Datasets:

---

kejian

/

SciRIFF-4096-0214-v1

like 0

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: A large collection of suppressor interactions that reveal functional plasticity of macromolecular complexes and degenerate pathways for circumvent\n\nKeyphrases: mutational robustness genomic sequence\n\nDataset descriptions:\nADAM: ADAM is organized as a half day Challenge, a Satellite Event of the ISBI 2020 conference in Iowa City, Iowa, USA. The ADAM challenge focuses on the investigation and development of algorithms associated with the diagnosis of Age-related Macular degeneration (AMD) and segmentation of lesions in fundus photos from AMD patients.\nBioGRID: BioGRID is a biomedical interaction repository with data compiled through comprehensive curation efforts. The current index is version 4.2.192 and searches 75,868 publications for 1,997,840 protein and genetic interactions, 29,093 chemical interactions and 959,750 post translational modifications from major model organism species.\nSParC: SParC is a large-scale dataset for complex, cross-domain, and context-dependent (multi-turn) semantic parsing and text-to-SQL task (interactive natural language interfaces for relational databases).\nComplexWebQuestions: ComplexWebQuestions is a dataset for answering complex questions that require reasoning over multiple web snippets. It contains a large set of complex questions in natural language, and can be used in multiple ways: By interacting with a search engine; As a reading comprehension task: the authors release 12,725,989 web snippets that are relevant for the questions, and were collected during the development of their model; As a semantic parsing task: each question is paired with a SPARQL query that can be executed against Freebase to retrieve the answer.\n\nOptions: A: ADAM B: BioGRID C: SParC D: ComplexWebQuestions", "role": "user" }, { "content": "BioGRID", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to recognize unseen images in semantic space.\n\nKeyphrases: zero-shot recognition image\n\nDataset descriptions:\nSUN3D: SUN3D contains a large-scale RGB-D video database, with 8 annotated sequences. Each frame has a semantic segmentation of the objects in the scene and information about the camera pose.\nSNIPS: The SNIPS Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity: SearchCreativeWork (e.g. Find me the I, Robot television show), GetWeather (e.g.\naPY: aPY is a coarse-grained dataset composed of 15339 images from 3 broad categories (animals, objects and vehicles), further divided into a total of 32 subcategories (aeroplane, …, zebra).\nReplica: The Replica Dataset is a dataset of high quality reconstructions of a variety of indoor spaces. Each reconstruction has clean dense geometry, high resolution and high dynamic range textures, glass and mirror surface information, planar segmentation as well as semantic class and instance segmentation.\n\nOptions: A: SUN3D B: SNIPS C: aPY D: Replica", "role": "user" }, { "content": "aPY", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nAutomatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM( 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level. Their system was shown to have beaten word-overlap metrics such as BLEU with large margins. We start with the question of whether an adversary can game the ADEM model. We design a battery of targeted attacks at the neural network based ADEM evaluation system and show that automatic evaluation of dialogue systems still has a long way to go. ADEM can get confused with a variation as simple as reversing the word order in the text! We report experiments on several such adversarial scenarios that draw out counterintuitive scores on the dialogue responses. We take a systematic look at the scoring function proposed by ADEM and connect it to linear system theory to predict the shortcomings evident in the system. We also devise an attack that can fool such a system to rate a response generation system as favorable. Finally, we allude to future research directions of using the adversarial attacks to design a truly automated dialogue evaluation system.\n\nCited Abstract(s):\n[1]: Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., I don’t know) regardless of the input. We suggest that the traditional objective function, i.e., the likelihood of output (response) given input (message) is unsuited to response generation tasks. Instead we propose using Maximum Mutual Information (MMI) as the objective function in neural models. Experimental results demonstrate that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.\n\n[2]: We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.\n\n[3]: We introduce Discriminative BLEU (∆BLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs. Reference strings are scored for quality by human raters on a scale of [−1, +1] to weight multi-reference BLEU. In tasks involving generation of conversational responses, ∆BLEU correlates reasonably with human judgments and outperforms sentence-level and IBM BLEU in terms of both Spearman’s ρ and Kendall’s τ .\n\n[4]: © 2015 Association for Computational Linguistics. Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates. With fewer heuristics, an objective evaluation in two differing test domains showed the proposed method improved performance compared to previous methods. Human judges scored the LSTM system higher on informativeness and naturalness and overall preferred it to the other systems..\n\n[5]: We present a data-driven approach to generating responses to Twitter status posts, based on phrase-based Statistical Machine Translation. We find that mapping conversational stimuli onto responses is more difficult than translating between languages, due to the wider range of possible responses, the larger fraction of unaligned words phrases, and the presence of large phrase pairs whose alignment cannot be further decomposed. After addressing these challenges, we compare approaches based on SMT and Information Retrieval in a human evaluation. We show that SMT outperforms IR on this task, and its output is preferred over actual human responses in 15 of cases. As far as we are aware, this is the first work to investigate the use of phrase-based SMT to directly translate a linguistic stimulus into an appropriate response.\n\n[6]: As a new way of training generative models, Generative Adversarial Net (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. However, it has limitations when the goal is for generating sequences of discrete tokens. A major reason lies in that the discrete outputs from the generative model make it difficult to pass the gradient update from the discriminative model to the generative model. Also, the discriminative model can only assess a complete sequence, while for a partially generated sequence, it is nontrivial to balance its current score and the future one once the entire sequence has been generated. In this paper, we propose a sequence generation framework, called SeqGAN, to solve the problems. Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update. The RL reward signal comes from the GAN discriminator judged on a complete sequence, and is passed back to the intermediate state-action steps using Monte Carlo search. Extensive experiments on synthetic data and real-world tasks demonstrate significant improvements over strong baselines.", "role": "user" }, { "content": "Since our work focuses on a critique of automatic evaluation metrics we first do a quick review of various popular metrics used for automatic evaluation and then review works which are similar in idea to ours and themselves do a critique of these evaluation metrics. The research on dialogue generation models is guided by the dialogue evaluation metrics which provide the means for comparison. BLEU and METEOR scores, originally used for machine translation, are adopted for this task by various works [3]7 [5] [2] [4] [3] [1] . BLEU analyses the co-occurrences of n-grams whereas METEOR creates an explicit alignment using exact matching, followed by WordNet synonyms, stemmed tokens, and paraphrases, in that order. Similarly the ROUGE metric variants, originally used for automatic summarization, work on overlapping units such as n-grams, word sub-sequences and word pairs. The ROUGE metrics being recall-oriented, require a sufficient number of references to produce reliable scores.", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nObservational learning and the formation of classes of reading skills by individuals with autism and other developmental disabilities . We investigated whether individuals with developmental disabilities will demonstrate stimulus classes after observing another individual demonstrate the prerequisite conditional discriminations . In Experiment 1 , participants learned conditional discriminations among dictated words , pictures , and printed words . They also observed a model without disabilities demonstrate conditional discriminations among a different set of dictated words , pictures , and printed words . The classes assigned to each participant belonged to a larger superordinate category , as did the classes assigned to each model . The superordinate categories were different for participants and models . All participants subsequently demonstrated full stimulus classes with the stimuli involved in direct training : They named pictures , read printed words , and matched pictures and words to one another . However , based on observing a model , none of the participants demonstrated full stimulus classes . In Experiment 2 , participants learned conditional discriminations among the stimuli in three sets , and observed a model 's training with the stimuli in three different sets . The classes assigned to each participant belonged to the same larger superordinate category as did those assigned to their respective model . All participants subsequently demonstrated full stimulus classes with the stimuli involved in direct training . They also demonstrated full classes with at least one of their model 's sets of training stimuli . When full stimulus classes did not occur from observing a model , participants named the model 's pictures , read the model 's printed words , or matched the model 's pictures and words . Stimulus class technology , coupled with the opportunity to observe another individual perform a skill , may be an economical and efficient means of teaching persons with developmental disabilities .", "role": "user" }, { "content": "{\"Intervention\": [\"observe another individual perform\", \"learned conditional discriminations among dictated words , pictures , and printed words . They also observed a model without disabilities demonstrate conditional discriminations among a different set of dictated words , pictures , and printed words . The classes assigned to each participant belonged to a larger superordinate category , as did the classes assigned to each model .\", \"Observational learning\", \"conditional discriminations among the stimuli\", \"observed a model \\u0027s training\", \"observing another individual demonstrate\", \"superordinate categories\", \"Stimulus class technology\"], \"Outcome\": [\"full classes\", \"stimulus classes .\", \"stimulus classes\", \"full stimulus classes\"], \"Participant\": [\"autism\", \"individuals with developmental disabilities\", \"persons with developmental disabilities .\"]}", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nTramadol suppository versus placebo for the relief of perineal pain after perineorrhaphy : a randomized controlled trial in Thailand . OBJECTIVE This randomized double-blinded control trial was conducted to compare the effectiveness of tramodol and placebo rectal suppository for the management of postpartum perineal pain after perineorrhaphy . MATERIAL AND METHOD One hundred women who gave birth vaginally with episiotomy and a second- or third-degree tear , were randomly assign to receive two tablets oftramadol 50 mg or two tablets ofplacebo , the pill were physically similar to the real drug . Pain ratings were recorded immediately after perineorrhaphy , 30 minutes , and 1 , 2 , 6 , 12 and 24 hours after first dose on a 10-cm visual analogue scale . Side effects and overall opinion were assessed . RESULTS Tramadol and placebo had no statistical significances in analgesic properties , assessed by the means of pain rating at the different time intervals . There were no serious adverse events reported . CONCLUSION No differences were found in between Tramadol and placebo in relief perineal pain after perineorrhaphy", "role": "user" }, { "content": "{\"Intervention\": [\"two tablets ofplacebo\", \"tramodol\", \"Tramadol\", \"oftramadol 50 mg\", \"placebo\", \"Tramadol suppository\"], \"Outcome\": [\"Side effects and overall opinion\", \"visual analogue scale .\", \"analgesic properties\", \"pain rating\", \"effectiveness\", \"perineal pain\", \"no serious adverse events\", \"postpartum perineal pain\", \"Pain ratings\"], \"Participant\": [\"women\", \"perineal pain\", \"second- or third-degree tear\"]}", "role": "assistant" } ]

[ { "content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\n[Effects of Salvia miltiorrhiza on serum levels of inflammatory cytokines in patients with severe acute pancreatitis].\nAbstract 1:\nTo study the effects of Salvia miltiorrhiza on serum levels of cytokines including interleukin-6 (IL-6), interleukin-8 (IL-8) and tumor necrosis factor-alpha (TNF-alpha) in patients with severe acute pancreatitis (SAP).\n Thirty-six SAP patients were randomly divided into Salvia miltiorrhiza-treated group and non-Salvia miltiorrhiza-treated group with eighteen patients in each group. Fourteen age-matched healthy volunteers were assigned to control group. Serum levels of IL-6, IL-8, and TNF-alpha were tested within 24 hours of admission and 7 days after admission.\n Compared with those of the healthy volunteers, serum levels of the three cytokines of the SAP patients were significantly elevated (P<0.05). Serum levels of the three cytokines were significantly decreased in both Salvia miltiorrhiza-treated group and non-Salvia miltiorrhiza-treated group after 7-day treatment (P<0.05). The declining of the serum levels of the three cytokines in Salvia miltiorrhiza-treated group was more obvious than that in non-Salvia miltiorrhiza-treated group.\n Salvia miltiorrhiza can treat SAP patients by reducing the serum levels of IL-6, IL-8, and TNF-alpha.", "role": "user" }, { "content": "Some Chinese medicinal herbs may work in acute pancreatitis. However, because the trials were of low quality, the evidence is too weak to recommend any single herb. Rigorously designed, randomized, double-blind, placebo-controlled trials are required.", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nindividual mouse x chromosome amplicons ( palindromic or tandem segmental duplications ) were first identified using the inverted repeats finder ( irf ) program9 .\nthe mus musculus reference sequence ( ncbi build 36.1 ) was used to select palindromes with arms 8 kb , 90% nucleotide identity between arms , and < 500 kb of each other .\n( 2004 ) palindrome analyses , should eliminate all repeats due to recent line insertions .\ncustom tracks can be downloaded from https://tandem.bu.edu to display all mouse x chromosome palindromes on the ucsc genome browser . in some cases the irf program truncated and/or missed palindrome arms . therefore , to resolve the complete structure of all irf - identified palindromes , custom perl code19 was used to characterize their genomic structure via triangular dot - plots ( supplementary fig .\n1 ) . since the irf program identifies only palindromes , we utilized an alternative strategy to detect amplicons in tandem , which could also confirm the irf - identified amplicons .\nensembl s biomart program ( http://www.ensembl.org/ ) was used to obtain all x - linked protein - coding genes with paralogous genes on the x chromosome ( supplementary table 1 ) .\nmulti - copy genes less than 1 mb apart , which share 80% amino acid identity between any two copies , and which are not found in multiple copies throughout the mouse genome ( e.g. retroviral proteins , ribosomal proteins , or olfactory receptors ) were considered putative ampliconic regions .\nmulti - copy gene clusters passing these three criteria ( supplementary table 1 ) were subjected to triangular dot - plot analysis19 to determine if the region is ampliconic .\nampliconic regions identified via this method confirmed the irf - identified amplicons as well as five new tandemly arrayed amplicons ( table 1 ) .\nrepeat unit boundaries and percent identities between exclusively tandemly arrayed amplicons were determined via clustalw20 .\nmulti - copy gene clusters fulfilling the three selection criteria , but not present in ampliconic regions were termed non - ampliconic multi - copy genes .\nto estimate gene copy number , we used both the ncbi build 37.1 annotation and protein sequence searches via tblastn to the mouse x chromosome reference sequence . to identify all protein - coding genes within the ampliconic repeats , each repeat unit was repeat masked ( http://www.repeatmasker.org ) and subsequently compared to the ncbi mouse est database using blast21 .\nwe also searched , via blast , for predicted genes without est support ( ncbi mouse ab initio database ) to uncover novel transcripts .\nsupplementary table 3 provides a list of all novel and known genes identified via blast searches .\ntotal rna was extracted using trizol ( gibco brl ) according to manufacturer s instructions . for dnase treatment\n, 3g total rna was incubated with 1.5 u rq dnase 1 ( promega ) at 37c for 90 mins .\nthe rna was precipitated , resuspended and then reverse transcribed using superscript ii reverse transcriptase ( 200 u , gibco brl ) for 90 mins at 42c .\npcr was performed using the parameters : 1 cycle 94c 3 mins , 35 cycles 94c 30secs , 56c 30secs , 72c 30secs , and then 1 cycle 72c 10mins .\nprimer sequences ( supplementary table 3 ) for all rt - pcr reactions were designed to detect at least two copies of each family member .\nwe used long range pcr products from bacs as probes for birc4 , fmr1 , scml2 , ott , slx - like 1 , slx , and zfx .\nwe analyzed published microarray expression data ( gene expression omnibus gse4193)7 from isolated germ cell populations of a spermatogonia , b spermatogonia , pachytene spermatocytes and round spermatids ( two replicates for each cell population ) .\n( 2006 ) to set the trimmed ( 2% from each side ) mean signal intensity to 125 . probes with < 100 signal intensity at all timepoints\nsingle - copy x - linked genes , summing to 552 , were selected from ensembl annotations of genes without mouse paralogs .\nthe 25 multi - copy genes probe - ids and expression values for each timepoint are listed in supplementary table 5 .\nwhen multiple probes matched a multi - copy gene ( see supplementary table 5 for genes with multiple probe_ids ) we selected a single probe , with the median signal intensity .\nwilcoxon ranks sum paired tests , using jmp 5.1 software ( sas institute inc . ) , were performed on all comparisons of average expression levels and were used because they diminish the influence of outliers .\nindividual mouse x chromosome amplicons ( palindromic or tandem segmental duplications ) were first identified using the inverted repeats finder ( irf ) program9 .\nthe mus musculus reference sequence ( ncbi build 36.1 ) was used to select palindromes with arms 8 kb , 90% nucleotide identity between arms , and < 500 kb of each other .\n( 2004 ) palindrome analyses , should eliminate all repeats due to recent line insertions .\ncustom tracks can be downloaded from https://tandem.bu.edu to display all mouse x chromosome palindromes on the ucsc genome browser . in some cases the irf program truncated and/or missed palindrome arms . therefore , to resolve the complete structure of all irf - identified palindromes , custom perl code19 was used to characterize their genomic structure via triangular dot - plots ( supplementary fig .\n1 ) . since the irf program identifies only palindromes , we utilized an alternative strategy to detect amplicons in tandem , which could also confirm the irf - identified amplicons .\nensembl s biomart program ( http://www.ensembl.org/ ) was used to obtain all x - linked protein - coding genes with paralogous genes on the x chromosome ( supplementary table 1 ) .\nmulti - copy genes less than 1 mb apart , which share 80% amino acid identity between any two copies , and which are not found in multiple copies throughout the mouse genome ( e.g. retroviral proteins , ribosomal proteins , or olfactory receptors ) were considered putative ampliconic regions .\nmulti - copy gene clusters passing these three criteria ( supplementary table 1 ) were subjected to triangular dot - plot analysis19 to determine if the region is ampliconic .\nampliconic regions identified via this method confirmed the irf - identified amplicons as well as five new tandemly arrayed amplicons ( table 1 ) .\nrepeat unit boundaries and percent identities between exclusively tandemly arrayed amplicons were determined via clustalw20 .\nmulti - copy gene clusters fulfilling the three selection criteria , but not present in ampliconic regions were termed non - ampliconic multi - copy genes .\nto estimate gene copy number , we used both the ncbi build 37.1 annotation and protein sequence searches via tblastn to the mouse x chromosome reference sequence . to identify all protein - coding genes within the ampliconic repeats , each repeat unit was repeat masked ( http://www.repeatmasker.org ) and subsequently compared to the ncbi mouse est database using blast21 .\nwe also searched , via blast , for predicted genes without est support ( ncbi mouse ab initio database ) to uncover novel transcripts .\nsupplementary table 3 provides a list of all novel and known genes identified via blast searches .\ntotal rna was extracted using trizol ( gibco brl ) according to manufacturer s instructions . for dnase treatment , 3g total rna was incubated with 1.5 u rq dnase 1 ( promega ) at 37c for 90 mins .\nthe rna was precipitated , resuspended and then reverse transcribed using superscript ii reverse transcriptase ( 200 u , gibco brl ) for 90 mins at 42c .\npcr was performed using the parameters : 1 cycle 94c 3 mins , 35 cycles 94c 30secs , 56c 30secs , 72c 30secs , and then 1 cycle 72c 10mins .\nprimer sequences ( supplementary table 3 ) for all rt - pcr reactions were designed to detect at least two copies of each family member .\nwe used long range pcr products from bacs as probes for birc4 , fmr1 , scml2 , ott , slx - like 1 , slx , and zfx .\nwe analyzed published microarray expression data ( gene expression omnibus gse4193)7 from isolated germ cell populations of a spermatogonia , b spermatogonia , pachytene spermatocytes and round spermatids ( two replicates for each cell population ) .\n( 2006 ) to set the trimmed ( 2% from each side ) mean signal intensity to 125 . probes with < 100 signal intensity at all timepoints\nsingle - copy x - linked genes , summing to 552 , were selected from ensembl annotations of genes without mouse paralogs .\nthe 25 multi - copy genes probe - ids and expression values for each timepoint are listed in supplementary table 5 .\nwhen multiple probes matched a multi - copy gene ( see supplementary table 5 for genes with multiple probe_ids ) we selected a single probe , with the median signal intensity .\nwilcoxon ranks sum paired tests , using jmp 5.1 software ( sas institute inc . ) , were performed on all comparisons of average expression levels and were used because they diminish the influence of outliers .", "role": "user" }, { "content": "according to the prevailing view , mammalian x chromosomes are enriched in spermatogenesis genes expressed before meiosis13 and deficient in spermatogenesis genes expressed after meiosis2,3 . \n the paucity of post - meiotic genes on the x chromosome has been interpreted as a consequence of meiotic sex chromosome inactivation ( msci ) the complete silencing of genes on the xy bivalent at meiotic prophase4,5 . \n recent studies have concluded that msci - initiated silencing persists beyond meiosis68 and that most x - genes remain repressed in round spermatids7 . \n we report here that 33 multi - copy gene families , representing ~273 mouse x - linked genes , are expressed in the testis and that this expression is predominantly in post - meiotic cells . \n rna fish and microarray analysis show that the maintenance of x chromosome post - meiotic repression is incomplete . \n furthermore , x - linked multi - copy genes exhibit expression levels similar to those of autosomal genes . \n thus , not only is the mouse x chromosome enriched for spermatogenesis genes functioning before meiosis , but in addition ~18% of mouse x - linked genes exhibit post - meiotic expression .", "role": "assistant" } ]

[ { "content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: Fractal analysis of the ischemic transition region in chronic ischemic heart disease using magnetic resonance imaging To introduce a novel hypothesis and method to characterise pathomechanisms underlying myocardial ischemia in chronic ischemic heart disease by local fractal analysis (FA) of the ischemic myocardial transition region in perfusion imaging. Vascular mechanisms to compensate ischemia are regulated at various vascular scales with their superimposed perfusion pattern being hypothetically self-similar. Dedicated FA software (\" FraktalWandler \") has been developed. Fractal dimensions during first-pass (FDfirst-pass) and recirculation (FDrecirculation) are hypothesised to indicate the predominating pathomechanism and ischemic severity, respectively. Twenty-six patients with evidence of myocardial ischemia in 108 ischemic myocardial segments on magnetic resonance imaging (MRI) were analysed. The 40th and 60th percentiles of FDfirst-pass were used for pathomechanical classification, assigning lesions with FDfirst-pass ≤ 2.335 to predominating coronary microvascular dysfunction (CMD) and ≥2.387 to predominating coronary artery disease (CAD). Optimal classification point in ROC analysis was FDfirst-pass = 2.358. FDrecirculation correlated moderately with per cent diameter stenosis in invasive coronary angiography in lesions classified CAD (r = 0.472, p = 0.001) but not CMD (r = 0.082, p = 0.600). The ischemic transition region may provide information on pathomechanical composition and severity of myocardial ischemia. FA of this region is feasible and may improve diagnosis compared to traditional noninvasive myocardial perfusion analysis. • A novel hypothesis and method is introduced to pathophysiologically characterise myocardial ischemia. • The ischemic transition region appears a meaningful diagnostic target in perfusion imaging. • Fractal analysis may characterise pathomechanical composition and severity of myocardial ischemia.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"vascular\", \"Vascular\"], \"Bacterium\": [], \"BiologicFunction\": [\"ischemia\", \"myocardial ischemia\", \"CAD\", \"ischemic\", \"coronary artery disease\", \"recirculation\", \"pathomechanisms\", \"chronic ischemic heart disease\", \"pathomechanism\", \"CMD\", \"regulated\", \"FDrecirculation\", \"coronary microvascular dysfunction\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"diagnosis\", \"lesions\", \"improve\"], \"Food\": [], \"HealthCareActivity\": [\"perfusion imaging\", \"magnetic resonance imaging\", \"MRI\", \"superimposed perfusion\", \"coronary angiography\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"scales\", \"software\", \"noninvasive\", \"FraktalWandler\", \"method\", \"classification\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"analysis\", \"FA\"], \"SpatialConcept\": [\"per cent diameter stenosis\", \"region\", \"myocardial\", \"segments\", \"pattern\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nAccuracy of spin-component scaled ADC(2) excitation energies and potential energy surfaces\n\nPaper sections:\nIntroduction\n<p>In two recent papers 1,2 in this Journal, we have extended the large pool of benchmark calculations on vertical excitation energy [3][4][5][6][7][8][9][10][11][12][13][14] with characterisation of the excited state potential energy surfaces using Coupled-Cluster (CC) type methods. In the first paper we have found 1 that the popular CC2 method 15 fails sometimes badly, depending on the type of the excited state. The parent CCSD method (termed either EOM-CCSD [16][17][18] or CCSD-LR 19,20 ) gives usually reasonable results, but the inclusion of approximate triple excitations is necessary to achieve high accuracy. Since this is generally not possible for larger systems, improved second order approximations are requested. 12,13 Along this line, in our recent study 2 we also investigated spin-component scaled versions of CC2 21,22 and found that both the scaledopposite-spin (SOS-CC2) and spin-component-scaled (SCS-CC2) variants cure the problem of CC2 to a considerable extent and the resulting potential energy surfaces run quite close to those obtained with CCSD.</p><p>Besides CC2, another second order method often used in applications is the so called ADC(2) (2nd order Algebraic Diagrammatic Construction) method. 23,24 This method is closely related to CC2, 25 and it is a widespread experience that CC2 and ADC(2) results are of very similar quality. 7,[25][26][27] In this paper we augment the results of our previous paper 2 and present the results of the same type of calculations, now using the ADC(2) and its spin-component scaled variants SOS-ADC(2) and SCS-ADC(2). We believe that this addition is necessary to get a complete picture about the performance of the second order methods which can be used and are being used to describe excited states of larger molecules.</p>\n\nThe ADC(2) method\n<p>The 2nd order Algebraic Diagrammatic Construction (ADC(2)) method has been introduced by Schirmer, 23,28 based on a diagrammatic perturbational expansion of the polarization propagator. 23 Later the ADC(2) method has been reintroduced by Trofimov and Schirmer. 24,29 The real advent of the method came when its relation to CC2 has been established and its implementation in program codes, e.g. in TURBOMOLE 30 pursued. The close relation of CC2 and ADC(2) has been discussed by Hättig 25 and recently in detail by Izsák,27 showing that ADC(2) can be considered as an approximation to CC2 by neglecting T 1 amplitudes (thus enforcing strictly second order) and symmetrising the Jacobian. As has been shown e.g. in ref. 12, neglect of T 1 amplitudes has a negligible effect on excitation energies. Symmetrisation, on the other hand, avoids technical issues related to the non-Hermitian formulation. 25 These two approximations also result in a slightly lower cost.</p>\n\nSpin-component scaled ADC(2)\n<p>The concept of spin-component scaled CC2, i.e. the introduction of spin scaling factors C OS and C SS into the formulae of the effective Hamiltonian has been first established by Hättig et al.,21 in the spirit of spin-component-scaled MP2 originally proposed by Grimme. 31,32 In case of the SCS (spin-component-scaled) variant the same-spin integrals are multiplied by a factor of C SS =1/3, while the opposite-spin integrals by C OS =6/5. In the SOS (scaledopposite-spin) version only the opposite-spin integrals are retained (C OS =1.3, C SS =0.0).</p><p>Using the above mentioned similarity of CC2 and ADC(2) theories, the same spin-scaled modifications can be introduced into ADC(2) in a straightforward manner, leading to the SCS-ADC(2) and SOS-ADC(2) models. The latter was first realized by Winter and Hättig,22 and later by Dreuw and co-workers 7,33 and, recently, by Mester and co-workers. 34,35 Today, implementations are available in the TURBOMOLE 30 and MRCC 36 program packages. The particular choice of SOS-ADC(2) is of outstanding importance for applications on large systems as, if combined with the Resolution-of-Identity approximation of the two-electron integrals, 37 it can be formulated to obey a computational cost scaling with no more than the fourth power of the system size. 22,38</p>\n\nComputational details\n<p>The same methodology as in the parent paper 2 has been used. To benchmark the accuracy of vertical excitation energies, 64 valence and 56 Rydberg states of 23 molecules have been calculated using the aug-cc-pVDZ basis set, with the core electrons not correlated. The calculations were performed using the TURBOMOLE 30 Gradients of the vertical excitation energy at the Franck-Condon point have been calculated numerically using the MRCC 36 program in the cc-pVDZ basis set. For comparison of the gradients, the length of the vectors, as well as their relative angle with respect to the reference values is evaluated.</p><p>Finally, the surface plots that follow the Frank-Condon forces in mass-weighted steps (for a detailed definition, see our previous paper 1 ) have also been evaluated in the cc-pVDZ basis by the MRCC program. 36 3 Results and discussion (The full set of results for the excitation energies is available in the Supporting Information.)</p><p>The errors of ADC(2) lie close to those of the unscaled CC2 model. In particular, the severe underestimation of Rydberg excitation energies is very apparent, with an error of -0.42 eV being worse than even CC2 by 0.04 eV. Nevertheless, the valence-Rydberg misbalance, shown in the last column of table 1, is exactly as large as that of CC2. The two spin-component scaled ADC(2) variants show statistics very similar to their CC2 counterparts, the difference of the mean errors being no more than 0.03 eV, and even the standard deviations follow the same pattern. The above mentioned misbalance is reduced by spin-component scaling by as much as 38 and 55 percent for the SCS-ADC(2) and SOS-ADC(2) models, respectively, essentially identical to the SCS-CC2 and SOS-CC2 results.</p>\n\nFranck-Condon gradients\n<p>Measures on the gradients of the excited state energies at the ground state equilibrium geometry are presented in tables 2, 3, 4, and 5. The ADC(2) gradients, as evaluated by their length and their direction relative to the reference vectors, show an accuracy similar to that of CC2, with no clear indication of one being better than the other. Compared to CC2, in many cases a larger error of the gradient length is accompanied by a more accurate direction of the vector, or vice versa. However, in situations where the description is clearly problematic (e.g. in some n-π * states of nucleobases), both measures are inferior to the CC2 result. For such states, the effect of spin-component scaling is generally also similar, marginally inferior compared to the respective CC2 variant, i.e. both SCS-ADC(2) and SOS-ADC(2) provide significantly better gradients compared to the canonical model. The only exception seems to be the π-π * state of formamide, where no improvement is seen for the ADC(2) methods, while the CC2 result is clearly surpassed by the spin-component scaled versions. This can be, however, attributed to the fact that the CC2 and ADC(2) single excitation vectors of this state show a slightly different mixing of dominant π-π * contributions. For excited states where the CC2 gradient is found to be satisfactory, the spin-component scaling in ADC(2) shifts the canonical values in the very same direction as seen in the CC2 cases. Although this does not clearly lead to more accurate gradients, the differences remain negligible as the nominal errors remain low in all such cases.</p>\n\nSurface scans\n<p>The excited state potential energy surface scans shown on figures 1, 2, 3, and 4 generally seem to emphasize the above findings even further. The ADC(2) and CC2 curves run very close to each other, at least in the first half of the explored PES. That is, wherever ADC(2) and CC2 gradients were found to be exceptionally inaccurate (like in case of the first n-π * state of cytosine), the respective plots form a well recognizable, distinct pair. The spin-component scaled ADC(2) models show a pattern similar to the one found earlier for their CC2 counterparts: 2 their divergence from the reference curve, as compared to regular ADC(2), is reduced considerably, giving nearly CCSD quality results for most investigated states. SOS-ADC(2) performs slightly better than SCS-ADC(2) in this analysis, but the difference of the two variants remains minor compared to how much they both improve over spin-unscaled ADC(2).</p>\n\nConclusions\n<p>The results presented above affirm earlier conclusions that ADC(2) and CC2 are closely related methods: not only statistics on vertical excitation energies for both valence and Rydberg states are close, but also the Frank-Condon gradients show very similar patterns.</p><p>In case of the surface scans one sees a failure of ADC(2) in situations when CC2 fails, as well. Noteworthy differences happen only for near-degeneracies where the character of the single excitation part of the solution vectors might be different for the two methods. Scaling spin-components differently in ADC(2) brings a significant improvement in most cases, very similarly to the CC2 case. Both the systematic error of the Rydberg excitation energies, and the misbalance between valence and Rydberg states are reduced. It also spectacularly corrects the potential energy surfaces when ADC(2) fails, while conserving the accuracy if it does not.</p><p>Therefore SOS-ADC(2), along with SOS-CC2, seems to be an economic and accurate variant for large calculations, considering the lowest, fourth power scaling of these methods with the system size. One should keep in mind, however, that spin-component scaling is mostly empirical (for an approximate theoretical justification for ground state see the paper of Szabados 40 ), and therefore the good performance can not be guaranteed for all systems and all situations.</p>", "role": "user" }, { "content": "In a recent paper of this Journal (Tajti and Szalay, JCTC 2019, 15, 5523) we have shown that failures of the CC2 method to describe Rydberg excited states, as well as potential energy surfaces of certain valence excited states can be cured by spincomponent scaled (SCS) versions SCS-CC2 and SOS-CC2 by a large extent. In this paper, the related and popular Second Order Algebraic Diagrammatic Construction (ADC( 2)) method and its SCS variants are inspected with the previously established methodology. The results reflect the similarity of the CC2 and ADC(2) models, showing identical problems in the case of the canonical form and the same improvement when spin-component-scaling is applied.", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\n[ Clinical application of irradiated drug-containing porcine-cornea to patients with ocular burns ] . OBJECTIVE To explore a new method for the management of patients with ocular burns . METHODS Fifty-five cases of patients with ocular burns ( in 88 eyes ) were randomly divided into treatment and control groups . Thirty cases in treatment group with 49 eyes were transplanted with irradiated drug-containing ( ofloxacin , acetyl cysteine and reduced glutathione ) porcine-cornea . 25 cases in control group with 39 eyes were treated with routine program . RESULTS Thirty-two eyes were rescued in treatment group with the cure rate of 65.3 % . But only 17 eyes were saved in control group with the cure rate of 43.59 % , indicating significant difference of the cure rate between the two groups ( P < 0.05 ) . CONCLUSION Irradiated drug-containing porcine-cornea might well be an ideal therapeutic material for the management of patients with ocular burns .", "role": "user" }, { "content": "{\"Intervention\": [\"acetyl cysteine\", \"porcine-cornea\", \"ofloxacin\", \"reduced glutathione\", \"drug-containing porcine-cornea\"], \"Outcome\": [\"eyes were rescued\", \"cure rate\", \"eyes were saved\"], \"Participant\": [\"49\", \"ocular burns\", \"Fifty-five\", \"88\"]}", "role": "assistant" } ]

[ { "content": "Find all entities of these types in the text: [\"Chemical\", \"Disease\"].\n\nOutput a JSON object.\n\nText:\nThe interpeduncular nucleus regulates nicotine's effects on free-field activity. Partial lesions were made with kainic acid in the interpeduncular nucleus of the ventral midbrain of the rat. Compared with sham-operated controls, lesions significantly (p < 0.25) blunted the early (<60 min) free-field locomotor hypoactivity caused by nicotine (0.5 mg kg(-1), i.m.), enhanced the later (60-120 min) nicotine-induced hyperactivity, and raised spontaneous nocturnal activity. Lesions reduced the extent of immunohistological staining for choline acetyltransferase in the interpeduncular nucleus (p <0.025), but not for tyrosine hydroxylase in the surrounding catecholaminergic A10 region. We conclude that the interpeduncular nucleus mediates nicotinic depression of locomotor activity and dampens nicotinic arousal mechanisms located elsewhere in the brain.", "role": "user" }, { "content": "{\"Chemical\": [\"tyrosine\", \"kainic acid\", \"choline\", \"nicotine\"], \"Disease\": [\"depression\", \"locomotor hypoactivity\", \"hyperactivity\"]}", "role": "assistant" } ]

[ { "content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: increasing proportion of cells recorded in the sub-G1 phase with increasing concentrations of arachidonic acid (Dymkowska et al., 2006).", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: hydroxychloroquine may limit spread of SARS-CoV-2 and morbidity and mortality of COVID-19 pandemic\n\nAbstract:\nBackgrounds.\nSince COVID-19 outbreak, various agents have been tested but no proven effective therapies have been identified.\nThis has led to a lot of controversies among associated researches.\nHence, in order to address the issue of using hydroxychloroquine in treating COVID-19 patients, we conducted a systematic review and meta-analysis.\nMethods.\nA thorough search was carried out to find relevant studies in MEDLINE, medRxiv, PubMed, Cochrane Database, China Academic Journals Full-text Database and Web of Science.\nTwo investigators independently reviewed 274 abstracts and 23 articles.\nThe trials which evaluated hydroxychloroquine for treatment of COVID-19 were included for this systematic review.\nTwo investigators assessed quality of the studies and data extraction was done by one reviewer and cross checked by the other.\nResults.\nFive trials involving 677 patients were included while conducting the meta-analysis.\nCompared with the control group, hydroxychloroquine with or without azithromycin showed benefits in positive-to-negative conversion of SARS-CoV-2 (odds ratio [OR], 1.95 [95% CI,0.19 to 19.73] and a reduction in progression rate (OR, 0.89 [95% CI, 0.58 to 1.37]), but without demonstrating any statistical significance.\nThis systematic review has also suggested a possible synergistic effect of the combination therapy which included hydroxychloroquine and azithromycin.\nHowever, the use of hydroxychloroquine alone was associated with increased mortality in COVID-19 patients.\nConclusion.\nThe use of hydroxychloroquine with or without azithromycin for treatment of COVID-19 patients, seems to be effective.\nThe combination of hydroxychloroquine and azithromycin has shown synergic effects.\nHowever, mortality rate was increased when the treatment was conducted with hydroxychloroquine.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Since COVID-19 outbreak, various agents have been tested but no proven effective therapies have been identified.\", \"However, the use of hydroxychloroquine alone was associated with increased mortality in COVID-19 patients.\", \"However, mortality rate was increased when the treatment was conducted with hydroxychloroquine.\"]}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: The WHO says there is no reason to believe cold weather can kill the new coronavirus, or other diseases, for that matter.\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\": \"SUPPORT\", \"evidence\": [\"In 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.\"]}", "role": "assistant" } ]

[ { "content": "Answer the following biomedical question based on the given context. Provide only the answer without additional explanation.\n\nQuestion: What is the association of spermidine with α-synuclein neurotoxicity?\n\nContext: Spermidine protects against α-synuclein neurotoxicity.\nHere, we show that administration of the naturally occurring polyamine spermidine, which declines continuously during aging in various species, alleviates a series of PD-related degenerative processes in the fruit fly Drosophila melanogaster and the nematode Caenorhabditis elegans, two established model systems for PD pathology. In the fruit fly, simple feeding with spermidine inhibited loss of climbing activity and early organismal death upon heterologous expression of human α-synuclein, which is thought to be the principal toxic trigger of PD. In this line, administration of spermidine rescued α-synuclein-induced loss of dopaminergic neurons, a hallmark of PD, in nematodes. Alleviation of PD-related neurodegeneration by spermidine was accompanied by induction of autophagy, suggesting that this cytoprotective process may be responsible for the beneficial effects of spermidine administration.\nSpermidine protects against α-synuclein neurotoxicity\nIn the fruit fly, simple feeding with spermidine inhibited loss of climbing activity and early organismal death upon heterologous expression of human α-synuclein, which is thought to be the principal toxic trigger of PD. In this line, administration of spermidine rescued α-synuclein-induced loss of dopaminergic neurons, a hallmark of PD, in nematodes\nTogether with the fact that spermidine facilitates late stages of α-Syn aggregation, our data demonstrate that spermidine promotes the very early stages of protein aggregation including α-Syn misfolding and dimerization. This finding suggests that increased levels of spermidine and potentially other polyamines can initiate the disease-related process of α-Syn.", "role": "user" }, { "content": "Spermidine protects against α-synuclein neurotoxicity", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: gargling warm water with salt or vinegar can eliminate the novel coronavirus, COVID-19. \n\nAbstract:\nPURPOSE: SARS-CoV-2 is a new pandemic influenza caused by a coronavirus which main route of transmission is through exhaled droplets that primarily infect the nose and the nasopharynx.\nThe aim of this paper is to evaluate the effect of acetic acid, the active component of vinegar, as a potential disinfectant agent for upper airways.\nMETHODS: Twenty-nine patients were enrolled and divided into two groups: group 1 (14 patients) was composed of patients treated with off-label hydroxychloroquine and lopinavir/ritonavir, whereas group 2 (15 patients) was composed of patients treated with hydroxychloroquine only, combined with the inhalation of acetic acid disinfectant at a 0.34% concentration.\nA questionnaire-based evaluation of symptoms was performed after 15 days in both groups.\nRESULTS: It appears that the number of patients treated with acetic acid (group 2) that experienced improvement in individual symptoms was double that of the other group of patients (group 1), although numbers are too small for robust statistical analysis.\nCONCLUSIONS: Considering its potential benefits and high availability, acetic acid disinfection appears to be a promising adjunctive therapy in cases of non-severe COVID-19 and deserves further investigation.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"CONCLUSIONS: Considering its potential benefits and high availability, acetic acid disinfection appears to be a promising adjunctive therapy in cases of non-severe COVID-19 and deserves further investigation.\"]}", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nEffectiveness of sensory integration interventions in children with autism spectrum disorders : a pilot study . The purpose of this pilot study was to establish a model for randomized controlled trial research , identify appropriate outcome measures , and address the effectiveness of sensory integration ( SI ) interventions in children with autism spectrum disorders ( ASD ) . Children ages 6-12 with ASD were randomly assigned to a fine motor or SI treatment group . Pretests and posttests measured social responsiveness , sensory processing , functional motor skills , and social-emotional factors . Results identified significant positive changes in Goal Attainment Scaling scores for both groups ; more significant changes occurred in the SI group , and a significant decrease in autistic mannerisms occurred in the SI group . No other results were significant . The study discusses considerations for designing future outcome studies for children with ASD .", "role": "user" }, { "content": "{\"Intervention\": [\"sensory integration ( SI )\", \"fine motor\", \"SI treatment\", \"sensory integration interventions\"], \"Outcome\": [\"Goal Attainment Scaling scores\", \"social responsiveness , sensory processing , functional motor skills , and social-emotional factors\", \"autistic mannerisms\"], \"Participant\": [\"ASD\", \"children\", \"autism spectrum disorders\", \"Children ages 6-12 with\"]}", "role": "assistant" } ]

[ { "content": "Extract all unique entities from this biomedical abstract. Only choose entities from these types: [\"Virus\", \"MedicalDevice\", \"BodySubstance\", \"SpatialConcept\", \"BiologicFunction\", \"ResearchActivity\", \"AnatomicalStructure\", \"ProfessionalOrOccupationalGroup\", \"HealthCareActivity\", \"BiomedicalOccupationOrDiscipline\", \"Bacterium\", \"Chemical\", \"InjuryOrPoisoning\", \"IntellectualProduct\", \"Finding\", \"ClinicalAttribute\", \"Organization\", \"Eukaryote\", \"Food\", \"BodySystem\", \"PopulationGroup\"].\n\nOutput a JSON object where keys are entity types and values are lists of extracted entities. If no entities found for a type, use empty list [].\n\nAbstract: Ergonomics of laparoscopic graspers and the importance of haptic feedback: the surgeons' perspective Haptic feedback is drastically reduced in laparoscopic surgery compared to open surgery. Introducing enhanced haptic feedback in laparoscopic instruments might well improve surgical safety and efficiency. In the design process of a laparoscopic grasper with enhanced haptic feedback, handle design should be addressed to strive for optimal usability and comfort. Additionally, the surgeons' perspective on the potential benefits of haptic feedback should be assessed to ascertain the clinical interest of enhanced haptic feedback. A questionnaire was designed to determine surgeons' use and preferences for laparoscopic instruments and expectations about enhanced haptic feedback. Surgeons were also asked whether they experience physical complaints related to laparoscopic instruments. The questionnaire was distributed to a group of laparoscopic surgeons based in Europe. From the 279 contacted subjects, 98 completed the questionnaire (response rate 35 %). Of all respondents, 77 % reported physical complaints directly attributable to the use of laparoscopic instruments. No evident similarity in the main preference for graspers was found, either with or without haptic feedback. According to respondents, the added value of haptic feedback could be of particular use in feeling differences in tissue consistencies, feeling the applied pressure, locating a tumor or enlarged lymph node, feeling arterial pulse, and limiting strain in the surgeon's hand. This study stresses that the high prevalence of physical complaints directly related to laparoscopic instruments among laparoscopic surgeons is still relevant. Furthermore, the potential benefits of enhanced haptic feedback in laparoscopic surgery are recognized by laparoscopic specialists. Therefore, haptic feedback is considered an unmet need in laparoscopy.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"tissue\", \"hand\"], \"Bacterium\": [], \"BiologicFunction\": [\"arterial pulse\", \"tumor\", \"enlarged lymph node\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"comfort\", \"improve\", \"strain\", \"found\", \"locating\"], \"Food\": [], \"HealthCareActivity\": [\"open surgery\", \"laparoscopy\", \"laparoscopic surgery\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"questionnaire\"], \"MedicalDevice\": [\"laparoscopic instruments\", \"laparoscopic graspers\", \"graspers\", \"laparoscopic grasper\", \"instruments\"], \"Organization\": [], \"PopulationGroup\": [\"subjects\", \"respondents\"], \"ProfessionalOrOccupationalGroup\": [\"laparoscopic specialists\", \"Surgeons\", \"laparoscopic surgeons\", \"surgeon\\u0027s\", \"surgeons\\u0027\"], \"ResearchActivity\": [], \"SpatialConcept\": [\"Europe\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: Earliest replicating and evolving entities are the ribozymes or viroids fulfilling several criteria of life. RNA can perform many aspects of life and influences our gene expression until today. The simplest structures with non-protein-coding information may represent models of life built on structural, not genetic information. Viruses today are obligatory parasites depending on host cells. Examples of how an independent lifestyle might have been lost include mitochondria, chloroplasts, Rickettsia and others, which used to be autonomous bacteria and became intracellular parasites or endosymbionts, thereby losing most of their genes. Even in vitro the loss of genes can be recapitulated all the way from coding to non-coding RNA. Furthermore, the giant viruses may indicate that there is no sharp border between living and non-living entities but an evolutionary continuum. Here, it is discussed how viruses can lose and gain genes, and that they are essential drivers of evolution. This discussion may stimulate the thinking about viruses as early possible forms of life. Apart from our view “viruses first”, there are others such as “proteins first” and “metabolism first.”\n\nText: Mycoplasma mycoides by systematic deletion of individual genes resulted in a synthetic minimal genome of 473 genes (Hutchison et al., 2016) . Can one consider simpler living entities? There are elements with zero genes that fulfill many criteria for early life: ribozymes, catalytic RNAs closely related to viroids. They were recovered in vitro from 10 15 molecules (aptamers), 220 nucleotides in length, by 10 rounds of selection. Among the many RNA species present in this collection of quasispecies RNAs were catalytically active members, enzymatically active ribozymes. The sequence space for 220-mer RNAs is about 3 × 10 132 (Eigen, 1971; Wilson and Szostak, 1999; Brackett and Dieckmann, 2006) . The selected ribozymes were able to replicate, cleave, join, and form peptide bonds. They can polymerize progeny chemically, allow for mutations to occur and can evolve. One molecule serves as catalyst, the other one as substrate. Replication of ribozymes was demonstrated in the test tube (Lincoln and Joyce, 2009) . Ribozymes can form peptide bonds between amino acids (Zhang and Cech, 1997) . Thus, small peptides were available by ribozyme activity. Consequently, an RNA modification has been proposed as peptide nucleic acid (PNA), with more stable peptide bonds instead of phosphodiester bonds (Zhang and Cech, 1997; Joyce, 2002) . Replication of RNA molecules can be performed chemically from RNA without polymerase enzymes. In addition, deoxyribozymes can form from ribonucleotides (Wilson and Szostak, 1999) . Thus, DNA can arise from RNA chemically, without the key protein enzyme, the reverse transcriptase. An entire living world is possible from non-coding RNA (ncRNA) before evolution of the genetic code and protein enzymes. Ribozymes naturally consist of circular single-stranded RNAs (Orgel, 2004) . They lack the genetic triplet code and do not encode proteins. Instead, they exhibit structural information by hairpin-loops that form hydrogen bonds between incomplete double strands, and loops free to interact with other molecules. They represent a quasispecies in which many species of RNA may form, such as ribozymes, tRNA-like molecules, and other ncRNAs. RNAs within such a pool can bind amino acids. Ninety different amino acids have been identified on the Murchison meteorite found in Australia, while on Earth only about 20 of them are used for protein synthesis (Meierhenrich, 2008) . Where formation of ribozymes occurred on the early Earth is a matter of speculation. The hydrothermal vents such as black smokers in the deep ocean are possibilities where life may have started (Martin et al., 2008) . There, temperature gradients and clay containing minerals such as magnesium or manganese are available. Pores or niches offer possibilities for concentration of building blocks, which is required for chemical reactions to occur. Interestingly, also ice is a candidate for ribozyme formation and chemical reactions. Ice crystals displace the biomolecules into the liquid phase, which leads to concentration, creating a quasicellular compartmentalization where de novo synthesis of nucleotide precursors is promoted. There, RNA and ribozymes can emerge, which are capable of self-replication (Attwater et al., 2010) . tRNA-amino acid complexes can find RNAs as \"mRNAs.\" Such interactions could have contributed to the evolution of the genetic code. This sequence of events can lead to primitive ribosome precursors. Ribozymes are the essential catalytic elements in ribosomes: \"The ribosome is a ribozyme\" (Cech, 2000) , supplemented with about a hundred scaffold proteins later during evolution. The proteins have structural functions and contribute indirectly to enzymatic activity. Are these ribosomebound ribozymes fossils from the early Earth? Small peptides can be formed by ribozymes before ribosomes evolved, whereby single or dimeric amino acids may originate from the universe (Meierhenrich, 2008) . Small peptides with basic amino acids can increase the catalytic activity of ribozymes as shown in vitro (Müller et al., 1994) . Such proteins are known as RNA-binding proteins from RNA viruses that protect the RNA genome, with motifs such as RAPRKKG of the nucleocapsid NCp7 of HIV (Schmalzbauer et al., 1996) . Peptides can enhance the catalytic activity of ribozymes up to a 100-fold (Müller et al., 1994) . Such peptides of RNA viruses serve as chaperones that remove higher ordered RNA structures, allowing for more efficient interaction of RNA molecules and increasing transcription rates of RNA polymerases (Müller et al., 1994) . Ribonucleoproteins may have also been functionally important during the evolution of ribosomes (Harish and Caetano-Anolles, 2012) . These pre-ribosomal structures are also similar to precursorlike structures of retroviruses. Reverse transcription can be performed by ribozymes chemically. This action does not necessarily require a protein polymerase such as the reverse transcriptase. Similarly, deoxyribonucleotides can arise by removal of an oxygen without the need of a protein enzyme (a reductase) as today, and allow for DNA polymerization (Wilson and Szostak, 1999; Joyce, 2002) . The same elements of the precursors for ribosomes are also building blocks of retroviruses, which may have a similar evolutionary origin (Moelling, 2012 (Moelling, , 2013 . tRNAs serve as primers for the reverse transcriptase, and the sequence of promoters of transposable elements are derived from tRNAs (Lander et al., 2001) . The ribozymes developed into more complex self-cleaving group II introns with insertion of genes encoding a reverse transcriptase and additional proteins (Moelling and Broecker, 2015; Moelling et al., 2017) (Figure 1) . It came as a surprise that the genomes of almost all species are rich in ncDNA, transcribed into ncRNAs but not encoding proteins, as evidenced, for instance, by the \"Encyclopedia of DNA Elements\" (ENCODE) project. ncDNA amounts to more than 98% of the human DNA genome (Deveson et al., 2017) . Higher organisms tend to have more non-coding information, which allows for more complex modes of gene regulation. The ncRNAs are regulators of the protein-coding sequences. Highly complex organisms such as humans typically have a high number of ncRNA and regulatory mechanisms. ncRNA can range from close to zero in the smallest bacteria such as Pelagibacter ubique to about 98% in the human genome. RNA viruses such as the retrovirus HIV harbor ncRNAs for gene regulation such as the trans-activating response element (TAR), the binding site for the Tat protein for early viral gene expression. Tat has a highly basic domain comprising mostly Lys and Arg residues, resembling other RNA binding proteins. ncRNA also serves on viral RNA genomes as ribosomal entry sites, primer binding sites or packaging signals. DNA synthesis depends on RNA synthesis as initial event, with RNA primers as starters for DNA replication, inside of cells as FIGURE 1 | A compartment is shown with essential components of life as discussed in the text. Non-coding RNA (ncRNA), , can perform many steps for life without protein-coding genes but only by structural information. Individual amino acids are indicated as black dots and may be available on Earth from the universe. DNA may have existed before retroviruses. The compartment can be interpreted as pre-virus or pre-cell. Viroid, green; RNA, red; DNA, black. well as during retroviral replication, proving a requirement of RNA (Flint, 2015) . The number of mammalian protein-coding genes is about 20,000. Surprisingly, this is only a fifth of the number of genes of bread wheat (Appels et al., 2018) . Tulips, maize and other plants also have larger genomes, indicating that the number of genes does not necessarily reflect the complexity of an organism. What makes these plant genomes so large, is still an open question. Could the giant genomes possibly be the result to breeding of plants by farmers or gardeners? According to Szostak there are molecules which appear like relics from the RNA world such as acetyl-CoA or vitamin B12, both of which are bound to a ribonucleotide for no obvious reason -was it \"forgotten\" to be removed? (Roberts and Szostak, 1997; Szostak et al., 2001; Szostak, 2011) . Perhaps the connected RNA serves as structural stabilizer. Lipid vesicles could have formed the first compartments and enclosed ribozymes, tRNAs with selected amino acids, and RNA which became mRNA. Is this a pre-cell or pre-virus (Figure 1) ? Patel et al. (2015) demonstrated that the building blocks of life, ribonucleotides, lipids and amino acids, can be formed from C, H, O, P, N, S in a \"one pot\" synthesis. This study can be regarded as a follow-up study of the classical Urey-Miller in vitro synthesis of biomolecules (Miller, 1953; Miller and Urey, 1959) . Transition from the RNA to the DNA world was promoted by the formation of the reverse transcriptase. The enzyme was first described in retroviruses but it is almost ubiquitous and found in numerous cellular species, many of which with unknown functions (Simon and Zimmerly, 2008; Lescot et al., 2016) . It is an important link between the RNA and the DNA worlds. The name reverse transcriptase is historical and irritating because it is the \"real\" transcriptase during the transition from the RNA to the DNA world. Similarly, the ribonuclease H (RNase H) is an essential enzyme of retroviruses (Mölling et al., 1971) . The RNase H turned out to be one of the five most frequent and ancient proteins (Ma et al., 2008 ) that belongs to a superfamily of more than sixty different unique representatives and 152 families with numerous functions (Majorek et al., 2014) . Some of the many tRNAs can become loaded with amino acids. There are viruses containing tRNA-like structures (TLS), resembling these early RNAs (Dreher, 2009) . The TLS of these viruses typically bind to a single amino acid. TLS-viruses include plant viruses, such as Turnip yellow mosaic virus, in Peanut clump virus, Tobacco mosaic virus (TMV), and Brome mosaic virus. Only half a tRNA is found in Narnaviruses of fungi. The amino acids known to be components of tRNA-like viruses are valine, histidine and tyrosine. The structures were also designated as \"mimicry, \" enhancing translation (Dreher, 2009 (Dreher, , 2010 . They look like \"frozen\" precursor-like elements for protein synthesis. This combination of a partial tRNA linked to one amino acid can be interpreted as an evolutionary early step toward protein synthesis, trapped in a viral element. Ribozymes are related to the protein-free viroids. Viroids are virus-like elements that belong to the virosphere, the world of viruses (Chela-Flores, 1994) . Viroids lack protein coats and therefore were initially not designated as viruses but virus-like viroids when they were discovered in 1971 by Theodor Diener. He described viroids as \"living fossils\" (Diener, 2016) (Figure 2) . From infected potatoes, Diener isolated the Potato spindle tuber viroid (PSTVd) whose genome was about a 100-fold smaller than those of viruses known at that time. The viroids known today are ranging from 246 to 467 nucleotides. They contain circular single-stranded RNA, are protein-free and self-replicating with no genetic information, but only structural FIGURE 2 | Viroids are hairpin-loop structures and are shown schematically and as electron micrograph. Viroids are, like ribozymes, without genetic information and play major biological roles today in plant diseases, in carnation flowers, in liver cancer, as catalyst of protein synthesis in ribosomes and as circular regulatory RNAs, as \"sponges\" for other regulatory RNAs. information in the form of hairpin-loops (Riesner et al., 1979) . They can generate copies of themselves in the appropriate environment. They were designated as the \"frontiers of life\" (Flores et al., 2014) . The knowledge of virus composition was based on TMV and its crystallization by Wendell Stanley in 1935 (Pennazio and Roggero, 2000) . The genome of TMV is protein-coding singlestranded RNA of about 6,400 nucleotides that is enclosed by a rod-like protein coat. Viroids, in contrast, do not encode proteins and lack coats but they are closely related to viruses. Viroids can lose their autonomy and rely on host RNA polymerases to replicate, are capable of infecting plants and many are economically important pathogens. There are two families, the nucleus-replicating Pospiviroidae such as PSTVd and the chloroplast-replicating Avsunviroidae like the Avocado sunblotch viroid (ASBVd). Their replication requires host enzymes.\nQuestion: What were the earliest replicating entities that fulfill several criteria for life?", "role": "user" }, { "content": "ribozymes or viroids", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: While the insect promoters are not effective for mammalian gene expression, appropriate promoters can be cloned into the baculovirus vaccine vectors. Baculovirus vectors have been tested as influenza vaccines, with the first reported vaccine using Autographa californica nuclear polyhedrosis virus (AcNPV) expressing the HA of PR8 under control of the CAG promoter (AcCAG-HA) [77] . Intramuscular, intranasal, intradermal, and intraperitoneal immunization or mice with AcCAG-HA elicited HA-specific antibody responses, however only intranasal immunization provided protection from lethal challenge. Interestingly, intranasal immunization with the wild type AcNPV also resulted in protection from PR8 challenge. The robust innate immune response to the baculovirus provided non-specific protection from subsequent influenza virus infection [78] . While these studies did not demonstrate specific protection, there were antigen-specific immune responses and potential adjuvant effects by the innate response. Baculovirus pseudotype viruses have also been explored. The G protein of vesicular stomatitis virus controlled by the insect polyhedron promoter and the HA of A/Chicken/Hubei/327/2004 (H5N1) HPAIV controlled by a CMV promoter were used to generate the BV-G-HA. Intramuscular immunization of mice or chickens with BV-G-HA elicited strong HI and VN serum antibody responses, IFN-γ responses, and protected from H5N1 challenge [79] . A separate study demonstrated efficacy using a bivalent pseudotyped baculovirus vector [80] . Baculovirus has also been used to generate an inactivated particle vaccine. The HA of A/Indonesia/CDC669/2006(H5N1) was incorporated into a commercial baculovirus vector controlled by the e1 promoter from White Spot Syndrome Virus. The resulting recombinant virus was propagated in insect (Sf9) cells and inactivated as a particle vaccine [81, 82] . Intranasal delivery with cholera toxin B as an adjuvant elicited robust HI titers and protected from lethal challenge [81] . Oral delivery of this encapsulated vaccine induced robust serum HI titers and mucosal IgA titers in mice, and protected from H5N1 HPAIV challenge. More recently, co-formulations of inactivated baculovirus vectors have also been shown to be effective in mice [83] . While there is growing data on the potential use of baculovirus or pseudotyped baculovirus as a vaccine vector, efficacy data in mammalian animal models other than mice is lacking. There is also no data on the safety in humans, reducing enthusiasm for baculovirus as a vaccine vector for influenza at this time. Newcastle disease virus (NDV) is a single-stranded, negative-sense RNA virus that causes disease in poultry. NDV has a number of appealing qualities as a vaccine vector. As an avian virus, there is little or no preexisting immunity to NDV in humans and NDV propagates to high titers in both chicken eggs and cell culture. As a paramyxovirus, there is no DNA phase in the virus lifecycle reducing concerns of integration events, and the levels of gene expression are driven by the proximity to the leader sequence at the 3' end of the viral genome. This gradient of gene expression enables attenuation through rearrangement of the genome, or by insertion of transgenes within the genome. Finally, pathogenicity of NDV is largely determined by features of the fusion protein enabling ready attenuation of the vaccine vector [84] . Reverse genetics, a method that allows NDV to be rescued from plasmids expressing the viral RNA polymerase and nucleocapsid proteins, was first reported in 1999 [85, 86] . This process has enabled manipulation of the NDV genome as well as incorporation of transgenes and the development of NDV vectors. Influenza was the first infectious disease targeted with a recombinant NDV (rNDV) vector. The HA protein of A/WSN/1933 (H1N1) was inserted into the Hitchner B1 vaccine strain. The HA protein was expressed on infected cells and was incorporated into infectious virions. While the virus was attenuated compared to the parental vaccine strain, it induced a robust serum antibody response and protected against homologous influenza virus challenge in a murine model of infection [87] . Subsequently, rNDV was tested as a vaccine vector for HPAIV having varying efficacy against H5 and H7 influenza virus infections in poultry [88] [89] [90] [91] [92] [93] [94] . These vaccines have the added benefit of potentially providing protection against both the influenza virus and NDV infection. NDV has also been explored as a vaccine vector for humans. Two NHP studies assessed the immunogenicity and efficacy of an rNDV expressing the HA or NA of A/Vietnam/1203/2004 (H5N1; VN1203) [95, 96] . Intranasal and intratracheal delivery of the rNDV-HA or rNDV-NA vaccines induced both serum and mucosal antibody responses and protected from HPAIV challenge [95, 96] . NDV has limited clinical data; however, phase I and phase I/II clinical trials have shown that the NDV vector is well-tolerated, even at high doses delivered intravenously [44, 97] . While these results are promising, additional studies are needed to advance NDV as a human vaccine vector for influenza. Parainfluenza virus type 5 (PIV5) is a paramyxovirus vaccine vector being explored for delivery of influenza and other infectious disease vaccine antigens. PIV5 has only recently been described as a vaccine vector [98] . Similar to other RNA viruses, PIV5 has a number of features that make it an attractive vaccine vector. For example, PIV5 has a stable RNA genome and no DNA phase in virus replication cycle reducing concerns of host genome integration or modification. PIV5 can be grown to very high titers in mammalian vaccine cell culture substrates and is not cytopathic allowing for extended culture and harvest of vaccine virus [98, 99] . Like NDV, PIV5 has a 3'-to 5' gradient of gene expression and insertion of transgenes at different locations in the genome can variably attenuate the virus and alter transgene expression [100] . PIV5 has broad tropism, infecting many cell types, tissues, and species without causing clinical disease, although PIV5 has been associated with -kennel cough‖ in dogs [99] . A reverse genetics system for PIV5 was first used to insert the HA gene from A/Udorn/307/72 (H3N2) into the PIV5 genome between the hemagglutinin-neuraminidase (HN) gene and the large (L) polymerase gene. Similar to NDV, the HA was expressed at high levels in infected cells and replicated similarly to the wild type virus, and importantly, was not pathogenic in immunodeficient mice [98] . Additionally, a single intranasal immunization in a murine model of influenza infection was shown to induce neutralizing antibody responses and protect against a virus expressing homologous HA protein [98] . PIV5 has also been explored as a vaccine against HPAIV. Recombinant PIV5 vaccines expressing the HA or NP from VN1203 were tested for efficacy in a murine challenge model. Mice intranasally vaccinated with a single dose of PIV5-H5 vaccine had robust serum and mucosal antibody responses, and were protected from lethal challenge. Notably, although cellular immune responses appeared to contribute to protection, serum antibody was sufficient for protection from challenge [100, 101] . Intramuscular immunization with PIV5-H5 was also shown to be effective at inducing neutralizing antibody responses and protecting against lethal influenza virus challenge [101] . PIV5 expressing the NP protein of HPAIV was also efficacious in the murine immunization and challenge model, where a single intranasal immunization induced robust CD8 + T cell responses and protected against homologous (H5N1) and heterosubtypic (H1N1) virus challenge [102] . Currently there is no clinical safety data for use of PIV5 in humans. However, live PIV5 has been a component of veterinary vaccines for -kennel cough‖ for >30 years, and veterinarians and dog owners are exposed to live PIV5 without reported disease [99] . This combined with preclinical data from a variety of animal models suggests that PIV5 as a vector is likely to be safe in humans. As preexisting immunity is a concern for all virus-vectored vaccines, it should be noted that there is no data on the levels of preexisting immunity to PIV5 in humans. However, a study evaluating the efficacy of a PIV5-H3 vaccine in canines previously vaccinated against PIV5 (kennel cough) showed induction of robust anti-H3 serum antibody responses as well as high serum antibody levels to the PIV5 vaccine, suggesting preexisting immunity to the PIV5 vector may not affect immunogenicity of vaccines even with repeated use [99] . Poxvirus vaccines have a long history and the notable hallmark of being responsible for eradication of smallpox. The termination of the smallpox virus vaccination program has resulted in a large population of poxvirus-naï ve individuals that provides the opportunity for the use of poxviruses as vectors without preexisting immunity concerns [103] . Poxvirus-vectored vaccines were first proposed for use in 1982 with two reports of recombinant vaccinia viruses encoding and expressing functional thymidine kinase gene from herpes virus [104, 105] . Within a year, a vaccinia virus encoding the HA of an H2N2 virus was shown to express a functional HA protein (cleaved in the HA1 and HA2 subunits) and be immunogenic in rabbits and hamsters [106] . Subsequently, all ten of the primary influenza proteins have been expressed in vaccine virus [107] . Early work with intact vaccinia virus vectors raised safety concerns, as there was substantial reactogenicity that hindered recombinant vaccine development [108] . Two vaccinia vectors were developed to address these safety concerns. The modified vaccinia virus Ankara (MVA) strain was attenuated by passage 530 times in chick embryo fibroblasts cultures. The second, New York vaccinia virus (NYVAC) was a plaque-purified clone of the Copenhagen vaccine strain rationally attenuated by deletion of 18 open reading frames [109] [110] [111] . Modified vaccinia virus Ankara (MVA) was developed prior to smallpox eradication to reduce or prevent adverse effects of other smallpox vaccines [109] . Serial tissue culture passage of MVA resulted in loss of 15% of the genome, and established a growth restriction for avian cells. The defects affected late stages in virus assembly in non-avian cells, a feature enabling use of the vector as single-round expression vector in non-permissive hosts. Interestingly, over two decades ago, recombinant MVA expressing the HA and NP of influenza virus was shown to be effective against lethal influenza virus challenge in a murine model [112] . Subsequently, MVA expressing various antigens from seasonal, pandemic (A/California/04/2009, pH1N1), equine (A/Equine/Kentucky/1/81 H3N8), and HPAI (VN1203) viruses have been shown to be efficacious in murine, ferret, NHP, and equine challenge models [113] . MVA vaccines are very effective stimulators of both cellular and humoral immunity. For example, abortive infection provides native expression of the influenza antigens enabling robust antibody responses to native surface viral antigens. Concurrently, the intracellular influenza peptides expressed by the pox vector enter the class I MHC antigen processing and presentation pathway enabling induction of CD8 + T cell antiviral responses. MVA also induces CD4 + T cell responses further contributing to the magnitude of the antigen-specific effector functions [107, [112] [113] [114] [115] . MVA is also a potent activator of early innate immune responses further enhancing adaptive immune responses [116] . Between early smallpox vaccine development and more recent vaccine vector development, MVA has undergone extensive safety testing and shown to be attenuated in severely immunocompromised animals and safe for use in children, adults, elderly, and immunocompromised persons. With extensive pre-clinical data, recombinant MVA vaccines expressing influenza antigens have been tested in clinical trials and been shown to be safe and immunogenic in humans [117] [118] [119] . These results combined with data from other (non-influenza) clinical and pre-clinical studies support MVA as a leading viral-vectored candidate vaccine. The NYVAC vector is a highly attenuated vaccinia virus strain. NYVAC is replication-restricted; however, it grows in chick embryo fibroblasts and Vero cells enabling vaccine-scale production. In non-permissive cells, critical late structural proteins are not produced stopping replication at the immature virion stage [120] . NYVAC is very attenuated and considered safe for use in humans of all ages; however, it predominantly induces a CD4 + T cell response which is different compared to MVA [114] . Both MVA and NYVAC provoke robust humoral responses, and can be delivered mucosally to induce mucosal antibody responses [121] . There has been only limited exploration of NYVAC as a vaccine vector for influenza virus; however, a vaccine expressing the HA from A/chicken/Indonesia/7/2003 (H5N1) was shown to induce potent neutralizing antibody responses and protect against challenge in swine [122] . While there is strong safety and efficacy data for use of NYVAC or MVA-vectored influenza vaccines, preexisting immunity remains a concern. Although the smallpox vaccination campaign has resulted in a population of poxvirus-naï ve people, the initiation of an MVA or NYVAC vaccination program for HIV, influenza or other pathogens will rapidly reduce this susceptible population. While there is significant interest in development of pox-vectored influenza virus vaccines, current influenza vaccination strategies rely upon regular immunization with vaccines matched to circulating strains\nQuestion: What would limit the use of poxvirus vectored vaccines?", "role": "user" }, { "content": "current influenza vaccination strategies rely upon regular immunization with vaccines matched to circulating strains", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: Replication defective rAd5 vaccines expressing influenza HA have also been tested in humans. A rAd5-HA expressing the HA from A/Puerto Rico/8/1934 (H1N1; PR8) was delivered to humans epicutaneously or intranasally and assayed for safety and immunogenicity. The vaccine was well tolerated and induced seroconversion with the intranasal administration had a higher conversion rate and higher geometric meant HI titers [41] . While clinical trials with rAd vectors have overall been successful, demonstrating safety and some level of efficacy, rAd5 as a vector has been negatively overshadowed by two clinical trial failures. The first trial was a gene therapy examination where high-dose intravenous delivery of an Ad vector resulted in the death of an 18-year-old male [42, 43] . The second clinical failure was using an Ad5-vectored HIV vaccine being tested as a part of a Step Study, a phase 2B clinical trial. In this study, individuals were vaccinated with the Ad5 vaccine vector expressing HIV-1 gag, pol, and nef genes. The vaccine induced HIV-specific T cell responses; however, the study was stopped after interim analysis suggested the vaccine did not achieve efficacy and individuals with high preexisting Ad5 antibody titers might have an increased risk of acquiring HIV-1 [44] [45] [46] . Subsequently, the rAd5 vaccine-associated risk was confirmed [47] . While these two instances do not suggest Ad-vector vaccines are unsafe or inefficacious, the umbra cast by the clinical trials notes has affected interest for all adenovirus vaccines, but interest still remains. Immunization with adenovirus vectors induces potent cellular and humoral immune responses that are initiated through toll-like receptor-dependent and independent pathways which induce robust pro-inflammatory cytokine responses. Recombinant Ad vaccines expressing HA antigens from pandemic H1N1 (pH1N1), H5 and H7 highly pathogenic avian influenza (HPAI) virus (HPAIV), and H9 avian influenza viruses have been tested for efficacy in a number of animal models, including chickens, mice, and ferrets, and been shown to be efficacious and provide protection from challenge [48, 49] . Several rAd5 vectors have been explored for delivery of non-HA antigens, influenza nucleoprotein (NP) and matrix 2 (M2) protein [29, [50] [51] [52] . The efficacy of non-HA antigens has led to their inclusion with HA-based vaccines to improve immunogenicity and broaden breadth of both humoral and cellular immunity [53, 54] . However, as both CD8 + T cell and neutralizing antibody responses are generated by the vector and vaccine antigens, immunological memory to these components can reduce efficacy and limit repeated use [48] . One drawback of an Ad5 vector is the potential for preexisting immunity, so alternative adenovirus serotypes have been explored as vectors, particularly non-human and uncommon human serotypes. Non-human adenovirus vectors include those from non-human primates (NHP), dogs, sheep, pigs, cows, birds and others [48, 55] . These vectors can infect a variety of cell types, but are generally attenuated in humans avoiding concerns of preexisting immunity. Swine, NHP and bovine adenoviruses expressing H5 HA antigens have been shown to induce immunity comparable to human rAd5-H5 vaccines [33, 56] . Recombinant, replication-defective adenoviruses from low-prevalence serotypes have also been shown to be efficacious. Low prevalence serotypes such as adenovirus types 3, 7, 11, and 35 can evade anti-Ad5 immune responses while maintaining effective antigen delivery and immunogenicity [48, 57] . Prime-boost strategies, using DNA or protein immunization in conjunction with an adenovirus vaccine booster immunization have also been explored as a means to avoided preexisting immunity [52] . Adeno-associated viruses (AAV) were first explored as gene therapy vectors. Like rAd vectors, rAAV have broad tropism infecting a variety of hosts, tissues, and proliferating and non-proliferating cell types [58] . AAVs had been generally not considered as vaccine vectors because they were widely considered to be poorly immunogenic. A seminal study using AAV-2 to express a HSV-2 glycoprotein showed this virus vaccine vector effectively induced potent CD8 + T cell and serum antibody responses, thereby opening the door to other rAAV vaccine-associated studies [59, 60] . AAV vector systems have a number of engaging properties. The wild type viruses are non-pathogenic and replication incompetent in humans and the recombinant AAV vector systems are even further attenuated [61] . As members of the parvovirus family, AAVs are small non-enveloped viruses that are stable and amenable to long-term storage without a cold chain. While there is limited preexisting immunity, availability of non-human strains as vaccine candidates eliminates these concerns. Modifications to the vector have increased immunogenicity, as well [60] . There are limited studies using AAVs as vaccine vectors for influenza. An AAV expressing an HA antigen was first shown to induce protective in 2001 [62] . Later, a hybrid AAV derived from two non-human primate isolates (AAVrh32.33) was used to express influenza NP and protect against PR8 challenge in mice [63] . Most recently, following the 2009 H1N1 influenza virus pandemic, rAAV vectors were generated expressing the HA, NP and matrix 1 (M1) proteins of A/Mexico/4603/2009 (pH1N1), and in murine immunization and challenge studies, the rAAV-HA and rAAV-NP were shown to be protective; however, mice vaccinated with rAAV-HA + NP + M1 had the most robust protection. Also, mice vaccinated with rAAV-HA + rAAV-NP + rAAV-M1 were also partially protected against heterologous (PR8, H1N1) challenge [63] . Most recently, an AAV vector was used to deliver passive immunity to influenza [64, 65] . In these studies, AAV (AAV8 and AAV9) was used to deliver an antibody transgene encoding a broadly cross-protective anti-influenza monoclonal antibody for in vivo expression. Both intramuscular and intranasal delivery of the AAVs was shown to protect against a number of influenza virus challenges in mice and ferrets, including H1N1 and H5N1 viruses [64, 65] . These studies suggest that rAAV vectors are promising vaccine and immunoprophylaxis vectors. To this point, while approximately 80 phase I, I/II, II, or III rAAV clinical trials are open, completed, or being reviewed, these have focused upon gene transfer studies and so there is as yet limited safety data for use of rAAV as vaccines [66] . Alphaviruses are positive-sense, single-stranded RNA viruses of the Togaviridae family. A variety of alphaviruses have been developed as vaccine vectors, including Semliki Forest virus (SFV), Sindbis (SIN) virus, Venezuelan equine encephalitis (VEE) virus, as well as chimeric viruses incorporating portions of SIN and VEE viruses. The replication defective vaccines or replicons do not encode viral structural proteins, having these portions of the genome replaces with transgenic material. The structural proteins are provided in cell culture production systems. One important feature of the replicon systems is the self-replicating nature of the RNA. Despite the partial viral genome, the RNAs are self-replicating and can express transgenes at very high levels [67] . SIN, SFV, and VEE have all been tested for efficacy as vaccine vectors for influenza virus [68] [69] [70] [71] . A VEE-based replicon system encoding the HA from PR8 was demonstrated to induce potent HA-specific immune response and protected from challenge in a murine model, despite repeated immunization with the vector expressing a control antigen, suggesting preexisting immunity may not be an issue for the replicon vaccine [68] . A separate study developed a VEE replicon system expressing the HA from A/Hong Kong/156/1997 (H5N1) and demonstrated varying efficacy after in ovo vaccination or vaccination of 1-day-old chicks [70] . A recombinant SIN virus was use as a vaccine vector to deliver a CD8 + T cell epitope only. The well-characterized NP epitope was transgenically expressed in the SIN system and shown to be immunogenic in mice, priming a robust CD8 + T cell response and reducing influenza virus titer after challenge [69] . More recently, a VEE replicon system expressing the HA protein of PR8 was shown to protect young adult (8-week-old) and aged (12-month-old) mice from lethal homologous challenge [72] . The VEE replicon systems are particularly appealing as the VEE targets antigen-presenting cells in the lymphatic tissues, priming rapid and robust immune responses [73] . VEE replicon systems can induce robust mucosal immune responses through intranasal or subcutaneous immunization [72] [73] [74] , and subcutaneous immunization with virus-like replicon particles (VRP) expressing HA-induced antigen-specific systemic IgG and fecal IgA antibodies [74] . VRPs derived from VEE virus have been developed as candidate vaccines for cytomegalovirus (CMV). A phase I clinical trial with the CMV VRP showed the vaccine was immunogenic, inducing CMV-neutralizing antibody responses and potent T cell responses. Moreover, the vaccine was well tolerated and considered safe [75] . A separate clinical trial assessed efficacy of repeated immunization with a VRP expressing a tumor antigen. The vaccine was safe and despite high vector-specific immunity after initial immunization, continued to boost transgene-specific immune responses upon boost [76] . While additional clinical data is needed, these reports suggest alphavirus replicon systems or VRPs may be safe and efficacious, even in the face of preexisting immunity. Baculovirus has been extensively used to produce recombinant proteins. Recently, a baculovirus-derived recombinant HA vaccine was approved for human use and was first available for use in the United States for the 2013-2014 influenza season [4] . Baculoviruses have also been explored as vaccine vectors. Baculoviruses have a number of advantages as vaccine vectors. The viruses have been extensively studied for protein expression and for pesticide use and so are readily manipulated. The vectors can accommodate large gene insertions, show limited cytopathic effect in mammalian cells, and have been shown to infect and express genes of interest in a spectrum of mammalian cells [77] . While the insect promoters are not effective for mammalian gene expression, appropriate promoters can be cloned into the baculovirus vaccine vectors. Baculovirus vectors have been tested as influenza vaccines, with the first reported vaccine using Autographa californica nuclear polyhedrosis virus (AcNPV) expressing the HA of PR8 under control of the CAG promoter (AcCAG-HA) [77] . Intramuscular, intranasal, intradermal, and intraperitoneal immunization or mice with AcCAG-HA elicited HA-specific antibody responses, however only intranasal immunization provided protection from lethal challenge. Interestingly, intranasal immunization with the wild type AcNPV also resulted in protection from PR8 challenge. The robust innate immune response to the baculovirus provided non-specific protection from subsequent influenza virus infection [78] . While these studies did not demonstrate specific protection, there were antigen-specific immune responses and potential adjuvant effects by the innate response. Baculovirus pseudotype viruses have also been explored. The G protein of vesicular stomatitis virus controlled by the insect polyhedron promoter and the HA of A/Chicken/Hubei/327/2004 (H5N1) HPAIV controlled by a CMV promoter were used to generate the BV-G-HA. Intramuscular immunization of mice or chickens with BV-G-HA elicited strong HI and VN serum antibody responses, IFN-γ responses, and protected from H5N1 challenge [79] . A separate study demonstrated efficacy using a bivalent pseudotyped baculovirus vector [80] . Baculovirus has also been used to generate an inactivated particle vaccine. The HA of A/Indonesia/CDC669/2006(H5N1) was incorporated into a commercial baculovirus vector controlled by the e1 promoter from White Spot Syndrome Virus. The resulting recombinant virus was propagated in insect (Sf9) cells and inactivated as a particle vaccine [81, 82] . Intranasal delivery with cholera toxin B as an adjuvant elicited robust HI titers and protected from lethal challenge [81] . Oral delivery of this encapsulated vaccine induced robust serum HI titers and mucosal IgA titers in mice, and protected from H5N1 HPAIV challenge. More recently, co-formulations of inactivated baculovirus vectors have also been shown to be effective in mice [83] . While there is growing data on the potential use of baculovirus or pseudotyped baculovirus as a vaccine vector, efficacy data in mammalian animal models other than mice is lacking. There is also no data on the safety in humans, reducing enthusiasm for baculovirus as a vaccine vector for influenza at this time. Newcastle disease virus (NDV) is a single-stranded, negative-sense RNA virus that causes disease in poultry. NDV has a number of appealing qualities as a vaccine vector. As an avian virus, there is little or no preexisting immunity to NDV in humans and NDV propagates to high titers in both chicken eggs and cell culture. As a paramyxovirus, there is no DNA phase in the virus lifecycle reducing concerns of integration events, and the levels of gene expression are driven by the proximity to the leader sequence at the 3' end of the viral genome. This gradient of gene expression enables attenuation through rearrangement of the genome, or by insertion of transgenes within the genome. Finally, pathogenicity of NDV is largely determined by features of the fusion protein enabling ready attenuation of the vaccine vector\nQuestion: What is the appealing quality of the NDV vector?", "role": "user" }, { "content": "pathogenicity of NDV is largely determined by features of the fusion protein enabling ready attenuation of the vaccine vector", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nThe informal settlements of the Global South are the least prepared for the pandemic of COVID-19 since basic needs such as water, toilets, sewers, drainage, waste collection, and secure and adequate housing are already in short supply or non-existent. Further, space constraints, violence, and overcrowding in slums make physical distancing and self-quarantine impractical, and the rapid spread of an infection highly likely. Residents of informal settlements are also economically vulnerable during any COVID-19 responses. Any responses to COVID-19 that do not recognize these realities will further jeopardize the survival of large segments of the urban population globally. Most top-down strategies to arrest an infectious disease will likely ignore the often-robust social groups and knowledge that already exist in many slums. Here, we offer a set of practice and policy suggestions that aim to (1) dampen the spread of COVID-19 based on the latest available science, (2) improve the likelihood of medical care for the urban poor whether or not they get infected, and (3) provide economic, social, and physical improvements and protections to the urban poor, including migrants, slum communities, and their residents, that can improve their long-term well-being. Immediate measures to protect residents of urban informal settlements, the homeless, those living in precarious settlements, and the entire population from COVID-19 include the following: (1) institute informal settlements/slum emergency planning committees in every urban informal settlement; (2) apply an immediate moratorium on evictions; (3) provide an immediate guarantee of payments to the poor; (4) immediately train and deploy community health workers; (5) immediately meet Sphere Humanitarian standards for water, sanitation, and hygiene; (6) provide immediate food assistance; (7) develop and implement a solid waste collection strategy; and (8) implement immediately a plan for mobility and health care. Lessons have been learned from earlier pandemics such as HIV and epidemics such as Ebola. They can be applied here. At the same time, the opportunity exists for public health, public administration, international aid, NGOs, and community groups to innovate beyond disaster response and move toward long-term plans.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nMedium chain triglyceride oil consumption as part of a weight loss diet does not lead to an adverse metabolic profile when compared to olive oil . OBJECTIVE Medium chain triglyceride ( MCT ) consumption may have a beneficial impact on weight management , however , some studies point to a negative impact of MCT oil consumption on cardiovascular disease risk . This study examined the effects of MCT oil consumption , as part of a weight loss diet , on metabolic risk profile compared to olive oil . DESIGN Thirty-one men and women , age 19-50 y and body mass index 27-33 kg/m ( 2 ) , completed this randomized , controlled , 16-week weight loss program . Oils were consumed at a level of approximately 12 % of the subjects ' prescribed energy intakes in the form of muffins and liquid oil . RESULTS After controlling for body weight , there was a significant effect of time on fasting serum glucose ( P = 0.0177 ) and total cholesterol ( P = 0.0386 ) concentrations , and on diastolic blood pressure ( P = 0.0413 ) , with reductions in these variables occurring over time ; there was no time-by-diet interaction for any of the parameters studied . Two of the 3 subjects in the MCT oil group with evidence of the metabolic syndrome at baseline did not have metabolic syndrome at endpoint . In the olive oil group , 6 subjects had the metabolic syndrome at baseline ; 2 subjects no longer had metabolic syndrome at endpoint , 1 person developed metabolic syndrome , and 4 subjects did not have any change in their metabolic syndrome status . CONCLUSIONS Our results suggest that MCT oil can be incorporated into a weight loss program without fear of adversely affecting metabolic risk factors . Distinction should be made regarding chain length when it comes to discussing the effects of saturated fats on metabolic risk factors .", "role": "user" }, { "content": "{\"Intervention\": [\"liquid oil\", \"MCT oil\", \"Medium chain triglyceride oil\", \"MCT oil consumption\", \"Medium chain triglyceride ( MCT )\", \"olive oil\"], \"Outcome\": [\"fasting serum glucose\", \"total cholesterol\", \"diastolic blood pressure\"], \"Participant\": [\"MCT oil\", \"Thirty-one\", \"body mass index 27-33 kg/m ( 2 )\", \"age 19-50 y\", \"metabolic syndrome\", \"men and women\"]}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Assembly, maturation and three-dimensional helical structure of the teratogenic rubella virus\nArticle:\nAbstract:\nViral infections during pregnancy are a significant cause of infant morbidity and mortality. Of these, rubella virus infection is a well-substantiated example that leads to miscarriages or severe fetal defects. However, structural information about the rubella virus has been lacking due to the pleomorphic nature of the virions. Here we report a helical structure of rubella virions using cryo-electron tomography. Sub-tomogram averaging of the surface spikes established the relative positions of the viral glycoproteins, which differed from the earlier icosahedral models of the virus. Tomographic analyses of in vitro assembled nucleocapsids and virions provide a template for viral assembly. Comparisons of immature and mature virions show large rearrangements in the glycoproteins that may be essential for forming the infectious virions. These results present the first known example of a helical membrane-enveloped virus, while also providing a structural basis for its assembly and maturation pathway.\nIntroduction:\nRubella virus is an airborne human pathogen that causes a contagious disease with measles-like symptoms in children and adults. Rubella infection in pregnant women can lead to fetal death or severe life-long disabilities such as mental retardation, deafness, cataracts and heart defects in the new-born infants, collectively referred to as congenital rubella syndrome[1]. Despite the availability of an effective vaccine for rubella since the 1960s, the virus is still a global health concern with over 100, 000 babies born with congenital rubella syndrome every year[2]. Rubella virus is an enveloped, positive-stranded RNA virus with virions ranging from 500 Å to 900 Å in diameter[3]. The virions form a variety of shapes that range from nearly spherical to elongated tube-like structures[3, 4]. The structural components of rubella virus are comprised of three proteins, glycoproteins E1( 58kDa), E2( 42–47kDa), and the capsid protein( 31kDa)[5, 6]. The glycoproteins are type I transmembrane proteins[5, 7] that form heterodimers on the virion surface[8]. E1 is responsible for recognition and attachment to cellular receptors[9]. It is also involved in membrane fusion in the presence of low pH and calcium ions[10–12]. E2 is required for efficient folding and transportation of E1 through cellular compartments[7, 8]. Of the two glycoproteins, only the structure of the E1 ectodomain in its trimeric, post-fusion conformation is known[13]. The rubella E1 ectodomain has an elongated structure, similar to the post-fusion conformations of the alphavirus E1 and flavivirus E glycoproteins[13]. The E1 ectodomain has three domains DI, DII and DIII. DII contains two conserved hydrophobic fusion loops at one end of the rubella E1 structure, whereas DI and DIII form the other end[13]. The third structural protein of rubella virus is the capsid protein, which interacts via its amino-terminal domain with the viral RNA genome to form the inner nucleocapsid[6, 14]. The capsid protein exists as a homodimer[8] and is attached to the viral membrane through the E2 signal peptide[15]. The atomic structure of the carboxy-terminal domain of the capsid protein is known[16] and presumably forms the structural framework of the viral nucleocapsid. The rubella virus structural proteins assemble on and bud from Golgi membranes[1, 4, 17] in host cells. The newly budded virions form uniformly dense particles within the Golgi and are referred to as ‘immature’ virions[18]. These immature virions undergo structural reorganization during their passage through the Golgi complex to form mature virions that have a double shell-like architecture. The mature virions are then secreted into the extracellular environment[3, 16, 18]. Based on their similar genome organizations, rubella virus and alphaviruses are classified as the only members of the Togavirus family[1, 19, 20]. However, these two groups of viruses have little sequence similarity[21] and differ in their assembly as well as maturation strategies[1, 18]. The alphaviruses include well-known viruses such as Chikungunya virus, Sindbis virus and Semliki Forest virus. They have been studied extensively and their structure determinations have been facilitated by the icosahedral nature of the virions[22–24]. Structural studies have helped in characterizing alphaviruses when complexed with neutralizing antibodies[25–30] and antiviral compounds[31–33]. However, structural information on rubella virus has been minimal owing to the pleomorphic nature of the virus. In this report, we have used a combination of cryo-electron tomography, sub-tomogram averaging and in vitro assembly studies to elucidate the three-dimensional structure and assembly of rubella virions. We have further taken advantage of the direct detector technology to achieve close to nanometer resolution for the sub-tomogram average of the asymmetric and relatively small rubella virus glycoprotein spikes( ~100kDa molecular weight). Additionally, we have isolated immature rubella virions that give insights into the different maturation states of rubella virus. Collectively, these analyses suggest a distinctive assembly and maturation pathway for rubella virus that might be critical for the teratogenic pathogenicity of this medically significant virus.\nDiscussion:\nThe rubella virus structure had been expected to have T = 3, icosahedral symmetry[1, 8, 41]. Instead, the structure of rubella virus, as shown here, has an irregular helical organization of its surface glycoproteins and a pseudo-tetrameric inner nucleocapsid arrangement. The glycoprotein arrangement in rubella virions is unique, as other known membrane enveloped viruses exhibit helical structures only in their inner nucleoprotein complex or in their matrix protein layer, such as in paramyxoviruses[42], marburgviruses[43], and influenza-A viruses[44]. Thus, rubella virus is the only known example of a helical surface structure associated with a membrane enveloped virus. The relative positions of the rubella glycoproteins, with an extended E1 conformation and with E2 at the base of the spike complex, is different from the glycoprotein heterodimer conformation observed in alphaviruses. However, this structural placement of rubella glycoproteins is consistent with protease studies[10, 45] and immunological reactivity studies on rubella virus[46, 47], which indicate that the E1 molecule is more exposed and accessible than E2 on the virion’s surface. E1 is the primary target for neutralizing antibodies against rubella virus. The common antibody binding region on E1( between residues 202 to 285)[48–52] is exposed to the surrounding environment in the spike density, given the orientation of E1 as determined by the fitting results. Though the E1 crystal structure used in this study is similar to the post-fusion E1 and E glycoprotein structures of alpha- and flaviviruses, the rubella E1 structure was determined under neutral pH and in the absence of detergents[13], unlike in the case of the post-fusion structures of alphavirus E1[53] and flavivirus E glycoproteins[54]. Moreover, the translation of domain III between the pre- and post-fusion conformations in alpha- and flaviviruses, is possibly a consequence of the large conformational change of the glycoproteins from being tangential to being almost perpendicular to the viral membrane. Under these considerations, the proposed movement of domain III in alpha- and flaviviruses might not be directly applicable to rubella virus. Even with a possible translational movement of domain III, the position of the volume assigned to rubella E2 would not change significantly. Furthermore, expression of rubella E1 and E2 ectodomains together results in secretion of the E1 ectodomain alone[13], indicating that the E2 ectodomain has a higher affinity to membranes than E1. Thus, these observations are consistent with the placement of E2 close to the base of the rubella glycoprotein spike, rendering it relatively inaccessible compared to E1. The molecular weight of rubella virus E2 is only about one half of E2 in alphaviruses. There is also no significant sequence similarity between the E2 proteins of rubella and alphaviruses. Hence, the structure of E2 in these viruses is probably quite different. In alphaviruses, the glycoprotein E1-E2 heterodimers lie close to the membrane surface in their pre-fusion state with the E1 fusion loop physically masked by the neighboring E2 molecule. In the rubella glycoprotein complex, the E1 protein extends out from the virion surface and does not appear to require E2 for shielding its two fusion loops. The rubella virus E1 crystal structure[13], which was determined in the absence of detergent and at neutral pH, also presents an extended E1 conformation with fusion loops exposed but not positioned for membrane insertion. The observed variability in the glycoprotein spikes suggest that the tips of the E1 structures are flexible, which would help E1 to avoid non-productive membrane interactions at neutral pH. This might also help explain the requirement for calcium ions to stabilize the rubella E1 fusion loop conformations for membrane insertion at low pH[12, 13]. Difference in the glycoprotein spike orientations between the immature and mature virion forms could also be to protect the fusion loops on the E1 glycoprotein structure from undergoing unproductive membrane interactions in the low pH environment of the cellular Golgi network. Subsequent virion maturation in the Golgi complex would then be necessary for reorganization of the viral envelope to yield fusion competent, extracellular, ‘spiky’ mature virus particles. A similar strategy of surface glycoprotein reorganization during virion maturation occurs also in bunyaviruses[55] and flaviviruses[56]. In addition to the glycoprotein arrangement, the association of protein tetramers to form enclosed shells as seen in the rubella virus nucleocapsids is also unusual and not observed in other known virus structures. Rubella capsid protein molecules expressed in bacterial cells, spontaneously form nucleocapsid cores in the presence of cellular nucleic acids. This indicates that the rubella capsid protein does not need the rubella genome for nucleocapsid formation, similar to previous observations[57], but can associate with random nucleic acids to form nucleocapsids. In the context of virus assembly, this implies that the binding of the capsid protein to the viral RNA is not entirely sequence specific. This suggests that the virus machinery uses other methods, such as an abundance of viral RNA relative to cellular RNA at the virus budding site[58], for efficient packaging of the viral genome into budding virions. Thus, rubella virus appears to share certain common characteristics, not only with alphaviruses but also with other arbovirus genera, such as flaviviruses and bunyaviruses. However, in addition to these features that suggest similarities to arboviruses, rubella virus has also evolved some unique traits such as an exposed E1 fusion loop conformation. Together, these observations point to a more complex structural evolution in rubella virus than previously assumed.", "role": "user" }, { "content": "Rubella virus ( RV ) causes serious fetal defects when contracted during pregnancy . Despite its medical importance , due to the irregular shapes and different sizes of the virions , the RV structure has remained unknown . Using cryo-electron tomography , we have determined the RV structure , which shows a unique , helical outer surface . Subsequent local averaging of the RV surface spikes has established the conformations of its immunogenic glycoproteins . In vitro assembly studies on the virus capsid protein have provided insights into the interactions necessary for virus assembly . Comparisons between mature and immature RV show large conformational changes in the virion structure that are essential for virus maturation . These results help to gain a structural understanding of RV pathogenicity , which may also be relevant to other teratogenic viruses .", "role": "assistant" } ]

[ { "content": "Based on the abstract below, determine if the claim is supported or contradicted. Output a JSON object with the verdict (\"SUPPORT\" or \"CONTRADICT\") and evidence sentences from the abstract.\n\nClaim: The mouse brain vasculature shows a distinct expression pattern of sars-cov-2 entry factors\n\nText:\nA large number of hospitalized COVID-19 patients show neurological symptoms such as ischemic-and hemorrhagic stroke as well as encephalitis, and SARS-CoV-2 can directly infect endothelial cells leading to endotheliitis across multiple vascular beds.\nThese findings suggest an involvement of the brain-and peripheral vasculature in COVID-19, but the underlying molecular mechanisms remain obscure.\nTo understand the potential mechanisms underlying SARS-CoV-2 tropism for brain vasculature, we constructed a molecular atlas of the expression patterns of SARS-CoV-2 viral entry-associated genes (receptors and proteases) and SARS-CoV-2 interaction partners in human (and mouse) adult and fetal brain as well as in multiple non-CNS tissues in single-cell RNA-sequencing data across various datasets.\nWe observed a distinct expression pattern of the cathepsins B (CTSB) and-L (CTSL)-which are able to substitute for the ACE2 co-receptor TMPRSS2-in the human vasculature with CTSB being mainly expressed in the brain vasculature and CTSL predominantly in the peripheral vasculature, and these observations were confirmed at the protein level in the Human Protein Atlas and using immunofluorescence stainings.\nThis expression pattern of SARS-CoV-2 viral-entry associated proteases and SARS-CoV-2 interaction partners was also present in endothelial cells and microglia in the fetal brain, suggesting a developmentally established SARS-CoV-2 entry machinery in the human vasculature.\nAt both the adult and fetal stages, we detected a distinct pattern of SARS-CoV-2 entry associated genes’ transcripts in brain vascular endothelial cells and microglia, providing a potential explanation for an inflammatory response in the brain endothelium upon SARS-CoV-2 infection.\nMoreover, CTSB was co-expressed in adult and fetal brain endothelial cells with genes and pathways involved in innate immunity and inflammation, angiogenesis, blood-brain-barrier permeability, vascular metabolism, and coagulation, providing a potential explanation for the role of brain endothelial cells in clinically observed (neuro)vascular symptoms in COVID-19 patients.\nOur study serves as a publicly available single-cell atlas of SARS-CoV-2 related entry factors and interaction partners in human and mouse brain endothelial-and perivascular cells, which can be employed for future studies in clinical samples of COVID-19 patients.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"We observed a distinct expression pattern of the cathepsins B (CTSB) and-L (CTSL)-which are able to substitute for the ACE2 co-receptor TMPRSS2-in the human vasculature with CTSB being mainly expressed in the brain vasculature and CTSL predominantly in the peripheral vasculature, and these observations were confirmed at the protein level in the Human Protein Atlas and using immunofluorescence stainings.\", \"This expression pattern of SARS-CoV-2 viral-entry associated proteases and SARS-CoV-2 interaction partners was also present in endothelial cells and microglia in the fetal brain, suggesting a developmentally established SARS-CoV-2 entry machinery in the human vasculature.\", \"Our study serves as a publicly available single-cell atlas of SARS-CoV-2 related entry factors and interaction partners in human and mouse brain endothelial-and perivascular cells, which can be employed for future studies in clinical samples of COVID-19 patients.\"]}", "role": "assistant" } ]

[ { "content": "Given an abstract from a computer science paper, extract all relationships between entities. Only use these relationship types:\n\n- \"USED-FOR\"\n- \"EVALUATE-FOR\" \n- \"FEATURE-OF\"\n- \"HYPONYM-OF\"\n- \"PART-OF\"\n- \"COMPARE\"\n- \"CONJUNCTION\"\n\nOutput your answer as a JSON array where each entry is [\"<Entity_A>\", \"<Entity_B>\", \"<RELATION_A_B>\"].\n\nAbstract:\n\nIn our current research into the design of cognitively well-motivated interfaces relying primarily on the display of graphical information, we have observed that graphical information alone does not provide sufficient support to users-particularly when situations arise that do not simply conform to the users ' expectations. This can occur due to too much information being requested, too little, information of the wrong kind, etc.. To solve this problem, we are working towards the integration of natural language generation to augment the interaction", "role": "user" }, { "content": "[[\"natural language generation\", \"interaction\", \"USED-FOR\"], [\"display of graphical information\", \"cognitively well-motivated interfaces\", \"USED-FOR\"]]", "role": "assistant" } ]

[ { "content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Clickhereforadditionaldatafile.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nINTRODUCTION: In recent years, computational polypharmacology has gained significant attention to study the promiscuous nature of drugs. Despite tremendous challenges, community-wide efforts have led to a variety of novel approaches for predicting drug polypharmacology. In particular, some rapid advances using machine learning and artificial intelligence have been reported with great success. AREAS COVERED: In this article, the authors provide a comprehensive update on the current state-of-the-art polypharmacology approaches and their applications, focusing on those reports published after our 2017 review article. The authors particularly discuss some novel, groundbreaking concepts, and methods that have been developed recently and applied to drug polypharmacology studies. EXPERT OPINION: Polypharmacology is evolving and novel concepts are being introduced to counter the current challenges in the field. However, major hurdles remain including incompleteness of high-quality experimental data, lack of in vitro and in vivo assays to characterize multi-targeting agents, shortage of robust computational methods, and challenges to identify the best target combinations and design effective multi-targeting agents. Fortunately, numerous national/international efforts including multi-omics and artificial intelligence initiatives as well as most recent collaborations on addressing the COVID-19 pandemic have shown significant promise to propel the field of polypharmacology forward.", "role": "user" }, { "content": "[\"Treatment\"]", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nPatients are avoiding hospitals for fear of contracting severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2). We are witnessing a re-emergence of rare complications of myocardial infarctions (MI) due to delayed revascularization. Herein, we describe a case of hemorrhagic pericarditis from thrombolytics administered to a patient with late presenting MI. (Level of Difficulty: Beginner.).", "role": "user" }, { "content": "[\"Case Report\"]", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: The Wireless Control Plane: An Overview and Directions for Future Research \nChapter Title: Securing the WCP control \n1. Abstract of Cited Paper (BIB001): Intelligent jamming (IJ) attacks go beyond applying brute-force power at the physical link, exploiting vulnerabilities specific to protocols or configurations. IJ attackers who can gain a foothold into a network by understanding and exploiting vulnerabilities can operate with a much lower chance of detection and a greater impact on the network. For example, one IJ technique exploits media access control (MAC) layer packet structure to selectively jam packets originating from or destined to a specific user. This project aims to create a moving target in the network protocol stack to mitigate IJ attacks. It introduces protocol agility at all layers of the stack to make such protocol-driven attacks infeasible. \n2. Abstract of Cited Paper (BIB002): The rapidly diversified market demands have presented a huge challenge to the conventional mobile broadband network architecture. On one hand, the limited machine room space and insufficient power supply make it impossible to accommodate exponentially growing amount of network equipment of operators. On the other hand, net heterogeneity caused by different specifications of wireless access equipment causes costly trouble related to management and optimization. This article, correspondingly, proposes a holistic solution involving different technologies, i.e. network function virtualization (NFV), software defined radio (SDR), and software defined network (SDN). In particular, we investigate both existing standards and possible extensions for 4G/5G mobile networks, followed by a few open issues for future research. \n3. Abstract of Cited Paper (BIB003): There has been increasing interest in adopting BlockChain (BC), that underpins the crypto-currency Bitcoin, in Internet of Things (IoT) for security and privacy. However, BCs are computationally expensive and involve high bandwidth overhead and delays, which are not suitable for most IoT devices. This paper proposes a lightweight BC-based architecture for IoT that virtually eliminates the overheads of classic BC, while maintaining most of its security and privacy benefits. IoT devices benefit from a private immutable ledger, that acts similar to BC but is managed centrally, to optimize energy consumption. High resource devices create an overlay network to implement a publicly accessible distributed BC that ensures end-to-end security and privacy. The proposed architecture uses distributed trust to reduce the block validation processing time. We explore our approach in a smart home setting as a representative case study for broader IoT applications. Qualitative evaluation of the architecture under common threat models highlights its effectiveness in providing security and privacy for IoT applications. Simulations demonstrate that our method decreases packet and processing overhead significantly compared to the BC implementation used in Bitcoin. \n4. Abstract of Cited Paper (BIB004): A smart city is a connected system in which things produce a huge quantity of data. We focused the attention on monitoring the environment quality in urban area by means of a distributed network of small mobile sensors that are devices on the Internet of Things (IoT). Sensors produce digital measurements, useful for investigating and studying the life quality in every part of the city. In our vision, environmental data must be available by everyone and shared with citizens, but it must be unmodifiable. We propose to solve the problem of the sensors data storage and management using a disruptive technology called blockchain. The blockchain responds to the demand of availability and unchangeability and, thanks to the potentiality of smart contracts, makes us able to manage sensor information and implement a control logic. In order to develop the software based on blockchain we chose to apply the SCRUM methodology because of its capabilities of being a flexible, adaptive and iterative methodology. \n5. Abstract of Cited Paper (BIB005): Localization performance in wireless networks has been traditionally benchmarked using the Cramer-Rao lower bound (CRLB), given a fixed geometry of anchor nodes and a target. However, by endowing the target and anchor locations with distributions, this paper recasts this traditional, scalar benchmark as a random variable. The goal of this work is to derive an analytical expression for the distribution of this now random CRLB, in the context of Time-of-Arrival-based positioning. ::: To derive this distribution, this work first analyzes how the CRLB is affected by the order statistics of the angles between consecutive participating anchors (i.e., internodal angles). This analysis reveals an intimate connection between the second largest internodal angle and the CRLB, which leads to an accurate approximation of the CRLB. Using this approximation, a closed-form expression for the distribution of the CRLB, conditioned on the number of participating anchors, is obtained. ::: Next, this conditioning is eliminated to derive an analytical expression for the marginal CRLB distribution. Since this marginal distribution accounts for all target and anchor positions, across all numbers of participating anchors, it therefore statistically characterizes localization error throughout an entire wireless network. This paper concludes with a comprehensive analysis of this new network-wide-CRLB paradigm.\n\nLiterature Review:", "role": "user" }, { "content": "Challenge: The WCP system has three major critical design issues: 1. Sensitive control information is prone to attack due to the distributed processing for control events among the distributed controllers. 2. The entire operation relies on susceptible software-based models. 3. Sensitive control information is broadcast over a vulnerable wireless channel. All of these design aspects raise the chances of attacking the WCP, e.g., denial of service (DoS), distributed denial of service (DDoS), and software jamming . Potential approach: Since the WCP is prone to a diverse range of malicious activities, an intelligent technique is required to tackle this challenge. Although the vulnerabilities of distributed processing, software, and wireless channels threaten the WCP, they could be clues for developing a robust security scheme for the WCP, owing to BlockChain (BC) BIB004 technology, and the moving target defense (MTD) BIB002 . The former could utilize the distributed entities (controllers) as trustworthy distributed ledgers to verify the integrity of the exchanged information among distributed controllers. It involves two powerful techniques: proof of work (POW) by miners (distributed entities) to attain the security requirements and chain of cryptographic blocks to guarantee the integrity of the exchanged information. It can be simply defined as a linked list (chain) data structure, where each element in the list is a cryptographic block. Each block in the chain has patches of an encrypted valid process (transaction) in addition to an encoded hash of the previous block in the chain. Thus, a chain of blocks is constructed in an iterative manner. The blockchain could also be seen as a distributed database shared among all distributed participants. Thus, an attacker needs to attack all nodes in the chain to collude against the network. In the latter, MTD provides a range of uncertainties in system configurations to complicate the system for attackers. The WCP's programmability features endow a myriad of system configurations because it deploys SDR and SDN to represent all layers of the protocol stack. MTD leverages this ability to randomly alter their configuration. To exemplify, recall the security API in the D-WCP architecture, which is shown in Figure 6 . The diversity in the PBS and the wireless controller's SDR interface configurations would be achieved by incorporating MTD and the adaptive modulation and coding (AMC) information base (AMCIB) into the PBS's security layer and wireless controller's security API, respectively. The AMCIB provides a diverse range of radio parameters that would be utilized by MTD to reconfigure the modulation and coding schemes of the radio signals. These MTD-based radio reconfigurations would secure the radio signal that will be transmitted over the wireless link as well as the PBS. The diversity in the SDN controller system configurations would be achieved by incorporating a virtualization layer with the control logic layer to virtualize the controller's resources, and hence, a diverse range of the controller system configurations would be available for the MTD-based security agent. Thus, the controller's MTD-based security agent would provide a twodimensional controller and radio configuration security scheme. Nevertheless, both BC and MTD have inherent limitations regarding their need for high processing power to process their algorithms. Thus, a smart algorithmic approach is still needed to address this challenge BIB005 for the WCP design. 5.3. How would SDN and SDR be synergistic for 5G and Beyond? Challenge: To provide a robust programmable framework for the WCP, SDN and SDR should cooperate harmonically. In fact, we are still far from this harmonic inter-operation of SDN with SDR because there is still the challenge of how the SDN controller directly programs the SDR-based PBS rather than only controlling its behavior Ramirez-Perez and Ramos (2016). Although they share the concept of abstracting hardware components and representing their functionalities with flexible software, the differential nature of the data that each software paradigm needs to process limits the achievement of real harmonization between the SDR and SDN. To illustrate, SDR software manipulates data, which are stochastic signals that are handled over stochastic systems (wireless channels) that mandate running sophisticated signal processing functions, such as fast Fourier transform (FFT). On the other hand, SDN software manipulates deterministic data that might have certain stochastic properties (e.g., control packets that have stochastic arrival times). Therefore, the challenge is how to converge these two software paradigms, which have to manipulate data with different characteristics. In other words, the challenge is how to achieve a robust convergence between Pyretic and GNU radio. Potential approach: Although there are noticeable efforts to integrate SDN with SDR for 5G and beyond, such as Ramirez-Perez and Ramos (2016); BIB003 , they have tackled the problem from only the reconfiguration and virtualization perspectives Ramirez-Perez and Ramos (2016) BIB001 . In the proposed D-WCP architecture, the wireless controller could achieve this convergence through its softradio API, as shown in Figure 6 . It is envisaged that the softradio API could work as a shared module between two different software models (GNU radio and SDN control logic). To exemplify, consider the deployment of shared memory to manage the operation between two different software, such as ns3 and Matlab BIB006 . However, this analogy is partially correct because the integration process is still carried out on software that handles deterministic data. Thus, the softradio API could not only be a shared memory between two software paradigms but also could be a powerful interface that computationally models the stochasticity of signals and reforms it, using very fast algorithms, to data shapes that can be manipulated by Pyretic or any developed language that could address the challenge of integrating the programmability of SDN with SDR within a unified development platform.", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Cooperative recurrent modular neural networks for constrained optimization: a survey of models and applications \nChapter Title: Neural network approaches \n1. Abstract of Cited Paper (BIB001): The neural method is a powerful nonlinear adaptive approach in various signal-processing scenarios. It is especially suitable for real-time application and hardware implementation. In this paper, we review its application in antenna array signal processing. This paper also serves as a tutorial to the neural method for antenna array signal processing. \n2. Abstract of Cited Paper (BIB002): Since the pioneering work of Amari and Oja, principal component neural networks and their extensions have become an active adaptive signal processing research field. One of such extensions is minor component analysis (MCA), that proves to be effective in tasks such as robust curve/surface fitting and noise reduction. The aims of the paper are to give a detailed and homogeneous review of one-unit first minor/principal component analysis and to propose an application to robust constrained beamforming. In particular, after a careful presentation of first/minor component analysis algorithms based on a single adaptive neuron, along with relevant convergence/steady-state theorems, it is shown how the adaptive robust constrained beamforming theory by Cox et al. may be advantageously recast into an MCA setting. Experimental results obtained with a triangular array of microphones introduced in a teleconference context help to assess the usefulness of the proposed theory. \n3. Abstract of Cited Paper (BIB003): Calculating an optimal beamforming weight is a main task of beamforming. Quadratic constraints on the weight vector of an adaptive linearly constrained minimum power (LCMP) beamformer can improve robustness to pointing errors and to random perturbations in sensor parameters. This paper presents a neural network approach to the robust LCMP beamformer with the quadratic constraint. Compared with the existing neural networks for the LCMP beamformer, the proposed neural network converges fast to an optimal weight. Compared with the existing adaptive algorithms for the robust LCMP beamformer, in addition to parallel implementation, the proposed neural network is guaranteed to converge exponentially to an optimal weight. Simulations demonstrate that the proposed neural network has better interference suppression and faster convergence than the existing neural networks and the adaptive algorithms.\n\nLiterature Review:", "role": "user" }, { "content": "Neural network approaches have been successfully applied to real-time beamforming BIB002 . Since the robust LCMP problem (70) is a complex valued one, it is first necessary to convert it into a real valued optimization Then (70) can be equivalent to the following optimization problem in terms of real valued vectors where T denotes transpose, x ¼ ½w There exist mainly three types of neural networks for the LCMP beamforming: the Hopfield neural network BIB001 , the RBF neural network , and the minor component (MC) neural network BIB003 . While the Hopfield neural network may be regarded as a special case of the Kennedy-Chua neural network . When applied to the robust LCMP beamforming problem (1), the Kennedy-Chua neural network can be represented as where k s [ 0 is a penalty parameter. The Kennedy-Chua network has a smaller network size, but the KennedyChua network converges to an approximate optimal solution of (3) due to the penalty parameter. The MC neural network can implement the beamformer with a quadratic constraint, but it has a slower convergence rate. Moreover, when implementing linear constraints, the computational complexity of the MC neural network will be added greatly. Recently, a cooperative recurrent neural network algorithm for real-time robust beamforming is developed in BIB004 where a [ 0 is a design parameter, x I ðtÞ; x II ðtÞ 2 R n ; xðtÞ ¼ ½x I ðtÞ; x II ðtÞ T 2 R 2n ; gðtÞ 2 R; qðtÞ 2 R 2m ; zðtÞ ¼ ½xðtÞ; gðtÞ; qðtÞ T 2 R 2ðnþmÞþ1 is a state vector, and u(t) is the output of the beamformer. We compare the CRNN (73) with the RLS-VL algorithm. It is easy to see that the CRNN algorithm requires 4n 2 + 8mn + 5n + m + 1 multiplications per iteration. For the RLS-VL algorithm, the RLS updating step requires 8n 2 + 8n + 1 multiplications per iteration and the variable loading step requires 4n 2 + 8n + 5 multiplications with one square operation per iteration. In addition, the weight w need to be decomposed into two components as follows where B is an n 9 (n-m) matrix which is obtained by solving the matrix equation C H B ¼ 0: Therefore, the CRNN algorithm (73) has a lower computational complexity than the RLS-VL algorithm. Moreover, it was shown in BIB004 that the CRNN algorithm (73) can converge exponentially to the optimal beamforming weight. Figure 15 shows the block diagram of the CRNN algorithm (73) for the robust LCMP beamforming. Example Consider a ten-sensor uniform linear array to receive three uncorrelated, narrow-band signals corrupted by an additive white noise in a stationary environment. A desired signal with signal to noise ratio (SNR) 10 dB impinges on the array from / 0 = -0.03p. Two interferences with interference to noise ratio (INR) 20 dB are located at / 1 = 0.29p and / 2 = 0.43p, respectively. Our simulation results are averaged over 200 independent trials. To compute the covariance matrix of yðtÞ we use the following average estimate where N = 1500 is a sample number. In addition, C is taken as the steering vector associated with the look direction. We compared the CRNN algorithm with the KennedyChua neural network (KCNN) algorithm, the minor component neural network (MCNN) algorithm, and the RLS-VL algorithm. First, let the penalty parameter k s be 20 in the KCNN algorithm, and let the initial diagonal loading and the forgetting factor be 0.1 and 0.9999, respectively in the RLS-VL algorithm. Figure 16 (a) displays the performance comparisons of array beam patterns using the CRNN, the MCNN, and the KCNN algorithm. Figure 16 (b) displays the performance comparisons of array beam patterns using the CRNN and the RLS-VL algorithm, where the initial estimation of the weigh vector is zero. It can be seen that the CRNN approach is able to maintain the mainlobe and null the interferers correctly, in contrast to the other three methods. Next, in order to illustrate the convergence rate, we compared the weight norm of the beamformer among four algorithms. The simulation results listed in Table 2 show that the CRNN algorithm has a faster convergence and a smaller weight norm than the other four algorithms.", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Comprehensive Survey of Neighborhood-based Recommendation Methods \nChapter Title: Correlation-based similarity \n1. Abstract of Cited Paper (BIB001): We present a framework for adaptive news access, based on machine learning techniques specifically designed for this task. First, we focus on the system's general functionality and system architecture. We then describe the interface and design of two deployed news agents that are part of the described architecture. While the first agent provides personalized news through a web-based interface, the second system is geared towards wireless information devices such as PDAs (personal digital assistants) and cell phones. Based on implicit and explicit user feedback, our agents use a machine learning algorithm to induce individual user models. Motivated by general shortcomings of other user modeling systems for Information Retrieval applications, as well as the specific requirements of news classification, we propose the induction of hybrid user models that consist of separate models for short-term and long-term interests. Furthermore, we illustrate how the described algorithm can be used to address an important issue that has thus far received little attention in the Information Retrieval community: a user's information need changes as a direct result of interaction with information. We empirically evaluate the system's performance based on data collected from regular system users. The goal of the evaluation is not only to understand the performance contributions of the algorithm's individual components, but also to assess the overall utility of the proposed user modeling techniques from a user perspective. Our results provide empirical evidence for the utility of the hybrid user model, and suggest that effective personalization can be achieved without requiring any extra effort from the user.\n\nLiterature Review:", "role": "user" }, { "content": "A measure of the similarity between two objects a and b, often used in information retrieval, consists in representing these objects in the form of two vectors x a and x b and computing the Cosine Vector (CV) (or Vector Space) similarity BIB001 BIB002 between these vectors: In the context of item recommendation, this measure can be employed to compute user similarities by considering a user u as a vector x u ∈ R |I| , where x ui = r ui if user u has rated item i, and 0 otherwise. The similarity between two users u and v would then be computed as where I uv once more denotes the items rated by both u and v. A problem with this measure is that is does not consider the differences in the mean and variance of the ratings made by users u and v. A popular measure that compares ratings where the effects of mean and variance have been removed is the Pearson Correlation (PC) similarity: (4.20) Note that this is different from computing the CV similarity on the Z-score normalized ratings, since the standard deviation of the ratings is evaluated only on the common items I uv , not on the entire set of items rated by u and v, i.e. I u and I v . The same idea can be used to obtain similarities between two items i and j , this time by comparing the ratings made by users that have rated both of these items: While the sign of a similarity weight indicates whether the correlation is direct or inverse, its magnitude (ranging from 0 to 1) represents the strength of the correlation. Example 4.7. The similarities between the pairs of users and items of our toy example, as computed using PC similarity, are shown in Figure 4 .3. We can see that Lucy's taste in movies is very close to Eric's (similarity of 0.922) but very different from John's (similarity of −0.938). This means that Eric's ratings can be trusted to predict Lucy's, and that Lucy should discard John's opinion on movies or consider the opposite. We also find that the people that like \"The Matrix\" also like \"Die Hard\" but hate \"Wall-E\". Note that these relations were discovered without having any knowledge of the genre, director or actors of these movies. The differences in the rating scales of individual users are often more pronounced than the differences in ratings given to individual items. Therefore, while computing the item similarities, it may be more appropriate to compare ratings that are centered on their user mean, instead of their item mean. The Adjusted Cosine (AC) similarity , is a modification of the PC item similarity which compares user-mean-centered ratings: In some cases, AC similarity has been found to outperform PC similarity on the prediction of ratings using an item-based method .", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: The Intranasal Application of Zanamivir and Carrageenan Is Synergistically Active against Influenza A Virus in the Murine Model\n\nhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC4459876/\n\nSHA: f0b1fa4036434b57c8307d43c39a4193f7e8053a\n\nAuthors: Morokutti-Kurz, Martina; König-Schuster, Marielle; Koller, Christiane; Graf, Christine; Graf, Philipp; Kirchoff, Norman; Reutterer, Benjamin; Seifert, Jan-Marcus; Unger, Hermann; Grassauer, Andreas; Prieschl-Grassauer, Eva; Nakowitsch, Sabine\nDate: 2015-06-08\nDOI: 10.1371/journal.pone.0128794\nLicense: cc-by\n\nAbstract: BACKGROUND: Carrageenan is a clinically proven and marketed compound for the treatment of viral upper respiratory tract infections . As infections caused by influenza virus are often accompanied by infections with other respiratory viruses the combination of a specific anti-influenza compound with the broadly active antiviral polymer has huge potential for the treatment of respiratory infections. Thus, the combination of the specific anti-influenza drug Zanamivir together with carrageenan in a formulation suitable for intranasal application was evaluated in-vitro and in-vivo. PRINCIPAL FINDINGS: We show in-vitro that carrageenan and Zanamivir act synergistically against several influenza A virus strains (H1N1(09)pdm, H3N2, H5N1, H7N7). Moreover, we demonstrate in a lethal influenza model with a low pathogenic H7N7 virus (HA closely related to the avian influenza A(H7N9) virus) and a H1N1(09)pdm influenza virus in C57BL/6 mice that the combined use of both compounds significantly increases survival of infected animals in comparison with both mono-therapies or placebo. Remarkably, this benefit is maintained even when the treatment starts up to 72 hours post infection. CONCLUSION: A nasal spray containing carrageenan and Zanamivir should therefore be tested for prevention and treatment of uncomplicated influenza in clinical trials. Text: The periodic appearance of new influenza variants poses a worldwide pandemic threat. Since the emergence of the new A(H7N9) virus, more than 400 human cases were reported to the WHO with a mortality rate of more than 35%. Most patients with A(H7N9) infections had contact with poultry or visited live animal markets. However, some sporadic cases seemed to be a result of human to human transmissions [1, 2] . In contrast to pandemic viruses which fulminantly enter the human population and cause high mortality rates, seasonal influenza viruses generally cause uncomplicated and transient infections in humans, with virus replication localized to the upper respiratory tract [3, 4] . However, in its fully developed form influenza is an acute respiratory disease resulting in hospitalizations and deaths mainly among high-risk groups. Worldwide, annual epidemics result in about three to five million cases of severe illness, and about 250,000 to 500,000 deaths [5] . For this reason WHO [6] and CDC [7] recommend antiviral treatment for any patient with suspected influenza who is at risk for influenza complications without previous laboratory confirmation. It is known that influenza virus infections are often accompanied by other viral pathogens [8] . Depending on the detection method (qRT-PCR or immunofluorescence) different ratios of co-infections have been found. Analysis by qRT-PCR revealed that 54.5-83.3% of influenza A or B positive patients were found to have at least one concomitant respiratory viral infection [9] [10] [11] [12] . The detection frequency with immunofluorescence was found to be even higher (90-100%) [13, 14] . Potential concomitant viral pathogens of influenza virus infections include human rhinovirus (hRV), respiratory syncytial virus, adenovirus, human coronavirus, human metapneumovirus and parainfluenza virus [14, 15] . As a result of the multiple infections, a specific anti-influenza mono-therapy treats the influenza virus infection only, but not the infection with the concomitant viral pathogen. Hence, the therapy often fails to sufficiently resolve symptoms. This is also reflected by the fact that neuraminidase inhibitors (NI) are highly efficacious in animal models investigating influenza mono-infections [16, 17] but show lower efficacy against influenza symptoms in clinical trials in adults with natural infections [18] . Therefore, there is a high medical need for a broadly acting antiviral therapy in combination with a specific anti-influenza therapy for treatment of patients suffering from upper respiratory tract symptoms. Ideally, the substances present in the combination complement each other by different modes of action, leading to a treatment that provides full protection against a broad range of different respiratory viruses as well as different influenza strains with a low probability to induce escape mutations. One approach for a broad antiviral therapy is the creation of a protective physical barrier in the nasal cavity using carrageenan. Carrageenan is a high molecular weight sulfated polymer derived from red seaweed (Rhodophyceae) that has been extensively used in food, cosmetic and pharmaceutical industry and is generally recognized as safe by the FDA (GRAS) (reviewed in [19] ). Three main forms of carrageenans are commercially used: kappa, iota and lambda. They differ from each other in the degree of sulfation, solubility and gelling properties [20] . The antiviral mechanism of carrageenan is based on the interference with viral attachment; as a consequence, viral entry is inhibited [21, 22] . Its antiviral activity is dependent on the type of polymer as well as the virus and the host cells [23] [24] [25] [26] [27] [28] [29] [30] [31] [32] and has been reviewed in [33] [34] [35] . We published that iota-carrageenan is a potent inhibitor of hRV [36] and influenza A [37] replication and demonstrated the antiviral efficacy of iota-carrageenan against common cold viruses by intranasal application in several randomized, double-blind, parallel group, placebo-controlled clinical trials [38] [39] [40] . The pooled analysis of two studies conducted in 153 children and 203 adults revealed that patients infected with any respiratory virus, who were intranasally treated with iota-carrageenan showed a 1.9 day faster recovery from common cold symptoms than placebo treated patients in the intention-to-treat population [41, 42] . The anti-influenza activity was shown by subgroup analysis of 49 influenza infected patients who benefited from a 3.3 days faster recovery from symptoms. The use of carrageenan nasal spray was associated with a significant reduction of the influenza viral load in nasal fluids and a significant increase in the number of virus free patients within the treatment period of 7 days. In good accordance Prieschl-Grassauer are co-founders of Marinomed Biotechnologie GmbH. Marinomed Biotechnologie GmbH had a role in study design, data collection and analysis, decision to publish, preparation of the manuscript and is financing the processing charge of the manuscript. with the literature [9] [10] [11] [12] [13] [14] we observed that the majority of influenza virus infected patients suffered from a concomitant respiratory viral infection (66%) as determined by real-time PCR. Carrageenan containing nasal sprays are already marketed for the treatment of respiratory viral infections under different brand names in 18 countries. At present the only available effective drugs for treatment and post exposure prevention of influenza are the NI (Oseltamivir and Zanamivir worldwide; Peramivir in Japan and South Korea). Since the large-scale use of M2 blockers for prophylaxis and treatment in humans [43] and farming [44] , the currently circulating influenza viruses already lack sensitivity to this drug group [45] . We have already shown an additive therapeutic effect of a combination therapy with intranasally applied iota-carrageenan and orally administered Oseltamivir in lethally H1N1 A/PR/ 8/34 infected mice and a treatment start 48 hours post infection (hpi) [37] . Due to these very promising results we further developed the concept of combining carrageenan with an NI therapy. In contrast to Oseltamivir, which needs to be activated by metabolic conversion, Zanamivir is directly applied as active drug and can also be administered intranasally [46] [47] [48] [49] [50] [51] [52] . The potential of an intranasal administration of Zanamivir was investigated by GlaxoSmithKline. In seven clinical challenge trials 66 volunteers were infected with influenza B/Yamagata/16/88 and 213 with influenza A/Texas/36/91 (H1N1). 156 of these participants got intranasally applied Zanamivir at different doses (daily dose levels from 6.4 mg to 96 mg) for prophylaxis or therapy [46, 47, 53, 54] . These challenge trials showed that treatment starting before and up to 36 hours post virus inoculation was associated with prevention of laboratory confirmed influenza and febrile illness as well as a reduction in viral titers, duration of shedding and symptoms. In total, safety data from 1092 patients after intranasal application of Zanamivir were published and no evidence for Zanamivir induced adverse events or increased frequencies of local nasal intolerance in comparison to placebo groups was found [46, 49, 52] . Taken together, the combination of a carrageenan nasal spray that provides broad antiviral activity against upper respiratory infections-including influenza-with Zanamivir, a specific anti-influenza drug, meets the existing medical need to treat multiple viral infections. In the present work we investigate the therapeutic effect of a combination of carrageenan and Zanamivir in-vitro and in an animal model. Kappa-carrageenan and iota-carrageenan were purchased from FMC Biopolymers (Philadelphia, PA). The identity, purity (>95%) of carrageenan subtypes and the molecular weight (>100,000) was confirmed by NMR analysis as described elsewhere [55] and the presence of lambda-carrageenan was below the detection limit of 3%. The dry polymer powders were dissolved in aqua bidest (Fresenius Kabi, Austria) to a final concentration of 2.4 mg/ml iota-and 0.8 mg/ml kappa-carrageenan. This 2x stock solution was sterile filtered through a 0.22 μm filter (PAA, Switzerland) and stored at room temperature until use. For further testing the stock solution was diluted to a mixture containing 1.2 mg/ml iota-carrageenan and 0.4 mg/ml kappa-carrageenan (hereinafter referred to as \"carrageenan\"). Zanamivir was purchased as powder (Haosun Pharma, China) and the identity and purity was confirmed by NMR analysis. Zanamivir was either dissolved in carrageenan or placebo solutions, followed by sterile filtration through a 0.22 μm filter (Sarstedt, Germany). For in-vivo studies all Zanamivir containing solutions were freshly prepared. Madin-Darby canine kidney (MDCK) cells were obtained from the American Type Culture Collection (ATCC, Manassas, VA) and cultivated in a 37°C incubator (Sanyo, Japan; CO 2 : 5%, relative humidity: >95%). MDCK cells were grown in Dulbecco's minimal essential (DMEM) high glucose medium (PAA, Austria) supplemented with 10% fetal bovine serum (FBS; PAA, Austria; heat inactivated). Influenza virus A/Hansa Hamburg/01/09 (H1N1(09)pdm) was kindly provided by Peter Staeheli Department of Virology, University of Freiburg, Germany and previously described in [56] ; A/Teal/Germany/Wv632/05 (H5N1) previously published in [57] (accession numbers CY061882-9) and A/Turkey/Germany/R11/01 (H7N7) (taxonomy ID 278191, accession number AEZ68716) were supplied by courtesy of Martin Beer, Institute of Diagnostic Virology, Friedrich-Loeffler-Institute, Riems, Germany; A/Aichi/2/68 (H3N2) was purchased from the ATCC. All influenza viruses were propagated in MDCK cells at 37°C and 5% CO 2 in influenza medium [Opti-Pro serum free medium (Gibco, Austria) supplemented with 4 mM L-glutamine (PAA, Austria), 1% antibiotic-antimycotic mix (PAA, Austria) and 5 μg/ml trypsin (Sigma Aldrich, Austria)]. To determine the 50% inhibitory concentration (IC 50 ) and the combination effect of carrageenan and Zanamivir, a semi-liquid plaque assay was developed. Into 96 well tissue culture plates 1.7x10 4 MDCK cells/well were seeded and infected at 90% confluence (24-28 hours later). Serial dilutions of carrageenan and Zanamivir were prepared in assay medium (influenza medium without trypsin). For infection, viruses were diluted to an MOI of 0.003 (H1N1(09)pdm and H3N2 Aichi), 0.015 (H5N1) or 0.004 (H7N7), respectively, in assay medium and incubated at room temperature (RT) for 10 min with the serial dilutions of carrageenan and/or Zanamivir, respectively. For evaluation of the combination effect of carrageenan and Zanamivir, viruses were diluted in assay medium containing constant concentrations of either carrageenan or Zanamivir. The other substance was serially diluted and used for virus incubation. Cells were infected in 6 replicates/compound dilution, respectively, and incubated at RT for 45 min before inoculum removal.\nQuestion: What is Carrageenan?", "role": "user" }, { "content": "a clinically proven and marketed compound for the treatment of viral upper respiratory tract infections", "role": "assistant" } ]

[ { "content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nconclusion\n\nContext before:\nWe have presented an ensemble approach to word sense disambiguation (Pedersen, 2000) where multiple Naive Bayesian classifiers, each based on co— occurrence features from varying sized windows of context, is shown to perform well on the widely studied nouns interest and line. One of our long-term objectives is to identify a core set of features that will be useful for disambiguating a wide class of words using both supervised and unsupervised methodologies.\n\nCitation:\nWe have presented an ensemble approach to word sense disambiguation ( Pedersen , 2000 ) where multiple Naive Bayesian classifiers , each based on co -- occurrence features from varying sized windows of context , is shown to perform well on the widely studied nouns interest and line .\n\nContext after:\nWhile the accuracy of this approach was as good as any previously published results, the learned models were complex and difficult to interpret, in effect acting as very accurate black boxes. Our experience has been that variations in learning algorithms are far less significant contributors to disambiguation accuracy than are variations in the feature set. In other words, an informative feature set will result in accurate disambiguation when used with a wide range of learning algorithms, but there is no learning algorithm that can perform well given an uninformative or misleading set of features. Therefore, our focus is on developing and discovering feature sets that make distinctions among word senses.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: We propose a method to improve the quality of open-domain response generation by filtering out generic utterances.\n\nKeyphrases: response generation text\n\nDataset descriptions:\nMedDG: MedDG is a large-scale high-quality Medical Dialogue dataset related to 12 types of common Gastrointestinal diseases. It contains more than 17K conversations collected from the online health consultation community.\nROSTD: A dataset of 4K out-of-domain (OOD) examples for the publicly available dataset from (Schuster et al. 2019).\nDailyDialog: DailyDialog is a high-quality multi-turn open-domain English dialog dataset. It contains 13,118 dialogues split into a training set with 11,118 dialogues and validation and test sets with 1000 dialogues each.\nCCNet: CCNet is a dataset extracted from Common Crawl with a different filtering process than for OSCAR. It was built using a language model trained on Wikipedia, in order to filter out bad quality texts such as code or tables.\n\nOptions: A: MedDG B: ROSTD C: DailyDialog D: CCNet", "role": "user" }, { "content": "DailyDialog", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\niliac vein compression syndrome ( ivcs ) , also called may - thurner syndrome or cockett syndrome , commonly refers to the anatomic variant resulting in compression of the left common iliac vein by the overriding iliac artery . in 1851 , virchow first described this anatomic variant when he observed a left - sided predominance of iliofemoral deep venous thrombosis ( dvt ) .\nlater , several studies showed that this anatomic variant was observed in 2232% of cadavers .\nit was not until 1958 that may and thurner established a detailed description of this syndrome by postulating that repetitive compression leads to the formation of spurs inside the affected iliac vein due to the proliferation of vascular endothelium .\ncompromised venous flow caused by both extraluminal compression and intraluminal obstruction made the patient increasingly predisposed to form dvt in the left lower extremity . then in 1965 ,\ncockett and thomas further explored the field and described an acute phase of swelling and left - sided iliofemoral thrombosis as well as a chronic phase that results in chronic venous insufficiency in ivcs patients . despite its relatively high prevalence\n, most ivcs patients could remain asymptomatic for their entire lifetime partly due to the formation of venous collaterals in the pelvis .\nhowever , prompt diagnosis of ivcs is still imperative to reduce inappropriate treatment and achieve a favorable outcome . like in the setting of ivcs ,\ndvt formation is also a known complication in hip fracture patients , and it can bring about serious clinical problems , with pulmonary embolism ( pe ) as its life - threatening complication in the acute phase and post - thrombotic syndrome in the chronic phase . recently , some authors reported extensive left - sided dvt formation in orthopedic surgery patients with concomitant ivcs , but the exact influence of ivcs on dvt formation in hip fracture patients is not well established .\nthe aim of this study was to investigate whether ivcs is a risk factor for dvt in hip fracture patients and the influence ivcs may have on the treatment of dvt .\nthis study was conducted on a consecutive series of old patients ( > 60 years ) admitted to our hospital from january 2011 to march 2016 with hip fractures ( fractures of femoral neck or trochanteric ) who underwent hemiarthroplasty or closed reduction and intramedullary fixation .\nall patients signed the informed consent for the venographies ( preoperative and postoperative ) and participation in this research . since ivcs showed a remarkable left - sided predominance , we focused our study only on the left lower extremity .\nthe diagnosis is established based on the presence of a constant intraluminal filling defect on at least two projections .\nexclusion criteria were as follow : pathologic fractures , patients who were contraindicated for contrast venography , patients who received contrast venography in the right leg only , and incomplete clinical data .\ndvt that has no symptoms , but is found only by screening , is labeled asymptomatic or incidental .\ndvt that has symptoms , such as pain and swelling , is labeled symptomatic dvt .\nthe clinical data of the patients were reviewed , including clinical manifestations ( especially lower extremity pain , swelling , and varicose veins ) , plasmin d - dimer concentration , and doppler ultrasound results .\nmeanwhile , the state of the left iliac vein was obtained from venography imaging , and patients with a 50% intraluminal constriction were diagnosed with ivcs ( figure 1 ) .\nusually , multiple left - to - right pelvic collaterals represent the chronic stage of ivc ( figure 2 ) . according to plasmin d - dimer concentration and doppler ultrasound results ,\nall patients were classified into two groups : the dvt group ( suspicious positive result ) and the non - dvt group ( confirmed negative result ) .\nthen , we further divided the patients in the dvt group into two subgroups : the dvt+/ivcs+ group and the dvt+/ivcs group by contrast venography results .\nall patients received low molecular weight heparin ( lmwh ) in a dose of 2500 u of dalteparin subcutaneously the morning after surgery and then 5000 u for 9 more days .\nchi - square test was used for the analysis of categorical data , while the t - test was used for parametric data .\nall analyses were performed using spss for windows , version 21.0 ( spss , chicago , illinois , usa ) .\nthere were 204 patients in the dvt group and 220 patients in the non - dvt group .\nas shown in table 1 , female patients in the two groups numbered 144 and 152 , respectively ( p=0.429 ) .\nthe mean age was 82.6 years ( range , 7593 years ) for the dvt group and 81.1 years ( range , 7294 years ) for the non - dvt group ( p=0.642 ) .\nthere were 84 femoral neck fractures and 120 trochanteric fractures in the dvt group , while the corresponding data in the non - dvt group were 86 and 134 ( p=0.374 ) .\na total of 180 patients in the dvt group had risk factors for developing dvt in addition to ivcs , including cardiovascular disease , smoking , immobilization ( average time of hospitalization after injury ) , previous history of dvt , or malignancy ; while in the non - dvt group , 191 patients had the above - mentioned risk factors ( p=0.597 ) .\nhence , there were no statistically significant differences regarding the mean age , sex distribution , fracture type , and accompanying risk factors between the two groups ( p>0.05 ) . according to contrast venography , 70 patients ( 34.3% )\nwere diagnosed with ivcs in the dvt group , while confirmed ivcs was found in 52 patients ( 23.6% ) in the non - dvt group ( p=0.02 ) ( table 2 ) .\nin addition , based on the contrast venography 710 days after surgery , the incidence of symptomatic dvt in the dvt+/ivcs+ group and the dvt+/ivcs group was 30.0% and 11.9% , respectively ( p=0.002 ) ( table 3 ) .\nthe current study clearly showed that ivcs serves as a risk factor for left - sided dvt in hip fracture patients ( p=0.02 , or=1.69 ) .\nthis result was as previously estimated because ivcs and hip fracture share a common mechanism of thrombus formation , which is known as the classic triad of virchow : hypercoagulability , endothelial injury , and venous stasis .\nconcomitant ivcs put hip fracture patients at an even higher risk to develop dvt compared to hip fracture alone . consequently\n, we recommend that greater attention should be paid to the status of the left iliac vein in hip fracture patients .\nin particular , acute formation of extensive iliofemoral thrombus in the left lower limb strongly suggests the existence of ivcs , making further diagnostic modalities necessary .\noverall , ivcs usually occurs in the second or third decade of life and is particularly prevalent in women .\nthe main risk factors for ivcs include prolonged immobilization , dehydration , abdomen lesions or surgery , contraceptive usage , or febrile illness .\nonce symptoms occur , the patient can present either acutely or chronically ; acute presentation of ivcs includes sudden onset of left lower extremity pain , swelling , and thrombus formation , while the chronic presentation of ivcs is varicose veins , skin pigmentation changes , ulcerations , chronic venous insufficiency , and venous claudication .\nonce the patient is suspected to have ivcs , further examination should be implemented to reach a diagnosis .\ncontrast venography remains the gold standard in diagnosing ivcs despite its various disadvantages . to date , diagnostic imaging criteria for ivcs are not well established , but a few indicators of ivcs can be ascertained , including a compression greater than 50% in the luminal diameter , the presence of venous collaterals , intraluminal spurs formation , and greater than 2 mm hg changes in hemodynamic flow across the stenotic region [ 1113 ] .\ncontrast venography demonstrates the degree of iliac vein stenosis and can visualize pelvic venous collaterals .\nother diagnostic techniques for ivcs include computed tomography ( ct ) , magnetic resonance venography ( mrv ) , and intravascular ultrasound ( ivus ) . in the current study ,\nthe postoperative symptomatic dvt rate in the dvt+/ivcs+ group was significantly higher than that in the dvt+/ivcs group ( p=0.002 , or=3.16 ) , indicating that ivcs patients do nt respond well to anticoagulation therapy alone .\na study showed that anticoagulation alone or removal of the thrombus with successive anticoagulation yielded a 73% recurrence of thrombosis in ivcs patients with venous spur formation . due to the mechanical nature of the obstruction in ivcs , anticoagulation or removal of the clot\ndoes not deal with the underlying cause of this disease ( external compression and intraluminal constriction ) .\nrecently , endovascular management has been regarded as the first - line treatment for ivcs .\nthrombolysis with / without prophylactic retrievable inferior vena cava filter placement followed by angioplasty / stenting of the afflicted iliac vein appears to be the best option in ivcs patients with extensive dvt .\noverall , the current study demonstrated that for left - sided dvt in hip fracture patients , ivcs is a risk factor that needs more attention and education .\nfurther studies concerning the relationship between ivcs and right - sided or bilateral dvt are needed in the future .\nthis study also showed the limitations of anticoagulation therapy alone in the treatment of dvt in ivcs patients .\nthe optimal treatment of ivcs still needs to be further elucidated by future studies with patients who have a different clinical status .\nthus , an interdisciplinary study should be carried out to achieve a better clinical outcome in the future .\nthe effect of anticoagulant therapy in ivcs - positive dvt patients seems not good , so early detection of ivcs and preventive anticoagulation are necessary for the orthopedic surgeon .\nivcs is an under - recognized risk factor for left - sided dvt in hip fracture patients .\nwhat s more , anticoagulation alone is insufficient for the treatment of dvt when it is complicated with ivcs .", "role": "user" }, { "content": "backgroundthe aim of this study was to identify whether iliac vein compression syndrome ( ivcs ) is a risk factor for left - sided deep venous thrombosis ( dvt ) in hip fracture patients and the influence ivcs may have on the treatment of dvt.material/methodsa retrospective study was carried out among 424 hip fracture patients admitted to our hospital from 2011 to 2016 . \n clinical data were analyzed , and all patients were classified into the dvt group and the non - dvt group based on plasmin d - dimer concentration and results of doppler ultrasound of the left lower limb . \n also , a 50% intraluminal constriction of the left iliac vein in the venography image was considered as ivcs . \n comparison of ivcs prevalence was made between the dvt group and the non - dvt group . \n patients in the dvt group were further divided into the dvt+/ivcs+ group and the dvt+/ivcs group to evaluate the influence ivcs may have on the treatment of dvt.resultsthere were 204 patients in the dvt group and 220 patients in the non - dvt group . \n no statistically significant differences were found regarding the mean age , sex distribution , fracture type , and accompanying risk factors between the two groups . \n a total of 70 patients ( 34.3% ) were diagnosed with ivcs in the dvt group , while confirmed ivcs was found in 52 patients ( 23.6% ) in the non - dvt group ( p=0.02 ) . \n postoperatively , the incidence of symptomatic dvt in the dvt+/ivcs+ group and the dvt+/ivcs group was 30.0% and 11.9% , respectively ( p=0.002).conclusionsivcs is an under - recognized risk factor for left - sided dvt in hip fracture patients . \n what s more , anticoagulation alone is insufficient for the treatment of dvt when it is complicated with ivcs . \n more aggressive measures have to be taken to achieve a favorable outcome .", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nPURPOSE OF REVIEW: The purpose of this review was to evaluate the available literature to determine what may be considered urgent indications for total hip arthroplasty, in the unprecedented setting of the worldwide COVID-19 pandemic. RECENT FINDINGS: SARS-CoV-2 is a novel coronavirus currently presenting in the form of a global pandemic, referred to as COVID-19. In this setting, multiple states have issued executive orders prohibiting \"elective\" surgery, including arthroplasty, in order to preserve healthcare resources. However, during this unprecedented reduction in elective surgery, there is likely to be some controversy as to what constitutes a purely \"elective\" procedure, versus an \"urgent\" procedure, particularly regarding hip arthroplasty. We reviewed the available literature for articles discussing the most commonly encountered indications for primary, conversion, and revision hip arthroplasty. Based upon the indications discussed in these articles, we further stratified these indications into \"elective\" versus \"urgent\" categories. In patients presenting with hip arthroplasty indications, the decision to proceed urgently with surgery should be based upon (a) the potential harm incurred by the patient if the surgery was delayed and (b) the potential risk incurred by the patient in the context of COVID-19 if surgery was performed. The authors present a decision-making algorithm for determining surgical urgency in three patients who underwent surgery in this context. Urgent total hip arthroplasty in the setting of the COVID-19 pandemic is a complex decision-making process, involving clinical and epidemiological factors. These decisions are best made in coordination with a multidisciplinary committee of one's peers. Region-specific issues such as hospital resources and availability of PPE may also inform the decision-making process.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Blockchain for 5G and Beyond Networks: A State of the Art Survey \nChapter Title: C. Smart transportation \n1. Abstract of Cited Paper (BIB001): 5G is ongoing, and it is an emerging platform that not only aims to augment existing but also introduce a plethora of novel applications that require ultra-reliable low-latency communication. It is a new radio access technology that provides building blocks to retrofit existing platforms (e.g., 2G, 3G, 4G, and WiFi) for greater coverage, accessibility, and higher network density with respect to cells and devices. It implies that 5G aims to satisfy a diverse set of communication requirements of the various stakeholders. Among the stakeholders, vehicles, in particular, will benefit from 5G at both the system and application levels. The authors present a tutorial perspective on vehicular communications using the building blocks provided by 5G. First, we identify and describe key requirements of emerging vehicular communications and assess existing standards to determine their limitations. Then we provide a glimpse of the adopted 5G architecture and identify some of its promising salient features for vehicular communications. Finally, key 5G building blocks (i.e., proximity services, mobile edge computing and network slicing) are explored in the context of vehicular communications, and associated design challenges are highlighted. \n2. Abstract of Cited Paper (BIB002): As an integral part of V2G networks, EVs receive electricity from not only the grid but also other EVs and may frequently feed the power back to the grid. Payment records in V2G networks are useful for extracting user behaviors and facilitating decision-making for optimized power supply, scheduling, pricing, and consumption. Sharing payment and user information, however, raises serious privacy concerns in addition to the existing challenge of secure and reliable transaction processing. In this article, we propose a blockchain-based privacy preserving payment mechanism for V2G networks, which enables data sharing while securing sensitive user information. The mechanism introduces a registration and data maintenance process that is based on a blockchain technique, which ensures the anonymity of user payment data while enabling payment auditing by privileged users. Our design is implemented based on Hyperledger to carefully evaluate its feasibility and effectiveness. \n3. Abstract of Cited Paper (BIB003): In this paper, we present a vision for a blockchain-based Mobility-as-a-Service (MaaS) as an application of edge computing. In current MaaS systems, a central MaaS operator plays a crucial role serving an intermediate layer which manages and controls the connections between transportation providers and passengers with several other features. Since the willingness of public and private transportation providers to connect to this layer is essential in the current realization of MaaS, in our vision, to eliminate this layer, a novel blockchain-based MaaS is proposed. The solution also improves trust and transparency for all stakeholders as well as eliminates the need to make commercial agreements with separate MaaS agents. From a technical perspective, the power of computing and resources are distributed to different transportation providers at the edge of the network providing trust in a decentralised way. The blockchain-based MaaS has the potential to emerge as the main component for a smart city transportation offering efficiency and reducing carbon dioxide emissions. \n4. Abstract of Cited Paper (BIB004): Smart city blueprint is constructed by increasing deployment of various Internet of Things devices. In this paper, we focus on data transmission and request for lane property right under the domain of an intelligent traffic system. IoT devices are usually deployed in a heterogeneous environment, with the natural gene of decentralization. Compared with cloud-based centralized architecture, in this paper, we introduce blockchain as a decentralized technology to let vehicles jointly collaborate without having to go through a central computing node authority. Data transmission between vehicles uses a peer-to-peer network in which every node communicates directly with every other node, verified by their relevant end-point nodes; lane’s acquisition right is approved by all relevant vehicle nodes, as well as with consensus agreed upon via smart contract. \n5. Abstract of Cited Paper (BIB005): Data sharing and privacy securing present extensive opportunities and challenges in vehicular network. This paper introduces ‘trust access authentication scheme’ as a mechanism to achieve real-time monitoring and promote collaborative sharing for vehicles. Blockchain, which can provide secure authentication and protected privacy, is a crucial technology. However, traditional cloud computing performs poorly in supplying low-latency and fast-response services for moving vehicles. In this situation, edge computing enabled Blockchain network appeals to be a promising method, where moving vehicles can access storage or computing resource and get authenticated from Blockchain edge nodes directly. In this paper, a hierarchical architecture is proposed consist of vehicular network layer, Blockchain edge layer and Block-chain network layer. Through a authentication mechanism adopting digital signature algorithm, it achieves trusted authentication and ensures valid verification. Moreover, a caching scheme based on many-to-many matching is proposed to minimize average delivery delay of vehicles. Simulation results prove that the proposed caching scheme has a better performance than existing schemes based on centralized model or edge caching strategy in terms of hit ratio and average delay. \n6. Abstract of Cited Paper (BIB006): Vehicular ad hoc networks (VANETs) have become an essential part in smart transportation systems of modern cities. However, because of dynamicity and infrastructure-less of VANETs, the ever increasing number of network security issues become obstacles for the realization of smart cities. Software-defined VANETs have provided a reliable way to manage VANETs dynamically and securely. However, the traditionally centralized control plane makes it vulnerable to malicious nodes and results in performance degradation. Therefore, a distributed control plane is necessary. How to reach a consensus among multiple controllers under complex vehicular environment is an essential problem. In this paper, we propose a novel blockchain-based distributed software-defined VANET framework (block-SDV) to establish a secure architecture to overcome the above issues. The trust features of blockchain nodes, the number of consensus nodes, trust features of each vehicle, and the computational capability of the blockchain are considered in a joint optimization problem, which is modeled as a Markov decision process with state space, action space and reward function. Since it is difficult to be solved by traditional methods, we propose a novel dueling deep ${Q}$ -learning (DDQL) with prioritized experience replay approach. Simulation results are presented to show the effectiveness of the proposed block-SDV framework. \n7. Abstract of Cited Paper (BIB007): Smart grid has emerged as a successful application of cyber-physical systems in the energy sector. Among numerous key technologies of the smart grid, vehicle-to-grid (V2G) provides a promising solution to reduce the level of demand–supply mismatch by leveraging the bidirectional energy-trading capabilities of electric vehicles. In this paper, we propose a secure and efficient V2G energy trading framework by exploring blockchain, contract theory, and edge computing. First, we develop a consortium blockchain-based secure energy trading mechanism for V2G. Then, we consider the information asymmetry scenario, and propose an efficient incentive mechanism based on contract theory. The social welfare optimization problem falls into the category of difference of convex programming and is solved by using the iterative convex–concave procedure algorithm. Next, edge computing has been incorporated to improve the successful probability of block creation. The computational resource allocation problem is modeled as a two-stage: 1) Stackelberg leader–follower game and 2) the optimal strategies are obtained by using the backward induction approach. Finally, the performance of the proposed framework is validated via numerical results and theoretical analysis.\n\nLiterature Review:", "role": "user" }, { "content": "With the rapid development of modern 5G communication and computation technologies, recent years have witnessed a tremendous growth in intelligent transportation systems (ITS), which create significant impacts on various aspects of our lives with smarter transport facilities and vehicles as well as better transport services BIB002 , BIB001 . Smart transportation is regarded as a key IoT application which refers to the integrated architectures of communication technologies and vehicular services in transportation systems. One critical issue in smart transportation is security risks resulted by dynamic vehicleto-vehicle (V2V) communications in untrusted vehicular environments and reliance on centralized network authorities. Blockchain shed lights on several inherent features to implement distributed data storage, peer-to-peer communication, and transparently anonymous user systems, which envisions to build secure, decentralized ITS systems to facilitate customer transportations BIB004 . One of the most significant services to realize intelligent transportation is data transmission among vehicles. How to provide efficient data exchange services in terms of low latency and increased network throughput while still ensure high degrees of security is a critical challenge. Blockchain would enhance QoS of the current ITS system by offering a decentralized management platform, wherein all vehicles and road side units (RSU) can perform data transmission and sharing on a peer-to-peer model to reduce end-to-end delay without using a vehicular authority BIB005 . In order to adapt the large volumes of electric vehicle (EV) charging/discharging demand during transportation, the blockchain concept is introduced in [257] that enables peerto-peer transaction and decentralized storage to record all transaction data of EVs. In fact, EVs can be considered as a mobile power backup device to support the smart grid for load flattening, peak shaving and frequency regulation. This new energy trading paradigm is known as vehicle-to-grid (V2G), which is essential to build a safer and more sustainable energy platform for both EVs and the main power grid. Consumer power loads from smart city are all connected to the public blockchain power exchanging platform, where the electricity supply and user demand information are transmitted, encrypted and recorded in the blockchain platform. In such a context, the EV can publish and transmit the charging or discharging orders (for buying and selling) to the power blockchain platform which executes the EV request, performs energy trading and payment, and saves the transaction to the distributed ledger, which is also visible to every vehicle in the vehicular network. In the line of discussion, the authors in BIB008 also analyse a V2G energy trading model with a combination of blockchain and edge computing. EVs can buy energy from local energy aggregators (LEAGs) via trading. The vehicular communication is secured by a consortium blockchain, in which all the transactions are created, propagated, and verified by authorized LEAGs. To further reduce latency and processing posing on burden blockchain, edge computing servers are employed to undertake block creation and mining. LEAGs can buy computation services from edge computing providers to finalize this process, and store mined blocks to the nearby edge nodes. The blockchain technology envisions a trustless network to eliminate the operation cost of the intermediary participation, which will realize a quicker, safer and cheaper way in ITS systems. Moreover, authentication for vehicle access is of paramount importance for vehicular networks. In this regard, smart contract would be a notable approach which can authenticate and verify vehicular transactions by triggering the programmed logic functions BIB006 . This enables direct authentication for registered vehicles without revealing device privacy and effectively prevents potential attacks from malicious vehicles. Recently, blockchain has been incorporated with SDN to build secured and controlled vehicular ad hoc networks (VANETs) BIB007 . With the increasing scale of the current VANETs, traditional VANET frameworks with centralized SDN control mechanisms obviously cannot match the diversification of VANET traffic requirements. Distributed SDN control can be an efficient solution to localize decision making to an individual controller, which thus minimizes the control plane response time to data plane requests. To achieve secure communications between SDN controllers as well as between SDN controllers and EVs, blockchain is leveraged to achieve agreement among different nodes in terms of traffic information and energy demands without using centralized trust management. Another aspect in VANETs is the security of power trading between EVs and V2G networks. In fact, it is very important to design a safe, efficient, transparent, information symmetrical trading model for VANETs to provide ubiquitous vehicular services (i.e. traffic transmission, vehicle cooperation, energy payment). Blockchain is introduced in BIB003 for a reliable decentralized power trading platform where a V2G EV trading smart contract is integrated for trading authentication and a decentralized energy ledger is for data storage and sharing without relying on a trusted third party, eliminating the need for trusted third parties to address the high cost, inefficiency, and insecure data storage of traditional centralized organizations.", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: doctors have been increasingly reporting cases of another battlefield raging within the body: the heart.\n\nAbstract:\nImportance: Increasing numbers of confirmed cases and mortality rates of coronavirus disease 2019 (COVID-19) are occurring in several countries and continents.\nInformation regarding the impact of cardiovascular complication on fatal outcome is scarce.\nObjective: To evaluate the association of underlying cardiovascular disease (CVD) and myocardial injury with fatal outcomes in patients with COVID-19.\nDesign, Setting, and Participants: This retrospective single-center case series analyzed patients with COVID-19 at the Seventh Hospital of Wuhan City, China, from January 23, 2020, to February 23, 2020.\nAnalysis began February 25, 2020.\nMain Outcomes and Measures: Demographic data, laboratory findings, comorbidities, and treatments were collected and analyzed in patients with and without elevation of troponin T (TnT) levels.\nResult: Among 187 patients with confirmed COVID-19, 144 patients (77%) were discharged and 43 patients (23%) died.\nThe mean (SD) age was 58.50 (14.66) years.\nOverall, 66 (35.3%) had underlying CVD including hypertension, coronary heart disease, and cardiomyopathy, and 52 (27.8%) exhibited myocardial injury as indicated by elevated TnT levels.\nThe mortality during hospitalization was 7.62% (8 of 105) for patients without underlying CVD and normal TnT levels, 13.33% (4 of 30) for those with underlying CVD and normal TnT levels, 37.50% (6 of 16) for those without underlying CVD but elevated TnT levels, and 69.44% (25 of 36) for those with underlying CVD and elevated TnTs.\nPatients with underlying CVD were more likely to exhibit elevation of TnT levels compared with the patients without CVD (36 [54.5%] vs 16 [13.2%]).\nPlasma TnT levels demonstrated a high and significantly positive linear correlation with plasma high-sensitivity C-reactive protein levels (ß = 0.530, P < .001) and N-terminal pro-brain natriuretic peptide (NT-proBNP) levels (ß = 0.613, P < .001).\nPlasma TnT and NT-proBNP levels during hospitalization (median [interquartile range (IQR)], 0.307 [0.094-0.600]; 1902.00 [728.35-8100.00]) and impending death (median [IQR], 0.141 [0.058-0.860]; 5375 [1179.50-25695.25]) increased significantly compared with admission values (median [IQR], 0.0355 [0.015-0.102]; 796.90 [401.93-1742.25]) in patients who died (P = .001; P < .001), while no significant dynamic changes of TnT (median [IQR], 0.010 [0.007-0.019]; 0.013 [0.007-0.022]; 0.011 [0.007-0.016]) and NT-proBNP (median [IQR], 352.20 [174.70-636.70]; 433.80 [155.80-1272.60]; 145.40 [63.4-526.50]) was observed in survivors (P = .96; P = .16).\nDuring hospitalization, patients with elevated TnT levels had more frequent malignant arrhythmias, and the use of glucocorticoid therapy (37 [71.2%] vs 69 [51.1%]) and mechanical ventilation (41 [59.6%] vs 14 [10.4%]) were higher compared with patients with normal TnT levels.\nThe mortality rates of patients with and without use of angiotensin-converting enzyme inhibitors/angiotensin receptor blockers was 36.8% (7 of 19) and 25.6% (43 of 168).\nConclusions and Relevance: Myocardial injury is significantly associated with fatal outcome of COVID-19, while the prognosis of patients with underlying CVD but without myocardial injury is relatively favorable.\nMyocardial injury is associated with cardiac dysfunction and arrhythmias.\nInflammation may be a potential mechanism for myocardial injury.\nAggressive treatment may be considered for patients at high risk of myocardial injury.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Conclusions and Relevance: Myocardial injury is significantly associated with fatal outcome of COVID-19, while the prognosis of patients with underlying CVD but without myocardial injury is relatively favorable.\", \"Myocardial injury is associated with cardiac dysfunction and arrhythmias.\", \"Inflammation may be a potential mechanism for myocardial injury.\"]}", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThere are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks. However, most existing datasets for instructional video analysis have the limitations in diversity and scale,which makes them far from many real-world applications where more diverse activities occur. Moreover, it still remains a great challenge to organize and harness such data. To address these problems, we introduce a large-scale dataset called \"COIN\" for COmprehensive INstructional video analysis. Organized with a hierarchical structure, the COIN dataset contains 11,827 videos of 180 tasks in 12 domains (e.g., vehicles, gadgets, etc.) related to our daily life. With a new developed toolbox, all the videos are annotated effectively with a series of step descriptions and the corresponding temporal boundaries. Furthermore, we propose a simple yet effective method to capture the dependencies among different steps, which can be easily plugged into conventional proposal-based action detection methods for localizing important steps in instructional videos. In order to provide a benchmark for instructional video analysis, we evaluate plenty of approaches on the COIN dataset under different evaluation criteria. We expect the introduction of the COIN dataset will promote the future in-depth research on instructional video analysis for the community.\n\nCited Abstract(s):\n[1]: We address the problem of activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times of each activity. We introduce a new model, Region Convolutional 3D Network (R-C3D), which encodes the video streams using a three-dimensional fully convolutional network, then generates candidate temporal regions containing activities, and finally classifies selected regions into specific activities. Computation is saved due to the sharing of convolutional features between the proposal and the classification pipelines. The entire model is trained end-to-end with jointly optimized localization and classification losses. R-C3D is faster than existing methods (569 frames per second on a single Titan X Maxwell GPU) and achieves state-of-the-art results on THUMOS’14. We further demonstrate that our model is a general activity detection framework that does not rely on assumptions about particular dataset properties by evaluating our approach on ActivityNet and Charades. Our code is available at http: ai.bu.edu r-c3d\n\n[2]: Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and determining completeness. This allows the framework to effectively distinguish positive proposals from background or incomplete ones, thus leading to both accurate recognition and localization. These components are integrated into a unified network that can be efficiently trained in an end-to-end fashion. Additionally, a simple yet effective temporal action proposal scheme, dubbed temporal actionness grouping (TAG) is devised to generate high quality action proposals. On two challenging benchmarks, THUMOS14 and ActivityNet, our method remarkably outperforms previous state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling actions with various temporal structures.\n\n[3]: State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R-CNN [5] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolutional features. For the very deep VGG-16 model [19], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2 mAP) and 2012 (70.4 mAP) using 300 proposals per image. Code is available at https: github.com ShaoqingRen faster_rcnn.\n\n[4]: We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8 accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.", "role": "user" }, { "content": "For the third category, we focus on step localization. This task is related to the area of action detection, where promising progress has also been achieved recently. For example, Zhao [2] developed structured segment networks (SSN) to model the temporal structure of each action instance with a structured temporal pyramid. Xu [1] introduced a Region Convolutional 3D Network (R-C3D) architecture, which was built on C3D [4] and Faster R-CNN [3] , to explore the region information of video frames. Compared with these methods, we attempt to further explore the dependencies of different steps, which lies in the intrinsic structure of instructional videos. Towards this goal, we proposed a new method with a bottom-up strategy and a top-down scheme. Our method can be easily plugged into recent proposal-based action detection methods and enhance the performance of step localization in instructional videos.", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nshoes provide protection from the environment and functional assistance , are fashionable , \n and enable adjustments for deformed feet and treatment for musculoskeletal injuries . \n\nalthough the origin of shoe wearing by humans is not known , they have been worn for the \n convenience of walking and protection of the feet for long1 .\nthe material and shape of shoes have evolved in modern times to \n suit the purpose of wearing shoes , but the main purpose of wearing shoes in the past was for \n protection2 .\nshoes can be easily changed \n to alter the load of the human body , since the material , shape , and heel height affect \n mobility and stability3 .\nbody movements , such as walking , are facilitated by the movement of the skeleton through \n muscle contraction , and the muscle activity can be analyzed using electromyography ( emg ) , \n which is a method of obtaining muscle information .\nit is essential to functionally analyze emg data during various activities to understand \n the effects of changes to muscle length4 . \n\nfunctional analysis of emg data demonstrates the relationships between movements \n and time about movement of the body , emg and power production , and emg and muscle \n fatigue5 .\na previous study analyzed static balance and muscle activity of the lower extremities in \n young adults depending on the period of high - heeled shoe wearing and reported that the \n rectus femoris ( rf ) and tibia anterior ( ta ) muscles did not appear to show significant \n differences6 .\nanother study related to \n kinetic differences between normal running shoes and spring - loaded running shoes reported \n that the rf activity on emg was higher with the latter shoes7 .\nthe effect of unstable sandals on instability during gait in \n healthy adults has been previously examined , and unstable shoes showed significant \n differences in the ankle joint and increased peroneal activity during pre - swing , while \n stable shoes increased medial gastrocnemius ( gm ) and decreased ta activities during \n mid - stance .\nthe stable shoes changed gait and muscle activity related to braking and \n progression and a softer and less stable forefoot increased evertor action during toe - off in \n the frontal plane .\nalthough the use of and aesthetic interest in the shoes of young women have increased in \n modern society , previous studies demonstrated that emg activity and muscle fatigue are \n related to high - heeled shoes and functional running shoes .\nthus , the purpose of this study \n was to analyze the effects of muscle activity on walking according to various shoes \n frequently worn by young women .\nthe 15 participants were students in their 20s at n university , cheonan - si , republic of \n korea . they had not had any musculoskeletal or neurological injuries , an athletic career , or \n\nthey were provided detailed information on this study and \n voluntarily provided written informed consent before the experiment .\nthis study was approved \n by the institutional review board of namseoul university . a body composition analyzer ( inbody720 ; biospace o. ltd . ,\nseoul , republic of korea ) was \n used to determine the general characteristics of the subjects . a treadmill\n( sns care m-400 m ; \n sns care co. , ltd . , goyang , republic of korea ) was used for walking , and a free emg system \n ( free emg ; bts inc . ,\nmilan , italy ) was used to measure the muscle activity of the lower \n extremities while the subjects wore different types of shoes and walked on the \n treadmill .\nthe participants \n were divided into three groups according to the types of shoes they wore : a converse \n sneakers group , a rain boots group , and a combat boots group .\nsurface electrodes ( 3 m red \n dot 2570 ; 3 m center , st .\npaul minnesota , usa ) were cleaned using alcohol - soaked cotton to \n minimize errors due to skin impedance and used to measure emg activity10 .\nthey were attached to the muscles at maximal static \n contraction to avoid errors that could affect the results .\nsix muscles , namely , the rf , \n vastus medialis ( vm ) , semimembranosus ( sm ) , ta , peroneus longus ( pl ) , and gm , were examined . \n\nthe rf is halfway between the patella and iliac spine on the front of the femur11 .\nthe vm is 50 degrees on the femoral \n longitudinal axis and 5 cm above the superomedial patella12 .\nthe sm is 3 cm from the lateral border of the thigh and halfway \n along the distance from the gluteal fold to behind the knee13 .\nthe pl is 25% between the fibula head and lateral malleolus14 . finally , the gm is 35% medially from the distal midline of the \n knee joint and 2 cm above this joint . in all cases ,\nthe root mean square of emg data was determined \n during walking , and the maximal voluntary muscle contraction was used to eliminate data \n errors due to personal characteristics .\nthe emg signal was normalized , the sampling rate was \n 1,000 hz , and the band - pass filter was 20500 hz .\nthe participants walked at a speed of 4 km / h15 for 30 min and rested 24 h between wearing each shoe to \n avoid fatigue effects16 .\nstatistical analysis was performed using spss version 18.0 for windows ( spss , inc . , \n\none - way analysis of variance ( anova ) was \n used to compare differences in muscle activity among shoe groups .\nif significant differences \n were found , the scheffe test was used for post - hoc analysis .\nthe study participants were healthy women in their early 20s ( table 1table 1.general characteristics of the participantssubjectsage ( years)height ( cm)weight ( kg)m sd20.5 0.5159.0 4.951.4 7.2 m sd : means standard deviation ) and wore three types of shoes during the test : converse sneakers , rain boots , \n and combat boots ( table 2table 2.general characteristics of the shoesshoesweight ( kg)shaft height ( cm)converse sneakers0.7117rain boots0.8017combat boots1.0017 ) .\nm sd : means standard deviation differences in the interaction effect of group and time were not noted in the one - way anova \n used to compare muscle activity among the three groups .\nhowever , the main effect of group showed significant differences for \n the vm ( table 3table 3.comparison of pre- and post - test muscle electromyography signals according to the \n groups ( mv)variablegrouppre - testpost - testm sdm sdrfconverse sneakers14.5 9.714.4 7.9rain boots11.2 4.116.9 10.7combat boots12.1 4.514.2 13.1vmconverse sneakers28.9 12.332.4 15.3rain boots42.3 18.042.5 21.5combat boots50.2 32.052.0 24.0smconverse sneakers213.8 125.8220.7 116.8rain boots169.0 70.4224.4 134.8combat boots197.7 112.1215.4 89.7taconverse sneakers35.6 12.333.0 12.1rain boots38.4 18.933.9 11.2combat boots32.6 16.331.8 14.0plconverse sneakers37.2 12.432.1 \n14.3rain boots36.2 18.338.4 17.7combat boots36.1 15.236.5 17.6gmconverse sneakers52.7 26.849.8 14.8rain boots43.3 23.145.0 22.4combat boots52.4 29.348.8 27.2*p\n< 0.05 ; : significant differences between groups ; : \n converse sneakers ; : rain boots ; : combat boots ; rf : rectus \n femoris , vm : vastus medialis ; sm : semimembranosus ; ta : tibialis anterior ; pl : peroneus \n longus ; gm : medial head of the gastrocnemius ; m sd : mean standard deviation ) .\nfurther , in the results of multiple comparisons of vm , the rain boots group \n showed significantly higher vm activity than the converse sneakers group , and the combat \n boots group showed significantly higher vm activity than the rain boots group .\n* p < 0.05 ; : significant differences between groups ; : \n converse sneakers ; : rain boots ; : combat boots ; rf : rectus \n femoris , vm : vastus medialis ; sm : semimembranosus ; ta : tibialis anterior ; pl : peroneus \n longus ; gm : medial head of the gastrocnemius ; m sd : mean standard deviation\nshoes that do not fit the feet change the foot bones and hamper gait posture , in addition \n to causing various adverse conditions , including calluses , corns , neuroma , hallux valgus , \n toe deformities , ankle sprains , achilles tendinitis , and knee and back pain . in modern \n society , women tend to disregard their own physical characteristics while choosing \n shoes17 .\nthe present study was conducted to analyze the muscle activity of the lower extremities \n depending on shoe type during walking among individuals in their 20s .\nthe results showed \n significant differences in the interaction effects of group and time or the main effect of \n time .\nvm activity \n differed significantly among the three groups : the activity in the rain boots group was \n significantly higher than that in the converse sneakers group , and that in the combat boots \n group was significantly higher than the activity in the rain boots group .\na previous study found that the impulsive force increased rapidly at heel - strike , because \n it made an angle like an edge , and the knee joint was unable to extend adequately at \n heel - strike7 .\nanother study that \n analyzed the effect of shoe sole form on knee and ankle joint muscle activity reported that \n vm activity was higher with high - heeled shoes and house shoes than with shoes that had a \n curved outsole . further , because high - heeled shoes elevate the anterior foot , the ta \n activity increased , gm activity decreased and led to increased knee extension at \n heel - strike , and vm activity increased10 . \n\na previous study analyzed the effects of the form of the outsole on lower leg emg signals \n during gait .\nwhen shoes with a curved outsole were used , the ankle joint showed increased \n dorsiflexion during heel - strike and the dorsiflexion state was maintained in the stance \n phase , while joint motion was decreased in the sagittal plane .\nthe curved outsole reduced \n the load on the joint , as dorsiflexion agonist activity increased and dorsiflexion \n antagonist activity decreased .\nin addition , as ankle push - off and push - off movement were \n delayed , unnecessary movement was avoided and the center of gravity was maintained during \n gait . for these reasons ,\nthe vm activity was increased when shoes with a curved outsole were \n used as compared to other shoes , since muscle activity was balanced on a supporting base . \n\nsimilar effects were noted with shoes that had an insole of the elevator shoe type18 .\nthe vm activity emphasized the function \n of contracture related to the stability of the medial knee joint at the end of \n extension19 ; when foot orthotic \n quadriceps and gluteus medius emg signals were tested during a selected exercise , the vm \n activity was found to be higher in the three - orthotic condition ( 7 medial rearfoot post , 4 \n lateral rearfoot post , and neutral rearfoot post ) than the no - orthotic condition .\nanother study reported that the vm \n activity induced mechanical changes in the patellofemoral joint to facilitate the vm \n activity during an orthotic intervention20 .\nfurther , the angle of the last rotation of tibialis anterior \n reportedly increases vm activity21 .\nthe results of the present study showed significant differences in vm activity depending on \n the shoe type : the rain boots group had significantly higher vm activity than the converse \n sneakers group , and the combat boots group had significantly higher activity than the rain \n boots group . in the groups of increasing vm activity ,\nknee extension increased because of \n gait to leaning the anterior part ; further , the angle of tibial rotation and mechanics of \n the patellofemoral joint changed to prevent lateral tracking and improve medial stability \n with the increase in knee extension .\nvm activity was considered to increase for efficient \n walking , as this reduced the load on the joint , prevented unnecessary movements , and \n balanced the center of gravity and support base . in conclusion , this study analyzed the effects of various shoe types during treadmill \n walking on lower extremity muscle activity determined using emg in healthy young women .\nthe \n results of one - way anova that compared emg signals among three shoe type groups showed no \n significant difference in the interaction effect of group and time .\nthe results of multiple comparison of vm activity showed \n significant differences : the rain boots group had significantly higher than the converse \n sneakers group , and the combat boots group had significantly higher activity than the rain \n boots group .\nthe vm activity was higher in the former two groups and enabled more effective \n walking and better balance , because shoe type affects tibial rotation depending on knee \n joint movement .", "role": "user" }, { "content": "[ purpose ] the purpose of this study was to analyze the effects of different shoe types on \n lower extremity muscle activity in healthy young women by using electromyography . \n [ subjects and methods ] fifteen healthy young women in their 20s were included in this \n single - group repeated measures study . \n the subjects were divided into three groups : \n converse sneakers , rain boots , and combat boots . \n the subjects walked on a treadmill at \n 4 km / h for 30 min , during which six muscles were examined using electromyography : the \n rectus femoris , vastus medialis , semimembranosus , tibialis anterior , peroneus longus , and \n medial head of the gastrocnemius . between switching shoe types , \n a 24-h rest period was \n instated to prevent the fatigue effect from treadmill walking . \n [ results ] one - way analysis \n of variance used to compare electromyography results among the three groups showed that \n the main effect of group differed significantly for the vastus medialis . \n vastus medialis \n activity was higher in the rain boots group than the converse sneakers group , and it was \n higher in the combat boots group than rain boots group . \n [ conclusion ] shoe type affects \n lower extremity muscle activity . our findings may help individuals choose the ideal shoes \n for daily walking .", "role": "assistant" } ]

[ { "content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nCloning and expression of the Epstein-Barr virus-encoded dUTPase: patients with acute, reactivated or chronic virus infection develop antibodies against the enzyme. The gene encoding the Epstein-Barr virus (EBV) -specific dUTPase was amplified from virus DNA by PCR. The active enzyme was expressed in Escherichia coli and in insect cells as a non-fusion protein. The protein from E. coli specifically converted dUTP to dUMP and did not react with other dNTPs or NTPs. Preliminary experiments yielded a Km value of about 0. 8 microM for dUTP. MAbs against the dUTPase reacted with a protein of approximately 31 kDa in 12-O-tetradecanoyl-phorbol-13-acetate (TPA) -stimulated B cells harbouring either type 1 or type 2 EBV. The protein was found in untreated cells at low levels, whereas induction of the lytic replication cycle by TPA treatment or by providing the immediate early transactivator BZLF1 in trans resulted in increased expression. We demonstrated that the virus dUTPase isolated from EBV-infected cells is a phosphoprotein. The protein expressed in insect cells was used to test for the presence of specific antibodies in sera from normal, healthy carriers and from patients with various diseases. While the sera of EBV-negative individuals (0 / 3) or healthy carriers (0 / 33) did not contain detectable levels of antibodies, patients with mononucleosis (5 / 18), chronic EBV infection (2 / 7), EBV reactivation (7 / 20) and human immunodeficiency virus infection (5 / 24) showed elevated antibody titres against the enzyme. This indicated that the dUTPase is expressed during EBV replication and reactivation. The enzyme might therefore be a potential target for drug therapy under conditions of active DNA replication.", "role": "user" }, { "content": "{\"CellLine\": [\"12 - O - tetradecanoyl - phorbol - 13 - acetate (TPA) - stimulated B cells\"], \"CellType\": [\"untreated cells\", \"insect cells\", \"EBV - infected cells\"], \"DNA\": [\"virus DNA\"], \"Protein\": [\"dUTP\", \"enzyme\", \"antibodies\", \"phosphoprotein\", \"non - fusion protein\", \"BZLF1\", \"specific antibodies\", \"Epstein - Barr virus (EBV) - specific dUTPase\", \"Epstein - Barr virus - encoded dUTPase\", \"virus dUTPase\", \"dUTPase\", \"immediate early transactivator\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Find all entities of these types in the text: [\"Chemical\", \"Disease\"].\n\nOutput a JSON object.\n\nText:\nVerapamil withdrawal as a possible cause of myocardial infarction in a hypertensive woman with a normal coronary angiogram. Verapamil is an effective and relatively-safe antihypertensive drug. Serious adverse effects are uncommon and mainly have been related to the depression of cardiac contractility and conduction, especially when the drug is combined with beta-blocking agents. We report a case in which myocardial infarction coincided with the introduction of captopril and the withdrawal of verapamil in a previously asymptomatic woman with severe hypertension. Possible mechanisms that involve a verapamil-related increase in platelet and/or vascular alpha 2-adrenoreceptor affinity for catecholamines are discussed.", "role": "user" }, { "content": "{\"Chemical\": [\"captopril\", \"catecholamines\", \"verapamil\", \"Verapamil\"], \"Disease\": [\"depression\", \"myocardial infarction\", \"hypertension\", \"hypertensive\"]}", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey on Resilient Machine Learning \nChapter Title: Evaluating Classifiers Security Against Evasion Attacks \n1. Abstract of Cited Paper (BIB001): In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system at test time by carefully manipulating attack samples. In this work, we present a simple but effective gradient-based approach that can be exploited to systematically assess the security of several, widely-used classification algorithms against evasion attacks. Following a recently proposed framework for security evaluation, we simulate attack scenarios that exhibit different risk levels for the classifier by increasing the attacker's knowledge of the system and her ability to manipulate attack samples. This gives the classifier designer a better picture of the classifier performance under evasion attacks, and allows him to perform a more informed model selection (or parameter setting). We evaluate our approach on the relevant security task of malware detection in PDF files, and show that such systems can be easily evaded. We also sketch some countermeasures suggested by our analysis.\n\nLiterature Review:", "role": "user" }, { "content": "Adversarial scenario is often not considered at design time. A framework to evaluate potential performance degradation under potential attacks is proposed by Biggio et al BIB001 . The proposed framework evaluates classifier security empirically. It formalizes and generalizes the main ideas proposed in pattern classification theory and design methods. This framework is used to build a gradient-based approach BIB002 to assess the security of widely-used classification algorithms against evasion attacks. This provides the designer a better picture of the classifier performance under potential evasion attacks. The designer therefore can perform a more informed model selection (or parameter setting).", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: The virus was later found to represent the type species of a new genus Hantavirus of the family Bunyaviridae , although it was later apparent that the first hantavirus to be isolated was the shrew-borne Thottapalayam virus [19] . The categorization of hantaviruses as belonging to the family Bunyaviridae is due in part to the consistent presence of three RNA genomes that are circularized in vivo as a result of the presence of terminal complementary nucleotides that help fold the genome into a -hairpin‖ morphology, first described for the Uukuniemi phlebovirus [19, 20] . Table 1 is a list of the predominant, serologically distinct pathogenic hantaviruses. Many other named genotypes are described, but such other pathogenic forms are generally closely related to Andes or, in some cases, Sin Nombre virus. During virus maturation, the precursor form GPC is processed using a membrane -bound protease into Gn and Gc, a cleavage that occurs, and appears to be signaled, after the conserved peptide signal WAASA at the C-terminal of Gn [24] . Although the two proteins can be expressed independently through transfection, they can be retained in the wrong cellular compartment (ER or aggresome); they thus must be co-expressed to allow them stability so that the two can be assembled correctly in the Golgi [25, [27] [28] [29] . A number of activities and properties have been identified for the hantavirus envelope glycoproteins, including some features that are suspected to be involved in the pathogenicity of the disease-causing serotypes, a possibility that has engendered experimental attention. The glycoproteins are the known or presumed ligands for at least two distinct cellular receptors, the 3 integrin chain and decay accelerating factor, or DAF [30, 31] ; with gC1qR/p32 also identified as another potential entry receptor [32] . Comparisons with the tick-borne encephalitis virus E protein, led Tischler et al. to consider the Gc glycoprotein as a potential class II fusion protein, perhaps imparting fusion activity to the virion, and this hypothesis has gained support in other studies [33, 34] . Additional activities have been identified with, or claimed to be related to, Gn. For many of these studies, an underlying premise has held that there are differences between the glycoproteins of -pathogenic‖ hantaviruses relative to viruses in the genus that are dubbed to be -non-pathogenic‖. While it is true that it has not yet been possible to link Prospect Hill virus (PHV) to human disease, the absence of evidence for its pathogenicity should perhaps not be equated with the evidence of its absence. One might only consider that the level of disease (e.g., lethargy, fever, proteinuria, and azotemia) associated with infection of nonhuman primates by PHV is not significantly different from that recorded for nonhuman primate models using the known-pathogen Puumala virus (PUUV) [35, 36] . For the purpose of this discussion we will presume that apathogenic hantaviruses are indeed apathogenic. While some studies have suggested that Gn glycoproteins are directed more rapidly into the ubiquitin-proteosome pathway than are apathogenic forms, others have interpreted differences in the handling of Gn glycoproteins across hantavirus species by the ubiquitin-proteosomal system as independent of pathogenicity [37] [38] [39] . Some investigators have directed their efforts toward identifying a differential capacity, either kinetic or in absolute magnitude, in the ability of pathogenic and apathogenic hantaviruses to elicit an interferon response in cells. One premise that emerges is that apathogenic forms would tend to induce an earlier innate response that would render it more likely that the virus would be quickly cleared or rendered less competent in its replication so as to blunt any pathological response in the host [40] [41] [42] . The anti-hantavirus innate response can in some cases be attributed to viral interaction as a ligand of TLR-3, but not in others, and in endothelial cells, it appears not to require more than the viral particle itself, even when introduced in replication-incompetent form [43, 44] . Proteins and mRNAs prominently induced by hantaviruses include MxA and IFIT-1 (ISG-56) and others including some with known or suspected anti-viral activity. Those hantaviruses, often highly pathogenic strains, that fail to induce a potent antiviral response, are suspected or presumed to have a (more) potent interferon-pathway antagonism mechanism relative to other viruses, a mechanism that acts positively to prevent an effective innate response from forming, at least early in infection [42, 45] . Yet some instances are reported wherein highly pathogenic hantaviruses, such as SNV, are also able to induce expression of interferon-stimulated gene mRNAs, even very early in infection, with ISG proteins, as expected, taking longer to appear in the cell [44] . Anti-interferon activities have also been attributed to the NSs protein that may be elaborated in cells infected by serotypes that encode this protein [46] . Other investigators have examined the activities of hantavirus glycoproteins and other proteins that might themselves directly affect some aspects of the pathogenic progression associated with hantavirus infection of humans, such as vascular permeability changes. While early attempts to directly cause increases in permeability of endothelial monolayers with viral particles or viral infection were largely disappointing, hantaviruses have been identified as adversely affecting endothelial migration over substrata and in potentiating VEG-F-induced endothelial permeability [47, 48] . The shorter (50-kD) nucleocapsid or N protein is a structural component of the viral nucleocapsid, along with the genomic viral RNA segments. As an RNA-binding protein that engages the hairpin termini of the genomic segments with high affinity [49, 50] , it limits the access of the RNA to host nucleases and helps to render viral replication a closed process within the cytoplasm. It also acts as a peripheral membrane protein, as does the L protein [51] , an activity that could play a role in its presumed, but not yet demonstrated function as matrix [52] . Until recently, it had not been appreciated that N has a wide variety of other activities, some of which can be linked, not only to fundamental requirements of replication, but also to the interference with an array of the intracellular processes of the normal cell. Thus, an interaction between the amino terminus of the hantavirus N protein and the cellular protein Daxx has been proposed, with the suggestion of potential pro-apoptotic consequences [51] . N is also reported to interact with actin microfilaments, and the SUMO-1 protein [53, 54] . Using reporter-gene based assays, Connie Schmaljohn and her colleagues have reported that Hantaan virus' nucleocapsid protein has an inhibitory role in inflammatory responses mediated by NF kappa B (NF-B). The effects on NF-B expression appeared to be confined to prevention of its nuclear translocation after its attempted activation with lipopolysaccharide, LPS [55] . In the cytoplasm of infected cells, N protein can be found in cellular P bodies where it sequesters and protects 5' caps. It may locate the caps through its interaction with DCP1, a key constituent of P bodies. During hantavirus infection, the viral RNAs become concentrated in P bodies, through their interaction with N and DCP1. The N protein demonstrates preferential protection of mRNAs engineered to prematurely terminate their encoded protein in comparison to native mRNAs [56] . N protein has been increasingly linked to viral replication and translation, sometimes in previously unanticipated ways. It is among a growing family of diverse viral proteins that can serve as a nonspecific -RNA chaperone‖, an activity that should facilitate the L polymerase's access to vRNA for transcription and replication, in that it can transiently dissociate misfolded RNA structures [57] . Some of N protein's effects on translation might not immediately be recognized to be adaptive in nature. It can replace the entire EIF4F translational initiation complex, simultaneously presenting the ribosome with a replacement for the cap-binding activity of eIF 4E, binding to the 43S pre-initiation complex as does eIF 4G, while replacing the helicase activity of eIF 4A, which is presumed to be needed to dissociate higher-order RNA structure [56, 58] . These three factors normally work together to achieve translational initiation. In P bodies, N protein's ability to bind at high affinity to capped native cellular oligoribonucleotides, along with its activity in protecting capped RNAs from degradation likely facilitates the access of capped oligonucleotides for use in transcriptional initiation by L polymerase (-cap snatching‖). Trafficking of N for viral assembly: Classically, N protein in infected cells appears to be clustered or particulate in nature, with a heavy concentration at a single perinuclear location, widely considered to be the Golgi [27] . The N proteins of hantaviruses are found in association with particulate fractions, and confocal microscopy and biochemical-inhibitor studies have shown that N tracks along microtubules but not with actin filaments [52] . The ultimate destination for N, for its assembly into viral particles is the Golgi, and it traffics there via the endoplasmic reticulum-Golgi intermediate complex (ERGIC), also known as vesicular-tubular cluster [52] . A dominant negative inhibitor, dynamitin, associated with dynein-mediated transport, reduced N's accumulation in the Golgi. Later studies suggested that the specific dependence on microtubular transport is specific to Old World hantaviruses such as HTNV, but that the New World hantavirus ANDV is instead associated with actin filaments [59] . However, recent data indicates that microtubular transport is indeed utilized for the New World hantavirus SNV [60] . Hantavirus diseases of man have long been suspected of having an immunopathogenic basis in part because of their relatively long incubation period of 2-3 weeks and the observed temporal association between immunologic derangements and the first appearance of signs and symptoms of hantavirus illness. HFRS and HCPS share many clinical features, leading many investigators to consider them to be, in essence, different manifestations of a similar pathogenic process, differing mainly in the primary target organs of disease expression ( Table 2 ). The pathogenesis of hantavirus infections is the topic of a continuously-updated review in the series UpToDate [61] . By the time symptoms appear in HCPS, both strong antiviral responses, and, for the more virulent viral genotypes, viral RNA can be detected in blood plasma or nucleated blood cells respectively [63, 64] . At least three studies have correlated plasma viral RNA with disease severity for HCPS and HFRS, suggesting that the replication of the virus plays an ongoing and real-time role in viral pathogenesis [65] [66] [67] . Several hallmark pathologic changes have been identified that occur in both HFRS and HCPS. A critical feature of both is a transient (~ 1-5 days) capillary leak involving the kidney and retroperitoneal space in HFRS and the lungs in HCPS. The resulting leakage is exudative in character, with chemical composition high in protein and resembling plasma. The continued experience indicating the strong tissue tropism for endothelial cells, specifically, is among the several factors that make β3 integrin an especially attractive candidate as an important in vivo receptor for hantaviruses. It is likely that hantaviruses arrive at their target tissues through uptake by regional lymph nodes, perhaps with or within an escorting lung histiocyte. The virus seeds local endothelium, where the first few infected cells give rise, ultimately, to a primary viremia, a process that appears to take a long time for hantavirus infections [62, 63] . By the time that secondary viremia emerges, the agents of the more severe forms of HFRS and HCPS have begun to achieve sufficient mass as to induce, through PAMP-PRR interactions and other means, the expression of proinflammatory cytokines [64] . For HCPS, that expression favors the pulmonary bed and lymphoid organs, yet, for unknown reasons, spares the retroperitoneum and, in general, the kidney. In HFRS the situation is reversed, and yet it is often not appreciated that the expected preferential tissue tropism of HFRS-associated viruses and their HCPS-associated counterparts for the renal and pulmonary beds, respectively, is not as one would predict through the manifestations of the two diseases. Local elaboration of inflammatory and chemotactic mediators is considered to be a requirement for the development of systemic disease symptoms, with those abnormalities sometimes culminating in shock and death. Yet it is not hypoxemia, due to the prominent pulmonary edema, that leads to death in most fatal cases of HCPS, but rather intoxication of the heart by as-yet-undefined mediators that leads to the low cardiac output state and the associated shock syndrome [64, 65] . It is tempting to speculate that mediators produced in the lung in connection with the inflammatory infiltrate can percolate through the coronary circulation with minimal dilution in HCPS, a disadvantageous consequence of the close anatomic juxtaposition of the two organs. Thus, at least three classes of potential mechanisms, some overlapping and all certainly nonexclusive of the others, could be presumed to underlie the pathogenesis of HCPS. These include:\n\n(1) Innate immune mechanisms. The nature of interactions between hantavirus pathogen-associated molecular patterns (PAMP) with the pattern recognition receptors (PRR) of susceptible endothelial cells are beginning to be clarified. The prototypical HTNV appears to be recognized by TLR-3 [43] . Such an infection has consequences such as increased expression of HLA-DR in dendritic cells [66] and differentiation of monocytes toward dendritic cells [67] . (2) Direct viral effects. The observed correlation between viral load and disease severity leaves the possibility open that hantavirus particles or RNA can themselves have toxic effects on cells or on signaling. Some investigators have favored direct viral toxicity, acting through the inhibition of endothelial cell barrier function, as an explanation for much of the capillary leak, although there is widespread agreement that multiple mechanisms that mediate pathogenesis likely operate simultaneously in the affected patient [68] . A potentially important clue toward the mechanism by which hantavirus infections deplete blood platelets and, in some cases cause hemorrhagic manifestations, was advanced by the recent discovery that pathogenic hantaviruses are able to recruit platelets to adhere to endothelial cell surfaces, with β3 integrin used as a critical binding element [69] . (3) Pathogenic effects caused by the activities of specific viral macromolecules. We have reviewed some of the activities associated with the Gn, Gc and N, virally-encoded polypeptides in previous sections.\nQuestion: Which new genus was the virus later found to represent?", "role": "user" }, { "content": "Hantavirus of the family Bunyaviridae", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nThe new normal of structure/function studies in the era of CRISPR/Cas9\n\nPaper sections:\nIntroduction\n<p>We set out to write this editorial for all of those working in metazoan systems — especially mammalian systems where clinically relevant biochemical discoveries can convert directly to drug screening platforms and preclinical assays — but have been frustrated with tools to manipulate endogenous genes and their expression. In part of the laboratory, one might have a question that can be tackled in budding yeast, where the 'awesome power' of its molecular genetic toolbox makes structure/function analysis of the protein or protein complex under investigation so immensely satisfying. For instance, in yeast, rapid gene replacements are possible because of the twin strengths of its naturally efficient homologous recombination and its haploid/diploid life cycle [1–4]. And, of course, the yeast community has innovated tricks and tools galore; all working so well that robots now routinely do systematic analysis [5–10]. But, alas, not all fundamental biological insights, nor many of the succulent details relevant to treating disease (or otherwise improving the human condition), will be answered by studying yeast. Plus, why should the part of the laboratory working on yeast be the only ones having fun? Happily, the recent and ongoing explosion in CRISPR/Cas9-based approaches is making biochemically related studies in complex biological systems more rapid, powerful, interesting, and convincing for the investigator.</p><p>In this piece, for the sake of simplicity, we focus on the use of CRISPR/Cas9-based approaches in mammalian cells, highlighting some examples where their development brings them to the brink of yeast-like 'awesomeness' for the biochemist seeking to relate findings with purified components to the underlying cell biology. We describe an array of CRISPR/Cas9-based tools that may be used to modulate gene expression, alter epigenetic states, mutate amino acids, and visualize the location of genomic loci in real time, and we discuss current limitations of CRISPR/Cas9 in gene editing and delivery. Finally, we provide an outlook for the future of CRISPR/Cas9 in drug discovery, biomedicine, and synthetic biology.</p>\n\nRapid CRISPR/Cas9-mediated gene knockout, knockin, and replacement\n<p>The utility of CRISPR/Cas9 to edit genes in diverse cell types and organisms is well established [11–18] and has been reviewed in detail elsewhere [19–22]. Briefly, in order for gene-editing to occur, the endonuclease Cas9 must first be targeted to a specific region within the genome. This is facilitated by a single-guide RNA (sgRNA), which contains a 20-nucleotide guide sequence that matches the target DNA sequence, as well as a scaffold region for Cas9 recognition and binding. The sgRNA base-pairs with the target DNA via Watson–Crick base-pairing and guides Cas9 to the region, placing Cas9 within the close proximity of the target gene. Cas9, then, cleaves both strands of the DNA, which is repaired by one of two DNA damage repair pathways: the error-prone non-homologous end-joining (NHEJ) or the high-fidelity homology-directed repair (HDR) pathway. Both of these repair pathways can lead to a desired editing outcome.</p><p>In the error-prone NHEJ pathway, the DNA double-stranded break (DSB) is repaired by inserting or deleting nucleotides at the DNA break point and then religating the two ends together. Insertion/deletions (indels) within coding exons of genes can cause frameshift mutations that lead to premature stop codons, thereby knocking out gene expression. The efficiency of this pathway in generating gene knockouts has facilitated large genome-wide knockout screens in human cells [23,24]. Additionally, combining this pathway with inducible Cas9 systems has allowed for temporal and dose-dependent control of Cas9 activity while achieving efficient knockout of the expression of hundreds of genes [25]. Thus, candidate genes for essential processes can now rapidly be assessed and compared without worrying about the common off-target and incomplete knockdown effects that made earlier transcription knockdown-based efforts (e.g. RNAi or equivalent) inconclusive and unconvincing.</p><p>While NHEJ is used to knock out genes, HDR can be used to knock in genes or other desired DNA sequences. In this pathway, a repair template — containing a custom-designed sequence flanked by regions of homology with the target gene — recombines with the target gene locus, resulting in the insertion of the desired sequence at the location of the DNA DSB. Although virtually any custom DNA sequence can be inserted into the gene, this approach is commonly used to insert tags onto protein-coding genes, including fluorescent protein tags, small peptide tags, and affinity tags that may be used to assess protein localization, function, and interacting partners, respectively.</p><p>HDR can also be used to replace entire genes in the genome in a single step [26,27]. Whole-gene replacement is a practical way to edit genes because it allows a gene to be differentially modified several times in a single reaction. For instance, rather than making multiple modifications to a gene one-at-a-time, the entire gene can be replaced with a version that has the desired changes, such as the addition of an N- or C- terminal tag and a mutation within the gene itself.</p><p>We devised a useful gene replacement strategy utilizing CRISPR/Cas9 technology (Figure 1A) [27]. In this strategy, a gene is simultaneously and differentially replaced on two alleles in a single step, generating a cell line in which the function and localization of a protein of interest, as well as its role in cell viability, can be rapidly assessed. Biallelic gene replacement is carried out by introducing two sgRNAs (targeting the 5′- and 3′-ends of the gene) and two custom repair templates into the cell, allowing the gene to be replaced on each allele simultaneously via CRISPR/Cas9. The first allele is replaced with a wild-type gene tagged with EGFP and an auxin-inducible degron (AID), which permits its rapid degradation [28]. The second allele is replaced with a mutant gene tagged with mCherry. Sorting for EGFP- and mCherry-positive cells by FACS leads to the isolation of a cell line carrying gene replacements on each allele within 1.5–3 weeks (Figure 1B), longer (but tolerably so) than it takes for haploid yeast gene replacements. Once the cell line is generated, the wild-type protein can be rapidly degraded upon the addition of the plant hormone auxin, allowing the mutant protein to be functionally characterized in the complete absence of wild-type protein. This approach is a starkly more satisfying experimental approach for structure/function studies of virtually all essential proteins than any earlier RNAi-based knockdown/rescue approaches: it avoids the 'wind-down phenotypes' generated by the slow removal of existing protein (itself highly variable between different proteins and only rarely measured). Rather, it achieves removal of the wild-type copy of a protein to below the level of detection within minutes.</p>\n\nExpanding the CRISPR/Cas9 toolbox\n<p>In addition to editing genes, CRISPR/Cas9 can be used as a sequence-specific, DNA-binding platform to target effector proteins to genetic loci. By mutating two key residues within its endonuclease domain, Cas9 can be rendered catalytically dead while still retaining its ability to bind to target DNA sequences [29]. Catalytically dead Cas9 (dCas9) acts as a de facto DNA-binding domain and, when fused to functional effectors, can modulate the expression of protein-coding genes, mutate bases within genes, and monitor the nuclear localization of genes in real time (Figure 2).</p><p>There are now many CRISPR/Cas9-based methodologies to modify the expression of genes from their endogenous loci. For instance, dCas9 can be fused to a transcriptional activator or repressor and targeted to a specific promoter (Figure 2A) [30–34]. When targeted with an individual sgRNA, these transcriptional effectors only modestly affect gene expression; however, targeting with multiple sgRNAs across the same promoter can amplify the effect on gene expression by 100–1000-fold [32–34], making these effective tools for manipulating endogenous gene expression.</p><p>Gene expression can also be manipulated by altering the epigenetic state of the gene regulatory elements that control it. Fusing dCas9 to a chromatin-modifying enzyme and targeting it to a gene promoter or enhancer can alter its epigenetic state, leading to gene activation or silencing (Figure 2B) [35–37]. In some cases, this approach is more effective than targeting transcriptional regulators themselves [35], making this a practical option for gene expression regulation.</p><p>In addition to modulating gene expression, dCas9 can be used to edit single bases within the genome (Figure 2C). dCas9 fused to base-editing proteins, such as cytidine and adenine deaminases, can convert C to T [38] and A to G [39]. When targeted to protein-coding genes, base editors can introduce point mutations more efficiently and with far fewer undesired products (such as indels) compared with standard gene-editing methods [38]. Additionally, these base-editing tools can introduce premature stop codons that truncate proteins or knock out gene expression altogether [40], making this a versatile approach for mutating and disrupting genes within the genome.</p><p>Gene expression is often dependent on nuclear organization, and spatiotemporal dynamics in chromatin can influence gene transcription. To monitor the location of genetic elements in real time, one can fuse dCas9 to one or more fluorescent proteins, such as GFP (Figure 2D) [41]. The utility of monitoring genetic loci has led to an expansion in dCas9 imaging tools that facilitate tracking of multiple loci simultaneously [42–46]. Additionally, one can amplify fluorescent signal intensity, using the so-called SunTag, to recruit up to 24 copies of GFP to a single locus [47], allowing for long-term, continuous tracking of genetic loci in living cells.</p>\n\nChallenges and limitations\n<p>The specificity of Cas9 is determined by the sgRNA, which base-pairs to target DNA sequences via its guide sequence. Although all nucleotides in the guide sequence are involved in sequence recognition, mismatches within the sequence can be tolerated, especially if they are distal to the RNA scaffold [48]. Thus, off-target sites may be edited if they closely resemble the target sequence. However, improvements to sgRNA design rules, algorithms that predict on- and off-target rates, and functional validation data have enabled the design of more effective sgRNAs that maximize on-target activity and minimize off-target rates [49,50]. Additionally, a variety of CRISPR/Cas9 tools designed to reduce off-target rates have been implemented with success [33,51].</p><p>The delivery of CRISPR/Cas9 genes to various cell types has also proved to be a challenge. Viruses are often used to deliver genes because they can infect a wide range of cell types. However, viruses also have limited packaging capacities, and most are only slightly larger than the Cas9 gene. Many smaller Cas9 orthologs have recently been identified [11,52], and use of these orthologs in place of the Cas9 typically used (SpCas9) may make delivery of CRISPR/Cas9 genes more feasible in the future.</p>\n\nThe future is now\n<p>The ease in which CRISPR/Cas9 can be used to manipulate genes has already shown its power to rapidly dissect protein function. CRISPR/Cas9 has actually made it easier to carry out complex structure/function analysis in diverse biological systems, including in mammalian cell, tissue, and organismal studies. For instance, in a matter of weeks, one can convincingly validate the conclusions of structural (e.g. test the functional importance of a key molecular interface that one identifies in a crystal structure) and proteomic (e.g. test the functional importance of a newly identified site of glycosylation) studies in cell models. Since the tools are simple, rapid, and easy to use, the expectations of the study to include a thorough and comprehensive functional analysis have been raised. As a field, we should demand conclusive and compelling gene manipulation for ourselves and our colleagues. Such a standard would certainly take a bold step to confront the recent attention to reproducibility in peer-reviewed published studies [53].</p><p>Beyond the impact to traditional structure/function studies, genome-wide screens using CRISPR/Cas9 are being implemented. Thus far, these screens have identified thousands of proteins that support cancer cell viability and regulate drug sensitivity, to name a couple of utilities, making this a powerful general system for drug development, validation, and discovery [54–56]. CRISPR/Cas9 genetic manipulations that utilize optimized sgRNAs to knock out, knock down, and activate genes will continue to provide an even more comprehensive understanding of protein function in disease, serve as an attractive tool for drug discovery and development, and open new horizons in gene therapy.</p><p>Perhaps, the most exciting aspects of CRISPR/Cas9 technology are in areas where it goes beyond improving existing methodologies but rather facilitates entirely new areas of biology. This thinking extends to some of the most ambitious proposals for synthetic biology, including instances where massive genetic 'gymnastics' must be achieved. One such area that has attracted attention because of its potential revolutionary clinical impact is in generating organs in animals (e.g. pigs) for transplantation into human patients (so-called xenotransplantation) to eliminate the need for human donors and enable personalized genetic edits and/or additions to avoid organ rejection. Indeed, CRISPR/Cas9 has already been used to simultaneously inactivate all of the porcine retroviral elements known as PERVs [57,58] that would otherwise pose a serious safety concern for retroviral infection. Many other challenges remain for xenotransplantation efforts to advance, potentially solved through the addition of large sets of humanizing genes through the development of useful synthetic chromosomes [59]. While synthetic mammalian chromosomes must overcome many hurdles not present in yeast where their precedent has been made [60,61], it is nearly certain their development will exploit the gene manipulation powers of CRISPR/Cas9.</p><p>In closing, from vital molecular/structural studies, to pathway discovery, to true frontiers of synthetic biology, CRISPR/Cas9-based technologies are making it all more feasible, satisfying, reliable, and rapid.</p>", "role": "user" }, { "content": "Major advances in gene-editing technologies have enabled the rapid dissection of proteins in complex biological systems, facilitating biological experiments to complement biochemical studies with purified components. In this editorial, we highlight CRISPR/Cas9-based strategies to rapidly manipulate endogenous genes \\xe2\\x80\\x94 strategies that have already transformed functional studies of proteins in metazoan systems. We further describe emerging tools using a catalytically dead version of Cas9 (dCas9) that do not cleave DNA, but can alter gene expression and/or local chromatin states, edit single nucleotide bases, and permit the visualization of specific genomic loci. Looking to the not-too-distant future, CRISPR/Cas9-based methodologies promise to lead to discoveries of new biology, opening the door for bold new synthetic biology platforms.", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nEffects of the cholinomimetic SDZ ENS-163 on scopolamine-induced cognitive impairment in humans . Scopolamine-induced cognitive impairment was used in healthy men to evaluate the central nervous system activity of the new cholinomimetic SDZ ENS-163 . Eighteen subjects were treated in a crossover design with oral placebo/intravenous saline , 50 mg of oral SDZ ENS-163/intravenous saline , oral placebo/0.4 mg of intravenous scopolamine , and 50 mg of oral SDZ ENS-163/0.4 mg of intravenous scopolamine . The administration of placebo with scopolamine caused significant cognitive impairment , as assessed by the Computerized Neuropsychological Test Battery ( CNTB ) , and also decreased salivation and heart rate . In contrast , SDZ ENS-163 with saline had no effect on CNTB scores , increased salivation , and increased heart rate . Despite the observed cholinomimetic effects of SDZ ENS-163 when administered with saline , the changes in CNTB scores , heart rate , and salivation were indistinguishable between placebo/scopolamine and SDZ ENS-163/scopolamine . Thus , 50 mg of oral SDZ ENS-163 has cholinomimetic activity in normal men , but this dose is insufficient to reverse the muscarinic effects of 0.4 mg of intravenous scopolamine .", "role": "user" }, { "content": "{\"Intervention\": [\"new cholinomimetic SDZ ENS-163\", \"cholinomimetic SDZ ENS-163\", \"50 mg of oral SDZ ENS-163/0.4 mg of intravenous scopolamine\", \"oral placebo/0.4 mg of intravenous scopolamine\", \"oral placebo/intravenous saline\", \"50 mg of oral SDZ ENS-163/intravenous saline\"], \"Outcome\": [\"significant cognitive impairment\", \"decreased salivation and heart rate\", \"heart rate\", \"CNTB scores\", \"salivation\", \"cholinomimetic activity\", \"changes in CNTB scores\", \"increased heart rate\", \"muscarinic effects\", \"Computerized Neuropsychological Test Battery ( CNTB )\", \"cholinomimetic effects\", \"cognitive impairment\", \"increased salivation\"], \"Participant\": [\"Scopolamine-induced cognitive impairment was used in healthy men\"]}", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to segment blood vessels from retinal images, and segment the optic disc and optic cup from\n\nKeyphrases: retinal image segmentation images\n\nDataset descriptions:\nROSE: Retinal OCTA SEgmentation dataset (ROSE) consists of 229 OCTA images with vessel annotations at either centerline-level or pixel level.\nADAM: ADAM is organized as a half day Challenge, a Satellite Event of the ISBI 2020 conference in Iowa City, Iowa, USA. The ADAM challenge focuses on the investigation and development of algorithms associated with the diagnosis of Age-related Macular degeneration (AMD) and segmentation of lesions in fundus photos from AMD patients.\nDRIVE: The Digital Retinal Images for Vessel Extraction (DRIVE) dataset is a dataset for retinal vessel segmentation. It consists of a total of JPEG 40 color fundus images; including 7 abnormal pathology cases.\nHRF: The HRF dataset is a dataset for retinal vessel segmentation which comprises 45 images and is organized as 15 subsets. Each subset contains one healthy fundus image, one image of patient with diabetic retinopathy and one glaucoma image.\n\nOptions: A: ROSE B: ADAM C: DRIVE D: HRF", "role": "user" }, { "content": "DRIVE", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\n24(S)-hydroxycholesterol is actively eliminated from neuronal cells by ABCA1. High cholesterol turnover catalyzed by cholesterol 24-hydroxylase is essential for neural functions, especially learning. Because 24(S)-hydroxycholesterol (24-OHC), produced by 24-hydroxylase, induces apoptosis of neuronal cells, it is vital to eliminate it rapidly from cells. Here, using differentiated SH-SY5Y neuron-like cells as a model, we examined whether 24-OHC is actively eliminated via transporters induced by its accumulation. The expression of ABCA1 and ABCG1 was induced by 24-OHC, as well as TO901317 and retinoic acid, which are ligands of the nuclear receptors LXR/RXR. When the expression of ABCA1 and ABCG1 was induced, 24-OHC efflux was stimulated in the presence of high density lipoprotein (HDL), whereas apolipoprotein A-I was not an efficient acceptor. The efflux was suppressed by the addition of siRNA against ABCA1, but not by ABCG1 siRNA. To confirm the role of each transporter, we analyzed HEK293 cells stably expressing human ABCA1 or ABCG1; we clearly observed 24-OHC efflux in the presence of HDL, whereas efflux in the presence of apolipoprotein A-I was marginal. Furthermore, the treatment of primary cerebral neurons with LXR/RXR ligands suppressed the toxicity of 24-OHC. These results suggest that ABCA1 actively eliminates 24-OHC in the presence of HDL as a lipid acceptor and protects neuronal cells. This article is protected by copyright. All rights reserved.", "role": "user" }, { "content": "{\"Chemical\": [\"24(S)-hydroxycholesterol\", \"cholesterol\", \"TO901317\", \"retinoic acid\", \"24-OHC\"]}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: The COVID crisis has created mental health issues that cannot be ignored.\n\nAbstract:\nImportance This article briefly reports the experience of mental health services and the lessons learned during the coronavirus disease 2019 (COVID-19) crisis.\nIn particular, this report offers opportunities to build on experience gained in managing the COVID-19 emergency in the Departments of Mental Health and Addiction (DMHAs) in Lombardy, the wealthiest Italian region, which has approximately 10 million inhabitants.\nObservations Italy has a National Mental Health System divided into 134 DMHAs, 27 of which are in Lombardy.\nIn the 4 weeks after the epidemic started, important changes occurred in the management of DMHAs in Lombardy.\nMany challenges have occurred in the management of health services.\nIn many hospitals, entire wards, including some psychiatric wards, have been reorganized to admit patients with COVID-19, and many physicians and nurses have been diverted to wards managing patients with COVID-19.\nMost day facilities for patients with psychiatric needs have been temporarily closed, whereas in residential facilities, patients who usually are free to come and go during the day have had to be confined in the facilities with very limited or no leave.\nThese changes have produced considerable stresses on people with severe mental disorders.\nMany outpatient clinics have limited appointments to those with the most urgent cases, and home visits, a common practice in most DMHAs, have been drastically reduced with potentially detrimental consequences for patients' well-being.\nAnother potential detrimental consequence of being forced to stay at home has been an increase in the hours spent face to face with families with high amounts of conflict.\nConclusions and Relevance Departments of Mental Health need to be equipped with appropriate e-health technologies and procedures to cope with situations such as the COVID-19 pandemic.\nAdditionally, interventions are needed to mitigate the potentially harmful consequences of quarantine.\nDepartments of Mental Health should be able to assume a leadership position in the psychosocial management of disasterlike situations, and this requires the acquisition of new skills, notably how to correctly inform the population about risk, train and disseminate effective preventive and management procedures for disasters, support health personnel and rescuers, and support those experiencing bereavement.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Most day facilities for patients with psychiatric needs have been temporarily closed, whereas in residential facilities, patients who usually are free to come and go during the day have had to be confined in the facilities with very limited or no leave.\", \"These changes have produced considerable stresses on people with severe mental disorders.\", \"Conclusions and Relevance Departments of Mental Health need to be equipped with appropriate e-health technologies and procedures to cope with situations such as the COVID-19 pandemic.\"]}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: CPSF6 Defines a Conserved Capsid Interface that Modulates HIV-1 Replication\nArticle:\nAbstract:\nThe HIV-1 genome enters cells inside a shell comprised of capsid( CA) protein. Variation in CA sequence alters HIV-1 infectivity and escape from host restriction factors. However, apart from the Cyclophilin A-binding loop, CA has no known interfaces with which to interact with cellular cofactors. Here we describe a novel protein-protein interface in the N-terminal domain of HIV-1 CA, determined by X-ray crystallography, which mediates both viral restriction and host cofactor dependence. The interface is highly conserved across lentiviruses and is accessible in the context of a hexameric lattice. Mutation of the interface prevents binding to and restriction by CPSF6-358, a truncated cytosolic form of the RNA processing factor, cleavage and polyadenylation specific factor 6( CPSF6). Furthermore, mutations that prevent CPSF6 binding also relieve dependence on nuclear entry cofactors TNPO3 and RanBP2. These results suggest that the HIV-1 capsid mediates direct host cofactor interactions to facilitate viral infection.\nIntroduction:\nThe HIV-1 genome enters target cells encapsulated in a fullerene capsid cone composed of capsid( CA) protein. The role of the capsid in early events of the HIV-1 replication cycle is not known, nor is it clear exactly how long the capsid remains associated with the infectious particle, or where the capsid disassembles. Early biochemical studies led to the view that the capsid is an inert shell, required during particle assembly and target cell entry, whereupon it rapidly falls apart( ‘uncoats’) to permit reverse transcription[1],[2]. However, recent data suggest that uncoating may occur later than previously thought, either during transport of the reverse transcribing virus to the nucleus, or once the reverse transcribing virus has docked at the nuclear pore[3],[4],[5],[6],[7]. This accommodates the possibility that the capsid may facilitate transit of the core towards the nucleus by interacting with the cell's cytoskeletal transport system[5]. An intact capsid would also be expected to maintain a high stoichiometry of reverse transcriptase enzyme to viral template, which is necessary for overcoming the rate limiting steps in reverse transcription[4],[8]. Like all lentiviruses, HIV-1 is able to infect non-dividing cells, which requires the exploitation of active host cell nuclear import processes[9]. CA mutations have been identified that specifically affect nuclear entry in non-dividing cells[10],[11],[12], suggesting a link between CA and nuclear import. However, apart from the Cyclophilin( Cyp)-binding loop, there are no known interfaces through which the CA can interact with host cell cofactors. CA mutations outside of the Cyp-binding loop have been suggested to exert their effect by altering capsid stability or particle assembly. For example, it has been proposed that CA mutations that decrease the ability of HIV-1 to enter the nucleus( Q63A/Q67A) or infect non-dividing cells( A92E, G94D or T54A/N57A) do so by causing the capsid to uncoat faster or slower than wild type[10],[11],[12],[13]. However, many CA mutations that give clear infectivity defects are located on an exposed surface in the CA hexamer structure( Figure 1,[14],[15]) and therefore seem unlikely to purely affect capsid stability. Recent genome-wide screens have implicated a number of nuclear import components as HIV-1 cofactors, including the nuclear pore proteins RanBP2( also called NUP358) and NUP153 and the karyopherin TNPO3[16],[17],[18]. In each case, there is evidence that the requirement for these import cofactors map to CA[6],[19],[20],[21],[22],[23],[24],[25]. Of particular interest, a single CA mutation( N74D) has been shown to affect the sensitivity of HIV-1 to depletion of RanBP2, Nup153 and TNPO3[6],[19]. Mutation N74D arose spontaneously during passage of HIV-1 in cells expressing CPSF6-358, an artificially truncated version of cleavage and polyadenylation specific factor 6( CPSF6, also known as CF Im) that perturbs HIV-1 nuclear entry[19]. CPSF6 is a pre-mRNA processing protein that dynamically shuttles between the nucleus and the cytoplasm[26] and contains a C-terminal nuclear-targeting arginine/serine-rich( RS-) domain[27],[28] of the type bound by TNPO3[29],[30]. CPSF6 lacking this RS-domain is no longer confined to the nucleus but is also found in the cytoplasm[28]. CPSF6-358( which is truncated at position 358 and therefore lacks the C-terminal RS-domain) was also found to be cytoplasmic and restricted HIV-1 before nuclear entry[19]. It is therefore significant that the HIV-1 CA N74D mutation not only allows escape from CPSF6-358 restriction but also results in the loss of viral dependence on several cofactors involved in nuclear entry( RanBP2, Nup153 and TNPO3). Here we show that CPSF6 binds specifically to a novel protein-protein interface on the N-terminal domain of HIV-1 CA. We show that this interface is structurally and functionally conserved across lentiviruses from different genera and is accessible in the context of an intact CA hexamer. We propose that CPSF6 interacts with incoming capsid during the post-entry stages before uncoating. Structure-guided mutagenesis of this interface reveals that CA residues that mediate CPSF6 binding also mediate dependence on TNPO3 and RanBP2. Finally, addition of an ectopic nuclear localization signal( NLS) to CPSF6-358 recovers its nuclear localization and restores HIV-1 infectivity, suggesting that the functional outcome of CPSF6 interaction with HIV-1 depends on whether CPSF6 is trafficking into the nucleus or remaining in the cytosol. Together, our data reveals that HIV-1 CA possesses a previously undescribed, conserved protein-protein interface that dictates cofactor dependence. Furthermore, it suggests that HIV-1 uses CA to interact directly with host cofactors and exploit cellular nuclear import pathways.\nDiscussion:\nAlthough there is extensive experimental evidence that the HIV-1 capsid is more than a packaging device to carry viral protein and nucleic acid into the cell, no interaction interfaces other than the Cyp-binding loop have been identified on its surface. For instance, despite considerable effort the structural interface between capsid and the restriction factor TRIM5α remains incompletely characterized. Here we have described the identification of a conserved interface within the N-terminal CA domain and shown that interface mutations alter HIV-1 interaction with CPSF6 and cofactors RanBP2 and TNPO3. Previously, CA mutation N74D has been shown to escape CPSF6-358 restriction whilst simultaneously relieving dependence on nuclear transport factors such as TNPO3 and a functional nuclear pore[6],[19]. We have shown that CA residue N74 makes an essential interaction with CPSF6, both by solving the crystal structure of a CPSF6:CA complex and by showing that mutation N74D abolishes binding to CPSF6. Furthermore, mutation N74D results in a virus that has no defect in infectious titre on immortalized cells but that cannot replicate in macrophages[6]. This suggests that CPSF6 may be an important cofactor in HIV infection. Further evidence in support of CPSF6 as a cofactor is that addition of an ectopic NLS to CPSF6-358 restores both nuclear localization of CPSF6-358 and HIV-1 infectivity. However, we cannot rule out that this might be due to a reduction in the concentration of cytosolic CPSF6-358 that would otherwise prevent functional interaction of endogenous CPSF6 with CA. CPSF6 is transported into the nucleus and contains an RS-domain, which is known to interact with karyopherins like TNPO3[29],[30]. A compelling model for the role of the CPSF6 interface in HIV-1 replication is therefore that binding to CPSF6 facilitates active nuclear transport. Such a model would explain why mutation N74D results in concomitant loss of both CPSF6 interaction and dependence on TNPO3 and RanBP2; if the virus cannot bind CPSF6 then it cannot recruit TNPO3 to pass through the nuclear pore. We have further substantiated the connection between CPSF6 binding and TNPO3 and RanBP2 dependence through structure-guided mutagenesis of the CPSF6-binding interface. This has identified five CA mutations that have the same pleiotropic effects as N74D( N57A, M66F, Q67A, K70A and T107A). If CPSF6 is an HIV-1 cofactor then it would allow seemingly conflicting data that report different viral targets for TNPO3 requirement and interaction to be resolved: the requirement for TNPO3 maps to CA[23], but TNPO3 has been found to bind integrase( IN) and not CA[17]. Recruitment of TNPO3 to CA-bound CPSF6 could explain why CA determines TNPO3 requirement, while also accommodating a role for IN as the direct viral binding partner of TNPO3. In this context, it is important to note that the interaction of CPSF6313–327 with CA, whilst specific, occurs with weak affinity. The affinity of the full-length protein for assembled virions is presumably significantly higher. The low affinity we have measured may be augmented by avidity, as there are many potential CPSF6 binding sites per virion, and CPSF6 is known to be part of a heterotetrameric protein complex together with CFIm25[39]. Alternatively, the addition of other proteins such as TNPO3 may stabilize the CPSF6:CA complex. For instance, it is possible that a larger complex comprising CPSF6, CA, TNPO3 and/or IN exists inside the cell and future structural investigation of this possibility is likely to be highly informative. Recent findings suggest that HIV-1 may utilize flexible nuclear import pathways[6],[19],[20]. Redundancy in HIV-1 infection is conceptually appealing as it provides a mechanism for viral escape from host immunity and effective zoonosis. For instance, the RS-domain of CPSF6 may be recognised by more than one karyopherin. Likewise, other RS-domain containing proteins may use the CPSF6 interface. This may be helpful for the virus but it adds to the complexity of investigating cofactor dependence. In this respect, interface mutations may be particularly useful to unpick which factors operate in a shared pathway and which are redundant. The seeming interdependency of multiple host factors on a single capsid mutant, N74, suggests that they operate in a single pathway, which the virus utilizes for efficient infection. Given the host factors involved, this single pathway most likely involves nuclear import of the virus. Irrespective of the role of CPSF6 itself, the conservation and location of the CPSF6 interface, together with the effects of mutations that disrupt it, suggest that it plays an important role in HIV-1 infection. The importance of the CPSF6 interface in HIV-1 infection is supported by the fact that random drug screening recently resulted in the discovery of a drug, PF-3450074, that inhibits infection and mimics very closely the core F321 residue of CPSF6( Figure 7A)[38]. The CPSF6-binding interface on HIV-1 CA possesses several important attributes that make it an ideal antiviral drug target, in that it is highly conserved, functionally important and druggable. Since PF-3450074 occupies only a subset of the entire CPSF6-binding site, it is unlikely to be as effective a drug as one that inhibits the entire interface. Our complexed HIV-1 CAN:CPSF6313–327 crystal structure provides a molecular delineation of the CPSF6 interface that may be useful in the development of antiviral therapeutics.", "role": "user" }, { "content": "In order to infect a host cell , HIV-1 must interact with and exploit cellular cofactors . Mutations within capsid , the protein shell that surrounds the virus , have been shown to affect virus usage of these cofactors and susceptibility to host antiviral proteins . However , with the exception of the Cyclophilin A-binding loop , there is no defined protein interface on the capsid that mediates interactions with cellular proteins . Here , we describe the identification of a conserved interface on HIV-1 capsid that binds the host protein CPSF6 and determines viral dependence on nuclear transport cofactors . This data illustrates how host-virus interactions allow HIV-1 to hitch a ride into the nucleus and reveals a potential new target for antiviral drugs .", "role": "assistant" } ]

[ { "content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nTrends in pediatric and adult bicycling deaths before and after passage of a bicycle helmet law.\nAbstract 1:\nThe goals were to examine bicycle-related mortality rates in Ontario, Canada, from 1991 to 2002 among bicyclists 1 to 15 years of age and 16 years of age through adulthood and to determine the effect of legislation (introduced in October 1995 for bicyclists <18 years of age) on mortality rates.\n The average numbers of deaths per year and mortality rates per 100000 person-years for the prelegislation and postlegislation periods, and the percentage changes, were calculated for each of the 2 age groups (1-15 years and >/=16 years). Differences before and after legislation in the 2 age groups were modeled in a time series analysis.\n There were 362 bicycle-related deaths in the 12-year period (1-15 years: 107 deaths; >/=16 years: 255 deaths). For bicyclists 1 to 15 years of age, the average number of deaths per year decreased 52%, the mortality rate per 100000 person-years decreased 55%, and the time series analysis demonstrated a significant reduction in deaths after legislation. The estimated change in the number of deaths per month was -0.59 deaths per month. For bicyclists >/=16 years of age, there were only slight changes in the average number of deaths per year and the mortality rate per 100000 person-years, and the time series analysis demonstrated no significant change in deaths after legislation.\n The bicycle-related mortality rate in children 1 to 15 years of age has decreased significantly, which may be attributable in part to helmet legislation. A similar reduction for bicyclists 16 years of age through adulthood was not identified. These findings support promotion of helmet use, enforcement of the existing law, and extension of the law to adult bicyclists.\n\n\nTitle 2:\nBicycle safety helmet legislation and bicycle-related non-fatal injuries in California.\nAbstract 2:\nThe objective of this study was to determine whether the bicycle safety helmet legislation in California, enacted in 1994, was associated with statistically significant reductions in head injuries among bicyclists aged 17 years and under who were subjected to the law. The study used 44,069 patient discharge cases from all public hospitals in California, from 1991 through 2000, and a case-control design to make direct comparisons between those subjected to the law (Youth) and those who were not (Adult) across the pre- and post-legislation periods. An aggregate data analysis approach and a pooled disaggregate data fitting technique using multinomial logit models were applied. The legislation was found to be associated with a reduction of 18.2% (99% confidence interval: 11.5-24.3%) in the proportion of traumatic brain injuries (Head-TBI) among Youth bicyclists. The proportions of other head, face, and neck injuries were not significantly changed across the pre- and post-legislation periods in this age group but there was a corresponding increase of 9% (5-13%) in the proportion of all other injuries. On the other hand, there was no statistically significant change in the proportions of injury outcomes for Adult bicyclists. The youngest riders, aged 0-9 years, had the greatest decrease in the proportion of Head-TBI. The reduction was the same for motor vehicle and non-motor-vehicle-related incidents. The bicycle safety helmet legislation was associated with a decrease in the likelihood of Head-TBI for non-urban residents but not for urbanites, for males but not for females, and for Whites, Asians, and Hispanics, but not Blacks and others.\n\n\nTitle 3:\nBicycle helmet prevalence two years after the introduction of mandatory use legislation for under 18 year olds in Alberta, Canada.\nAbstract 3:\nTo determine changes in helmet use in cyclists following the introduction of a bicycle helmet law for children under age 18.\n Cyclists were observed by two independent observers from July to August 2004 (post-legislation) in Edmonton, Alberta. The data were compared with a similar survey completed at the same locations and days in July to August 2000 (pre-legislation). Data were collected for 271 cyclists in 2004 and 699 cyclists in 2000.\n The overall prevalence of helmet use increased from 43% (95% CI 39 to 47%) in 2000 to 53% (95% CI 47 to 59%) in 2004. Helmet use increased in those under 18, but did not change in those 18 and older. In the cluster adjusted multivariate Poisson regression model, the prevalence of helmet use significantly increased for those under age 18 (adjusted prevalence ratio (APR) 3.69, 95% CI 2.65 to 5.14), but not for those 18 years and older (APR 1.17, 95% CI 0.95 to 1.43).\n Extension of legislation to all age groups should be considered.\n\n\nTitle 4:\nPolice enforcement as part of a comprehensive bicycle helmet program.\nAbstract 4:\nBicycle-related head injuries cause >150 deaths and 45 000 nonfatal injuries among children in the United States annually. Although bicycle helmets are highly effective against head injury, only 24% of US children regularly wear one. Georgia mandated bicycle helmet use for children, effective July 1993. During that summer, 1 rural Georgia community passed an ordinance instructing police officers to impound the bicycle of any unhelmeted child. We evaluated the effect of active police enforcement of this ordinance, combined with a helmet giveaway and education program.\n During April 1997, approximately 580 children in kindergarten through grade 7 received free helmets, fitting instructions, and safety education. Police then began impounding bicycles of unhelmeted children. We conducted an observational study, unobtrusively observing helmet use just before helmet distribution, several times during the next 5 months, and once 2 years later.\n Before the program began, none of 97 observed riders wore a helmet. During the next 5 months, helmet use among 358 observed children averaged 45% (range: 30%-71%), a significant increase in all race and gender groups. In contrast, adult use did not change significantly. Police impounded 167 bicycles during the study, an average of 1 per day. Two years after program initiation, 21 of 39 child riders (54%) were observed wearing a helmet.\n Without enforcement, the state and local laws did not prompt helmet use in this community, yet active police enforcement, coupled with helmet giveaways and education, was effective and lasting.\n\n\nTitle 5:\nImpact of mandatory helmet legislation on bicycle-related head injuries in children: a population-based study.\nAbstract 5:\nChildhood bicycle-related head injuries can be prevented through the use of helmets. Although helmet legislation has proved to be a successful strategy for the adoption of helmets, its effect on the rates of head injury is uncertain. In Canada, 4 provinces have such legislation. The objective of this study was to measure the impact of helmet legislation on bicycle-related head injuries in Canadian children.\n Routinely collected data from the Canadian Institute for Health Information identified all Canadian children (5-19 years) who were hospitalized for bicycling-related injuries from 1994-1998. Children were categorized as head or other injury on the basis of International Classification of Diseases, Ninth Revision, codes. Rates of head injuries and other injuries were compared over time in provinces that adopted legislation and those that did not.\n Of the 9650 children who were hospitalized because of a bicycle-related injury, 3426 sustained injuries to the head and face and the remaining 6224 had other injuries. The bicycle-related head injury rate declined significantly (45% reduction) in provinces where legislation had been adopted compared with provinces and territories that did not adopt legislation (27% reduction).\n This country-wide study compared rates of head injury in regions with and without mandatory helmet legislation. Comparing head injuries with other non-head-injured children controlled for potential differences in children's cycling habits. The strong protective association between helmet legislation and head injuries supports the adoption of helmet legislation as an effective tool in the prevention of childhood bicycle-related head injuries.\n\n\nTitle 6:\nTrends in helmet use and head injuries in San Diego County: the effect of bicycle helmet legislation.\nAbstract 6:\nThe purpose of this study is to evaluate the effect of California's bicycle helmet law on bicycle-related head injuries in San Diego County with a year 2000 population of approximately 3 million people. The study design is an ecological trend design based on observational data from a Trauma Registry. Outcome measures include helmet use compliance, site/severity of injury and abbreviated injury scale (AIS). There were 1116 bicycle trauma patients recorded in the San Diego County Trauma Registry between 1992 and 1996. The percentages of pre-law and post-law helmet use were 13.2 and 31.7%, respectively. Over the whole study period, the overall helmet use increased by an average of 43% per year with an averaged 84% rate increase in helmet use among children. Only 16.1% of patients with serious head injury used helmets, compared to 28.2% in those who did not have serious head injury. The odds ratio of helmet use against serious head injuries is 0.43 (95% CI 0.28-0.66) after adjusting for age, ethnicity and time. The p-values for comparing pre- and post-legislation serious head injury rates are p=0.764, 0.4 and 0.194 for the overall, adult and child populations, respectively. Helmet legislation increased helmet use in the targeted child population and the effect was carried over to the adult population. Helmet use has a protective effect against serious head injury. Probably due to several of its limitations, the current study did not confirm that helmet legislation alone significantly reduced head injury rates in San Diego County during the study period.", "role": "user" }, { "content": "Bicycle helmet legislation appears to be effective in increasing helmet use and decreasing head injury rates in the populations for which it is implemented. However, there are very few high quality evaluative studies that measure these outcomes, and none that reported data on possible declines in bicycle use.", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nTemplate-matching methods for visual tracking have gained popularity recently due to their good performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking accuracy still far from state-of-the-art. In this paper, we propose a dynamic memory network to adapt the template to the target's appearance variations during tracking. The reading and writing process of the external memory is controlled by an LSTM network with the search feature map as input. A spatial attention mechanism is applied to concentrate the LSTM input on the potential target as the location of the target is at first unknown. To prevent aggressive model adaptivity, we apply gated residual template learning to control the amount of retrieved memory that is used to combine with the initial template. In order to alleviate the drift problem, we also design a \"negative\" memory unit that stores templates for distractors, which are used to cancel out wrong responses from the object template. To further boost the tracking performance, an auxiliary classification loss is added after the feature extractor part. Unlike tracking-by-detection methods where the object's information is maintained by the weight parameters of neural networks, which requires expensive online fine-tuning to be adaptable, our tracker runs completely feed-forward and adapts to the target's appearance changes by updating the external memory. Moreover, the capacity of our model is not determined by the network size as with other trackers --- the capacity can be easily enlarged as the memory requirements of a task increase, which is favorable for memorizing long-term object information. Extensive experiments on the OTB and VOT datasets demonstrate that our trackers perform favorably against state-of-the-art tracking methods while retaining real-time speed.\n\nCited Abstract(s):\n[1]: We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking groundtruths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify target in each domain. We train each domain in the network iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance in existing tracking benchmarks.\n\n[2]: Abstract Recently, deep learning has achieved great success in visual tracking. The goal of this paper is to review the state-of-the-art tracking methods based on deep learning. First, we introduce the background of deep visual tracking, including the fundamental concepts of visual tracking and related deep learning algorithms. Second, we categorize the existing deep-learning-based trackers into three classes according to network structure, network function and network training. For each categorize, we explain its analysis of the network perspective and analyze papers in different categories. Then, we conduct extensive experiments to compare the representative methods on the popular OTB-100, TC-128 and VOT2015 benchmarks. Based on our observations, we conclude that: (1) The usage of the convolutional neural network (CNN) model could significantly improve the tracking performance. (2) The trackers using the convolutional neural network (CNN) model to distinguish the tracked object from its surrounding background could get more accurate results, while using the CNN model for template matching is usually faster. (3) The trackers with deep features perform much better than those with low-level hand-crafted features. (4) Deep features from different convolutional layers have different characteristics and the effective combination of them usually results in a more robust tracker. (5) The deep visual trackers using end-to-end networks usually perform better than the trackers merely using feature extraction networks. (6) For visual tracking, the most suitable network training method is to per-train networks with video information and online fine-tune them with subsequent observations. Finally, we summarize our manuscript and highlight our insights, and point out the further trends for deep visual tracking.\n\n[3]: We propose an extremely simple but effective regularization technique of convolutional neural networks (CNNs), referred to as BranchOut, for online ensemble tracking. Our algorithm employs a CNN for target representation, which has a common convolutional layers but has multiple branches of fully connected layers. For better regularization, a subset of branches in the CNN are selected randomly for online learning whenever target appearance models need to be updated. Each branch may have a different number of layers to maintain variable abstraction levels of target appearances. BranchOut with multi-level target representation allows us to learn robust target appearance models with diversity and handle various challenges in visual tracking problem effectively. The proposed algorithm is evaluated in standard tracking benchmarks and shows the state-of-the-art performance even without additional pretraining on external tracking sequences.\n\n[4]: We propose a new approach for general object tracking with fully convolutional neural network. Instead of treating convolutional neural network (CNN) as a black-box feature extractor, we conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet. The discoveries motivate the design of our tracking system. It is found that convolutional layers in different levels characterize the target from different perspectives. A top layer encodes more semantic features and serves as a category detector, while a lower layer carries more discriminative information and can better separate the target from distracters with similar appearance. Both layers are jointly used with a switch mechanism during tracking. It is also found that for a tracking target, only a subset of neurons are relevant. A feature map selection method is developed to remove noisy and irrelevant feature maps, which can reduce computation redundancy and improve tracking accuracy. Extensive evaluation on the widely used tracking benchmark [36] shows that the proposed tacker outperforms the state-of-the-art significantly.\n\n[5]: Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different \"thinned\" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.", "role": "user" }, { "content": "With the widespread use of CNNs in the computer vision community, many methods [2] have applied CNNs as the classifier to localize the target. [4] uses two fully convolutional neural networks to estimate the target's bounding box, including a GNet that captures category information and an SNet that classifies the target from the background. [1] presents a multi-domain learning framework to learn the shared representation of objects from different sequences. Motived by Dropout [2]2 , BranchOut [3] adopts multiple branches of fully connected layers, from which a random subset are selected for training, which regularizes the neural networks to avoid overfitting. Unlike these tracking-by-detection algorithms, which need costly stochastic gradient decent (SGD) updating, our method runs completely feed-forward and adapts to the object's appearance variations through a memory writing process, thus achieving real-time performance.", "role": "assistant" } ]

[ { "content": "Based on the dataset descriptions below, which datasets would be suitable for the following research question? Your response should be a JSON array.\n\nQuestion: I want to learn reciprocal feature representations from multiple, heterogenous input sources.\n\nKeywords: semantic video analysis rgb optical flow\n\nDataset descriptions:\nFlightmare Simulator: Flightmare is composed of two main components: a configurable rendering engine built on Unity and a flexible physics engine for dynamics simulation. Those two components are totally decoupled and can run independently from each other.\nMPII: The MPII Human Pose Dataset for single person pose estimation is composed of about 25K images of which 15K are training samples, 3K are validation samples and 7K are testing samples (which labels are withheld by the authors). The images are taken from YouTube videos covering 410 different human activities and the poses are manually annotated with up to 16 body joints.\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).\nRDD-2020: The Road Damage Dataset 2020 (RDD-2020) Secondly is a large-scale heterogeneous dataset comprising 26620 images collected from multiple countries using smartphones. The images are collected from roads in India, Japan and the Czech Republic.\nHMDB51: The HMDB51 dataset is a large collection of realistic videos from various sources, including movies and web videos. The dataset is composed of 6,766 video clips from 51 action categories (such as “jump”, “kiss” and “laugh”), with each category containing at least 101 clips.\nSNIPS: The SNIPS Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity: SearchCreativeWork (e.g. Find me the I, Robot television show), GetWeather (e.g.\n\nOptions: A: Flightmare Simulator B: MPII C: UCF101 D: RDD-2020 E: HMDB51 F: SNIPS", "role": "user" }, { "content": "[\"MPII\", \"UCF101\", \"HMDB51\"]", "role": "assistant" } ]

[ { "content": "Read the following paper excerpts and answer the question. Output a JSON object with \"answer\" and \"evidence\" fields. The answer must be extracted directly from the paper text.\n\nIf the question cannot be answered from the given text, respond with \"null\".\n\nPaper: Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models\n\nAs deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks (RNNs), state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining an RNN with a hidden Markov model (HMM), a simpler and more transparent model. We explore various combinations of RNNs and HMMs: an HMM trained on LSTM states; a hybrid model where an HMM is trained first, then a small LSTM is given HMM state distributions and trained to fill in gaps in the HMM's performance; and a jointly trained hybrid model. We find that the LSTM and HMM learn complementary information about the features in the text.\n\nIntroduction\nFollowing the recent progress in deep learning, researchers and practitioners of machine learning are recognizing the importance of understanding and interpreting what goes on inside these black box models. Recurrent neural networks have recently revolutionized speech recognition and translation, and these powerful models could be very useful in other applications involving sequential data. However, adoption has been slow in applications such as health care, where practitioners are reluctant to let an opaque expert system make crucial decisions. If we can make the inner workings of RNNs more interpretable, more applications can benefit from their power.\nThere are several aspects of what makes a model or algorithm understandable to humans. One aspect is model complexity or parsimony. Another aspect is the ability to trace back from a prediction or model component to particularly influential features in the data BIBREF0 BIBREF1 . This could be useful for understanding mistakes made by neural networks, which have human-level performance most of the time, but can perform very poorly on seemingly easy cases. For instance, convolutional networks can misclassify adversarial examples with very high confidence BIBREF2 , and made headlines in 2015 when the image tagging algorithm in Google Photos mislabeled African Americans as gorillas. It's reasonable to expect recurrent networks to fail in similar ways as well. It would thus be useful to have more visibility into where these sorts of errors come from, i.e. which groups of features contribute to such flawed predictions.\nSeveral promising approaches to interpreting RNNs have been developed recently. BIBREF3 have approached this by using gradient boosting trees to predict LSTM output probabilities and explain which features played a part in the prediction. They do not model the internal structure of the LSTM, but instead approximate the entire architecture as a black box. BIBREF4 showed that in LSTM language models, around 10% of the memory state dimensions can be interpreted with the naked eye by color-coding the text data with the state values; some of them track quotes, brackets and other clearly identifiable aspects of the text. Building on these results, we take a somewhat more systematic approach to looking for interpretable hidden state dimensions, by using decision trees to predict individual hidden state dimensions (Figure 2 ). We visualize the overall dynamics of the hidden states by coloring the training data with the k-means clusters on the state vectors (Figures 3 , 3 ).\nWe explore several methods for building interpretable models by combining LSTMs and HMMs. The existing body of literature mostly focuses on methods that specifically train the RNN to predict HMM states BIBREF5 or posteriors BIBREF6 , referred to as hybrid or tandem methods respectively. We first investigate an approach that does not require the RNN to be modified in order to make it understandable, as the interpretation happens after the fact. Here, we model the big picture of the state changes in the LSTM, by extracting the hidden states and approximating them with a continuous emission hidden Markov model (HMM). We then take the reverse approach where the HMM state probabilities are added to the output layer of the LSTM (see Figure 1 ). The LSTM model can then make use of the information from the HMM, and fill in the gaps when the HMM is not performing well, resulting in an LSTM with a smaller number of hidden state dimensions that could be interpreted individually (Figures 3 , 3 ).\n\nMethods\nWe compare a hybrid HMM-LSTM approach with a continuous emission HMM (trained on the hidden states of a 2-layer LSTM), and a discrete emission HMM (trained directly on data).\n\nLSTM models\nWe use a character-level LSTM with 1 layer and no dropout, based on the Element-Research library. We train the LSTM for 10 epochs, starting with a learning rate of 1, where the learning rate is halved whenever $\\exp (-l_t) > \\exp (-l_{t-1}) + 1$ , where $l_t$ is the log likelihood score at epoch $t$ . The $L_2$ -norm of the parameter gradient vector is clipped at a threshold of 5.\n\nHidden Markov models\nThe HMM training procedure is as follows:\nInitialization of HMM hidden states:\n(Discrete HMM) Random multinomial draw for each time step (i.i.d. across time steps).\n(Continuous HMM) K-means clusters fit on LSTM states, to speed up convergence relative to random initialization.\nAt each iteration:\nSample states using Forward Filtering Backwards Sampling algorithm (FFBS, BIBREF7 ).\nSample transition parameters from a Multinomial-Dirichlet posterior. Let $n_{ij}$ be the number of transitions from state $i$ to state $j$ . Then the posterior distribution of the $i$ -th row of transition matrix $T$ (corresponding to transitions from state $i$ ) is: $T_i \\sim \\text{Mult}(n_{ij} | T_i) \\text{Dir}(T_i | \\alpha )$ \nwhere $\\alpha $ is the Dirichlet hyperparameter.\n(Continuous HMM) Sample multivariate normal emission parameters from Normal-Inverse-Wishart posterior for state $i$ : $ \\mu _i, \\Sigma _i \\sim N(y|\\mu _i, \\Sigma _i) N(\\mu _i |0, \\Sigma _i) \\text{IW}(\\Sigma _i) $ \n(Discrete HMM) Sample the emission parameters from a Multinomial-Dirichlet posterior.\nEvaluation:\nWe evaluate the methods on how well they predict the next observation in the validation set. For the HMM models, we do a forward pass on the validation set (no backward pass unlike the full FFBS), and compute the HMM state distribution vector $p_t$ for each time step $t$ . Then we compute the predictive likelihood for the next observation as follows: $ P(y_{t+1} | p_t) =\\sum _{x_t=1}^n \\sum _{x_{t+1}=1}^n p_{tx_t} \\cdot T_{x_t, x_{t+1}} \\cdot P(y_{t+1} | x_{t+1})$ \nwhere $n$ is the number of hidden states in the HMM.\n\nHybrid models\nOur main hybrid model is put together sequentially, as shown in Figure 1 . We first run the discrete HMM on the data, outputting the hidden state distributions obtained by the HMM's forward pass, and then add this information to the architecture in parallel with a 1-layer LSTM. The linear layer between the LSTM and the prediction layer is augmented with an extra column for each HMM state. The LSTM component of this architecture can be smaller than a standalone LSTM, since it only needs to fill in the gaps in the HMM's predictions. The HMM is written in Python, and the rest of the architecture is in Torch.\nWe also build a joint hybrid model, where the LSTM and HMM are simultaneously trained in Torch. We implemented an HMM Torch module, optimized using stochastic gradient descent rather than FFBS. Similarly to the sequential hybrid model, we concatenate the LSTM outputs with the HMM state probabilities.\n\nExperiments\nWe test the models on several text data sets on the character level: the Penn Tree Bank (5M characters), and two data sets used by BIBREF4 , Tiny Shakespeare (1M characters) and Linux Kernel (5M characters). We chose $k=20$ for the continuous HMM based on a PCA analysis of the LSTM states, as the first 20 components captured almost all the variance.\nTable 1 shows the predictive log likelihood of the next text character for each method. On all text data sets, the hybrid algorithm performs a bit better than the standalone LSTM with the same LSTM state dimension. This effect gets smaller as we increase the LSTM size and the HMM makes less difference to the prediction (though it can still make a difference in terms of interpretability). The hybrid algorithm with 20 HMM states does better than the one with 10 HMM states. The joint hybrid algorithm outperforms the sequential hybrid on Shakespeare data, but does worse on PTB and Linux data, which suggests that the joint hybrid is more helpful for smaller data sets. The joint hybrid is an order of magnitude slower than the sequential hybrid, as the SGD-based HMM is slower to train than the FFBS-based HMM.\nWe interpret the HMM and LSTM states in the hybrid algorithm with 10 LSTM state dimensions and 10 HMM states in Figures 3 and 3 , showing which features are identified by the HMM and LSTM components. In Figures 3 and 3 , we color-code the training data with the 10 HMM states. In Figures 3 and 3 , we apply k-means clustering to the LSTM state vectors, and color-code the training data with the clusters. The HMM and LSTM states pick up on spaces, indentation, and special characters in the data (such as comment symbols in Linux data). We see some examples where the HMM and LSTM complement each other, such as learning different things about spaces and comments on Linux data, or punctuation on the Shakespeare data. In Figure 2 , we see that some individual LSTM hidden state dimensions identify similar features, such as comment symbols in the Linux data.\n\nConclusion and future work\nHybrid HMM-RNN approaches combine the interpretability of HMMs with the predictive power of RNNs. Sometimes, a small hybrid model can perform better than a standalone LSTM of the same size. We use visualizations to show how the LSTM and HMM components of the hybrid algorithm complement each other in terms of features learned in the data.\n\nFigure 1: Hybrid HMM-LSTM algorithms (the dashed blocks indicate the components trained using SGD in Torch).\n\nTable 1: Predictive loglikelihood (LL) comparison, sorted by validation set performance.\n\nFigure 2: Visualizing HMM and LSTM states on Linux data for the hybrid with 10 LSTM state dimensions and 10 HMM states. The HMM and LSTM components learn some complementary features in the text related to spaces and comments.\n\nFigure 3: Decision tree predicting an individual hidden state dimension of the hybrid algorithm based on the preceding characters on the Linux data. Nodes with uninformative splits are represented with . . . .\n\nQuestion: Which methods do the authors use to reach the conclusion that LSTMs and HMMs learn complementary information?", "role": "user" }, { "content": "{\"answer\": [\"decision trees to predict individual hidden state dimensions\", \"apply k-means clustering to the LSTM state vectors, and color-code the training data with the clusters\"], \"evidence\": [\"Several promising approaches to interpreting RNNs have been developed recently. BIBREF3 have approached this by using gradient boosting trees to predict LSTM output probabilities and explain which features played a part in the prediction. They do not model the internal structure of the LSTM, but instead approximate the entire architecture as a black box. BIBREF4 showed that in LSTM language models, around 10% of the memory state dimensions can be interpreted with the naked eye by color-coding the text data with the state values; some of them track quotes, brackets and other clearly identifiable aspects of the text. Building on these results, we take a somewhat more systematic approach to looking for interpretable hidden state dimensions, by using decision trees to predict individual hidden state dimensions (Figure 2 ). We visualize the overall dynamics of the hidden states by coloring the training data with the k-means clusters on the state vectors (Figures 3 , 3 ).\", \"We interpret the HMM and LSTM states in the hybrid algorithm with 10 LSTM state dimensions and 10 HMM states in Figures 3 and 3 , showing which features are identified by the HMM and LSTM components. In Figures 3 and 3 , we color-code the training data with the 10 HMM states. In Figures 3 and 3 , we apply k-means clustering to the LSTM state vectors, and color-code the training data with the clusters. The HMM and LSTM states pick up on spaces, indentation, and special characters in the data (such as comment symbols in Linux data). We see some examples where the HMM and LSTM complement each other, such as learning different things about spaces and comments on Linux data, or punctuation on the Shakespeare data. In Figure 2 , we see that some individual LSTM hidden state dimensions identify similar features, such as comment symbols in the Linux data.\"]}", "role": "assistant" } ]

[ { "content": "Read the following paper excerpts and answer the question. Output a JSON object with \"answer\" and \"evidence\" fields. The answer must be extracted directly from the paper text.\n\nIf the question cannot be answered from the given text, respond with \"null\".\n\nPaper: The Wiki Music dataset: A tool for computational analysis of popular music\n\nIs it possible use algorithms to find trends in the history of popular music? And is it possible to predict the characteristics of future music genres? In order to answer these questions, we produced a hand-crafted dataset with the intent to put together features about style, psychology, sociology and typology, annotated by music genre and indexed by time and decade. We collected a list of popular genres by decade from Wikipedia and scored music genres based on Wikipedia descriptions. Using statistical and machine learning techniques, we find trends in the musical preferences and use time series forecasting to evaluate the prediction of future music genres.\n\nExperiments\nWhat are the tendencies that confirm or disconfirm previous findings? We noticed very interesting remarks just from the distributions of the features, reported in figure FIGREF11.\nWe can see that most of the popular music genres have a novelty score between 0.5 and 0.65, which is medium-high. This confirms the findings of previous work about the optimal level of innovation and acceptance. It is interesting to note that almost all the popular genres come from an urban context, where the connections between communities are more likely to create innovations. Moreover, we can see that the distribution of mainstream media is bi-modal: this means that an important percentage of genres are popularized by means of underground or new media. This happened many times in music history, from the the free radios to the web of the user-generated content. Crucially, popular music genres strongly tend to be perceived as technically virtuous.\nWhy the sound changed from acoustic to synthetic during the last century? To answer this question we used a correlation analysis with the sound feature as target. It emerged that the change towards sampled and synthetic sound is correlated to dancing, to intensity/aggressiveness, to a larger drug usage and to a large variety of infleunces, while it is negatively correlated to large bands and mellow tones. In summary a more synthetic sound allowed a more intense and danceable music, reducing the number of musicians (in other words reducing costs for the industry).\nHow the music taste of the audience of popular music changed in the last century? The trend lines of the MUSIC model features, reported in figure FIGREF12, reveal that audiences wanted products more and more contemporary, intense and a little bit novel or sophisticated, but less and less mellow and (surprisingly) unpretentious. In other words, the audiences of popular music are getting more demanding as the quality and variety of the music products increases.\nIs it possible to predict future genres by means of the genre scale? To answer this question we used time series forecasting. In particular, we exploited all the features in the years from 1900 to 2010 to train a predictive model of the scores from 2011 to 2018. As the year of the genre label is arbitrary, predicted scores and labels can be not aligned, thus MAE or RSME are not suitable evaluation metrics. As evaluation metric we defined average accuracy as $a=\\frac{\\sum count(|l-h|<0.1)}{count(t)} $, where the label (l) and the prediction (h) can be anywhere within the year serie (t). Table TABREF13, shows the results of the prediction of genre scale for the years 2011 to 2018 with different algorithms: linear regression (LR), Support Vector Machine (SVM), multi layer perceptron (MPL), nearest neighbors (IBk), and a meta classifier (stacking) with SVM+MLP+IBk.\nThe results reveal that the forecasting of music genres is a non-linear problem, that IBk predicts the closest sequence to the annotated one and that a meta classifier with nearest neighborsBIBREF22 is the most accurate in the prediction. Deep Learning algorithms does not perform well in this case because the dataset is not large enough. Last remark: feature reduction (from 41 to 14) does not affect the results obtained with IBk and meta classifiers, indicating that there is no curse of dimensionality.\n\nFig. 2. Distributions of some of the features annotated in the dataset.\n\nQuestion: What trends are found in musical preferences?", "role": "user" }, { "content": "{\"answer\": [\"audiences wanted products more and more contemporary, intense and a little bit novel or sophisticated, but less and less mellow and (surprisingly) unpretentious\"], \"evidence\": [\"How the music taste of the audience of popular music changed in the last century? The trend lines of the MUSIC model features, reported in figure FIGREF12, reveal that audiences wanted products more and more contemporary, intense and a little bit novel or sophisticated, but less and less mellow and (surprisingly) unpretentious. In other words, the audiences of popular music are getting more demanding as the quality and variety of the music products increases.\"]}", "role": "assistant" } ]

[ { "content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: SmallfilterstripessoakedwithsaturatedDiIwereimplantedintotheefferentfiberbundlenearthefloorplateorintotheascendingordescendingafferentsinthealarplate[42].", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Identify relationships between chemical compounds and genes in this abstract. Use only these relation types: ['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\nFormat your output as a JSON array with entries like [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"].\n\nAbstract:\nIron overload inhibits osteoblast biological activity through oxidative stress. Iron overload has recently been connected with bone mineral density in osteoporosis. However, to date, the effect of iron overload on osteoblasts remains poorly understood. The purpose of this study is to examine osteoblast biological activity under iron overload. The osteoblast cells (hFOB1.19) were cultured in a medium supplemented with different concentrations (50, 100, and 200   μM) of ferric ammonium citrate as a donor of ferric ion. Intracellular iron was measured with a confocal laser scanning microscope. Reactive oxygen species (ROS) were detected by 2,7-dichlorofluorescin diacetate fluorophotometry. Osteoblast biological activities were evaluated by measuring the activity of alkaline phosphatase (ALP) and mineralization function. Results indicated that iron overload could consequently increase intracellular iron concentration and intracellular ROS levels in a concentration-dependent manner. Additionally, ALP activity was suppressed, and a decline in the number of mineralized nodules was observed in in vitro cultured osteoblast cells. According to these results, it seems that iron overload probably inhibits osteoblast function through higher oxidative stress following increased intracellular iron concentrations.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nProphylactic amnioinfusion in pregnancies complicated by oligohydramnios : a prospective study . Prophylactic amnioinfusion was assessed in term and post-dates pregnancies with decreased amniotic fluid volume . Subjects were randomly assigned to one of three groups : amnioinfusion with warmed saline solution , room-temperature saline , or control . Patients receiving prophylactic amnioinfusion had a significant decrease in both the frequency and severity of variable decelerations in the first stage of labor ( P = .006 ) and in the average total number of variable decelerations in the first and second stages of labor ( P = .01 ) compared with controls . There was no observed effect on newborn serum electrolyte levels with amnioinfusion , nor was there any apparent benefit of infusion of warmed saline compared with room-temperature saline . In contrast to premature gestations with oligohydramnios , prophylactic amnioinfusion was not associated with a significant improvement in mean umbilical arterial and venous pH or a significant decrease in cesarean delivery for fetal distress ( P = .09 ) . This is perhaps because the term fetus has an enhanced ability to tolerate recurrent episodes of heart rate decelerations without demonstrating the rapid metabolic changes seen in the premature fetus .", "role": "user" }, { "content": "{\"Intervention\": [\"warmed saline solution\", \"control\", \"room-temperature saline\", \"amnioinfusion\"], \"Outcome\": [\"heart rate decelerations\", \"cesarean delivery for fetal distress\", \"mean umbilical arterial and venous pH\", \"frequency and severity of variable decelerations in the first stage of labor\", \"significant decrease\", \"newborn serum electrolyte levels\"], \"Participant\": [\"Prophylactic amnioinfusion in pregnancies complicated by oligohydramnios :\", \"term and post-dates pregnancies with decreased amniotic fluid volume .\"]}", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nBrief report : mediation of treatment effect in a communication intervention for pre-school children with autism . Tests of mediation in treatment trials can illuminate processes of change and suggest causal influences in development . We conducted a mediation analysis of a previously published randomised controlled trial of parent-mediated communication-focused treatment for autism against ordinary care , with 28 children aged 2-5 years ( Aldred et al . in J Child Psychol Psychiatr 45:1-11 , 2004 ) . The hypothesised mediating process , targeted by the intervention , was an increase in parental synchronous response within parent-child interaction . The results showed partial mediation , with change in synchrony accounting for 34 % of the positive intervention effect on autism symptomatology ( Autism Diagnostic Observation Schedule communication and social domain algorithm ) ; the result was confirmed by bootstrap estimation . Improved parental synchronous response to child communication can alter short-term autism symptom outcome with targeted therapy .", "role": "user" }, { "content": "{\"Intervention\": [\"parent-mediated communication-focused treatment\"], \"Outcome\": [], \"Participant\": [\"pre-school children with autism .\"]}", "role": "assistant" } ]

[ { "content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What is the role of anhedonia in coronary disease patients?\nContext: Reduced positive affect and depression/anxiety were associated with poor prognosis, but reduced positive affect was the only independent predictor of events. The incidence of death/MI in adequate versus reduced positive affect patients was 4% (29/663) vs. 11% (23/211); HR = 2.55 (95% CI 1.46-4.34, P = 0.001), adjusting for clinical variables. Reduced positive affect and diabetes were independent prognostic factors, and patients with one (HR = 2.84, 95% CI 1.58-5.10) or both (HR = 5.61, 95% CI 2.25-13.99) of these factors had a higher risk when compared with nondiabetic patients with adequate positive affect, P < or = 0.003.\nReduced positive affect independently predicted death/MI following stent implantation, and improved risk stratification above and beyond diabetes.\nReduced positive affect (anhedonia) predicts major clinical events following implantation of coronary-artery stents.\nt follow-up, there were 176 clinical events (36 deaths, 8 MIs, 58 ACS, 55 hospital readmissions, 19 heart failures). Dimensional anhedonia and depression were associated with poor prognosis, but anhedonia was the only predictor of severe cardiac events and clinical events after adjusting for demographic and clinical variables.\nContrary to depression, categorical anhedonia (PAS >23) was an independent and significant predictor of severe cardiac events after adjusting for clinical variables.\nThe incidence of death/MI in hedonics vs anhedonics was 11.1% vs 22.1% (hazard ratio = 2.18; 95% confidence interval, 1.11-4.26).\nDimensional and categorical anhedonias predicted independently severe cardiac events and clinical events after ACS.\nOnly depressive symptoms of fatigue-sadness predicted prognosis in univariate (hazard ratio [HR]=1.8, 95% CI 1.1-3.0, P=.025) and multivariate analysis (HR=1.8, 95% CI 1.1-2.9, P=.025). Symptoms of anhedonia (HR=1.6, 95% CI 0.9-2.8, P=.102) and depressive cognitions (HR=1.3, 95% CI 0.7-2.2, P=.402) did not.\nControlling for sex, age, and medical covariates, anhedonia (adjusted hazard ratio, 1.58; 95% confidence interval, 1.16-2.14; P < .01) was a significant predictor of combined MACE and ACM, but depressed mood was not.\nAnhedonia continued to significantly predict outcomes (P < .05) when additionally controlling for MDE diagnosis or depressive symptom severity.\nAnhedonia identifies risk of MACE and ACM beyond that of established medical prognostic indicators, including MDE and depressive symptom severity.\nThe incidence of mortality in anhedonic patients was 22.7% (65/286) vs. 13.2% (121/920) in non-anhedonic patients (HR = 1.66, 95% CI [1.19-2.32], p = 0.003).\nCumulative hazard functions were significantly different for anhedonic vs. non-anhedonic patients (log-rank χ(2) = 16.61, p < 0.001).\nn multivariable analysis, anhedonia remained independently associated with all-cause mortality (HR = 1.51, 95% CI [1.03-2.22], p = 0.036), after adjusting for socio-demographics, clinical characteristics, and negative and relaxed affect.\nAnhedonia was independently associated with a 1.5-fold increased risk for all-cause mortality in patients who survived the first 6 months post-PCI.\nDepressive symptoms related to lack of enjoyment or pleasure and physical or cognitive slowing, as measured by the HADS-D, predicted all-cause mortality at 8 years ACS patients, whereas other depressive and anxiety symptoms did not.", "role": "user" }, { "content": "Anhedonia is associated with poor prognosis in patients with coronary disease. Namely, in patients with coronary disease, anhedonia was associated with increased mortality, greater risk for major cardiac event, impaired physical health status, more cardiac symptoms, more feelings of disability. These associations were independent from clinical and demographic factors.", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey of Location Prediction on Twitter \nChapter Title: Home Location Prediction \n1. Abstract of Cited Paper (BIB001): This purpose of this introductory paper is threefold. First, it introduces the Monte Carlo method with emphasis on probabilistic machine learning. Second, it reviews the main building blocks of modern Markov chain Monte Carlo simulation, thereby providing and introduction to the remaining papers of this special issue. Lastly, it discusses new interesting research horizons. \n2. Abstract of Cited Paper (BIB002): We investigate automatic geolocation (i.e. identification of the location, expressed as latitude/longitude coordinates) of documents. Geolocation can be an effective means of summarizing large document collections and it is an important component of geographic information retrieval. We describe several simple supervised methods for document geolocation using only the document's raw text as evidence. All of our methods predict locations in the context of geodesic grids of varying degrees of resolution. We evaluate the methods on geotagged Wikipedia articles and Twitter feeds. For Wikipedia, our best method obtains a median prediction error of just 11.8 kilometers. Twitter geolocation is more challenging: we obtain a median error of 479 km, an improvement on previous results for the dataset. \n3. Abstract of Cited Paper (BIB003): Geolocation prediction is vital to geospatial applications like localised search and local event detection. Predominately, social media geolocation models are based on full text data, including common words with no geospatial dimension (e.g. today) and noisy strings (tmrw), potentially hampering prediction and leading to slower/more memory-intensive models. In this paper, we focus on finding location indicative words (LIWs) via feature selection, and establishing whether the reduced feature set boosts geolocation accuracy. Our results show that an information gain ratiobased approach surpasses other methods at LIW selection, outperforming state-of-the-art geolocation prediction methods by 10.6% in accuracy and reducing the mean and median of prediction error distance by 45km and 209km, respectively, on a public dataset. We further formulate notions of prediction confidence, and demonstrate that performance is even higher in cases where our model is more confident, striking a trade-off between accuracy and coverage. Finally, the identified LIWs reveal regional language differences, which could be potentially useful for lexicographers. \n4. Abstract of Cited Paper (BIB004): The geographical properties of words have recently begun to be exploited for geolocating documents based solely on their text, often in the context of social media and online content. One common approach for geolocating texts is rooted in information retrieval. Given training documents labeled with latitude/longitude coordinates, a grid is overlaid on the Earth and pseudo-documents constructed by concatenating the documents within a given grid cell; then a location for a test document is chosen based on the most similar pseudo-document. Uniform grids are normally used, but they are sensitive to the dispersion of documents over the earth. We define an alternative grid construction using k-d trees that more robustly adapts to data, especially with larger training sets. We also provide a better way of choosing the locations for pseudo-documents. We evaluate these strategies on existing Wikipedia and Twitter corpora, as well as a new, larger Twitter corpus. The adaptive grid achieves competitive results with a uniform grid on small training sets and outperforms it on the large Twitter corpus. The two grid constructions can also be combined to produce consistently strong results across all training sets. \n5. Abstract of Cited Paper (BIB005): The location profiles of social media users are valuable for various applications, such as marketing and real-world analysis. As most users do not disclose their home locations, the problem of inferring home locations has been well studied in recent years. In fact, most existing methods perform batch inference using static (i.e., pre-stored) social media contents. However, social media contents are generated and delivered in real-time as social streams. In this situation, it is important to continuously update current inference results based on the newly arriving contents to improve the results over time. Moreover, it is effective for location inference to use the spatiotemporal correlation between contents and locations. The main idea of this paper is that we can infer the locations of users who simultaneously post about a local event (e.g., earthquakes). Hence, in this paper, we propose an online location inference method over social streams that exploits the spatiotemporal correlation, achieving 1) continuous updates with low computational and storage costs, and 2) better inference accuracy than that of existing methods. The experimental results using a Twitter dataset show that our method reduces the inference error to less than 68% of existing methods. The results also show that the proposed method can update inference results in constant time regardless of the amount of accumulated contents. \n6. Abstract of Cited Paper (BIB006): Text-based document geolocation is commonly rooted in language-based information retrieval techniques over geodesic grids. These methods ignore the natural hierarchy of cells in such grids and fall afoul of independence assumptions. We demonstrate the effectiveness of using logistic regression models on a hierarchy of nodes in the grid, which improves upon the state of the art accuracy by several percent and reduces mean error distances by hundreds of kilometers on data from Twitter, Wikipedia, and Flickr. We also show that logistic regression performs feature selection effectively, assigning high weights to geocentric terms.\n\nLiterature Review:", "role": "user" }, { "content": "Home locations refer to Twitter users' long-term residential addresses. The prediction of home locations may enable various applications, e.g., local content recommendation, location-based advertisement, public health monitoring, and public opinion polling estimation. According to specific requirements of applications, home locations may be represented at different levels of granularity. Generally, there are three categories of home location granularity: • Administrative regions, i.e., home locations are represented by countries, states, or cities where they are located. • Geographical grids, i.e., the earth is partitioned into cells of equal or varying sizes 3 , and home locations are represented by the cells they fall in. • Geographical coordinates, i.e., homes are represented by their latitudes and longitudes. Coordinates may be self-reported or converted from administrative regions or cells by taking their centers. BIB001 Geo-tags may be in the form of point-of-interests (e.g., a hotel or a shopping mall) or simply geographical coordinates (latitudes and longitudes). BIB002 Equal-sized cells are achieved by uniformly binning latitudes and longitudes BIB003 . The major drawback is that rural areas are over-represented at the expense of urban areas. Therefore, quadtree BIB006 or k-dimensional tree (k-d tree) BIB004 BIB005 BIB007 ] are adopted to achieve varying-sized cells with better resolutions on populated areas. Ground truth home locations may be collected from users' self-declared profiles. For example, in Figure 1 , the user reports that she lives in NY (New York). Due to possible privacy concerns, empty and noisy information also appear in user profiles. some studies also aggregate geo-tags attached with users' tweets as their ground truth home locations. Possible aggregating approaches include: • Choose the most frequent city involved in the geotags. • Choose the first valid geotag, and convert it to an administrative region, a cell, or coordinates. • Choose the geometric median 4 of the geo-tags. For the sake of evaluation, a uniform level of granularity should be decided and fixed for an application. However, to achieve maximum coverage of ground truths, user profiles and geo-tag aggregations could be utilized in combination. Knowing home locations of Twitter users may enable various applications, such as local content recommendation, location-based advertisement, public health monitoring, and public opinion polling. However, because it is optional for Twitter users to complete their profiles, Twitter users' home locations are largely absent or noisy. Therefore, many research efforts have been spent on predicting users' home locations. For most works, home locations are predicted at city-level, and sometimes at state or country level. In this section, we detail them according to different inputs they are based on, namely tweet contents, Twitter network, and tweet contexts. Note that many works simultaneously involve multiple inputs, especially the first two. In this case, they will be discussed multiple times, where assumptions and techniques regarding different inputs are discussed in corresponding subsections.", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nRecognizing freehand sketches with high arbitrariness is greatly challenging. Most existing methods either ignore the geometric characteristics or treat sketches as handwritten characters with fixed structural ordering. Consequently, they can hardly yield high recognition performance even though sophisticated learning techniques are employed. In this paper, we propose a sequential deep learning strategy that combines both shape and texture features. A coded shape descriptor is exploited to characterize the geometry of sketch strokes with high flexibility, while the outputs of constitutional neural networks (CNN) are taken as the abstract texture feature. We develop dual deep networks with memorable gated recurrent units (GRUs), and sequentially feed these two types of features into the dual networks, respectively. These dual networks enable the feature fusion by another gated recurrent unit (GRU), and thus accurately recognize sketches invariant to stroke ordering. The experiments on the TU-Berlin data set show that our method outperforms the average of human and state-of-the-art algorithms even when significant shape and appearance variations occur.\n\nCited Abstract(s):\n[1]: We propose a multi-scale multi-channel deep neural network framework that, for the first time, yields sketch recognition performance surpassing that of humans. Our superior performance is a result of explicitly embedding the unique characteristics of sketches in our model: (i) a network architecture designed for sketch rather than natural photo statistics, (ii) a multi-channel generalisation that encodes sequential ordering in the sketching process, and (iii) a multi-scale network ensemble with joint Bayesian fusion that accounts for the different levels of abstraction exhibited in free-hand sketches. We show that state-of-the-art deep networks specifically engineered for photos of natural objects fail to perform well on sketch recognition, regardless whether they are trained using photo or sketch. Our network on the other hand not only delivers the best performance on the largest human sketch dataset to date, but also is small in size making efficient training possible using just CPUs.\n\n[2]: We propose a deep learning approach to free-hand sketch recognition that achieves state-of-the-art performance, significantly surpassing that of humans. Our superior performance is a result of modelling and exploiting the unique characteristics of free-hand sketches, i.e., consisting of an ordered set of strokes but lacking visual cues such as colour and texture, being highly iconic and abstract, and exhibiting extremely large appearance variations due to different levels of abstraction and deformation. Specifically, our deep neural network, termed Sketch-a-Net has the following novel components: (i) we propose a network architecture designed for sketch rather than natural photo statistics. (ii) Two novel data augmentation strategies are developed which exploit the unique sketch-domain properties to modify and synthesise sketch training data at multiple abstraction levels. Based on this idea we are able to both significantly increase the volume and diversity of sketches for training, and address the challenge of varying levels of sketching detail commonplace in free-hand sketches. (iii) We explore different network ensemble fusion strategies, including a re-purposed joint Bayesian scheme, to further improve recognition performance. We show that state-of-the-art deep networks specifically engineered for photos of natural objects fail to perform well on sketch recognition, regardless whether they are trained using photos or sketches. Furthermore, through visualising the learned filters, we offer useful insights in to where the superior performance of our network comes from.", "role": "user" }, { "content": "In order to exploit appropriate learning architecture for sketch recognition, [1] [2] develop a network named as Sketch-A-Net (SAN), which enlarges the pooling sizes and patches of filters to cater the sparse character of sketches. Different from traditional images, sketches involve inherent sequential property. [1] and [2] divide the strokes in several groups according to the strokes order. However, CNNs can not build connections between sequential strokes.", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nStochastic simulation is a widely used method for estimating quantities in models of chemical reaction networks where uncertainty plays a crucial role. However, reducing the statistical uncertainty of the corresponding estimators requires the generation of a large number of simulation runs, which is computationally expensive. To reduce the number of necessary runs, we propose a variance reduction technique based on control variates. We exploit constraints on the statistical moments of the stochastic process to reduce the estimators' variances. We develop an algorithm that selects appropriate control variates in an on-line fashion and demonstrate the efficiency of our approach on several case studies.\n\nCited Abstract(s):\n[1]: Model-based prediction of stochastic noise in biomolecular reactions often resorts to approximation with unknown precision. As a result, unexpected stochastic fluctuation causes a headache for the designers of biomolecular circuits. This paper proposes a convex optimization approach to quantifying the steady state moments of molecular copy counts with theoretical rigor. We show that the stochastic moments lie in a convex semi-algebraic set specified by linear matrix inequalities. Thus, the upper and the lower bounds of some moments can be computed by a semidefinite program. Using a protein dimerization process as an example, we demonstrate that the proposed method can precisely predict the mean and the variance of the copy number of the monomer protein.\n\n[2]: \n\n[3]: The stochastic dynamics of biochemical networks are usually modelled with the chemical master equation (CME). The stationary distributions of CMEs are seldom solvable analytically, and numerical methods typically produce estimates with uncontrolled errors. Here, we introduce mathematical programming approaches that yield approximations of these distributions with computable error bounds which enable the verification of their accuracy. First, we use semidefinite programming to compute increasingly tighter upper and lower bounds on the moments of the stationary distributions for networks with rational propensities. Second, we use these moment bounds to formulate linear programs that yield convergent upper and lower bounds on the stationary distributions themselves, their marginals and stationary averages. The bounds obtained also provide a computational test for the uniqueness of the distribution. In the unique case, the bounds form an approximation of the stationary distribution with a computable bound on its error. In the non-unique case, our approach yields converging approximations of the ergodic distributions. We illustrate our methodology through several biochemical examples taken from the literature: Schl \"ogl's model for a chemical bifurcation, a two-dimensional toggle switch, a model for bursty gene expression, and a dimerisation model with multiple stationary distributions.\n\n[4]: Applying the method of moments to the chemical master equation appearing in stochastic chemical kinetics often leads to the so-called closure problem. Recently, several authors showed that this problem can be partially overcome using moment-based semidefinite programs (SDPs). In particular, they showed that moment-based SDPs can be used to calculate rigorous bounds on various descriptions of the stochastic chemical kinetic system’s stationary distribution(s)—for example, mean molecular counts, variances in these counts, and so on. In this paper, we show that these ideas can be extended to the corresponding dynamic problem, calculating time-varying bounds on the same descriptions.\n\n[5]: The predictive ability of stochastic chemical reactions is currently limited by the lack of closed form solutions to the governing chemical master equation. To overcome this limitation, this letter proposes a computational method capable of predicting mathematically rigorous upper and lower bounds of transient moments for reactions governed by the law of mass action. We first derive an equation that transient moments must satisfy based on the moment equation. Although this equation is underdetermined, we introduce a set of semidefinite constraints known as moment condition to narrow the feasible set of the variables in the equation. Using these conditions, we formulate a semidefinite program that efficiently and rigorously computes the bounds of transient moment dynamics. The proposed method is demonstrated with illustrative numerical examples and is compared with related works to discuss advantages and limitations.\n\n[6]: Calibrating parameters is a crucial problem within quantitative modeling approaches to reaction networks. Existing methods for stochastic models rely either on statistical sampling or can only be applied to small systems. Here, we present an inference procedure for stochastic models in equilibrium that is based on a moment matching scheme with optimal weighting and that can be used with high-throughput data like the one collected by flow cytometry. Our method does not require an approximation of the underlying equilibrium probability distribution and, if reaction rate constants have to be learned, the optimal values can be computed by solving a linear system of equations. We discuss important practical issues such as the selection of the moments and evaluate the effectiveness of the proposed approach on three case studies.\n\n[7]: This paper proposes a methodology to estimate characteristic functions of stochastic differential equations that are defined over polynomials. For such systems, the time evolution of the characteristic function is governed by a partial differential equation; consequently, the stationary characteristic function can be obtained by solving an ordinary differential equation (ODE). However, except for a few special cases, the solution to the ODE consists of unknown coefficients. These coefficients are closely related with the stationary moments of the process, which could be estimated by utilizing the fact that the characteristic function is positive definite. The method is illustrated via examples.", "role": "user" }, { "content": "While the moment closure method uses ad-hoc approximations for high order moments to facilitate numerical integration, they can be avoided in some contexts. For the equilibrium distribution, for example, the time-derivative of all moments is equal to zero. This directly yields constraints that have been used for parameter estimation at steady-state [4]3 and bounding moments of the equilibrium distribution using semi-definite programming [7] [2] [3] . The latter technique of bounding moments has been successfully adapted in the context of transient analysis [4] [1] [5] . We adapt the constraints proposed in these works to improve statistical estimations via stochastic simulation (cf. section ).", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nThe R740S mutation in the V-ATPase a3 subunit increases lysosomal pH, impairs NFATc1 translocation, and decreases in vitro osteoclastogenesis. Vacuolar H(+) -ATPase (V-ATPase), a multisubunit enzyme located at the ruffled border and in lysosomes of osteoclasts, is necessary for bone resorption. We previously showed that heterozygous mice with an R740S mutation in the a3 subunit of V-ATPase (+/R740S) have mild osteopetrosis resulting from an ∼90% reduction in proton translocation across osteoclast membranes. Here we show that lysosomal pH is also higher in +/R740S compared with wild-type (+/+) osteoclasts. Both osteoclast number and size were decreased in cultures of +/R740S compared with +/+ bone marrow cells, with concomitant decreased expression of key osteoclast markers (TRAP, cathepsin K, OSCAR, DC-STAMP, and NFATc1), suggesting that low lysosomal pH plays an important role in osteoclastogenesis. To elucidate the molecular mechanism of this inhibition, NFATc1 activation was assessed. NFATc1 nuclear translocation was significantly reduced in +/R740S compared with +/+ cells; however, this was not because of impaired enzymatic activity of calcineurin, the phosphatase responsible for NFATc1 dephosphorylation. Protein and RNA expression levels of regulator of calcineurin 1 (RCAN1), an endogenous inhibitor of NFATc1 activation and a protein degraded in lysosomes, were not significantly different between +/R740S and +/+ osteoclasts, but the RCAN1/NFATc1 ratio was significantly higher in +/R740S versus +/+ cells. The lysosomal inhibitor chloroquine significantly increased RCAN1 accumulation in +/+ cells, consistent with the hypothesis that higher lysosomal pH impairs RCAN1 degradation, leading to a higher RCAN1/NFATc1 ratio and consequently NFATc1 inhibition. Our data indicate that increased lysosomal pH in osteoclasts leads to decreased NFATc1 signaling and nuclear translocation, resulting in a cell autonomous impairment of osteoclastogenesis in vitro.", "role": "user" }, { "content": "{\"Chemical\": [\"chloroquine\", \"H(+)\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nA Concise Total Synthesis of (+)-Waihoensene Guided by Quaternary\\nCenter Analysis\n\nPaper sections:\n\n<p>The structures of angular triquinane natural products have long fascinated\nsynthetic chemists, not only due to the challenges presented by their diverse fused ring\nsystems and congested frames, but also because of their overall stereochemical\ncomplexity and density.[1] Indeed, as\nshown in Scheme 1, many of these natural products\n(such as 1 and 2) possess three all-carbon quaternary\ncenters,[2] often contiguous\n(colored here in blue). Some, such as laurenene (3),[3] possess a fourth (denoted here in orange),\nthough to the best of our knowledge, only the natural product waihoensene\n(4),[4] isolated in\n1997 by the Weavers group from Podocarpus totara var.\nwaihoensis,[5] has\nfour such centers arrayed in a row. Within some, quaternary centers comprise as much as\n20% of their carbon atoms. Further, many natural products in this class, particularly as\nexemplified by 3 and 4, are devoid of typically reactive\nfunctional groups; both of these molecules possess only a lone alkene outside of their\nalkane-based frames. Over the past few years, our group has engaged in a research\nprogram seeking to develop strategies and tactics to efficiently synthesize similarly\nunique terpenes (such as 5–7) lacking in traditional\nfunctional groups.[6] Key lessons\nlearned from those endeavors include: 1) using a bare modicum of added functional groups\nfor critical C–C bond formations and strategically using those groups for\nmultiple purposes, and 2) viewing the quaternary centers within the targets as key\ncomponents to include in retrosynthetic planning, specifically in thinking about how the\npresence of one (such as the green colored center in 7) could assist in the\nformation of others. Herein, we show how the application of these ideas has led to a\nconcise 17-step asymmetric total synthesis of waihoensene (4).</p><p>While it has been proposed that waihoensene (4) can arise\nbiosynthetically from laurenene (3), the only synthesis achieved at the\ntime our work commenced was a non-biomimetic, but highly creative approach from the Lee\ngroup which delivered racemic material.[7] Their effort, shown in a condensed format in Scheme 1, illustrates the tenets of quaternary center-guided\nsynthesis in that the quaternary center present within 8 assisted in the\nformation of the other three. Of note, the two additional centers within 9,\nformed concurrently via a cascade process, proceeded with 3.3:1 selectivity for\n9 and other isomers, while installation of the remaining two methyl\ngroups, leading to the final all-carbon quaternary center, was stereospecific. Our\nretrosynthetic analysis of the target as guided by its four contiguous quaternary\ncenters suggested that the same initial quaternary center used by the Lee group would be\nthe ideal starting point, but not in the form of a six-membered ring. Rather, it was the\nneighboring five-membered ring of the final target as expressed by 12,\nwhere our approach sought to use its lone quaternary center to introduce each additional\nquaternary center individually in a stereocontrolled fashion. Thus, from\n12, we anticipated that a Conia-ene reaction could lead to a second ring\nand quaternary center as expressed in 11, which, if elaborated to\n10, could then enable the formation of the third center found in\n9 through a Pauson–Khand reaction.[8] In this way, the original ester, alkyne, and\nketone functional groups of 12 would serve as the only functional group\nlynchpins needed to achieve all bond formations, chain homologations, and other elements\nof tailoring required to reach the final target. As validation for the power of this\napproach, as well as interest in waihoensene as a target in general, a synthesis of\n(+)-waihoensene by Yang, Huang, and co-workers was published while this paper was under\nreview using similar key bond constructions, albeit in unique ways,[9] as was an additional model study from Tu and\nWang.[10]</p><p>Our efforts began with the preparation of a chiral and protected version of\n12 in the form of 19 as shown in Scheme 2. Following the reaction of Grignard reagent\n14[11] with\n13 to afford functionalized α,β-unsaturated ketone\n15, use of Hoveyda's asymmetric conjugate addition\nchemistry,[12] as guided by\nN-heterocyclic carbene complex 16, generated the\nall-carbon quaternary center of 17 in excellent yield (81–92%) and\nhigh enantioselectivity (82–92% ee), variable based on the scale\nof the reaction. From here, a partially regioselective addition of a methyl ester could\nbe achieved via deprotonation with NaHMDS and subsequent trapping with Mander's\nreagent, affording a 1.8:1 mixture of 19 and 18 in 88%\ncombined yield. Extensive screening revealed that no other conditions were superior in\nterms of throughput, noting, however, that LiHMDS did give higher selectivity in terms\nof desired enolate formation, but a lower numerical yield of 19. We\nattribute the potential regioselectivity observed for all bases to be due to a weak\ndirecting effect from the alkyne.[6c,13] While this step did not proceed with\nideal levels of selectivity, the undesired regioisomer (18) could be\nrecycled to 17 through a Krapcho decarboxylation.[14] Of note, efforts to forge the critical\nquaternary carbon in an enantioselective manner with the ester present were\nunsuccessful. While the key precursor (21) could be prepared using a method\ndeveloped by our group starting from lactone 20,[15] subsequent attempts at asymmetric methyl\naddition were uniformly unsuccessful (see SI for details); the racemic addition\nreaction, by contrast, worked quite well when promoted with\nCuBr•Me2S.</p><p>With one ring and quaternary center forged effectively, our focus next turned to\ngenerating a second ring and quaternary center through a Conia-ene reaction. As shown in\nScheme 3, that step, following TBAF-mediated\nremoval of the TMS group from the alkyne, proceeded smoothly and quantitatively with\nonly 0.96 mol % each of Ph3PAuCl and AgOTf to afford the desired\nbicyclo[4.3.0] framework of 11.[16] Critically, this reaction proved highly scalable, even when\nusing gram quantities of starting material, with no decrease in overall efficiency; to\nour knowledge, this Conia-ene reaction is the first leading to the formation of a\nsix-membered ring containing two vicinal quaternary carbons starting from a\nfive-membered ring precursor.[17]</p><p>Now that the alkyne had served its role in generating the alkene of\n11, we sought to convert it into the respective methyl group of the\nfinal target through a facially selective reduction. That event would formally require\nthe addition of hydrogen from the concave face. Pleasingly, however,\nconventional hydrogenation using Pd/C (Table 1,\nEntry 1) led to the desired product (22) as the predominant diastereomer as\nconfirmed by X-ray crystallographic analysis, albeit in low yield (20%). Further\nscreening revealed that hydrogenation with PtO2 (Entry 2) in\nCH2Cl2 gave much better yield and selectivity (76%\n22, 3.2:1 dr). Given that a hydrogen atom transfer\n(HAT)-type hydrogenation, as developed by Shenvi,[18] demonstrated the same trend in diastereoselectivity (2.5:1,\nEntry 3), these collective outcomes suggest that 22 is both kinetically and\nthermodynamically favored as the hydrogenation product. Intriguingly, a reversal in\nstereoselectivity was observed when Crabtree's catalyst was employed (Entry 4),\npossibly due to directing effects by the neighboring ester motif.[19] As such, these results could provide guidance\non stereodivergent applications of such intermediates for the synthesis of other\nmolecules.</p><p>Given that this additional chiral center had now been secured, the ketone within\n22 was then olefinated with excess Ph3P=CH2,\nusing KOt-Bu in toluene at reflux to generate the ylide and then\nreacting it with the substrate for 12 h.[20] No other condition set afforded the desired product effectively,\nwith the need for elevated temperature, prolonged reaction time, and large excess in\nreagents likely reflecting the neighboring steric bulk of the vicinal quaternary\ncarbons. Next, with an eye towards performing the designed Pauson–Khand reaction,\nthe ester was converted into aldehyde 26 through a one-pot procedure\ninvolving sequential DIBAL-H reduction, t-BuOH quench, and\nDess–Martin periodinane-mediated oxidation as developed during our total\nsynthesis of 6 (cf. Scheme\n1);[6b] a slightly\nhigher yield was obtained by performing the reduction and oxidation steps separately.\nHowever, despite the facility of this operation, subsequent conversion of the aldehyde\nwithin 26 to the chain homologated alkyne needed for the\nPauson–Khand step (i.e. 10) proved quite challenging. Many efforts\nproved fruitless, either due to an inability to forge the alkyne of 10 or\nto afford the natural product using a differentially functionalized version of\n10.[21] Ultimately,\nthe desired intermediate was accessed through a 4-step sequence involving an initial\nHorner–Wadsworth–Emmons homologation, producing an inconsequential 1.7:1\nmixture of alkene isomers that were subsequently erased by chemoselective single\nelectron transfer (SET)-based reduction using magnesium metal in MeOH.[22] These operations produced\n27 in 67% overall yield. Then, following DIBAL-H reduction of the\nnitrile to the respective aldehyde, a highly silica gel-unstable material (potentially\ndue to a Prins-type cyclization, although unverified), immediate treatment of this crude\nproduct with the Ohira–Bestmann reagent afforded 10 in 55%\nyield.[23]</p><p>With this compound in hand, we were delighted to find that the designed\nPauson–Khand reaction worked to forge the third quaternary center of the target\nas well as generate the full angular triquinane framework of waihoensene. That event,\nachieved by stirring 10 with stoichiometric Co2(CO)8\nand then heating the resultant cobalt complex at 160 °C in mesitylene under a CO\natmosphere, delivered 9 in 50% yield. The uncommonly high temperature used\nfor this reaction[24] was critical to\nits success, likely due to the increased reaction rate overcoming the energy-barrier\nneeded for quaternary center formation.[25] Pleasingly, our synthetic 9 matched all reported\nspectral data obtained by the Lee group.[7a] We then followed the same general sequence utilized in that\nsynthesis to access waihoensene (4), optimizing the final step by using the\nWittig homologation procedure deployed earlier for the conversion of 22 to\n24. That event proceeded in 83% yield, while the Lee procedure using\nthe Petasis reagent[26] led to a 32%\nyield. All spectral data for synthetic 4, including the sign and general\nmagnitude of its optical rotation, matched that reported by Weavers,[5] confirming its absolute configuration. We also\nobtained a single-crystal of compound (±)-28, further verifying the\nintegrity of our sequence. In total, we have prepared ~50 mg of the natural\nproduct across all runs of our sequence.</p><p>In conclusion, we have completed an enantioselective total synthesis of\n(+)-waihoensene in 17-steps from commercially available starting materials. This overall\nlength compares favorably to past efforts. That outcome is due, in large part, to\nutilizing a modicum of functional groups, none of which were extraneous, to repeatedly\neffect key C–C bond formations and overall tailoring coupled with overarching\nretrosynthetic design orchestrated by viewing the quaternary centers as a central\norganizing feature. Efforts to extend these lessons, and some of the unique elements of\nthe Conia-ene and Pauson–Khand steps, to other targets are the subject of current\ninvestigations.</p>", "role": "user" }, { "content": "The four contiguous all-carbon quaternary centers of waihoensene, coupled with the absence of any traditional reactive functional groups other than a single alkene, renders it a particularly challenging synthetic target among angular triquinane natural products. Here, we show that its polycyclic frame can be assembled concisely by using a strategically selected quaternary center to guide the formation of the other three through judiciously selected C\\xe2\\x80\\x93C bond formation reactions. Those events, which included a unique Conia-ene cyclization and a challenging Pauson\\xe2\\x80\\x93Khand reaction, afforded a 17-step synthesis of the molecule in enantioenriched form.", "role": "assistant" } ]

[ { "content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\nLongitudinal associations of lifestyle factors and weight status with insulin resistance (HOMA-IR) in preadolescent children: the large prospective cohort study IDEFICS\nAbstract 1:\nBackground This study investigates prospect i ve associations of anthropometrical and lifestyle indices with insulin resistance ( IR ) in European children from the IDEFICS cohort . Insulin resistance ( IR ) is a growing concern in childhood obesity and a central aspect of the metabolic syndrome ( MS ) . It most likely represents the link between obesity and type 2 diabetes . Methods This longitudinal study included 3348 preadolescent children aged 3 to 10.9 years from 8 European countries who were observed from 2007/2008 to 2009/2010 . The main outcome measure in the present analysis is HOMA-IR ( homeostasis model assessment as a common proxy indicator to quantify IR ) at follow-up and in its longitudinal development . Anthropometrical measures and lifestyle indices , including objective ly determined physical activity , were considered , among others factors , as determinants of IR . Prospect i ve associations between IR at follow-up and anthropometrical and lifestyle indices were estimated by logistic regression models . Results Country-specific prevalence rates of IR in the IDEFICS cohort of European children showed a positive trend with weight category . Prospect i ve multivariate analyses showed the strongest positive associations of IR with BMI z-score ( OR = 2.6 for unit change from the mean , 95 % CI 2.1–3.1 ) and z-score of waist circumference ( OR = 2.2 for unit change from the mean , 95 % CI 1.9–2.6 ) , which were analysed in separate models , but also for sex ( OR = 2.2 for girls vs. boys , 95 % CI 1.5–3.1 up to OR 2.5 , 95 % CI 1.8–3.6 depending on the model ) , audio-visual media time ( OR = 1.2 for an additional hour per day , 95 % CI 1.0–1.4 in both models ) and an inverse association of objective ly determined physical activity ( OR = 0.5 for 3rd compared to 1st quartile , 95 % CI 0.3–0.9 in both models ) . A longitudinal reduction of HOMA-IR was accompanied with a parallel decline in BMI . Conclusions This study is , to our knowledge , the first prospect i ve study on IR in a preadolescent children ’s population . It supports the common hypothesis that overweight and obesity are the main determinants of IR . Our data also indicate that physical inactivity and a sedentary lifestyle are likewise associated with the development of IR , independent of weight status . The promotion of physical activity should thus be considered as an equal option to dietary intervention for the treatment of IR in the paediatric practice\n\n\nTitle 2:\nSleep Duration and Risk of Type 2 Diabetes\nAbstract 2:\nIn this study of 4525 children , a 1-hour-longer sleep duration was associated with lower levels of adiposity , insulin resistance , and fasting glucose . BACKGROUND : Associations between sleep duration and type 2 diabetes ( T2D ) risk markers in childhood have been little studied . We examined associations between self-reported sleep duration and T2D risk markers in children . METHODS : Cross-sectional study of 4525 multiethnic UK children aged 9 to 10 years . Sleep time was calculated from self-reported usual time of going to bed and getting up on a school day , vali date d in a subset using accelerometers . Fasting blood sample s provided levels of serum lipids and insulin , plasma glucose , and HbA1c . Physical measures included height , weight , bioimpedance , and blood pressure . Multilevel linear regression models of anthropometric , T2D , and cardiovascular risk markers with sleep duration were adjusted for sex , age , month , ethnicity , socioeconomic position , observer ( physical measures only ) , and r and om effect of school . RESULTS : On average , children slept 10.5 hours per night ( 95 % range 8.0–12.0 hours ) . There were strong inverse grade d relationships between sleep duration , adiposity , and diabetes risk markers . In adjusted models , a 1-hour-longer sleep duration was associated with 0.19 lower BMI ( 95 % confidence interval [ CI ] 0.09 to 0.28 ) , 0.03 kg/m5 lower fat mass index ( 95 % CI 0.00 to 0.05 kg/m5 ) , 2.9 % lower homeostasis model assessment insulin resistance ( 95 % CI 1.2 % to 4.4 % ) , and 0.24 % lower fasting glucose ( 95 % CI 0.03 % to 0.44 % ) ; there was no association with HbA1c or cardiovascular risk . Associations with insulin and glucose remained after an additional adjustment for adiposity markers . CONCLUSIONS : The finding of an inverse association between sleep duration and T2D risk markers in childhood is novel . Intervention studies are needed to establish the causality of these associations , which could provide a simple strategy for early T2D prevention", "role": "user" }, { "content": "The strongest evidence of an association with sleep is with obesity , hypertension , and insulin sensitivity .", "role": "assistant" } ]

[ { "content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nintroduction\n\nContext before:\nThis observation has led some researchers, e.g., Cooper and Paccia-Cooper (1980), to claim a direct mapping between the syntactic phrase and the prosodic phrase. (to pronounced /tu/) When it comes to sentence-level prosody, especially phrasing, it is often true, as we will see below, that a sequence of words dominated by the same syntactic node cohere more closely than a sequence of words dominated by two different nodes. Who did you speak to?\n\nCitation:\nThis observation has led some researchers , e.g. , Cooper and Paccia-Cooper ( 1980 ) , to claim a direct mapping between the syntactic phrase and the prosodic phrase .\n\nContext after:\nHowever, this claim is controversial because of the misa:ignments that occur between the two levels of phrasing. For example, in considering the connection between syntax and phrasing, the linguistic literature most often refers to examples of embedded sentences. Sentences like 12, from Chomsky (1965), are frequently cited. (Square brackets mark off the NP constituents that contain embedded sentences.)", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nThe Epstein-Barr virus nuclear antigen 2 (EBNA2), a protein required for B lymphocyte immortalization, induces the synthesis of type I interferon in Burkitt 's lymphoma cell lines. Epstein-Barr virus nuclear antigen 2 (EBNA2), a protein involved in cell transformation, interferes with the cellular response to type I interferons (IFN-alpha / beta). We investigated the function of conditionally expressed EBNA2 in the context of the IFN response in Burkitt 's lymphoma cell lines. Expression of EBNA2 led to the transcriptional activation of both endogenous or transfected IFN-stimulated genes (ISGs), genes which contain within their promoters either the interferon-stimulated response element (ISRE) or the gamma interferon activation site (GAS). In search of a molecular mechanism for the transcriptional induction of ISGs, we observed an EBNA2-dependent synthesis of IFN-beta mRNA at low levels and the secretion of low amounts of IFN. A transfected IFN-beta promoter responded to EBNA2 activation, and a sequence closely resembling a RBP-Jkappa binding site was pinpointed as a potential target of EBNA2 activity. EBNA2-dependent transcriptional induction of the IFN-beta promoter occurred in EBV-negative Burkitt 's lymphoma cells, indicating that other EBV genes were not required for the induction of IFN-beta synthesis.", "role": "user" }, { "content": "{\"CellLine\": [\"EBV - negative Burkitt \\u0027s lymphoma cells\", \"Burkitt \\u0027s lymphoma cell lines\"], \"CellType\": [\"B lymphocyte\"], \"DNA\": [\"ISGs\", \"ISRE\", \"interferon - stimulated response element\", \"GAS\", \"RBP - Jkappa binding site\", \"gamma interferon activation site\", \"IFN - stimulated genes\", \"promoters\", \"EBV genes\", \"IFN - beta promoter\"], \"Protein\": [\"type I interferons\", \"EBNA2\", \"IFN - beta\", \"Epstein - Barr virus nuclear antigen 2\", \"IFN\", \"type I interferon\", \"IFN - alpha / beta\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Proactive Resilience of Power Systems Against Natural Disasters: A Literature Review \nChapter Title: B. THE ROLE OF RENEWABLE ENERGY INTEGRATION ON ENHANCING POWER SYSTEM RESILIENCE \n1. Abstract of Cited Paper (BIB001): ABSTRACTOptimal sizing of hybrid renewable energy systems (HRES) to satisfy load requirements with the highest reliability and lowest cost is a crucial step in building HRESs to supply electricity ...\n\nLiterature Review:", "role": "user" }, { "content": "Renewable energy sources (RES) incorporate different technologies, such as, wind turbines, solar PV, electric vehicles and energy storage. Conventionally, the interconnection standards necessitate that RES be disconnected from disasters . However, with increasing RES penetration, there is a critical desire to reconsider this issue. A case of this is the view of utilizing RES during the restoration process BIB001 , and another is utilizing RES in resilience to respond to protect frameworks. Notwithstanding, given that a few RES (eg, wind and solar) are regularly fickle and hard to anticipate precisely, managing vulnerability might be a major issue in using RES to enhance the system's resilience to withstand disasters. In addition, the difficulty in managing the vulnerability can be extraordinary as the profound penetration of the RES is as of now in progress. Likewise, as uncovered in an ongoing overview BIB002 , numerous facilities notice cost requirements and financial related imperatives as an impediment to disavowing RES. Subsequently, making RES economical can be significant in advancing the use of these sources in enhancing power system resilience. Moreover, we ought to know about the potential antagonistic effects of incorporating RES into the power system. Numerous ideas have been introduced to integrate RES into power systems and to minimize the cost objective function . In this regard, a hybrid RES system integrated into the grid and its smart operation is proposed in this paper in order to enhance the system resilience. The system incorporates wind turbines, solar PV, and electrical vehicle integrated to the grid through AC/DC bus as shown in Fig.7 . A smart management system to monitoring and control the entire system is planned so as to guarantee an adequate balance between the generated and demanded energy. The system employs an intelligent optimization algorithm (IOA) to manage the control, the load data, and the metrological data of the RES (e.g. wind speed, radiation, temperature). The main objective of the IOA is to manage the proposed system to fulfill the minimum total cost (TC) and maintain the system energy balance as shown in the accompanying constraints: Where, FC is the cost function of the borrowed energy from the grid, P g,t (t) is the power transfer between the system and the grid, and C g,t is the price/kWh per hour, t through the life time of the system, T . P w,t (t), P pv,t (t) are the wind and PV power, respectively. P g,t (t) is the transfer power between the electrical vehicle and the system, and P l,t (t) is the load demand. Getting minimum cost of the proposed system insures its economical operation with in turn enhance the system resiliency.", "role": "assistant" } ]

[ { "content": "Summarize the paper:\n\nPaper text:\n\nStructured tabular data is the most commonly used form of data in industry according to a Kaggle ML and DS Survey.\nGradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data.\nThe recent work of Super Characters method using two-dimensional word embedding achieved state-of-the-art results in text classification tasks, showcasing the promise of this new approach.\nIn this paper, we propose the SuperTML method, which borrows the idea of Super Characters method and two-dimensional embedding to address the problem of classification on tabular data.\nFor each input of tabular data, the features are first projected into two-dimensional embedding like an image, and then this image is fed into fine-tuned ImageNet CNN models for classification.\nExperimental results have shown that the proposed SuperTML method have achieved state-of-the-art results on both large and small datasets.\nIn data science, data is categorized into structured data and unstructured data.\nStructured data is also known as tabular data, and the terms will be used interchangeably.\nAnthony Goldbloom, the founder and CEO of Kaggle observed that winning techniques have been divided by whether the data was structured or unstructured BID12 .\nCurrently, DNN models are widely applied for usage on unstructured data such as image, speech, and text.\nAccording to Anthony, \"When the data is unstructured, its definitely CNNs and RNNs that are carrying the day\" BID12 .\nThe successful CNN model in the ImageNet competition BID8 has outperformed human Preliminary work.\nUnder review by the International Conference on Machine Learning (ICML).\nDo not distribute.for image classification task by ResNet BID6 since 2015.On the other side of the spectrum, machine learning models such as Support Vector Machine (SVM), Gradient Boosting Trees (GBT), Random Forest, and Logistic Regression, have been used to process structured data.\nAccording to a recent survey of 14,000 data scientists by Kaggle (2017) , a subdivision of structured data known as relational data is reported as the most popular type of data in industry, with at least 65% working daily with relational data.\nRegarding structured data competitions, Anthony says that currently XGBoost is winning practically every competition in the structured data category BID4 .\nXGBoost BID2 is one popular package implementing the Gradient Boosting method.Recent research has tried using one-dimensional embedding and implementing RNNs or one-dimensional CNNs to address the TML (Tabular Machine Learning) tasks, or tasks that deal with structured data processing BID7 BID11 , and also categorical embedding for tabular data with categorical features BID5 .\nHowever, this reliance upon onedimensional embeddings may soon come to change.\nRecent NLP research has shown that the two-dimensional embedding of the Super Characters method BID9 is capable of achieving state-of-the-art results on large dataset benchmarks.\nThe Super Characters method is a two-step method that was initially designed for text classification problems.\nIn the first step, the characters of the input text are drawn onto a blank image.\nIn the second step, the image is fed into two-dimensional CNN models for classification.\nThe two-dimensional CNN models are trained by fine-tuning from pretrained models on large image dataset, e.g. ImageNet.In this paper, we propose the SuperTML method, which borrows the concept of the Super Characters method to address TML problems.\nFor each input, tabular features are first projected onto a two-dimensional embedding and fed into fine-tuned two-dimensional CNN models for classification.\nThe proposed SuperTML method handles the categorical type and missing values in tabular data automatically, without need for explicit conversion into numerical type values.\nThe proposed SuperTML method borrows the idea of twodimensional embedding from Super Characters and transfers the knowledge learned from computer vision to the structured tabular data.\nExperimental results shows that the proposed SuperTML method has achieved state-of-the-art results on both large and small tabular dataset TAB2", "role": "user" }, { "content": "Deep learning for structured tabular data machine learning using pre-trained CNN model from ImageNet.", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nClinical effects of buspirone in social phobia : a double-blind placebo-controlled study . BACKGROUND The results of open pilot studies suggest that the serotonin-1A ( 5-HT1A ) receptor agonist buspirone might be effective in social phobia . METHOD In the present study , the efficacy of buspirone was investigated in patients with social phobia using a 12-week double-blind placebo-controlled design . Thirty social phobic patients ( DSM-IV ) were treated with either buspirone 30 mg daily or placebo . Efficacy of treatment was measured using the Social Phobia Scale ( subscores anxiety and avoidance ) and the Hamilton Rating Scale for Anxiety . RESULTS Taking a reduction of 50 % or more on the Social Phobia Scale as a criterion for clinically relevant improvement , only 1 patient on buspirone and 1 on placebo were classified as responder to treatment . A subjective and clinically relevant improvement was reported by 4 patients ( 27 % ) on buspirone and 2 patients ( 13 % ) on placebo . There were no statistically significant differences between buspirone and placebo on any of the outcome measures . Generally speaking , buspirone was well tolerated . CONCLUSION The results of the study do not support the results of open studies , in which a reduction of social anxiety and social avoidance was reported in patients with social phobia treated with buspirone .", "role": "user" }, { "content": "{\"Intervention\": [\"serotonin-1A ( 5-HT1A ) receptor agonist buspirone\", \"placebo\", \"buspirone\", \"placebo-controlled\"], \"Outcome\": [\"well tolerated\", \"Social Phobia Scale ( subscores anxiety and avoidance )\", \"Social Phobia Scale\", \"efficacy\", \"reduction\", \"Hamilton Rating Scale for Anxiety\", \"social anxiety and social avoidance\", \"relevant improvement\"], \"Participant\": [\"social phobia\", \"social phobic patients ( DSM-IV )\", \"Thirty\"]}", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: The neuraminidase inhibitors oseltamivir and zanamivir as well as the adamantanes amantadin and rimantadin that interfere with the influenza M2 protein are licensed for the treament of influenza [1] [2] [3] [4] 6] . However, the use of both drug classes is limited by the emergence of resistant virus strains. In seasonal influenza strains, the majority of H3N2 viruses and a great proportion of H1N1 viruses in humans are now considered to be amantadine-and rimantadine-resistant [10] [11] [12] [13] . Moreover, a drastic increase in oseltamivir-resistant H1N1 viruses has been reported during the 2007/2008 influenza season in the northern hemisphere [14] [15] [16] [17] . Preliminary data from the United States predict a further rise for the 2008/2009 season, possibly resulting in more than 90% of the circulating H1N1 strains to be oseltamivir resistant [14] . H5N1 virus strains appear to be generally less sensitive to antiviral treatment than seasonal influenza A virus strains and treatment-resistant H5N1 strains emerge [1] [2] [3] [4] 6, [18] [19] [20] [21] . More-over, parenteral agents for the treatment of seriously ill patients are missing. Glycyrrhizin, a triterpene saponine, is a constituent of licorice root. It has been found to interfere with replication and/or cytopathogenic effect (CPE) induction of many viruses including respiratory viruses such as respiratory syncytial virus, SARS coronavirus, HIV, and influenza viruses [22] [23] [24] [25] [26] [27] [28] . Moreover, antiinflammatory and immunomodulatory properties were attributed to glycyrrhizin [26] . The severity of human H5N1 disease has been associated with hypercytokinaemia (''cytokine storm'') [29, 30] . Delayed antiviral plus immunomodulator treatment reduced H5N1-induced mortality in mice [31] . Therefore, antiinflammatory and immunomodulatory effects exerted by glycyrrhizin may be beneficial for treatment of H5N1. Also, glycyrrhizin is a known antioxidant [26] and antioxidants were already shown to interfere with influenza A virus replication and virus-induced pro-inflammatory responses [32] [33] [34] . Stronger Neo-Minophagen C (SNMC) is a glycyrrhizin preparation (available as tablets or parenteral formulation) that is approved in Japan for the treatment of chronic hepatic diseases and is marketed in Japan, China, Korea, Taiwan, Indonesia, India, and Mongolia. Here, we investigated the influence of SNMC on H5N1 replication, on H5N1-induced cytokine expression, on H5N1-induced cellular oxidative stress, and on critical H5N1-induced cellular signalling events in human pneumocytes (A549 cell line). Glycyrrhizin (Stronger Neo Minophagen C) was obtained from Minophagen Pharmaceuticals Co., Ltd. (Tokyo, Japan). The influenza strain A/Vietnam/1203/04 (H5N1) was received from the WHO Influenza Centre (National Institute for Medical Research, London, UK). The H5N1 influenza strain A/Thailand/ 1(Kan-1)/04 was obtained from Prof. Pilaipan Puthavathana (Mahidol University, Bangkok, Thailand). Virus stocks were prepared by infecting Vero cells (African green monkey kidney; ATCC, Manassas, VA) and aliquots were stored at 280uC. Virus titres were determined as 50% tissue culture infectious dose (TCID 50 /ml) in confluent Vero cells in 96-well microtiter plates. A549 cells (human lung carcinoma; ATCC: CCL-185, obtained from LGC Standards GmbH, Wesel, Germany) were grown at 37uC in minimal essential medium (MEM) supplemented with 10% FBS, 100 IU/ml of penicillin and 100 mg/ml streptomycin. Human monocytes were isolated from buffy coats of healthy donors, obtained from Institute of Transfusion Medicine and Immune Haematology, German Red Cross Blood Donor Center, Johann Wolfgang Goethe-University, Frankfurt am Main. After centrifugation on Ficoll (Biocoll)-Hypaque density gradient (Biochrom AG, Berlin, Germany), mononuclear cells were collected from the interface and washed with PBS. Then, monocytes were isolated using magnetically labeled CD14 MicroBeads (Miltenyi Biotec GmbH, Bergisch Gladbach, Germany) following the manufacturer's instructions. Monocytes were cultivated in IMDM supplemented with 10% pooled human serum, 100 IU/ml of penicillin, and 100 mg/ml streptomycin. The cellular viability was assessed on confluent cell layers with CellTiter-GloH Luminescent Cell Viability Assay (Promega GmbH, Mannheim, Germany) according to the manufacturers' protocol. Cell viability was expressed as percentage of non-treated control. To determine intracellular NP localisation, H5N1-infected A549 were fixed 8 hours p.i. for 15 min with ice-cold acetone/ methanol (40:60, Mallinckrodt Baker B.V., Deventer, The Netherlands) and stained with a mouse monoclonal antibody (1 h incubation, 1:1000 in PBS) directed against the influenza A virus nucleoprotein (NP) (Millipore, Molsheim, France). An Alexa Fluor 488 goat anti-mouse IgG (H&L) (Invitrogen, Eugene, Oregon, USA) was used (1 h incubation, 1:1000 in PBS) as secondary antibody. Nuclei were stained using 49,6-diamidino-2phenylindole (DAPI) (Sigma-Aldrich Chemie GmbH, Munich, Germany). Fluorescence was visualised using Olympus IX 1 fluorescence microscope (Olympus, Planegg, Germany). For flow cytometric analysis, the same antibodies were used. The cytopathogenic effect (CPE) reduction assay was performed as described before [34] . Confluent A549 cell monolayers grown in 96-well microtitre plates were infected with influenza A strains at the indicated multiplicities of infection (MOIs). After a one hour adsorption period, cells were washed to remove non-detached virus. The virus-induced CPE was recorded at 24 h post infection (p.i.). Unless otherwise stated, A549 cells were continuously treated with glycyrrhizin starting with a 1 h pre-incubation period. For time-ofaddition experiments, glycyrrhizin was added exclusively during the 1 h pre-incubation period, exclusively during the 1 h adsorption period, or after exclusively after the wash-out of input virus. Total RNA was isolated from cell cultures using TRI reagent (Sigma-Aldrich, Munich, Germany). Real time PCR for H5 was performed using described methods [35] . The following primers were used: sense 59 acg tat gac tac ccg cag tat tca g 39; antisense 59 aga cca gcy acc atg att gc 39; probe 6-FAM-tca aca gtg gcg agt tcc cta gca-TAMRA. The fraction of cells with fractional DNA content (''sub-G1'' cell subpopulation) indicates cytotoxicity. Sub-G1 cells are considered to be dead (usually apoptotic) cells. Cells were fixed with 70% ethanol for two hours at 220uC. The cellular DNA was stained using propidium iodide (20 mg/ml) and analysed by flow cytometry (FacsCalibur, BD Biosciences, Heidelberg, Germany). Caspase activation was measured using the Caspase-Glo 8, 9, or 3/7 Assays (Promega, Mannheim, Germany) following the manufacturer's instructions. Cell culture supernatants were collected and frozen at 280uC. Cytokines/chemokines were quantified by specific ELISA Duo Sets (R&D Systems GmbH, Wiesbaden, Germany) following the manufacturer's instructions. NFkB activity was investigated in H5N1 (MOI 0.01)-infected cells by quantification of the NFkB subunits Rel A (p65) and NFkB1 (p50) from nuclear extracts using the TransAM TM transcription factor DNA-binding ELISAs (Active Motif, Rixensart, Belgium). Nuclear extract were prepared using the Nuclear Extract Kit (Active Motif, Carlsbad, CA, USA) following the manufacturer's instruction. Cell culture supernatants were investigated for chemotactic activity by measurement of the activity to induce monocyte migration through membrane inserts in 24-well plates (pore size 8 mm; BD Biosciences, Heidelberg, Germany). Monocytes (1610 6 in 100 ml of IMDM with 10% pooled human serum) were added into the cell culture inserts (upper chamber) and cell culture supernatants (300 ml), were added to the lower chamber of the well. After a 48 h incubation period, cells were fixed with 4% paraformaldehyde and permeabilised with PBS containing 0.3% Tritron X-100. Then, nuclei were stained with 49,6-diamidino-2phenylindole (DAPI). The upper side of the membrane was wiped with a wet swab to remove the cells, while the lower side of the membrane was rinsed with PBS. The number of cells at the lower side of each membrane was quantified by counting of cells from three randomly chosen sections (3.7 mm 2 ) using an Olympus IX 1 fluorescence microscope (Olympus, Planegg, Germany). Cells were lysed in Triton X-sample buffer and separated by SDS-PAGE. Nuclear extract were prepared using the Nuclear Extract Kit (Active Motif, Carlsbad, CA, USA) following the manufacturer's instruction. Proteins were detected using specific antibodies against bactin (Sigma-Aldrich Chemie GmbH, Munich, Germany), JNK, phosphorylated JNK, p38, or phosphorylated p38, (all purchased from New England Biolabs GmbH, Frankfurt am Main, Germany) and were visualised by enhanced chemiluminescence using a commercially available kit (Amersham, Freiburg, Germany). Reactive oxygen species (ROS) were detected using the Image-iT LIVE Green Reactive Oxygen Species Kit (Molecular Probes, distributed by Invitrogen, Karlsruhe, Germany). Two groups were compared by t-test. More groups were compared by ANOVA with subsequent Student-Newman-Keuls test. The A549 cell line, derived from a human pulmonary adenocarcinoma, is an established model for type II pneumocytes [36] , and commonly used for the investigation of the effect of influenza viruses on this cell type [see e.g. 6,37,38]. If not otherwise stated, glycyrrhizin was continuously present in cell culture media starting with a 1 h preinfection period. Glycyrrhizin 200 mg/ml (the maximum tested concentration) did not affect A549 cell viability (data not shown) but clearly decreased CPE formation in A549 cells infected with the H5N1 influenza strain A/Thailand/1(Kan-1)/04 at MOIs of 0.01, 0.1 or 1 ( Figure 1A ). Similar results were obtained in A549 cells infected with strain A/Vietnam/1203/04 (H5N1) (Suppl. Figure 1A) . Staining of A549 cells for influenza A nucleoprotein 24 h after infection with strain H5N1 A/Thailand/1(Kan-1)/04 indicated that glycyrrhizin 200 mg/ml significantly reduces the number of influenza A nucleoprotein positive cells ( Figure 1B) . To examine the influence of glycyrrhizin on virus progeny, A549 cells were infected with the H5N1 influenza strain A/ Thailand/1(Kan-1)/04 at MOI 0.01 or MOI 1 and infectious virus titres were determined 24 h post infection ( Figure 1C ). While glycyrrhizin in concentrations up to 50 mg/ml did not affect H5N1 replication, moderate effects were exerted by glycyrrhizin 100 mg/ ml and more pronounced effects by glycyrrhizin 200 mg/ml (MOI 0.01: 13-fold reduction, MOI 1: 10-fold reduction). Next, influence of glycyrrhizin on H5N1 replication was confirmed by the detection of viral (H5) RNA using quantitative PCR. Only glycyrrhizin concentrations $100 mg/ml significantly reduced Figure 1B) or H5N1 A/Vietnam/1203/04-infected (Suppl. Figure 1C ) A549 cells (MOI 0.01) 24 h post infection. Time-of-addition experiments revealed that maximal effects were achieved when glycyrrhizin was continuously present starting with a 1 h pre-incubation period ( Figure 1D ). Addition of glycyrrhizin post infection showed reduced antiviral effects while pre-incubation alone or glycyrrhizin addition during the adsorption period did not significantly affect H5N1 replication. For investigation of H5N1-induced cytokine expression, five pro-inflammatory genes were chosen that had been correlated to severity of influenza disease: CXCL10 (also known as interferon-cinducible protein 10, IP-10), interleukin 6 (IL6), interleukin 8, (IL8; also known as CXCL8), CCL2 (also known as monocyte chemoattractant protein 1, MCP-1), and CCL5 (also known as RANTES). A549 cells were infected with H5N1 A/Thailand/ 1(Kan-1)/04 or H5N1 A/Vietnam/1203/04 at MOI 0.01, 0.1, or 1. Glycyrrhizin treatment was performed with 25, 50, 100, or 200 mg/ml. Cytokine expression was detected 24 h post infection by ELISA.\nQuestion: What is the effect of oseltamivir and zanamivir?", "role": "user" }, { "content": "neuraminidase inhibitors", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: This system uses multiple DVNs to handle different tasks, and can perform different tasks in\n\nKeyphrases: multiple tasks\n\nDataset descriptions:\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\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.\nMicrosoft Research Multimodal Aligned Recipe Corpus: To construct the MICROSOFT RESEARCH MULTIMODAL ALIGNED RECIPE CORPUS the authors first extract a large number of text and video recipes from the web. The goal is to find joint alignments between multiple text recipes and multiple video recipes for the same dish.\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.\n\nOptions: A: CIFAR-10 B: ReCAM C: Microsoft Research Multimodal Aligned Recipe Corpus D: JIGSAWS", "role": "user" }, { "content": "CIFAR-10", "role": "assistant" } ]

[ { "content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What is the basis of the capture Hi-C experimental protocol?\nContext: We use Capture Hi-C to investigate, for the first time, the interactions between associated variants for four autoimmune diseases and their functional targets in B- and T-cell lines.\nChromosome conformation capture implemented in Hi-C allows for genome-wide agnostic characterization of chromatin contacts.\nHere we develop a capture Hi-C (cHi-C) approach to allow an agnostic characterization of these physical interactions on a genome-wide scale.\nCapture Hi-C (CHi-C), which, by incorporating a sequence capture step into a Hi-C protocol, allows high-resolution analysis of targeted regions of the genome.\nHere we use Capture Hi-C (CHi-C), an adapted genome conformation assay, to examine the long-range interactions of almost 22,000 promoters in 2 human blood cell types.\nHere we use high-throughput chromosome conformation capture techniques (Hi-C) for 19,023 promoter fragments to catalog the regulatory landscape of colorectal cancer in cell lines, mapping CREs and integrating these with whole-genome sequence and expression data from The Cancer Genome Atlas7,8\nTo address this, Capture Hi-C (CHi-C) enriches standard Hi-C libraries for regions of biological interest, for example by specifically targeting gene promoters, aiding identification of biologically significant chromatin interactions compared to conventional Hi-C, for an equivalent number of sequence reads\nWe developed Promoter Capture Hi-C (PCHi-C) to enable the genome-wide detection of distal promoter-interacting regions (PIRs), for all promoters in a single experiment.\nHere, we use Capture Hi-C (CHi-C) to annotate 63 loci; we identify 110 putative target genes at 33 loci.", "role": "user" }, { "content": "Capture Hi-C (CHi-C), which, by incorporating a sequence capture step into a Hi-C protocol, allows high-resolution analysis of targeted regions of the genome. To address this, Capture Hi-C (CHi-C) enriches standard Hi-C libraries for regions of biological interest, for example by specifically targeting gene promoters, aiding identification of biologically significant chromatin interactions compared to conventional Hi-C, for an equivalent number of sequence reads We use Capture Hi-C to investigate, for the first time, the interactions between associated variants for four autoimmune diseases and their functional targets in B- and T-cell lines. We developed Promoter Capture Hi-C (PCHi-C) to enable the genome-wide detection of distal promoter-interacting regions (PIRs), for all promoters in a single experiment. Here we use high-throughput chromosome conformation capture techniques (Hi-C) for 19,023 promoter fragments to catalog the regulatory landscape of colorectal cancer in cell lines, mapping CREs and integrating these with whole-genome sequence and expression data from The Cancer Genome Atlas7,8 Here we use Capture Hi-C (CHi-C), an adapted genome conformation assay, to examine the long-range interactions of almost 22,000 promoters in 2 human blood cell types.", "role": "assistant" } ]

[ { "content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Is transcription of eRNA bidirectional?\n\nContext: In addition to widespread transcription of long non-coding RNAs (lncRNAs) in mammalian cells, bidirectional ncRNAs are transcribed on enhancers, and are thus referred to as enhancer RNAs (eRNAs).\nKallikrein-related peptidase 3 (KLK3), which codes for prostate-specific antigen (PSA), is a well-known AR-regulated gene and its upstream enhancers produce bidirectional enhancer RNAs (eRNAs), termed KLK3e.\nThe distal enhancer of the gonadotropin hormone α-subunit gene, chorionic gonadotropin alpha (Cga), is responsible for Cga cell-specific expression in gonadotropes and thyrotropes, and we show here that it encodes two bidirectional nonpolyadenylated RNAs whose levels are increased somewhat by exposure to gonadotropin-releasing hormone but are not necessarily linked to Cga transcriptional activity.\nA richer picture has taken shape, integrating transcription of coding genes, enhancer RNAs (eRNAs), and various other noncoding transcriptional events. In this review we give an overview of recent studies detailing the mechanisms of RNA polymerase II (RNA Pol II)-based transcriptional initiation and discuss the ways in which transcriptional direction is established as well as its functional implications.\nXR-seq maps capture transcription-coupled repair at sites of divergent gene promoters and bidirectional enhancer RNA (eRNA) production at enhancers\nXR-seq maps capture transcription-coupled repair at sites of divergent gene promoters and bidirectional enhancer RNA (eRNA) production at enhancers.\nThe distal enhancer of the gonadotropin hormone α-subunit gene, chorionic gonadotropin alpha (Cga), is responsible for Cga cell-specific expression in gonadotropes and thyrotropes, and we show here that it encodes two bidirectional nonpolyadenylated RNAs whose levels are increased somewhat by exposure to gonadotropin-releasing hormone but are not necessarily linked to Cga transcriptional activity.\nUsing this approach, we have defined a class of primary transcripts (eRNAs) that are transcribed uni- or bidirectionally from estrogen receptor binding sites (ERBSs) with an average transcription unit length of ∼3-5 kb.\nXR-seq maps capture transcription-coupled repair at sites of divergent gene promoters and bidirectional enhancer RNA (eRNA) production at enhancers.\nWe identify 76 enhancer RNAs (eRNAs), 40 canonical lncRNAs, 65 antisense lncRNAs and 35 regions of bidirectional transcription (RBT) that are differentially expressed in response to bacterial lipopolysaccharide (LPS).\nXR-seq maps capture transcription-coupled repair at sites of divergent gene promoters and bidirectional enhancer RNA (eRNA) production at enhancers.\nInstead, communication between promoters and enhancers can be bidirectional with promoters required to activate enhancer transcription.\nA new paradigm has emerged in recent years characterizing transcription initiation as a bidirectional process encompassing a larger proportion of the genome than previously thought.", "role": "user" }, { "content": "yes", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: The Characteristics of Heterozygous Protein Truncating Variants in the Human Genome\nArticle:\nAbstract:\nSequencing projects have identified large numbers of rare stop-gain and frameshift variants in the human genome. As most of these are observed in the heterozygous state, they test a gene’s tolerance to haploinsufficiency and dominant loss of function. We analyzed the distribution of truncating variants across 16, 260 autosomal protein coding genes in 11, 546 individuals. We observed 39, 893 truncating variants affecting 12, 062 genes, which significantly differed from an expectation of 12, 916 genes under a model of neutral de novo mutation( p<10−4). Extrapolating this to increasing numbers of sequenced individuals, we estimate that 10. 8% of human genes do not tolerate heterozygous truncating variants. An additional 10 to 15% of truncated genes may be rescued by incomplete penetrance or compensatory mutations, or because the truncating variants are of limited functional impact. The study of protein truncating variants delineates the essential genome and, more generally, identifies rare heterozygous variants as an unexplored source of diversity of phenotypic traits and diseases.\nIntroduction:\nRecent population expansion and limited purifying selection have led to an abundance of rare human genetic variation[1–3] including stop-gain and frameshift mutations. Thus, there is increasing interest in the identification of natural human knockouts[3–8] through the cataloguing of homozygous truncations. However, heterozygous truncation can also lead to deleterious functional consequences through haploinsufficiency due to decreased gene dosage, or through a dominant-negative effect[9, 10]. In order to quantify the importance of heterozygous protein truncating variation, we characterized genes showing fewer de novo truncations in the general population than expected under a neutral model. We hypothesized that there is a set of genes that cannot tolerate heterozygous protein truncating variants( PTVs) because of early life lethality.\nDiscussion:\nThis work identifies a substantial proportion of genes that do not tolerate loss of one of the two gene copies, and by the evidence for a gradient of haploinsufficiency across a large proportion of the coding genome. Heterozygous PTVs are rarely compensated at the gene expression level, as shown in our previous work[13] and in recent analyses[7]. Despite the absence of dosage compensation, Rivas et al. suggest that homeostatic mechanisms at the cellular level maintain biological function[7]. However, we show clear evidence that over 10% of the genes cannot be compensated, while an additional 10 to 15% of truncated genes may be rescued by incomplete penetrance or compensatory mutations, or because the truncating variants are of limited functional impact. The importance of these variants has also been observed in model organisms. Studies in mice show that when homozygous knockout mutants are not viable, up to 71. 7% of heterozygous PTVs have phenotypic consequences[24]. The systematic phenotyping of knockout mice also demonstrates that haploinsufficiency might be more common than generally suspected[25]. However, a practical limitation of the above approaches, in particular in animal studies, is that observation of phenotypes resulting from damaging mutations may require exposure to specific triggers or environmental interactions[6, 25]. In contrast, in humans, life-long exposures may eventually reveal a phenotypic trait or disease associated with heterozygous gene truncations[8]. Here, clinical symptoms could be observed later in life, and present sporadically–not necessarily within a pedigree. This is illustrated by a recent report on the consequences of haploinsufficiency of cytotoxic T-lymphocyte-associated protein 4 gene( CTLA-4) presenting as undiagnosed or misdiagnosed sporadic autoimmune disorder in the second to fifth decades of life[26]. Despite the prevalence of rare heterozygous PTVs, there has been more attention to the occurrence of homozygous truncations( human knockouts). However, the genes that are observed with biallelic PTVs have, as a set, characteristics of dispensability: less conservation, greater redundancy, less biological and cellular centrality, and limited essentiality in mice and cellular models. Thus, we argue that homozygous truncations result from high allele frequency variants that are less likely to carry functional consequences( the exception being recessive disorders in a population). There are a number of possible limitations to the present study. In the modeling work, we analyzed rare variants( less than <1% allele frequency) to focus on de novo events and for consistency with the de novo mutation rates estimated by Samocha et al.[12]. Nevertheless, our estimates held true when the whole analysis was repeated with the smaller subset of singleton variants—singletons possibly reflect false positive sequencing and alignment calls. It was also repeated with all variants irrespective of allele frequency( instead of analyzing variants of less than 1% allele frequency)( S3 Fig). Initially we omitted splice-site variants because of less predictability of the functional consequences. Extending the analysis to include splice-site variants did not change the results and conclusions( S3 Fig and S5 Table). This demonstrates that the results do not originate from a specific subset of variants. We did not have primary control on sequencing coverage for some of the exome sequence datasets that could result in ascertainment errors. To correct for this potential bias, we discarded genes where the observed number of synonymous mutations deviated from expectation. The intolerance of genes to de novo truncation was assessed across combined human populations. Therefore, estimations of the haploinsufficient genome account for the fraction of haploinsufficient genes common to all humans. Intolerance to heterozygous PTVs should be regarded as a different concept than gene sequence conservation. PTVs in a conserved gene might have a recessive mode of inheritance and are thus potentially observable in a viable individual. On the other extreme, positively selected genes could be haploinsufficient upon heterozygous truncation. These considerations notwithstanding, we consistently identified a quantifiable fraction of the human genome that is intolerant to heterozygous PTVs, with an estimated lower bound of 9. 5%. The prevalent nature of rare heterozygous PTVs suggests that a map of “essentiality” on the basis of dominant loss of function is within reach. The concept of the essential genome has been explored in analyses of minimal bacterial genomes[27], mouse knockout studies[28], studies of transposon or chemical mutagenesis[29], and in studies that used CRISPR-Cas9 genome-editing technology[14, 30]. Here, we propose that mapping the haploinsufficient genome will improve the understanding of the genetic architecture of diseases. In agreement with the recent work of Li et al.,[6] we argue that the burden of rare human heterozygous variation is an unexplored source of diversity of phenotypic traits and diseases.", "role": "user" }, { "content": "Genome sequencing provides evidence for large numbers of putative protein truncating variants in humans . Most truncating variants are only observed in few individuals but are collectively prevalent and widely distributed across the coding genome . Most of the truncating variants are so rare that they are only observed in heterozygosis . The current study identifies 10% of genes where heterozygous truncations are not observed and describes their biological characteristics . In addition , for genes where rare truncations are observed , we argue that these are an unexplored source of diversity of phenotypic traits and diseases .", "role": "assistant" } ]

[ { "content": "Summarize the paper:\n\nPaper text:\n\nWe investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs.\nAs our main theoretical contribution, we clarify the situation with bias in GAN loss functions raised by recent work: we show that gradient estimators used in the optimization process for both MMD GANs and Wasserstein GANs are unbiased, but learning a discriminator based on samples leads to biased gradients for the generator parameters.\nWe also discuss the issue of kernel choice for the MMD critic, and characterize the kernel corresponding to the energy distance used for the Cramér GAN critic.\nBeing an integral probability metric, the MMD benefits from training strategies recently developed for Wasserstein GANs.\nIn experiments, the MMD GAN is able to employ a smaller critic network than the Wasserstein GAN, resulting in a simpler and faster-training algorithm with matching performance.\nWe also propose an improved measure of GAN convergence, the Kernel Inception Distance, and show how to use it to dynamically adapt learning rates during GAN training.\nGenerative Adversarial Networks (GANs; BID10 provide a powerful method for general-purpose generative modeling of datasets.\nGiven examples from some distribution, a GAN attempts to learn a generator function, which maps from some fixed noise distribution to samples that attempt to mimic a reference or target distribution.\nThe generator is trained to trick a discriminator, or critic, which tries to distinguish between generated and target samples.\nThis alternative to standard maximum likelihood approaches for training generative models has brought about a rush of interest over the past several years.\nLikelihoods do not necessarily correspond well to sample quality BID13 , and GAN-type objectives focus much more on producing plausible samples, as illustrated particularly directly by Danihelka et al. (2017) .\nThis class of models has recently led to many impressive examples of image generation (e.g. Huang et al., 2017a; Jin et al., 2017; Zhu et al., 2017) .GANs\nare, however, notoriously tricky to train (Salimans et al., 2016) . This\nmight be understood in terms of the discriminator class. BID10\nshowed that, when the discriminator is trained to optimality among a rich enough function class, the generator network attempts to minimize the Jensen-Shannon divergence between the generator and target distributions. This\nresult has been extended to general f -divergences by Nowozin et al. (2016) . According\nto BID1 , however, it is likely that both the GAN and reference probability measures are supported on manifolds within a larger space, as occurs for the set of images in the space of possible pixel values. These manifolds\nmight not intersect at all, or at best might intersect on sets of measure zero. In this case, the\nJensen-Shannon divergence is constant, and the KL and reverse-KL divergences are infinite, meaning that they provide no useful gradient for the generator to follow. This helps to explain\nsome of the instability of GAN training.The lack of sensitivity to distance, meaning that nearby but non-overlapping regions of high probability mass are not considered similar, is a long-recognized problem for KL divergence-based discrepancy measures (e.g. Gneiting & Raftery, 2007, Section 4.2) . It is natural to address\nthis problem using Integral Probability Metrics (IPMs; Müller, 1997) : these measure the distance between probability measures via the largest discrepancy in expectation over a class of \"well behaved\" witness functions. Thus, IPMs are able to signal\nproximity in the probability mass of the generator and reference distributions. (Section 2 describes this framework\nin more detail.) BID1 proposed to use the Wasserstein\ndistance between distributions as the discriminator, which is an integral probability metric constructed from the witness class of 1-Lipschitz functions. To implement the Wasserstein critic,\nArjovsky et al. originally proposed weight clipping of the discriminator network, to enforce k-Lipschitz smoothness. Gulrajani et al. (2017) improved on\nthis result by directly constraining the gradient of the discriminator network at points between the generator and reference samples. This new Wasserstein GAN implementation\n, called WGAN-GP, is more stable and easier to train.A second integral probability metric used in GAN variants is the maximum mean discrepancy (MMD), for which the witness function class is a unit ball in a reproducing kernel Hilbert space (RKHS). Generative adversarial models based on\nminimizing the MMD were first considered by Li et al. (2015) and Dziugaite et al. (2015) . These works optimized a generator to minimize\nthe MMD with a fixed kernel, either using a generic kernel on image pixels or by modeling autoencoder representations instead of images directly. BID9 instead minimized the statistical power\nof an MMD-based test with a fixed kernel. Such approaches struggle with complex natural\nimages, where pixel distances are of little value, and fixed representations can easily be tricked, as in the adversarial examples of BID10 .Adversarial training of the MMD loss is thus an\nobvious choice to advance these methods. Here the kernel MMD is defined on the output of\na convolutional network, which is trained adversarially. Recent notable work has made use of the IPM representation\nof the MMD to employ the same witness function regularization strategies as BID1 and Gulrajani et al. (2017) , effectively corresponding to an additional constraint on the MMD function class. Without such constraints, the convolutional features are unstable\nand difficult to train BID9 . Li et al. (2017b) essentially used the weight clipping strategy of\nArjovsky et al., with additional constraints to encourage the kernel distribution embeddings to be injective. 1 In light of the observations by Gulrajani et al., however, we use\na gradient constraint on the MMD witness function in the present work (see Sections 2.1 and 2.2).2 Bellemare et al. (2017) 's method, the Cramér GAN, also used the gradient\nconstraint strategy of Gulrajani et al. in their discriminator network. As we discuss in Section 2.3, the Cramér GAN discriminator is related to\nthe energy distance, which is an instance of the MMD (Sejdinovic et al., 2013) , and which can therefore use a gradient constraint on the witness function. Note, however, that there are important differences between the Cramér GAN\ncritic and the energy distance, which make it more akin to the optimization of a scoring rule: we provide further details in Appendix A. Weight clipping and gradient constraints are not the only approaches possible: variance features (Mroueh et al., 2017) and constraints (Mroueh & Sercu, 2017) can work, as can other optimization strategies (Berthelot et al., 2017; Li et al., 2017a) .Given that both the Wasserstein distance and the MMD are integral probability\nmetrics, it is of interest to consider how they differ when used in GAN training. Bellemare et al. (2017) showed that optimizing the empirical Wasserstein distance\ncan lead to biased gradients for the generator, and gave an explicit example where optimizing with these biased gradients leads the optimizer to incorrect parameter values, even in expectation. They then claim that the energy distance does not suffer from these problems. As\nour main theoretical contribution, we substantially clarify the bias situation\nin Section 3. First, we show (Theorem 1) that the natural maximum mean discrepancy estimator, including\nthe estimator of energy distance, has unbiased gradients when used \"on top\" of a fixed deep network representation. The generator gradients obtained from a trained representation, however, will be biased relative\nto the desired gradients of the optimal critic based on infinitely many samples. This situation is exactly analogous to WGANs: the generator's gradients with a fixed critic are\nunbiased, but gradients from a learned critic are biased with respect to the supremum over critics.MMD GANs, though, do have some advantages over Wasserstein GANs. Certainly we would not expect the MMD on its own to perform well on raw image data, since these\ndata lie on a low dimensional manifold embedded in a higher dimensional pixel space. Once the images are mapped through appropriately trained convolutional layers, however, they can\nfollow a much simpler distribution with broader support across the mapped domain: a phenomenon also observed in autoencoders (Bengio et al., 2013) . In this setting, the MMD with characteristic kernels BID4 shows strong discriminative performance\nbetween distributions. To achieve comparable performance, a WGAN without the advantage of a kernel on the transformed space\nrequires many more convolutional filters in the critic. In our experiments (Section 5), we find that MMD GANs achieve the same generator performance as WGAN-GPs\nwith smaller discriminator networks, resulting in GANs with fewer parameters and computationally faster training. Thus, the MMD GAN discriminator can be understood as a hybrid model that plays to the strengths of both\nthe initial convolutional mappings and the kernel layer that sits on top.", "role": "user" }, { "content": "Explain bias situation with MMD GANs; MMD GANs work with smaller critic networks than WGAN-GPs; new GAN evaluation metric.", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to train a fully-supervised convolutional neural network to classify images.\n\nKeyphrases: image classification\n\nDataset descriptions:\nHelen: The HELEN dataset is composed of 2330 face images of 400×400 pixels with labeled facial components generated through manually-annotated contours along eyes, eyebrows, nose, lips and jawline.\nBirdsnap: Birdsnap is a large bird dataset consisting of 49,829 images from 500 bird species with 47,386 images used for training and 2,443 images used for testing.\nGoPro: The GoPro dataset for deblurring consists of 3,214 blurred images with the size of 1,280×720 that are divided into 2,103 training images and 1,111 test images. The dataset consists of pairs of a realistic blurry image and the corresponding ground truth shapr image that are obtained by a high-speed camera.\nImageNet: The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection.\n\nOptions: A: Helen B: Birdsnap C: GoPro D: ImageNet", "role": "user" }, { "content": "ImageNet", "role": "assistant" } ]

[ { "content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: The impairment of mPFC in BD may be due, in part, to the symptoms of prominent cognitive and behavioral problems, including difficulties in making appropriate decisions (Minassian et al. 2004; Van der Gucht et al. 2009), which accompanied with bipolar mania.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Identify relationships between chemical compounds and genes in this abstract. Use only these relation types: ['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\nFormat your output as a JSON array with entries like [\"<Entity_A>\", \"<RELATION_A_B>\", \"<Entity_B>\"].\n\nAbstract:\nSUR-dependent modulation of KATP channels by an N-terminal KIR6.2 peptide. Defining intersubunit gating interactions. Ntp and Ctp, synthetic peptides based on the N- and C-terminal sequences of K (IR) 6.0, respectively, were used to probe gating of K (IR) 6.0/SUR K (ATP) channels. Micromolar Ntp dose-dependently increased the mean open channel probability in ligand-free solution (P (O (max))) and attenuated the ATP inhibition of K (IR) 6.2/SUR1, but had no effect on homomeric K (IR) 6.2 channels. Ntp (up to approximately 10 (-4) m) did not affect significantly the mean open or \" fast, \" K (+) driving force-dependent, intraburst closed times, verifying that Ntp selectively modulates the ratio of mean burst to interburst times. Ctp and Rnp, a randomized Ntp, had no effect, indicating that the effects of Ntp are structure specific. Ntp opened K (IR) 6.1/SUR1 channels normally silent in the absence of stimulatory Mg (-) nucleotide (s) and attenuated the coupling of high-affinity sulfonylurea binding with K (ATP) pore closure. These effects resemble those seen with N-terminal deletions (DeltaN) of K (IR) 6.0, and application of Ntp to DeltaNK (ATP) channels decreased their P (O (max)) and apparent IC (50) for ATP in the absence of Mg (2 +). The results are consistent with a competition between Ntp and the endogenous N terminus for a site of interaction on the cytoplasmic face of the channel or with partial replacement of the deleted N terminus by Ntp, respectively. The K (IR) N terminus and the TMD0-L0 segment of SUR1 are known to control the P (O (max)). The L0 linker has been reported to be required for glibenclamide binding, and DeltaNK (IR) 6.2/SUR1 channels exhibit reduced labeling of K (IR) with (125) I-azidoglibenclamide, implying that the K (IR) N terminus and L0 of SUR1 are in proximity. We hypothesize that L0 interacts with the K (IR) N terminus in ligand-inhibited K (ATP) channels and put forward a model, based on the architecture of BtuCD, MsbA, and the KcsA channel, in which TMD0-L0 links the MDR-like core of SUR with the K (IR) pore.", "role": "user" }, { "content": "[[\"N\", \"PART-OF\", \"K (IR\"], [\"125) I-azidoglibenclamide\", \"DIRECT-REGULATOR\", \"K (IR\"], [\"sulfonylurea\", \"DIRECT-REGULATOR\", \"K (ATP\"], [\"ATP\", \"INHIBITOR\", \"DeltaNK (ATP) channels\"]]", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nAssociation of ATP-binding cassette transporter variants with the risk of Alzheimer's disease. Aim: A number of studies have demonstrated that ABCB1 and BCRP (ABCG2) actively transport Aβ. We aimed to investigate the association of genetic variants of selected multidrug transporters with Alzheimer's disease (AD) in histopathologically confirmed AD cases and controls. Materials & methods: DNA from brain tissue of 71 AD cases with Consortium to Establish a Registry for Alzheimer's Disease (CERAD) neuropathological stages B/C and 81 controls was genotyped for selected variants in ABCA1, ABCA7, ABCB1, ABCC2 and ABCG2. In addition, the APOE4 status was analyzed. Results: The novel ABCA7 SNP, rs3752246, tended to be associated with AD in our study. Variants in ABCB1 were significantly less frequent in AD cases older than 65 years of age and among females. This association of ABCB1 2677G>T (rs2032582) was more pronounced in APOE4-negative cases (p = 0.005). However, only ABCC2 3972C>T (rs3740066) was significantly associated with AD risk after logistic regression analysis including all variants. Other transporters showed a lack of association. Conclusion: Our results support the hypothesis that ABCB1 and possibly other ABC-transporters are involved in the process of Aβ accumulation in the aging brain and may modulate the risk for AD in an allele-specific manner, and thus might represent a new target for prevention and treatment of AD. Original submitted 8 October 2012; Revision submitted 22 January 2013.", "role": "user" }, { "content": "{\"Chemical\": [\"ATP\"]}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Face masks may be inadvertently giving people Covid-19 immunity and making them get less sick from the virus\n\nAbstract:\nWe identified seasonal human coronaviruses, influenza viruses and rhinoviruses in exhaled breath and coughs of children and adults with acute respiratory illness.\nSurgical face masks significantly reduced detection of influenza virus RNA in respiratory droplets and coronavirus RNA in aerosols, with a trend toward reduced detection of coronavirus RNA in respiratory droplets.\nOur results indicate that surgical face masks could prevent transmission of human coronaviruses and influenza viruses from symptomatic individuals.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Surgical face masks significantly reduced detection of influenza virus RNA in respiratory droplets and coronavirus RNA in aerosols, with a trend toward reduced detection of coronavirus RNA in respiratory droplets.\", \"Our results indicate that surgical face masks could prevent transmission of human coronaviruses and influenza viruses from symptomatic individuals.\"]}", "role": "assistant" } ]

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

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Survey of Privacy Data Protection Technology in Cloud Computing \nChapter Title: Cipher text retrieval \n1. Abstract of Cited Paper (BIB001): The cloud storage based information retrieval service is a promising technology that will form a vigorous market in the near future. Although there have been numerous studies proposed about secure data retrieval over encrypted data in cloud services, most of them focus on providing the strict security for the data stored in a third party domain. However, those approaches require stupendous costs centralized on the cloud service provider, which could be a principal impediment to achieve efficient data retrieval in cloud storage. In this paper, we propose an efficient data retrieval scheme using attribute-based encryption. The proposed scheme is best suited for cloud storage systems with massive amount of data. It provides rich expressiveness as regards access control and fast searches with simple comparisons of searching entities. The proposed scheme also guarantees data security and user privacy during the data retrieval process.\n\nLiterature Review:", "role": "user" }, { "content": "Cipher text retrieval is based on the method of index or the cipher text. In order to improve the efficiency of retrieval and protect the privacy of users, the encrypted BIB001 (Encryption Searchable) can be searched. At present, according to the different construct algorithms, Cipher text retrieval mechanism is divided into two categories: Searchable Symmetric Encryption (SSE) mechanism, which is based on symmetric cryptography algorithms, and Public Key Encryption with Keyword Search (PEKS), which is based on public key cryptography algorithm. In order to support the multi user encrypted retrieval in Cloud computing platform, and support the search conditions of complex logic, the Based Searchable Encryption BIB002 (ABSE) mechanism is proposed. ABSE mechanism defines keyword with attributes, which can express the search conditions better. When users search the keywords, search evidence is generated according to the attributes and then is sent to the cloud computing platform. The Cloud computing platform immediately finds the correct results through all the cipher texts.", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nCrystal Structure of the Redox-Active Cofactor DBMIB Bound to Circadian Clock Protein KaiA and Structural Basis for DBMIB\\xe2\\x80\\x99s Ability to Prevent Stimulation of KaiC Phosphorylation by KaiA\n\nPaper sections:\n\n<p>In the photosynthetic cyanobacterium Synechococcus elongatus (S. elongatus) the KaiA, KaiB and KaiC proteins constitute a post-translational circadian oscillator (PTO).1–4 The discovery that regular patterns of KaiC phosphorylation and dephosphorylation with a period of 24 hours are generated when the three proteins are incubated in a test tube in the presence of ATP,5 rendered this system an attractive target for biochemical and biophysical investigations of the inner workings of a molecular clock. The central cog, KaiC, exhibits auto-phosphorylation and -dephosphorylation,6,7 as well as ATPase activities.8 Dephosphorylation proceeds via a phosphotransferase mechanism that returns phosphates from Ser and Thr residues back to ADP, thus endowing KaiC also with an ATP synthase activity.9 KaiA enhances KaiC phosphorylation,10,11 and KaiB antagonizes KaiA action.11,12</p><p>The input and output pathways of the clock comprise a variety of factors that transmit environmental cues to the inner timer and deliver temporal information based on the phosphorylation loop to downstream cellular processes that include clock-controlled gene expression, respectively (reviewed in refs. 3 and 4). Proteins participating in the input pathway that have been characterized to date include LdpA13,14 and CikA.15,16 Both are redox-active factors; whereas CikA is a histidine kinase LdpA is an iron sulphur protein. CikA was shown to be required for resetting of the phase of the rhythm following a dark pulse,15 and mutations in the protein resulted in shortened periods of the oscillator and altered patterns of KaiC phosphorylation.</p><p>The brominated and water-soluble plastoquinone (PQ) analog 2,5-dibromo-3-methyl-6-isopropyl-p-benzoquinone (DBMIB; Figure 1)17 was found to destabilize both LdpA and CikA.14 Interestingly, the so-called pseudoreceiver (PsR) domain of CikA is able to bind DBMIB and a series of additional quinone analogs,18,19 thus implicating this His kinase in indirect information transfer on the light environment to the central cyanobacterial timer via redox changes in bound quinone.18</p><p>A more recent study also established binding between the PsR domain of KaiA and DBMIB and therefore provided evidence for KaiA acting as a sensor of environmental signals and modulating the circadian clock as a result of changes in the redox state.20 Accordingly, the oxidized but not the reduced form of DBMIB binds to KaiA and induces protein oligomerization, ultimately preventing KaiA from binding to KaiC and stimulating phosphorylation of the latter.20 KaiA forms a domain-swapped dimer21 (Figure 1), whereby the N-terminal domains (N-KaiA) adopt a PsR-like fold11,21 and the C-terminal α-helical bundle domains (C-KaiA)22,23 are responsible for dimerization and KaiC binding.24 Native polyacrylamide gel electrophoresis (PAGE) in conjunction with NMR solution experiments supported binding of DBMIB to the N-KaiA PsR domain as the underlying cause of protein aggregation.20 Conversely, lack of mobility changes in native PAGE assays of mixtures of the C-KaiA and DBMIB appeared to argue against an involvement of this domain in light-induced control of the clock mediated by KaiA. However, this study did not attempt to characterize the binding modes of DBMIB in greater detail.</p><p>To establish the precise KaiA binding sites and coordination modes of DBMIB, we determined the crystal structure of full-length S. elongatus KaiA soaked in a solution of the oxidized form of DBMIB at a resolution of 2.38 Å (see the Supporting Information for experimental details, Table S1 for refinement parameters, Figures S1 and S2 for the quality of the final electron density, Figure S3 for KaiA loop conformations, and Figure S4 for a temperature factor analysis). We established four unique binding sites for DBMIB (DBMIBs 1–4; Figure 1), such that each KaiA dimer in the crystal is surrounded by eight DBMIB molecules (Figure S5; the KaiA dimer does not adopt crystallographic twofold symmetry). DBMIB 1 is located between the N- and C-KaiA domains from different subunits at dimer interface III. DBMIBs 2 and 4 are interacting mainly with N-KaiA, but like molecule 1, they establish contacts to domains from symmetry-related KaiAs. By contrast, DBMIB 3 is bound at dimer interface I of C-KaiA domains and is exclusively associated with one KaiA dimer (Figure 1), thus revealing an unexpected binding mode.</p><p>Closer examination of the binding modes of DBMIB molecules reveals common features and a preference for a particular folding topology (Figure S6). In all four cases, the quinone analog sits adjacent to the N-terminus of an α-helix that is preceded by a turn involving proline (Figures 1, 2). For DBMIBs 1, 2 and 4, the turn is between a β-strand and the α-helix and DBMIB 3 sits close to a turn between α-helices. Whereas P115a is located at some distance from DBMIB 1 (Figure 2A), DBMIB 3 actually stacks onto P229a (Figure 2C) and DBMIBs 2 and 4 are associated with P61b and P61a, respectively (Figure 2B, D). With DBMIB 1 and DMBIB 4, a lysine and an arginine, respectively, snake along the aromatic moiety of the binder, thus providing a hydrophobic platform. In two cases there is potential for formation of a halogen bond involving close vicinity (< 3.3 Å) between an electronegative moiety (keto or caboxylate oxygen) and bromine (marked by an asterisk in Figure 2 panels A and B). Further, DBMIBs 2 and 4 are adjacent to newly built loops in the complex structure [missing in the native KaiA structure21 (Figure S2, SI file)] and establish indirect or direct contacts with a residue from the loop (i.e. S87b, DBMIB 2, and R85a, DMBIB 4, resp.).</p><p>In addition to the above similarities, there are a number of differences between the binding modes of individual DBMIB molecules. For example, DBMIB 1 is wedged between two antiparallel amide moieties, the top one contributed by E112a and the bottom one by K189b, such that the keto oxygen of E112a establishes a water-mediated contact to a DBMIB keto oxygen (Figure 2A). In the case of DBMIB 2, a tight turn in the N-KaiA backbone sits atop the aromatic moiety and amide N-H groups from S62b and R64b (Figure 2B) are directed toward DBMIB keto oxygens. An N-H from a third residue (F63b) forms a hydrogen bond to the keto oxygen from N60b three residues away, thus tying together the turn, with the hydrogen bond positioned more or less parallel to the DBMIB ring.</p><p>The locations of DBMIB binding sites allow a more detailed understanding of the cofactor's mode of action in terms of transmitting environmental cues, i.e. light conditions, to the KaiABC timer. Residues from the N-KaiA PsR-like domain are responsible for the majority of interactions seen for DBMIBs 1, 2 and 4 (Figure 2; N-KaiA domains of the original dimer in the crystal are colored in pink). Residues interacting with DBMIB (i.e. E112a and K189b; DBMIB 1), closely associated with DBMIB (i.e. A59b, water-mediated; DBMIB 2) or DBMIB atoms themselves (i.e. Br2, DBMIB 2) then establish contacts to N-KaiA domains from symmetry mates, consistent with the aggregation model.20 The coordination site observed for DBMIB 1, stitching together PsR N-KaiA and C-KaiA domains (Figure 2A), and the improved ordering of loops directly associated with cofactor binding (DBMIB 2, 4; Figure 2B, D) are also pointing in the direction of reduced flexibility and potentially aggregation.</p><p>The association of DBMIB 3 exclusively with C-KaiA domains prompted us to examine an additional mode of interference of DBMIB with KaiA-stimulated phosphorylation of KaiC. The binding site of DBMIB 3 overlaps with a portion of the binding interface between KaiC C-terminal peptide and KaiA dimer24 (Figure 3), but cannot be expected to result in a bandshift in native PAGE.20 Whereas the structure of the C-KaiA:KaiC peptide complex in solution discloses binding of two peptides per KaiA dimer,24 in the crystal the site equivalent to the one occupied by DBMIB 3 on the opposite side of the dimer is sealed off by a lattice contact between KaiA symmetry mates. SDS-PAGE assays of C-KaiA-stimulated KaiC phosphorylation in the presence and absence of the oxidized form of DBMIB reveal a slightly impaired activity of KaiA in the former case (Figure 4, top two panels), providing support for DBMIB affecting KaiC-peptide binding.</p><p>In summary, the binding modes of several of the DBMIB molecules visualized in the crystal structure of the KaiA:DBMIB complex are consistent with N-KaiA PsR-domain aggregation20 and reduced KaiA inter-domain flexibility. The newly discovered DBMIB associated with C-KaiA alone together with the reduced ability of this domain to enhance KaiC phosphorylation in the presence of DBMIB suggest a more complex involvement of the cofactor in the mediation of the clock's light input pathway.</p><p>\n Supporting Information\n</p><p>Methods and materials, Table S1 and Figures S1-S8. This material is available free of charge via the Internet at http://pubs.acs.org.</p><p>\n Accession Codes\n</p><p>The PDB code (http://www.rcsb.org) for the complex is 4G86.</p><p>The authors declare no competing financial interest.</p>", "role": "user" }, { "content": "KaiA protein that stimulates KaiC phosphorylation in the cyanobacterial circadian clock was recently shown to be destabilized by dibromothymoquinone (DBMIB), thus revealing KaiA as a sensor of the plastoquinone (PQ) redox state and suggesting an indirect control of the clock by light through PQ redox changes. Here we show using X-ray crystallography that several DBMIBs are bound to KaiA dimer. Some binding modes are consistent with oligomerization of N-terminal KaiA pseudoreceiver domains and/or reduced inter-domain flexibility. DBMIB bound to the C-terminal KaiA (C-KaiA) domain and limited stimulation of KaiC kinase activity by C-KaiA in the presence of DBMIB demonstrate that the cofactor may weakly inhibit KaiA-KaiC binding.", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a new member of the coronavirus family that can cause coronavirus disease 2019 (COVID-19). COVID-9 has become a global pandemic with severe health issues around the world. Identifying the accurate immunopathogenesis of the COVID-19 and the immune response against SARS-CoV-2 is necessary for the development of therapeutic approaches and rational drug design. This paper aims to overview the updated clinical data on the immunopathogenesis of the COVID-19 and review the innate and adaptive immune response to SARS-CoV-2. Also, challenges of the immune response to SARS-CoV-2 leading to dysfunctional immune response and their contribution to the progression of the disease have been discussed. To achieve a more efficient immune response, multiple methods could be applied, including regulation of the immune response, augmentation of the immune system against the virus, inhibition of the dysfunctional immune checkpoints, and inhibition of the viral replication/infection. Based on the immune response against SARS-CoV-2 and its dysfunction, we introduce potential immunotherapies as well as reviewing recruiting/completed clinical trials of COVID-19.", "role": "user" }, { "content": "[\"Treatment\", \"Mechanism\"]", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Coronaviruses are generally thought to be spread from person-to-person through respiratory droplets.\n\nAbstract:\nThe current outbreak of the novel coronavirus disease 2019 (COVID-19) in more than 250 countries has become a serious threat to the health of people around the world.\nHuman-to-human transmission of the Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) occurs most often when people are in the incubation stage of the disease or are carriers and have no symptoms.\nTherefore, in this study, was discussed the role of environmental factors and conditions such as temperature, humidity, wind speed as well as food, water and sewage, air, insects, inanimate surfaces, and hands in COVID-19 transmission.\nThe results of studies on the stability of the SARS-CoV-2 on different levels showed that the resistance of this virus on smooth surfaces was higher than others.\nTemperature increase and sunlight can facilitate the destruction of SARS-COV-2 and the stability of it on surfaces.\nWhen the minimum ambient air temperature increases by 1 °C, the cumulative number of cases decreases by 0.86%.\nAccording to the latest evidence, the presence of coronavirus in the sewer has been confirmed, but there is no evidence that it is transmitted through sewage or contaminated drinking water.\nAlso, SARS-COV-2 transmission through food, food packages, and food handlers has not been identified as a risk factor for the disease.\nAccording to the latest studies, the possibility of transmitting SARS-COV-2 bioaerosol through the air has been reported in the internal environment of ophthalmology.\nThe results additionally show that infectious bio-aerosols can move up to 6 feet.\nThere have been no reports of SARS-COV-2 transmission by blood-feeding arthropods such as mosquitoes.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nFacile regiodivergent synthesis of spiro pyrrole-substituted pseudothiohydantoins and thiohydantoins via reaction of [<i>e</i>]-fused 1<i>H</i>-pyrrole-2,3-diones with thiourea\n\nPaper sections:\nIntroduction\n<p>Hydantoin (imidazolidine-2,4-dione) derivatives are omnipresent among biologically active compounds [1]. Many of them are commercially available drugs, for example, anticonvulsants phenytoin [2] and albutoin [3], the muscle relaxant dantrolene [4], or the nonsteroidal antiandrogen agent enzalutamide [5] (Figure 1). Despite this fact, hydantoin derivatives belong to a special group of scaffolds in medicinal chemistry. Indeed, they are structurally related to rhodanine (2-thioxothiazolidin-4-one), and sometimes are classified as pan-assay interference compounds (PAINS), which are abhorrent in high-throughput screenings [6]. To clarify whether such compounds are privi-Scheme 2: Syntheses of regioisomeric 5-spiro-substituted thiohydantoins and pseudothiohydantoins: previous [10] and this work. leged scaffolds or promiscuous binders, Mendgen and co-workers performed a systematic comparative study on rhodanines and related structures with respect to their medicinal chemistry properties [7]. As a result, it was shown that such structures could be suitable scaffolds for medicinal chemistry under proper conditions of biological evaluation, while their medicinal chemistry properties dramatically depend on the structure of the five-membered heterocyclic moiety and substituents in the C-5 position [7]. Some pseudothiohydantoins (2-iminothiazolidin-4-ones) are known to undergo a pseudothiohydantoin-thiohydantoin rearrangement (PTR, Scheme 1) [8][9][10][11], which is a special case of a quite poorly investigated iminothiolactone-thiolactam rearrangement [12][13][14][15][16]. This reaction offers attractive opportunities for the design of libraries of regioisomeric hydantoin-based compounds for drug discovery. Spiro heterocycles are relatively new and insufficiently investigated structures in medicinal chemistry [17,18]. The introduction of spiro-fused cyclic moieties in small molecules increases the degree of their structural (shape) complexity, which may lead to the reduced binding promiscuity and improved clinical success [19]. Thus, recent development of 3D modelling methods facilitated investigations on the importance of 3D properties of small-molecular drug candidates [20][21][22] and inspired chemists to develop diversity-oriented methods for complex 3D molecules [23,24].</p><p>Considering that to the best of our knowledge, only a sole report exists [10] that describes the synthesis of regioisomeric 5-spiro-substituted thiohydantoins and pseudothiohydantoins and their PTR (Scheme 2), we were encouraged to develop a divergent synthetic approach to access regioisomeric thiohydantoins and pseudothiohydantoins that are spiro-fused to a pharmacologically valuable pyrrole-2-one fragment and to investigate the scope and conditions of their PTR behavior (Scheme 2).</p>\n\nResults and Discussion\n<p>1H-Pyrrole-2,3-diones fused at [e]-side (FPDs) 1 can be viewed as a versatile polyelectrophilic synthetic platform (Figure 2), enabling facile preparation of libraries of heterocyclic molecules with an emphasis on skeletal diversity from a single set of reagents [25][26][27].</p><p>One of the most intriguing chemical properties of FPDs 1 is their ability to undergo a cyclocondensation with 1,3-binucleophilic reagents to form spiro [4.4] heterocycles bearing a pharmacophoric pyrrole-2-one moiety (Scheme 3) [28,29]. We employed this feature as a key step in the development of a straightforward and concise synthetic approach towards regioisomeric thiohydantoins and pseudothiohydantoins spiro-fused to a pyrrole-2-one fragment.</p><p>To test the preparation of the target spiro-fused pseudothiohydantoins and thiohydantoins, we examined the reaction of FPD 1a with thiourea by heating equimolar amounts of the reagents in toluene for 5 min (until the disappearance of the dark violet color of FPD 1a). The reaction mixture was examined by UPLC-MS. Two major products with m/z = 396 ([M + H] + , ESI + ) were observed in a ratio of ≈1:1, which corresponded to adducts of thiourea with FPD 1a. The adducts were isolated, and their structures were elucidated as the desired spiro-fused thiohydantoin 2a and pseudothiohydantoin 3a (Scheme 4).</p><p>It should be pointed out that earlier, we have communicated initial data on this transformation [30,31]. However, taking into account more advanced structure elucidation methods employed in the present work (e.g., NMR, single crystal X-ray diffraction), we concluded that the structures of the products were identified incorrectly, and they are revised herein (for a detailed revision see Supporting Information File 1).</p><p>Next, to find out whether compounds 2a and 3a were prone to undergo PTR, they were heated in open capillaries at 130 °C for 2 h, and the resulting mixtures were examined by UPLC-MS. As a result, we found that compound 2a did not rearrange, and compound 3a partially converted into its regioisomer 2a due to irreversible PTR (Scheme 5).</p><p>Possibly, when carrying out the reaction of FPD 1a with thiourea by refluxing the reaction mixture in toluene, part of the product 3a was converted into 2a because of PTR. We assumed that at lower temperatures, the main product of the reaction could be pseudothiohydantoin 3a. To prove this assumption, we examined the reaction of FPD 1a with thiourea at room temperature in various solvents (Table 1).</p><p>Obviously, the ratio of products 2a and 3a was dependent not only on the temperature of the reaction, but also on the polarity of the solvent. We found that optimal conditions for dominant formation of pseudothiohydantoin 3a were applied by stirring the reaction mixture at room temperature in ethyl or butyl acetate (Table 1, entries 2 and 6). For the development of a convenient procedure for thiohydantoin 2a without isolation of its regioisomer 3a being required, we carried out the reaction of FPD 1a with thiourea in various solvents under reflux (Table 2). As a result of this optimization, we established that thiohydantoin 2a was formed as major product upon refluxing the reaction mixture in butyl acetate or 1,4-dioxane (Table 2, entries 3, 4, and 7). Interestingly, at different reagent ratios, the yield of compound 2a was affected as well (Table 2, entries 3 and 4). When the reagents were mixed prior to heating (Table 2, entry 3), the yield of compound 2a was lower than when the reagents were mixed in the boiling solvent (Table 2, entry 4). Probably, compound 2a was formed not only as a result of the corresponding PTR, but as a result of a concurrent attack of the amino group of thiourea on the C-3a atom of FPD 1a (Scheme 6). Using the optimization data, we obtained a series of spiro-fused thiohydantoins 2a-m and pseudothiohydantoins 3a-m by utilizing various FPDs 1a-n (Table 3). The aryl group-bearing FPDs 1a-m reacted facilely to yield the desired compounds 2 and 3, but ethoxycarbonyl group-bearing FPD 1n reacted unselectively, giving a complex mixture of hardly identifiable products due to the occurrence of multiple side reactions involving the ethoxycarbonyl group.</p><p>Next, we examined the influence of substituents in the thiourea motif on its reaction with FPDs 1. It was found that monosubstituted thioureas (N-methylthiourea, N-phenylthiourea, N-(4chlorophenyl)thiourea, N-(3,5-dimethylphenyl)thiourea, N-(4nitrophenyl)thiourea, and N-1-naphtylthiourea) reacted with FPD 1a unselectively, forming a mixture of four inseparable adducts (the reaction mixtures were analyzed by UPLC-MS) (Scheme 7). Unfortunately, we did not succeed to find any conditions for a selective formation of either of them.</p><p>Unexpectedly, the implementation of N-acetylthiourea in the reaction with FPDs 1, both under conditions A and B (see Ta- ble 3), afforded only one type of adducts, pseudothiohydantoins 4 (Table 4). Boiling compounds 4 in various solvents and heating them in open capillaries at 130 °C for 12 h did not provoke PTR, and compounds 4 remained unconverted. This phenomenon could be explained by the influence of the electron-withdrawing effect of the acetyl group, which reduced the nucleophilic properties of the acetyl-substituted nitrogen atom in N-acetylthiourea and decreased its reactivity, preventing the formation of regioisomeric compounds.</p><p>1,3-Dibutylthiourea reacted smoothly at room temperature in ethyl acetate with FPDs 1 to form mixtures of products 5 and 6</p><p>(Scheme 8). Moreover, it was observed that the percentage of compounds 5 in reaction mixtures increased over time upon storage of the solutions. As such, 6 readily underwent PTR, affording the corresponding compounds 5, but unfortunately, we did not succeed to isolate pseudothiohydantoins 6.</p><p>The reaction of FPDs 1 with 1,3-dibutylthiourea in 1,4-dioxane resulted in exclusive formation of thiohydantoins 5 upon heating at reflux for 2-4 h (Table 5).</p><p>The facility of thiohydantoins 5 formation could be explained by the electron-donating effect of the butyl substituents, which increased the nucleophilicity of the butyl-substituted nitrogen atoms and promoted its attack on the electrophilic center C-3a of FPDs 1.</p><p>The reaction of FPDs 1 with 1,3-diphenylthiourea proceeded in a similar manner. Thiohydantoins 7 were predominantly formed when the reaction was conducted at reflux in 1,4-dioxane, and pseudothiohydantoins 8 were formed as main products at room temperature (Table 6).</p><p>Notably, the formation of thiohydantoins 7 required longer time in comparison with unsubstituted thiourea and 1,3-dibutylthiourea. Possible reasons for this are the influence of the steric hindrance induced by the phenyl substituents and weakening of the nucleophilic properties of the phenyl-substituted nitrogen atom, which prevented a nucleophilic attack of 1,3-diphenylthiourea on the electrophilic center C-3a of FPDs 1.</p><p>The observed PTRs could have proceed through two alternative pathways (Scheme 9), with the first stage being dissociation of the C spiro -S bond [32]</p>\n\nConclusion\n<p>In conclusion, we have developed a divergent approach to pharmaceutically interesting regiomeric thiohydantoins and pseudothiohydantoins spiro-fused to a pyrrole-2-one fragment via the reaction of [e]-fused 1H-pyrrole-2,3-diones with thioureas. The obtained pseudothiohydantoins were found to be prone to undergo a pseudothiohydantoin-thiohydantoin rearrangement. Therein, the substituents of the thiourea moiety were found to be crucial for tuning the conditions of this rearrangement. Notably, the reactions proceeded under catalyst-free conditions with good yields.</p>", "role": "user" }, { "content": "A highly divergent synthesis of regioisomeric thiohydantoins and pseudothiohydantoins spiro-fused to a pharmacologically valuable pyrrole-2-one fragment involving the reaction of [e]-fused 1H-pyrrole-2,3-diones with thioureas was developed. The obtained spiro pseudothiohydantoin derivatives were found to undergo a pseudothiohydantoin-thiohydantoin rearrangement. The reactions were shown to proceed under catalyst-free conditions in good yields, and the products were isolated without applying preparative chromatography methods.", "role": "assistant" } ]

[ { "content": "Based on the RCT reports below, write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article.\n\n\n\nTitle 1:\n[Curettage or not after spontaneous abortion?].\nAbstract 1:\nIn most cases of miscarriage, standard procedure has until recently been surgical revision of the uterine cavity.\n 94 women with first trimester miscarriage were randomized to surgical revision (n = 48) or expectation (n = 46) after informed consent. Women with unacceptable pain or bleeding, or uterine contents of more than 20 mm diameter on sonography were not included. The patients were followed up seven to ten days later with gynaecological examination, sonography, and determination of levels of haemoglobin, leukocytes, C-reactive protein and HCG.\n In the revision group there were no operative complications, no cases of infection, and no unscheduled consultations. Mean duration of bleeding was 4.8 days (range 1-11 days). In the observation group there were no cases of infection, surgical revision was carried out in seven patients, and there were six unscheduled consultations. Mean duration of bleeding was 7.3 days (range 2-27 days). The women undergoing surgical revision had less pain and bleeding.\n Women with first trimester miscarriage may safely be observed without surgical revision but may have somewhat more pain and more vaginal bleeding than if revision is carried out.\n\n\nTitle 2:\nManagement of miscarriage: expectant, medical, or surgical? Results of randomised controlled trial (miscarriage treatment (MIST) trial).\nAbstract 2:\nTo ascertain whether a clinically important difference exists in the incidence of gynaecological infection between surgical management and expectant or medical management of miscarriage.\n Randomised controlled trial comparing medical and expectant management with surgical management of first trimester miscarriage.\n Early pregnancy assessment units of seven hospitals in the United Kingdom.\n Women of less than 13 weeks' gestation, with a diagnosis of early fetal demise or incomplete miscarriage.\n Expectant management (no specific intervention); medical management (vaginal dose of misoprostol preceded, for women with early fetal demise, by oral mifepristone 24-48 hours earlier); surgical management (surgical evacuation).\n Confirmed gynaecological infection at 14 days and eight weeks; need for unplanned admission or surgical intervention.\n 1200 women were recruited: 399 to expectant management, 398 to medical management, and 403 to surgical management. No differences were found in the incidence of confirmed infection within 14 days between the expectant group (3%) and the surgical group (3%) (risk difference 0.2%, 95% confidence interval - 2.2% to 2.7%) or between the medical group (2%) and the surgical group (0.7%, - 1.6% to 3.1%). Compared with the surgical group, the number of unplanned hospital admissions was significantly higher in both the expectant group (risk difference - 41%, - 47% to - 36%) and the medical group (- 10%, - 15% to - 6%). Similarly, when compared with the surgical group, the number of women who had an unplanned surgical curettage was significantly higher in the expectant group (risk difference - 39%, - 44% to - 34%) and the medical group (- 30%, - 35% to - 25%).\n The incidence of gynaecological infection after surgical, expectant, and medical management of first trimester miscarriage is low (2-3%), and no evidence exists of a difference by the method of management. However, significantly more unplanned admissions and unplanned surgical curettage occurred after expectant management and medical management than after surgical management. TRIAL REGISTRATION NATIONAL RESEARCH REGISTER: N0467011677/N0467073587.\n\n\nTitle 3:\nRandomised trial of expectant versus surgical management of spontaneous miscarriage.\nAbstract 3:\nThirty-five women with retained products of conception after spontaneous miscarriage were randomised to expectant (n = 19) or surgical (n = 16) management, respectively. Women were reviewed at one week, two weeks and six months. There were no significant differences in the number of days of pain, bleeding, sick leave or return to normal periods. Nine of twelve women from the expectant group and six of nine from the surgical group who attempted to conceive did so by six months. All 16 women were satisfied with conservative management. This study provides further reassurance when considering expectant management for spontaneous miscarriage both in the short and medium term.\n\n\nTitle 4:\nManagement of miscarriage: a randomized controlled trial of expectant management versus surgical evacuation.\nAbstract 4:\nIn many countries, surgical uterine evacuation is the standard treatment for women with a miscarriage, but expectant management has been advocated as an alternative. The choice between the two options cannot be based on published evidence alone, because randomized clinical trials are scarce while generalizability of findings to patients with a strong preference for either management options is unclear.\n In a randomized controlled trial, the complications and efficacy of either expectant or surgical management for miscarriages were compared, and the results in patients who refused randomization and were managed according to their own preference were studied. In total, 122 patients were randomized and 305 were managed according to their choice.\n No differences were found in the number of emergency curettages and complications between expectant and surgical management. Efficacy at 6 weeks was 30/64 (47%) in women allocated to expectant management, and 55/58 (95%) in women allocated to surgical evacuation. After 7 days, 37% of expectantly managed women had a spontaneous complete miscarriage. After 6 weeks, intention-to-treat analysis including cross-overs showed similar effectiveness (92% versus 100%). Results in the preference groups were comparable with those in the randomized groups.\n In our experience a waiting period of 7 days after diagnosis may prevent 37% of surgical procedures.\n\n\nTitle 5:\nA randomised trial of surgical, medical and expectant management of first trimester spontaneous miscarriage.\nAbstract 5:\nMedical management and expectant care have been considered possible alternatives to surgical evacuation of the uterus for first trimester spontaneous miscarriage in recent years.\n To compare the effectiveness and safety of medical and expectant management with surgical management for first trimester incomplete or inevitable miscarriage.\n Forty women were recruited following diagnosis of incomplete or inevitable miscarriage, and randomised to surgical, medical or expectant care via an off-site, computerised enrollment system. The primary outcome was the effectiveness of medical (vaginal misoprostol) and expectant management relative to surgical evacuation, assessed at 10-14 days and 8 weeks post-recruitment. Infection, pain, bleeding, anxiety, depression, physical and emotional recovery were assessed also. Analysis was by intention-to-treat.\n Effectiveness at 8 weeks was lower for medical (80.0%) and expectant (78.6%) than for surgical management (100.0%). Two women in the medical group had confirmed infections. Bleeding lasted longer in the expectant group than in the surgical group. There were no significant differences in pain, physical recovery, anxiety or depression between the groups. 54.6%, 42.9% and 57.1% of the surgical, medical and expectant groups respectively would opt for the same treatment again.\n Expectant care appears to be sufficiently safe and effective to be offered as an option for women. Medical management might carry a higher risk of infection than surgical or expectant care.\n\n\nTitle 6:\nExpectant management of first-trimester spontaneous abortion.\nAbstract 6:\nApproximately 15% of registered pregnancies end in spontaneous abortion, and for 50 years or so dilatation and curettage (D&C) has been the usual management. In a prospective randomised trial we compared the clinical results after either expectant management or D&C, for miscarriages of less than 13 weeks' gestation in which transvaginal ultrasound examination showed intrauterine tissue and/or blood clots with a diameter 15-50 mm. 103 patients were randomised to expectant management and spontaneous resolution of pregnancy occurred within 3 days in 81 cases (79%). 52 patients were randomised to D&C. 3 infections were diagnosed among patients who underwent expectant management (3%); 5 infections and 1 case of postoperative anaemia were observed among patients randomised to D&C (11%). The duration of vaginal bleeding was a mean of 1.3 days longer in the expectant management group (p < 0.02). Convalescence time, time during which patients experienced pain, and packed-cell volume 3 and 14 days after inclusion did not differ significantly between the groups. This study shows that expectant management of selected cases of spontaneous abortion has a similar outcome to D&C.", "role": "user" }, { "content": "Expectant management led to a higher risk of incomplete miscarriage, need for unplanned (or additional) surgical emptying of the uterus, bleeding and need for transfusion. Risk of infection and psychological outcomes were similar for both groups. Costs were lower for expectant management. Given the lack of clear superiority of either approach, the woman's preference should be important in decision making. Pharmacological ('medical') management has added choices for women and their clinicians and has been examined in other reviews.", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey of Public-Key Cryptosystems \nChapter Title: XTR \n1. Abstract of Cited Paper (BIB001): The cryptographic properties of third-order linear feedback shift-register (LFSR) sequences over GF(p) are investigated. A fast computational algorithm for evaluating the kth term of a characteristic sequence of order 3 is presented. Based on these properties, a new public-key distribution scheme and an RSA-type encryption algorithm are proposed. Their security, implementation, information rate, and computational cost for the new schemes are discussed. \n2. Abstract of Cited Paper (BIB002): This paper introduces the XTR public key system. XTR is based on a new method to represent elements of a subgroup of a multiplicative group of a finite field. Application of XTR in cryptographic protocols leads to substantial savings both in communication and computational overhead without compromising security. \n3. Abstract of Cited Paper (BIB003): We show that finding an efficiently computable injective homomorphism from the XTR subgroup into the group of points over GF(p2) of a particular type of supersingular elliptic curve is at least as hard as solving the Diffie–Hellman problem in the XTR subgroup. This provides strong evidence for a negative answer to the question posed by Vanstone and Menezes at the Crypto 2000 Rump Session on the possibility of efficiently inverting the MOV embedding into the XTR subgroup. As a side result we show that the Decision Diffie–Hellman problem in the group of points on this type of supersingular elliptic curves is efficiently computable, which provides an example of a group where the Decision Diffie–Hellman problem is simple, while the Diffie–Hellman and discrete logarithm problems are presumably not. So-called distortion maps on groups of points on elliptic curves that play an important role in our cryptanalysis also lead to cryptographic applications of independent interest. These applications are an improvement of Joux’s one round protocol for tripartite Diffie–Hellman key exchange and a non-refutable digital signature scheme that supports escrowable encryption. We also discuss the applicability of our methods to general elliptic curves defined over finite fields which includes a classification of elliptic curve groups where distortion maps exist.\n\nLiterature Review:", "role": "user" }, { "content": "A special case of the Diffie-Hellman system, proposed by A. K. Lenstra and E. R. Verheul BIB003 (see also BIB002 ), has aroused considerable interest. As in §5, one works in the subgroup G of prime order N in the multiplicative group of the finite field F q . We take q = p 6 , where p is a prime that is ≡ 2 (mod 3), and N is chosen so that it divides the factor p 2 − p + 1 of p 6 − 1 (in which case the subgroup G is not contained in any proper subfield of F q ). In practice N should have roughly the same bitlength as p; it is recommended that both have about 170 bits, in which case q has over 1000 bits. It is not hard to set up the parameters N and p. For example, if r is chosen so that both r 2 − r + 1 and r 2 + 1 are prime, then one can set N = r 2 − r + 1 and p = N + r = r 2 + 1 (in which case obviously A crucial innovation in BIB003 is that the elements of G can be represented using only 2 log 2 p bits rather than log 2 q = 6 log 2 p bits. Moreover, exponentiation can be done directly with these short representations. This leads to greater efficiency and short key sizes comparable to those in elliptic curve cryptography. Since the mathematics is relatively simple (as in RSA), Lenstra and Verheul feel that their system \"may be regarded as the best of two worlds, RSA and ECC [elliptic curve cryptography]\" (p. 2 of BIB003 ). The group used in XTR is closely related to the group of points on a certain supersingular elliptic curve defined over F p 2 . In fact, the Weil pairing embedding in BIB001 maps this elliptic curve group to precisely the XTR group. Since the publication of BIB001 , the existence of this reduction map from a supersingular elliptic curve to the multiplicative group of a finite field has traditionally been considered to be a security weakness arguing against the use of supersingular curves. Thus, some cryptographers have doubted the wisdom of using a system that is closely related to a version of elliptic curve cryptography that had been rejected. However, Verheul BIB004 has pointed out that the Weil pairing embedding reduces the elliptic curve DLP to the XTR group DLP, not viceversa; and he believes that the DLP in their group is likely to be strictly harder than the DLP on the curve. In addition, the Boneh-Lynn-Shacham signature scheme described in §6.5 shows that supersingular elliptic curves should not be automatically ruled out for use in cryptography. By the same token, XTR also deserves serious study and consideration.", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nCannabisin B induces autophagic cell death by inhibiting the AKT/mTOR pathway and S phase cell cycle arrest in HepG2 cells. This study investigates the anticancer properties of cannabisin B, purified from hempseed hull, in HepG2 human hepatoblastoma cells. The results indicate that cannabisin B significantly inhibited cell proliferation by inducing autophagic cell death rather than typical apoptosis. Cell viability transiently increased upon the addition of a low concentration of cannabisin B but decreased upon the addition of high concentrations. Cannabisin B-induced changes in cell viability were completely inhibited by pre-treatment with 3-methyladenine (3-MA), indicating that the induction of autophagy by cannabisin B caused cell death. Additionally, cannabisin B induced S phase cell cycle arrest in a dose-dependent manner. Moreover, cannabisin B was found to inhibit survival signaling by blocking the activation of AKT and down-stream targets of the mammalian target of rapamycin (mTOR). These findings suggest that cannabisin B possesses considerable antiproliferative activity and that it may be utilised as a promising chemopreventive agent against hepatoblastoma disease.", "role": "user" }, { "content": "{\"Chemical\": [\"3-methyladenine\", \"Cannabisin B\", \"rapamycin\", \"cannabisin B\", \"3-MA\"]}", "role": "assistant" } ]

[ { "content": "Find all entities of these types in the text: [\"Gene\"].\n\nOutput a JSON object.\n\nText:\nAutophagy suppresses Ras-driven epithelial tumourigenesis by limiting the accumulation of reactive oxygen species. Activation of Ras signalling occurs in ~30% of human cancers; however, activated Ras alone is not sufficient for tumourigenesis. In a screen for tumour suppressors that cooperate with oncogenic Ras (Ras(V12)) in Drosophila, we identified genes involved in the autophagy pathway. Bioinformatic analysis of human tumours revealed that several core autophagy genes, including GABARAP, correlate with oncogenic KRAS mutations and poor prognosis in human pancreatic cancer, supporting a potential tumour-suppressive effect of the pathway in Ras-driven human cancers. In Drosophila, we demonstrate that blocking autophagy at any step of the pathway enhances Ras(V12)-driven epithelial tissue overgrowth via the accumulation of reactive oxygen species and activation of the Jun kinase stress response pathway. Blocking autophagy in Ras(V12) clones also results in non-cell-autonomous effects with autophagy, cell proliferation and caspase activation induced in adjacent wild-type cells. Our study has implications for understanding the interplay between perturbations in Ras signalling and autophagy in tumourigenesis, which might inform the development of novel therapeutics targeting Ras-driven cancers.Oncogene advance online publication, 5 June 2017; doi:10.1038/onc.2017.175.", "role": "user" }, { "content": "{\"Gene\": [\"Jun kinase\", \"GABARAP\", \"Ras\", \"KRAS\", \"Ras(V12)\"]}", "role": "assistant" } ]

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

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Widely used drugs to control high blood pressure do not help protect against severe Covid-19\n\nAbstract:\nOBJECTIVE: To investigate the association between hypertension and outcome in patients with Coronavirus Disease 2019 (COVID-19) pneumonia.\nMETHODS: We performed a systematic literature search from several databases on studies that assess hypertension and outcome in COVID-19.\nComposite of poor outcome, comprising of mortality, severe COVID-19, acute respiratory distress syndrome (ARDS), need for intensive care unit (ICU) care and disease progression were the outcomes of interest.\nRESULTS: A total of 6560 patients were pooled from 30 studies.\nHypertension was associated with increased composite poor outcome (risk ratio (RR) 2.11 (95% confidence interval (CI) 1.85, 2.40), p < 0.001; I2, 44%) and its sub-group, including mortality (RR 2.21 (1.74, 2.81), p < 0.001; I2, 66%), severe COVID-19 (RR 2.04 (1.69, 2.47), p < 0.001; I2 31%), ARDS (RR 1.64 (1.11, 2.43), p = 0.01; I2,0%, p = 0.35), ICU care (RR 2.11 (1.34, 3.33), p = 0.001; I2 18%, p = 0.30), and disease progression (RR 3.01 (1.51, 5.99), p = 0.002; I2 0%, p = 0.55).\nMeta-regression analysis showed that gender (p = 0.013) was a covariate that affects the association.\nThe association was stronger in studies with a percentage of males < 55% compared to ⩾ 55% (RR 2.32 v. RR 1.79).\nCONCLUSION: Hypertension was associated with increased composite poor outcome, including mortality, severe COVID-19, ARDS, need for ICU care and disease progression in patients with COVID-19.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Extract drug combinations from this sentence and classify each combination into one of these categories:\n- POS: Positive interaction between drugs\n- NEG: Negative interaction between drugs\n- COMB: Drugs used together with unknown interaction type\n\nOutput only a JSON array where each entry is [drug_1, drug_2, ..., drug_n, category].\n\nparagraph: Neoadjuvant trastuzumab , pertuzumab , and chemotherapy versus trastuzumab emtansine plus pertuzumab in patients with HER2-positive breast cancer ( KRISTINE ): a randomised , open-label , multicentre , phase 3 trial . HER2-targeted treatments have improved outcomes in patients with HER2-positive breast cancer in the neoadjuvant, adjuvant, and metastatic settings; however, some patients remain at risk of relapse or death for many years after treatment of early-stage disease. Therefore, new strategies are needed. We did a phase 3 trial to assess a neoadjuvant regimen for HER2-positive breast cancer that replaces traditional systemic chemotherapy with targeted treatment. ### methods We did a randomised, open-label phase 3 KRISTINE trial in 68 Translational Research In Oncology centres (hospitals and specialty cancer centres in Asia, Europe, USA, and Canada). Eligible participants were aged 18 years or older with centrally confirmed HER2-positive stage II-III operable breast cancer (>2 cm tumour size), an Eastern Cooperative Oncology Group performance status of 0-1, and a baseline left ventricular ejection fraction of at least 55% (by echocardiogram or multiple-gated acquisition scan). We randomly assigned participants (1:1) to receive either trastuzumab emtansine plus pertuzumab or docetaxel, carboplatin, and trastuzumab plus pertuzumab. We did the randomisation via an interactive response system under a permuted block randomisation scheme (block size of four), stratified by hormone receptor status, stage at diagnosis, and geographical location. Patients received six cycles (every 3 weeks) of neoadjuvant trastuzumab emtansine plus pertuzumab (trastuzumab emtansine 3·6 mg/kg; pertuzumab 840 mg loading dose, 420 mg maintenance doses) or docetaxel, carboplatin, and trastuzumab plus pertuzumab (docetaxel 75 mg/m ### findings Between June 25, 2014, and June 15, 2015, we randomly assigned 444 patients to neoadjuvant treatment with trastuzumab emtansine plus pertuzumab (n=223) or docetaxel, carboplatin, and trastuzumab plus pertuzumab (n=221). A pathological complete response was achieved by 99 (44·4%) of 223 patients in the trastuzumab emtansine plus pertuzumab group and 123 (55·7%) of 221 patients in the docetaxel, carboplatin, and trastuzumab plus pertuzumab group (absolute difference -11·3 percentage points, 95% CI -20·5 to -2·0; p=0·016). During neoadjuvant treatment, compared with patients receiving docetaxel, carboplatin, and trastuzumab plus pertuzumab, fewer patients receiving trastuzumab emtansine plus pertuzumab had a grade 3-4 adverse event (29 [13%] of 223 vs 141 [64%] of 219) or a serious adverse event (11 [5%] of 223 vs 63 [29%] of 219). The most common grade 3-4 adverse events in the trastuzumab emtansine plus pertuzumab group were decreased platelet count (three [1%] of 223 patients vs 11 [5%] of 219 with docetaxel, carboplatin, and trastuzumab plus pertuzumab), fatigue (three [1%] vs seven [3%]), alanine aminotransferase increase (three [1%] vs four [2%]), and hypokalaemia (three [1%] vs five [2%]). The most common grade 3-4 adverse events in the docetaxel, carboplatin, and trastuzumab plus pertuzumab group were neutropenia (55 [25%] of 219 vs one [<1%] of 223 with trastuzumab emtansine plus pertuzumab), diarrhoea (33 [15%] vs 2 [<1%]), and febrile neutropenia (33 [15%] vs 0). No deaths were reported during neoadjuvant treatment. ### interpretation Traditional neoadjuvant systemic chemotherapy plus dual HER2-targeted blockade (docetaxel, carboplatin, and trastuzumab plus pertuzumab) resulted in significantly more patients achieving a pathological complete response than HER2-targeted chemotherapy plus HER2-targeted blockade (trastuzumab emtansine plus pertuzumab); however, numerically more grade 3-4 and serious adverse events occurred in the chemotherapy plus trastuzumab and pertuzumab group. Further efforts to improve the efficacy of chemotherapy without imparting more toxicity are warranted. ### funding F Hoffmann-La Roche and Genentech.\n\nsentence: Neoadjuvant trastuzumab , pertuzumab , and chemotherapy versus trastuzumab emtansine plus pertuzumab in patients with HER2-positive breast cancer ( KRISTINE ): a randomised , open-label , multicentre , phase 3 trial .", "role": "user" }, { "content": "[[\"trastuzumab\", \"pertuzumab\", \"trastuzumab emtansine\", \"pertuzumab\", \"POS\"]]", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey and Tutorial of Electromagnetic Radiation and Reduction in Mobile Communication Systems \nChapter Title: E. Massive MIMO \n1. Abstract of Cited Paper (BIB001): Presents a list of articles published by the IEEE Signal Processing Society (SPS) that ranked among the top 100 most downloaded IEEE Xplore articles. \n2. Abstract of Cited Paper (BIB002): Multi-user MIMO offers big advantages over conventional point-to-point MIMO: it works with cheap single-antenna terminals, a rich scattering environment is not required, and resource allocation is simplified because every active terminal utilizes all of the time-frequency bins. However, multi-user MIMO, as originally envisioned, with roughly equal numbers of service antennas and terminals and frequency-division duplex operation, is not a scalable technology. Massive MIMO (also known as large-scale antenna systems, very large MIMO, hyper MIMO, full-dimension MIMO, and ARGOS) makes a clean break with current practice through the use of a large excess of service antennas over active terminals and time-division duplex operation. Extra antennas help by focusing energy into ever smaller regions of space to bring huge improvements in throughput and radiated energy efficiency. Other benefits of massive MIMO include extensive use of inexpensive low-power components, reduced latency, simplification of the MAC layer, and robustness against intentional jamming. The anticipated throughput depends on the propagation environment providing asymptotically orthogonal channels to the terminals, but so far experiments have not disclosed any limitations in this regard. While massive MIMO renders many traditional research problems irrelevant, it uncovers entirely new problems that urgently need attention: the challenge of making many low-cost low-precision components that work effectively together, acquisition and synchronization for newly joined terminals, the exploitation of extra degrees of freedom provided by the excess of service antennas, reducing internal power consumption to achieve total energy efficiency reductions, and finding new deployment scenarios. This article presents an overview of the massive MIMO concept and contemporary research on the topic. \n3. Abstract of Cited Paper (BIB003): We consider the problem of designing transmit beamformer and power for downlink cooperative base-station (BS) system with a large antenna arrays. Since the design of the beamforming vector at the transmitter requires high computational complexity, in a large antenna arrays, we utilize the zero-forcing transmit beamformer, which is the simplest form and the optimal performance in a large antenna arrays. Therefore, this paper focuses on the design of power allocation with fixed transmit beamformer for minimizing the transmit power while meeting target signal-to-interference-and-noise-ratio (SINR) of each user and power constraints. We consider two scenarios according to the power constraints of cooperative BSs. One scenario is the sum power constraint on the cooperative base-stations. In this case, the cooperative BSs share the total available transmit power. However, each BS exists a maximum available transmit power in practical implementations. Thus, we consider a more realistic per BS power constraints.We proposed the solution strategies for both scenarios: For the sum power constraint case, a simple intuitive solution, where the power is allocated without regard to the power constraint until the SINR constraints is satisfied, is presented. For the per BS power constraints case, we use the properties of a large antenna arrays to find the solution of closed form. We also demonstrate, via numerical simulation, the performance of proposed strategy is convergent to the optimal performance which is achieved by using the iterative algorithm. \n4. Abstract of Cited Paper (BIB004): A multiplicity of autonomous terminals simultaneously transmits data streams to a compact array of antennas. The array uses imperfect channel-state information derived from transmitted pilots to extract the individual data streams. The power radiated by the terminals can be made inversely proportional to the square-root of the number of base station antennas with no reduction in performance. In contrast if perfect channel-state information were available the power could be made inversely proportional to the number of antennas. Lower capacity bounds for maximum-ratio combining (MRC), zero-forcing (ZF) and minimum mean-square error (MMSE) detection are derived. An MRC receiver normally performs worse than ZF and MMSE. However as power levels are reduced, the cross-talk introduced by the inferior maximum-ratio receiver eventually falls below the noise level and this simple receiver becomes a viable option. The tradeoff between the energy efficiency (as measured in bits/J) and spectral efficiency (as measured in bits/channel use/terminal) is quantified for a channel model that includes small-scale fading but not large-scale fading. It is shown that the use of moderately large antenna arrays can improve the spectral and energy efficiency with orders of magnitude compared to a single-antenna system.\n\nLiterature Review:", "role": "user" }, { "content": "Massive MIMO, also known as very large MIMO, is an emerging technology whereby a BS with a large number of small antennas, an order of magnitude higher than in current MIMO systems, simultaneously serves a much smaller number of mobile users in the same time-frequency resource. Each antenna in the system uses extremely low power such that the power per antenna is inversely proportional to the number of antennas in the BS BIB002 . The large number of antennas significantly reduces the transmit power of the BS which could result in lower EM radiation exposure levels BIB003 - BIB004 . Fig. 8 depicts the concept of massive MIMO. Massive MIMO utilizes spatial multiplexing which relies on accurate knowledge of the CSI both in the uplink and downlink. In the uplink, mobile users send pilot signals to the BS which then estimates the CSI between itself and the user terminal. However, obtaining the CSI is a bit more challenging in the downlink as each mobile user would have to estimate the channel responses between itself and each antenna at the BS and feed them back to the BS. This could be computationally and time demanding as the number of antennas at the BS increases. A solution to this problem is to operate massive MIMO systems in the time division duplex (TDD) mode. It relies on the reciprocity between the uplink and downlink channels and, thus, the BS can estimate the CSI by using the uplink pilots BIB003 . Massive MIMO also has the potential of considerably increasing spectral efficiency through aggressive spatial multiplexing and significantly improving energy-efficiency by using very low-power antennas and amplifiers BIB002 . It has been shown in BIB005 that massive MIMO could increase energy-efficiency by 3 orders of magnitude by using simple linear processing such as maximum ratio combining (MRC) and zero forcing (ZF) at the BS. The authors in BIB001 have shown that the transmit power of mobile terminals in massive MIMO systems is inversely proportional to the number of antennas at the BS, when there is perfect knowledge of the CSI, and inversely proportional to the square root of the number of antennas at the BS if the information about the channel is imperfect. Given that massive MIMO is a relatively new technology, there is no research work on massive MIMO that explicitly focuses on reducing EM radiation exposure, to the best of our knowledge. However, the direct relationship between transmit power and EM radiation, and the fact that massive MIMO has the ability to reduce the transmit power of mobile terminals by at least the square-root of the number of antennas at the BS, depending on the CSI quality, imply that implementing massive MIMO could reduce the SAR of mobile terminals by a factor of at least the square-root of the number of antennas at the BS.", "role": "assistant" } ]

[ { "content": "Extract all unique entities of these types from the following clinical trial criteria: [\"Negation\", \"Observation\", \"ReferencePoint\", \"Procedure\", \"Drug\", \"Measurement\", \"Value\", \"Person\", \"Multiplier\", \"Device\", \"Qualifier\", \"Mood\", \"Temporal\", \"Condition\", \"Visit\", \"Scope\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities are found for a type, use [].\n\nText:\n\nActive opioid dependence\nAcute or chronic pain requiring opioid treatment\nAcute liver injury (liver aminotransferase concentrations >5 times the upper limit of normal)\nHealth condition considered unsafe for inclusion (at discretion of PI and/or attending physician)\nLack of capacity or willingness to consent\nCurrently prescribed pharmacotherapy for alcohol dependence (not including treatment of acute alcohol withdrawal syndrome)\nPrevious significant adverse reaction to naltrexone or diluent\nPregnant, nursing, or not using effective methods of birth control\nPrisoners (as defined by Office of Human Research Protection) at the time of enrollment ARE NOT ELIGIBLE for study entry. However, subjects who become prisoners after being enrolled will be included and not be withdrawn from the study. Patients on parole or probation are eligible for enrollment.", "role": "user" }, { "content": "{\"Condition\": [\"pain\", \"Acute liver injury\", \"alcohol dependence\", \"acute alcohol withdrawal syndrome\", \"opioid dependence\", \"Pregnant\", \"nursing\", \"Health condition\", \"adverse reaction\"], \"Device\": [], \"Drug\": [\"diluent\", \"naltrexone\"], \"Measurement\": [\"liver aminotransferase concentrations\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [\"Lack of\", \"not including\", \"not\"], \"Observation\": [\"willingness to consent\", \"city or onsent\\nCur\"], \"Person\": [\"Prisoners\"], \"Procedure\": [\"birth control\", \"treatment\", \"opioid treatment\", \"pharmacotherapy\"], \"Qualifier\": [\"Active\", \"considered unsafe for inclusion\", \"Office of Human Research Protection\", \"chronic\", \"effective methods\", \"significant\", \"Acute\"], \"ReferencePoint\": [\"the time of enrollment\"], \"Scope\": [\"naltrexone or diluent\", \"Acute or chronic\", \"capacity or willingness to consent\", \"liver aminotransferase concentrations \\u003e5 times the upper limit of normal\"], \"Temporal\": [\"at the time of enrollment\", \"Currently\", \"Previous\"], \"Value\": [\"\\u003e5 times the upper limit of normal\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nInhibition of T cell and promotion of natural killer cell development by the dominant negative helix loop helix factor Id3. Bipotential T / natural killer (NK) progenitor cells are present in the human thymus. Despite their bipotential capacity, these progenitors develop predominantly to T cells in the thymus. The mechanisms controlling this developmental choice are unknown. Here we present evidence that a member (s) of the family of basic helix loop helix (bHLH) transcription factors determines lineage specification of NK / T cell progenitors. The natural dominant negative HLH factor Id3, which blocks transcriptional activity of a number of known bHLH factors, was expressed in CD34 + progenitor cells by retrovirus-mediated gene transfer. Constitutive expression of Id3 completely blocks development of CD34 + cells into T cells in a fetal thymic organ culture (FTOC). In contrast, development into NK cells in an FTOC is enhanced. Thus, the activity of a bHLH transcription factor is necessary for T lineage differentiation of bipotential precursors, in the absence of which a default pathway leading to NK cell development is chosen. Our results identify a molecular switch for lineage specification in early lymphoid precursors of humans.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"T cells\", \"NK / T cell progenitors\", \"NK cells\", \"bipotential precursors\", \"CD34 + cells\", \"Bipotential T / natural killer (NK) progenitor cells\", \"CD34 + progenitor cells\", \"these progenitors\", \"early lymphoid precursors\", \"T cell\"], \"DNA\": [], \"Protein\": [\"dominant negative HLH factor\", \"Id3\", \"bHLH transcription factor\", \"dominant negative helix loop helix factor\", \"basic helix loop helix (bHLH) transcription factors\", \"bHLH factors\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Classify the intent of this citation sentence by choosing from: [\"Method\", \"Background\", \"Result\"].\n\nMethod: Cites for methodology\nBackground: Cites for background information\nResult: Cites for findings\n\nCitation: Conventional meta-analysis proceeds by conducting a separate meta-analysis for each type of treatment against all others [5].", "role": "user" }, { "content": "Method", "role": "assistant" } ]