased Stat3 activation with increased expression of GP130 receptors. Intact biological function of overexpressed receptors was confirmed by IL-6 stimulation of the cells. Based on model results, sequestering of LIFR by GP130 to form a nonsignaling heterodimer, which has been shown to exist transiently[12], can account for this behavior. Higher differentiation was observed in the highest GP130 overexpressing cell lines in the absence of LIF( Figure 4C). This response may be attributed either to reduced Stat3 activation from endogenously produced GP130 ligands[44] or possibly to increased activation of ERK by SHP2 through the GP130 receptors contributing to the response[25, 45]. Global sensitivity analysis of the system was performed by considering two parameter interactions; this approach covered the entire solution space of these interactions and provided a computationally feasible method to perform this analysis compared with previous attempts[31]. Clustering( Figure 5B) demonstrated how different parameters interact to yield similar effects. It is noteworthy that sets of inhibitory and stimulatory signaling interactions appeared distributed across the signaling network. Points of sensitivity may represent important nodes of crosstalk between pathways, and nonintuitive pathway behavior could arise from the alteration of seemingly innocuous parameters. These possibilities may in part account for the observation that conserved signaling pathways affect a variety of cell processes in a cell-type and context-dependent manner. A number of other signaling pathways have recently been implicated in ESC self-renewal; this analysis provides a first step toward understanding this signaling crosstalk. GSA results were verified experimentally by specifically targeting signaling steps for which specific inhibitors were available. The impact of a reduction in the rates of nuclear export of Stat3- and Jak-mediated receptor activation in isolation and in combination were determined experimentally and corroborated model predictions. Interaction of two targets, which clustered together in the GSA, SOCS3 induction and receptor production, was verified, demonstrating that they synergize similarly. Although this sensitivity analysis focused on Stat3 activation due to its importance to self-renewal of mouse ESCs; the same analysis could be performed for any protein in the signal transduction pathway( see Figure S10). Based on GSA, nuclear export of Stat3, nuclear phosphatase activity, and inhibition by SOCS3 were the most sensitive parameters for manipulating pathway output. Although other mechanisms of desensitization, in particular receptor desensitization or differential transport kinetics between phosphorylated and unphosphorylated receptors, are possible, our investigation points out a series of possible mechanisms through which desensitization can occur. More importantly, this approach allows for determination of importance of each mechanism to desensitization. Computational investigation of the dynamics of pathway desensitization to ligand stimulation was a particularly interesting application of GSA. In agreement with previous reports, SOCS3, but neither SHP2 nor PIAS3 kinetics, could account for pathway desensitization[26]. The phenomena of desensitization is an interesting feature of the Jak-Stat signaling pathway, which lends itself to a computational approach for identifying methods of circumventing this inhibitory behavior. To do this, we predicted the effects of two different ligand-dosing frequencies on Stat3 activation and examined their consequences on ESC fate. Although both sets of conditions were exposed to the same overall amount of LIF, the conditions with the LIF cycle period of 1 h retained a higher percentage of Oct4+ cells. Therefore, knowledge of dynamic pathway behavior such as desensitization can be used to identify nonintuitive targets or cell culture manipulations to control stem cell behavior. In summary, directing stem cell fate requires knowledge of how intracellular signaling can be controlled. To do this, we used a combined computational and experimental approach to study the kinetics of the Jak/Stat3 pathway in mouse ESCs. Although such mass action kinetics models can be improved, for example by including more detailed reaction mechanisms and interpathway interactions, this approach utilized herein provided us with an appropriate representation of the network dynamics and has allowed identification of interesting behaviors and properties of this signaling pathway. Modeling predicted novel effects of signaling( which were experimentally verified), and global sensitivity analysis led us to understand how this pathway is controlled. Based on computational predictions of desensitization kinetics, the self-renewal response of ESCs was modulated by controlling the frequency of ligand stimulation. This approach is useful for optimizing stem cell cultures by providing a ligand delivery regimen based on knowledge of intracellular signaling pathway kinetics. Our approach can be used to find key targets for control of intrapathway kinetics in stem cells. What is now required is to develop direct links between the nuclear concentration of activated Stat3 and cell fate decisions in individual cells. Ultimately, this requires insight into how cells convert graded stimuli into a threshold-based cell fate decision. Adapting the model presented herein to single cell signaling and integrating it with approaches to describe gene regulatory networks will yield a deep understanding of stem cell self-renewal.", "role": "user" }, { "content": "Directing stem cell fate requires knowledge of how intracellular signaling pathways integrate environmental stimuli to make decisions to stay as stem cells ( self-renew ) or to differentiate into specific functional cell types . We developed and validated a computational model of signal transducer and activator of transcription-3 ( Stat3 ) pathway kinetics , a signaling network involved in mouse embryonic stem cell ( ESC ) self-renewal . Our analysis demonstrates that stem cell fate control is regulated by a distributed set of parameters that positively and negatively regulate Stat3 activation . We further demonstrate that we can take advantage of differences in the timing of signaling pathway activation and inhibition to design a strategy to deliver self-renewal stimuli to stem cells in a more efficient manner . Ultimately , the use of stem cells in biotechnological applications will require an in-depth understanding of how cells integrate diverse environmental stimuli to make cell fate decisions .", "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 white mutation in Drosophila affecting?\n\nContext: The classic eye-color gene white (w) in Drosophila melanogaster (fruitfly) has unexpected behavioral consequences.\nWe conclude that beyond the classical eye-color phenotype, mutations in Drosophila white gene could impair several biological functions affecting parameters like mobility, life span and stress tolerance.", "role": "user" }, { "content": "Βeyond the classical eye-color phenotype, mutations in Drosophila white gene could impair several biological functions affecting parameters like mobility, life span and stress tolerance.", "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: Sequential recommendation aimsto accurately characterize users’ dynamic interestsby modeling their past behavior sequences (Rendle, 2010; Rendle et al., 2010; Kang and McAuley, 2018; Chen et al., 2021; Liet al., 2021a; Liuet al., 2021a).Early works on SR usually modelanitem-to-item transaction patternbased on MarkovChains (Rendle, 2010; He and McAuley, 2016).FPMC (Rendle et al., 2010)combines the advantages of Markov Chainsand matrix factorizationto fuse both sequential patternsand users’ general interest.With the recent advances of deep learning,many deep sequential recommendation modelsare also developed (Tang and Wang, 2018; Hidasi et al., 2015; Kang and McAuley, 2018; Sunet al., 2019). Such as Convolutional Neural Networks (CNN)-based (Tang and Wang, 2018) andRNN-based (Hidasi et al., 2015) models.The recent success of Transformer (Vaswani et al., 2017)also motivatesthe developments of pure Transformer-based SR models.SASRec (Kang and McAuley, 2018)utilizes unidirectional Transformerto assign weights to each interacted item adaptively.BERT4Rec (Sunet al., 2019) improves that byutilizing a bidirectional Transformerwith a Cloze task (Taylor, 1953)to fuse user behaviors information fromleft and right directions into each item.LSAN (Liet al., 2021a) improves SASRecon reducing model size perspective.It proposes a temporal context-aware embeddingand twin-attention network, which are light weighted.ASReP (Liuet al., 2021b) further alleviatesthe data-sparsity issueby leveraging a pre-trained Transformeron the revised user behavior sequences toaugment short sequences.In this paper, we study thepotential of addressing data sparsity issuesand improving SR via self-supervised learning.\n\nQuestion: Did the authors have an experiment showing the self-supervised learning can mitigate data sparsity issue?", "role": "user" }, { "content": "No, they do not.", "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: Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines\n\nIn this paper, we describe a methodology to infer Bullish or Bearish sentiment towards companies/brands. More specifically, our approach leverages affective lexica and word embeddings in combination with convolutional neural networks to infer the sentiment of financial news headlines towards a target company. Such architecture was used and evaluated in the context of the SemEval 2017 challenge (task 5, subtask 2), in which it obtained the best performance.\n\nIntroduction\nReal time information is key for decision making in highly technical domains such as finance. The explosive growth of financial technology industry (Fintech) continued in 2016, partially due to the current interest in the market for Artificial Intelligence-based technologies.\nOpinion-rich texts such as micro-blogging and news can have an important impact in the financial sector (e.g. raise or fall in stock value) or in the overall economy (e.g. the Greek public debt crisis). In such a context, having granular access to the opinions of an important part of the population is of key importance to any public and private actor in the field. In order to take advantage of this raw data, it is thus needed to develop machine learning methods allowing to convert unstructured text into information that can be managed and exploited.\nIn this paper, we address the sentiment analysis problem applied to financial headlines, where the goal is, for a given news headline and target company, to infer its polarity score i.e. how positive (or negative) the sentence is with respect to the target company. Previous research BIBREF0 has highlighted the association between news items and market fluctiations; hence, in the financial domain, sentiment analysis can be used as a proxy for bullish (i.e. positive, upwards trend) or bearish (i.e. negative, downwards trend) attitude towards a specific financial actor, allowing to identify and monitor in real-time the sentiment associated with e.g. stocks or brands.\nOur contribution leverages pre-trained word embeddings (GloVe, trained on wikipedia+gigaword corpus), the DepecheMood affective lexicon, and convolutional neural networks.\n\nRelated Works\nWhile image and sound come with a natural high dimensional embedding, the issue of which is the best representation is still an open research problem in the context of natural language and text. It is beyond the scope of this paper to do a thorough overview of word representations, for this we refer the interest reader to the excellent review provided by BIBREF1 . Here, we will just introduce the main representations that are related to the proposed method.\n\nData\nThe data consists of a set of financial news headlines, crawled from several online outlets such as Yahoo Finance, where each sentence contains one or more company names/brands.\nEach tuple (headline, company) is annotated with a sentiment score ranging from -1 (very negative, bearish) to 1 (very positive, bullish). The training/test sets provided contain 1142 and 491 annotated sentences, respectively.\nA sample instance is reported below:\nHeadline: “Morrisons book second consecutive quarter of sales growth”\nCompany name: “Morrisons”\nSentiment score: 0.43\n\nMethod\nIn Figure FIGREF5 , we can see the overall architecture of our model.\n\nSentence representation and preprocessing\nMinimal preprocessing was adopted in our approach: we replaced the target company's name with a fixed word <company> and numbers with <number>. The sentences were then tokenized using spaces as separator and keeping punctuation symbols as separate tokens.\nThe words are represented as fixed length vectors INLINEFORM0 resulting from the concatenation of GloVe pre-trained embeddings and DepecheMood BIBREF19 lexicon representation. Since we cannot directly concatenate token-based embeddings (provided in GloVe) with the lemma#PoS-based representation available in DepecheMood, we proceeded to re-build the latter in token-based form, applying the exact same methodology albeit with two differences: we started from a larger dataset (51.9K news articles instead of 25.3K) and used a frequency cut-off, i.e. keeping only those tokens that appear at least 5 times in the corpus.\nThese word-level representation are used as the first layer of our network. During training we allow the weights of the representation to be updated. We further add the VADER score for the sentence under analysis. The complete sentence representation is presented in Algorithm UID8 .\nInputInput OutputOutput The sentence embedding INLINEFORM0 INLINEFORM1 \n INLINEFORM0 in INLINEFORM1 INLINEFORM2 = [GloVe( INLINEFORM3 , INLINEFORM4 ), DepecheMood( INLINEFORM5 )] INLINEFORM6 Sentence representation\n\nArchitectural Details\nA 1D convolutional layer with filters of multiple sizes {2, 3, 4} is applied to the sequence of word embeddings. The filters are used to learn useful translation-invariant representations of the sequential input data. A global max-pooling is then applied across the sequence for each filter output.\nWe apply the concatenation layer to the output of the global max-pooling and the output of VADER.\nThe activation function used between layers is ReLU BIBREF24 except for the out layer where tanh is used to map the output into [-1, 1] range.\nDropout BIBREF25 was used to avoid over-fitting to the training data: it prevents the co-adaptation of the neurones and it also provides an inexpensive way to average an exponential number of networks. In addition, we averaged the output of multiple networks with the same architecture but trained independently with different random seeds in order to reduce noise.\nThe loss function used is the cosine distance between the predicted scores and the gold standard for each batch. Even though stochastic optimization methods like Adam BIBREF26 are usually applied to loss functions that are written as a sum of per-sample loss, which is not the case for the cosine, it converges to an acceptable solution. The loss can be written as : DISPLAYFORM0 \nwhere INLINEFORM0 and INLINEFORM1 are the predicted and true sentiment scores for batch INLINEFORM2 , respectively.\nThe algorithm for training/testing our model is reported in Algorithm UID15 .\nInputInput OutputOutput ParameterParameters A set of trained models INLINEFORM0 , and the predictions INLINEFORM1 for the test set INLINEFORM2 The number INLINEFORM3 of models to train INLINEFORM4 see sec 3.1 INLINEFORM5 in INLINEFORM6 INLINEFORM7 ) see Alg. UID8 INLINEFORM8 INLINEFORM9 see Eq. EQREF16 INLINEFORM10 INLINEFORM11 INLINEFORM12 Training/Testing algorithm. To build our model, we set N=10.\n\nResults\nIn this section, we report the results obtained by our model according to challenge official evaluation metric, which is based cosine-similarity and described in BIBREF27 . Results are reported for three diverse configurations: (i) the full system; (ii) the system without using word embeddings (i.e. Glove and DepecheMood); and (iii) the system without using pre-processing. In Table TABREF17 we show model's performances on the challenge training data, in a 5-fold cross-validation setting.\nFurther, the final performances obtained with our approach on the challenge test set are reported in Table TABREF18 . Consistently with the cross-validation performances shown earlier, we observe the beneficial impact of word-representations and basic pre-processing.\n\nConclusions\nIn this paper, we presented the network architecture used for the Fortia-FBK submission to the Semeval-2017 Task 5, Subtask 2 challenge, with the goal of predicting positive (bullish) or negative (bearish) attitude towards a target brand from financial news headlines. The proposed system ranked 1st in such challenge.\nOur approach is based on 1d convolutions and uses fine-tuning of unsupervised word representations and a rule based sentiment model in its inputs. We showed that the use of pre-computed word representations allows to reduce over-fitting and to achieve significantly better generalization, while some basic pre-processing was needed to further improve the performance.\n\nFigure 1: Network architecture\n\nTable 2: Final results\n\nTable 1: Cross-validation results\n\nQuestion: What embeddings do they use?", "role": "user" }, { "content": "{\"answer\": [\"GloVe\"], \"evidence\": [\"Our contribution leverages pre-trained word embeddings (GloVe, trained on wikipedia+gigaword corpus), the DepecheMood affective lexicon, and convolutional neural networks.\"]}", "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:\nunderstanding the origin and nature of galaxy scaling relations is a fundamental quest of any successful theory of galaxy formation .\nthe success of a particular theory will be judged by its ability to predict the slope , scatter , and zero - point of any robust galaxy scaling relation at any particular wavelength .\nthe scaling relations between rotation velocity , @xmath0 , size , @xmath1 , and luminosity , @xmath2 , are of special interest as they are linked via the virial theorem .\ncourteau ( 2007 ; hereafter c07 ) compiled a sample of 1303 disk galaxies for which accurate rotational velocities and near - infrared sizes and luminosities are available .\nwe refer the reader to c07 for details about this compilation .\nthe @xmath3 scaling relations for these galaxies are shown in fig . 1 .\nthe solid black lines in each panel show orthogonal linear fits to the combined data set , while the dashed lines show the @xmath4 scatter in these relations .\nthe points are color - coded according to central surface brightness .\nthis reveals the fundamental independence of surface brightness of the @xmath5 relation . as discussed in c07 ,\nthe @xmath5 relation is also independent of disk size and residuals from the size - luminosity relation .\nthis is unexpected , as the simplest models of galaxies embedded in dark matter halos predict a strong surface brightness dependence , unless disk galaxies are dominated by dark matter within their optical regions ( courteau & rix 1999 ; dutton 2007 ) .\ncosmological numerical simulations of galaxies have so far all encountered the same fundamental problem : model galaxies rotate too fast and are too compact compared to observed ones ( e.g. eke , navarro & steinmetz 2001 ; hereafter ens ) . whether this is the result of numerical artifacts or a reflexion of incomplete physics , or both , as yet to be resolved .\nhowever , the recent simulations by governato ( 2007 ; hereafter g07 ) would have , according to their authors , overcome difficulties of yester efforts and achieved a new breakthrough . quoting from their abstract : the @xmath5 relation has long been a benchmark test for hierarchical models of galaxy formation . in order to establish a fair comparison between observed and predicted scaling relations ,\nall the relevant parameters must be measured in a similar way between models and observations and drawn from comparable parent samples .\nrotational velocities from resolved rotation curves are typically measured at 2.2r@xmath6 , where r@xmath6 is the disk scale length ( courteau 1997 ) .\nthe total luminosity and @xmath7 are also typically measured from near - ir surface brightness profiles which probe the underlying stellar mass nearly free of extinction .\ng07 measured the rotation velocities of their model galaxies at 2.2 and 3.5 @xmath7 .\nbright disk galaxies have flat rotation curves beyond 2 - 3 @xmath7 and the specific choice of velocities matters little .\nthis would not be true for fainter galaxies whose rotation curves may keep rising up to the last data point .\nthe situation is backwards for g07 whose rotation curves for all 3 models show a steep inner rise and rapid decline in the outer regions .\ncare must thus be exercised when measuring a fiducial rotational velocity .\nfurthermore , g07 use @xmath8-band scale lengths which are , for their models , either twice as large or twice as small as the @xmath9-band scale lengths . as a result ,\ng07 measured @xmath10 either significantly within or beyond the actual maximum rotation velocities for their 3 model galaxies .\nobservations however show that @xmath8-band scale lengths are typically 20% greater than those at @xmath9 band ( de jong 1996 ) .\nthe wide range of @xmath11 disk scale lengths in g07 is thus unexpected .\ng07 state that _ `` at the resolution of our standard runs the total mass profile and the quantity of stars have converged at radii corresponding to a couple of disc scale lengths.''_. thus the rotation curves should be resolved at 2.2@xmath7 measured in the k - band . from their rotation curves we can estimate @xmath12165 , 280 , and 330 km s@xmath13 for the 3 model galaxies .\n1 shows that these new models create galaxies that fall more than @xmath4 off the vl relation .\n1 also shows the rl and rv relations , where we have used the k - band sizes from g07 .\nour data use i - band scale lengths , and so to make a fair comparison we have increased the model scale lengths by 0.05 dex ( de jong 1996 ) . nevertheless , g07 galaxies are too small by a factor @xmath14 for a given luminosity and by a factor @xmath15 for a given velocity , which again corresponds to @xmath4 offsets from the mean relations .\nthus a fair comparison between the models and data indicates that the g07 model galaxies suffer the same fate as previous cosmological simulations ( e.g. ens ) , namely that they rotate too fast and are too small .\nit should be noted however , that ens measured velocities at radii which enclosed essentially all of the cold baryons at @xmath16 . for the g07 simulations these radii correspond to 9 , 18 and 24 kpc . using rotation velocities measured at such large radii the g07 galaxies do indeed fall on the i - band , stellar mass and baryonic tf relations .\nthus , in this sense , the g07 simulations are an improvement over ens\n. however , the main challenge for galaxy formation models is to produce disk galaxies with the correct distributions of baryons and dark matter within the central few kpc . while g07 claimed that their simulations achieved this landmark , our analysis suggests the opposite .\nwe have so far dwelled on establishing fair data - model comparisons . perhaps of even greater relevance\nis whether the simulations are well enough resolved to warrant such an exercise .\ng07 claimed that their simulations have converged beyond one stellar disk scale length , which should be adequate for the extraction of reliable disk sizes and rotation velocities .\ng07 ran one of their models ( to z=0.5 ) increasing the number of particles eight - fold , up to 4.2 million particles .\nconvergence of the rotation curves between the two model galaxies differing only in the number of particles is only reached at @xmath17 kpc , corresponding to @xmath18 .\nthis raises concerns that the disk sizes and rotation velocities at @xmath19 have indeed not been adequately resolved .\nit is no surprise that these simulations , like most others at this writing , should have resolution problems .\nkaufmann ( 2007 ) showed that even with a million gas and dark matter particles , numerical effects result in spurious angular momentum losses , and this is for the idealized case of a galaxy growing in an isolated halo .\nfor a galaxy and halo growing hierarchically , even higher resolution is needed to resolve the progenitor galaxies and halos at high redshift .\ncurrent semi - analytical models ( sams ) of galaxy formation face a similar challenge as n - body realisations .\nforemost , sams also fail to match the zero point of the @xmath5 relation and the luminosity function of disk galaxies simultaneously ( see dutton and somerville in these proceedings for more discussion ) .\nearly sams did not model galaxy rotation curves and simply equated @xmath20 with the virial velocity of the halo , @xmath21 .\nmodern sams are often only marginally more sophisticated .\nfor example the galics sam ( hatton 2003 ) use an ad hoc function to relate @xmath20 to @xmath21 , while for the millennium sam , croton ( 2006 ) assume that @xmath20 is equal to the maximum circular velocity of the halo , _ prior _ to galaxy formation , which is only 10 to 20% larger than @xmath21 for typical halo concentrations ( e.g. bullock 2001 ) .\nthe galform sams of benson ( 2003 ) are most complete by including the effects of dissipating baryons and halo contraction . however , these authors measure @xmath20 at the disk half mass radius , corresponding to 1.68 @xmath7 for an exponential disk .\nobservational studies do not use rotation velocity measurements at such small radii since they are more susceptible to effects of inclination and non - circular motions . matching the zero point of the @xmath5 relation\nhas been a long - standing problem for hierarchical galaxy formation models , which may call for a departure from the standard theory of disk galaxy formation ( dutton 2007 ) , or even require a modification of cdm on small scales .", "role": "user" }, { "content": "the scaling relations between rotation velocity , size and luminosity form a benchmark test for any theory of disk galaxy formation . \n we confront recent theoretical models of disk formation to a recent large compilation of such scaling relations . \n we stress the importance of achieving a fair comparison between models and observations .", "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\nDehydroepiandrosterone post-transcriptionally modifies CYP1A2 induction involving androgen receptor. The pharmacological dosage of dehydroepiandrosterone (DHEA) protects against chemically induced carcinogenesis. The chemoprotective activity of DHEA is attributed to its inhibitory potential for the expression of CYP1A enzymes, which are highly responsible for metabolic activation of several mutagenic and carcinogenic chemicals. The present work investigated whether the chemoprevention by DHEA was due to diminished transcriptional activation of CYP1A genes or to the post-transcriptional modulation of CYP1A expression. In primary human hepatocytes, DHEA diminished the increase in CYP1A activities (7-ethoxyresorufin O-dealkylation and phenacetin O-dealkylation) and in CYP1A2 mRNA level induced by 3-methylcholanthrene, but did not alter the amount of CYP1A1 and CYP1B1 mRNA. The androgen receptor seemed to be involved in DHEA-mediated diminishment of CYP1A2 induction, which was attenuated in the presence of bicalutamide, the androgen receptor antagonist. The potential role of the glucocorticoid receptor and estrogen receptor in DHEA-mediated decrease in CYP1A2 induction was excluded. The developed computational model of CYP1A2 induction kinetics and CYP1A2 mRNA degradation proposed that a post-transcriptional mechanism was likely to be the primary mechanism of the DHEA-mediated diminishment of CYP1A2 induction. The hypothesis was confirmed by the results of actinomycin D-chase experiments in MCF-7 and LNCaP cells, displaying that the degradation rates of CYP1A2 mRNA were significantly higher in the cells exposed to DHEA. The novel findings on DHEA-mediated modulation of CYP1A2 mRNA stability may account for the beneficial effects of DHEA by decreasing the metabolic activation of pro-carcinogenic compounds.", "role": "user" }, { "content": "{\"Chemical\": [\"O\", \"dehydroepiandrosterone\", \"7-ethoxyresorufin\", \"phenacetin\", \"bicalutamide\", \"DHEA\", \"3-methylcholanthrene\", \"actinomycin D\", \"Dehydroepiandrosterone\", \"androgen\", \"estrogen\"]}", "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\nEarlier operations in the foot and leg, that is judged to complicate training\nknown arthritis.\nknown diabetes\nLeg ulcerations or infections in the foot.\nJudged unable to comply with the training protocol.\nDaily use of pain killers\nGlucocorticosteroid injection to the diseased achilles tendon within the last 6 months.\nEarlier allergic reactions to glucocorticosteroid or local anesthetic.\nPregnancy or planning to become pregnant\nBMI above 30.", "role": "user" }, { "content": "{\"Condition\": [\"allergic reactions\", \"pregnant\", \"diseased achilles tendon\", \"diabetes\", \"arthritis\", \"Leg ulcerations\", \"infections in the foot\", \"Pregnancy\"], \"Device\": [], \"Drug\": [\"pain killers\", \"local anesthetic\", \"Glucocorticosteroid\", \"glucocorticosteroid\"], \"Measurement\": [\"BMI\"], \"Mood\": [\"planning to become\"], \"Multiplier\": [\"Daily\"], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [\"injection\"], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [\"glucocorticosteroid or local anesthetic\"], \"Temporal\": [\"Earlier\", \"within the last 6 months\"], \"Value\": [\"above 30\"], \"Visit\": []}", "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: In vivo insertion pool sequencing identifies virulence factors in a complex fungal–host interaction\nArticle:\nAbstract:\nLarge-scale insertional mutagenesis screens can be powerful genome-wide tools if they are streamlined with efficient downstream analysis, which is a serious bottleneck in complex biological systems. A major impediment to the success of next-generation sequencing( NGS)-based screens for virulence factors is that the genetic material of pathogens is often underrepresented within the eukaryotic host, making detection extremely challenging. We therefore established insertion Pool-Sequencing( iPool-Seq) on maize infected with the biotrophic fungus U. maydis. iPool-Seq features tagmentation, unique molecular barcodes, and affinity purification of pathogen insertion mutant DNA from in vivo-infected tissues. In a proof of concept using iPool-Seq, we identified 28 virulence factors, including 23 that were previously uncharacterized, from an initial pool of 195 candidate effector mutants. Because of its sensitivity and quantitative nature, iPool-Seq can be applied to any insertional mutagenesis library and is especially suitable for genetically complex setups like pooled infections of eukaryotic hosts.\nIntroduction:\nVirulence factors are key for successful infections by pathogens. Their identification is of major interest because of the necessity to develop effective counter strategies. For instance, fungal virulence factors are typically identified by mutating single loci in fungi, followed by individual fungal mutant infections of host tissue and subsequent assessment of pathogen fitness[1–4]. Individual infection assays are not ideal for the genetic screening of a large number of pathogen mutants because they are laborious, cost-intensive, and—most importantly—assessment of infections is often subjective and qualitative rather than quantitative. An attractive alternative is infection with a pool of pathogen mutants allowing direct assessment of individual pathogen fitness in the same host tissue. However, using a pooled pathogen infection creates the challenge of identifying pathogens with reduced virulence within a complex mixture of genetic material extracted from infected host tissue. Mutant collections can be efficiently generated using insertional mutagenesis. Insertional mutagenesis employs gene cassettes that commonly comprise a selectable marker under the control of a strong constitutive promoter. The detection of genome–cassette junctions can serve as a molecular identifier for each insertion mutant. During screening, insertional mutants before selection in the host are defined as the genetic input, whereas surviving insertional mutants after selection comprise the genetic output. Insertional mutagenesis can be achieved randomly through transposon insertion[5–8] or Agrobacterium tumefaciens-mediated transformation[3, 9], or specifically through site-specific insertion by homologous recombination[10, 11]. Over the last decade, several approaches were established that use massive parallel sequencing for the detection of inserted gene cassettes. These approaches were successfully used to track mutants from the small genomes of prokaryotic pathogens and allowed the identification of bacterial genes involved in virulence or host colonization after pooled infections[12–16]. However, only a few attempts were reported that identified virulence factors using pools of eukaryotic pathogens[17]. The main factors limiting the successful insertional mutagenesis of eukaryotic pathogens by pooled infections in complex host-pathogen systems are variable infection rates of individually mutated pathogens, the size ratio of host/pathogen genomes, the inability to sufficiently detect inserted gene cassettes from pathogenic material, and biases that arise through PCR-based amplification steps. To enable successful and quantitative insertion mutant screen-based identification of virulence factors in complex biological systems, we developed insertion Pool-Sequencing( iPool-Seq). We determined the sensitivity and efficiency of iPool-Seq using an insertion mutant collection of 195 predicted virulence factors encoded by the maize pathogen U. maydis. The haploid U. maydis genome consists of approximately 20. 5 megabases[18, 19], whereas the diploid genome of maize is 2. 3 gigabases large[20]. This represents a 100-fold genome size difference, which is beside the proportion between fungal and host plant genome abundance as a limiting factor, making the robust detection of U. maydis sequence information in infected maize tissue necessary. The iPool-Seq workflow consists of Tn5 Transposase-mediated tagmentation of complex genomic DNA( gDNA) allowing efficient library preparation from low-input material[21, 22]. This is followed by the efficient enrichment of extremely rare insertion cassettes from fungal genomes using biotin-streptavidin affinity purification of PCR products. Amplification biases are monitored through incorporated unique molecular identifiers( UMIs). Insertional mutant fitness within host tissues is directly measured through quantification of UMI counts present in infected output material compared to UMI counts from the input library. iPool-Seq on U. maydis infections of maize confirmed the identity of 5 known fungal virulence factors that were included as positive controls in the screen. Importantly, 23 previously unreported virulence factors encoded by U. maydis were uncovered. Three of these factors were confirmed to be novel virulence factors of U. maydis after testing by individual infection. The combination of pooled insertion mutant infections and iPool-Seq technology represents a straightforward and cost-effective approach to map insertion mutants in complex host–pathogen systems with the potential to generate genome-wide virulence maps of relevant crop pathogens and beyond.\nDiscussion:\nPooled mutant screens have proven to be very powerful tools to uncover individual genes affecting particular phenotypes in a time- and cost-effective fashion. Positive selection screens usually lead to limited numbers of individual surviving cells that are easily identifiable by a combination of restriction enzyme digests, inverse PCR, and sequencing. Negative selection screens rely on the survival of most analyzed cells, making it necessary to devise methodology that allows comparing the presence/absence of genetic information before and after selection. To tackle the later challenge, several insertional mutagenesis approaches have been developed[31]. Although successful in bacterial systems for the elucidation of virulence factors[5, 13, 32], such insertion mutant approaches were not widely used in eukaryotic systems, mainly because of unresolved technical issues such as low sensitivity and system-intrinsic limitations( for example, genome ploidy, lifestyle of the investigated model system). Here, we introduce iPool-Seq as a versatile and highly sensitive method for the analysis of insertion mutant pools before and after selection, enabling both negative and positive mutant selection screens in complex eukaryotic systems including the analysis of host–pathogen interactions. We used iPool-Seq to examine virulence factors from a defined set of mutants of the crop fungus U. maydis, both confirming known factors and identifying novel ones. From the predicted mutant collection we used, most mutants were not significantly depleted from the output reads, indicating no function in virulence for the underlying genes. However, the role of some factors could be difficult to decipher, for example, because their action could be covered by functional redundancy of other virulence factors. Although we infected insertion mutants in dense pools, depleted insertional mutants appeared not to be affected by in trans complementation, by using the secreted factors of neighbouring fungal cells for example. Nevertheless, it cannot be excluded that, for certain gene products, in trans complementation could occur and mask the virulence defect of the respective mutant in a pooled infection setup. In conclusion, negative depletion screens have limitations to decipher redundancy and potential in trans complementation of virulence factors. In addition, we did not identify significantly enriched mutants in the iPool-Seq analysis of the mutant collection. A significant enrichment of output reads would indicate the loss of a negative regulator of virulence. A possible reason that we did not find enrichment could be our choice of the maize accession, EGB, which is highly susceptible to the U. maydis strain SG200. Microscopy of U. maydis strain SG200 infecting maize tissue implies that many cells fail to penetrate the host[28]. In very complex insertion mutant libraries, this large individual failure rate could lead to the loss of mutants that lack any real defect in virulence. Therefore, for genome-wide virulence maps of U. maydis and similar biotrophic pathogens, the size of the insertion mutant pool must be individually adapted to the infection rate of the respective pathogen. To overcome this problem, genome-wide screens might need to be performed in subpools, as it has been done in a previous study with the fungal pathogen Cryptococcus neoformans[11]. iPool-Seq uses insertion cassette–specific primers to amplify the genomic insertion junctions from a mutant pool[17]. Additionally, iPool-Seq enriches for PCR products by using biotin/streptavidin interaction, an approach that has previously been used in bacterial transposon integration site identification methods such as high-throughput insertion tracking by deep sequencing( HITS)[5]. Importantly, UMIs in the adapter primer allow in silico elimination of PCR biases. The unique barcode identifiers additionally overcome cluster position identification problems during Illumina sequencing that would otherwise occur when the first bases from the insertion flank would otherwise be identical for all mutant loci. Dark cycle sequencing, as used in Quantitative insertion-site sequencing( QIseq) for example, is therefore unnecessary[17]. iPool-Seq was established using a defined insertion mutant collection of U. maydis. However, the technology can be adapted to any insertion mutant collection, such as transposon or A. tumefaciens-derived T-DNA libraries[33, 34]. The modeling of the iPool-Seq sensitivity indicates that iPool-Seq meets all premises to work for high-throughput. Therefore, iPool-Seq promises to be a versatile technology for reanalysis of existing knock-in, activation-tagging, or transposon-insertion libraries, dramatically reducing labor costs for selection screens when compared to classical scoring approaches. Additionally, the relatively low costs of iPool-Seq for broad screens could also foster research in less funded emerging model systems. Due to the strong enrichment of insertion gene cassettes, the sequencing depth and costs of iPool-Seq are low. Thus, this technology will enable researchers to test diverse new selection criteria to efficiently build genotype–phenotype relationships. This will help to fill the knowledge gap that is currently still hampering research as exemplified for the well annotated U. maydis genome with 6, 786 protein-encoding genes, of which 41. 5% are in the category unknown[35]. Moreover, even if genes are annotated, their involvement in various biological processes might, simply, not yet be known. From the candidate virulence factors that we identified with iPool-Seq, we chose 3 for verification and confirmed their virulence defect by classical scoring of disease symptoms. However, the assessment of disease symptoms is indirect, and discrepancies between the two methods might occur for other novel virulence factors. We speculate that the U. maydis genome encodes virulence factors whose mutants show reduced proliferation but still cause full disease symptoms based on qualitative measures. In line with this, the iPool-Seq data did not show significant depletions for two mutants that were previously reported with mild defects in symptom induction[24]. In contrast to these disease ratings, iPool-Seq has the potential to identify virulence factors that do not have an obvious effect on symptom formation on a genome-wide level. In summary, we have demonstrated the functional genomic technology iPool-Seq by identifying both known and novel virulence factors from pooled infection assays of a biotrophic fungus within a complex host background. iPool-Seq is therefore a sensitive in vivo tool for researchers to help fill the genotype–phenotype gap in the post-genomic era.", "role": "user" }, { "content": "Insertion mutant screens are widely used to identify genotype–phenotype relationships . In negative selection screens , a major limitation is the efficient identification of mutants that are lost or retained after selection . To identify these mutants , the two genomic sequences flanking the insertion cassette must be found . However , pinpointing these insertion flanks within a genome is like looking for a needle in a haystack; a problem that becomes even worse when several organisms form a biotrophic interaction . To overcome this hurdle , we developed insertion Pool-Sequencing ( iPool-Seq ) . With iPool-Seq , we were able to efficiently amplify and enrich insertion flanks from complex genomic DNA samples . This technique allows for the quantification of relative insertion mutant abundance before and after selection by next-generation sequencing ( NGS ) . We demonstrate the power of iPool-Seq with a negative selection screen by infecting maize with 195 candidate effector mutants of the fungal pathogen Ustilago maydis . We identified 28 virulence factors , of which 23 have not been previously described . iPool-Seq is extremely sensitive , cost- and time-efficient , and promises to be a powerful tool for identifying target genes in large selection screens .", "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:\nrecent results from reverberation - mapping of the broad emission - line regions ( blr ) in agn indicate that the blr distance from the central radiation source roughly scales as @xmath1 ( peterson 1995 ) .\nrecently we have elaborated a different method for estimating the blr distance , using the emission - line photoionization model . in order to explain the anticorrelation between the h@xmath2 line width and the soft x - ray spectral slope in narrow - line seyfert 1 galaxies ( nls1 ) ( boller , brandt and fink 1996 ; wang , brinkmann and bergeron 1996 ) , wandel and boller ( 1997 ) showed that a steeper spectrum would produce a blr at a relatively larger distance from the central source ,\nso the keplerian velocity is lower .\nthis modified blr distance calculated from the photoionization relation agrees well with the reverberation distance ( wandel 1996 ; 1997 ) . in this work\nwe connect this model to the r(blr ) @xmath3 relation by independently determining the central mass from the x - ray variability .\nif the emission lines are doppler - broadened by keplerian motion in the gravitational potential of the central mass , the full width at half maximum is given by : @xmath4 where m is the mass of the central black hole and r the radius of the emission line region .\nthe physical conditions in the ionized gas emitting the broad lines are characterized by the ionization parameter u , the ratio of ionizing photons to electrons @xmath5 where @xmath6 is the luminosity of the central source , per unit energy , @xmath7 is the electron density .\nthe radius of the blr may then be written as @xmath8 where @xmath9 is the ionizing luminosity , and @xmath10 is the mean energy of the ionizing photons .\ntypical values in agn clouds give @xmath11 ( cf .\nrees , netzer & ferland 1989 ) . for @xmath12\n( 2 ) gives @xmath13 where @xmath10 is in rydbergs .\nassuming the ionizing spectrum has a power - law shape with the spectral index of the soft x - ray band ( found e.g. from the rosat data ) , @xmath14 , gives the observed anti - correlation between the line width and the spectral index ( wandel and boller 1997 ) .\nwandel ( 1996 ; 1997 ) has shown that the blr radius calculated from eq .\n( 2 ) above does indeed agree well with the radius estimates available from reverberation calculations for about a dozen objects ( see kaspi et.al .\n1996 and these proceedings ) .\nwe present an independent derivation of the radius - luminosity relation , determining the mass from x - ray variability .\nan upper limit for the black hole mass is given by ( e.g. wandel & mushotzky 1986 ) @xmath15 where @xmath16 is in seconds .\nthis relation assumes that the bulk of the x - ray continuum is emitted within 5 schwarzschild radii . using the doubling time as the characteristic time for variability we determine upper limits for the black hole mass for those objects whose continuum luminosities\nhave been observed to vary significantly .\n1 gives the doubling time ( we have extrapolated amplitude variations linearly to a factor of 2 to determine @xmath16 ) versus the observed fwhm .\nalthough there is some scatter , there is a strong indication for an increase of the doubling time with observed fwhm .\nthis may indicate a relation between the central mass and the line width .\nwe may use eq .\n( 1 ) to establish an estimate for the blr radius calculated from the observed line width and x - ray variability , independent of the luminosity , which can test the r - l@xmath17 relation : @xmath18 note that this is an upper limit , as is eq . ( 4 ) .\nthe diamonds in figure 2 show the blr radius calculated from eq .\n( 5 ) vs. the x - ray luminosity for the objects in our sample with significant x - ray variability and a few objects from wandel and mushotzky ( 1986 ) .\nwe see that there is no correlation between r and l. on the other hand , as expected , the blr radius calculated from the photoionization model ( eq .\n3 ) shows a clear @xmath19 correlation ( circles in figure 2 ) , which is confirmed independently by reverberatiom mapping .\nlooking at figure 2 we may conclude that the x - ray variability method systematically overestimates the central mass for the low luminosity nls1 galaxies .", "role": "user" }, { "content": "we developed a new method of determination of the size of the broad emission - line region ( blr ) in active galactic nuclei . \n this method relates the radius of the broad - line region of agn to the soft x - ray luminosity and spectral index . comparing the blr distances calculated from our model to the blr distances determined by reverberation mapping \n shows that our scaling law agrees with the @xmath0 empirical relation . \n here we investigate a complimentary method of estimating the blr distance - based on the keplerian broadening of the emission lines and the central mass estimated from x - ray variability .", "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\nThe SARS-CoV-2 virus responsible for the COVID-19 pandemic can result in severe or fatal disease in a subset of infected patients. While the pathogenesis of severe COVID-19 disease has yet to be fully elucidated, an overexuberant and harmful immune response to the SARS-CoV-2 virus may be a pivotal aspect of critical illness in this patient population. The inflammatory cytokine, IL-6, has been found to be consistently elevated in severely ill COVID-19 patients, prompting speculation that IL-6 is an important driver of the pathologic process. The inappropriately elevated levels of inflammatory cytokines in COVID-19 patients is similar to cytokine release syndrome (CRS) observed in cell therapy patients. We sought to describe outcomes in a series of severely ill patients with COVID-19 CRS following treatment with anti-IL-6/IL-6-Receptor (anti-IL-6/IL-6-R) therapy, including tocilizumab or siltuximab. At our academic community medical center, we formed a multi-disciplinary committee for selecting severely ill COVID-19 patients for therapy with anti-IL-6 or IL-6-R agents. Key selection criteria included evidence of hyperinflammation, most notably elevated levels of C-reactive protein (CRP) and ferritin, and an increasing oxygen requirement. By the data cutoff point, we treated 31 patients with anti-IL-6/IL-6-R agents including 12 who had already been intubated. Overall, 27 (87%) patients are alive and 24 (77%) have been discharged from the hospital. Clinical responses to anti-IL-6/IL-6-R therapy were accompanied by significant decreases in temperature, oxygen requirement, CRP, IL-6, and IL-10 levels. Based on these data, we believe anti-IL-6/IL-6-R therapy can be effective in managing early CRS related to COVID-19 disease. Further study of anti-IL-6/IL-6-R therapy alone and in combination with other classes of therapeutics is warranted and trials are underway.", "role": "user" }, { "content": "[\"Treatment\"]", "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:\nTheEScellswerescreenedforhomologousrecombinationbyPCRwiththeforwardprimer,neoF(5'-GGGTCGTTTGTTCGGATCAA-3')fromneocassette,andreverseprimerintron6R(5'-ACCAGTTGGTCCTAGCTCGA-3'),whichislocatedoutsidethetargetingconstructinmouseAbcg8intron6.", "role": "user" }, { "content": "[]", "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: Protein structure and sequence reanalysis of 2019-ncov genome refutes snakes as its intermediate host and the unique similarity between its spike protein insertions and hiv-1 .\n\nAbstract:\nAs the infection of 2019-nCoV coronavirus is quickly developing into a global pneumonia epidemic, the careful analysis of its transmission and cellular mechanisms is sorely needed.\nIn this Communication, we first analyzed two recent studies that concluded that snakes are the intermediate hosts of 2019-nCoV and that the 2019-nCoV spike protein insertions share a unique similarity to HIV-1.\nHowever, the reimplementation of the analyses, built on larger scale data sets using state-of-the-art bioinformatics methods and databases, presents clear evidence that rebuts these conclusions.\nNext, using metagenomic samples from Manis javanica, we assembled a draft genome of the 2019-nCoV-like coronavirus, which shows 73% coverage and 91% sequence identity to the 2019-nCoV genome.\nIn particular, the alignments of the spike surface glycoprotein receptor binding domain revealed four times more variations in the bat coronavirus RaTG13 than in the Manis coronavirus compared with 2019-nCoV, suggesting the pangolin as a missing link in the transmission of 2019-nCoV from bats to human.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"In this Communication, we first analyzed two recent studies that concluded that snakes are the intermediate hosts of 2019-nCoV and that the 2019-nCoV spike protein insertions share a unique similarity to HIV-1.\"]}", "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: Both vitamin C and vitamin D have been implicated in boosting immune response.\n\nAbstract:\nOptimal nutrition can improve well-being and might mitigate the risk and morbidity associated with coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).\nThis review summarizes nutritional guidelines to support dietary counseling provided by dietitians and health-related professionals.\nThe majority of documents encouraged the consumption of fruits, vegetables, and whole grain foods.\nThirty-one percent of the guidelines highlighted the importance of minerals and vitamins such as zinc and vitamins C, A, and D to maintain a well-functioning immune system.\nDietary supplementation has not been linked to COVID-19 prevention.\nHowever, supplementation with vitamins C and D, as well as with zinc and selenium, was highlighted as potentially beneficial for individuals with, or at risk of, respiratory viral infections or for those in whom nutrient deficiency is detected.\nThere was no convincing evidence that food or food packaging is associated with the transmission of COVID-19, but good hygiene practices for handling and preparing foods were recommended.\nNo changes to breastfeeding recommendations have been made, even in women diagnosed with COVID-19.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"The majority of documents encouraged the consumption of fruits, vegetables, and whole grain foods.\", \"Thirty-one percent of the guidelines highlighted the importance of minerals and vitamins such as zinc and vitamins C, A, and D to maintain a well-functioning immune system.\", \"Dietary supplementation has not been linked to COVID-19 prevention.\", \"However, supplementation with vitamins C and D, as well as with zinc and selenium, was highlighted as potentially beneficial for individuals with, or at risk of, respiratory viral infections or for those in whom nutrient deficiency is detected.\"]}", "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:\nSynthesis of \\xce\\xb2-branched tryptophan analogs using an engineered subunit of tryptophan synthase\n\nPaper sections:\n\n<p>Amino acids possess a rich array of functionality that has made them ideal building blocks for complex molecular structures. In addition to the small set of amino acids that form the basis of naturally occurring proteins, nature has produced a myriad of non-canonical amino acids (ncAAs) that are non-proteinogenic, but are nonetheless prevalent in other classes of natural products.1 Chemists have applied both natural and artificial ncAAs in the development of chemical probes and asymmetric catalysts as well as industrial products such as agrochemicals and small-molecule pharmaceuticals.2 However, the efficient synthesis of ncAAs is notoriously challenging since it requires methods that can form the products in high enantioenrichment while tolerating their dense functionality.3 The difficulty is compounded with β-branched amino acids, which necessitate both enantio- and diastereoselective synthetic methods.4 As a result, access to these compounds often requires lengthy synthetic routes with the use of numerous protecting groups. Biocatalytic routes to ncAAs present an attractive alternative because they often feature exquisite stereoselectivity and do not require protecting groups. As such, there is continued demand for enzymes that can enable production of diverse ncAAs.</p><p>A striking example of an enzyme with a broad substrate scope is tryptophan synthase (TrpS), a pyridoxal phosphate (PLP)-dependent enzyme that catalyzes the condensation of indole (1) and l-serine (Ser, 2) to form l-tryptophan (Trp, 3, Figure 1a).5 It is well-precedented that TrpS can accept nucleophiles other than 1,6 but the only electrophiles that are known to replace 2 are amino acids such as l-cysteine and β-chloro-L-alanine, which lead to the same products as 2, albeit with diminished efficiency.7 This desirable reaction is catalyzed by the β-subunit (TrpB) of the αββα heteromeric enzyme complex, but further expansion of the substrate scope through protein engineering is complicated by the presence of the α-subunit (TrpA), without which the catalytic efficiency of TrpB is significantly attenuated.5 Recently, we used directed evolution of TrpB from the hyperthermophile Pyrococcus furiosus to create a variant, PfTrpB0B2, that maintains high catalytic efficiency outside of the native heteroenzyme complex.8 We explored the substrate scope of this stand-alone enzyme with the hypothesis that any promising activity could be optimized through further evolution for efficient production of ncAAs.</p><p>We tested analogs of 2 with PfTrpB0B2, with the goal of expanding the scope of substrates that can serve as electrophiles in this reaction manifold (Figure S1). In the course of this exploration we were pleased to discover that l-threonine (Thr, 4) could substitute for Ser to yield a single product that we determined to be (2S,3S)-β-methyltryptophan (β-MeTrp, 5, Figure 1b), corresponding to substitution with retention of configuration (Figure 2).9</p><p>To our knowledge, this reactivity is unprecedented for TrpB. While an analogous reaction has been reported for TrpS from Salmonella typhimurium, this required a substantially stronger nucleophile (benzyl mercaptan) to obtain even 1% of the activity relative to Ser, and the stereochemistry of the product was not determined.10 Compound 5 is valuable because it is an intermediate in the biosynthetic pathways to several natural products such as maremycin and the anti-tumor agent streptonigrin (Figure 1c).9,11 The chemical synthesis of 5 has excellent selectivity, but requires many chemical manipulations.12 Similarly, the biosynthesis of 5, which uses three enzymes in a 4-step pathway from 3 using S-adenosylmethionine as the methyl source,9,11 is unsuitable for large-scale production of 5 or its derivatives. The reaction reported here represents a significantly more efficient route to this valuable intermediate. We therefore sought to optimize the enzyme for this novel reaction using directed evolution.</p><p>To identify the best parent enzyme for subsequent engineering we first measured production of 5 using purified enzymes from each generation in the evolution of PfTrpB0B2. PfTrpBWT was an inefficient catalyst, performing just 66 turnovers in 24 hours (Table S1). This activity was enhanced approximately 6-fold with the single amino acid substitution T292S and further to ∼660 TTN with the enzyme PfTrpB4D11, which incorporates four additional mutations (E17G, I68V, F274S, and T321A). PfTrpB0B2 exhibited a decrease in activity with Thr (Table S1) compared to PfTrpB4D11, despite having higher activity with Ser.8 We therefore selected PfTrpB4D11 as the parent for directed evolution.</p><p>Previous studies have shown that the catalytic activity of TrpB is governed by open-close transitions of the communication (COMM) domain,5,8 and mutations that alter this dynamic in the reactivated subunits are distributed throughout the protein structure.8 As such, we elected to apply random mutagenesis for the first round of evolution for activity with Thr. To determine an optimal mutational load we measured the retention of function of 352 clones from libraries with different mutation rates (Figure S2). In this process, we found six missense mutations in five clones with at least a 2-fold increase in Vmax, obviating the need for screening a more expansive library. The most active clone from this library, PfTrpB4G1, had ∼3.8-fold increased activity and contained the single mutation F95L, which abuts the COMM domain.</p><p>Notably, another activated variant contained two mutations, I16V and Q89L, of which the former is adjacent to the E17G mutation already present in the parent enzyme. These six mutations were randomly recombined and the resulting variants screened for activity, which resulted in the final variant PfTrpB2B9. Three mutations, F95L, I16V, and V384A, were retained in this enzyme, which is eight mutations away from wild type and has at least a 6,000-fold boost in productivity (Figure 3). This increase is in part due to an elevated expression level of soluble protein, from ∼80 mg PfTrpBWT per L medium to ∼350 mg of PfTrpB2B9.</p><p>To assess the basis of this new activity, we used UV-vis spectroscopy, which reports on the steady state distribution of the PLP-bound intermediates in the catalytic cycle (Figure 2). Addition of Ser to PfTrpBWT shifts λmax from 412 nm to 428 nm, corresponding to transimination of the lysine-bound internal aldimine, E(Ain), to a Ser-bound external aldimine, E(Aex1).8 Unexpectedly, addition of 20 mM Thr to PfTrpBWT did not result in any spectral shift indicative of Thr binding. However, this experiment cannot distinguish between Thr simply not binding or Thr binding non-covalently but not favoring formation of E(Aex1). We soaked Thr into crystals of PfTrpBWT, and diffraction yielded a 1.54-Å structure that shows Thr bound non-covalently (Figure 4a, Table S2). The Thr hydroxyl forms a 2.7-Å hydrogen bond with the sidechain of Asp300, an interaction that is also observed in the Ser E(Aex1). Modeling of a hypothetical Thr E(Aex1) that maintains the Asp300 hydrogen bond reveals a strong steric clash between the Thr methyl group and the backbone carbonyl of Gly298 (Figure S3), accounting for the lack of E(Aex1) observed by UV-vis spectroscopy.</p><p>UV-vis spectroscopy was used to probe the basis for enhanced activity through directed evolution. Addition of 20 mM Thr to the engineered proteins from each generation resulted in a clear trend (Figure 4b and S4): the 412 nm peak decreased while a new absorbance band at 350 nm with a broad shoulder out to 550 nm appeared, consistent with accumulation of the electrophilic amino-acrylate species E(A-A). A similar phenomenon was observed during directed evolution for independent TrpB function,8 however comparison of the Ser- and Thr-bound PfTrpB2B9 spectra indicates that E(A-A) with Thr is much less stable (Figure S5).</p><p>The engineered PfTrpB2B9 enzyme has several desirable features as a catalyst for β-MeTrp production. It is robustly expressed in E. coli, can be prepared in a moderately pure form as a heat-treated lysate (Figure S6), and its thermal stability permits high reaction temperatures, routinely up to 75 °C, which greatly increases the solubility of hydrophobic substrates. However, in reactions with one equivalent each of indole and Thr, we observed only 44 % conversion to product, corresponding to 2,220 turnovers (Figure S7). A critical clue explaining this low conversion came from UV-vis spectroscopy, which revealed that addition of Thr to PfTrpB2B9 results in a time-dependent increase in absorbance at 320 nm, while the remainder of the spectrum remains constant (Figure S8). We attribute this to α-ketobutyrate production from the well-described deami-nation reaction that results when a nucleophile does not add into C-β, and E(Ain) is reformed through transimination.7 The precise mechanism of deamination is unknown, but the net effect is an abortive reaction wherein the aminoacrylate hydrolyzes to form α-ketobutyrate and ammonium. We therefore added additional equivalents of Thr to the β-substitution reaction with indole (Figure S7), which enabled >99 % conversion of indole to β-MeTrp and up to 8,200 total turnovers to the desired product (Chart 1) with >99 % ee and de.</p><p>With these reaction conditions we next characterized the substrate scope of the reaction with Thr. Previously, we screened a small panel of indole-like nucleophiles for reaction with PfTrpB0B2 and Ser.8 We expanded on this panel of nucleophiles and tested for activity with PfTrpB2B9 using a 10-fold molar excess of Thr to nucleophile (Chart 1). Reactions were run to intermediate yield to determine the TTN with a given nucleophile. The identity of the products was established with a separate preparative-scale reaction using 100 mM nucleophile, 1.0 M Thr, and 0.02-0.13 mol % PfTrpB2B9 catalyst. We observed good reactivity with the 2-methyl and 6-methyl indole substrates, but decreased TTNs compared to indole demonstrate that the active site is sensitive to steric perturbations. To probe the role of electronic effects on the C-C bond-forming step, we tested activity with 4-fluoro and 5-fluoroindole, which are more closely isosteric with indole but have decreased electron density in the π-system. We observed product formation with each substrate and 3.4-fold lower TTN with the 4-fluoro substrate, which is more electron deficient at C-3 than the 5-fluoro substituent. The increased steric constraints of the active site were again clear, as we did not observe any activity with the 5-chloro-, 5-bromo, and 6-hydroxyindoles, which do undergo reaction with Ser.8</p><p>A productive reaction with 220 turnovers was observed with 7-azaindole, which is a substantially weaker nucleophile than indole. Interestingly, a second product was detected in the reaction with 7-azaindole that is consistent with N-alkylation. This regioselectivity is well known with indazole, which we found reacts exclusively to form an N-alkylated product. Surprisingly, we did not observe product formation with indoline, which is a stronger nucleophile than both indazole and indole and reacts significantly faster in the reaction with Ser. Future studies will be needed to ascertain the origin of this effect. Lastly, we tested for S-alkylation using thiophenol and measured 1,300 turnovers.</p><p>In conclusion, we have discovered a new, non-natural enzymatic route for the production of (2S, 3S)-β-MeTrp. This activity lies in the β-subunit of TrpS, which was subsequently engineered for increased activity with Thr as the amino acid donor. The development of the resultant catalyst, PfTrpB2B9, was greatly facilitated by previous efforts to replace the native two-enzyme system with a single stand-alone catalyst.8 The engineered enzymes have high thermal stability and expression in E. coli, enhancing their utility as practical catalysts. This enzymatic route to β-MeTrp is dramatically shorter than previous synthetic routes and also the native 3-enzyme pathway to this natural metabolite.911 This study highlights the ability of engineered biocatalysts to efficiently produce complicated molecules from simple precursors, and offers a simple and expandable route for the production of β-methyl ncAA analogs.</p>", "role": "user" }, { "content": "We report that l-threonine may substitute for l-serine in the \\xce\\xb2-substitution reaction of an engineered subunit of tryptophan synthase from Pyrococcus furiosus, yielding (2S,3S)-\\xce\\xb2-methyltryptophan (\\xce\\xb2-MeTrp) in a single step. The trace activity of the wild-type \\xce\\xb2-subunit on this substrate was enhanced more than 1,000-fold by directed evolution. Structural and spectroscopic data indicate that this increase is correlated with stabilization of the electrophilic aminoacrylate intermediate. The engineered biocatalyst also reacts with a variety of indole analogs and thiophenol for diastereoselective C-C, C-N, and C-S bond forming reactions. This new activity circumvents the 3-enzyme pathway that produces \\xce\\xb2-MeTrp in nature and offers a simple and expandable route to preparing derivatives of this valuable building block.", "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\nOff-policy learning, the task of evaluating and improving policies using historic data collected from a logging policy, is important because on-policy evaluation is usually expensive and has adverse impacts.\nOne of the major challenge of off-policy learning is to derive counterfactual estimators that also has low variance and thus low generalization error. \n\nIn this work, inspired by learning bounds for importance sampling problems, we present a new counterfactual learning principle for off-policy learning with bandit feedbacks.Our method regularizes the generalization error by minimizing the distribution divergence between the logging policy and the new policy, and removes the need for iterating through all training samples to compute sample variance regularization in prior work.\nWith neural network policies, our end-to-end training algorithms using variational divergence minimization showed significant improvement over conventional baseline algorithms and is also consistent with our theoretical results.\nOff-policy learning refers to evaluating and improving a deterministic policy using historic data collected from a stationary policy, which is important because in real-world scenarios on-policy evaluation is oftentimes expensive and has adverse impacts.\nFor instance, evaluating a new treatment option, a clinical policy, by administering it to patients requires rigorous human clinical trials, in which patients are exposed to risks of serious side effects.\nAs another example, an online advertising A/B testing can incur high cost for advertisers and bring them few gains.\nTherefore, we need to utilize historic data to perform off-policy evaluation and learning that can enable safe exploration of the hypothesis space of policies before deploying them.There has been extensive studies on off-policy learning in the context of reinforcement learning and contextual bandits, including various methods such as Q learning BID33 ), doubly robust estimator BID8 ), self-normalized (Swaminathan & Joachims (2015b) ), etc.\nA recently emerging direction of off-policy learning involves the use of logged interaction data with bandit feedback.\nHowever, in this setting, we can only observe limited feedback, often in the form of a scalar reward or loss, for every action; a larger amount of information about other possibilities is never revealed, such as what reward we could have obtained had we taken another action, the best action we should have take, and the relationship between the change in policy and the change in reward.\nFor example, after an item is suggested to a user by an online recommendation system, although we can observe the user's subsequent interactions with this particular item, we cannot anticipate the user's reaction to other items that could have been the better options.Using historic data to perform off-policy learning in bandit feedback case faces a common challenge in counterfactual inference: How do we handle the distribution mismatch between the logging policy and a new policy and the induced generalization error?\nTo answer this question, BID34 derived the new counterfactual risk minimization framework, that added the sample variance as a regularization term into conventional empirical risk minimization objective.\nHowever, the parametrization of policies in their work as linear stochastic models has limited representation power, and the computation of sample variance regularization requires iterating through all training samples.\nAlthough a first-order approximation technique was proposed in the paper, deriving accurate and efficient end-to-end training algorithms under this framework still remains a challenging task.Our contribution in this paper is three-fold:1.\nBy drawing a connection to the generalization error bound of importance sampling BID6 ), we propose a new learning principle for off-policy learning with bandit feedback.\nWe explicitly regularize the generalization error of the new policy by minimizing the distribution divergence between it and the logging policy.\nThe proposed learning objective automatically trade off between emipircal risk and sample variance.\n2. To enable end-to-end training, we propose to parametrize the policy as a neural network, and solves the divergence minimization problem using recent work on variational divergence minimization BID26 ) and Gumbel soft-max BID18 ) sampling.\n3. Our experiment evaluation on benchmark datasets shows significant improvement in performance over conventional baselines, and case studies also corroborates the soundness of our theoretical proofs.\nIn this paper, we started from an intuition that explicitly regularizing variance can help improve the generalization performance of off-policy learning for logged bandit datasets, and proposed a new training principle inspired by learning bounds for importance sampling problems.\nThe theoretical discussion guided us to a training objective as the combination of importance reweighted loss and a regularization term of distribution divergence measuring the distribution match between the logging policy and the policy we are learning.\nBy applying variational divergence minimization and Gumbel soft-max sampling techniques, we are able to train neural network policies end-to-end to minimize the variance regularized objective.\nEvaluations on benchmark datasets proved the effectiveness of our learning principle and training algorithm, and further case studies also verified our theoretical discussion.Limitations of the work mainly lies in the need for the propensity scores (the probability an action is taken by the logging policy), which may not always be available.\nLearning to estimate propensity scores and plug the estimation into our training framework will increase the applicability of our algorithms.\nFor example, as suggested by BID6 , directly learning importance weights (the ratio between new policy probability to the logging policy probability) has comparable theoretical guarantees, which might be a good extension for the proposed algorithm.Although the work focuses on off-policy from logged data, the techniques and theorems may be extended to general supervised learning and reinforcement learning.\nIt will be interesting to study how A. PROOFS DISPLAYFORM0 We apply Lemma 1 to z, importance sampling weight function w(z) = p(z)/p 0 (z) = h(y|x)/h 0 (y|x), and loss l(z)/L, we have DISPLAYFORM1 Thus, we have DISPLAYFORM2 Proof.\nFor a single hypothesis denoted as δ with values DISPLAYFORM3 By Lemma 1, the variance can be bounded using Reni divergence as DISPLAYFORM4 Applying Bernstein's concentration bounds we have DISPLAYFORM5 σ 2 (Z)+ LM/3 ), we can obtain that with probability at least 1 − η, the following bounds for importance sampling of bandit learning holds DISPLAYFORM6 , where the second inequality comes from the fact that DISPLAYFORM7 sampled from logging policy h 0 ; regularization hyper-parameter λ Result: An optimized generator h * θ (y|x) that is an approximate minimizer of R(w) initialization; while Not Converged do / * Update discriminator * / Sample a mini-batch of 'fake' samples (x i ,ŷ i ) with x i from D andŷ i ∼ h θ t (y|x i ); Sample a mini-batch of 'real' samples (x i , y i ) from D ; Update w t+1 = w t + η w ∂F (T w , h θ )(10) ; / * Update generator * / Sample a mini-batch of m samples from D ; Sample a mini-batch of m 1 'fake' samples ; Estimate the generator gradient as g 2 = F (T w , h θ )(10) ; Update θ t+1 = θ t − η θ (g 1 + λg 2 ) ; end Algorithm 3: Minimizing Variance Regularized Risk -Co-Training Version", "role": "user" }, { "content": "For off-policy learning with bandit feedbacks, we propose a new variance regularized counterfactual learning algorithm, which has both theoretical foundations and superior empirical performance.", "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: Sars-cov-2 is also detectable in the vaginal fluid of women with severe covid-19 infection\n\nAbstract:\nBACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is spread mainly through respiratory droplets or direct contact.\nHowever, the infection condition of the genital system is unknown.\nOur aim in this study was to determine if SARS-CoV-2 is present in the vaginal fluid of women with coronavirus disease 2019 (COVID-19).\nMETHODS: Ten women with confirmed severe COVID-19 pneumonia admitted to the Tongji Zhongfa Hospital intensive care unit from 4 February 2020 through 24 February 2020 were included.\nClinical records, laboratory results, and computed tomography examinations were retrospectively reviewed.\nThe potential for genital infection was accessed by testing for the presence of SARS-CoV-2 in vaginal fluids obtained from vaginal swab samples.\nReverse transcriptase polymerase chain reaction was used to confirm the SARS-CoV-2 infection in vaginal fluids.\nRESULTS: The clinical characteristics of the 10 women were similar to those reported in other severe COVID-19 patients.\nAll 10 patients were tested for SARS-CoV-2 in vaginal fluid, and all samples tested negative for the virus.\nCONCLUSIONS: Findings from this small group of cases suggest that SARS-CoV-2 virus does not exist in the vaginal fluids of severe COVID-19 patients.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"All 10 patients were tested for SARS-CoV-2 in vaginal fluid, and all samples tested negative for the 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: [\"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\nDefining therapeutic targets by using adenovirus: blocking NF-kappaB inhibits both inflammatory and destructive mechanisms in rheumatoid synovium but spares anti-inflammatory mediators. The role of the transcription factor NF-kappaB in the pathogenesis of rheumatoid arthritis has long been a subject of controversy. We used an adenoviral technique of blocking NF-kappaB through overexpression of the inhibitory subunit IkappaBalpha, which has the advantage that it can be used in the diseased tissue itself, with > 90% of the synovial macrophages, fibroblasts, and T cells infected. We found that the spontaneous production of tumor necrosis factor alpha and other pro-inflammatory cytokines is NF-kappaB-dependent in rheumatoid synovial tissue, in contrast to the main anti-inflammatory mediators, like IL-10 and-11, and the IL-1 receptor antagonist. Of even more interest, IkappaBalpha overexpression inhibited the production of matrix metalloproteinases 1 and 3 while not affecting their tissue inhibitor. Blocking NF-kappaB in the rheumatoid joint thus has a very beneficial profile, reducing both the inflammatory response and the tissue destruction. The adenoviral technique described here has widespread applicability, allowing rapid testing of the effects of blocking a potential therapeutic target in either cultures of normal cells or in the diseased tissue itself.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"T cells\", \"normal cells\", \"fibroblasts\", \"synovial macrophages\"], \"DNA\": [], \"Protein\": [\"cytokines\", \"transcription factor\", \"pro - inflammatory cytokines\", \"inhibitory subunit\", \"tumor necrosis factor alpha\", \"anti - inflammatory mediators\", \"matrix metalloproteinases 1 and 3\", \"NF - kappaB\", \"IL - 10 and - 11\", \"IL - 1 receptor antagonist\", \"IkappaBalpha\"], \"RNA\": []}", "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 mutation is targeted by Tepotinib?\n\nContext: BACKGROUND: A splice-site mutation that results in a loss of transcription of exon 14 in the oncogenic driver MET occurs in 3 to 4% of patients with non-small-cell lung cancer (NSCLC). We evaluated the efficacy and safety of tepotinib, a highly selective MET inhibitor, in this patient population.\nCONCLUSIONS: Among patients with advanced NSCLC with a confirmed MET exon 14 skipping mutation, the use of tepotinib was associated with a partial response in approximately half the patients.\nManagement of Non-small Cell Lung Cancer Patients with MET Exon 14 Skipping Mutations.\nIf type I MET inhibitors (crizotinib, capmatinib, tepotinib, savolitinib) drug resistance is developed, type II MET inhibitors (cabozantinib, glesatinib, merestinib) can be considered.\nDrugs targeting MET 14 exon skipping mutation bring new hope to patients. MET inhibitors that are currently on the market or are about to be marketed include: crizotinib, cabozantinib, savolitinib and tepotinib.\nAt least five MET-targeted TKIs, including crizotinib, cabozantinib, capmatinib, tepotinib, and glesatinib, are being investigated clinically for patients with MET exon 14 altered-NSCLC.\nTepotinib hydrochloride is an orally bioavailable, mesenchymal-epithelial transition (MET) TKI developed mainly for selected NSCLC patients with METex14 skipping mutations.\nhibitors for MET exon 14 skipping mutation such as capmatinib and tepotinib have elucidated their effectiveness. Only a few reports have suggested their efficacy ag\nTepotinib is an oral MET inhibitor approved for metastatic non-small cell lung cancer (NSCLC) harboring MET exon 14 (METex14) skipping mutations.\nET exon 14 skipping mutation and poor performance status salvaged by marked leptomeningeal metastases response to tepotinib. We further provide measures of plasma/cerebrospinal fluid concentrations of t\nTepotinib is a key drug for cancer patients with mesenchymal-epithelial transition receptor tyrosine kinase proto-oncogene (MET) exon 14 skipping mutation.\nHerein, we report a case of a patient with metastatic lung adenocarcinoma harboring a MET exon 14 splice site mutation who has had prolonged disease control by a second-generation MET-TKI tepotinib. A 66-yr-old man was diagn\nRecently, in METex14-mutated NSCLC, multitarget tyrosine kinase inhibitors (TKIs), such as crizotinib and cabozantinib, as well as MET-selective TKIs, such as tepotinib and capmatinib, have demonstrated durable responses.\nTepotinib is an oral MET inhibitor approved for metastatic non-small cell lung cancer (NSCLC) harboring MET exon 14 (METex14) skipping mutations. Ex\n(NSCLC). The MET inhibitor tepotinib has demonstrated clinical efficacy in patients with MET exon 14 skipp\nification (~14%). In 2020, the approval of two MET-tyrosine kinase inhibitors (TKIs), capmatinib and tepotinib, for NSCLCs carrying MET∆ex14 dawned a new era for ME\nRecently approved and highly specific small-molecule inhibitors of c-MET exon 14 skipping mutations (e.g., capmatinib, tepotinib) are a new and important therapeutic option for the treatment of non-small cell lung cancer (NSCLC) patients harbouring c-MET alterations. Seve\n, in METex14-mutated NSCLC, multitarget tyrosine kinase inhibitors (TKIs), such as crizotinib and cabozantinib, as well as MET-selective TKIs, such as tepotinib and capmatinib, have demonstrated durable responses. In this study\ntudies reported that NSCLC patients harboring a METex14del responded well to MET-tyrosine kinase inhibitors (TKIs), including tepotinib. Tepotinib\nrgeted TKIs, including crizotinib, cabozantinib, capmatinib, tepotinib, and glesatinib, are being investigated clinically for patients with MET exon 14 altered-NSCLC. A further two compounds\nTepotinib is a key drug for cancer patients with mesenchymal-epithelial transition receptor tyrosine kinase proto-oncogene (MET) exon 14 skipping mutation.\n. Several tyrosine kinase inhibitors for MET exon 14 skipping mutation such as capmatinib and tepotinib have elucidated their effect\nTepotinib at this dose has obtained regulatory approval for the treatment of patients with non-small cell lung cancer harboring MET exon 14 skipping.\nActivity and bioavailability of tepotinib for leptomeningeal metastasis of NSCLC with MET exon 14 skipping mutation.\nExamining treatment-naive or tepotinib-resistant cells with MET amplification or METex14 skipping mutations identifies other receptor tyrosine kinases (RTKs) that co-exist in cells prior to tepotinib exposure and become more prominent upon tepotinib resistance.", "role": "user" }, { "content": "MET Exon 14 Skipping Mutation", "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: Toward Proactive, Adaptive Defense: A Survey on Moving Target Defense \nChapter Title: F. Vehicular Networks \n1. Abstract of Cited Paper (BIB001): Cybersecurity is increasingly important for the safety and reliability of autonomous vehicles. The controller area network (CAN) is the most widely used in-vehicle network for automotive safety-critical applications. Enhancing the cybersecurity ability of CAN while considering the real-time, schedulability, and cost constraints becomes an urgent issue. To address this problem, a real-time, and schedulability analysis-guaranteed security mechanism [identification hopping CAN (IDH-CAN)] is proposed in this paper, which aims to improve the security performance of CAN under the constraints of automotive real-time applications. In order to support the operation of the IDH-CAN mechanism, an IDH-CAN controller is also designed and implemented on a field-programmable gate array, which can work as a hardware firewall in the data link layer of CAN to isolate cyberattacks from the physical layer. Meanwhile, to maximize the information entropy of the CAN message ID on the physical layer, the ID hopping table generation and optimization algorithms for IDH-CAN are also proposed. Then, information security evaluation experiments based on information entropy comparison are deployed. The simulation and practical evaluations demonstrate the effectiveness of the proposed mechanism in defending reverse engineering, targeted denial of service, and replay attacks without violating real-time and schedulability constraints. \n2. Abstract of Cited Paper (BIB002): Cyber-Physical Systems (CPS) have traditionally been considered more static with more regular communication patterns when compared to classical information technology networks. Because the structure of most CPS remains unchanged during long periods of times, they become vulnerable to adversaries with the precise knowledge of the system, and who can tailor their attacks based on their knowledge about the system dynamics, communications, and control. \n3. Abstract of Cited Paper (BIB003): New vehicles have become increasingly targeted for cyber-attacks as their rate of digitalization is accelerated. Research on vehicle hacking has highlighted the security vulnerabilities of in-vehicle controller area networks (CANs) as the biggest problem. In particular, a CAN does not offer access control, authentication, or confidentiality, so it fails to prevent reconnaissance operations conducted by an adversary. Because its static configuration (CAN ID, data frame transmission cycle, and data field format) is used in an in-vehicle network environment, the adversary can conduct reconnaissance and easily acquire information to be used for an attack. One of the moving target defense strategies, network address shuffling (NAS), is an extremely practical security solution that can prevent in-vehicle CAN reconnaissance acts. In this paper, we propose a CAN ID shuffling technique using NAS. Our proposed security solution aims to increase the cost burden for the adversary to analyze CAN data frames. To evaluate the performance of the proposed security solution, we conducted an evaluation based on a labcar. Our proposed security solution may be implemented without altering the unique characteristics of the CAN standard. Hence, it can be used as a practical countermeasure to solve the problems affecting in-vehicle CANs. \n4. Abstract of Cited Paper (BIB004): As connected and autonomous vehicle technology evolves, the design of in-vehicle network architecture, which connects multiple electronic control units (ECUs) and internal sensors and supports connectivity to the outside of the vehicle, has increased significantly to meet security needs. However, the heterogeneous structure of the in-vehicle network and lack of security consideration has introduced a lack of scalability and security concerns. In this work, we propose a shuffling-based moving target defense (MTD) technique aiming to disturb network reconnaissance attacks and deployed it in the proposed software-defined networking (SDN)-based in-vehicle network architecture. To validate the proposed MTD, we compare the service availability of our proposed MTD and non-MTD counterpart in the presence of the reconnaissance-based false message injection attacks.\n\nLiterature Review:", "role": "user" }, { "content": "Along with significant developments in autonomous driving technologies, the importance of securing vehicular networks such as inter-vehicle networks (e.g., vehicle-tovehicle, vehicle-to-infrastructure networks) and intra-vehicle networks (e.g., control area networks) has increased. To protect the vehicular networks, several proactive MTD techniques have been developed. Now we discuss what key MTD techniques, main attacks, defense methodologies, and evaluation methods are considered in existing works for securing vehicular networks. MTD Techniques: The key MTD technologies addressed in vehicular communication environments include diversitybased multi-path transmission MTD in vehicle-to-vehicle (V2V) communication , , topology shuffling-based MTD in multi-vehicle systems BIB003 , CAN (Controller Area Network) ID hopping BIB001 , BIB002 and CAN ID shuffling BIB004 in in-vehicle networks, and IP shuffling in in-vehicle SDN environments BIB005 . Main Attacks: The common attacks considered in intervehicular networks include eavesdropping, packet sniffing and modification, or signal jamming attacks , . The works on intra-vehicular networks considered false message injection BIB005 , DoS BIB001 , or impersonation attacks BIB004 . Since vehicular communication may deal with important vehicle driving data, the major concern of MTD is to counteract attacks leaking out the information from driving control components and injecting the false information to critical components in in-vehicle networks. Key Methodologies: Ghourab et al. proposed the forwarding path diversity-based MTD to disrupt eavesdroppers or signal jammers in inter-vehicular communication networks. In this approach, vehicles randomly select nearby available vehicles while this randomization dynamically assigns different paths for the packets to be transmitted. The authors later, in , proposed a multidimensional MTD technique to secure Vehicle to Vehicle (V2V) communication systems working based on a wireless medium. They utilized a spatiotemporal diversity as an MTD technique using signal obfuscation in a wireless environment to change the wireless transmission pattern to defend against possible attacks. Humayed and Luo BIB001 proposed the use of random switching topologies for multi-vehicle systems as an MTD mechanism which can decrease the adverse impact of the attack. Similarly, Giraldo and Cardenas BIB003 proposed an MTD strategy for multi-vehicle systems to mitigate the impact of the attacks or increase attack complexity, rather than detecting the attacks. They identified an optimal network topology to mitigate the attack deviation. Humayed and Luo BIB001 presented a CAN ID hopping mechanism, similar to shuffling-based randomizing technologies. When DDoS attacks are detected, ECUs (engine control units) generate new IDs by adding an offset value to their ID value. The hopping synchronization is achieved from the gateway of ECUs. Wu et al. BIB002 proposed an ID hopping (IDH-CAN) mechanism by implementing additional hardware to maximize the information entropy of the CAN IDs. Woo et al. BIB004 presented a shared key based CAN ID shuffling technique (CIST). CIST changes an ECU ID using a one-time ID generated by a hash function with a group session key from the ECU gateway. Whenever a node transmits data, each ECU uses different IDs for the transmission. Yoon et al. BIB005 proposed IP shuffling based MTD in an in-vehicle SDN to disrupt false injection attacks. They presented an SDN-based in-vehicle architecture and an IP address shuffling method that can prevent the leakage of ECU ID information from invehicle networks. Fig. 15 describes an example architecture of MTD for in-vehicle CAN in which CAN IDs are periodically shuffled as an MTD mechanism. Evaluation Methods: As observed in other domains, some works are evaluated based on numerical analysis and analytical models , , BIB003 by measuring the effectiveness of MTD in terms of security performance and defense cost. Most works in the CAN environment used prototype-based evaluation to validate their MTD mechanisms BIB001 , BIB004 , BIB005 . Wu et al. BIB002 conducted their experiments on a real CAN testbed to verify security enhancements in terms of the information entropy. Yoon et al. BIB005 investigated their proposed IP shuffling-based MTD on a real SDN-based environment and validated their MTD in terms of service availability of ECU nodes. Ghourab et al. validated their proposed MTD technique in V2V communication via simulation experiments. They showed that the proposed method can increase the channel security and confusion factor while decreasing the intercept probability. Giraldo and Cardenas BIB003 validated their proposed MTD method in a multi-vehicle system by mitigating the impact of performance degradation in vehicular platooning and Unmanned Aerial Vehicle (UAV) formation contexts. Pros and Cons: While most MTD technologies today focus on IP-based networks, some MTD technologies for in-vehicle networks have the advantage of extending MTD coverage in which they can be applied to a bus network environment such as CAN. However, when vehicles are configured with various heterogeneous in-vehicle networking protocols such as CAN, local interconnect network (LIN) and FlexRay, an MTD technique is hard to apply to protect the entire in-vehicle network. Moreover, as we discussed in other domains, it is still difficult to balance security and performance in terms of maximizing service availability while minimizing vulnerability and defense costs.", "role": "assistant" } ]

[ { "content": "You have to answer a biomedical question in binary format, i.e., only yes and no are acceptable answers. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Does replication timing affect the rate of somatic mutations?\n\nContext: Here we observe that mutation rate, as reflected in recent evolutionary divergence and human nucleotide diversity, is markedly increased in later-replicating regions of the human genome\nll classes of substitutions are affected, suggesting a generalized mechanism involving replication time-dependent DNA damage\nWe show that mutation rate varies 6-fold across a single chromosome, that this variation is correlated with replication timing, and we propose a model to explain this variation that relies on the temporal separation of two processes for replicating past damaged DNA: error-free DNA damage tolerance and translesion synthesis.\nRecent studies revealed a long suspected replication-timing effect on mutation rate, but the mechanisms that regulate the increase in mutation rate as the genome is replicated remain unclear.\nDNA repair systems, in general, are less efficient in late replicating heterochromatic regions compared to early replicating euchromatic regions of the genome.\nThe mutational profile of the yeast genome is shaped by replication\nthe mutation rate increases with the replication timing by more than 30% between the earliest and the latest replicating regions.\nThus, we show that the leading replicating strands present an excess of C over G and of A over T in the genome of S. cerevisiae (reciprocally an excess of G + T over C + A in lagging strands)\nLate-replicating domains have higher divergence and diversity in Drosophila melanogaster\nRecent evidence also suggests that late replication is associated with high mutability in yeast.\nLimited evidence from one chromosome arm in Drosophila melanogaster suggests the opposite pattern, with regions overlapping early-firing origins showing increased levels of diversity and divergence\nThe mutation rate for DNA mismatch repair null strains was approximately 1 mutation per genome per generation, 225-fold greater than the wild-type rate. The mutations were distributed randomly throughout the genome, independent of replication timing.\nMany single-nucleotide substitutions in cancer genomes arise because of errors in DNA replication, which is spatio-temporally stratified.\nHere we propose that DNA replication patterns help shape the mutational landscapes of normal and cancer genomes\nUsing data on five fully sequenced cancer types and two personal genomes, we determined that the frequency of intergenic single-nucleotide substitution is significantly higher in late DNA replication timing regions, even after controlling for a number of genomic features\nwe found that genomic regions in close spatial proximity to late-replicating domains display similar mutation spectra as the late-replicating regions themselves\nIn addition, certain chromosome rearrangements found in cancer cells and in cells exposed to ionizing radiation display a significant delay in replication timing of >3 hours that affects the entire chromosome(2,3). Recent work from our lab indicates that disruption of discrete cis-acting autosomal loci result in an extremely late replicating phenotype that affects the entire chromosome(4).\nA conservative estimate is that at least 1-2% of new deleterious mutations affect some aspect of DNA replication, repair, or chromosome segregation. Since deleterious mutations can have an effect even as heterozygotes, this mutation accumulation can create an inherited background of late-acting mutations that themselves enhance mutation rate.\nDrake calculates that lytic RNA viruses display spontaneous mutation rates of approximately one per genome while most have mutation rates that are approximately 0.1 per genome (Drake 1993). This constancy of germline mutation rates among microbial species need not necessarily mean constancy of the somatic mutation rates.\nA recent flurry of reports correlates replication timing (RT) with mutation rates during both evolution and cancer.\nDNA replication timing, genome stability and cancer: late and/or delayed DNA replication timing is associated with increased genomic instability.\nSince deleterious mutations can have an effect even as heterozygotes, this mutation accumulation can create an inherited background of late-acting mutations that themselves enhance mutation rate.\nIn addition, this method allows for the unambiguous identification of chromosomal rearrangements that correlate with changes in replication timing that affect the entire chromosome.", "role": "user" }, { "content": "yes", "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\nConformationally restricted homotryptamines. Part 6: Indole-5-cycloalkyl methylamines as selective serotonin reuptake inhibitors. Racemic 5- (trans-2-aminomethylcyclopropyl) indoles, 5- (trans-2-aminomethylcyclopentyl) indoles, and 5- (cis-2-aminomethylcyclopentyl) indoles were synthesized and evaluated as selective serotonin reuptake inhibitors. These analogs followed SAR trends similar to those previously reported for 3-cycloalkyl substituted indoles. The most potent analogs exhibited single digit nanomolar inhibition at the human serotonin transporter but were 10-fold less active than the previously reported compounds.", "role": "user" }, { "content": "[]", "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: The Jujube Genome Provides Insights into Genome Evolution and the Domestication of Sweetness/Acidity Taste in Fruit Trees\nArticle:\nAbstract:\nJujube( Ziziphus jujuba Mill.) belongs to the Rhamnaceae family and is a popular fruit tree species with immense economic and nutritional value. Here, we report a draft genome of the dry jujube cultivar ‘Junzao’ and the genome resequencing of 31 geographically diverse accessions of cultivated and wild jujubes( Ziziphus jujuba var. spinosa). Comparative analysis revealed that the genome of ‘Dongzao’, a fresh jujube, was ~86. 5 Mb larger than that of the ‘Junzao’, partially due to the recent insertions of transposable elements in the ‘Dongzao’ genome. We constructed eight proto-chromosomes of the common ancestor of Rhamnaceae and Rosaceae, two sister families in the order Rosales, and elucidated the evolutionary processes that have shaped the genome structures of modern jujubes. Population structure analysis revealed the complex genetic background of jujubes resulting from extensive hybridizations between jujube and its wild relatives. Notably, several key genes that control fruit organic acid metabolism and sugar content were identified in the selective sweep regions. We also identified S-locus genes controlling gametophytic self-incompatibility and investigated haplotype patterns of the S locus in the jujube genomes, which would provide a guideline for parent selection for jujube crossbreeding. This study provides valuable genomic resources for jujube improvement, and offers insights into jujube genome evolution and its population structure and domestication.\nIntroduction:\nChinese jujube( Ziziphus jujuba Mill.)( 2n = 2x = 24), native to China, is one of the oldest cultivated fruit trees, with more than 7, 000 years of domestication history[1]. It belongs to the Rhamnaceae family in the Rosales order. Jujube is valued as a woody crop and traditional herbal medicine, and cultivated on 2 million hectares in China alone, with an annual production of approximately 4. 32 million tons[2]. Jujube cultivars have been traditionally classified as fresh or dry, and dry jujubes account for approximately 80% of the total production. Ripe fruits of dry jujube have a coarse texture while those of fresh types have a crisp texture. Cultivated jujubes were domesticated from their wild ancestors( Z. jujuba Mill. var. spinosa Hu.) through an artificial selection process for important agronomic traits, which resulted in architectural and structural changes in the tree such as a transition from bushes with more thorns to trees with fewer thorns and enlarged fruit sizes[1, 3]. As with many agricultural crops, taste attributes of jujube fruits, such as sweetness and sourness, have been the subject of human selection. Fruits of cultivated jujubes have higher levels of sugars( up to 72% of the dry weight), while wild jujube fruits accumulate more soluble organic acids[3, 4]. The domestication mechanism of fruit sweetness and acidity taste from their wild relatives is still not well characterized. Therefore, characterization of the sugar and acid metabolism of domesticated and wild jujubes through genome-wide analyses would help elucidate the genomic mechanism underlying fruit sweetness and acidity taste improvement. The majority of jujube cultivars produce few seeds due to self-incompatibility or cross-incompatibility, which limit the practical artificial breeding of jujube. Gametophytic self-incompatibility( GSI) system is controlled by the S locus and has been found to operate in several Ziziphus species, including Z. jujuba[5–7]. Parents sharing the same S haplotype often result in seedless jujube kernels. Therefore, identification of the self-incompatibility locus( S locus) genes would provide a guideline to facilitate jujube breeding. Recently, the draft genome of a fresh jujube cultivar ‘Dongzao’ with a high level of heterozygosity was reported, and it provides insights into the ascorbic acid metabolism and the adaptation mechanism to abiotic/biotic stresses[8]. However, little is known about jujube evolution, domestication, and the genetic bases of fruit quality. The genome sequencing of additional diverse jujubes would help us to address these questions, laying the foundation for improved strategies for jujube breeding. Here, we report the genome of a dry jujube cultivar ‘Junzao’ Fig A and Fig B in S1 File,). We also resequenced the genomes of 31 cultivated and wild jujube accessions with a range of geographical distributions. The genome sequences provided insights into the evolution of Rhamnaceae. Integrative transcriptome and resequencing analyses illuminated the genomic mechanisms underlying the domestication events of fruit sweetness and acidity.\nDiscussion:\nWe report the 351-Mb genome of the heterozygous dry jujube cultivar ‘Junzao, ’ which is 86. 5 Mb smaller than the assembled ‘Dongzao’ genome( 437. 7 Mb)[8]. We performed a series of analyses to characterize the size difference between the two genome assemblies, and revealed that the difference was primarily attributed to different levels of transposable elements, redundant sequences caused by heterozygosity, and bacterial contaminated sequences. In addition, we note that the k-mer and flow cytometry analyses of leaves from a ‘Dongzao’ mature tree indicated a similar genome size( ~352 Mb) to that of ‘Junzao’( Table B and Table W in S2 File). There are several reports of tissue culture-induced genome-level changes in plants, and one of the major underlying factors is the proliferation of transportable elements[17, 18]. Accordingly, the use of in vitro cultured plantlets as the source material for genome sequencing could lead to complex genetic background to some extent. We resequenced a wide range of jujube cultivars and their wild relatives covering different fruit types( dry or fresh) and geographical distributions. This exploration revealed the various consequences of artificial selection during jujube domestication and elucidated the history of jujube domestication. Genome-wide SNP analysis revealed that naturally grown wild jujubes possessed higher diversity than cultivated jujubes, and the overall genetic diversity of jujube is similar to that of peach[19] but lower than that of several herbaceous species, such as soybean[20], rice[21] and cucumber[22]. A complex genetic background, caused by natural or artificial hybridization, was also revealed, which might explain why some semi-wild jujubes exhibited few traits that could distinguish them from cultivated jujubes, other than a sour taste and smaller fruit and tree sizes. Consistent with the population structure deduced by chloroplast diversity[23], our analyses using various approaches supported the hypothesis of an admixed population structure of wild and cultivated jujubes. We propose that this pattern reflects frequent exchanges of jujube germplasm between human populations from different sites and natural and artificial hybridizations. The domestication of jujube has involved the selection for the fruit sourness and sweetness profiles, which are determined by acid and sugar metabolism. Analysis of fruit sugar and acid contents in a wide range of apple accessions suggested that fruit acidity rather than sweetness is likely to have undergone selection during apple domestication[24]. In this study, we found that unlike apple, sugar and acid metabolism were both undergone human selection during jujube domestication( Fig 3A). In particular, four genes and several sugar transporters involved in acid and sugar metabolism were determined to be putatively under human selection, of which two genes( NADP-ME and PK) are closely associated with the production of malate, which contributes directly to the acid taste of the fruit[25]. In addition, the expression levels of genes encoding enzymes, such as NADP-ME, PK, PEPC and MDH were substantially lower in cultivated jujube fruits in comparison with wild jujubes. Differential expression of the same gene sets between high-and low-acid apple fruits has also been reported[25, 26]. GSI have been characterized in the Rosaceae, Solanaceae and Plantaginaceae families which involves an S locus[27]. Although GSI is widely present in the Ziziphus species, the molecular mechanism controlling the hybridization behavior in jujubes is unknown. We identified the jujube S locus on the basis of genome sequence information, which was supported by gene expression analysis. Analyses of the S-locus genotypes of the 31 accessions provide guidelines for parent selection for crossbreeding. We have proved this strategy by crossing two random combinations with different S haplotypes, i. e., ‘Dongzao’ × ‘Linyilizao’[28] and ‘Dongzao’ × ‘Zhongningyuanzao’[29].", "role": "user" }, { "content": "A balanced sweetness and acidity taste is among the most important characteristics of fruits . It is generally believed that human selection of sweetness plays a crucial role in the process of domestication from wild to cultivated fruit trees . However , the molecular mechanisms underlying fruit taste domestication still remain unclear . It is also unclear whether taste improvement is mainly determined by positive selection of advantageous traits such as sweetness or negative selection of disadvantageous trait such as acidity . Chinese jujube , domesticated from the wild jujube , is an economically important fruit tree crop in China . In this study , we sequenced and assembled the genome of a dry jujube and analyzed the genetic relationship between cultivated and wild jujubes through genome resequencing . Key genes involved in the acid and sugar metabolism were identified in the selective sweep regions . This finding suggested an important domestication pattern in fruit taste and also provided insights into the fruit molecular breeding and improvement .", "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 intense physical activity associated with longevity?\n\nContext: Our major finding is that repeated very intense exercise prolongs life span in well trained practitioners.\nDeath rates declined with increased levels of total activity (estimated in kilocalories), and declined also with increased intensity of effort measured as from none, to light, to moderately vigorous or vigorous sports play. Death rates at any given quantity of physical exercise were lower for men playing moderately intense sports than for less vigorous men.\nhe purpose of this study was to investigate if jogging, which can be very vigorous, is associated with increased all-cause mortality in men and women.\nThis long-term study of joggers showed that jogging was associated with significantly lower all-cause mortality and a substantial increase in survival for both men and women.\nLight activities (<4 multiples of resting metabolic rate (METs)) were not associated with reduced mortality rates, moderate activities (4-<6 METs) appeared somewhat beneficial, and vigorous activities (> or =6 METs) clearly predicted lower mortality rates (p, trend = 0.72, 0.07, and <0.001, respectively).\nThese data demonstrate a graded inverse relationship between total physical activity and mortality. Furthermore, vigorous activities but not nonvigorous activities were associated with longevity.\nThe capacity for prolonged and vigorous physical exercise, particularly if the exercise is recreational, is a strong indicator of longevity.", "role": "user" }, { "content": "yes", "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: Effect of intravitreal dexamethasone on macular edema in von Hippel-Lindau disease assessed using swept-source optical coherence tomography: a case report. Von Hippel-Lindau disease is a rare hereditary syndrome caused by germinal mutations in a von Hippel-Lindau tumor-suppressing gene. Retinal hemangioblastoma is the ocular hallmark lesion of von Hippel-Lindau disease. ### Case Presentation A 20-year-old Caucasian woman presented to our institution with painless visual impairment in the right eye. A fundus ophthalmoscopic evaluation and swept-source optical coherence tomographic examination revealed a retinal hemangioblastoma associated with cystoid macular edema. On the basis of the clinical ocular findings and genetic analysis, von Hippel-Lindau disease was diagnosed. Following an intravitreal injection of ranibizumab , off-label administration of intravitreal dexamethasone was considered to reduce the edema . An almost complete resolution of the edema in the macular area was observed 1 week after the injection. Finally, laser photocoagulation and transconjunctival cryotherapy were performed; the patient developed \"ablatio fugax\" after cryotherapy. ### conclusions In our experience, intravitreal dexamethasone administration has proven to be a useful tool for reducing retinal hemangioblastoma-related macular edema in von Hippel-Lindau disease and may be considered a potentially valuable treatment that can be used in combination with other therapies.\n\nsentence: Following an intravitreal injection of ranibizumab , off-label administration of intravitreal dexamethasone was considered to reduce the edema .", "role": "user" }, { "content": "[[\"ranibizumab\", \"dexamethasone\", \"POS\"]]", "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:\nPyridine N-oxides as HAT reagents for photochemical C-H functionalization of electron-deficient heteroarenes\n\nPaper sections:\n\n<p>In 2021 Zhang reported that an electrochemically generated pyridine N-oxyl radical cation is capable of abstracting a hydrogen atom from water molecules. 17 Inspired by this result, we envision pyridine N-oxides as hydrogen atom transfer reagents in C-C bond forming reactions. To test this hypothesis, we used them in the photocatalytic generation of C(sp3) radicals from alkanes, which then engage in a reaction with electron-deficient heteroarenes. Photoinduced Minisci-type azines alkylations with precursors of the C(sp</p>\n\n3\n<p>)-H radical have already been extensively studied, using various terminal oxidants, [18][19][20] such as: organic peroxides, 21 persulfates, 22 and recently air. 23 Most of them, however, require a significant excess of the reagent and the use of a photocatalyst. We commenced our studies by performing UV-Vis absorption measurements, since it is well documented that pyridine derivatives easily form EDA complexes, [24][25][26] (Figure 1). A spectrum of a mixture of lepidine (1) and 2,6lutidine N-oxide (3) is merely a sum of the absorption of the components; however, upon the addition of an equimolar amount of TFA, an increase in the absorbance of the charge-transfer band was observed around 380 nm (Figure 1A). In fact, the addition of TFA up to 1 equiv. led to a gradual increase in absorption in this region (Figure 1B), suggesting the formation of the EDA complex between protonated lepidine (1) and 2,6-lutidine N-oxide (3). Photoexcitation of the formed complex should generate the N-oxyl radical cation, which, according to Zhang's results, should then abstract the hydrogen atom from the C-H bonds generating the corresponding C-centred radical (Scheme 1C). UV-A irradiation of the model reaction of lepidine (1) with cyclooctane (2) in the presence of 2,6lutidine N-oxide (3) and sulfuric acid in an acetonitrile/water mixture gave alkylated lepidine 4a in a modest yield (Table 1, entry 1). Less energetic violet light (405 nm, entry 2) induced the reaction as well, without having a negative effect on the yield. Prolonging the reaction time did not improve the conversion; however, an increase in the amount of an acid led to the formation of product 4a in high yield (entries 3, 4). Among a selection of acids tested, TFA maintained the yield at a high level (entry 5). Lewis acids also promoted the reaction functioning as an alternative activating agent for the heterocyclic substrate, in the presence of Zn(OTf) 2 the yield of product 4a increased up to 81% (entry 7). The energy of the EDA complex charge transfer band corresponds to the difference between the donor ionization energy and the acceptor electron affinity, 27 thus the behaviour of pyridine N-oxides with both EWG and EDG as HAT reagents were tested (see SI); however, the initially used 2,6-lutidine N-oxide (3) was the most efficient. entry Deviation from optimal conditions yield (%) 1</p><p>1.5 equiv. of N-oxide 3, 1 equiv. of H2SO4 instead of TFA in CH3CN/H2O (5:1) irradiated at 365 nm With the optimized conditions in hand, the scope of nucleophilic radical precursors was investigated (Scheme 2). The method proved to be effective in generating radicals from various types of formal hydrogen atom donors: alkanes, alkenes, amides, and ethers. In particular, the reaction is insensitive to the ring size of secondary alkanes and provided corresponding products 4a-d in good yields (76-87%). The process could be scaled up to 1 mmol, however prolonged reaction time is required to achieve decent yield of the product 4c. Among alkenes, both cyclohexene and 2-ethyl-but-1-ene furnished mainly hydroxylated products 4e and 4f, even when the reaction was carried out under anhydrous conditions. This result suggests that hydroxyl radicals are generated during the reaction course. As far as amides are concerned, the reaction with dimethylacetamide selectively afforded compound 4g in 52% yield, however, full conversion was not achieved with Zn(OTf) 2 . These substrates performed best with TFA as an additive, for product 4g the yield increased to 72%. The use of DMF as a substrate led to a mixture of products 4h and 4i. The abstraction of hydrogen atom from the α-position is highly preferred (4h, 52%), although the acylation product 4i was also observed. For 1-Boc-pyrrolidine, the yield decreased slightly (60%), presumably due to steric hindrance. In general, the abstraction of secondary hydrogen atoms is preferred over primary ones, as evidenced by the alkylation with 1methylpyrrolidone, which gave product 4k in a yield of 57%. Secondary amides are also well tolerated, and, gratifyingly, substitution at the nitrogen atom was not observed. Aromatic amide (pyrrolidinyl benzamide) gave corresponding product 4n in good yield. Pyridine N-oxides were also effective in generating radicals from ethers under the reaction conditions developed. Alkylation with diethyl ether, methyl-tert-butyl ether, and 1,4-dioxane in the presence of Zn(OTf) 2 as the activating agent procced in decent yield. Next, the scope of electron-deficient heteroarenes was explored using cyclohexane as the alkylating agent (Scheme 3). 2-Methylquinoline, despite its similarity to lepidine, provided C4 alkylation product 4r in a marginally lower yield (68%), indicating a preference for C2 alkylation. A similar result was obtained for slightly less electron-deficient 2-phenylquinoline (61%). The alkylation of quinolines with electron-withdrawing groups is less efficient. Isoquinolines gave only alkylated products at position 1 (5a). However, substitution at position 5 with the halogen atom led to alkylated derivative 5b in a somewhat diminished yield. For some substrates, fine-tuning of the reaction conditions was required. Increasing the amount of TFA and prolonging the reaction time enabled alkylation of methyl isonicotinate and 4-phenylpyridine, in the first case only a significant amount of monoalkylation product 6a was isolated, for the latter, both mono-and dialkylation products 6b and 6c formed. Similar conditions were used for the monoalkylation of 4,4'-bipyridine (6d). The process is feasible for alkylation of highly conjugated azines, 4-methylbenzo[h]quinoline and phenantridine, although product of the latter 7 formed in a low yield. Heteroaromatics with two nitrogen atoms are also suitable starting materials; benzopirazine and benzopyridiazine furnished predominantly monoalkylated products 9a and 10. In general, the scope of heteroaromatic substrates seems, as for now, limited to quinolines and isoquinolines with slightly electron-donating substituents, which is inherently connected with the need for efficient formation of an EDA complex between the N-oxide and the substrate. Thus, by the proper choice of N-oxides with matching electronic properties, the scope can presumably be broadened. Along this line, we reexamined two selected examples to see if the yields of the corresponding products improve when different N-oxides are used (Table 2). Indeed, for more electron-rich phenantridine, the yield increased when more electron-deficient 2-cyano-6-methylpyridine N-oxide was used. On the contrary, the yield decreased with electron-rich 2,4,6-trimethylpyridine N-oxide as an HAT reagent. More electron-deficient substrate 3-(methoxycarbonyl)-quinoline provided the corresponding product 4w and the yield is virtually independent of the selected N-oxide. Reaction conditions: phenanthridine 0.1 mmol, cyclohexane 1.0 mmol, TFA 0.3 mmol, N-oxide 0.125 mmol in 1.5 ml of MeCN irradiated with 405 nm LED for 18 h, yields determined by GC.</p><p>We have proved that pyridine N-oxides can indeed act as reagents for the activation of inert C-H bonds in the synthetically useful, photochemical Minisci-type alkylation of azines. Next, we turned our attention to understanding their mode of action. During our initial studies, we confirmed that the formation of EDA complex I is a key to this process (Figure 1). The experiment with a radical scavenger confirmed the radical nature of thetransformation. In the presence of TEMPO only traces of the product were observed but when TEMPO was added after 3 hours of irradiation, peaks with m/z corresponding to adducts of radicals III and V with TEMPO were detected by ESI-MS. The formation of hydroxylated products 4e and 4f in the reaction with alkenes conducted under anhydrous conditions corroborates the formation of the hydroxyl radical in the reaction mixture (Scheme 2). Given that there are no other sources of oxygen atoms and the fact that 2,6-lutidine is a byproduct in this reaction, hydroxyl radicals must originate from the protonated N-oxide. Their generation from pyridine N-oxides upon photochemical reduction by an NADH analogue has already been suggested. 11 Based on the evidence collected, we propose a plausible mechanism depicted in Scheme 4. The reaction starts from the formation of an EDA complex I between protonated lepidine and the N-oxide. After irradiation, radical II derived from lepidine and N-oxyl radical cation III is formed. The hydrogen atom is abstracted from a substrate to give corresponding radical V, which then reacts with the protonated lepidine. The resultant radical adduct VI after hydrogen atom abstraction gives the final product in its protonated form. The reaction requires an overstoichiometric amount of N-oxide, and no traces of the reduced product is observed, which imposes the SET process between protonated N-oxide VI and lepidinederived radical II.</p><p>Scheme 4 Mechanistic proposal.</p><p>In conclusion, we have discovered that under light irradiation pyridine N-oxides can act as an HAT reagent. The EDA complex, formed between protonated azines and pyridine N-oxides, provides a Noxyl radical cation, which abstracts a hydrogen atom from alkanes, alkenes, amides, and ethers. The revealed reactivity was tested in a photochemical C-H functionalization of electron-deficient heteroaromatic compounds with formal hydrogen atom donors as alkylating agents. The developed protocol is very simple, as it requires only substrates, a slight excess of N-oxide, and a Brønsted or Lewis acid for the activation of an azine. The scope of an alkylating agent is broad, and the yields of the corresponding products are high. We hope that our discovery will lead to the development of new photochemical methods using pyridine N-oxides as a mild and efficient hydrogen atom transfer reagent.</p>", "role": "user" }, { "content": "Pyridine N-oxides only recenly marked their presence in the photocatalysis outbreak, mainly serving as oxypyridinium salt precursors. Herein, their unique reactivity as a hydrogen atom transfer reagent in photochemical, Minisci-type alkylation of electron-deficient heteroarenes is unveiled. The formation of an EDA complex between a heterocyclic substrate and N-oxide precludes the need for a photocatalyst. The developed method allows for a broad range of radical precursors to be used, namely alkanes, alkenes, amides, and ethers, for efficient alkylation of azines.The relevance of heterocyclic N-oxides in various branches of modern organic chemistry is constantly increasing, 1 primarily used as intermediates in the synthesis of the corresponding heterocyclic compounds, they are now investigated as APIs in therapeutics 2 or as energetic materials.3 Their Lewis basic properties predispose them to be used as organocatalysts, 4 while in transition metal-catalysed C-H activation reactions the constituent oxygen atom serves as a directing group. 5 Furthermore, aromatic N-oxides can also be viewed as nitrones that engage as 1,3-dipoles in dipolar cycloadditions, a very useful method for their C-2 selective functionalization.6Over decades photochemistry of pyridine N-oxides has been extensively studied.7 Their direct photolysis leads to ring contraction, 8 expansion, 9 or fragmentation 10 depending on the substituents.They can also either accept 11 or donate electrons. 12,13 In this regard, the photocatalitcally 13 or electrochemically 12 generated pyridine N-oxyl radical forms complexes with hydrocarbons, which decompose in the absence of oxygen; 13 otherwise a mixture of the corresponding alcohols and ketones is obtained.12 Only recently, have N-oxides marked their presence in the photoredox catalysis outbreak. They mainly serve as precursors of oxypyridinium salts that act as a source of CF 3 and alkyl radicals (Scheme 1A). 14 Recently, Hu et. al. proposed the formation of an electron donor-acceptor complex (EDA) between pyridine N-oxide and the corresponding oxypyridinium salt that enables photochemical cascading trifluorometylation-cyclization of cyanamide alkenes (Scheme 1B). 15 Similarly, N-alkoxy pyridinium salts proved useful in photochemical α-phosphorylation of aromatic tertiary amines.16Scheme 1 Pyridine N-oxide in modern photochemical reactions.", "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:\nSpecific TP53 and/or Ki-ras mutations as independent predictors of clinical outcome in sporadic colorectal adenocarcinomas: results of a 5-year Gruppo Oncologico dell'Italia Meridionale (GOIM) prospective study.\nAbstract 1:\nBACKGROUND Although Ki-ras and TP53 mutations have probably been the genetic abnormalities most exhaustively implicated and studied in colorectal cancer ( CRC ) progression , their significance in terms of disease relapse and overall survival has not yet clearly been established . PATIENTS AND METHODS A prospect i ve study was carried out on paired tumor and normal colon tissue sample s from a consecutive series of 160 previously-untreated patients , undergoing resective surgery for primary operable sporadic CRC . Mutations within the TP53 ( exons 5 - 8 ) and Ki-ras ( exon 2 ) genes were detected by PCR-SSCP analyses following sequencing . RESULTS Mutation analyses of exons 5 to 8 of the TP53 gene showed mutations in 43 % ( 68/160 ) of the cases , while mutation analyses of exon 2 of the Ki-ras gene showed mutations in 46 % ( 74/160 ) of the cases . Multivariate analyses showed that clinical outcome were strongly associated with the presence of specific TP53 mutations in L3 domain alone ( only in DFS ) or in combination with specific Ki-ras mutations at codon 13 . CONCLUSION Specific TP53 mutations in L3 domain alone ( only in DFS ) or in combination with specific Ki-ras mutations at codon 13 are associated with a worse prognosis in sporadic CRC\n\n\nTitle 2:\nSpecific codon 13 K-ras mutations are predictive of clinical outcome in colorectal cancer patients, whereas codon 12 K-ras mutations are associated with mucinous histotype.\nAbstract 2:\nBACKGROUND K-ras mutations , one of the earliest events observed in colorectal carcinogenesis , are mostly found in codons 12 and 13 , and less frequently in codon 61 , all three of which are estimated to be critical for the biological activity of the protein . Nevertheless the prognostic significance of such mutations remains controversial . Our purpose was to assess whether any or specific K-ras mutations in primary colorectal cancer had prognostic significance and were linked to clinico-pathological parameters . PATIENTS AND METHODS Paired tumor and normal tissue sample s from a consecutive series of 160 untreated patients ( median of follow up 71 months ) , undergoing resective surgery for primary colorectal carcinoma , were prospect ively studied for K-ras mutations by PCR/single str and conformation polymorphism sequencing . RESULTS Seventy-four of the 160 ( 46 % ) primary colorectal carcinomas presented mutations in K-ras : 54 % in codon 12 , 42 % in codon 13 ( particularly G-->A transition ) and 4 % in both . Codon 12 K-ras mutations were associated with mucinous histotype ( P < 0.01 ) , while codon 13 K-ras mutations were associated with advanced Dukes ' stage ( P < 0.05 ) , lymph-node metastasis ( P < 0.05 ) and high S-phase fraction ( P < 0.05 ) . Multivariate analysis showed that codon 13 K-ras mutations , but not any mutation , were independently related to risk of relapse or death . CONCLUSIONS Our results suggest that codon 12 K-ras mutations may have a role in the mucinous differentiation pathway , while codon 13 mutations have biological relevance in terms of colorectal cancer clinical outcome\n\n\nTitle 3:\nThe type of K-ras mutation determines prognosis in colorectal cancer.\nAbstract 3:\nBACKGROUND Mutations involving the oncogene K-ras in colorectal cancer may be related to tumor aggressiveness . However , the value of K-ras gene determination as a prognostic marker has not been clearly established . PATIENTS AND METHODS The results from 98 patients recruited in a prospect i ve study analyzing the effect of a K-ras mutation as a prognostic factor in colorectal cancer are reported . RESULTS Disease-free ( P = 0.02 ) and overall survival ( P = 0.03 ) were significantly reduced for patients harboring a K-ras mutation . Two specific mutations demonstrated a significantly increased risk of disease recurrence , namely , 12-TGT ( P = 0.04 ) and 13-GAC substitutions ( P = 0.002 ) . Patients with either of these substitutions had a 2-year disease-free survival rate of 37 % compared with that of 67 % for the group of patients harboring any other mutation type or a wild-type status ( P = 0.01 ) . CONCLUSIONS The results herein presented suggest that K-ras acts as a prognostic factor in colorectal cancer and that this effect is probably related to a limited number of defined mutations\n\n\nTitle 4:\nPrognostic factors of colorectal cancer: K-ras mutation, overexpression of the p53 protein, and cell proliferative activity.\nAbstract 4:\nBetween June 1990 and April 1991 , 62 colorectal tumors were assessed in a prospect i ve fashion on the basis of various tumor characteristics . Parameters included K-ras mutation , overexpression of the p53 protein , and proliferating cell nuclear cell antigen , as well as st and ard histopathologic examination . A multivariate analysis showed that K-ras mutation correlated with vascular invasion ( P < 0.01 ) and hematogenous metastasis ( P < 0.01 ) . With regard to survival time , multivariate analyses using the Cox proportional hazard model suggested that status of lymph node metastasis ( P < 0.01 , relative risk [ rr ] = 7.27 ) , TNM stage ( P < 0.05 , rr = 5.37 ) , lymphatic invasion ( P < 0.05 , rr = 4.48 ) , and K-ras mutation ( P < 0.06 , rr = 3.69 ) are the most independent prognostic factors . We compared the prognostic value of the molecular assays and st and ard TNM prognostic factors by multivariate analysis\n\n\nTitle 5:\np53 and K-ras gene mutations correlate with tumor aggressiveness but are not of routine prognostic value in colorectal cancer.\nAbstract 5:\nPURPOSE p53 gene and K-ras mutations are among the most common genetic alterations present in colorectal cancer . The prognostic utility of such mutations remains controversial . The purpose of this study was to prospect ively evaluate the prognostic significance of p53 and K-ras gene mutations in colorectal cancer . PATIENTS AND METHODS One hundred forty patients were analyzed . Tumors belonging to the microsatellite mutator phenotype were excluded ( n = 8) . Mutations at the K-ras and p53 genes were detected and characterized by restriction fragment length polymorphism , single-str and conformation polymorphism , and sequencing , as appropriate . RESULTS p53 mutations were detected in 66 ( 50 % ) and K-ras mutations were detected in 54 ( 41 % ) of the 132 patients . In 26 cases ( 20 % ) , ras and p53 mutations coexisted ; in 38 cases ( 29 % ) , neither mutation was found . Multivariate analysis of the whole population analyzed ( n = 132 ) showed that survival was strongly correlated with the presence of p53 mutations alone or in combination with K-ras mutations ( P = .002 ; log-rank test ) . When only patients undergoing a radical resection were considered ( R0 ; n = 101 ) , p53 mutations were no longer of prognostic significance . CONCLUSION p53 mutations alone or in combination with K-ras mutations are correlated with a worse outcome . However , the routine use of these mutations as prognostic markers in the clinical setting is not recommended\n\n\nTitle 6:\nClinical Significance of K-Ras Mutations in Intraoperative Tumor Drainage Blood From Patients With Colorectal Carcinoma\nAbstract 6:\nBackground : Recurrent and metastatic carcinoma of the colorectum remains a major problem . This may be ascribed to the presence of micrometastasis at diagnosis . The purpose of this study was to analyze prospect ively the clinical value of detecting K-ras mutations in the perioperative circulating blood from patients with colorectal carcinoma . Methods : Twenty-four patients whose tumor carried mutations in codon 12 of the K-ras gene were studied for the presence of cancer cells in perioperative blood sample s , in particular , tumor drainage sample s. A detection assay using CD45 immunomagnetic separation plus nested mutant allele specific amplification ( MASA ) was performed . Results : K-ras mutations in CD45 negative cells in tumor drainage blood were detected in 7 ( 29.2 % ) of 24 patients . There was no significant relationship between the presence of a K-ras mutation and clinicopathological features . Four ( 57.1 % ) of the seven patients with a positive K-ras mutation in drainage blood had early recurrent disease . Of the 17 patients with no K-ras mutation , none developed metastatic disease . The recurrence rate of the K-ras mutation positive group was higher than that of the K-ras mutation negative group ( P < .01 ) . There was a significant difference , regarding prognosis , between K-ras mutation positive and negative groups ( P < .01 ) . Conclusions : This preliminary study demonstrates that the detection of circulating cancer cells in the tumor drainage blood by our new assay system may provide a predictor of recurrence and metastasis of colorectal cancer\n\n\nTitle 7:\nK-ras and p16 aberrations confer poor prognosis in human colorectal cancer.\nAbstract 7:\nPURPOSE Mutations in the K-ras gene are frequent in human cancer . ras activation in primary cells results in a cellular senescence phenotype that is precluded by inactivation of p16 . At the clinical level , this may imply a differential behavior for tumors with alternative or cooperative activation of K-ras function and impairment of p16 pathways . PATIENTS AND METHODS We have determined the presence of mutations in the K-ras gene and the methylation status of p16 promoter in a series of 119 prospect ively collected colorectal carcinomas . p53 mutations and p14 alternative reading frame methylation status were also assessed . Associations with survival were investigated . RESULTS K-ras mutations were present in 44 ( 38 % ) of 115 cases , and p16 methylation was present in 42 ( 37 % ) of 113 cases . p53 mutations were detected in 50 % ( 56 of 115 ) and p14 methylation in 29 % ( 32 of 112 ) of cases . K-ras and p16 alterations were independent genetic events . Presence of K-ras or p16 genetic alterations ( analyzed independently ) was associated with shorter survival , although differences were not statistically significant . Cox analysis of the two variables combined showed a diminished survival as the results of an interaction between p16 and K-ras . Alternative alteration of K-ras and p16 genes was an independent prognostic factor in human colorectal cancer in univariate and multivariate analysis . Differences were maintained when cases undergoing radical surgery and without distant metastases were considered . CONCLUSION These results suggest that the combined K-ras and p16 analyses may be of prognostic use in human colorectal cancer\n\n\nTitle 8:\nPhase II trial of cetuximab in patients with refractory colorectal cancer that expresses the epidermal growth factor receptor.\nAbstract 8:\nPURPOSE To evaluate the antitumor activity and toxicity of single-agent cetuximab in patients with chemotherapy-refractory colorectal cancer whose tumors express the epidermal growth factor receptor . PATIENTS AND METHODS Phase II , open-label clinical trial . Patients were required to have EGFr expression demonstrated on formalin-fixed paraffin-embedded tumor tissue by immunohistochemical staining before study participation . Patients were required to have received irinotecan , either alone or in a combination regimen , and to have demonstrated clinical failure on this regimen before study entry . Cetuximab was administered weekly by intravenous infusion . The first dose of 400 mg/m(2 ) was given during the course of 2 hours . Subsequent weekly treatments were given at a dose of 250 mg/m(2 ) during the course of 1 hour . RESULTS Fifty-seven eligible patients were treated . All were assessable for toxicity and response . The most commonly encountered grade 3 to 4 adverse events , regardless of relationship to study drug , were an acne-like skin rash , predominantly on the face and upper torso ( 86 % with any grade ; 18 % with grade 3 ) , and a composite of asthenia , fatigue , malaise , or lethargy ( 56 % with any grade , 9 % with grade 3 ) . Two patients ( 3.5 % ) experienced grade 3 allergic reactions requiring discontinuation of study treatment . A third patient experienced a grade 3 allergic reaction that resolved , and the patient continued on the study . Neither diarrhea nor neutropenia were dose limiting in any of the 57 patients treated . Five patients ( 9 % ; 95 % CI , 3 % to 19 % ) achieved a partial response . Twenty-one additional patients had stable disease or minor responses . The median survival in these previously treated patients with chemotherapy-refractory colorectal cancer is 6.4 months . CONCLUSION Cetuximab on this once-weekly schedule has modest activity and is well-tolerated as a single agent in patients with chemotherapy-refractory colorectal cancer whose tumors express the epidermal growth factor receptor . Further studies of cetuximab will evaluate the use of cetuximab in conjunction with first-line and adjuvant treatments for this disease", "role": "user" }, { "content": ": Overall K-ras gene mutations seem not to correlate with the prognosis of patients with colorectal cancer .", "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\nExperimental reproducibility and replicability are critical topics in machine learning.\nAuthors have often raised concerns about their lack in scientific publications to improve the quality of the field.\nRecently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works.\n\nAs such, several Graph Neural Network models have been developed to effectively tackle graph classification.\nHowever, experimental procedures often lack rigorousness and are hardly reproducible.\nMotivated by this, we provide an overview of common practices that should be avoided to fairly compare with the state of the art.\nTo counter this troubling trend, we ran more than 47000 experiments in a controlled and uniform framework to re-evaluate five popular models across nine common benchmarks.\nMoreover, by comparing GNNs with structure-agnostic baselines we provide convincing evidence that, on some datasets, structural information has not been exploited yet.\nWe believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.\nOver the years, researchers have raised concerns about several flaws in scholarship, such as experimental reproducibility and replicability in machine learning (McDermott, 1976; Lipton & Steinhardt, 2018) and science in general (National Academies of Sciences & Medicine, 2019) .\nThese issues are not easy to address, as a collective effort is required to avoid bad practices.\nExamples include the ambiguity of experimental procedures, the impossibility of reproducing results and the improper comparison of machine learning models.\nAs a result, it can be difficult to uniformly assess the effectiveness of one method against another.\nThis work investigates these issues for the graph representation learning field, by providing a uniform and rigorous benchmarking of state-of-the-art models.\nGraph Neural Networks (GNNs) (Micheli, 2009; Scarselli et al., 2008) have recently become the standard tool for machine learning on graphs.\nThese architectures effectively combine node features and graph topology to build distributed node representations.\nGNNs can be used to solve node classification (Kipf & Welling, 2017) and link prediction tasks, or they can be applied to downstream graph classification (Bacciu et al., 2018) .\nIn literature, such models are usually evaluated on chemical and social domains (Xu et al., 2019) .\nGiven their appeal, an ever increasing number of GNNs is being developed (Gilmer et al., 2017) .\nHowever, despite the theoretical advancements reached by the latest contributions in the field, we find that the experimental settings are in many cases ambiguous or not reproducible.\nSome of the most common reproducibility problems we encounter in this field concern hyperparameters selection and the correct usage of data splits for model selection versus model assessment.\nMoreover, the evaluation code is sometimes missing or incomplete, and experiments are not standardized across different works in terms of node and edge features.\nThese issues easily generate doubts and confusion among practitioners that need a fully transparent and reproducible experimental setting.\nAs a matter of fact, the evaluation of a model goes through two different phases, namely model selection on the validation set and model assessment on the test set.\nClearly, to fail in keeping these phases well separated could lead to over-optimistic and biased estimates of the true performance of a model, making it hard for other researchers to present competitive results without following the same ambiguous evaluation procedures.\nWith this premise, our primary contribution is to provide the graph learning community with a fair performance comparison among GNN architectures, using a standardized and reproducible experimental environment.\nMore in detail, we performed a large number of experiments within a rigorous model selection and assessment framework, in which all models were compared using the same features and the same data splits.\nSecondly, we investigate if and to what extent current GNN models can effectively exploit graph structure.\nTo this end, we add two domain-specific and structure-agnostic baselines, whose purpose is to disentangle the contribution of structural information from node features.\nMuch to our surprise, we found out that these baselines can even perform better than GNNs on some datasets; this calls for moderation when reporting improvements that do not clearly outperform structure-agnostic competitors.\nOur last contribution is a study on the effect of node degrees as features in social datasets.\nIndeed, we show that providing the degree can be beneficial in terms of performances, and it has also implications in the number of GNN layers needed to reach good results.\nWe publicly release code and dataset splits to reproduce our results, in order to allow other researchers to carry out rigorous evaluations with minimum additional effort 1 .\nDisclaimer Before delving into the work, we would like to clarify that this work does not aim at pinpointing the best (or worst) performing GNN, nor it disavows the effort researchers have put in the development of these models.\nRather, it is intended to be an attempt to set up a standardized and uniform evaluation framework for GNNs, such that future contributions can be compared fairly and objectively with existing architectures.\nIn this paper, we wanted to show how a rigorous empirical evaluation of GNNs can help design future experiments and better reason about the effectiveness of different architectural choices.\nTo this aim, we highlighted ambiguities in the experimental settings of different papers, and we proposed a clear and reproducible procedure for future comparisons.\nWe then provided a complete re-evaluation of five GNNs on nine datasets, which required a significant amount of time and computational resources.\nThis uniform environment helped us reason about the role of structure, as we found that structure-agnostic baselines outperform GNNs on some chemical datasets, thus suggesting that structural properties have not been exploited yet.\nMoreover, we objectively analyzed the effect of the degree feature on performances and model selection in social datasets, unveiling an effect on the depth of GNNs.\nFinally, we provide the graph learning community with reliable and reproducible results to which GNN practitioners can compare their architectures.\nWe hope that this work, along with the library we release, will prove useful to researchers and practitioners that want to compare GNNs in a more rigorous way.", "role": "user" }, { "content": "We provide a rigorous comparison of different Graph Neural Networks for graph classification.", "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 CRAPome database?\n\nContext: the contaminant repository for affinity purification (the CRAPome)", "role": "user" }, { "content": "The CRAPome is a contaminant repository for affinity purification-mass spectrometry data.", "role": "assistant" } ]

[ { "content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"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\nHypomorphic mutations in meckelin (MKS3/TMEM67) cause nephronophthisis with liver fibrosis (NPHP11). BACKGROUND: Nephronophthisis (NPHP), a rare recessive cystic kidney disease, is the most frequent genetic cause of chronic renal failure in children and young adults. Mutations in nine genes (NPHP1-9) have been identified. NPHP can be associated with retinal degeneration (Senior-Loken syndrome), brainstem and cerebellar anomalies (Joubert syndrome), or liver fibrosis. METHODS: To identify a causative gene for the subset of patients with associated liver fibrosis, the authors performed a genome wide linkage search in a consanguineous family with three affected patients using 50K SNP microarrays and homozygosity mapping. RESULTS: The authors obtained a significant maximum parametric LOD (logarithm of odds) score of Z(max) = 3.72 on chromosome 8q22 and identified a homozygous missense mutation in the gene MKS3/TMEM67. When examining a worldwide cohort of 62 independent patients with NPHP and associated liver fibrosis we identified altogether four novel mutations (p.W290L, p.C615R, p.G821S, and p.G821R) in five of them. Mutations of MKS3/TMEM67, found recently in Meckel-Gruber syndrome (MKS) type 3 and Joubert syndrome (JBTS) type 6, are predominantly truncating mutations. In contrast, the mutations detected here in patients with NPHP and associated liver fibrosis are exclusively missense mutations. This suggests that they may represent hypomorphic alleles, leading to a milder phenotype compared with the more severe MKS or JBTS phenotype. Additionally, mutation analysis for MKS3/TMEM67 in 120 patients with JBTS yielded seven different (four novel) mutations in five patients, four of whom also presented with congenital liver fibrosis. CONCLUSIONS: Hypomorphic MKS3/TMEM67 mutations cause NPHP with liver fibrosis (NPHP11). This is the first report of MKS3 mutations in patients with no vermian agenesis and without neurological signs. Thus NPHP, JBTS, and MKS represent allelic disorders.", "role": "user" }, { "content": "{\"Gene\": [\"meckelin\", \"MKS3\", \"TMEM67\", \"NPHP1-9\", \"NPHP11\"]}", "role": "assistant" } ]

[ { "content": "You will be given an abstract from a computer science research paper. Given the abstract, your task is to extract all unique relationships between entities of the following, and ONLY the following, types:\n\n- \"USED-FOR\": For instance, \"Our method models user proficiency\" -> [\"method\", \"user proficiency\", \"USED-FOR\"].\n- \"EVALUATE-FOR\": For instance, \"We evaluate our method using F1-measure\" -> [\"F1-measure\", \"method\", \"EVALUATE-FOR\"].\n- \"FEATURE-OF\": For instance, \"prior knowledge of the model\" -> [\"prior knowledge\", \"model\", \"FEATURE-OF\"].\n- \"HYPONYM-OF\": For instance, \"TUIT is a software library\" -> [\"TUIT\", \"software library\", \"HYPONYM-OF\"].\n- \"PART-OF\": For instance, \"We incorporate NLU module into the system\" -> [\"NLU module\", \"system\", \"PART-OF\"].\n- \"COMPARE\": For instance, \"Unlike the quantitative prior, the qualitative prior is often ignored\" -> [\"quantitative prior\", \"qualitative prior\", \"COMPARE\"].\n- \"CONJUNCTION\": For instance, \"obtained from human expert or knowledge base\" -> [\"human expert\", \"knowledge base\", \"CONJUNCTION\"].\n\nFormat your output as a JSON array. Each entry in the array should express a single relation, formatted as [\"<Entity_A>\", \"<Entity_B>\", \"<RELATION_A_B>\"]. An example output might look like:\n\n[[\"neural networks\", \"classification\", \"USED-FOR\"], [\"neuron\", \"neural network\", \"PART-OF\"]].\n\nIf no relations are found, please return an empty JSON array \"[]\".\n\nAbstract:\n\nThis paper presents a maximum entropy word alignment algorithm for Arabic-English based on supervised training data. We demonstrate that it is feasible to create training material for problems in machine translation and that a mixture of supervised and unsupervised methods yields superior performance. The probabilistic model used in the alignment directly models the link decisions. Significant improvement over traditional word alignment techniques is shown as well as improvement on several machine translation tests. Performance of the algorithm is contrasted with human annotation performance.", "role": "user" }, { "content": "[[\"training material\", \"machine translation\", \"USED-FOR\"], [\"maximum entropy word alignment algorithm\", \"human annotation\", \"COMPARE\"], [\"supervised training data\", \"maximum entropy word alignment algorithm\", \"USED-FOR\"], [\"word alignment techniques\", \"machine translation tests\", \"USED-FOR\"], [\"probabilistic model\", \"link decisions\", \"USED-FOR\"], [\"probabilistic model\", \"alignment\", \"USED-FOR\"], [\"Arabic-English\", \"maximum entropy word alignment algorithm\", \"USED-FOR\"]]", "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: Retinal Ganglion Cells Can Rapidly Change Polarity from Off to On \nArticle:\nAbstract:\nRetinal ganglion cells are commonly classified as On-center or Off-center depending on whether they are excited predominantly by brightening or dimming within the receptive field. Here we report that many ganglion cells in the salamander retina can switch from one response type to the other, depending on stimulus events far from the receptive field. Specifically, a shift of the peripheral image—as produced by a rapid eye movement—causes a brief transition in visual sensitivity from Off-type to On-type for approximately 100 ms. We show that these ganglion cells receive inputs from both On and Off bipolar cells, and the Off inputs are normally dominant. The peripheral shift strongly modulates the strength of these two inputs in opposite directions, facilitating the On pathway and suppressing the Off pathway. Furthermore, we identify certain wide-field amacrine cells that contribute to this modulation. Depolarizing such an amacrine cell affects nearby ganglion cells in the same way as the peripheral image shift, facilitating the On inputs and suppressing the Off inputs. This study illustrates how inhibitory interneurons can rapidly gate the flow of information within a circuit, dramatically altering the behavior of the principal neurons in the course of a computation.\nIntroduction:\nIn the retina, signals flow along parallel, spatially distributed pathways[1]. A major split occurs at the very first synapse: On bipolar cells and Off bipolar cells respond to light with the opposite sign. Retinal ganglion cells receive excitatory input from On or Off bipolars within their dendritic field. Accordingly, On ganglion cells are excited by an increase of illumination in the receptive field center, and Off ganglion cells by a decrease. In addition, certain ganglion cells draw on both bipolar cell types, and are excited transiently both at the onset and the offset of illumination[2, 3]. Light falling on the receptive field surround generally antagonizes the action of light in the center: An On cell will be inhibited and an Off cell excited. By contrast, moving stimuli in the receptive field surround can cause a great variety of effects. Pure image motion in the periphery, without stimulation of the receptive field center, is often found to excite retinal ganglion cells[4–7], although certain moving patterns produce inhibition[8–10]. When the receptive field center is stimulated as well, peripheral motion generally suppresses the cell's sensitivity to the center[11–14], with the occasional differing report[6]. In natural vision, large displacements of the entire visual field are very common[15, 16]. Some animals, including humans, make eye saccades several times a second, whereas others move their heads to explore a visual scene; in either case, the image shifts rapidly over the retina. Human visual sensitivity decreases dramatically during a saccade, and also during passive image shifts in absence of eye movements[17, 18]. Thus at least part of the suppression is triggered by the visual stimulus, rather than central eye control signals. Both saccades and passive peripheral image shifts inhibit visual responses in the lateral geniculate nucleus[18, 19], and this may well be the site of the perceptual suppression[20]. The picture emerging from these studies is that each visual neuron monitors events within its receptive field, but the gain of its response to these stimuli can be modulated by global shifts in the image. Here we present evidence from retinal ganglion cells showing that an image shift can have more profound effects by fundamentally altering what stimulus features the neuron will sense. In extreme cases, this leads to the transient conversion of an Off response into an On response. Exploring the retinal circuits underlying this response reversal, we found that the effect of an image shift can be mimicked by depolarizing certain amacrine cells. These are part of the lateral network that communicates global image motion to the ganglion cells.\nDiscussion:\nA popular view of sensory neurons treats them as “labeled lines”: Each nerve fiber is labeled with a certain sensory feature, and the neuron's firing reports to central brain circuits how prominent that feature is in the stimulus[33]. In this picture, a peripheral image shift leads to a sudden and transient relabeling of optic nerve fibers, and we showed that for some retinal ganglion cells, this relabeling amounts to a complete change in sign of the sensory feature. Under these conditions, the labeled line picture is of limited value, and it becomes necessary to inspect this dynamic process further. Although all ganglion cell types experience a change in neural coding( Figure 2), the issue is most clearly illustrated by the On-Off cells. Figure 10 plots the visual message of such a neuron for spikes produced at different times before or after the image shift. When there is no motion in the periphery, a spike from this neuron reports a dimming within its receptive field. But shortly after a peripheral image shift, a spike stands for a brightening in the receptive field. One notable aspect of the recoding is its speed: It occurs with a short latency of about 80 ms after the image shift, and the change in sign of the visual message lasts only about 100 ms( Figures 2C, 5B, and 6B). By comparison, the duration of the spike-triggered average stimulus is about 400 ms( Figures 4A and 10). Thus the modulation of the message carried by the neuron occurs on a time scale shorter than the visual message itself. This is in clear distinction to various adaptation phenomena—such as light adaptation[34] and contrast adaptation[23]—for which the coding rules can change on a time scale considerably longer than the message. As a consequence of this very rapid modulation, one finds that the change in sign of the visual message extends even to time points that precede the peripheral image shift( dashed line in Figure 10). This means that a light stimulus at one point in time may either increase or decrease the neuron's firing, but the decision about this is made only later in time, depending on the occurrence of an image shift. It may seem paradoxical that the report to the brain about one visual event can be altered by a subsequent visual event, but similar effects are well known in human perception, for example in phenomena of “backward masking”[35]. The present instance is easily understood in the context of the circuit model in Figure 7. The temporal integration that determines the 0. 4-s time course of the visual message is performed separately in each of the bipolar cell pathways; thus, each bipolar cell holds a record of events 0. 4 s in the past. The amacrine cell circuit then simply switches which of those two records gets forwarded to the ganglion cell, without altering the content of the bipolar cell signal( Figure 5C). In natural vision, large image shifts happen prominently during saccadic eye or head movements[15, 16]. What are the functional consequences of the observed “relabeling” for the coding of such visual events? First, it is useful to note the temporal properties of the neural message from the typical ganglion cell. The average stimulus preceding a spike( Figure 10) is a biphasic curve, with almost perfect cancellation between the positive and negative lobes. This means that the neuron reports the difference between the current intensity and the preceding intensity. This is a common feature of ganglion cells in many species[36, 37]. Under baseline conditions, long before or after the saccade, the neuron of Figure 10 is excited by a decrease in intensity, but shortly after the saccade, it is excited by an increase in intensity. For spikes emitted during this period, the negative lobe of the visual message falls before the saccade and the positive lobe falls after the saccade. Therefore, these spikes report the change in the retinal image that is introduced by the saccade, whereas spikes occurring earlier or later report changes intrinsic to the visual scene. For saccade-related image changes, this neuron reports a brightening, but for scene-related changes, it reports a dimming. What could be the possible benefit of such a scheme? Most vertebrate retinas show an asymmetry between the On and Off pathways: Generally the Off ganglion cells are more numerous and have smaller receptive fields[38–40]. Various ecological arguments have been invoked for this; in the case of amphibians, the bias may be related to a behavioral preference for dark hiding spots[15, 41]. In the salamander, the predominance of Off-type retinal responses is evident regardless of how one samples the optic nerve signals[42–44]. Even among the On-Off ganglion cells, there is a strong bias toward the Off pathway under baseline conditions[45]( Figure 6A). However, during the brief period that encodes saccade-related changes in the image, this bias transiently disappears, and over the entire population of ganglion cells, the On responses are as frequent as Off responses( Figure 6B). Note that image changes resulting from a rigid shift have an important distinguishing property: comparing all points in the image, the intensity increases are necessarily matched by intensity decreases. This is true even if the image itself is strongly biased, say for small dark objects on a large bright background. Thus, if the goal is to signal the image changes that result from a saccade, it is best to treat brightening and dimming on an equal footing, and devote the same number of On and Off channels. After the saccade, the ganglion cell population reverts to signaling scene-related changes, with an Off bias presumably governed by the ethological goals of visual analysis. The rapid switch allows the retina to use the same resources for two different modes, interleaved in time. Clearly, this interpretation is speculative and would benefit from further insight into the use of saccade-related signals in downstream visual areas. It is a common observation in retinal studies that large-scale image motion causes a suppression of local processing[10–12], and this is thought to be implemented via inhibition from long-range amacrine cells[13, 14]. In addition to this suppression, we found a strong transient enhancement that was specific to the On pathway( Figure 6B). We propose that this sign inversion is implemented by a second amacrine cell, which tonically suppresses the On pathway[46], but is itself inhibited by the image shift( Figure 7). Although alternative circuits can be imagined to implement the observed effects, we identified a type of wide-field amacrine cell that seems to act as proposed in Figure 7. This neuron gets depolarized by a peripheral image shift, and in turn its activity can alter the On/Off balance in nearby ganglion cells by a factor of 2. Because amacrine cells are frequently coupled by electrical junctions, injecting current into one neuron may well depolarize more than one cell. However, the currents used were similar in strength to the synaptic currents under visual stimulation[47], and thus the same events are likely to occur during routine visual processing. This raises the question of how strongly individual amacrine cells in this population are driven by visual stimuli short of a global image shift, for example from local movement within the scene, since such stimuli could result in local modulation of the On/Off ratios among ganglion cells. Note that these transient On-type amacrine cells( Figure 8) are different from the Off-type polyaxonal amacrine cells involved in the processing of small fixational eye movements[14]. Thus, there is some progress in identifying functions for specific subcircuits and interneurons of the retina, though the intricacy of the inner plexiform layer still leaves many challenges[48]. For example, it is clear that other kinds of amacrine cells also contribute to suppression of the Off pathway by an image shift, since much of this survives when On responses are blocked in APB( Figure 3C). Seen in a broader context, we have illustrated an instance in which two very different signaling pathways are connected to a target neuron, and a neural switch controls which of the pathways is allowed to provide the input signal( Figure 7). Such switching circuits have been postulated previously, to explain dramatic changes in neuronal selectivities. For example, the visual receptive field of a cortical neuron can shift depending on the state of the animal's attention[49]. Also, in experiments that induce binocular rivalry, some cortical neurons appear to be connected alternatingly to the left or the right eye[50]. More generally, the ability to rapidly reroute information flow based on the outcome of an earlier computation is essential in computing machines, and it is difficult to imagine brain function without it[51]. It is intriguing to find the principle used as early as the retina. Here it appears that switching is accomplished by inhibitory local neurons( Figures 8 and 9) that control individual synaptic inputs to the target neuron, presumably through mechanisms of presynaptic inhibition( Figure 7). It will be useful to study this neural switch in more detail, and test whether the mechanisms generalize to other brain circuits.", "role": "user" }, { "content": "The eye communicates to the brain all the information needed for vision in the form of electrical pulses , or spikes , on optic nerve fibers . These spikes are produced by retinal ganglion cells , the output neurons of the retina . In a popular view of retinal function , each ganglion cell responds to a small region of interest in the visual image , known as its receptive field , and is specialized for certain image features within that window . When a cell encounters that image feature , the neuron responds by firing one or more spikes . Different neurons are tuned to different features . For example , some ganglion cells fire when light dims , others when it brightens . Here we show that a rapid shift in the image on the retina can cause a dramatic change in a neuron's preferred feature: For example , a dimming-detector can briefly turn into a brightening-detector . We explore the mechanisms that implement such a switch of feature tuning , and the consequences it might have for visual processing .", "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\nRecent advancements in small molecule inhibitors of insulin-like growth factor-1 receptor (IGF-1R) tyrosine kinase as anticancer agents. Advancements in understanding of the genetics, genomics, biochemistry and the pharmacology of cancer inhuman, have driven the current cancer chemotherapy to intently focus on development of target-based approaches rather than conventional approaches. From among the various targets identified, validated and inhibited at different hallmarks of cancer, protein tyrosine kinases (PTKs) have been exploited the most. Insulin receptors (IRs), insulin like growth factor receptors (IGF-1R) and their hybrid receptors belong to tyrosine kinase receptor (TKR) family, constitute a structural homology among them and generate a growth promoting IGF system on binding with either insulin, IGF-1 or IGF-2. The system induces the mitogenic effects through a torrent of cell signals produced as a result of cross talk with other growth promoting peptides and steroidal hormones, ultimately resulting in hijacking apoptosis and increasing cell proliferation and cell survival in cancer cells. Various strategies such as anti-IGF-1R antibodies, IGF-1 mimetic peptides, antisense strategies, IGF-1R specific peptide aptamers, targeted degradation of IGF-1R and expression of dominant negative IGF-1R mutants have been explored to inhibit the IGF-1R signaling. However, targeting IGF-1R with small molecules has gained considerable attention in last few years due to their ease of synthesis, ease of optimization of absorption,distribution, metabolism, excretion and toxicity (ADMET) parameters, oral route of administration, lesser side effects and cost effectiveness. The present review provides a broad overview and discusses the highlights on discoveries, SAR studies and binding interactions of small molecules with either IGF-1R active or allosteric sites reported till date.", "role": "user" }, { "content": "{\"Chemical\": [\"steroidal hormones\", \"tyrosine\"]}", "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:\nBosutinib versus imatinib in newly diagnosed chronic-phase chronic myeloid leukemia: results from the BELA trial.\nAbstract 1:\nPURPOSE Bosutinib is an oral Src/Abl tyrosine kinase inhibitor . The phase III Bosutinib Efficacy and Safety in Newly Diagnosed Chronic Myeloid Leukemia ( BELA ) trial compared bosutinib with imatinib in newly diagnosed , chronic-phase chronic myeloid leukemia ( CML ) . PATIENTS AND METHODS A total of 502 patients were r and omly assigned 1:1 to bosutinib 500 mg per day or imatinib 400 mg per day . RESULTS The complete cytogenetic response ( CCyR ) rate at 12 months was not different for bosutinib ( 70 % ; 95 % CI , 64 % to 76 % ) versus imatinib ( 68 % ; 95 % CI , 62 % to 74 % ; two-sided P = .601 ) ; therefore , the study did not achieve its primary end point . The major molecular response ( MMR ) rate at 12 months was higher with bosutinib ( 41 % ; 95 % CI , 35 % to 47 % ) compared with imatinib ( 27 % ; 95 % CI , 22 % to 33 % ; two-sided P < .001 ) . Time to CCyR and MMR was faster with bosutinib compared with imatinib ( two-sided P < .001 for both ) . On-treatment transformation to accelerated/blast phase occurred in four patients ( 2 % ) on bosutinib compared with 10 patients ( 4 % ) on imatinib . A total of three CML-related deaths occurred on the bosutinib arm compared with eight on the imatinib arm . The safety profiles of bosutinib and imatinib were distinct ; GI and liver-related events were more frequent with bosutinib , whereas neutropenia , musculoskeletal disorders , and edema were more frequent with imatinib . CONCLUSION This ongoing trial did not meet its primary end point of CCyR at 12 months , despite the observed higher MMR rate at 12 months , faster times to CCyR and MMR , fewer on-treatment transformations to accelerated/blast phase , and fewer CML-related deaths with bosutinib compared with imatinib . Each drug had a distinct safety profile\n\n\nTitle 2:\nMulticenter independent assessment of outcomes in chronic myeloid leukemia patients treated with imatinib.\nAbstract 2:\nBACKGROUND Imatinib slows development of chronic myeloid leukemia ( CML ) . However , available information on morbidity and mortality is largely based on sponsored trials , whereas independent long-term field studies are lacking . PATIENTS AND METHODS Consecutive CML patients who started imatinib treatment before 2005 and who were in complete cytogenetic remission ( CCyR ) after 2 years ( ± 3 months ) were eligible for enrollment in the independent multicenter Imatinib Long-Term ( Side ) Effects ( ILTE ) study . Incidence of the first serious and nonserious adverse events and loss of CCyR were estimated according to the Kaplan-Meier method and compared with the st and ard log-rank test . Attainment of negative Philadelphia chromosome hematopoiesis was assessed with cytogenetics and quantitative polymerase chain reaction . Cumulative incidence of death related or unrelated to CML progression was estimated , accounting for competing risks , according to the Kalbleisch-Prentice method . St and ardized incidence ratios were calculated based on population rates specific for sex and age classes . Confidence intervals were calculated by the exact method based on the χ(2 ) distribution . All statistical tests were two-sided . RESULTS A total of 832 patients who were treated for a median of 5.8 years were enrolled . There were 139 recorded serious adverse events , of which 19.4 % were imatinib-related . A total of 830 nonserious adverse events were observed in 53 % of patients ; 560 ( 68 % ) were imatinib-related . The most frequent were muscle cramps , asthenia , edema , skin fragility , diarrhea , tendon , or ligament lesions . Nineteen patients ( 2.3 % ) discontinued imatinib because of drug-related toxic effects . Forty-five patients lost CCyR , at a rate of 1.4 per 100 person-years . Durable ( > 1 year ) negative Philadelphia chromosome hematopoiesis was attained by 179 patients . Twenty deaths were observed , with a 4.8 % mortality incidence rate ( st and ardized incidence ratio = 0.7 ; 95 % confidence interval = 0.40 to 1.10 , P = .08 ) , with only six ( 30 % ) associated with CML progression . CONCLUSIONS In this study , CML-related deaths were uncommon in CML patients who were in CCyR 2 years after starting imatinib , and survival was not statistically significantly different from that of the general population\n\n\nTitle 3:\nImatinib compared with interferon and low-dose cytarabine for newly diagnosed chronic-phase chronic myeloid leukemia.\nAbstract 3:\nBACKGROUND Imatinib , a selective inhibitor of the BCR-ABL tyrosine kinase , produces high response rates in patients with chronic-phase chronic myeloid leukemia ( CML ) who have had no response to interferon alfa . We compared the efficacy of imatinib with that of interferon alfa combined with low-dose cytarabine in newly diagnosed chronic-phase CML . METHODS We r and omly assigned 1106 patients to receive imatinib ( 553 patients ) or interferon alfa plus low-dose cytarabine ( 553 patients ) . Crossover to the alternative group was allowed if stringent criteria defining treatment failure or intolerance were met . Patients were evaluated for hematologic and cytogenetic responses , toxic effects , and rates of progression . RESULTS After a median follow-up of 19 months , the estimated rate of a major cytogenetic response ( 0 to 35 percent of cells in metaphase positive for the Philadelphia chromosome ) at 18 months was 87.1 percent ( 95 percent confidence interval , 84.1 to 90.0 ) in the imatinib group and 34.7 percent ( 95 percent confidence interval , 29.3 to 40.0 ) in the group given interferon alfa plus cytarabine ( P<0.001 ) . The estimated rates of complete cytogenetic response were 76.2 percent ( 95 percent confidence interval , 72.5 to 79.9 ) and 14.5 percent ( 95 percent confidence interval , 10.5 to 18.5 ) , respectively ( P<0.001 ) . At 18 months , the estimated rate of freedom from progression to accelerated-phase or blast-crisis CML was 96.7 percent in the imatinib group and 91.5 percent in the combination-therapy group ( P<0.001 ) . Imatinib was better tolerated than combination therapy . CONCLUSIONS In terms of hematologic and cytogenetic responses , tolerability , and the likelihood of progression to accelerated-phase or blast-crisis CML , imatinib was superior to interferon alfa plus low-dose cytarabine as first-line therapy in newly diagnosed chronic-phase CML\n\n\nTitle 4:\nHealth-related quality of life of bosutinib (SKI-606) in imatinib-resistant or imatinib-intolerant chronic phase chronic myeloid leukemia.\nAbstract 4:\nUnderst and ing the impact of second-line tyrosine kinase inhibitor therapy on the health-related quality of life ( HRQOL ) of imatinib (IM)-resistant and IM-intolerant chronic phase chronic myeloid leukemia ( CP CML ) patients is important given the increased survival that comes with therapy . As part of a bosutinib single-arm phase 2 trial , 200 IM-resistant and 88 IM-intolerant CP CML patients ' HRQOL was assessed prior to and throughout treatment with the Functional Assessment of Cancer Therapy-Leukemia ( FACT-Leu ) . Little HRQOL impairment was demonstrated at baseline . Over the course of 96 weeks on bosutinib therapy , patients noted statistically significant and /or clinical ly meaningful improvements on several FACT-Leu scales\n\n\nTitle 5:\nQuality of life on imatinib.\nAbstract 5:\nImatinib ( Gleevec ) , a highly effective specific tyrosine kinase inhibitor , demonstrates a better side effect profile than interferon-alpha ( IFN ) , which impairs patients ' quality of life ( QoL ) . This phase III international study evaluated QoL outcomes in 1,106 newly diagnosed patients with chronic-phase chronic myeloid leukemia ( CML ) who were r and omized to receive either imatinib 400 mg daily or IFN up to 5 MU/m(2)/d with cytarabine ( Ara-C ) 20 mg/m(2)/d added for 10 days every month ( IFN + LDAC ) . Crossover to the other treatment arm was permitted due to a lack of efficacy or treatment intolerance . QoL was assessed with the Functional Assessment of Cancer Therapy-Biologic Response Modifiers ( FACT-BRM ) at baseline , monthly for 6 months and then at months 9 , 12 , and 18 . The Trial Outcome Index ( TOI ; a composite endpoint of physical/functional/treatment-specific subscales ) was the primary endpoint . Secondary endpoints measured were social/family well-being ( SFWB ) and emotional well-being ( EWB ) . QoL was analyzed for the first 18 months of treatment using mixed effects growth curve models . The primary analyses were intention-to-treat ( ITT ) ; secondary analyses incorporated crossover as a time-dependent covariate . A total of 1,049 patients completed at least one QoL assessment . Two hundred sixty-one patients ( 50 % ) crossed over from IFN to imatinib and 11 ( 2 % ) crossed over from imatinib to IFN . There was a significant decline in TOI scores for the IFN treatment arm compared with preservation of baseline TOI scores in the imatinib arm ( P < .001 , ITT ) . Mean social/family and EWB scores were 22.8 and 19.5 , respectively , for imatinib and 21.6 and 17.6 , respectively , for IFN ( P < .001 , ITT ) . After crossing over from IFN to imatinib , patients experienced a significant ( P < .001 ) increase in TOI scores . Imatinib offers clear QoL advantages over IFN as first-line treatment of chronic-phase CML . In addition , patients who crossed over to imatinib reported higher QoL than those who remained on IFN . Semin Hematol 40(suppl 2):31 - 36\n\n\nTitle 6:\nQuality of life in patients with newly diagnosed chronic phase chronic myeloid leukemia on imatinib versus interferon alfa plus low-dose cytarabine: results from the IRIS Study.\nAbstract 6:\nPURPOSE Quality of life ( QOL ) outcomes in patients with chronic myeloid leukemia ( CML ) were evaluated in an international phase III study . PATIENTS AND METHODS Newly diagnosed patients with chronic phase CML were r and omly assigned to imatinib or interferon alfa plus subcutaneous low-dose cytarabine ( IFN+LDAC ) . Cross-over to the other treatment was permitted because of intolerance or lack of efficacy . Patients completed cancer-specific QOL ( Functional Assessment of Cancer Therapy-Biologic Response Modifiers ) and utility ( Euro QoL-5D ) question naires at baseline and during treatment ( n = 1,049 ) . The primary QOL end point was the Trial Outcome Index ( TOI ; a measure of physical function and well-being ) . Secondary end points included social and family well-being ( SFWB ) , emotional well-being ( EWB ) , and the utility score . Primary analyses were intention to treat with secondary analyses accounting for cross-over . RESULTS Patients receiving IFN+LDAC experienced a large decline in the TOI , whereas those receiving imatinib maintained their baseline level . Treatment differences at each visit were significant ( P < .001 ) and clinical ly relevant in favor of imatinib . Mean SFWB , EWB , and utility scores were also significantly better for those patients taking imatinib . Patients who crossed over to imatinib experienced a large increase in TOI ; significant ( P < .001 ) differences were observed between patients who did and did not cross over in favor of imatinib . CONCLUSION Imatinib offers clear QOL advantages compared with IFN+LDAC as first-line treatment of chronic phase CML . In addition , patients who cross over to imatinib from IFN+LDAC experience a significant improvement in QOL compared with patients who continue to take IFN+LDAC\n\n\nTitle 7:\nAssessment of quality of life with imatinib mesylate as first-line treatment in chronic phase-chronic myeloid leukemia\nAbstract 7:\nImatinib mesylate ( IM ) is a first-line treatment of chronic phase-chronic myeloid leukemia ( CP-CML ) . The primary objective of this study was to assess the quality of life ( QOL ) in patients with CP-CML treated with IM . Ninety patients with newly diagnosed CP-CML were assessed for QOL with first-line IM . Patients completed the cancer-specific FACT-BRM question naire ( functional assessment of cancer therapy-biologic response modifiers ) at baseline and at 3 and 6 months . FACT-BRM consists of subscales including physical well-being ( PWB ) , social and family well-being ( SFWB ) , emotional well-being ( EWB ) , functional well-being ( FWB ) , BRM-physical , and BRM-mental . The primary endpoint was the Trial Outcome Index ( TOI ) , created as a measure of physical function and well-being . An increase of ≥5 from baseline was considered to be a clinical ly significant improvement . The mean TOI score increased from 75.5 at baseline to 85.2 ( p<0.0001 ) at 6 months , representing a healthy QOL . When comparing the individual TOI subscales , there was a mean increase of 16.4 in the daily functioning and well-being score , and a mean decrease of 6.2 , 4.9 , and 16.1 was noted in fatigue , emotional/cognitive dysfunction , and side-effects scores at 6 months , respectively . Improvement was not affected by age , sex , or Sokal score . With prolonged treatment , IM results in a higher physical well-being , less fatigue and emotional and cognitive dysfunction , and very few side-effects", "role": "user" }, { "content": "The most solid data in this area indicate that CML patients receiving TKIs have a worse HRQOL profile when compared to their peers , without cancer , in the general population and interventions to improve HRQOL outcomes are thus needed .\nHowever , HRQOL assessment in these studies emphasize the unique information provided by the patient 's perspective .", "role": "assistant" } ]

[ { "content": "You will be shown biomedical passages and your task is to answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: Which is the genetic lesion associated with Huntington’s disease?\n\nContext: Early in 1993, an unstable, expanded trinucleotide repeat in a novel gene of unknown function was identified on HD chromosomes. This discovery unleased a flurry of experimentation that has established the expanded CAG repeat the almost universal cause of the characteristic neurologic symptoms and pathology of this neurodegenerative disorder of midlife onset.", "role": "user" }, { "content": "A CAG trinucleotide repeat expansion in the HD gene", "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:\nMacrocyclic Inhibitors of 3C and 3C-like Proteases of Picornavirus, Norovirus, and Coronavirus\n\nPaper sections:\n\n<p>The picornavirus-like protease supercluster includes viruses in the Picornaviridae, Coronaviridae, and Caliciviridae families. Many human pathogens of major medical and economic importance belong to these virus families. For instance, the family Picornaviridae includes enterovirus (enterovirus, EV; coxsackievirus, CV; poliovirus, PV), human rhinovirus (HRV), and hepatitis A virus (HAV).1-2 Non-polio enteroviruses are responsible for 10-15 million symptomatic infections in the U.S. each year,3 while HRV is the major causative agent of upper respiratory tract infections.4 In the Coronaviridae family, severe acute respiratory syndrome (SARS) caused by SARS-coronavirus (SARS-CoA) is a recognized global threat to public health.5 Noroviruses belong to the Norovirus genus of the Caliciviridae family and are highly contagious human pathogens that are the most common cause of food borne and water borne acute viral gastroenteritis.6 Thus, norovirus infection constitutes an important public health problem. There are currently no vaccines (except for poliovirus) or specific antiviral agents for combating infections caused by the aforementioned viruses; thus, there is an urgent and unmet need for the discovery and development of broad spectrum small-molecule therapeutics and prophylactics for these important pathogens.7-10</p><p>The picornaviral genome consists of a positive sense, single-stranded RNA of ∼7.5 kb in length that encodes a large precursor polyprotein that requires proteolytic processing to generate mature viral proteins.1-2 Processing of the polyprotein is primarily mediated by the viral 3C protease (3Cpro). Likewise, the ∼ 30 kb genome of SARS-CoV comprises both nonstructural and structural regions. Two polyproteins (designated as pp1a and pp1ab) encoded by the viral genome undergo proteolytic processing by two proteases: a chymotrypsin-like cysteine protease (3C-like protease, 3CLpro) and a papain-like protease (PLpro), to generate functionally active proteins. Finally, the 7-8 kb RNA genome of noroviruses encodes a polyprotein that is processed by a 3C-like protease (3CLpro) to generate mature proteins.11 Although there is high genetic diversity among these viruses, 3Cpro and 3CLpro are highly conserved, as well as essential for virus replication.</p><p>Inspection of the crystal structures of picornavirus 3Cpro12-15 and norovirus 3CLpro,16-19 reveals that the proteases share in common a chymotrypsin-like fold, a Cys-His-Glu/Asp catalytic triad (EV and CV 3Cpro, and NV 3CLpro) or Cys-His dyad (SARS-CoV 3CLpro),20 an extended binding site, and a preference for cleaving at Gln-Gly (P1-P1′) junctions in protein and synthetic peptidyl substrates (vide infra). The confluence of structural similarities in the active sites, mechanism of action, and substrate specificity preferences of EV and CV 3Cpro,12-13 SARS-CoV 3CLpro,20-21 and NV 3CLpro11,17,22 (Table 1) suggests that a drug-like entity can be fashioned that displays inhibitory activity against all three proteases, making them appealing targets for the discovery of broad spectrum antiviral agents.16,23</p><p>Picornavirus 3Cpro,2 SARS-CoV 3CLpro23 and NV 3CLpro24 have been the subject of intense investigations. We report herein the design, synthesis, and in vitro evaluation of a representative member of a new class of macrocyclic transition state inhibitors (I) (Figure 1) that is effective against all three proteases. To our knowledge, this is the first report describing the inhibition of 3Cpro and 3CLpro of pathogens belonging to the picornavirus-like protease supercluster, by a macrocyclic inhibitor.</p><p>The design of macrocyclic inhibitor (I) rested on the following considerations: (a) proteases are known to recognize their ligands in the β-strand conformation;25 (b) macrocyclization is an effective way of pre-organizing a peptidyl transition state mimic in a β-strand conformation suitable for binding to the active site of a protease;26-28 (c) in general, macrocyclization increases affinity by reducing the loss of entropy upon inhibitor binding, as well as cellular permeability, and proteolytic stability;29 (d) macrocyclization improves drug-like characteristics;30-31 (e) the plasticity of the S3 subsite in the 3C and 3CL proteases was exploited in the design of macrocyclic inhibitor (I) by tethering the P1 Gln side chain to the P3 residue side chain; and, (e) computational and modeling studies suggested that a ring size corresponding to n = 3 would produce good receptor binding and minimal intra-ligand strain.</p><p>Based on the aforementioned considerations, inhibitor (I) was assembled in a convergent fashion by first constructing fragments 2 and 4, followed by subsequent coupling of the two fragments to generate acyclic precursor 5 (Scheme 1). Cyclization was subsequently accomplished using click chemistry.32-35 Thus, fragment 2 was synthesized by coupling (L) Boc-protected propargyl glycine with (L) leucine methyl ester using EDCI/HOBt/DIEA/DMF to yield the dipeptidyl ester which was subsequently treated with dry HCl in dioxane to remove the N-terminal Boc protecting group. Reaction with benzylchloroformate yielded the Cbz-protected ester which was hydrolyzed with LiOH in aqueous THF to yield the corresponding acid 2. EDCI-mediated coupling of commercially available (L) Boc-Glu-OCH3 with NH2(CH2)nN3 (n=3), followed by removal of the Boc group, yielded fragment 4.36 The amino alkyl azide was conveniently synthesized by converting BocNH(CH2)nOH to the mesylate via treatment with methanesulfonyl chloride in the presence of triethylamine, followed by reaction with sodium azide in DMF and removal of the protective group. Coupling of fragment 2 with 4 using standard coupling conditions yielded acyclic precursor 5 which was treated with Cu(I)Br/DBU in dichloromethane to furnish compound 6 in 45% yield. Compound 6 was treated with lithium borohydride to yield alcohol 7 (84% yield) which, upon Dess-Martin periodinane oxidation37, and subsequent purification gave macrocyclic aldehyde 8 (Scheme 1, structure (I), n = 3, R = isobutyl, X = CHO), as a white solid.38 The inhibitory activity of aldehyde 8 was evaluated in vitro as previously described.16,39-42 Compound 8 displayed inhibitory activity against NV 3CLpro (IC50 5.1 μM), enterovirus (CVB3 Nancy strain) 3Cpro (1.8 μM), and SARS-CoV 3CLpro (IC50 15.5 μM).</p><p>In order to gain insight and understanding into the binding of inhibitor 8 to the active site of each protease, computer modeling was used. Thus, the receptor structures were prepared from the following protein data bank (PDB) crystal structures: A) NV 3CLpro from 2IPH,17 B) CV 3C pro from 3ZZB,43 and C) SARS-CoV 3CLpro from 2ZU5.44 These three receptor models were chosen by virtue of having cocrystallized ligands that each displayed the following three features consistent with the likely binding mode of inhibitor 8: i) a covalent attachment to the catalytically active cysteine (analogous to the terminal aldehyde in inhibitor 8), ii) branched alkyl, as per isobutyl group in 8, and iii) aryl (phenylalanine or Cbz), as per Cbz in 8. This permitted the intelligent prepositioning of inhibitor 8 into each of the three protease receptors, which was accomplished in Pymol45 via manual docking. Pymol was then used to produce a computational framework for refining the docked conformation as follows: a ligand-receptor complex was generated by protonating the preliminary receptor-ligand complex (according to physiological pH with anionic aspartate and glutamate residues, and cationic lysine and arginine residues), then retaining only the ligand plus all complete residues with at least one atom located within no more than 6.0 Å from any ligand atom. The resulting complex models were then permitted to undergo 1000 molecular mechanics optimization steps in Avogadro46 using the MMFF94 force field and electrostatic charge model.47 The resulting complexes were then rendered in PyMol. The computational studies indicate that inhibitor 8 is capable of nestling snugly in the active site of the 3C and 3CL proteases.</p><p>In summary, we report herein for the first time the inhibition of the 3Cpro and 3CL pro of viral pathogens belonging to the picornavirus-like protease supercluster by a macrocyclic inhibitor. A full account describing the exploration of R, linker, n (ring size), and the nature of warhead X, will be reported in due course.</p>", "role": "user" }, { "content": "The design, synthesis, and in vitro evaluation of the first macrocyclic inhibitor of 3C and 3C-like proteases of picornavirus, norovirus, and coronavirus are reported. The in vitro inhibitory activity (50% effective concentration) of the macrocyclic inhibitor toward enterovirus 3C protease (CVB3 Nancy strain), and coronavirus (SARS-CoV) and norovirus 3C-like proteases, was determined to be 1.8, 15.5 and 5.1 \\xce\\xbcM, respectively.", "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: Moving Objects Analytics: Survey on Future Location&Trajectory Prediction Methods \nChapter Title: Summary \n1. Abstract of Cited Paper (BIB001): A predictive spatio-temporal query retrieves the set of moving objects that will intersect a query window during a future time interval. Currently, the only access method for processing such queries in practice is the TPR-tree. In this paper we first perform an analysis to determine the factors that affect the performance of predictive queries and show that several of these factors are not considered by the TPR-tree, which uses the insertion/deletion algorithms of the R*-tree designed for static data. Motivated by this, we propose a new index structure called the TPR*- tree, which takes into account the unique features of dynamic objects through a set of improved construction algorithms. In addition, we provide cost models that determine the optimal performance achievable by any data-partition spatio-temporal access method. Using experimental comparison, we illustrate that the TPR*-tree is nearly-optimal and significantly outperforms the TPR-tree under all conditions. \n2. Abstract of Cited Paper (BIB002): The objective of this paper is to build an air traffic flow prediction model. The air traffic flow prediction plays a key role in the airspace simulation model and air traffic flow management system. In China the air traffic information in each regional control center has not integrated together by now. The information only in a single regional control center can not reach the requirement of the current method based on 4-dimensional trajectory prediction. The new method is needed to solve this problem. Large collection of radar data is stored. But there is no effort made to extract useful information from the database to help in the estimation. Data mining is the process of extracting patterns as well as predicting previously unknown trends from large quantities of data. Neural network and statistics are frequently applied to data mining with various objectives. This paper employs neural networks combined with the statistical analysis of historical data to forecast the traffic flow. Two models with different types and input data are proposed. The accuracy of two models is tested and compared to each other using flow data at an arrival fix in Beijing control center. The result shows that these models are feasible for practical implementations. The suitable models for different prediction conditions are also suggested. \n3. Abstract of Cited Paper (BIB003): Existing methods for peediction spatio-temporal databases assume that objects move according to linear functions. This severely limits their applicability, since in practice movement is more complex, and individual objects may follow drastically diffferent motion patterns. In order to overcome these problems, we first introduce a general framework for monitoring and indexing moving objects, where (i) each boject computes individually the function that accurately captures its movement and (ii) a server indexes the object locations at a coarse level and processes queries using a filter-refinement mechanism. Our second contribution is a novel recursive motion function that supports a broad class of non-linear motion patterns. The function does not presume any a-priori movement but can postulate the particular motion of each object by examining its locations at recent timestamps. Finally. we propse an efficient indexing scheme that faciliates the processing of predicitive queries without false misses. \n4. Abstract of Cited Paper (BIB004): A number of air traffic management decision support tools (DST) are being developed to help air traffic managers and controllers improve capacity, efficiency, and safety in the National Airspace System. Although DST functionality may vary widely, trajectory prediction algorithms can be found at the core of most DST. A methodology is presented for the automated statistical analysis of trajectory prediction accuracy as a function of phase of flight (level-flight, climb, descent) and look-ahead time. The methodology is focused on improving trajectory prediction algorithm performance for DST applications such as conflict detection and arrival metering. The methodology has been implemented in software and tested with air traffic data. Aggregate trajectory prediction accuracy statistics are computed and displayed in histogram format based on 2,774 large commercial jet flights from five different days of Fort Worth Center air traffic data. The results show that trajectory prediction anomalies can be detected by examining error distributions for large numbers of trajectory predictions. The ability of the trajectory analysis methodology to detect the effects of subsequent changes to the trajectory prediction algorithm and to aircraft performance model parameters was also demonstrated. \n5. Abstract of Cited Paper (BIB005): To maximize the capacity of airports by optimally allocating available resources such as runways, the arrival times of individual aircraft need to be computed. However, accurately predicting arrival times is difficult because aircraft trajectories are frequently vectored off the standard approach procedures. This paper introduces a new framework for predicting aircraft arrival times by incorporating probabilistic information for the types of trajectory patterns that will be applied by human air traffic controllers. The major patterns of the trajectories are identified, and the probabilities of those patterns are computed based on the patterns of the preceding aircraft. The proposed method is applied to traffic scenarios in real operations to demonstrate its performance. \n6. Abstract of Cited Paper (BIB006): At the heart of Air Traffic Management (ATM) lies the Decision Support Systems (DST) that rely upon accurate trajectory prediction to determine how the airspace will look like in the future to make better decisions and advisories. Dealing with airspace that is prone to congestion due to environmental factors still remains the challenge especially when a deterministic approach is used in the trajectory prediction process. In this paper, we describe a novel stochastic trajectory prediction approach for ATM that can be used for more efficient and realistic flight planning and to assist airspace flow management, potentially resulting in higher safety, capacity, and efficiency commensurate with fuel savings thereby reducing emissions for a better environment. Our approach considers airspace as a 3D grid network, where each grid point is a location of a weather observation. We hypothetically build cubes around these grid points, so the entire airspace can be considered as a set of cubes. Each cube is defined by its centroid, the original grid point, and associated weather parameters that remain homogeneous within the cube during a period of time. Then, we align raw trajectories to a set of cube centroids which are basically fixed 3D positions independent of trajectory data. This creates a new form of trajectories which are 4D joint cubes, where each cube is a segment that is associated with not only spatio-temporal attributes but also with weather parameters. Next, we exploit machine learning techniques to train inference models from historical data and apply a stochastic model, a Hidden Markov Model (HMM), to predict trajectories taking environmental uncertainties into account. During the process, we apply time series clustering to generate input observations from an excessive set of weather parameters to feed into the Viterbi algorithm. Our experiments use a real trajectory dataset with pertaining weather observations and demonstrate the effectiveness of our approach to the trajectory prediction process for ATM.\n\nLiterature Review:", "role": "user" }, { "content": "In this section, we provided a survey of over twenty (precisely, twenty-four) FLP techniques, actually falling in one of three categories: (i) those performing short-term predictions based on the motion vectors of moving objects (typically, points), which are appropriately indexed in spatial access methods (R-trees, etc.), (ii) those predicting future locations by exploiting patterns (classification trees, association rules, etc.) over the past movements of objects, and (iii) those applying core machine learning approaches (SVR, NN, etc.), where models are trained by pat movements. Table I summarizes the most representative works, also giving notes on the datasets used for the experimental evaluation of the corresponding proposals. Summarizing, we provide the following remarks (and hints for practitioners) about the surveyed FLP techniques: -Vector-based approaches, inspired by the spatial database management domain, aim to model current locations (and perhaps short history) of objects as motion functions in order to be able to predict future locations by some kind of extrapolation. This is more or less the concept and the state-of-the-art in this category of methods includes, at least, TPR*-tree BIB002 , B x -tree [44] , and STP-tree BIB004 . -Pattern-based approaches, inspired by the spatial data mining domain, exploit on data mining patterns (classification models, frequent / sequential patterns etc.) that are built upon the history of movements. Under this prism, the prediction task is an instantiation of the pattern that most fits to the short history of the object's movement (the 'tail' of its trajectory so far). In this section, we provided a survey of over twenty (precisely, twenty-five) TP techniques and variants, which fall into five main categories. Most state-of-the-art methods can be labeled as stochastic, regression-based, clustering-based or some hybrid combination of these basic approaches. Especially for the aviation domain, other methods address the TP problem indirectly, under the collaborative scope of conflict detection and resolution (CD&R) or collision avoidance (CA). The climb phase TP is of particular importance and it requires the embedding of other external parameters, including weather, aircraft properties, etc., with methods typically referred to as semantic-aware TP due to their inherent increased dimensionality (enriched spatio-temporal input space). Table II summarizes the most representative works and provides additional notes with respect to the datasets used in the corresponding experimental evaluation in each one. Summarizing, we provide the following remarks (and hints for practitioners) about the surveyed TP techniques: -Stochastic approaches formalize the TP task via designing proper probabilistic models based on historical trajectory data and then providing predictions in the maximum-likelihood sense, typically by some form of HMM or similar formulation; current state-of-the-art includes, at least, HMM-based BIB007 , segmented/phased trajectories BIB005 and confidence interval-based . -Regression-based methods provide abstract functional mapping between the input and the output (typically the spatio-temporal space), either analytically by some mathematical formulation (e.g. linear regressors) or by data-driven non-linear learners (e.g. NNs) whereas clustering-based approaches are based on the assumption that the analysis of historical trajectory data provides valid trends and mobility patterns as the basis for TP; current state-of-the-art includes, at least, NN-based BIB001 , statistical data mining BIB003 , vectored area navigation arrivals BIB006 In the two tables listing the FLP and TP works surveyed in this paper, cf. Section 3.4 and Section 4.6, respectively, we presented the techniques in a compact form in order to highlight the various approaches and their specifications regarding the input/output of the algorithms. Moreover, these tables bring together information about the different datasets that have been used for evaluation purposes in those works. As it turns out, although the mobility domain is unquestionably a field that contributes to the challenges of the big data era (i.e. the well-known 3 V's, namely volume, velocity, and variety), the proposals so far do not adequately address these challenges, especially when the application in hand tackles more than one V. In the sections that follow, we provide a possible view from the future, by highlighting, on the one hand, the key limitations of the current approaches and, on the other hand, interesting research directions that need to be addressed by the research community.", "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: Vitamin D Level Reduces The Risk of Death From COVID-19\n\nAbstract:\nThe outbreak of COVID-19 has created a global public health crisis.\nLittle is known about the protective factors of this infection.\nTherefore, preventive health measures that can reduce the risk of infection, progression and severity are desperately needed.\nThis review discussed the possible roles of vitamin D in reducing the risk of COVID-19 and other acute respiratory tract infections and severity.\nMoreover, this study determined the correlation of vitamin D levels with COVID-19 cases and deaths in 20 European countries as of 20 May 2020.\nA significant negative correlation (p=0.033) has been observed between mean vitamin D levels and COVID-19 cases per one million population in European countries.\nHowever, the correlation of vitamin D with COVID-19 deaths of these countries was not significant.\nSome retrospective studies demonstrated a correlation between vitamin D status and COVID-19 severity and mortality, while other studies did not find the correlation when confounding variables are adjusted.\nSeveral studies demonstrated the role of vitamin D in reducing the risk of acute viral respiratory tract infections and pneumonia.\nThese include direct inhibition with viral replication or with anti-inflammatory or immunomodulatory ways.\nIn the meta-analysis, vitamin D supplementation has been shown as safe and effective against acute respiratory tract infections.\nThus, people who are at higher risk of vitamin D deficiency during this global pandemic should consider taking vitamin D supplements to maintain the circulating 25(OH)D in the optimal levels (75-125nmol/L).\nIn conclusion, there is not enough evidence on the association between vitamin D levels and COVID-19 severity and mortality.\nTherefore, randomized control trials and cohort studies are necessary to test this hypothesis.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"A significant negative correlation (p=0.033) has been observed between mean vitamin D levels and COVID-19 cases per one million population in European countries.\", \"Several studies demonstrated the role of vitamin D in reducing the risk of acute viral respiratory tract infections and pneumonia.\", \"These include direct inhibition with viral replication or with anti-inflammatory or immunomodulatory ways.\", \"In the meta-analysis, vitamin D supplementation has been shown as safe and effective against acute respiratory tract infections.\", \"Thus, people who are at higher risk of vitamin D deficiency during this global pandemic should consider taking vitamin D supplements to maintain the circulating 25(OH)D in the optimal levels (75-125nmol/L).\"]}", "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\nIn all methods, the SVM problem with Gaussian and linear kernel are solved by sequential minimal optimization algorithm (Platt, 1998) and dual coordinate descent algo-", "role": "user" }, { "content": "Method", "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\nSources of secondary metabolite variation in Dysidea avara (Porifera: Demospongiae): the importance of having good neighbors. Several studies report temporal, geographical, and intra-individual variation in sponge metabolite yields. However, the internal and/or external factors that regulate the metabolite production remain poorly understood. Dysidea avara is a demosponge that produces sesquiterpenoids (avarol and derivatives) with interesting medical properties, which has prompted addressed studies to obtain enough amounts of these metabolites for research on drug discovery. Within this framework, specimens of Dysidea avara from a population of the Northwest Mediterranean were sampled and their secondary metabolites quantified to assess their variability and the possible relationship with external (seasonality, interactions with neighbors) and internal (reproductive stages) factors. The results show a variation of the amount of both avarol and its monoacetate derivative with time, with no clear relationship with seawater temperature. A trade-off with sponge reproduction was not found either. However, our results showed for the first time that sponges are able to increase production or accumulation of secondary metabolites in their peripheral zone depending on the nature of their neighbors. This finding could explain part of the high variability in the amount of secondary metabolites usually found in chemical ecology studies on sponges and opens new biotechnological approaches to enhance the metabolite yield in sponge cultures.", "role": "user" }, { "content": "{\"Chemical\": [\"sesquiterpenoids\", \"avarol and its monoacetate\", \"avarol\"]}", "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: Forty Years of Erratic Insecticide Resistance Evolution in the Mosquito Culex pipiens\nArticle:\nAbstract:\nOne view of adaptation is that it proceeds by the slow and steady accumulation of beneficial mutations with small effects. It is difficult to test this model, since in most cases the genetic basis of adaptation can only be studied a posteriori with traits that have evolved for a long period of time through an unknown sequence of steps. In this paper, we show how ace-1, a gene involved in resistance to organophosphorous insecticide in the mosquito Culex pipiens, has evolved during 40 years of an insecticide control program. Initially, a major resistance allele with strong deleterious side effects spread through the population. Later, a duplication combining a susceptible and a resistance ace-1 allele began to spread but did not replace the original resistance allele, as it is sublethal when homozygous. Last, a second duplication,( also sublethal when homozygous) began to spread because heterozygotes for the two duplications do not exhibit deleterious pleiotropic effects. Double overdominance now maintains these four alleles across treated and nontreated areas. Thus, ace-1 evolution does not proceed via the steady accumulation of beneficial mutations. Instead, resistance evolution has been an erratic combination of mutation, positive selection, and the rearrangement of existing variation leading to complex genetic architecture.\nIntroduction:\nAdaptation is often envisioned as a slow and regular improvement, a view embodied by Fisher's geometrical model of adaptation, whereby mutations fix if they bring the current phenotype closer to an optimum[1, 2]. However, the trajectory towards the optimum can take a truly tortuous path[3], as adaptation uses almost any allele that brings it closer to the optimum, regardless of its negative side effects. “Evolution is a tinkerer, ” as emphasized by Jacob[4], may indeed be more than a pretty metaphor. That beneficial mutations often have deleterious pleiotropic effects is well established( i. e., they generate a fitness cost[1, 5–8]). Pleiotropy causes an “evolutionary inertia”[9] whereby beneficial mutations often only ameliorate the side effects of the last beneficial mutation. This process of “amelioration”[10] can follow a scenario a la Fisher[11] with modifiers or compensatory mutations occurring at different loci, or with allele replacement at the same locus( Haldane[12]). Both cases have been reported( e. g.,[10, 13–16]). However, it is perhaps less often appreciated that pleiotropy can have more dramatic consequences. First, the pleiotropic effects of beneficial mutations may be more complex than simply deleterious. Second, they may trigger the evolution of the genetic architecture and gene number. This paper illustrates these two aspects with the tortuous path taken during the evolution of insecticide resistance in Culex pipiens mosquitoes in southern France. In natural populations of the mosquito Culex pipiens, various resistance genes have been selected over the course of ∼40 y of control using organophosphorous( OP) insecticides( see[17] for a review). OP insecticides kill by inhibiting acetylcholinesterase( AChE1) in the central nervous system. The genetic basis of OP resistance involves two main loci, the super-locus Ester and the locus ace-1, both of which have major resistance alleles. Strong direct and indirect evidence indicate that the resistance alleles have a “fitness cost”; i. e., they are selected against in the nontreated areas( see reviews in[17, 18]). At the Ester locus, the different resistance alleles are not identical and one has slowly replaced the other[15, 16]. At the ace-1 locus, the resistance allele present worldwide, ace-1R, displays a single amino acid mutation( G119S), changing the glycine at position 119 into a serine. This large effect point mutation confers high resistance towards OP insecticides due to lower affinity and has arisen independently in several mosquito species[19–21]. However, this mutation also exhibits a strong deleterious side effect: G119S is less efficient at degrading acetylcholine( ACh) than the susceptible variant of AChE1. Overall, G119S causes a more than 60% reduction in enzymatic activity in the absence of insecticide[22], which alters the optimal functioning of cholinergic synapses of the central nervous system and probably causes the various developmental and behavioral problems that have been identified in individuals carrying ace-1R[23–25]. Field surveys also quantified the overall fitness cost of this allele in the wild. Fitness values are 1 and 0. 89 for a susceptible and resistant homozygote, respectively, in the absence of insecticide( i. e., when only the cost applies[26, 27]). However, in a treated habitat, only ace-1R-carrying individuals survive. A few years after the appearance and spread of ace-1R, several duplications of the ace-1 gene appeared in wild populations, each involving a resistant and a susceptible copy of the ace-1 gene on the same chromosome[28–30]. We refer to these new duplicated haplotypes as ace-1D. The ace-1 copies involved in these duplicated haplotypes are barely distinguishable from local single-copy alleles. In particular, within a population, the sequence of the local ace-1D resistant copy is always identical to the sequence of the single-copy ace-1R allele[30]. In the Montpellier area of Southern France, the appearance of a duplicated haplotype was indirectly inferred and traced back to at least 1993[29]. More recently, sequence data of ace-1 confirmed the presence of duplication, but surprisingly also revealed the presence of two distinct duplicated haplotypes in Montpellier area( ace-1D2 and ace-1D3)[30]. Other independent duplications were also found in the Caribbean( Martinique, ace-1D1) and Philippines( Palawan, ace-1D4)[30]. Gene duplication is an important type of mutation because it fosters the evolution of new functions[12, 31–33]. In the case of ace-1, a strong genetic constraint drives resistance evolution, as the degree of resistance and the ability to degrade ACh trade off; OP and ACh molecules compete for the same active site of AChE1. Duplication may be a way to disentangle the two functions, i. e., by improving synapse signalling and mosquito's fitness while maintaining resistance. Thus, our working hypothesis is that the spread of ace-1 duplications is driven by the increased AChE1 activity in individuals carrying ace-1D compared to those carrying ace-1R. In the last survey eight y ago[29], indirect estimation indicated a rapid initial increase of ace-1D, suggesting a strong selective advantage of ace-1D over ace-1R( in the range of 3%–6% of ace-1R fitness[29]). Based on these previous findings, we expected the duplicated haplotype to quickly replace ace-1R. The aim of this study was to test this prediction and to understand more precisely the fitness relationship between the various genotypes( single resistance or susceptible alleles, duplicated haplotypes and their heterozygotes) in treated and nontreated areas. Surprisingly, we show that ace-1D did not replace ace-1R. Several experiments indicated that duplications, while favored when heterozygous, exhibit very strong deleterious effects when homozygous. Our work thus highlights a novel scenario of adaptive evolution and trade-offs that hinge on the genetic architecture underlying the expression of resistance variation.\nDiscussion:\nThis study shows how ace-1, one of the two major genes involved in resistance to OP insecticide in the mosquito Culex pipiens, evolved in the last 40 y of control using insecticides. The evolution of resistance to insecticide in C. pipiens does not follow a classical scenario whereby a beneficial mutation with deleterious side effects spreads and is followed by a steady “amelioration” process correcting for these side effects. About 10 y after the beginning of OP treatments( 1977), the major resistance allele ace-1R, which is beneficial in the treated area but has strong deleterious pleiotropic effects in absence of insecticide, appeared and spread[17, 18]. Because of this fitness cost and incoming gene flow from the nontreated area favored by the absence of insecticide treatment in winter, it did not fix but remained polymorphic with a clinal pattern across treated and nontreated areas[26, 27, 35]. In the early nineties, at least one and probably two duplications involving a resistance and susceptible ace-1 copy, started to spread and replace ace-1R[29, 30]. Our lab experiments indicate that these two duplications are both severely deleterious when homozygous, but that heterozygotes involving either ace-1S or ace-1R alleles do not exhibit deleterious side effects. After ∼1999, the pooled frequency of the duplications does not vary significantly, suggesting that the four “alleles”( ace-1S, ace-1R, ace-1D2, and ace-1D3) reached a stable equilibrium. The stability of the duplicated haplotype frequencies since 1996 suggests that both duplications occurred and spread before 1996. This latter conclusion is tentative, since our data may not be accurate enough to detect the small perturbation of the frequency equilibrium caused by the spread of one of the duplications after 1996, due to the indirect estimation of duplicated haplotype frequency. Clearly, however, considerable polymorphism in this system is maintained by both overdominance and migration. What is the mechanism by which overdominance operates? First, a duplicated haplotype restores AChE1 activity while maintaining resistance[30]. It therefore combines resistance with no deleterious pleiotropic effect caused by a deficit of AChE1 activity. An excess of AChE1 activity may be deleterious as well, but the one caused by the duplication is mild. For this reason, duplications certainly exhibit at least marginal overdominance over treated and nontreated areas. Duplications could be described as “generalist” haplotypes that perform well in both habitats, compared to the “specialist” alleles ace-1S and ace-1R. Second, through lab experiments, we found, surprisingly, that both ace-1D2 and ace-1D3 duplications cause very strong deleterious effects when homozygous. However, these effects disappear in ace-1D2/ace-1D3 heterozygotes. The simplest explanation for this observation is that each duplication occurred independently rather than being generated by recombination( which may not be surprising, given the high duplication rate at this locus[30]), and that they carry distinct recessive sublethal mutations not necessarily related to ace-1–mediated resistance. Distinct unequal crossing over could have generated each duplication and in the same time disrupted different genes close to ace-1. Alternatively, different sublethal recessive mutations could have hitchhiked with the initial spread of each duplication. In all cases, these explanations require that the duplications cannot get rid of these deleterious mutations by recombining. It therefore suggests that recombination is very low around or within the duplicated haploypes or that they are situated on chromosomal inversions( and thus behave like a “balancer region” in analogy with the balancer chromosomes used in laboratory Drosophila). The fact that we never observed in laboratory crosses a recombinant separating the two ace-1 duplicated copies[30] is consistent with this last hypothesis. We consider this explanation plausible since duplication events involve an important modification of the genome, which can easily disrupt other genes or regulatory regions[31, 33, 36]. This example of adaptation involves three successful steps( the formation of ace-1R, ace-1D2 and ace-1D3), each of them being driven by natural selection. However, each of these three steps presents severe deleterious pleiotropic effects. The deleterious pleiotropic effect of ace-1R may be unavoidable if changing the AChE1 active site to decrease affinity towards OP insecticide necessarily also leads to a lower affinity towards ACh. However, the occurrence and spread of duplications that are sublethal when homozygotic is more perplexing. For instance, another ace-1 duplication, ace-1D1 seems to have spread and be almost fixed on the island of Martinique[37], indicating that ace-1 duplications do not necessarily involve strong deleterious pleiotropic effects when homozygous( confirmed by laboratory analyses, P. Labbé and M. Weill, unpublished data). However, once a duplication with a recessive cost has spread, even partially, in a population, selection is likely to be less effective at replacing it with a better one because the fate of a beneficial mutation is mostly determined when it is rare and therefore by its heterozygous effect[38]. Since ace-1D2 or ace-1D3 duplications enjoy almost no fitness cost when heterozygotic, any new duplication has a low chance to spread in these populations( although migration bringing fitter haplotypes could help escaping this apparent dead end). Thus, selection has taken the mosquito populations on a difficult path indeed. More generally, we may wonder if such a tortuous adaptive trajectory is frequent in nature. Clearly, gene duplications may solve many genetic trade-offs and chromosome rearrangements such as inversions may strongly perturb the genetic architecture. This type of situation may be more common with strong selective pressure and strong pleiotropy, whereas less intense selection may select for more subtle variation( e. g., see[39]). Nevertheless, insecticide resistance may not be an exception, since other selective pressures appear to be intense as well( e. g., parasitism[40, 41]) and thus could favor similar complex genetic responses. The new molecular tools available will allow deeper investigation of adaptation genetics evolution, and thus will help to settle the issue of the frequency of the kind of complex patterns uncovered by our study. In the long term, selection may produce exquisite adaptations, but this study lays bare that even impressive adaptations are likely to have begun with a process of trial and error that seems to be anything but optimal. It appears that natural selection is forced to tinker with available variability, despite the costs, rather than build impressive and cost-free adaptations that are wholly novel.", "role": "user" }, { "content": "Adaptation is not always a straightforward process , and often results from natural selection tinkering with available variation . We present in this study just such a tortuous natural selection pathway , which allows the mosquito Culex pipiens to resist organophosphorous insecticides . In the Montpellier area , following the use of insecticide to control mosquito populations , a high-resistance allele of the insecticide target enzyme appeared . But this allele also displayed strong deleterious side effects . Recently , several duplicated haplotypes began to spread in natural population that put in tandem a susceptible and a resistant allele . We show that the duplicated haplotypes actually display reduced side effects compared to the resistant allele when in the heterozygous state , but also new and strong costs in the homozygote . This pattern leads to an unexpected equilibrium between four different alleles across treated and nontreated areas . The story of resistance in C . pipiens is indeed far from a slow progression toward a “perfect” adaptation . Rather , selection for resistance to insecticide is a long process of trial and error leading to an uncommon genetic architecture .", "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\nTwo PTF1 binding sites are present in the 2.3 kb Ptf1a regulatory sequence Sequence analysis of the two highly conserved peaks in the 2.3 kb enhancer revealed the presence of two PTF1 binding sites, referred to here as the proximal (P) and the distal (D) PTF1 sites (Masui et al., 2008).", "role": "user" }, { "content": "Background", "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: From mechanical metamorphosis to empathic interaction: a historical overview of robotic creatures \nChapter Title: The Emergence of Robotic Art \n1. Abstract of Cited Paper (BIB001): Technical developments, trends in popular culture and widespread interest in the scientific community can not account for the proliferation of robotic creatures in the art context, oddly neglected by art theory. In this paper we discuss robotic creation as a crucial domain for contemporary art theory taking as a point of reference the concepts of objecthood, interaction, conceptualisation and anthropomorphism.\n\nLiterature Review:", "role": "user" }, { "content": "During Modernism, numerous artists tried to develop automated machines. They extensively explored robotics in order to develop a new medium to express the hybrid of robots, media, systems, life forms, and context BIB001 . The significance of robotic art is required in the new aesthetic dimension of modeling behavior and developing unprecedented interactive communications in physical spaces BIB001 . declared that \"Robots belong to a new category of objects and situations disruptive to the traditional taxonomy of art (p. 4).\" After the introduction of K-456 by Nam June Paik and machine suicide by Tinguely, the Survival Research Laboratories (SRL) astonished spectators with aggressive machines that could pretend to attack an audience BIB002 . Since 1979, Mark Pauline and the SRL performed with dangerous robotic machines. The Rabot was assembled by grafting a mechanical exoskeleton to the dead body of a rabbit in order to generate a reverse walking motion at the show An Unfortunate Spectacle of Violent Self-Destruction in 1981 BIB001 . Contrary to Kempelen's fear of mechanical intelligence in the 18th century , their robotic performances revealed that the fear of mechanical behaviors seemed to be out of control. In the (a) robot K-456 (b) robot K-456 hit by car (Fig. 7) . This transplanted robotic hand, which was activated by the electric signal from his abdomen and leg, attached to his right arm and could write out \"THE THIRD HAND\" by following the movements of his right hand BIB001 . The SRL and Stelarc tried to combine mechanical components with flesh in order to evoke the uncanny to frightened spectators. Their performances were traced to the avant-garde in the 1960's, when Nam June Paik appeared like an artistic shaman with new media rather than traditional miseen-scène.", "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: Bortezomib prevents cytarabine resistance in MCL, which is characterized by down-regulation of dCK and up-regulation of SPIB resulting in high NF-κB activity. The addition of high-dose cytarabine to the treatment of mantle cell lymphoma (MCL) has significantly prolonged survival of patients, but relapses are common and are normally associated with increased resistance. To elucidate the mechanisms responsible for cytarabine resistance, and to create a tool for drug discovery investigations, we established a unique and molecularly reproducible cytarabine resistant model from the Z138 MCL cell line. ### methods Effects of different substances on cytarabine-sensitive and resistant cells were evaluated by assessment of cell proliferation using [methyl-14C]-thymidine incorporation and molecular changes were investigated by protein and gene expression analyses. ### results Gene expression profiling revealed that major transcriptional changes occur during the initial phase of adaptation to cellular growth in cytarabine containing media, and only few key genes, including SPIB, are deregulated upon the later development of resistance. Resistance was shown to be mediated by down-regulation of the deoxycytidine kinase (dCK) protein, responsible for activation of nucleoside analogue prodrugs. This key event, emphasized by cross-resistance to other nucleoside analogues, did not only effect resistance but also levels of SPIB and NF-κB, as assessed through forced overexpression in resistant cells. Thus, for the first time we show that regulation of drug resistance through prevention of conversion of pro-drug into active drug are closely linked to increased proliferation and resistance to apoptosis in MCL. Using drug libraries, we identify several substances with growth reducing effect on cytarabine resistant cells. We further hypothesized that co-treatment with bortezomib could prevent resistance development. This was confirmed and show that the dCK levels are retained upon co-treatment , indicating a clinical use for bortezomib treatment in combination with cytarabine to avoid development of resistance . The possibility to predict cytarabine resistance in diagnostic samples was assessed, but analysis show that a majority of patients have moderate to high expression of dCK at diagnosis, corresponding well to the initial clinical response to cytarabine treatment. ### conclusion We show that cytarabine resistance potentially can be avoided or at least delayed through co-treatment with bortezomib, and that down-regulation of dCK and up-regulation of SPIB and NF-κB are the main molecular events driving cytarabine resistance development.\n\nsentence: This was confirmed and show that the dCK levels are retained upon co-treatment , indicating a clinical use for bortezomib treatment in combination with cytarabine to avoid development of resistance .", "role": "user" }, { "content": "[[\"bortezomib\", \"cytarabine\", \"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: [\"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\nProstaglandin E2 induction of binding activity to CRE and AP-2 elements in human T lymphocytes. Prostaglandins of the E series are immunomodulatory agents which exert inhibitory as well as stimulatory effects on a variety of immune responses. Since it is known that PGE2 is able to increase cAMP levels, we investigated whether it can affect gene expression through the activation of the transcription factors which bind enhancer elements in the promoter regions of cAMP-regulated genes. Using electrophoretic mobility shift assay, we demonstrated that a short treatment of human T lymphocytes with PGE2 induces specific binding activity to CRE and AP-2, but not AP-1, DNA elements. Since the okadaic acid, a potent protein phosphatase inhibitor, prolongs the induction of the binding activity, phosphorylation events are likely to occur. This activity seems to be due to increased cAMP levels because forskolin and IBMX mimic the effects of PGE2. More interestingly, transfection experiments with CRE-CAT plasmide show that PGE2 activates the transcription of a CRE-containing promoter. These data support the positive role for PGE2 on some immune functions.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"human T lymphocytes\"], \"DNA\": [\"AP - 2\", \"CRE - CAT plasmide\", \"cAMP - regulated genes\", \"CRE -\", \"CRE - containing promoter\", \"AP - 1 , DNA elements\", \"AP - 2 elements\", \"CRE\"], \"Protein\": [\"transcription factors\", \"AP - 1\"], \"RNA\": []}", "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:\nto study about the utility of goniometry in screening for limited joint mobility ( ljm ) in patients attending a secondary level diabetic clinic .\nrandomly selected data of 100 patients attending a secondary level diabetic clinic without any complications were used .\nrange of movement around the ankle joint and 1 metatarsal joint was done using goniometry .\nselected 100 patients attending a secondary level diabetic clinic and on regular follow - up were included in the study .\nsick patients requiring parenteral feeds , iv antibiotics , co - morbid conditions such as microvascular complication , autonomic gastroparesis , and diabetic foot infections were excluded from the study .\ngoniometric screening for ljm is a cheap and effective screening tool for detecting early structural deformity producing a higher plantar pressure and ulcer , and thereby preventing them at early stage .\nlevin reports that 20% of all diabetic patients entering the hospital are admitted because of foot problems .\nthe most important etiological factors that have been associated with diabetic polyneuropathy ( dpn ) are poor glycemic control , visceral obesity , diabetes duration , height , hypertension , age , smoking , hypoinsulinemia , and dyslipidemia . \n\nfoot ulceration is common , affecting up to 25% of patients with diabetes during their lifetime.over 85% of lower limb amputations are preceded by foot ulcers and diabetes remains the most common cause of non - traumatic amputation in western countries.prevention is the first step toward solving diabetic foot problems .\nalthough it was estimated that a leg is lost to diabetes somewhere in the world every 30 s , a more important fact is that upto 85% of all amputations in diabetes is preventable.reductions in amputations will only be achieved if healthcare professionals from all specialties realize that , as brand once stated , \npain is god 's greatest gift to mankind : it is the loss of pain that permits patients with neuropathy to develop ulcers and continue walking on them despite the presence of often overwhelming infection.strategies aimed at preventing foot ulcers are cost - effective and can even be cost - saving if increased education and effort are focused on those patients with recognized risk factors for the development of foot problems.diabetes is now the most common cause of charcot neuroarthropathy . \n \nfoot ulceration is common , affecting up to 25% of patients with diabetes during their lifetime . over 85% of lower limb amputations\nare preceded by foot ulcers and diabetes remains the most common cause of non - traumatic amputation in western countries .\nalthough it was estimated that a leg is lost to diabetes somewhere in the world every 30 s , a more important fact is that upto 85% of all amputations in diabetes is preventable .\nreductions in amputations will only be achieved if healthcare professionals from all specialties realize that , as brand once stated , \npain is god 's greatest gift to mankind : it is the loss of pain that permits patients with neuropathy to develop ulcers and continue walking on them despite the presence of often overwhelming infection .\nstrategies aimed at preventing foot ulcers are cost - effective and can even be cost - saving if increased education and effort are focused on those patients with recognized risk factors for the development of foot problems .\nthe consensus development conference on standardized measures in diabetic neuropathy recommended the following five measures to be employed in the diagnosis of diabetic neuropathy : \n clinical measuresmorphological and biochemical analyseselectrodiagnostic assessmentquantitative sensory testing , andautonomic nervous system testing . \n \nmorphological and biochemical analyses electrodiagnostic assessment quantitative sensory testing , and autonomic nervous system testing .\nmore recently , watkins and edmonds have suggested a classification based on the natural history of the various syndromes , which clearly separates them into three distinct groups : \n progressive neuropathiesreversible neuropathiespressure palsies . \n \nprogressive neuropathies reversible neuropathies there is no association with duration of diabetes or other microvascular complications of diabetes .\nthe national commission on diabetes reported that an estimated 5 - 15% of diabetic patients will require a lower extremity amputation at some point in their lives .\nmost and sinnock also report that 45% of all lower extremity amputations are in patients with dm and that diabetic patients have a risk rate 15 times higher than the non - diabetic patients .\nmany factors can contribute to plantar ulcers in diabetic patients , but the two major factors are believed to be antipathy and neuropathy .\nlevin describes the sequence of ulceration secondary to neuropathy from sensory , motor , and autonomic nerve fibers .\nsensory loss can allow painless trauma , and motor neuropathy can lead to muscle atrophy and foot deformity , which causes increased pressure on parts of the insensitive foot .\nbrand has strongly emphasized the role of decreased sensation and concurrent increased , repetitive mechanical pressures as principal causative factors in ulceration .\nhe described that the gradual decrease in sensation seen in diabetic patients and noted a certain threshold of insensitivity they reach that puts them at risk for ulceration .\nin addition to obvious deformity , limited joint mobility ( ljm ) of the foot and ankle may decrease flexibility and increase susceptibility to ulceration .\nlimited joint mobility has been well documented in the upper extremity of patients with insulin - dependent diabetes mellitus ( iddm ) and recently in the shoulders of patients with non - insulin - dependent diabetes mellitus ( niddm ) .", "role": "user" }, { "content": "aim : to study about the utility of goniometry in screening for limited joint mobility ( ljm ) in patients attending a secondary level diabetic clinic.materials and methods : randomly selected data of 100 patients attending a secondary level diabetic clinic without any complications were used . \n baseline neuropathy assessments , namely monofilament and biothesiometry were done . \n range of movement around the ankle joint and 1st metatarsal joint was done using goniometry . \n both the results were compared.inclusion criteria : selected 100 patients attending a secondary level diabetic clinic and on regular follow - up were included in the study.exclusion criteria : sick patients requiring parenteral feeds , iv antibiotics , co - morbid conditions such as microvascular complication , autonomic gastroparesis , and diabetic foot infections were excluded from the study.conclusion:goniometric screening for ljm is a cheap and effective screening tool for detecting early structural deformity producing a higher plantar pressure and ulcer , and thereby preventing them at early stage .", "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 carboxyl-terminal cytoplasmic domain of CD36 is required for oxidized low-density lipoprotein modulation of NF-kappaB activity by tumor necrosis factor-alpha. The binding of oxidized low-density lipoprotein (Ox LDL) by monocyte-macrophages causes pleiotropic effects, including changes in gene expression, and is thought to represent an early event in atherogenesis. The integral membrane glycoprotein CD36 appears to play a physiological role in binding and uptake of Ox LDL by monocyte-macrophages, although the molecular events associated with CD36-Ox LDL interaction are unknown. To approach this issue, we used CD36 transfected Chinese hampster ovary (CHO) cells, exposed them to Ox LDL, and determined changes in the activity of the transcription factor NF-kappaB. We report here that Ox LDL enhanced DNA binding activity of nuclear extracts to an NF-kappaB sequence following activation of CD36-producing CHO cells with the proinflammatory cytokine tumor necrosis factor-alpha (TNF-alpha). This enhanced DNA binding activity was inhibited by coincubation of CD36 transfected cells with the human CD36-specific antibody OKM5. We also determined that activation of NF-kappaB DNA binding activity required an intact carboxyl-terminal cytoplasmic segment on CD36. Our results support the idea that human CD36 mediates signal transduction events in response to Ox LDL.", "role": "user" }, { "content": "{\"CellLine\": [\"CD36 - producing CHO cells\"], \"CellType\": [\"macrophages\", \"monocyte - macrophages\", \"Chinese hampster ovary (CHO) cells\", \"monocyte\", \"- macrophages\"], \"DNA\": [\"NF - kappaB sequence\"], \"Protein\": [\"carboxyl - terminal cytoplasmic domain\", \"The integral membrane glycoprotein CD36\", \"transcription factor\", \"tumor necrosis factor - alpha\", \"human CD36 - specific antibody\", \"TNF - alpha\", \"human CD36\", \"glycoprotein CD36\", \"OKM5\", \"NF - kappaB\", \"carboxyl - terminal cytoplasmic segment\", \"proinflammatory cytokine\", \"CD36\"], \"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: [\"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\nProphylactic lidocaine in the early phase of suspected myocardial infarction . Four hundred two patients with suspected myocardial infarction seen within 6 hours of the onset of symptoms entered a double-blind randomized trial of lidocaine vs placebo . During the 1 hour after administration of the drug the incidence of ventricular fibrillation or sustained ventricular tachycardia among the 204 patients with acute myocardial infarction was low , 1.5 % . Lidocaine , given in a 300 mg dose intramuscularly followed by 100 mg intravenously , did not prevent sustained ventricular tachycardia , although there was a significant reduction in the number of patients with warning arrhythmias between 15 and 45 minutes after the administration of lidocaine ( p less than 0.05 ) . The average plasma lidocaine level 10 minutes after administration for patients without a myocardial infarction was significantly higher than that for patients with an acute infarction . The mean plasma lidocaine level of patients on beta-blocking agents was no different from that in patients not on beta blocking agents . During the 1-hour study period , the incidence of central nervous system side effects was significantly greater in the lidocaine group , hypotension occurred in 11 patients , nine of whom had received lidocaine , and four patients died from asystole , three of whom had had lidocaine . We can not advocate the administration of lidocaine prophylactically in the early hours of suspected myocardial infarction .", "role": "user" }, { "content": "{\"Intervention\": [\"Lidocaine\", \"lidocaine\", \"Prophylactic lidocaine\", \"placebo\"], \"Outcome\": [\"average plasma lidocaine level\", \"minutes after\", \"died\", \"number of patients with warning arrhythmias\", \"incidence of ventricular fibrillation\", \"sustained ventricular tachycardia\", \"mean plasma lidocaine level\", \"incidence of central nervous system side effects\", \"hypotension\"], \"Participant\": [\"Four hundred two\", \"204\", \"myocardial infarction\"]}", "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 does the SAGA complex acronym stands for?\n\nContext: SAGA (Spt-Ada-Gcn5 Acetyltransferase)\nSAGA (Spt-Ada-Gcn5-acetyltransferase)\nSpt-Ada-Gcn5-acetyltransferase (SAGA)\nSpt-Ada-Gcn5-acetyltransferase (SAGA) complex is a transcription coactivator\nthe yeast transcriptional coactivator Spt-Ada-Gcn5 acetyltransferase (SAGA)", "role": "user" }, { "content": "Spt-Ada-Gcn5-acetyltransferase", "role": "assistant" } ]