Datasets:

---

kejian

/

SciRIFF-4096-0214-v1

like 0

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nNuclear Factor κB Mediates Suppression of Canonical Transient Receptor Potential 6 Expression by Reactive Oxygen Species and Protein Kinase C in Kidney Cells. This study was carried out to explore the molecular mechanism for down-regulation of TRPC6 expression in the reactive oxygen species (ROS)/PKC signaling in kidney cells. In cultured human mesangial cells, H2O2 and TNF-α inhibited TRPC6 mRNA expression in a time-dependent manner. Inhibition of NF-κB reversed both H2O2- and phorbol 12-myristate 13-acetate (PMA)-induced decrease in TRPC6 protein expression. Activation of NF-κB by knocking down IκBα using siRNA could mimic the suppressive effect of ROS/PKC on TRPC6. a Ca(2+) imaging study showed that activation and inhibition of NF-κB significantly decreased and increased the TRPC6-mediated Ca(2+) entry, respectively. Further experiments showed that PMA, but not its inactive analog 4α-phorbol 12, 13-didecanoate (4α-PDD), caused phosphorylation of IκBα and stimulated the nuclear translocation of NF-κB p50 and p65 subunits. The PMA-dependent IκBα phosphorylation was significantly inhibited by Gö6976. Electrophoretic mobility shift assay revealed that PMA stimulated DNA binding activity of NF-κB. Furthermore, specific knockdown of p65, but not p50, prevented an H2O2 inhibitory effect on TRPC6 protein expression, suggesting p65 as a predominant NF-κB subunit repressing TRPC6. In agreement with a major role of p65, chromatin immunoprecipitation assays showed that PMA treatment induced p65 binding to the TRPC6 promoter. Moreover, PMA treatment increased the association of p65 with histone deacetylase (HDAC) and decreased histone acetylation at the TRPC6 promoter. Consistently, knockdown of HDAC2 by siRNA or inhibition of HDAC with trichostatin A prevented a H2O2-induced decrease in TRPC6 mRNA and protein expressions, respectively. Taken together, our findings imply an important role of NF-κB in a negative regulation of TRPC6 expression at the gene transcription level in kidney cells.", "role": "user" }, { "content": "{\"Chemical\": [\"phorbol 12-myristate 13-acetate\", \"4\\u03b1-PDD\", \"Oxygen\", \"PMA\", \"trichostatin A\", \"4\\u03b1-phorbol 12, 13-didecanoate\", \"G\\u00f66976\", \"Ca(2+)\", \"H2O2\", \"oxygen\"]}", "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:\nMouse brain serine racemase catalyzes specific elimination of L-serine to pyruvate. D-Serine was previously identified in mammalian brain and was shown to be a co-agonist at the 'glycine' site of the N-methyl-D-aspartate (NMDA) -type receptors. Racemization of serine is catalyzed by serine racemase, a pyridoxal 5'-phosphate-dependent enzyme expressed mainly in brain and liver. NMDA receptor overactivation has been implicated in a number of pathological conditions and inhibitors of serine racemase are thus potentially interesting targets for therapy. We expressed recombinant mouse serine racemase in insect cells and purified it to near homogeneity. The enzyme is a non-covalent homodimer in solution and requires divalent cations Mg (2 +), Ca (2 +) or Mn (2 +) for activity but not for dimerization. In addition to the racemization it also catalyzes specific elimination of L-Ser to pyruvate. D-Serine is eliminated much less efficiently. Both L-serine racemization and elimination activities of serine racemase are of comparable magnitude, display alkaline pH optimum and are negligible below pH 6.5.", "role": "user" }, { "content": "[[\"L-serine\", \"SUBSTRATE\", \"Mouse brain serine racemase\"], [\"serine\", \"SUBSTRATE\", \"serine racemase\"], [\"pyruvate\", \"PRODUCT-OF\", \"Mouse brain serine racemase\"], [\"glycine\", \"PART-OF\", \"N-methyl-D-aspartate (NMDA) -type receptors\"], [\"D-Serine\", \"AGONIST\", \"N-methyl-D-aspartate (NMDA) -type receptors\"]]", "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\nCalcium signalling in T cells stimulated by a cyclophilin B-binding protein. The immunosuppressant drug cyclosporin A blocks a calcium-dependent signal from the T-cell receptor (TCR) that normally leads to T-cell activation. When bound to cyclophilin, cyclosporin A binds and inactivates the key signalling intermediate calcineurin. To identify potential cellular homologues of cyclosporin A that might regulate calcium signalling, we have cloned human genes encoding cyclophilin B-binding-proteins using the yeast two-hybrid system. One gene product, when overexpressed in Jurkat T cells, specifically induced transcription from the interleukin-2 enhancer, by activating the T-cell-specific transcription factors NF-AT and NF-IL2A. This protein, termed calcium-signal modulating cyclophilin ligand (CAML), acts downstream of the TCR and upstream of calcineurin by causing an influx of calcium. CAML appears to be a new participant in the calcium-signal transduction pathway, implicating cyclophilin B in calcium signalling, even in the absence of cyclosporin.", "role": "user" }, { "content": "{\"CellLine\": [\"Jurkat T cells\"], \"CellType\": [\"T cells\"], \"DNA\": [\"interleukin - 2 enhancer\"], \"Protein\": [\"cyclophilin B - binding protein\", \"T - cell receptor\", \"NF - AT\", \"calcium - signal modulating cyclophilin ligand\", \"cyclophilin\", \"T - cell - specific transcription factors\", \"cyclophilin B - binding - proteins\", \"calcineurin\", \"NF - IL2A\", \"cyclophilin B\", \"TCR\", \"CAML\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: The Underlying Molecular and Network Level Mechanisms in the Evolution of Robustness in Gene Regulatory Networks\nArticle:\nAbstract:\nGene regulatory networks show robustness to perturbations. Previous works identified robustness as an emergent property of gene network evolution but the underlying molecular mechanisms are poorly understood. We used a multi-tier modeling approach that integrates molecular sequence and structure information with network architecture and population dynamics. Structural models of transcription factor-DNA complexes are used to estimate relative binding specificities. In this model, mutations in the DNA cause changes on two levels:( a) at the sequence level in individual binding sites( modulating binding specificity), and( b) at the network level( creating and destroying binding sites). We used this model to dissect the underlying mechanisms responsible for the evolution of robustness in gene regulatory networks. Results suggest that in sparse architectures( represented by short promoters), a mixture of local-sequence and network-architecture level changes are exploited. At the local-sequence level, robustness evolves by decreasing the probabilities of both the destruction of existent and generation of new binding sites. Meanwhile, in highly interconnected architectures( represented by long promoters), robustness evolves almost entirely via network level changes, deleting and creating binding sites that modify the network architecture.\nIntroduction:\nRobustness to genetic and environmental perturbations is ubiquitous in biological systems[1]. An abundance of theoretical and experimental evidence has shown robustness operating at many levels ranging from microRNA precursors[2] to metabolic pathways[3] and gene regulatory networks[4]. By definition, genetic robustness will facilitate the accumulation of genetic variation in a population, which in turn may prove useful for adaptation or evolvability[5]–[7]. Previous theoretical studies using gene regulatory network models have shown how robustness evolves under conditions of stabilizing selection[8]. In this class of models, mutations were allowed to alter only the interaction strengths, constraining the model to fixed network architectures. Therefore these models were not suitable to explore potentially important factors such as evolved redundancy[9], modularity[10] and degeneracy[11],[12]. Model refinements that allowed the network architecture itself to evolve have highlighted the importance of network lability even under conditions of stabilizing selection, while making arbitrary and sometimes conflicting assumptions about gain and loss of interactions[13],[14]. The network lability seen in these cases coincides with genomic studies where, for example, high rates of gain and loss of cis-regulatory elements are observed[15]–[17] including cases where function is highly conserved[18]. The actual mechanisms underlying changes in network interactions will predominantly involve mutations at the sequence level in cis-regulatory regions[19],[20] rather than changes in protein sequence and structure[21]. Even though many transcription factors binding sites( TFBSs) have been characterized in detail[22],[23], there is still a limited understanding of the evolutionary forces involved in the creation and maintenance of these TFBSs in the context of a gene regulatory network. Relevant theoretical studies have addressed evolution of cis-regulation by considering single TFBSs or groups of TFBSs within a single cis-regulatory region, for example, by calculating the distribution of canonical site variants under mutation-selection balance[24],[25]. One potential mechanism for achieving robustness at the sequence level is TFBS redundancy[26],[27], i. e., the maintenance of multiple copies of binding sites for a particular transcription factor. A variety of evolutionary forces may be involved in maintaining TFBS redundancy, including recombination within the cis-regulatory region or simply the length of the promoter region, which increases the probability of creating a binding sites de novo[9]. The evolution of robustness in gene regulatory networks is likely to involve mechanisms at both the local-sequence and network-architecture levels. Until now these two levels have been considered separately. Here we present a model that combines these two levels, enabling us to address their relative influence and how they interact in the context of the evolution of robustness. At the sequence level we use structural models of transcription factor( TF)-DNA interactions to estimate binding specificities for all possible DNA binding sites, which allows an explicit sequence-level representation of upstream regulatory regions( URRs) in determining the architecture of the gene regulatory network. Point mutations drive changes at the sequence level of individual TFBSs( which can change the binding specificity) or at the network-architecture level by creating or deleting interactions. Using this model we are able to quantify the relative contributions of the sequence and network level mechanisms to the evolution of robustness. We find that in sparse architectures, reflected in the use of short URRs, a mixture of local-sequence and network-architecture level changes are exploited, whereas in highly interconnected architectures( simulated with long URRs) the balance shifts almost entirely to the network level.\nDiscussion:\nThe available structural information about TF-DNA complexes allowed us to construct an explicit DNA sequence based model of gene regulatory networks for the study of the genetic mechanisms that make a biological system robust to mutations. The level of connectivity and architecture of gene regulatory networks in biological systems is still being explored, therefore in this study we considered and discussed networks that span a range of interconnectedness between genes. While our model has limitations, most notably the simplified model of transcriptional regulation where no restrictions are applied to positioning or interaction between TFBSs, it has allowed us to probe the mechanisms underlying robustness in gene networks at the DNA level. By extending this approach in the future, more detailed questions will become amenable to investigation, for example, understanding the evolutionary forces that shape promoter architectural features such as TFBS clustering and cooperativity. However, addressing questions such as these will require more detailed modeling of the transcriptional process, perhaps by incorporating thermodynamics-based models that include distance-dependent interactions among TFBSs and position dependent negative regulation or repression[28]. The model could also incorporate more complicated population-level mechanisms, such as recombination within promoter regions, as it has been shown to evolve robustness even more efficiently[9]. Our results showed that sparse networks, which could be broadly related to gene regulatory mechanisms in simpler organisms, show a contribution from both local-sequence level and network-architecture level mechanisms to robustness. These sparse networks have difficulties in rewiring connections, since the few available need to be conserved to maintain a viable phenotype. Instead, these networks rely on local-sequence mechanisms, manipulating the genetic sequence to decrease the probability of generating spurious binding sites de novo( TFBS avoidance mechanism) and decrease the probability of losing existing binding sites( TFBS conservation mechanism). When assuming a small specificity gap between non-specific and specific binding( γ), TFBS avoidance becomes a dominant driving force in evolving robustness. On the other hand, when greater robustness in sparse networks is achieved by means of a larger specificity gap, it happens by balancing out TFBS avoidance, TFBS conservation and network rewiring. Meanwhile, in more interconnected networks, which one could relate to higher level organisms, we observe a complete shift towards the use of network-architecture level mechanisms. Specifically, these networks rewire, exploring different network motifs and fixing those that dampen the harmful effects of mutations. We would argue that this rewiring constitutes an increase in complexity of the network. Evolution of network complexity in more interconnected networks thus appears as the dominant source of robustness, especially in networks with a large specificity gap separating binding and non-binding sites. There is evidence in the literature of the existence of all three observed mechanisms. i) TFBS avoidance: Hahn and coworkers examined polymerase binding regions in Eubacteria and Archaea genomes and showed that polymerase binding sites were under-represented in binding-free regions, even more so in Eubacteria[52]. ii) TFBS conservation: Wunderlich and Mirny[53] compared the information content of TFBSs in prokaryotes and eukaryotes, finding that the simpler prokaryotic organisms use TFBSs with higher information content than the more complex eukaryotic organisms. Higher information content is equivalent to higher TFBS conservation values in our simulations, since both measures are directly proportional to the interaction strengths of TFBSs( see Fig. S8 for the relationship with our calculated binding specificities). iii) Network complexity: the use of this mechanism requires extensive turnover of TFBSs and there is evidence in the literature of this phenomenon. For example, Bradley et al. observed that the same genes in closely related species of Drosophila were differently regulated[54] and Ben-Tabou de-Leon and Davidson also showed differences at the promoter level in gene regulatory networks of two related species, the sea star and sea urchin[55]. The existence of network motifs that are robust to interferences have also been previously described[56],[57], but the conditions of their evolution still remains under scrutiny[58]. Depending on the explored parameters in our simulations, we observed a varied interplay of the different mechanisms. While it is uncertain which of them better reflects real biological organisms, it is encouraging that our model demonstrated all the three naturally observed mechanisms. Leclerc[13] previously estimated the number of TF inputs per gene in gene regulatory networks for different organisms and found them to be sparsely connected, with values ranging from 1. 37( Escherichia coli) to 2. 75( Arabidopsis thaliana). However, this analysis did not contain measurements for higher organisms such as mouse or human, for which the number of inputs per gene could be higher given the apparent trend of increasing number of TF inputs per gene with organismal “complexity”. According to these estimates, promoters with more than 100 bp in our linear model would result in unrealistic levels of interconnections. The evolution of increased complexity is a major unaddressed question in Biology[59]. Our results suggest a potential path for increased complexity as a consequence of the shift to network-architecture level changes when more interconnected networks are considered. Two outcomes suggest that network-architecture level changes are more effective at evolving robustness than local-sequence changes. First, local-sequence level changes were not used under high connectivity in spite of also having equal, if not greater, access to these types of changes. This suggests that robustness at the network level is more easily evolved. Second, the increase in robustness is stronger under conditions of high connectivity( Fig. 3A). Thus, high connectivity settings create favorable conditions to employ more effective network-architecture level changes towards evolving robustness.", "role": "user" }, { "content": "Development from egg to embryo depends to a large extent on regulatory networks of genes called transcription factors . Previous research has shown these gene regulatory networks to be robust to perturbations at the level of the connections between transcription factors . Here , we investigate the mechanisms underlying the evolution of robustness in gene networks using a modeling approach , which considers three levels: binding of individual transcription factors to DNA , dynamics of gene expression levels , and fitness effects at the population level . In our model the gene regulatory network is determined by transcription factor binding sites within DNA sequences , which undergo mutation . We categorize these mutations in a continuum ranging from silent mutations , which have no effect on regulation and change only the DNA sequence ( local-sequence level ) , to mutations that change connections between genes in the network ( network-architecture level ) . We find that in sparse networks , containing few connections between genes , a balance of local-sequence and network-architecture level mechanisms are responsible for the evolution of robustness , but when the network is densely connected the network-architecture level mechanisms become dominant . We argue that the shift towards the network-architecture level for more densely-connected networks offers a potential explanation for the evolution of increased complexity .", "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:\nProposed synergistic effect of calcium channel blockers with lipid-lowering therapy in retarding progression of coronary atherosclerosis . Lipid-lowering therapy now has undoubtedly proven to be an effective therapeutic modality to retard the progression of coronary atherosclerosis . An additional approach for prevention of the progression of atherosclerosis is calcium channel blocker ( CCB ) treatment . Evidence indicating that CCBs inhibit atherosclerosis is less unequivocal than the clear evidence for lipid-lowering therapy . Many investigations support the view that a number of key processes in atherosclerosis may be influenced by CCBs . From the \" negative \" and \" positive \" studies with CCBs performed in animals and humans we must conclude that apparently some , but not all , types or stages of the atherosclerotic process are inhibited by CCBs . To assess whether lipid-lowering therapy and CCB treatment may have an additive or synergistic beneficial effect on human atherosclerosis , which is conceivable because their anti-atherosclerotic properties differ , data from the angiographic lipid-lowering trial REGRESS ( pravastatin vs. placebo ) were reviewed . In REGRESS , patients in the pravastatin group had significantly less progression if cotreated with CCBs as compared with those with no CCB cotreatment , whereas in the placebo ( no pravastatin ) group no effect of CCB treatment was observed . With respect to angiographic new lesion formation , in the pravastatin group there were 50 % less patients with new angiographic lesions if cotreated with CCBs as compared with no CCB cotreatment , whereas in the placebo ( no pravastatin ) group , again , no significant effect of CCB treatment was observed . No beneficial effects of CCB treatment on clinical events were observed during the 2-year study follow-up . In view of the correlation between angiographic progression and subsequent clinical events as demonstrated in several large trials , it is not unrealistic to also anticipate in this population , a beneficial effect on clinical events with longer follow-up . Although the REGRESS trial was not designed to evaluate combination therapy , the results suggest that addition of CCBs to HMG-CoA reductase inhibitor therapy ( pravastatin ) acts synergistically in retarding the progression of established coronary atherosclerosis . These results appear to warrant prospective randomized trials to determine in a more definitive manner the merits of this combination in the prevention of progression of coronary atherosclerosis . Currently a number of studies in these fields are being designed or are already underway .", "role": "user" }, { "content": "{\"Intervention\": [\"lipid-lowering therapy\", \"calcium channel blocker ( CCB )\", \"placebo ( no pravastatin )\", \"pravastatin\", \"Lipid-lowering therapy\", \"lipid-lowering therapy .\", \"CCBs\", \"CCB\", \"calcium channel blockers\", \"placebo\"], \"Outcome\": [\"clinical events\", \"angiographic progression\", \"atherosclerosis\", \"progression of atherosclerosis\", \"angiographic new lesion formation\", \"progression of coronary atherosclerosis\", \"progression of established coronary atherosclerosis\", \"angiographic lesions\", \"progression\"], \"Participant\": [\"retarding progression of coronary atherosclerosis\"]}", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: A model to learn a low dimensional feature space.\n\nKeyphrases: image retrieval images text\n\nDataset descriptions:\nMOT15: MOT2015 is a dataset for multiple object tracking. It contains 11 different indoor and outdoor scenes of public places with pedestrians as the objects of interest, where camera motion, camera angle and imaging condition vary greatly.\nMNIST-1D: A minimalist, low-memory, and low-compute alternative to classic deep learning benchmarks. The training examples are 20 times smaller than MNIST examples yet they differentiate more clearly between linear, nonlinear, and convolutional models which attain 32, 68, and 94% accuracy respectively (these models obtain 94, 99+, and 99+% on MNIST).\nRL Unplugged: RL Unplugged is suite of benchmarks for offline reinforcement learning. The RL Unplugged is designed around the following considerations: to facilitate ease of use, the datasets are provided with a unified API which makes it easy for the practitioner to work with all data in the suite once a general pipeline has been established.\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).\n\nOptions: A: MOT15 B: MNIST-1D C: RL Unplugged D: CIFAR-10", "role": "user" }, { "content": "CIFAR-10", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: hand sanitizer is not effective against COVID-19\n\nAbstract:\nBACKGROUND: The emergence of the novel virus, SARS-CoV-2, has posed unprecedented challenges to public health around the world.\nCurrently, strategies to deal with COVID-19 are purely supportive and preventative, aimed at reducing transmission.\nAn effective and simple method for reducing transmission of infections in the public or healthcare settings is hand hygiene.\nUnfortunately, little is known regarding the efficacy of hand sanitizers against SARS-CoV-2.\nMETHODS: In this review, an extensive literature search was performed to succinctly summarize the primary active ingredients and mechanisms of action of hand sanitizers, compare the effectiveness and compliance of gel and foam sanitizers, and predict whether alcohol and non-alcohol hand sanitizers would be effective against SARS-CoV-2.\nRESULTS: Most alcohol based hand sanitizers are effective at inactivating enveloped viruses, including coronaviruses.\nWith what is currently known in the literature, one may not confidently suggest one mode of hand sanitizing delivery over the other.\nWhen hand washing with soap and water is unavailable, a sufficient volume of sanitizer is necessary to ensure complete hand coverage, and compliance is critical for appropriate hand hygiene.\nCONCLUSIONS: By extrapolating effectiveness of hand sanitizers on viruses of similar structure to SARS-CoV-2, this virus should be effectively inactivated with current hand hygiene products, though future research should attempt to determine this directly.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"RESULTS: Most alcohol based hand sanitizers are effective at inactivating enveloped viruses, including coronaviruses.\", \"When hand washing with soap and water is unavailable, a sufficient volume of sanitizer is necessary to ensure complete hand coverage, and compliance is critical for appropriate hand hygiene.\", \"CONCLUSIONS: By extrapolating effectiveness of hand sanitizers on viruses of similar structure to SARS-CoV-2, this virus should be effectively inactivated with current hand hygiene products, though future research should attempt to determine this directly.\"]}", "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:\nTreatment of acute ischaemic stroke with the low-affinity , use-dependent NMDA antagonist AR-R15896AR . A safety and tolerability study . BACKGROUND AND PURPOSE A low-affinity , use-dependent N-Methyl-D-Aspartate ( NMDA ) antagonist AR-R15896AR has neuroprotective properties in animal models of ischaemic stroke . The aim of the present study was to examine the safety and tolerability of a new and higher dosage regimen that would enable acute stroke patients to achieve and maintain neuroprotective plasma concentrations . METHODS A randomised , multi-centre , double-blind , placebo-controlled , parallel group study was carried out at 19 centres in France , Germany and the Netherlands in patients with a clinical diagnosis of acute ischaemic stroke , and onset of symptoms within 12 hours before start of study drug administration . Two loading doses of 3.5 mg/kg of AR-R15896AR over 60 minutes , followed by a 2.5 mg/kg infusion over the next 120 minutes were given . Eight hours after the start of the loading dose infusion , the first maintenance dose ( 120 mg ) was administered over 60 minutes . Eight further maintenance infusions were administered at intervals of 8 hours over a total treatment period of 3 days . Main variables were safety , tolerability and pharmacokinetics . Follow-up assessments also included the Barthel Index ( BI ) and the NIH Stroke Scale ( NIHSS ) at 4-7 days after the end of the last infusion and at 30 days after the onset of stroke . RESULTS 103 patients with acute ischaemic stroke were randomised to either treatment with AR-R15896AR ( 70 patients ) or placebo ( 33 patients ) . Mortality was not significantly different in the AR-R15896AR group compared with the placebo group ( 10 % vs. 6 % ) . Serious adverse events during treatment due to psychiatric conditions were associated with AR-R15896AR ( 3 vs. 0 ) . Other side effects were more common in the group treated with AR-R15896AR : vomiting ( 29 % vs. 9 % ) , nausea ( 23 % vs. 12 % ) , fever ( 17 % vs. 12 % ) , agitation ( 7 % vs. 3 % ) , dizziness ( 7 % vs. 0 % ) , and hallucinations ( 6 % vs. 0 % ) . No significant difference between the two groups ( with respect to the proportions of patients with favourable outcome ) was detected in either the analysis of the BI or the NIHSS . Pharmacokinetic data showed that plasma concentrations of AR-R15896AR were in the expected neuroprotective range . CONCLUSION In most of the patients with acute stroke receiving AR-R15896AR the intended high plasma levels were reached within a short time period . However , active treatment produced more side effects than placebo , thus indicating safety concerns and tolerability issues for use in high doses in an acute stroke population .", "role": "user" }, { "content": "{\"Intervention\": [\"Two loading doses of 3.5 mg/kg of AR-R15896AR\", \"N-Methyl-D-Aspartate ( NMDA ) antagonist AR-R15896AR\", \"NMDA antagonist AR-R15896AR\", \"AR-R15896AR\", \"placebo-controlled\", \"placebo\"], \"Outcome\": [\"safety , tolerability and pharmacokinetics .\", \"plasma concentrations of AR-R15896AR\", \"high plasma levels\", \"agitation\", \"dizziness\", \"hallucinations\", \"NIH Stroke Scale ( NIHSS )\", \"safety and tolerability\", \"nausea\", \"side effects\", \"Serious adverse events\", \"Barthel Index ( BI )\", \"vomiting\", \"fever\", \"Mortality\"], \"Participant\": [\"acute ischaemic stroke\", \"103 patients\", \"animal models of ischaemic stroke\"]}", "role": "assistant" } ]

[ { "content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What is DNAshape?\nContext: DNAshape: a method for the high-throughput prediction of DNA structural features on a genomic scale.\nWe present a method and web server for predicting DNA structural features in a high-throughput (HT) manner for massive sequence data. This approach provides the framework for the integration of DNA sequence and shape analyses in genome-wide studies. The HT methodology uses a sliding-window approach to mine DNA structural information obtained from Monte Carlo simulations. It requires only nucleotide sequence as input and instantly predicts multiple structural features of DNA (minor groove width, roll, propeller twist and helix twist). The results of rigorous validations of the HT predictions based on DNA structures solved by X-ray crystallography and NMR spectroscopy, hydroxyl radical cleavage data, statistical analysis and cross-validation, and molecular dynamics simulations provide strong confidence in this approach. The DNAshape web server is freely available at http://rohslab.cmb.usc.edu/DNAshape/.", "role": "user" }, { "content": "DNAshape is a method and web server for predicting DNA structural features in a high-throughput (HT) manner for massive sequence data. This approach provides the framework for the integration of DNA sequence and shape analyses in genome-wide studies. The HT methodology uses a sliding-window approach to mine DNA structural information obtained from Monte Carlo simulations. It requires only nucleotide sequence as input and instantly predicts multiple structural features of DNA (minor groove width, roll, propeller twist and helix twist). The results of rigorous validations of the HT predictions based on DNA structures solved by X-ray crystallography and NMR spectroscopy, hydroxyl radical cleavage data, statistical analysis and cross-validation, and molecular dynamics simulations provide strong confidence in this approach. The DNAshape web server is freely available at http://rohslab.cmb.usc.edu/DNAshape/.", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: A few pets - including cats and dogs - also have been infected with the virus that causes COVID-19. This happened mostly after the animals were in close contact with people infected with the COVID-19 virus.\n\nAbstract:\nLittle information on the SARS-CoV-2 virus in animals is available to date.\nWhereas no one husbandry animal case has been reported to date, which would have significant implications in food safety, companion animals play a role in COVID-19 epidemiology that opens up new questions.\nThere is evidence that SARS-CoV-2 can infect felines, dogs and minks, and there is evidence of human-to-animal infection.\nLikewise, the S protein nucleotide sequence of the SARS-CoV-2 virus isolated in domestic animals and humans is identical, and the replication of the SARS-CoV-2 in cats is efficient.\nBesides, the epidemiological evidence for this current pandemic indicates that the spillover to humans was associated with close contact between man and exotic animals, very probably in Chinese wet markets, thus there is a growing general consensus that the exotic animal markets, should be strictly regulated.\nThe examination of these findings and the particular role of animals in COVID-19 should be carefully analyzed in order to establish preparation and containment measures.\nAnimal management and epidemiological surveillance must be also considered for COVID-19 control, and it can open up new questions regarding COVID-19 epidemiology and the role that animals play in it.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"There is evidence that SARS-CoV-2 can infect felines, dogs and minks, and there is evidence of human-to-animal infection.\", \"Likewise, the S protein nucleotide sequence of the SARS-CoV-2 virus isolated in domestic animals and humans is identical, and the replication of the SARS-CoV-2 in cats is efficient.\"]}", "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:\nAcute exposure to acid fog : influence of breathing pattern on effective dose . Concern about the possible adverse health effects of acid fog has been fed by two observations : air pollution disasters earlier in this century were typically associated with fog , and current samples of fog water can be strongly acid . To study the acute effects of acid fog on the lung , the authors generated a monodisperse 10 microM MMAD aerosol of H2SO4 with a pH of 2.0 and a nominal concentration of 500 micrograms/m3 . They exposed seven healthy young men on alternate days to acid or control equiosmolar NaCl aerosol during 40 min of resting ventilation and 20 min of exercise ; the latter was sufficiently intense to induce oronasal breathing . Exposure was by means of a head dome , a head-only exposure device that permitted continuous measurement ( unfettered breathing ) of Vr , f , VE , and the onset and persistence of oronasal breathing . In this article the authors compare the relative importance of parameters contributing to the between-subject variability in estimated hydrogen ion dose to the lower airways ( H+LAW ) , based on analysis of variance . Physiologic parameters accounted for 70 % of the variability , of which 34 % was due to differences in duration of oronasal breathing ( tON ) and 36 % to differences in ventilation rate during oronasal breathing ( VE ( ON ) ) ; inhaled hydrogen ion concentration [ H+ ] , the environmental parameter , contributed only 30 % . Minute ventilation at the time of transition from nasal to oronasal breathing varied significantly among subjects even if normalized to FVC , an index of lung size .", "role": "user" }, { "content": "{\"Intervention\": [\"monodisperse 10 microM MMAD aerosol of H2SO4\", \"nominal concentration\", \"acid\", \"control\", \"equiosmolar NaCl aerosol\"], \"Outcome\": [\"lower airways\", \"oronasal breathing\", \"adverse health effects\", \"duration of oronasal breathing ( tON )\", \"effective dose\", \"ventilation rate during oronasal breathing ( VE ( ON ) ) ; inhaled hydrogen ion concentration [ H+ ]\"], \"Participant\": [\"exposure to acid fog :\", \"seven\", \"healthy young men\"]}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Taking a hot bath does not prevent the new coronavirus disease \n\nAbstract:\nBACKGROUND: Corona Virus Disease-2019 (COVID-19) has spread widely throughout the world since the end of 2019.\nNucleic acid testing (NAT) has played an important role in patient diagnosis and management of COVID-19.\nIn some circumstances, thermal inactivation at 56 °C has been recommended to inactivate Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) before NAT.\nHowever, this procedure could theoretically disrupt nucleic acid integrity of this single-stranded RNA virus and cause false negatives in real-time polymerase chain reaction (RT-PCR) tests.\nMETHODS: We investigated whether thermal inactivation could affect the results of viral NAT.\nWe examined the effects of thermal inactivation on the quantitative RT-PCR results of SARS-CoV-2 particularly with regard to the rates of false-negative results for specimens carrying low viral loads.\nWe additionally investigated the effects of different specimen types, sample preservation times and a chemical inactivation approach on NAT.\nRESULTS: Our work showed increased Ct values in specimens from diagnosed COVID-19 patients in RT-PCR tests after thermal incubation.\nMoreover, about half of the weak-positive samples (7 of 15 samples, 46.7%) were RT-PCR negative after heat inactivation in at least one parallel testing.\nThe use of guanidinium-based lysis for preservation of these specimens had a smaller impact on RT-PCR results with fewer false negatives (2 of 15 samples, 13.3%) and significantly less increase in Ct values than heat inactivation.\nCONCLUSION: Thermal inactivation adversely affected the efficiency of RT-PCR for SARS-CoV-2 detection.\nGiven the limited applicability associated with chemical inactivators, other approaches to ensure the overall protection of laboratory personnel need consideration.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Find all entities of these types in the text: [\"Gene\"].\n\nOutput a JSON object.\n\nText:\nSuperoxide dismutase 1 overexpression in mice abolishes maternal diabetes-induced endoplasmic reticulum stress in diabetic embryopathy. OBJECTIVE: Both oxidative stress and endoplasmic reticulum stress (ER stress) are causal events in diabetic embryopathy. We tested whether oxidative stress causes ER stress. STUDY DESIGN: Wild-type (WT) and superoxide dismutase 1 (SOD1)-overexpressing day 8.75 embryos from nondiabetic WT control with SOD1 transgenic male and diabetic WT female with SOD1 transgenic male were analyzed for ER stress markers: C/EBP-homologous protein (CHOP), calnexin, eukaryotic initiation factor 2α (eIF2α), protein kinase ribonucleic acid (RNA)-like ER kinase (PERK), binding immunoglobulin protein, protein disulfide isomerase family A member 3, kinases inositol-requiring protein-1α (IRE1α), and the X-box binding protein (XBP1) messenger RNA (mRNA) splicing. RESULTS: Maternal diabetes significantly increased the levels of CHOP, calnexin, phosphorylated (p)-eIF2α, p-PERK, and p-IRE1α; triggered XBP1 mRNA splicing; and enhanced ER chaperone gene expression in WT embryos. SOD1 overexpression blocked these diabetes-induced ER stress markers. CONCLUSION: Mitigating oxidative stress via SOD1 overexpression blocks maternal diabetes-induced ER stress in vivo.", "role": "user" }, { "content": "{\"Gene\": [\"eIF2\\u03b1\", \"calnexin\", \"IRE1\\u03b1\", \"superoxide dismutase 1\", \"X-box binding protein\", \"XBP1\", \"binding immunoglobulin protein\", \"SOD1\", \"protein kinase ribonucleic acid (RNA)-like ER kinase\", \"immunoglobulin\", \"PERK\", \"protein disulfide isomerase family A\\u00a0member 3\", \"C/EBP-homologous protein\", \"eukaryotic initiation factor 2\\u03b1\", \"kinases inositol-requiring protein-1\\u03b1\", \"CHOP\", \"Superoxide dismutase 1\"]}", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Techniques for Interface Stress Measurements within Prosthetic Sockets of Transtibial Amputees: A Review of the Past 50 Years of Research \nChapter Title: PTB vs. TSB Sockets \n1. Abstract of Cited Paper (BIB001): Force sensing resistors (FSR) have been used to measure dynamic stump/socket interface pressures during the gait of a trans-tibial amputee. A total of 350 pressure sensors were attached to the inner wall of a hydrocast socket. Data were sampled at 150Hz during approximately 0.8 seconds of prosthetic stance of gait. The dynamic pressure distributions within a hand cast socket reported by Convery and Buis (1998) are compared with those monitored within a hydrocast socket for the same amputee. The pressure gradients within the hydrocast socket are less than that of the hand cast Patellar-Tendon-Bearing (PTB) socket. The proximal “ring” of high pressure in the hand cast PTB socket is replaced with a more distal pressure in the hydrocast socket. \n2. Abstract of Cited Paper (BIB002): Abstract— This study compared the pressure distribution atthe residual limb and socket interface in amputees wearing apressure cast (PCast) socket system with amputees wearing thepatellar-tendon-bearing (PTB) socket. The PCast systemrequires the subject to place his or her residual limb in a pres-sure chamber. Pressure is applied to the residual limb while thesubject adopts a normal standing position. Four unilateral maleamputees were fitted with both PTB and PCast sockets. Usinga specially built strain-gauge-type pressure transducer, werecorded residual limb and socket pressure profiles for eachsubject wearing the two types of sockets during standing andwalking. While some subjects exhibited similar anterior-posterior or medial-lateral pressure profiles for both prosthe-ses, especially during push-off, other subjects exhibited highpressure distally in the PCast so cket or higher-pressure concen-tration at the proximal region in the PTB socket. Key words: biomechanics, pressure, prosthesis, residual limb,socket, transtibial amputees. \n3. Abstract of Cited Paper (BIB003): In this study, we investigated and compared the dynamic interface pressure distribution of hands-off and hands-on transtibial prosthetic systems by means of pressure mapping. Of the 48 established unilateral amputees recruited, half (n = 24) had been wearing pressure-cast prostheses (IceCast Compact) and the other half (n = 24) had been wearing hand-cast sockets of the patellar tendon bearing design. We measured the dynamic pressure profile of more than 90% of the area within each prosthetic socket by means of four Tekscan F-Scan socket transducer arrays. We compared the interface pressure between socket concepts. We found that the distribution of dynamic pressure at the limb-socket interface was similar for the two intervention (socket prescription) groups. However, a significant difference was found in the magnitude of the interface pressure between the two socket concepts; the interface pressures recorded in the hands-off sockets were higher than those seen in the hands-on concept. Despite the differences in interface pressure, the level of satisfaction with the sockets was similar between subject groups. The sockets instrumented for this study had been in daily use for at least 6 months, with no residual-limb health problems.\n\nLiterature Review:", "role": "user" }, { "content": "Goh et al. compared the pressure distribution of a PCast socket with traditional PTB sockets using piston-type SG transducers BIB003 . The transducers were mounted at 16 sites of interest within the sockets of four transtibial amputees who volunteered for this study. Two subjects had a similar pressure profile for the two types of sockets. The third subject exhibited a ring of high pressure at the proximal part in PTB socket while the fourth had higher pressure distally at the PCast socket. It seems that due to the low number of amputees participating in this study, the researchers could not determine which socket concept was the best. However, they avoided the high curvature regions such as tibia1 crest, patellar tendon, and fibular head. Using a limited number of SG transducers (i.e., 16 sites) in previous investigations could not provide an overall impression of the residual limb-socket interface pressure distribution during amputee gait. This is because the stresses in areas between the measurement sites are dismissed. In research and clinical settings, researchers preferred the use of F-Socket system as it could cover more than 90 percent of the interior surface of a transtibial sockets as shown in Figure 4 above. Convery and Buis were the first to use a F-Socket system for comparing the residual limb-socket interface pressure distributions in PTB and Hydrocast (TSB) sockets under dynamic conditions BIB001 BIB002 . The sensors were attached to the inner socket wall and data were collected during the gait stance phase Goh et al. compared the pressure distribution of a PCast socket with traditional PTB sockets using piston-type SG transducers BIB003 . The transducers were mounted at 16 sites of interest within the sockets of four transtibial amputees who volunteered for this study. Two subjects had a similar pressure profile for the two types of sockets. The third subject exhibited a ring of high pressure at the proximal part in PTB socket while the fourth had higher pressure distally at the PCast socket. It seems that due to the low number of amputees participating in this study, the researchers could not determine which socket concept was the best. However, they avoided the high curvature regions such as tibia1 crest, patellar tendon, and fibular head. Using a limited number of SG transducers (i.e., 16 sites) in previous investigations could not provide an overall impression of the residual limb-socket interface pressure distribution during amputee gait. This is because the stresses in areas between the measurement sites are dismissed. In research and clinical settings, researchers preferred the use of F-Socket system as it could cover more than 90 percent of the interior surface of a transtibial sockets as shown in Figure 4 above. Convery and Buis were the first to use a F-Socket system for comparing the residual limb-socket interface pressure distributions in PTB and Hydrocast (TSB) sockets under dynamic conditions BIB001 BIB002 . The sensors were attached to the inner socket wall and data were collected during the gait stance phase of a single amputee. The same experimental procedures with a TSB socket were repeated for comparison purposes. Pressure gradients within the Hydrocast socket during gait were found to be less pronounced and more evenly distributed than in PTB sockets with emphasizing that more distal pressure in TSB sockets was noted. In addition, a ring of high pressures was observed at the proximal level of PTB socket with no major distal end pressure. Dumbleton et al. conducted a similar study, comparing the dynamic interface pressure distribution and patient satisfaction between PTB sockets with Pelite liner and Hydrostatic sockets with silicone liners at various regions on the residual limb during ambulation BIB004 . A larger number of amputees (n = 48) were involved in this study; half wore PTB sockets while the other half wore pressure-cast sockets. The transducers were inserted in between the liner and socket, calibrated using specially made calibration platform that employs air inflatable bladder. The results showed that smaller variations in the interface pressures were found in pressure-cast socket, leading to a more consistently fitting socket. Pressure variations in PTB socket were steeper, resulting in increased shear stresses which are major causes of skin problems. Despite the different casting techniques, the interface pressures were higher in pressure-cast socket concept and not, as expected, in the PTB socket concept. Due to this discrepancy, the researchers could not confirm the uniform pressure distribution in the hydrostatic socket concept, highlighting that the interface pressure distribution exhibited a consistent pattern in the two socket types.", "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: Covid-19 was declared a pandemic in March 2020. Since then, governments have implemented unprecedented public health measures to contain the virus. This study will provide evidence to inform responses to the pandemic by: i) estimating population prevalence and trends of self-reported symptoms of Covid-19 and the proportions of symptomatic individuals and household contacts testing positive for Covid-19; ii) describing acceptance and compliance with physical-distancing measures, explore effects of public health measures on physical, mental and social wellbeing; iii) developing a mathematical network model to inform decisions on the optimal levels of physical distancing measures. Methods: Two cross-sectional nationally-representative telephone surveys will be conducted in Ireland using random digit-dialling, with response rates estimates based on proportion of non-operational and non-answering numbers. The first survey with four waves in May and June will address adherence to social distancing measures and whether the respondent or other household members are or have been unwell during the preceding two weeks with one or more symptoms of Covid-19. The second survey with three waves in June, July and September will address knowledge, attitudes, and compliance towards physical-distancing measures and physical, mental and social wellbeing. The mathematical network model will be developed for all-Ireland (on various levels of spatial granularity including the scale of counties and electoral divisions) based on outputs from both cross-sectional surveys and relevant publicly available data to inform decisions on optimal levels and duration of physical distancing measures. Discussion: This study will contribute to our understanding of the impact and sustainability of public health measures of the Covid-19 pandemic. Findings will have long-lasting benefits, informing decision-making on the best levels, and duration of physical-distancing measures, balancing a range of factors including capacity of the health service with the effects on individuals' wellbeing and economic disruption. Findings will be shared with key policy-makers.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Strialhyperpigmentationhasalsobeenobservedinotherconditionsthatareassociatedwithfreeradicalstress,suchasacoustictrauma[37].", "role": "user" }, { "content": "[\"free radical\"]", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nGram-Scale Synthesis of a Bench-Stable 5,5\\xe2\\x80\\xb3-Unsubstituted Terpyrrole\n\nPaper sections:\n\n<p>The development of synthetic procedures that allow for the economic preparation of α,α'-linked pyrroles in an efficient and scalable manner continues to attract attention.1–5 To date, numerous routes toward β-functionalized and relatively stable bipyrroles6 as well as quaterpyrroles7,8 have been described. However, synthetic methods for the preparation of terpyrroles remain limited (Figure 1). The first workable approach to such species was detailed by Rapaport and co-workers and involved an acid catalyzed trimerization of pyrrole followed by Pd/C-catalyzed dehydrogenation.9 Following this, LeGeoff and co-workers,10 Meijer and co-workers,11 and Sessler and co-workers12 subjected 1,4-diketo precursors to Paal-Knorr conditions thus defining creation of the central pyrrole as the key synthetic step. More recently, Carretero and co-workers have implemented a 1,3-dipolar cycloaddition for the iterative construction of pyrrole subunits. Though elegant in nature, these and other routes13 suffer from poor to moderate overall yields. Moreover, they often require a pyrrole nitrogen protecting group or capping of the terminal α-position. They also suffer from long step counts and produce 5,5\"-unsusbstituted terpyrrole products that lack appreciable stability. We have therefore devoted effort toward the development of new methodologies that allow access to stable terpyrrole derivatives. Here, we present the gram-scale synthesis of a 5,5\"-unsubstituted terpyrrole via a tandem Suzuki coupling protocol with in situ deprotection. The approach detailed here relies on commercially available and easily prepared precursors.</p><p>The ability of carbalkoxy substituents to attenuate the reactivity of pyrrole is well -appreciated in building complex pyrrole-based structures.14–18 We thus postulated that incorporating β-ethyl ester functionalities into the central pyrrole would improve the stability of the resulting terpyrrole. Gratifyingly, the tandem Suzuki cross-coupling of an easily prepared dibromo pyrrole (2)19 with commercially available N-Boc-pyrrole-2-boronic acid (3, 2.4 equiv) furnished terpyrrole (1) in 92% yield on a greater than 5-g scale after purification. As shown in Scheme 1, the reaction conditions involved the use of PdCl2(PPh3)2 (20 mol %) as the catalyst, K2CO3 (5 equiv) as a base, and a N,N-dimethylformamide/ H2O mixture (5:1, v/v) as solvent with heating to 120 °C for 5 h 20,21</p><p>The stability of the new 5,5\"-unsusbtituted terpyrrole species allowed single crystals suitable for X-ray diffraction analysis grown from slow evaporation of dichloromethane/hexanes (1:1, v/v).22 The resulting structure proved analogous to previously reported structurally characterized terpyrroles, as well as those analyzed by means of calculations.2,23–27 Specifically, compound 1 adopts an alternating planar—antiperiplanar—antiperiplanar conformation in the solid state (Figure 2). In the case of 1, the β-carbethoxy groups are involved in hydrogen-bonding interactions with the pyrrole NH protons, as inferred from the NH to adjacent carbonyl bond distance of 1.98(3) Å (N1–H to O) and 2.21(3) Å (N2–H to O) (Figures S5 and S6).28 As a result, the terminal pyrrole subunits are twisted relative to the central pyrrole with the NH portion pointed toward the carbonyl oxygen. The pyrrole—pyrrole torsional angles are 164.75° (N1 to N0) and 154.83° (N2 to N0).</p><p>UV—vis spectrophotometric analysis of terpyrrole 1 revealed a strong absorbance band at λmax = 327 nm (ε = 17 000 M−1 cm−1) (Figure 3a). The fluorescence profile was also determined with an emission maximum at 433 nm when excited at 327 nm in acetonitrile (Figure 3b).</p><p>1H NMR spectroscopic studies were carried out to probe the stability of the new terpyrrole. Based on these studies, a 47% recovery was found when compound 1 was dissolved in CDCl3 and maintained under laboratory conditions for 72 h and then subjected to purification by silica gel column chromatography (Figures S1 and S2). Terpyrrole 1 proved more stable as a solid. Based on 1H NMR spectroscopic analyses, less than 1% degradation was seen over the course of 1 week (Figure S3).</p><p>In conclusion, we have developed a facile synthesis of a new, bench-stable terpyrrole amenable to preparation on gram scale using commercially available and easily prepared precursors. The importance of bipyrrole, terpyrrole, and tetrapyrrole building blocks in expanded porphyrin and porphyrin analogue chemistry leads us to predict that precursors such as 1 will have a role to play in accessing new porphyrinoid and oligopyrrolic constructs.</p>\n\nGeneral Information.\n<p>All reagents and solvents were purchased from commercial supplies and used without further purification. Analytical thin-layer chromatography (TLC) was performed using commercial precoated silica gel plates containing a fluorescent indicator. Column chromatography was carried out using silica gel (0.040–0.063 mm). High-resolution mass spectra (HRMS) were measured using an Ion Spec Fourier Transform mass spectrometer (9.4 T). Proton and carbon NMR spectra were recorded using a Varian 400 spectrometer or Bruker Avance III 500 MHz instrument at room temperature, and chemical shifts are reported in ppm using TMS or solvent residual signals as internal reference standards. Data for 1H NMR spectra are reported as follows: chemical shift (δ ppm), multiplicity, coupling constant (Hz), and integration. Data for 13 C NMR spectra are reported in terms of chemical shift. All NMR spectroscopic solvents were purchased from Cambridge Isotope Laboratories. UV-vis spectra were recorded from 250 to 800 nm using a Varian Cary 5000 spectrophotometer at room temperature. Fluorescence spectra were recorded on a Photon Technology International Fluorescence Master fluorimeter. The source was a 75 W xenon short arc lamp. A cell length of 10 mm and spectroscopic grade acetonitrile were used for all UV-vis and fluorescence studies.</p><p>PdCl2(PPh3)2 was purchased from Strem Chemicals Inc. and used as received. N-Boc-pyrrole-2-boronic acid (3) was purchased from Frontier Scientific and used as received. Ethyl 2,5-dibromopyrrole-3,4-dicarboxylate19 is a known compound and was prepared following reported procedures.</p>\n\nDiethyl 1H,1\\xe2\\x80\\x99 H,1\\xe2\\x80\\x9d H-[2,2\\xe2\\x80\\x99:5\\xe2\\x80\\x99,2\\xe2\\x80\\x9d-Terpyrrole]-3\\xe2\\x80\\x99,4\\xe2\\x80\\x99-dicarboxylate(1).\n<p>An oven-dried round-bottom flask containing diethyl 2,5-dibromopyrrole-3,4-dicarboxylate (2) (7.0 g, 0.019 mol), PdCl2(PPh3)2 (2.66 g, 0.0038 mol, 20 mol %), N-Boc-pyrrole-2-boronic acid (3) (9.6 g, 0.046 mol, 2.4 equiv), and K2CO3 (13.1 g, 0.094 mol, 5 equiv) was degassed with a strong flow of N2 for 15 min. At the same time a round-bottom flask containing N,N-dimethylfor-mamide (200 mL) and H2O (40 mL) was degassed with N2 for 15 min. The DMF/H2O (5:1, v/v) solution was added to the solids via cannula, and the reaction mixture was transferred to an oil bath and then heated to 120 °C for 5 h. N2 was bubbled through the solvent for the first 15 min, and then a nitrogen atmosphere was maintained for the entire reaction time. The reaction flask was then transferred to a rotary evaporator, and the solvent was removed under reduced pressure (<40 mbar at 80 °C). The resultant crude solid was taken up in dichloromethane and purified by flash column chromatography over silica gel to yield a pale oil with a yellow tint. The oil was taken up in dichloromethane/hexanes (25 mL; 1/1, v/v), and the solvent was removed in vacuo (<20 mbar at 40 °C). This procedure for dissolution and removal of solvent was repeated three times. The resultant solid was taken up in dichloromethane (35 mL), and hexanes were added until precipitation occurred. The mixture was warmed to 40 °C, allowed to cool slowly to room temperature, and cooled in an ice bath for 15 min followed by filtering to yield 1 as a cream-white solid (5.99 g, 92% yield). 1H NMR (400 MHz, CDCl3): δ 11.07 (s, 2H), 8.62 (s, 1H), 6.91 (tt, J = 2.5, 1.1 Hz, 2H), 6.50 (ddt, J = 3.6, 2.3, 1.2 Hz, 2H), 6.29 (dtd, J = 3.6, 2.6, 1.0 Hz, 2h), 4.31 (qd, J = 7.2, 1.0 Hz, 4H), 1.35 (td, J = 7.2, 1.0 Hz, 6H) ppm. 13C NMR (101 MHz, CDCl3) δ 167.4, 129.7, 122.7, 119.9, 110.0, 109.5, 106.8, 61.3, 14.3 ppm. HRMS (ESI+) m/z: [M + Na]+ calcd for C18H19N3O4Na, 364.1268; found, 364.1259.</p>", "role": "user" }, { "content": "The controlled preparation of higher order oligopyr-rolic species holds broad utility across the chemical and material sciences. Here, we describe the gram-scale synthesis of a bench-stable 5,5\\xe2\\x80\\x9d-unsubstituted terpyrrole in excellent yield via a tandem Suzuki cross-coupling with in situ deprotection. The solution and solid-state stability as well as UV-vis, fluorescence, and single crystal X-ray diffraction structure are also detailed.", "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\nAutomatic image annotation is a newly developed and promising technique to provide semantic image retrieval via text descriptions. It concerns a process of automatically labeling the image contents with a pre-defined set of keywords which are exploited to represent the image semantics. A Maximum Entropy Model-based approach to the task of automatic image annotation is proposed in this paper. In the phase of training, a basic visual vocabulary consisting of blob-tokens to describe the image content is generated at first; then the statistical relationship is modeled between the blob-tokens and keywords by a Maximum Entropy Model constructed from the training set of labeled images. In the phase of annotation, for an unlabeled image, the most likely associated keywords are predicted in terms of the blob-token set extracted from the given image. We carried out experiments on a medium-sized image collection with about 5000 images from Corel Photo CDs. The experimental results demonstrated that the annotation performance of this method outperforms some traditional annotation methods by about 8% in mean precision, showing a potential of the Maximum Entropy Model in the task of automatic image annotation.", "role": "user" }, { "content": "[[\"annotation methods\", \"Automatic image annotation\", \"USED-FOR\"], [\"text descriptions\", \"semantic image retrieval\", \"USED-FOR\"], [\"method\", \"annotation methods\", \"COMPARE\"], [\"keywords\", \"automatically labeling the image contents\", \"USED-FOR\"], [\"Maximum Entropy Model-based approach\", \"Automatic image annotation\", \"USED-FOR\"], [\"Maximum Entropy Model\", \"statistical relationship\", \"USED-FOR\"], [\"mean precision\", \"annotation methods\", \"EVALUATE-FOR\"], [\"Maximum Entropy Model\", \"Automatic image annotation\", \"USED-FOR\"], [\"blob-tokens\", \"visual vocabulary\", \"PART-OF\"], [\"blob-token set\", \"keywords\", \"USED-FOR\"], [\"method\", \"Automatic image annotation\", \"USED-FOR\"], [\"Corel Photo CDs\", \"medium-sized image collection\", \"USED-FOR\"], [\"Automatic image annotation\", \"semantic image retrieval\", \"USED-FOR\"], [\"keywords\", \"image semantics\", \"USED-FOR\"], [\"visual vocabulary\", \"image content\", \"USED-FOR\"]]", "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\nGenerally healthy, postmenopausal woman who seeks treatment for hot flushes. \nMeets 1 of the following: At least 12 months of spontaneous amenorrhea; At least 6 months of spontaneous amenorrhea with serum follicle-stimulating hormone (FSH) levels > 40 mIU/mL; At least 6 weeks postsurgical bilateral oophorectomy (with or without hysterectomy). Hysterectomized without bilateral oophorectomy and with serum FSH levels >40 mIU/mL.", "role": "user" }, { "content": "{\"Condition\": [\"Hysterectomized\", \"healthy\", \"hot flushes\", \"postmenopausal\", \"spontaneous amenorrhea\"], \"Device\": [], \"Drug\": [], \"Measurement\": [\"serum follicle-stimulating hormone (FSH) levels\", \"serum FSH levels\"], \"Mood\": [], \"Multiplier\": [\"Meets 1 of the following\"], \"Negation\": [\"without\"], \"Observation\": [], \"Person\": [\"woman\"], \"Procedure\": [\"bilateral oophorectomy with hysterectomy\", \"bilateral oophorectomy without hysterectomy\", \"bilateral oophorectomy\"], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [\"bilateral oophorectomy (with or without hysterectomy)\", \"Hysterectomized without bilateral oophorectomy and with serum FSH levels \\u003e40 mIU/mL\", \"with or without hysterectomy\", \"At least 6 weeks postsurgical bilateral oophorectomy (with or without hysterectomy)\", \"At least 6 months of spontaneous amenorrhea with serum follicle-stimulating hormone (FSH) levels \\u003e 40 mIU/mL\"], \"Temporal\": [\"At least 6 weeks postsurgical\", \"At least 12 months\", \"At least 6 months\"], \"Value\": [\"\\u003e40 mIU/mL\", \"\\u003e 40 mIU/mL\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: An Open Receptor-Binding Cavity of Hemagglutinin-Esterase-Fusion Glycoprotein from Newly-Identified Influenza D Virus: Basis for Its Broad Cell Tropism\nArticle:\nAbstract:\nInfluenza viruses cause seasonal flu each year and pandemics or epidemic sporadically, posing a major threat to public health. Recently, a new influenza D virus( IDV) was isolated from pigs and cattle. Here, we reveal that the IDV utilizes 9-O-acetylated sialic acids as its receptor for virus entry. Then, we determined the crystal structures of hemagglutinin-esterase-fusion glycoprotein( HEF) of IDV both in its free form and in complex with the receptor and enzymatic substrate analogs. The IDV HEF shows an extremely similar structural fold as the human-infecting influenza C virus( ICV) HEF. However, IDV HEF has an open receptor-binding cavity to accommodate diverse extended glycan moieties. This structural difference provides an explanation for the phenomenon that the IDV has a broad cell tropism. As IDV HEF is structurally and functionally similar to ICV HEF, our findings highlight the potential threat of the virus to public health.\nIntroduction:\nInfluenza viruses are enveloped, segmented, single-stranded, negative-sense RNA viruses and belong to the family Orthomyxoviridae[1]. The genomes of influenza A virus( IAV) and influenza B virus( IBV) consist of eight RNA segments, whereas influenza C viruses( ICV) only have seven segments. Both IAV and IBV contain two major surface glycoproteins: the hemagglutinin( HA), which binds to sialylated host cell receptors and mediates membrane fusion; and the neuraminidase( NA), which destroys the receptor by cleaving sialic acid from host cell membranes, thereby releasing newly assembled virus particles[1], and likely assisting initial invasion by destroying sialylated mucin decoys[2]. ICV, however, has only one major surface glycoprotein, the hemagglutinin-esterase-fusion( HEF) protein, which possesses all-in-one of receptor binding, receptor destroying and membrane fusion activities[3, 4]. While IAV infects avian, human, swine, and many other mammalian species including dogs, horses, tigers and seals, IBV and ICV are found principally in humans and rarely infect other species[3]. ICV usually causes mild upper respiratory tract infections in children with cough, rhinitis and rhinorrhea as clinical symptoms[5, 6]. The virus only occasionally spreads to the lower respiratory tract and causes bronchitis, bronchiectasie and broncho-pneumonia[7]. Encephalopathy has also been occasionally reported[8]. Seroepidemiological studies have revealed that ICV is widely distributed globally and that the majority of humans acquire antibodies against the virus early in life[9, 10]. Aside from humans, there is evidence that ICV possesses the ability to infect animals[3]. Serological studies showed that antibodies against ICV are present in pigs[11–13]. In 1981, fifteen strains of ICV were isolated from domestic pigs in China[14], which showed characters highly related to viruses isolated from humans in Japan[15, 16]. Furthermore, pigs have been shown to be susceptible to experimental infection with both pig and human ICVs, and the virus is able to be transmitted from the infected to uninfected contact pigs[14], suggesting that interspecies transmission of ICV between humans and pigs might occur in nature. Dogs may also serve as a natural reservoir for human ICV due to the presence of viral replication and clinical symptoms in experimental infections and the prevalence of antibody to ICV among dogs[12, 17–19]. In 2011, an influenza C-like virus was isolated from swine in Oklahoma( D/swine/Oklahoma/1334/ 2011[D/OK]) exhibiting influenza-like symptoms[20]. The genome of this virus also contains seven segments, and sequence analysis showed approximately 50% overall amino acid homology to either human or previous swine ICVs. D/OK did not cross-react with antibodies against human ICVs and, importantly, was unable to reassort with human ICVs or generate viable progeny[20–22]. However, the low seroprevalence rate observed in both swine and humans to D/OK( 9. 5% and 1. 3%, respectively) suggested that swine and humans are not likely to be a major reservoir of this novel virus[20]. Subsequent serological studies have showed that antibodies against D/OK are almost ubiquitously present in cattle, and several novel D/OK-like virus strains have been isolated from cattle with respiratory disease which could be divided into two distinct lineages represented by D/OK and D/bovine/Oklahoma/660/2013( D/660)[21, 23]. These two genetic and antigenic distinct clades have been shown to reassort with each other[23]. In addition, D/OK has a broader cell tropism than human ICV and is capable of infecting ferrets, pigs and guinea pigs and transmit to naive animals by direct contact[20, 24]. Based on these differences to ICV it was suggested that this virus warrants classification as a new genus of influenza virus, named influenza D virus( IDV) with cattle as the potential reservoir[21]. Subsequently, more IDVs or viral genomic segments were identified from China and France in cattle, suggesting the wide geographic distribution of IDV[25, 26]. Interestingly, IDV is common in clinical samples of bovine respiratory disease complex( BRDC), which is the leading cause of morbidity and mortality in feedlot cattle[23, 27]. BRDC is a challenging multi-factorial disease caused by viral, bacterial pathogens and environmental factors, leading to severe clinical signs and deaths[28]. IDV was detected in clinical BRDC samples, co-infected with bovine coronavirus( BCV), bovine viral diarrhea virus( BVDV), bovine respiratory syncytial virus( BRSV), bovine herpesvirus 1( BHV-1), and Pasteurella multocida, Mannheimia haemolytica, Histophilus somni et al, suggesting IDV has the pathogenic potential in BRDC[23]. In addition, a latest serological study showed that antibodies to IDV were present in sheep and goats in United States, suggesting that small ruminants are also susceptible to IDV infection[29]. To further evaluate the infectivity and transmissibility of IDV, we expressed and purified the ectodomain of D/OK HEF, and determined that it also uses 9-O-Acetyl-Sia as its receptor by glycan microarray. We also solved the crystal structure of D/OK HEF, both in its native state( resolution of 2. 4 Å) and in complex with its receptor analogue( resolution of 3. 1 Å), and the structure of the enzymatically inactive HEF( resolution of 2. 4 Å) alone and in complex with two receptor analogs respectively( both resolutions of 2. 2 Å). Indeed, our results show that IDV HEF is functionally and structurally similar to ICV HEF, but with some distinct characteristics.\nDiscussion:\nSince the first ICV strain( C/Taylor/1233/47) was isolated in 1947 during an epidemic of respiratory illness, hundreds of viruses have been isolated in clinical specimens[48–50], due to its inconspicuous or mild symptoms and lack of suitable cell lines for virus isolation[51]. Recently, a dozen of novel IDV strains have been isolated from both pigs and cattle, strains that are distantly related to human ICV[20, 21, 23, 25, 26, 52]. Ferrets, guinea pigs and small ruminants( sheep and goats) have also been found to be susceptible to the virus[20, 24, 29]. Clearly, the viral traits necessary for host switching are different between ICV and IDV. Here, we solved the structure of IDV HEF alone and in complex with its receptor analogs. We found that the overall structure of IDV is extremely similar to that of ICV, despite sharing a relatively low sequence identity of only 53%[20]. This finding is similar to the structural similarity observed between HAs of IAV and IBV[37]. The IDV HEF structure was modeled by Modeller 9. 10 using the ICV HEF as template in a previous study[20], and they had an overall similar structure with ICV HEF. However, the details of interactions between the ligands and receptor-binding site and substrate binding site were not predicted precisely. Notably, we found that the receptor-binding site of IDV HEF occurs in an open channel between 230-helix and 270-loop. By contrast, in the receptor-binding site of ICV HEF the K235 of 230-helix and D269 of 270-loop form a salt bridge interaction, pulling the 270-loop up to connect with 230-helix and close the channel. The open channel in the receptor-binding site of IDV HEF could provide the space to accommodate an array of glycan linkages found in diverse host receptors which might explain why IDV has a broad cell tropism. Although the receptor specificity and adaptability of viral surface protein is one crucial determinant for host jump, other viral proteins may also be restrictive barriers to viral host range. PA, PB1 and PB2, which comprise the RNA-dependent RNA polymerase complex have long been implicated in playing a crucial role in determining host tropism[53, 54]. Furthermore, innate immune responses, intracellular factors and cross-species contacts may also affect host adaptation[55]. Therefore, a better understanding of the ecological, evolutionary and molecular mechanisms of IDV is essential in order to explain the broader host and cellular range of IDV and accurately assess the risk of transmission to other host species. We determined that IDV HEF uses the glycan derivatives, 9-O-Ac-Sia as its receptor. We show that both ICV and IDV HEF proteins can bind to the trachea of human, swine and bovine. Considering the ability of IDV to transmit in ferrets and guinea pigs, and its pathogenicity in pigs and cattle, its public health threat for transmission to human must be monitored. A number of studies have examined occupational risk factors for zoonotic influenza virus infections, including open bird market workers, swine workers, meat processing workers, veterinarians and poultry workers, concluding that these populations are indeed at greater risk of infection with zoonotic IAV[56, 57]. Therefore, the surveillance of IDV infection in animal farm workers with influenza-like illness must be performed. Moreover, given the major economic importance of cattle and swine, further research into the pathobiology of IDV in these hosts, especially putative role in BRDC, needs to be conducted. Another important phenomenon observed earlier is that IDV is unable to reassort with the ICV[20, 21]. As the only glycoprotein on the virus surface, it was suggested that the HEF protein may affect virus reassortment by incompatible protein functions in ICV and IDV[20, 21]. However, herein we have described the structure of IDV HEF and found it to be highly structurally and functionally similar to ICV HEF. Previous work has shown that there exist two discrepancies at the extremely conserved non-coding regions of seven RNA segments( the first twelve nucleotides at each 3' end as well as the last eleven nucleotides at each 5' end) between ICV and IDV genomes[20]. In addition, the non-conserved non-coding regions adjacent to each coding region are significantly variable[20]. Therefore, we propose that the packaging signal compatibility may be the important factor for the heterotypic incompatibilities between ICV and IDV. The esterase pocket of IDV HEF is highly conserved among ICV and nidovirus HE proteins and could represent a potential drug target for developing broad-spectrum inhibitors. Therefore, rational modification of the substrate analog based on our structures may provide a potential route for the development of novel therapeutics against both orthomyxovirus HEFs and nidovirus HEs. In conclusion, our functional and structural approach for the IDV surface protein HEF clearly reveals the virus’ similarities and distinctions in comparison to the ICV and that the virus could be a potential concern for public health as the viral HEF can bind human trachea epithelia.", "role": "user" }, { "content": "Of the Orthomyxoviridae family of viruses , influenza A , B and C viruses all can cause disease in humans . Recently , a novel influenza D virus ( IDV ) with approximately 50% amino acid identity to human influenza C virus ( ICV ) is found in pigs and cattle . This novel virus can establish infection in other mammals including ferrets and guinea pigs . However , the cellular receptor for viral entry and the molecular mechanism for its broad host range is unclear . We performed combined structural and functional studies on the viral surface protein , hemagglutinin-esterase-fusion ( HEF ) , and demonstrated that IDV ( like ICV ) uses 9-O-acetylated sialic acid as its receptor , but the IDV HEF has an open receptor-binding cavity to accommodate diverse extended glycan moieties . Our findings reveal in exquisite detail how the receptors or substrates bind to the receptor-binding site or esterase active site , providing a clue for the development of novel therapeutics against the conserved esterase pocket . Furthermore , the IDV HEF can bind human trachea epithelia , indicating that the IDV virus may become a potential threat to public health .", "role": "assistant" } ]

[ { "content": "Extract entities of these types from the text: [\"Drug\", \"Brand\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\nDicumarol and warfarin may decrease hypoprothrombinemic effect. Other depressasnts such as alcohol, barbiturates, and MAOIs may enhance CNS depression when administered with ethchlorvynol.", "role": "user" }, { "content": "{\"Brand\": [], \"Drug\": [\"Dicumarol\", \"alcohol\", \"ethchlorvynol\", \"warfarin\"], \"DrugGroup\": [\"MAOIs\", \"barbiturates\"], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nVisual localization is one of the primary capabilities for mobile robots. Long-term visual localization in real time is particularly challenging, in which the robot is required to efficiently localize itself using visual data where appearance may change significantly over time. In this paper, we propose a cloud-based visual localization system targeting at long-term localization in real time. On the robot, we employ two estimators to achieve accurate and real-time performance. One is a sliding-window based visual inertial odometry, which integrates constraints from consecutive observations and self-motion measurements, as well as the constraints induced by localization on the cloud. This estimator builds a local visual submap as the virtual observation which is then sent to the cloud as new localization constraints. The other one is a delayed state Extended Kalman Filter to fuse the pose of the robot localized from the cloud, the local odometry and the high-frequency inertial measurements. On the cloud, we propose a longer sliding-window based localization method to aggregate the virtual observations for larger field of view, leading to more robust alignment between virtual observations and the map. Under this architecture, the robot can achieve drift-free and real-time localization using onboard resources even in a network with limited bandwidth, high latency and existence of package loss, which enables the autonomous navigation in real-world environment. We evaluate the effectiveness of our system on a dataset with challenging seasonal and illuminative variations. We further validate the robustness of the system under challenging network conditions.\n\nCited Abstract(s):\n[1]: Visual place recognition is a challenging problem due to the vast range of ways in which the appearance of real-world places can vary. In recent years, improvements in visual sensing capabilities, an ever-increasing focus on long-term mobile robot autonomy, and the ability to draw on state-of-the-art research in other disciplines—particularly recognition in computer vision and animal navigation in neuroscience—have all contributed to significant advances in visual place recognition systems. This paper presents a survey of the visual place recognition research landscape. We start by introducing the concepts behind place recognition—the role of place recognition in the animal kingdom, how a “place” is defined in a robotics context, and the major components of a place recognition system. Long-term robot operations have revealed that changing appearance can be a significant factor in visual place recognition failure; therefore, we discuss how place recognition solutions can implicitly or explicitly account for appearance change within the environment. Finally, we close with a discussion on the future of visual place recognition, in particular with respect to the rapid advances being made in the related fields of deep learning, semantic scene understanding, and video description.\n\n[2]: Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100 precision with recall rates of up to 60 .", "role": "user" }, { "content": "Instead of local features, the global image feature is shown to be more robust to appearance change. In [1] [2] , they try to find the topological localization through place recognition and give satisfactory performance. In spite of the faster computation, this class of methods fail to provide metric localization, thus insufficient as a positional feedback for navigation.", "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: As reported previously (Summerbell, 1976; Sweeney et al., 1989), there is a proximodistal sequence in the differentiation of both the cartilage and muscle.", "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: SARS-CoV-2's rapid spread is likely due to the movements of people with no or very mild symptoms - namely, those who are unaware that they even have the virus. That is why social distancing is such an important containment measure, they explain.\n\nAbstract:\nThe Australian and New Zealand governments both initiated strict social distancing measures in response to the COVID-19 pandemic in late March.\nIt remains difficult to quantify the impact this had in reducing the spread of the virus.\nBayesian structural time series model provide a model to quantify the scenario in which these government-level interventions were not placed.\nOur models predict these strict social distancing measures caused a 79% and 61% reduction in the daily cases of COVID-19 across Australia and New Zealand respectively.\nThis provides both evidence and impetus for governments considering similar measures in response to COVID-19 and other pandemics.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Our models predict these strict social distancing measures caused a 79% and 61% reduction in the daily cases of COVID-19 across Australia and New Zealand respectively.\", \"This provides both evidence and impetus for governments considering similar measures in response to COVID-19 and other pandemics.\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nthe issues of long - term outcome mortality , morbidity and quality of life are finally receiving attention in the field of intensive care research .\nwe owe it to our patients and to their relatives to learn as much as we can about what we as clinicians can do to improve long - term outcome . a recent study focused on an initial technique of renal replacement therapy and its effect on patient survival and kidney survival in critically ill patients with acute kidney injury .\nthe study is the third publication from the beginning and ending supportive therapy for the kidney investigators writing committee . enrolling 1,218 patients treated with continuous renal replacement therapy ( crrt ) or with intermittent renal replacement therapy ( irrt ) for acute renal failure in 54 intensive care units in 23 countries , the investigators followed the patients to death or to hospital discharge .\ntheir findings were interesting ; patients treated with crrt ( n = 1,006 , 82.6% ) had higher illness severity scores and required vasopressor drugs and mechanical ventilation more frequently compared with those receiving irrt ( n = 212 , 17.4% ) .\nthe reasons for initiating renal replacement therapy also differed ; for instance , sepsis was more common in the crrt group . considering the different patient categories , the authors unsurprisingly found that unadjusted hospital survival was lower in the crrt group .\nmultivariable logistic regression , however , showed that the choice of renal replacement therapy was not an independent predictor of hospital survival or of dialysis - free hospital survival .\nmost importantly , the study showed that the choice of crrt was a predictor of dialysis independence at hospital discharge among survivors ( odds ratio = 3.3 , 95% confidence interval = 1.86.0 , p < 0.0001 ) .\nthe authors conclude that , worldwide , the choice of crrt as the initial therapy is not a predictor of hospital survival or of dialysis - free hospital survival , but that it is an independent predictor of renal recovery among survivors .\nthe authors speculate on the reasons for this , and on whether hypotension plays a part .\nthe numbers of reported hypotensive episodes were indeed significantly higher in the irrt group than in the crrt group ( 27.9% and 18.8% , respectively ) .\nperhaps it is the poor outcome measured as mortality of critically ill patients with acute renal failure that has prevented the research community from evaluating the determinants of long - term morbidity .\nthe vast differences between countries and regions concerning the choice of the initial technique of renal replacement therapy could also have hampered this field of research [ 3 - 5 ] .\nsurgery and internal medicine are disciplines with several hundred years of history is this an explanation for the fact that long - term outcome is an integrated and natural part of clinical studies in those fields ?\nthe adolescent specialty of intensive care medicine , born in 1952 after the polio epidemic in copenhagen , has been satisfied with less ; namely , with the reporting of short - term mortality .\nfirst , chronic dialysis therapy is associated with significant impairment of health - related quality of life [ 7 - 9 ] .\ndialysis therapy is also costly , with annual costs in the range of $ 51,25269,517 .\none study showed that the estimated cost per quality - adjusted life - year saved by initiating dialysis was $ 128,200 .\nfinally , the overall mortality of patients with renal failure requiring dialysis exceeds that of the general population .\nrecent swedish data from the swedish register of active uremia report a 28.1% yearly mortality ratio for patients on chronic hemodialysis . in collaboration with the swedish intensive care nephrology group , we performed a study of 2,202 patients with acute renal failure .\nthese patients were treated with either crrt or irrt in 32 swedish intensive care units .\nwe addressed the same issue as the beginning and ending supportive therapy investigators ; namely whether treatment modality used during intensive care affects renal recovery .\nno association was found between dialysis modality and 90-day mortality . among the 90-day survivors ,\nthe risk of end - stage renal disease requiring hemodialysis was considerably higher in 90-day survivors treated with irrt than in those treated with crrt ( adjusted odds ratio = 2.60 , 95% confidence interval = 1.54.3 ) .\nthe trend towards a higher risk of end - stage renal disease with irrt , however , decreased with increasing duration of follow - up . among the 90-day survivors who did develop end - stage renal disease , the risk of death was markedly higher in patients treated with irrt than in those treated with crrt ( hazard ratio = 2.3 , 95% confidence interval = 1.34.1 ) . in conclusion\n, the beginning and ending supportive therapy study shows that crrt and irrt are used for quite different patient categories , where sicker and more hemodynamically unstable patients more often than not are treated with crrt .\nfurthermore , both that study and the national study by the swedish intensive care nephrology group investigators point to the fact that crrt is associated with a bigger chance of renal recovery .\nthe findings of these two large studies ( 1,218 and 2,202 patients , respectively ) are in keeping with previous clinical evidence . in a randomized controlled trial by mehta and colleagues , benefits for crrt regarding renal recovery\nchronic renal insufficiency at death or at hospital discharge was diagnosed in 17% of patients with initial therapy of irrt versus only 4% of patients\nwhose initial therapy was crrt ( p = 0.01 ) . for patients receiving an adequate trial of monotherapy , the recovery of renal function was 92% for crrt versus 59% for irrt ( p < 0.01 ) .\nfinally , a higher percentage of subjects crossing over from irrt to crrt recovered their renal function compared with the patients crossing over in the opposite direction ( 45% versus 7% , respectively ; p < 0.01 ) . as higher costs associated with crrt have been used in the debate regarding the choice of modality , the downstream costs of end - stage renal disease requiring chronic hemodialysis may have to be considered in future discussions .\nnaturally , we do look forward to long - term studies of renal outcome on patients treated with sustained low efficiency ( daily ) dialysis . as members of the intensive care research community , we need to strive towards gathering more data concerning long - term outcome .\nthe studies mentioned above are welcome additions to critical care epidemiology in general , and to the field of acute kidney injury in particular .", "role": "user" }, { "content": "long - term outcome mortality , morbidity and quality of life is finally receiving attention in the field of intensive care research . \n a number of recent studies have focused on patient survival and kidney survival after acute renal failure . \n the present review focuses on the third publication from the beginning and ending supportive therapy for the kidney investigators writing committee . \n their study took place in 54 intensive care units in 23 countries . \n the main findings of the beginning and ending supportive therapy study was that the choice of continuous renal replacement therapy as the initial therapy is not a predictor of hospital survival or of dialysis - free hospital survival , but that it is an independent predictor of renal recovery among survivors . in conclusion \n , the critical care research community needs to focus on long - term outcome . \n a number of recent studies of acute renal failure have done just that .", "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: Definition 0.2.1 The stratified bisimulation relations (Milner, 1980; Hennessy and Milner, 1985) ∼k⊆ Pr× Pr for k ∈ N are defined as follows:\n• E ∼0 F for all E,F ∈ Pr • E ∼k+1 F iff for each a ∈ Act: if E\na−→ E′ then there is F ′ ∈ Pr such that F a−→ F ′ and E′ ∼k F ′; and if F a−→ F ′ then there…", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nModulation of the cellular redox status by the Alternaria toxins alternariol and alternariol monomethyl ether. The mycotoxin alternariol (AOH) has been reported to possess genotoxic properties, inducing enhanced levels of DNA damage after only 1 h of incubation. In the present study we addressed the question whether the induction of oxidative stress might contribute to the genotoxic effects of AOH or its naturally occurring monomethylether (AME). In the dichlorofluorescein (DCF) assay, treatment of HT29 cells for 1 h enhanced the formation of dichlorofluorescein, indicative for ROS formation. The total glutathione (tGSH) was transiently decreased. In accordance with the results of the DCF assay, AOH and AME enhanced the proportion of the transcription factor Nrf2 in the nucleus. Concomitantly, the Nrf2/ARE-dependent genes γ-glutamylcysteine ligase (γ-GCL) and glutathione-S-transferase (GSTA1/2) showed enhanced transcript levels. After 24 h of incubation this effect was also reflected on the protein level by an increase of GST activity. However, in spite of the positive DCF assay and the activation of the redox-sensitive Nrf2/ARE-pathway, the level of oxidative DNA damage, measured in the comet assay by the addition of formamidopyrimidine-DNA-glycosylase (fpg) remained unaffected. Of note, after 3 h of incubation no significant DNA damaging potential of AOH and AME was detectable, indicating either inactivation of the compounds or enhanced DNA repair. In summary, the mycotoxins AOH and AME were found to modulate the redox balance of HT29 cells but without apparent negative effect on DNA integrity.", "role": "user" }, { "content": "{\"Chemical\": [\"glutathione\", \"\\u03b3-glutamylcysteine\", \"S\", \"AME\", \"AOH\", \"alternariol monomethyl ether\", \"alternariol\", \"DCF\", \"dichlorofluorescein\", \"monomethylether\", \"formamidopyrimidine\"]}", "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: Investigation of the mycobacterial enzyme HsaD as a potential novel target for anti-tubercular agents using a fragment -based drug design approach With the emergence of extensively drug-resistant tuberculosis, there is a need for new anti-tubercular drugs that work through novel mechanisms of action. The meta cleavage product hydrolase, HsaD, has been demonstrated to be critical for the survival of Mycobacterium tuberculosis in macrophages and is encoded in an operon involved in cholesterol catabolism, which is identical in M. tuberculosis and M. bovis BCG. We generated a mutant strain of M. bovis BCG with a deletion of hsaD and tested its growth on cholesterol. Using a fragment based approach, over 1000 compounds were screened by a combination of differential scanning fluorimetry, NMR spectroscopy and enzymatic assay with pure recombinant HsaD to identify potential inhibitors. We used enzymological and structural studies to investigate derivatives of the inhibitors identified and to test their effects on growth of M. bovis BCG and M. tuberculosis. The hsaD deleted strain was unable to grow on cholesterol as sole carbon source but did grow on glucose. Of seven chemically distinct 'hits' from the library, two chemical classes of fragments were found to bind in the vicinity of the active site of HsaD by X-ray crystallography. The compounds also inhibited growth of M. tuberculosis on cholesterol. The most potent inhibitor of HsaD was also found to be the best inhibitor of mycobacterial growth on cholesterol -supplemented minimal medium. We propose that HsaD is a novel therapeutic target, which should be fully exploited in order to design and discover new anti-tubercular drugs.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"macrophages\", \"hsaD\", \"operon\"], \"Bacterium\": [\"Mycobacterium tuberculosis\", \"M. bovis BCG\", \"M. tuberculosis\"], \"BiologicFunction\": [\"mutant\", \"deleted\", \"deletion\", \"cholesterol catabolism\", \"extensively drug-resistant tuberculosis\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [\"fragments\"], \"BodySystem\": [], \"Chemical\": [\"carbon\", \"enzyme\", \"chemical classes\", \"glucose\", \"inhibitor\", \"library\", \"anti-tubercular agents\", \"compounds\", \"meta cleavage product hydrolase\", \"anti-tubercular drugs\", \"HsaD\", \"inhibitors\", \"cholesterol\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"unable\", \"source\"], \"Food\": [], \"HealthCareActivity\": [\"screened\", \"differential scanning fluorimetry\", \"Investigation\", \"enzymatic assay\", \"investigate\", \"NMR spectroscopy\", \"X-ray crystallography\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"structural studies\"], \"SpatialConcept\": [\"approach\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to re-evaluate popular graph classification models and provide a more rigorous evaluation framework.\n\nKeyphrases: graph classification\n\nDataset descriptions:\nCOVERAGE: COVERAGE contains copymove forged (CMFD) images and their originals with similar but genuine objects (SGOs). COVERAGE is designed to highlight and address tamper detection ambiguity of popular methods, caused by self-similarity within natural images.\nPROTEINS: PROTEINS is a dataset of proteins that are classified as enzymes or non-enzymes. Nodes represent the amino acids and two nodes are connected by an edge if they are less than 6 Angstroms apart.\nWiC-TSV: WiC-TSV is a new multi-domain evaluation benchmark for Word Sense Disambiguation. More specifically, it is a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as a binary classification task thus being independent of external sense inventories, and the coverage of various domains.\nTweetEval: TweetEval introduces an evaluation framework consisting of seven heterogeneous Twitter-specific classification tasks.\n\nOptions: A: COVERAGE B: PROTEINS C: WiC-TSV D: TweetEval", "role": "user" }, { "content": "PROTEINS", "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\nInfection caused by novel coronavirus (severe acute respiratory syndrome coronavirus 2, SARS-CoV-2) has been associated with coagulopathy. We present a case of a previously healthy 49-year-old female who was admitted to the hospital for coronavirus disease 2019 (COVID-19) pneumonia and later found to have extensive deep vein thrombosis (DVT) in all four extremities. This was accompanied by a steep rise in D-dimer levels and positive antiphospholipid antibodies (APLA) on further testing. She clinically improved on hydroxychloroquine and therapeutic anticoagulation. This is one of the first case reports describing APLA-associated DVT in a patient with COVID-19 pneumonia. Transient elevation of APLA from the viral illness may play a role in thrombosis associated with COVID-19.", "role": "user" }, { "content": "[\"Case Report\"]", "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 inter-relationships between K1, K1O and anticoagulants in dogs and humans have been previously investigated [25, 26].", "role": "user" }, { "content": "Method", "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:\nexperiments\n\nContext before:\nFor Berkeley system, we use the reported results from Durrett and Klein (2014). \u0000 Results for HOTCoref are slightly different from the results reported in Bj¨orkelund and Kuhn (2014). 12We do not provide results from Berkeley and HOTCoref on ACE-2004 dataset as they do not directly support ACE input.\n\nCitation:\nFor Berkeley system , we use the reported results from Durrett and Klein ( 2014 ) .\n\nContext after:\nshows significant improvement on all metrics for both datasets. Existing systems only report results on mentions. Here, we also show their performance evaluated on mention heads. When evaluated on mention heads rather than mentions13, we can always expect a performance increase for all systems on both datasets.", "role": "user" }, { "content": "CompareOrContrast", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: Increased eosinophilia, in turn, worsens the classical symptoms of disease and may further lead to life-threatening conditions due to breathing difficulties. On the other hand, patients with COPD and patients with CRS without nasal polyp (CRSsNP) are more neutrophilic in nature due to the expression of neutrophil chemoattractants such as CXCL9, CXCL10, and CXCL11 (Cukic et al., 2012; Brightling and Greening, 2019) . The pathology of these airway diseases is characterized by airway remodeling due to the presence of remodeling factors such as matrix metalloproteinases (MMPs) released from infiltrating neutrophils (Linden et al., 2019) . Viral infections in such conditions will then cause increase neutrophilic activation; worsening the symptoms and airway remodeling in the airway thereby exacerbating COPD, CRSsNP and even CRSwNP in certain cases (Wang et al., 2009; Tacon et al., 2010; Linden et al., 2019) . An epithelial-centric alarmin pathway around IL-25, IL-33 and thymic stromal lymphopoietin (TSLP), and their interaction with group 2 innate lymphoid cells (ILC2) has also recently been identified (Nagarkar et al., 2012; Hong et al., 2018; Allinne et al., 2019) . IL-25, IL-33 and TSLP are type 2 inflammatory cytokines expressed by the epithelial cells upon injury to the epithelial barrier (Gabryelska et al., 2019; Roan et al., 2019) . ILC2s are a group of lymphoid cells lacking both B and T cell receptors but play a crucial role in secreting type 2 cytokines to perpetuate type 2 inflammation when activated (Scanlon and McKenzie, 2012; Li and Hendriks, 2013) . In the event of viral infection, cell death and injury to the epithelial barrier will also induce the expression of IL-25, IL-33 and TSLP, with heighten expression in an inflamed airway (Allakhverdi et al., 2007; Goldsmith et al., 2012; Byers et al., 2013; Shaw et al., 2013; Beale et al., 2014; Jackson et al., 2014; Uller and Persson, 2018; Ravanetti et al., 2019) . These 3 cytokines then work in concert to activate ILC2s to further secrete type 2 cytokines IL-4, IL-5, and IL-13 which further aggravate the type 2 inflammation in the airway causing acute exacerbation (Camelo et al., 2017) . In the case of COPD, increased ILC2 activation, which retain the capability of differentiating to ILC1, may also further augment the neutrophilic response and further aggravate the exacerbation (Silver et al., 2016) . Interestingly, these factors are not released to any great extent and do not activate an ILC2 response during viral infection in healthy individuals (Yan et al., 2016; Tan et al., 2018a) ; despite augmenting a type 2 exacerbation in chronically inflamed airways (Jurak et al., 2018) . These classical mechanisms of viral induced acute exacerbations are summarized in Figure 1 . As integration of the virology, microbiology and immunology of viral infection becomes more interlinked, additional factors and FIGURE 1 | Current understanding of viral induced exacerbation of chronic airway inflammatory diseases. Upon virus infection in the airway, antiviral state will be activated to clear the invading pathogen from the airway. Immune response and injury factors released from the infected epithelium normally would induce a rapid type 1 immunity that facilitates viral clearance. However, in the inflamed airway, the cytokines and chemokines released instead augmented the inflammation present in the chronically inflamed airway, strengthening the neutrophilic infiltration in COPD airway, and eosinophilic infiltration in the asthmatic airway. The effect is also further compounded by the participation of Th1 and ILC1 cells in the COPD airway; and Th2 and ILC2 cells in the asthmatic airway. Frontiers in Cell and Developmental Biology | www.frontiersin.org mechanisms have been implicated in acute exacerbations during and after viral infection (Murray et al., 2006) . Murray et al. (2006) has underlined the synergistic effect of viral infection with other sensitizing agents in causing more severe acute exacerbations in the airway. This is especially true when not all exacerbation events occurred during the viral infection but may also occur well after viral clearance (Kim et al., 2008; Stolz et al., 2019) in particular the late onset of a bacterial infection (Singanayagam et al., 2018 (Singanayagam et al., , 2019a . In addition, viruses do not need to directly infect the lower airway to cause an acute exacerbation, as the nasal epithelium remains the primary site of most infections. Moreover, not all viral infections of the airway will lead to acute exacerbations, suggesting a more complex interplay between the virus and upper airway epithelium which synergize with the local airway environment in line with the \"united airway\" hypothesis (Kurai et al., 2013) . On the other hand, viral infections or their components persist in patients with chronic airway inflammatory disease (Kling et al., 2005; Wood et al., 2011; Ravi et al., 2019) . Hence, their presence may further alter the local environment and contribute to current and future exacerbations. Future studies should be performed using metagenomics in addition to PCR analysis to determine the contribution of the microbiome and mycobiome to viral infections. In this review, we highlight recent data regarding viral interactions with the airway epithelium that could also contribute to, or further aggravate, acute exacerbations of chronic airway inflammatory diseases. Patients with chronic airway inflammatory diseases have impaired or reduced ability of viral clearance (Hammond et al., 2015; McKendry et al., 2016; Akbarshahi et al., 2018; Gill et al., 2018; Wang et al., 2018; Singanayagam et al., 2019b) . Their impairment stems from a type 2-skewed inflammatory response which deprives the airway of important type 1 responsive CD8 cells that are responsible for the complete clearance of virusinfected cells (Becker, 2006; McKendry et al., 2016) . This is especially evident in weak type 1 inflammation-inducing viruses such as RV and RSV (Kling et al., 2005; Wood et al., 2011; Ravi et al., 2019) . Additionally, there are also evidence of reduced type I (IFNβ) and III (IFNλ) interferon production due to type 2-skewed inflammation, which contributes to imperfect clearance of the virus resulting in persistence of viral components, or the live virus in the airway epithelium (Contoli et al., 2006; Hwang et al., 2019; Wark, 2019) . Due to the viral components remaining in the airway, antiviral genes such as type I interferons, inflammasome activating factors and cytokines remained activated resulting in prolong airway inflammation (Wood et al., 2011; Essaidi-Laziosi et al., 2018) . These factors enhance granulocyte infiltration thus prolonging the exacerbation symptoms. Such persistent inflammation may also be found within DNA viruses such as AdV, hCMV and HSV, whose infections generally persist longer (Imperiale and Jiang, 2015) , further contributing to chronic activation of inflammation when they infect the airway (Yang et al., 2008; Morimoto et al., 2009; Imperiale and Jiang, 2015; Lan et al., 2016; Tan et al., 2016; Kowalski et al., 2017) . With that note, human papilloma virus (HPV), a DNA virus highly associated with head and neck cancers and respiratory papillomatosis, is also linked with the chronic inflammation that precedes the malignancies (de Visser et al., 2005; Gillison et al., 2012; Bonomi et al., 2014; Fernandes et al., 2015) . Therefore, the role of HPV infection in causing chronic inflammation in the airway and their association to exacerbations of chronic airway inflammatory diseases, which is scarcely explored, should be investigated in the future. Furthermore, viral persistence which lead to continuous expression of antiviral genes may also lead to the development of steroid resistance, which is seen with RV, RSV, and PIV infection (Chi et al., 2011; Ford et al., 2013; Papi et al., 2013) . The use of steroid to suppress the inflammation may also cause the virus to linger longer in the airway due to the lack of antiviral clearance (Kim et al., 2008; Hammond et al., 2015; Hewitt et al., 2016; McKendry et al., 2016; Singanayagam et al., 2019b) . The concomitant development of steroid resistance together with recurring or prolong viral infection thus added considerable burden to the management of acute exacerbation, which should be the future focus of research to resolve the dual complications arising from viral infection. On the other end of the spectrum, viruses that induce strong type 1 inflammation and cell death such as IFV (Yan et al., 2016; Guibas et al., 2018) and certain CoV (including the recently emerged COVID-19 virus) (Tao et al., 2013; Yue et al., 2018; Zhu et al., 2020) , may not cause prolonged inflammation due to strong induction of antiviral clearance. These infections, however, cause massive damage and cell death to the epithelial barrier, so much so that areas of the epithelium may be completely absent post infection (Yan et al., 2016; Tan et al., 2019) . Factors such as RANTES and CXCL10, which recruit immune cells to induce apoptosis, are strongly induced from IFV infected epithelium (Ampomah et al., 2018; Tan et al., 2019) . Additionally, necroptotic factors such as RIP3 further compounds the cell deaths in IFV infected epithelium . The massive cell death induced may result in worsening of the acute exacerbation due to the release of their cellular content into the airway, further evoking an inflammatory response in the airway (Guibas et al., 2018) . Moreover, the destruction of the epithelial barrier may cause further contact with other pathogens and allergens in the airway which may then prolong exacerbations or results in new exacerbations. Epithelial destruction may also promote further epithelial remodeling during its regeneration as viral infection induces the expression of remodeling genes such as MMPs and growth factors . Infections that cause massive destruction of the epithelium, such as IFV, usually result in severe acute exacerbations with non-classical symptoms of chronic airway inflammatory diseases. Fortunately, annual vaccines are available to prevent IFV infections (Vasileiou et al., 2017; Zheng et al., 2018) ; and it is recommended that patients with chronic airway inflammatory disease receive their annual influenza vaccination as the best means to prevent severe IFV induced exacerbation. \n\nAnother mechanism that viral infections may use to drive acute exacerbations is the induction of vasodilation or tight junction opening factors which may increase the rate of infiltration. Infection with a multitude of respiratory viruses causes disruption of tight junctions with the resulting increased rate of viral infiltration. This also increases the chances of allergens coming into contact with airway immune cells. For example, IFV infection was found to induce oncostatin M (OSM) which causes tight junction opening (Pothoven et al., 2015; Tian et al., 2018) . Similarly, RV and RSV infections usually cause tight junction opening which may also increase the infiltration rate of eosinophils and thus worsening of the classical symptoms of chronic airway inflammatory diseases (Sajjan et al., 2008; Kast et al., 2017; Kim et al., 2018) . In addition, the expression of vasodilating factors and fluid homeostatic factors such as angiopoietin-like 4 (ANGPTL4) and bactericidal/permeabilityincreasing fold-containing family member A1 (BPIFA1) are also associated with viral infections and pneumonia development, which may worsen inflammation in the lower airway Akram et al., 2018) . These factors may serve as targets to prevent viral-induced exacerbations during the management of acute exacerbation of chronic airway inflammatory diseases. Another recent area of interest is the relationship between asthma and COPD exacerbations and their association with the airway microbiome. The development of chronic airway inflammatory diseases is usually linked to specific bacterial species in the microbiome which may thrive in the inflamed airway environment (Diver et al., 2019) . In the event of a viral infection such as RV infection, the effect induced by the virus may destabilize the equilibrium of the microbiome present (Molyneaux et al., 2013; Kloepfer et al., 2014; Kloepfer et al., 2017; Jubinville et al., 2018; van Rijn et al., 2019) . In addition, viral infection may disrupt biofilm colonies in the upper airway (e.g., Streptococcus pneumoniae) microbiome to be release into the lower airway and worsening the inflammation (Marks et al., 2013; Chao et al., 2014) .\nQuestion: What is recommended that patients with chronic airway inflammatory disease?", "role": "user" }, { "content": "receive their annual influenza vaccination as the best means to prevent severe IFV induced exacerbation.", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nadvanced chronic periodontitis often coexists with poorly controlled diabetes , such that diabetes is considered to be a risk factor for periodontitis .\nmany studies conducted among adults have reported a significant positive two - way association between diabetes ( both type-1 and type-2 ) and periodontal disease that is , diabetes increases risk of developing periodontitis and worsens preexisting periodontitis and periodontitis may raise the risk of diabetes .\nperiodontal infection can increase systemic inflammation , which in turn may induce a chronic state of insulin resistance , contributing to the cycle of hyperglycemia and advanced glycation end product - protein binding accumulation .\ntherefore , it can amplify the classical pathway of connective tissue degradation , destruction and proliferation in diabetes .\nmoreover , studies have also shown that treating periodontitis in diabetic patients has a beneficial effect on their blood glucose control .\non the other hand , poorly controlled diabetes is an important risk factor for periodontitis , and gingivitis , and sometimes periodontitis is the first sign that a diabetic patient presents with .\nthe impact of periodontitis on the diabetes - related inflammatory status has also been studied .\nit has been indicated that the cytokine induced inflammatory state in periodontitis can contribute to the overall low grade inflammation that occurs in diabetes .\na recent study investigated the relationship between chronic periodontitis , impaired fasting glucose ( ifg ) , and diabetes in the us population and found chronic periodontitis to be positively associated in a linear relation with ifg and diabetes in us adults .\nstudies evaluating the relationship between impaired glucose tolerance ( igt ) and periodontal disease among japanese population suggest that periodontal disease is positively associated with igt , but other studies found no such association .\nobesity and impaired lipid profile are other strong risk factors for type-2 diabetes , which in turn is a risk factor for periodontal disease .\nthe extent of coronary atherosclerosis is positively correlated with pro - atherogenic lipids , that is , total cholesterol , low - density lipoprotein ( ldl ) cholesterol and triglycerides ( tg ) , and negatively correlated with anti - atherogenic high density lipoprotein ( hdl ) cholesterol . the high prevalence of cardiovascular disease and periodontitis in individuals with diabetes may be attributed to an increased inflammatory response leading to atherosclerosis as compared to those without diabetes .\nthough there are many studies that have evaluated the interrelationship between the diabetic status of an individual with his / her periodontal status ; the authors however could not find studies / research reports that evaluated relationship between various biochemical parameters like lipid profile and oral glucose tolerance test ( ogtt ) with periodontal health / disease status , in both healthy and diabetic patients .\nhence , this study was designed to investigate the association between chronic periodontitis and diabetes by taking dental plaque index ( dpi ) and community periodontal index ( cpi ) score as periodontal health / disease dependent variables and lipid profile and ogtt as biochemical parameters in healthy , diabetic and igt subjects .\nthis study began in 2008 in the department of biochemistry and the department of periodontics at baba jaswant singh dental college hospital and research institute , ludhiana with the subjects reporting to the opd of the department of periodontics .\nall patients reporting to the department of periodontics were interviewed and questioned about their diabetic / lipid profile status .\nany patient reporting a known self or family history of deranged lipid / diabetic profile was provisionally selected for this study . of these ,\na group of 120 patients who were willing to form a part of the study were finally selected and were sent for blood and periodontal examination .\nthe subjects undertaken also fulfilled the following criteria - community periodontal index ( cpi ) score of 2 or more [ table 1 ] and cpi loss of attachment score of 0 and above [ table 2 ] . community periodontal index cpi loss of attachment score subjects with community periodontal index loss of attachment score 0 underwent a periodontal examination to determine mean periodontal pocket depth and attachment loss . for the biochemical analyses , the reports of ogtt and lipid profile tests were analyzed as per who criteria for the diagnosis of diabetes that is , normal glucose tolerance ( ngt ; fasting and 2 h postchallenge plasma glucose levels < 110 mg / dl and < 140 mg / dl , respectively ) , diabetes ( fasting or 2 h postchallenge plasma glucose levels 126 mg / dl or 200 mg / dl , respectively ) and igt ( igt ; all others with some glucose tolerance impairment including impaired fasting glucose ( ifg ) , that is , with one of the two glucose tolerance levels between normal and diabetic values and the other below the diabetic level ) .\nthe samples of venous blood were taken in the fasting state for ogtt and lipid profile analysis .\nimmediately after , 75 g glucose dissolved in 300 ml water was given to be ingested in about 5 min and sample of blood was again collected at an interval of 30 min for a period of 3 h for glucose tolerance test ( gtt ) analysis .\ndata obtained was tabulated , compared and statistically analyzed using z - test to know the correlation between lipid profile test values , type 2 diabetes mellitus and periodontitis .\nsubjects with community periodontal index loss of attachment score 0 underwent a periodontal examination to determine mean periodontal pocket depth and attachment loss . for the biochemical analyses , the reports of ogtt and lipid profile tests were analyzed as per who criteria for the diagnosis of diabetes that is , normal glucose tolerance ( ngt ; fasting and 2 h postchallenge plasma glucose levels < 110 mg / dl and < 140 mg / dl , respectively ) , diabetes ( fasting or 2 h postchallenge plasma glucose levels 126 mg / dl or 200 mg / dl , respectively ) and igt ( igt ; all others with some glucose tolerance impairment including impaired fasting glucose ( ifg ) , that is , with one of the two glucose tolerance levels between normal and diabetic values and the other below the diabetic level ) .\nthe samples of venous blood were taken in the fasting state for ogtt and lipid profile analysis .\nimmediately after , 75 g glucose dissolved in 300 ml water was given to be ingested in about 5 min and sample of blood was again collected at an interval of 30 min for a period of 3 h for glucose tolerance test ( gtt ) analysis .\ndata obtained was tabulated , compared and statistically analyzed using z - test to know the correlation between lipid profile test values , type 2 diabetes mellitus and periodontitis .\nsubjects with community periodontal index loss of attachment score 0 underwent a periodontal examination to determine mean periodontal pocket depth and attachment loss . for the biochemical analyses , the reports of ogtt and lipid profile tests were analyzed as per who criteria for the diagnosis of diabetes that is , normal glucose tolerance ( ngt ; fasting and 2 h postchallenge plasma glucose levels < 110 mg / dl and < 140 mg / dl , respectively ) , diabetes ( fasting or 2 h postchallenge plasma glucose levels 126 mg / dl or 200 mg / dl , respectively ) and igt ( igt ; all others with some glucose tolerance impairment including impaired fasting glucose ( ifg ) , that is , with one of the two glucose tolerance levels between normal and diabetic values and the other below the diabetic level ) .\nthe samples of venous blood were taken in the fasting state for ogtt and lipid profile analysis .\nimmediately after , 75 g glucose dissolved in 300 ml water was given to be ingested in about 5 min and sample of blood was again collected at an interval of 30 min for a period of 3 h for glucose tolerance test ( gtt ) analysis .\ndata obtained was tabulated , compared and statistically analyzed using z - test to know the correlation between lipid profile test values , type 2 diabetes mellitus and periodontitis .\nof 120 subjects undertaken for study , 35 patients were found to be periodontally healthy and 85 periodontally diseased ; 48 subjects had igt , and 17 had diabetes and the rest of the subjects that is , 55 had ngt .\nall subjects were assessed for their periodontal condition by taking dpi [ table 3 ] and cpi scoreas parameters . when dpi score ( suggesting periodontal condition of the patient ) and ogtt results were compared and studied , it was observed that dpi for ngt , igt and diabetic patients were 1.05 0.5 , 1.16 0.7 , and 1.65 0.8 , respectively [ table 4 ] . when cpi score ( suggesting periodontal condition of the patient ) and ogtt results were studied , it was observed that cpi score for ngt , igt , and diabetics were 1.33 0.4 , 1.67 0.5 , and 2.33 0.8 , respectively [ table 4 ] .\na similar correlation was found between ldl levels and ogtt results , that is , ldl levels in patients with ngt and igt were within normal range , while it was higher than normal in patients with diabetes [ table 5 ] .\nmean total cholesterol and mean hdl values were within normal range for all ogtt patient types [ table 5 ] . in a correlation table of various biochemical analyses and periodontal parameters , [ table 6 ]\nit is evident that out of 85 periodontally diseased patients 35 showed abnormal fasting blood sugar levels and 61 showed abnormal post prandial blood sugar levels which potrays a non - significant co - relation . of the 85 periodontally diseased patients 77 patients showed abnormal total serum cholesterol level , 65 showed abnormal ldl cholesterol level and 71 showed abnormal tg levels .\nthese findings suggest that worsening lipid profile test values can be positively correlated with increased severity of periodontal disease [ highly significant p < 0.001 ] .\ndental plaque index ( sillness and loe , 1964 ) periodontal condition of subjects in relation to their biochemical status association of participants diabetic status ogtt and lipid profile tests correlation between periodontal condition and various biochemical parameters\nthe results of this study show that in patients having poor periodontal condition poor ogtt score was observed .\nit is also clear that as the periodontal condition and ogtt scores worsen , the tg levels and ldl levels also worsen . it has been shown that diabetes is one of the predisposing factors for the development of periodontal disease .\nthe inter relationships between periodontitis and diabetes provide an example of systemic disease predisposing to oral infection , and once that infection is established , oral infection exacerbates the systemic disease .\nit has been shown that diabetic patients are prone to elevated ldl cholesterol and tgs even when blood glucose levels were well controlled .\nthis is significant ; as our study indicated that hyperlipidemia may be one of the factors associated with periodontitis .\nthe results of the study suggest that periodontitis itself may lead to elevated ldl / tg levels . within this context\n, it may be put forth that in addition to effects of diabetes , periodontitis may contribute to elevated serum lipids and potentially to systemic disease arising from chronic hyperlipidemia . in a recent study in women subjects ,\nperiodontal disease was shown to be associated with later development of impaired glucose metabolism with a prior history of gestational diabetes . therefore ,\ntreating periodontal disease may in addition to controlling and or improving the diabetic status of the patient may also improve the deranged lipid profile in a patient . when seen in this context , treating periodontal disease may also have a significant impact on improving the systemic health of the patient as both diabetes and a deranged lipid profile are known risk factors for several life - threatening diseases and conditions . as this study has demonstrated that the lipid profile can be a determinant of diabetes and periodontitis and vice versa\nmany cases of diabetes and deranged lipid profile may remain undiagnosed , and screening of patients in dental clinics may lead to a diagnosis of these in some cases .\nit is evident from this study that abnormal levels of total serum cholesterol , ldl cholesterol , and tgs can be positively correlated with periodontally diseased conditions . as evidence of close link between periodontal disease , diabetes and deranged lipid profile\nis seen , treating and preventing recurrence of periodontal disease in patients with diabetes and deranged lipid profile values should be considered an important component of the treatment and management of patients suffering from diabetes and deranged lipid profile .", "role": "user" }, { "content": "objective : a two - way relationship between diabetes and periodontal disease has been suggested ; whereas obesity and impaired lipid profile are risk factors for type-2 diabetes mellitus . \n this study examined the relationship between lipid profile , oral glucose tolerance test ( ogtt ) with periodontal health / disease dependent variables in healthy , diabetic and impaired glucose tolerance subjects.materials and methods:120 patients were selected for the study and were determined to be periodontally healthy or diseased . \n all these patients underwent biochemical tests for ogtt and lipid profile analysis and data was compared using z-test.results:the ogtt results deteriorated with deteriorating periodontal condition . a similar correlation \n was also observed between worsening lipid profile test values , ogtt score , and periodontal condition.conclusion:this study indicates that hyperlipidemia may be one of the factors associated with periodontitis and that periodontitis may itself lead to abnormal serum lipid levels . \n therefore , in addition to effects on diabetes , periodontitis may contribute to elevated serum lipid levels and therefore potentially to systemic disease arising from chronic hyperlipidemia .", "role": "assistant" } ]

[ { "content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Is imatinib an antidepressant drug?\n\nContext: Gastrointestinal stromal tumor (GIST) is the most common mesenchymal tumor of the gastrointestinal tract. Surgery remains the elective treatment. We retrospectively compared two group of patients, who underwent surgery for GIST before and after Imatinib advent in order to analyze the recurrence and survival rate.\nAdjuvant imatinib 400 mg/day for 3 years duration is a standard treatment in all patients with significant risk of recurrence following resection of primary GISTs\nR1 surgery (versus R0) alone is not an indication for adjuvant imatinib in low-risk GIST.\nTreatment is not recommended in an imatinib-insensitive D842V-mutated GIST\nPrognostic factors such as tumor size, mitotic rate and presence of metastases may provide an indication for adjuvant imatinib mesylate (IM) treatment. Here we present a young patient with a large GIST with high-risk features who is in complete remission after surgical excision and adjuvant IM treatment. This patient is the only colon-located CD117-positive case where IM was administered.\nImatinib mesylate is the sole BCR-ABL tyrosine kinase inhibitor approved as first-line treatment of accelerated-phase (AP) chronic myeloid leukemia (CML).\nimatinib mesylate could be a therapeutic target of strategies against osteosarcoma tumors.\nAllogeneic hematopoietic stem cell transplantation (HSCT) is well-established as a potentially curative treatment for patients who have chronic myeloid leukemia. The success of imatinib and other tyrosine kinase inhibitors (TKI) as initial therapy has changed the treatment paradigm for this disease.\nImatinib plus hydroxyurea is well tolerated among patients with meningioma but has modest anti-tumor activity for this indication.\nKi67 correlated with time to recurrence (p=0.022). Ki67 >11% was taken as the indication to start imatinib chemotherapy (sensitivity 61.5%, specificity 92.0%, p=0.022).\nSignificant pharmacokinetic interactions have already been shown between St. John's Wort (SJW) and the anticancer drugs imatinib and irinotecan.\nfor CML we analysed imatinib, dasatinib and nilotinib.\nImatinib mesylate, an orally administered kinase inhibitor that targets the Kit (CD117) protein, currently has 10 approved indications including treatment of chronic myelogenous leukemia and metastatic gastrointestinal stromal tumors (GIST).\nThe drugs were assessed according to clinical evidence on efficacy and safety, based on Micromedex categorization, on systematic reviews and meta-analyses. Indications present in the legal documentation were compared to the indications approved by regulatory agencies. RESULTS: Bevacizumab, capecitabine, cetuximab, erlotinib, rituximab, imatinib, and temozolomide\nBcr-Abl, an oncogene responsible for CML\nBcr-Abl-expressing cells showed resistance to death activated by spindle defects, reversed by imatinib.\nImatinib, an oral tyrosine kinase inhibitor (TKI), is first-line treatment in patients with metastatic or unresectable GIST.\nSurgical indication for metastatic gastrointestinal stromal tumor (GIST) treated with imatinib is not yet established.\nSurgery of residual disease upon best clinical response seems associated with survival benefit compared with historical controls in similar patient collectives treated with imatinib alone.\nTo explore the effect of preoperative imatinib mesylate (IM) in patients with unresectable or locally advanced primary gastrointestinal stromal tumor (GIST)\nThe patient had been diagnosed 14 months earlier and had been submitted to surgery, followed by adjuvant radiotherapy and temozolomide-based chemotherapy. On clinical suspicion of recurrence 5 months later, magnetic resonance imaging (MRI) revealed a lesion at the site of preceded surgery, which was treated by imatinib mesylate\nRadical surgery remains the most effective method of GIST treatment. In inoperable/metastatic lesion the treatment of choice is tyrosinase kinase inhibitor--imatinib.\nImatinib mesylate (STI571), a specific Bcr-Abl inhibitor, has shown a potent antileukemic activity in clinical studies of chronic myeloid leukemia (CML) patients.\nImatinib, an inhibitor of the tyrosine kinase activity of c-kit, was used as an adjuvant chemotherapy in two patients who underwent curative surgery for recurrent gastrointestinal stromal tumors.\nAdjuvant imatinib 400 mg/day for 3 years duration is a standard treatment in all patients with significant risk of recurrence following resection of primary GISTs.", "role": "user" }, { "content": "no", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nBid-centric service descriptions have the potential to offer a new cloud service provisioning model that promotes portability, diversity of choice and differentiation between providers. A bid matching model based on requirements and capabilities is presented that provides the basis for such an approach. In order to facilitate the bidding process, tenders should be specified as abstractly as possible so that the solution space is not needlessly restricted. To this end, we describe how partial TOSCA service descriptions allow for a range of diverse solutions to be proposed by multiple providers in response to tenders. Rather than adopting a lowest common denominator approach, true portability should allow for the relative strengths and differentiating features of cloud service providers to be applied to bids. With this in mind, we describe how TOSCA service descriptions could be augmented with additional information in order to facilitate heterogeneity in proposed solutions, such as the use of coprocessors and provider-specific services.\n\nCited Abstract(s):\n[1]: In this paper, we present a novel combinatorial auction (CA) based trading infrastructure to enable the supply and demand of Cloud services from different Cloud providers (CP). We propose a new auction policy that considers the relationship among CPs (mutual business relationship) in bidding mechanism. In our new auction-based market model, we allow the group of service providers to publish their bids collaboratively as a single bid to the auctioneer. It gives service providers a chance to autonomously find partners and make groups. Then they can use group strategy to increase their competitive power and compete for winning the bid (s). This will reduce conflicts, as well as collaboration cost and negotiation time, among participants as compare to existing CA-based market model. We implement our proposed market model of trading service in a simulated environment and study its economic efficiency with existing model.\n\n[2]: Cloud computing has been an emerging model which aims at allowing customers to utilize computing resources hosted by Cloud Service Providers (CSPs). More and more consumers rely on CSPs to supply computing and storage service on the one hand, and CSPs try to attract consumers on favorable terms on the other. In such competitive cloud computing markets, pricing policies are critical to market efficiency. While CSPs often publish their prices and charge users according to the amount of resources they consume, auction mechanism is rarely applied. In fact a feasible auction mechanism is the most effective method for allocation of resources, especially double auction is more efficient and flexible for it enables buyers and sellers to enter bids and offers simultaneously. In this paper we bring up an electronic auction platform for cloud, and a cloud Continuous Double Auction (CDA) mechanism is formulated to match orders and facilitate trading based on the platform. Some evaluating criteria are defined to analyze the efficiency of markets and strategies. Furthermore, the selection of bidding strategies for the auction plays a very important role for each player to maximize its own profit, so we developed a novel bidding strategy for cloud CDA, BH-strategy, which is a two-stage game bidding strategy. At last we designed three simulation scenarios to compare the performance of our strategy with other dominating bidding strategies and proved that BH-strategy has better performance on surpluses, successful transactions and market efficiency. In addition, we discussed that our cloud CDA mechanism is feasible for cloud computing resource allocation.", "role": "user" }, { "content": "Shi present an electronic auction platform for cloud resources based on a continuous double auction mechanism [2] . The platform uses trading rounds to match bids from consumers with asks from cloud service providers. A two stage game bidding strategy is also presented. Song present another market model based on combinatorial auctions [1] . This model allows for collaboration between service providers when creating bids. Service providers can autonomously find partners and create groups that increase their competitive power and hence improve their chances of submitting a winning bid.", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Sex-specific triacylglycerides are widely conserved in Drosophila and mediate mating behavior\nArticle:\nAbstract:\nPheromones play an important role in the behavior, ecology, and evolution of many organisms. The structure of many insect pheromones typically consists of a hydrocarbon backbone, occasionally modified with various functional oxygen groups. Here we show that sex-specific triacylclyerides( TAGs) are broadly conserved across the subgenus Drosophila in 11 species and represent a novel class of pheromones that has been largely overlooked. In desert-adapted drosophilids, 13 different TAGs are secreted exclusively by males from the ejaculatory bulb, transferred to females during mating, and function synergistically to inhibit courtship from other males. Sex-specific TAGs are comprised of at least one short branched tiglic acid and a long linear fatty acyl component, an unusual structural motif that has not been reported before in other natural products. The diversification of chemical cues used by desert-adapted Drosophila as pheromones may be related to their specialized diet of fermenting cacti.\nIntroduction:\nChemical communication significantly influences many complex social behaviors, including aggression, kin recognition, and courtship( Wyatt, 2003). The chemical structures and functions of insect pheromones have been intensely studied because of the fascinating diversity of behavioral properties and relevance to questions of speciation, reproductive isolation, and applications to pest control( Witzgall et al., 2010). Since the discovery of Bombykol in 1959( Butenandt et al., 1959), hundreds of insect pheromones have been identified, including straight chain and branched alkanes and alkenes, oxygen-containing derivatives such as wax esters, fatty alcohols, and aldehydes, sterols, and isoprene-based compounds( Tillman et al., 1999; El-Sayed, 2012). In Drosophila, pheromones are produced by oenocytes( specialized epithelial cells in both males and females) and the male ejaculatory bulb and subsequently secreted onto the cuticular surface and anogenital region, respectively( Billeter et al., 2009; Yew et al., 2009). Previous studies of Sophophora and Drosophila flies identified alkanes, alkenes, and oxygen-modified hydrocarbons as the major lipids used as pheromones( Jallon and David, 1987; Greenspan and Ferveur, 2000). Recently, triacylglycerides( TAGs), which are normally found in the fat bodies and used for energy storage, were observed on the cuticles of flies from the Drosophila repleta and Drosophila quinaria groups( Yew et al., 2011; Curtis et al., 2013). However, almost nothing is known about the structure, chemical diversity, conserved expression, and functional roles of these exogenously secreted TAGs. To explore the role of TAGs as pheromones and the ubiquity of their expression in Drosophila, we used ultraviolet laser desorption/ionization mass spectrometry( UV-LDI MS) to analyze the cuticular profiles of flies from seven major Sophophora and Drosophila groups. We also investigated the chemical structures of sex-specific TAGs and their role as sex pheromones in species from the D. repleta group. Our studies indicate that TAGs are a broadly conserved, structurally atypical class of Drosophila pheromones that has been overlooked.\nDiscussion:\nSynergistic interactions between multiple sensory cues in chemical communication have been described in several forms, in many cases involving a combination of enantiomers( Borden et al., 1976) or a blend of molecules from the same chemical class( Lecomte et al., 1998; Srinivasan et al., 2008). Famously, the honey bee queen uses a blend of least nine different fatty acids and alcohols secreted by multiple glands( Keeling et al., 2003) The parasitic wasp Lariophagus distinguendus was recently reported to use TAGs together with a branched alkane to promote mating behavior( Kühbandner et al., 2012). Food odors are also known to synergize with aggregation pheromones in beetles( Lin et al., 1992) and with sex pheromones in Drosophila( Grosjean et al., 2011). Pheromonal synergism between completely different classes of molecules is rare and may be a mechanism to increase combinatorial complexity. Interestingly, only some of the D. arizonae TAGs appear to play a role as an anti-aphrodisiac. The quiescent stereoisomers could be used as potential future chemical cues( Niehuis et al., 2013). Sex-specific TAGs found on desert-adapted drosophilids are the first examples of natural products bearing combinations of branched and linear fatty acyl side chains. Conventional naturally occurring TAGs found in plant oils and animal fat typically consist of linear fatty acyl moieties that have 16, 18, or 20 carbons( Nelson et al., 2008). Although medium and short chain fatty acyls have been found in TAGs from, respectively, whale blubber( Litchfield et al., 1971) and bovine milk fat( Breckenridge and Kuksis, 1968), they are only in combination with linear and even-numbered carbon acyls. In contrast, sex-specific TAGs from flies exhibit an unusual combination of short and long chain acyl components with odd and even numbers of carbons. To what extent can these unconventional structures be attributed to diet? Previous and current work has shown that altering the diet of desert-adapted flies results in a quantitative change in hydrocarbons and sex-specific triglycerides( Figure 4)( Toolson et al., 1990; Etges et al., 2006; Etges et al., 2009; Yew et al., 2011). Notably, many of the substrates on which the drosophilids subsist and oviposit contain compounds that can be toxic for other animals. For example, desert-adapted D. arizonae and D. mojavensis feed on fermenting cacti, which have high levels of triterpene glycosides, medium chain fatty acids, and sterol diols, compounds which can serve as toxic plant defense chemicals( Fogleman and Danielson, 2001). Similarly, Drosophila subquinaria and Drosophila recens are found exclusively on mushrooms that are rich in secondary metabolites such as isoprenoids and fatty acids in a variety of lengths, from 4 to 26 carbons( Wandati et al., 2013; Pedneault et al., 2008) but also contain high levels of toxic compounds like alpha-amanitin( Jaenike et al., 1983; Courtney et al., 1990). Slime fluxes, on which D. virilis and D. robusta can be found, have large bacterial communities that can be inhospitable to other drosophilids( Carson and Stalker, 1951; Powell, 1997). Bacterial wetwood infections have been shown to produce acetate, butyrate, valerate, hexanoate, and propionate( Ward and Zeikus, 1980), which could be directly incorporated into the TAGs or serve as precursors for branched or linear fatty acids, as has been observed for nitidulid beetles( Carpophilus spp)( Bartelt and Weisleder, 1996). The ability of drosophilids that produce sex-specific TAGs to thrive on these specialized substrates alludes to the possibility that enzymes used for detoxification may have been adapted for TAG synthesis. Notably, cytochrome P450 monooxygenases have been identified in other insects as playing a crucial role in detoxification and cuticular lipid synthesis( Li et al., 2004; Qiu et al., 2012). In bark beetles, it has been suggested that a key cytochrome P450 enzyme used in pheromone synthesis was previously used for detoxification( Blomquist et al., 2010). Alternatively, conservation of TAG expression may be more related to phylogenetic effects than functional adaptation( Oliveira et al., 2011). A second pathway for TAG synthesis relies on de novo production of precursors. Each of the desert-adapted drosophilids tested in this study are still able to produce TAGs despite being raised on standard laboratory fly media. Thus, desert-adapted drosophilids are capable of using precursors from the environment and synthesizing the components de novo though significant quantitative differences are found for some TAG molecules. Based on these observations, we expect that lab-raised flies are likely to have quantitative differences in lipid profiles compared to natural populations because of the differences between the natural diet and a highly simplified lab diet. Both pathways for precursor synthesis are used by numerous Coleoptera beetle species for the production of aggregation pheromones( Tillman et al., 1999). The ability to utilize different production pathways may enable insects to switch host plants while preserving conspecific signaling. Elucidation of the biochemical pathways underlying TAG synthesis is needed to better understand whether dietary sequestration or de novo production is preferentially used by desert-adapted drosophlids and to determine the ancestral state of TAG production. In this study, we have identified an unusual chemical class of pheromones in the form of triacylglycerides and described their function as anti-aphrodisiacs. Specialized TAGs were prevalent across other Drosophila species and may also be found in other insect orders and have other functions. For example, triolein in the fire ant, Solenopsis invicta, acts as a brood pheromone and has application as bait when combined with toxicants( Bigley and Vinson, 1975). The chiral 1, 2-dioleyl-3-palmitolyl glycerol is also a brood pheromone in the honey bee, Apis mellifera( Koeniger and Veith, 1984). Taken together, triacylglycerides represent a broadly conserved and largely overlooked class of pheromones. Ultimately, to understand the evolutionary origin of these unusual molecules, it will be important to determine the behavioral function of sex-specific TAGs in other species and the underlying biosynthetic pathways. Using a broad range of analytical methods for chemical profiling will expand the detectable range of chemical classes used in communication. Correlating gene expression in the ejaculatory bulb across multiple TAG-expressing species will enable us to identify candidate biosynthetic enzymes and to provide molecular markers that will allow the evolution and function of this surprising chemical phenotype to be traced.", "role": "user" }, { "content": "For animals , the ultimate purpose of life is to have sex , as nothing is more important than passing down your genes to future generations . A wide range of strategies are therefore employed throughout nature to maximize the chances of sexual success , from ostentatious courtship rituals to the subtle subliminal signals sent out using chemicals called pheromones . Plants and animals release pheromones to influence the behavior of other plants and animals , often without the recipient being aware of it . Hundreds of different insect pheromones have been discovered . Fruit flies release a number of different pheromones , all with similar chemical structures . Now , Chin et al . have discovered that male flies belonging to several species of fruit fly that live in the desert release chemicals called triacylglycerides ( TAGs ) , which are commonly used for energy storage by many organisms as pheromones . During sex , the male fly rubs the TAGs onto the body of the female , which makes her less attractive to other male flies for several hours , thus increasing his chances of parenthood and passing his genes to future generations . TAGs are also found in other insect species , but have been largely overlooked as pheromones . Moreover , the TAGs discovered by Chin et al . have an unusual structure , not previously seen in nature , which may result from the diet of fermenting cacti the desert-dwelling fruit flies enjoy .", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nSequence-specific RNA Photocleavage by Single-stranded DNA in Presence of Riboflavin\n\nPaper sections:\n\n<p>for isoalloxazine derivatives which was obtained from in vitro selection [18][19][20] . As shown in Fig. 1A, they found the riboflavin could specifically recognize the G•U wobble in RNA duplex and induce the oxidative cleavage reaction through photosensitization. The Cleavage occurred independently of the residue located at the 3′ of the U (red, Fig. 1A), and the nucleoside downstream of the uracil (U) of the G•U base pairing was verified to be removed through oxidative mechanism. Their work inspires us to ask questions: How about the RNA/DNA duplex containing G•U wobble pair? Can any RNA sequence be photocleaved by DNA strand in presence of riboflavin?</p><p>As shown in Fig. 1B, a DNA strand was designed to complimentary to RNA target sequence except for forming a G•U wobble pair at the 17 nt position. The photocleavage of RNA target was verified by the isotope-labeled experiments (Fig. 1C). The 5′ 32 P-labeled RNA target with 26 nt in length was incubated with the DNA sequence in presence 200 μ M of riboflavin at 25 °C. After 4 h of irradiation with 45 W household light, a clear cleaving fragment with 17 nt in length was observed based on the PAGE gel analysis. Meanwhile, no cleavage could be observed when the DNA strand, riboflavin or light irradiation was absent in the cleaving reaction (Lane 1-3, Fig. 1C). To verify the importance of G•U wobble pair for the cleavage, the full complementary DNA sequence of RNA target was applied into the same reaction (Fig. 1B). As illustrated in the lane 4 of PAGE analysis in Fig. 1C, 5′ 32 P-labeled RNA target kept intact after 4 h irradiation under the same reaction condition in presence of full complementary DNA strand, which indicates riboflavin could recognize the G•U wobble in RNA/DNA duplex to induce the site-selective photocleavage of RNA target.</p><p>The chemical requirements for the RNA photocleavage were investigated. As shown in Fig. 2A, the DNA strand worked efficiently even without magnesium ion in presence of 200 μ M riboflavin (lane 1), and the cleavage efficiency did not change too much with different concentrations of Mg 2+ (Lane 2-4). However, the catalytic activity of the DNA strand strongly depended on the concentration of riboflavin (Fig. 2B). The photocleavge of RNA target by the DNA strand increased along with the increase of riboflavin concentration, reaching the maximal activity in around 50 μ M (Fig. 2B). Moreover, the temperature has little influence to the cleavage efficiency based on the DNA strand in combination with riboflavin from 20 to 40 o C (data no shown). Under optimal condition, the DNA strand in combination with riboflavin catalyzed the photocleavage of target RNA with a k obs as high as 0.25 h −1 , the half life being around 6 hours, which is much faster than most of reported artificial ribonucleases 2 . The RNA substrate containing XUY for this strategy has been carefully studied (Supplementary Fig. S1). The nucleoside X located at the 5′ of the uracil of the G•U base pair could affect the cleavage efficiency of RNA substrates (G ≈ A > C > U). The nucleoside Y RNA in substrate that will be removed from 3′ of U revealed the tread of C > U > A > G in terms of cleavage efficiency (Supplementary Fig. S1). The RNA substrate for the sequence-specific photocleavage has the frequency of one repeat in every 4 bp, which reveals the broad generality of this molecular tool with respect to different RNA sequence. The length of two binding arms of the DNA strand is variable and the catalytic efficiency would not be affected as long as the total length of two binding arms are longer than 12 nt (Supplementary Fig. S2).</p><p>As comparison, the RNA hairpin (35 nt in length) that encodes the same sequence of RNA target at 5′ end was applied to self-cleavage under the same conditions. Both the intramolecular and intermolecular reaction provided the cleaved products with the same length (Lane 2 and Lane 4, Fig. 3C), revealing riboflavin could bind to the G•U wobble base pair in RNA/RNA as well as RNA/DNA duplexes and photocleave the RNA target sequence with similar efficiency. However, the cleaved product has slightly faster mobility than the 5-32 P-labeled RNA marker (17 nt), revealing the presence of one more phosphate group at the 3′ -end (Lane 1 and Lane 2, Fig. 3C). Therefore, T4 polynucleotide kinase (PNK) that could remove phosphate group from 3′ -end of RNA has been added to the reaction mixture. The treatment with PNK didn't change the mobility of cleaved fragment on gel (Lane 2 and Lane 4, Fig. 3C), indicating that the cleavage reaction could go through oxidative elimination mechanism to form unnatural 3′ -phosphate RNA terminal. Moreover, the photocleavage activity reduce 74% in the absence of oxygen (Fig. 3D), revealing the excited photosensitizer interacts with ground state oxygen to generate a singlet oxygen molecule, which is the same as what Famlok group has observed in the photocleavage of RNA duplex 19 .</p><p>To validate the scope of this method, mircoRNA21 with 22 nt in length was applied as the target to verify whether our photocleavage method based on the DNA strand in combination with riboflavin can work or not. An uracil (U) in the middle of mircoRNA21 was selected as the cleaving site, and the DNA strand was designed to complement to the target sequence except for the formation of a G•U wobble (Fig. 4A). As shown in the isotope-labeled experiment, a cleaved fragment with expected length (11 nt) was detected based on the PAGE analysis of the photo-induced cleavage reaction (Lane 3 Fig. 4B). For the longer RNA target, we can design multiplex cleaving-sites to improve the cleavage efficiency and specificity based on our method. As a proof-of-concept, three uracil (U) of RNA (Long-RNA, Fig. 4C) has been targeted by DNA strand, and any of them once cleaved by DNA strands could result in the disfunction of RNA target. As comparison, RNA (Short-RNA, Fig. 4C) with only one cleaving-site was cleaved by one DNA strand under same reaction condition. After 2 h of photocleavage in presence of riboflavin, more than 53% of the longer RNA containing three cleaving-sites was cleaved, while only 28% of cleavage obtained for the reaction of the shorter RNA (Lane 3 and Lane 6, Fig. 4D).</p><p>To further confirm the DNA stand in combination with riboflavin as tool to hinder the RNA function through cleavage, RNA mimic of GFP (Green Fluorescent Protein) was chosen as the object of study. Recently, Jaffrey group has described a complex of RNA aptamer (24-2) and a derivative of the GFP fluorophore, 3,5-difluoro-4-hydroxybenzylidene imidazolinone (DFHBI), termed as \"Spinach\" that emits fluorescence upon transformation in specific conformation 21 (Fig. 5A). This RNA-fluorophore complex displays fluorescence properties similar to GFP and is unlike most fluorescent proteins, resistant to photo-bleaching and conditionally fluorescent. We designed DNA strand (24-2-Cat) to cleave RNA 24-2 through forming G•U wobble base pair at 31 nt position of the uracil (U) (Fig. 5B), and the cleavage activity of 24-2-Cat to RNA target in presence of riboflavin was verify by the following isotop-labeled experiment and PAGE analysis (Lane 3 Fig. 5C). The fluorescence intensity of the complexes (24-2 + DFHBI) was significant (blue curve, Fig. 5D). However, by adding 24-2-Cat into the reaction, the fluorescence intensity dropped to 44.61% after 5 h photocleavage in comparison with the reaction without the DNA strand (green curve, Fig. 5D). As a control, full complementary DNA sequence (24-2-NC, Fig. 5B) was introduced into the same reaction as a comparison, showing only 7.59% fluorescence intensity decrease (red curve, Fig. 5D). Those results indicates the photocleavage can directly hinder the function of RNA target through cleavage other than block the RNA target by forming DNA/RNA duplex.</p>\n\nDiscussion\n<p>The established sequence-specific photocleavge of RNA described here appears to have several promising features to become a new molecular tool for research and application as follows: (1) the designation of DNA strand to realize the seqence specific cleavage of RNA target is very easy to fulfill only if there are uracil nucleotides in the RNA sequence and the DNA strand is complementary to the target sequence expect to form a G•U wobble in between. (2) Though the minimal size of DNA strand is 13 nt in length, high sequence specificity could be achieved by increase the length of DNA stand to form the longer DNA/RNA duplex with target. The efficiency of the cleavage reaction based on the DNA strand in combination with riboflavin is very high. And the cleaving specificity and efficiency could be further improved by introducing more strands to cleave the same RNA at multiplex cites. (3) The cleavage of RNA by DNA strand is under tight control by using light as switch, which means the cleavage could be carried out according to specific spatial and temporal requirements. Moreover, the photosensitizer, riboflavin (vitamin B2), is endogenic coenzyme existing in the cell of most living creature, which makes this method possible to apply in vivo. (4) Unlike antisense oligonucleotide, the DNA strand in our method could interfere with the function of RNA through the irreversible photocleavge, forming cleaved fragments with unnatural 3′ -phosphate RNA terminal.</p><p>In summary, we developed a new RNA-cleaving DNA strand that catalyzes the sequence-specific photo-induced cleavage of RNA at the 3′ of the uracil of G•U wobble base pair in the presence of rioflavin as cofactors. Unlike most artificial ribonuclease that need conjugate functional chemical group to DNA sequence to fulfill the cleavage of RNA molecules specifically, the DNA strand described here is unmodified DNA sequence, cooperating with riboflavin to realize the photocleavage of RNA target through oxidative elimination mechanism. This method has broad substrate scope if the targeted RNA contains required uracil nucleotide that has high frequency of one repeat in every 4 bp. The function of RNA molecules were successfully hinder by photocleavage based on our method in vitro, which was proved to proceed through the cleavage reaction other than the hybridization with target. The biocompatibility of this method makes the DNA strand in combination with riboflavin a promising manipulable molecular tool in vivo. The direct conjunction the DNA strand with riboflavin and the application our method in the cell experiment is underway in our lab.</p>", "role": "user" }, { "content": "Constant efforts have been made to develop new method to realize sequence-specific RNA degradation, which could cause inhibition of the expression of targeted gene. Herein, by using an unmodified short DNA oligonucleotide for sequence recognition and endogenic small molecue, vitamin B2 (riboflavin) as photosensitizer, we report a simple strategy to realize the sequencespecific photocleavage of targeted RNA. The DNA strand is complimentary to the target sequence to form DNA/RNA duplex containing a G•U wobble in the middle. The cleavage reaction goes through oxidative elimination mechanism at the nucleoside downstream of U of the G•U wobble in duplex to obtain unnatural RNA terminal, and the whole process is under tight control by using light as switch, which means the cleavage could be carried out according to specific spatial and temporal requirements. The biocompatibility of this method makes the DNA strand in combination with riboflavin a promising molecular tool for RNA manipulation.Site-selective RNA cleavage to inhibit expression of special genes is consistently pursued by scientist for the promising application in biotechnology and therapy as well as biology. Previous research focused on gene suppression strategies through RNA degradation involving antisense oligonucleotides and artificial ribonucleases 1-5 . More efforts are still need to put into these methodologies to improve the efficiency before they could be broadly adapted as genomic or therapeutic tools. Since the first description of RNA interference (RNAi), there has been rapid progress towards its application as a therapeutic modality 6 . The mechanism of the RNAi is that the RNAi (the length of RNA must be longer than 21 bases), generated from double-stranded RNA, leads to specific degradation of complementary mRNA sequences 7 , triggers silencing of homologous gene expression 8 . Therefore, RNAi requires cell's own machinery to fulfill its job. Ribozymes found in nature 9,10 and deoxyribozyme obtained from in vitro selection 11,12 could high-efficiently cleave the targeted RNA sequence-specifically through formation the right tertiary structure, which usually comprises of a catalytic domain which are flanked by two substrate-recognition domains.Dilara Crate and Charles Wilson reported a site-specific inactivation of RNA transcripts through Laser-induced hydrolysis of the malachite green (MG)-binding RNA, which extend the RNA cleavage into a new scenario, namely under tight spatial and temporal control 13 . The application of this method is facing several challenges: (1) How to Introduction of the MG-binding motif into the 5′ untranslated region (UTR) of target RNA. (2) Toxicological effects of malachite green when applied in therapy. Herein, by using an unmodified short DNA oligonucleotide as binder and endogenic small molecue, vitamin B2 (riboflavin) as photosensitizer, we report a sample strategy to realize the sequence-specific photocleavage of targeted RNA.Riboflavin, as the most efficient natural photoshensitizer, has been shown to induce photooxidative DNA damage via the generation of an 8-hydroxydeoxyguanosine intermediate [14][15][16][17] . The flavin-oligonucleotide conjugates have been successfully applied in the photocleavage of double stranded DNA target. In 1997, Famulok group reported that riboflavin could cleave RNA molecules with overwhelming specificity at G•U wobble via a photo-induced mechanism when they study an RNA aptamer", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nDiscovery of Imidazoquinolines with Toll-Like Receptor 7/8 Independent Cytokine Induction\n\nPaper sections:\n\n<p>Toll-like receptors 7 and 8 (TLR 7/8) are key targets for the design of small molecule immunomodulators for use as vaccine adjuvants and anticancer/antiviral agents.1,2,3 These receptors trigger the NF-κB mediated production of proflammatory cytokines and chemokines in response to the presence of viral single stranded RNA (ssRNA) within the endosome of B cells and dendritic cells.4 The imidazoquinolines imiquimod (1) and resiquimod (2) are potent agonists of this pathway. These compounds first appeared in the patent literature in the 1980s.5,6 Topical imiquimod cream was FDA approved in 1997 for the treatment of basal cell carcinoma and there remains extensive interest in optimizing this class of compounds for multiple indications.7,8 Although their ability to induce interferon-α (IFNα) was known at that time, the mechanism of action was not discovered until 2002 when Hemmi et al. definitively linked the imidazoquinolines to TLR 7 function.9 They reported that both 1 and 2 failed to induce cytokine production in TLR 7 deficient mice. The results were further supported and extended by Gorden et al. and Jurk et al. who disclosed that resiquimod also activates the TLR 8 signaling pathway. 10,11</p><p>Following the discovery that imidazoquinolines activate TLR-7 and -8, Gerster et al. reported the synthesis and evaluation of a large series of analogs that included many compounds from the original patent literature.12 Although the compounds were evaluated for IFNα production, TLR 7/8 functional data was not reported. The most potent analogs were found to contain a short alkyl chain at the C-2 position (with n-butyl showing the highest potency) and short, hydroxyl alkyl chains at N-1. In terms of aryl substitutions, it was determined that the amino group at C-4 was required for activity. Although the chemistry was limited, simple substitutions to the remaining aryl positions were found to abolish activity, except in the case of C-7. The C-7 methoxy, hydroxyl, and methyl derivatives retained modest IFNα production. In more recent work, Shukla et al. verified the TLR 7 activity of a series of C-2 and N-1 substituted imdazoquinolines, including imiquimod.13 Their results indicated that the most potent and TLR 7 selective compounds contained an n-butyl group at C-2 (as suggested by Gerster et al.) and either a 2-hydroxy-2-methylpropyl or benzyl group at N-1. Although it was reported that all the C-2 alkyl compounds were TLR 7 selective, a systematic evaluation of TLR 8 binding was not presented.</p><p>One of the limiting factors in the design and synthesis of imidazoquinolines for screening is the cumbersome nature of the synthetic route. Prior reports have used traditional heterocyclic chemistry that is borrowed from purine base synthesis.14 The approach applies a modified Traube reaction to annulate diaminoquinolines by condensation with ortho esters or acid chlorides (yielding the desired imidazoquinoline tricycle). While this approach allows substitutions to be efficiently introduced to the imidazole ring system, modifications to the quinoline ring are more complicated, requiring additional synthetic steps to be added to obtain the substituted precursors. Functional group modifications must also be compatible with the reaction conditions used in subsequent steps, further limiting the synthetic pathway. To address this problem, we have developed an alternative route that exploits the Suzuki-Miyaura reaction to efficiently synthesize highly substituted imidazoquinolines in 4 steps. In this report, we describe the application of this chemistry to produce a set of C-7 methoxy carbonyl derivatives (5–6) in addition to un-substituted analogs (3–4). We also present TLR 7/8 and cytokine screening data that indicates this series functions through a unique pathway in activating cytokine production.</p><p>The synthesis of 3–6 begins with the multicomponent condensation of the aminomalononitrile (7), orthoester (8a/b), and β-amino alcohol (9) to afford the 5-amino-imidazole-4-carbonitriles (10a/b).15,16 The key iodoimidazole intermediates (11a/b) are obtained in good yield using a modified Sandmeyer reaction employing isoamyl nitrite and diiodomethane. 17 Suzuki coupling of 11a/b with 2– aminophenylboronic acid (12a) or 2–amino–4–methoxycarbonylphenylboronic acid (12b) furnishes the atropisomeric intermediates (13–16). Intramolecular cyclization is achieved by treatment of the heterobiaryl intermediates with either anhydrous HCl or NaOMe to afford the desired imidazoquinolines (3–6). Acid catalysis is preferred for substrates 15–16 due to partial saponification of the methyl esters under the basic conditions. Although this approach provides an efficient method to install novel functionality on the benzene ring of the quinoline, we found that the efficiency of the cross coupling step was influenced by the C-2 alkyl substituent. It was noted that 11b reacted sluggishly with a significant portion undergoing competitive protio-dehalogenation while 11a furnished the desired cross–coupled products (13 and 14) in 3 h with high yields. To avoid steric hindrance with the bulky C-2 substituent, the N-1 group in 11b likely is directed toward the 5-iodo substituent, thereby hindering the palladium–catalyzed cross coupling and explaining its lower intrinsic reactivity.</p><p>Compounds 1–6 were initially screened using TLR 7 and TLR 8 reporter cell lines for their ability to induce the NF-κB pathway. Consistent with prior studies, imiquimod (1) was determined to be a selective TLR 7 agonist, whereas resiquimod (2) triggered both TLR7 and TLR 8 (as reported in Table 1). Resiquimod also showed an increased potency at TLR 7 as compared to that of imiquimod. This increased potency may be linked to the C-2 substituent as suggested by the activity of compound 3. Deletion of the C-2 ethoxymethyl moiety of resiquimod resulted in a 67-fold drop in TLR 7 agonist activity and abolished TLR 8 activation entirely. Further evidence to support the vital role C-2 substitution plays in both potency and selectivity can be found in the data reported for 4. Both TLR 7 and 8 function was restored and enhanced by addition of a C-2 butyl group to 3. The C-2 butyl substitution in 4 increased TLR 7 and 8 potency by approximately 10- and 60-fold, respectively, when compared to resiquimod.</p><p>The most intriguing and novel findings were revealed when a methyl ester was added to the quinoline ring at C-7, generating compound 5. This compound was entirely devoid of TLR 7 and TLR 8 agonist activity as measured by the reporter cells. This result was completely unexpected. Based on previous reports that indicated C-7 substituted imidazoquinolines stimulated the release of IFNα, the compounds were further screened for cytokine production. The results given in Table 1 show that despite displaying no appreciable activity in triggering TLR 7 or 8, compound 5 induced the release of interleukin 1 beta (IL-1β) from mouse bone marrow derived dendritic cells (BMDC) at levels 15 times greater than compounds 1–4. In addition to IL-1β, compound 5 induced 2–3 times more TNFα and IL-12p40 than imiquimod, demonstrating a broad induction of inflammatory cytokines (commonly links with TLR activation). Once again, TLR 7 and 8 binding was restored by addition of a C-2 butyl group to 5. Although 6 was not the most potent TLR 7 and 8 agonist of the group, the ability to significantly enhance IL-1β production was retained, suggesting the C-7 methyl ester derivatives are triggering an alternative pathway to cytokine production.</p><p>To our knowledge this is the first demonstration of an imidazoquinoline that triggers a profound induction of inflammatory cytokines in the absence of TLR 7 or 8 agonist activity. Although the mode of action of 5 is currently not known, some clues to the pathways involved may be found in high levels of IL-1β reported for 5 and 6. The unique and important role of IL-1β has only recently been appreciated as \"signal three\" for activation of CD4 T cells. Specifically, IL-1 receptor deficient CD4 T cells have inferior proliferative and functional capacities, demonstrating a direct effect of IL-1β on the T cell. Moreover, recombinant IL-1β can profoundly improve memory T cell formation and antibody responses against protein antigens in mice. 18 It is important to note that IL-1β release is dependent on activation of the inflammasome, an intracellular pathway that senses microbial infection including ssRNA.19 Thus, it is reasonable to conclude that the alternative pathway accessed by the C-7 methyl ester derivatives may involve inflammasome activation. Considering that IL-1β has a unique capacity to increase antibody responses and modulate CD4 T cell differentiation, this discovery could be the first step in developing novel imidazoquinoline analogs that have superior activity as vaccine adjuvants or for single agent therapy. This hypothesis awaits validation in mouse models and human patients.</p>", "role": "user" }, { "content": "Toll-like receptors (TLRs) are key targets in the design of immunomodulating agents for use as vaccine adjuvants and anticancer treatments. The imidazoquinolines, imiquimod and resiquimod, have been shown to activate TLR-7 and -8 which in turn induce cytokine production as part of the innate immune response. Herein, we report the synthesis and discovery of a C7-methoxycarbonyl derivative of imiquimod that stimulates cytokine production but is devoid of TLR-7/8 activity. Data is presented that shows this analog not only induces IL-12p40 and TNF production, similar to that of imiquimod and resiquimod, but greatly enhances the production of IL-1\\xce\\xb2, a key cytokine involved in activation of CD4 T cells. It is further demonstrated that TLR-7/8 activation can be recovered by the addition of a C2-alkyl substituent to this newly discovered analog. The results support the existence of an alternative mechanism of action by which imidazoquinolines can stimulate cytokine production.", "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 number of protein coding genes in the human genome?\n\nContext: Here, seven membrane protein topology prediction methods based on different underlying algorithms, such as hidden Markov models, neural networks and support vector machines, have been used for analysis of the protein sequences from the 21,416 annotated genes in the human genome.\nhe GENCODE 7 release contains 20,687 protein-coding and 9640 long noncoding RNA loci and has 33,977 coding transcripts not represented in UCSC genes and RefSeq\nCurrent catalogs list a total of approximately 24,500 putative protein-coding genes.\nClustering of these sequences using cross-species relationships suggests that millions of expressed sequences may correspond to only approximately 20,000 distinct protein-coding transcripts.", "role": "user" }, { "content": "Between 20,000 and 25,000", "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:\nEffect on neutrophil kinetics and serum opsonic capacity of intravenous administration of immune globulin to neonates with clinical signs of early-onset sepsis.\nAbstract 1:\nThis study was designed to test the hypothesis that administration of immune globulin to human neonates with early-onset bacterial sepsis would (1) facilitate neutrophil egress from the marrow, (2) improve serum opsonic capacity, and (3) facilitate recovery from the infectious illness. Twenty-two newborn infants with clinical signs of early-onset sepsis were given an intravenous infusion of either 750 mg of immune globulin (IVIG) per kilogram of body weight or the same volume of a vehicle control (albumin). All 22 infants survived, but significant hematologic, immunologic, and respiratory differences were observed after the IVIG and not after the control infusion. Eleven of the patients had neutropenia; 24 hours after the infusions, the neutropenia had resolved in all six IVIG recipients but persisted in all five control recipients (p less than 0.001). Ten patients had I/T neutrophil ratios (a measure of immature neutrophils to total neutrophils on the leukocyte differential count) of less than 0.2. One hour after completion of the infusions, all five IVIG recipients had elevated I/T ratios (mean +/- SEM:0.10 +/- 0.05 before vs 0.43 +/- 0.03 after infusion; p less than 0.001), suggesting a prompt release of neutrophils from the marrow neutrophil storage pool into the circulation; no increase in the I/T ratio was observed in the control recipients. Six hours after the IVIG infusions, the ratio of arterial oxygen tension to fraction of inspired oxygen increased; no increase was observed after control infusions. Serum concentrations of IgG, IgG1, IgG2, IgG3, IgG4, and total hemolytic complement and the capacity of serum to support opsonophagocytosis of type II and type III group B streptococci increased markedly in the IVIG recipients but not in the control subjects. We conclude that administration of 750 mg IVIG per kilogram to neonates with clinical signs of early-onset sepsis was associated with immunologic, hematologic, and physiologic improvement.\n\n\nTitle 2:\nImmunoglobulin supplementation in prevention or treatment of neonatal sepsis.\nAbstract 2:\nnan\n\n\nTitle 3:\nIgM-enriched intravenous immunoglobulin therapy in neonatal sepsis.\nAbstract 3:\nDespite the development of newer generation of antibiotics, mortality from neonatal sepsis remains high. In a prospective, randomized study, we investigated the use of IgM-enriched immunoglobulin therapy in neonatal sepsis. Two groups of 30 infants each (matched for gestational age, sex, weight, and other variables) were randomly allocated to receive either antibiotics alone (control group) or antibiotics plus 5 mL/kg/d for four days of IgM-enriched immunoglobulin intravenously (immunotherapy group). Mortality from sepsis in the control group was 20% (6/30), while in the immunotherapy group it was 3.3% (1/30). We conclude that IgM-enriched immunoglobulin therapy in conjunction with antibiotic therapy significantly reduces mortality from neonatal sepsis.\n\n\nTitle 4:\nThe use of IgM-enriched intravenous immunoglobulin for the treatment of neonatal sepsis in preterm infants.\nAbstract 4:\nThe value of IgM-enriched immunoglobulin therapy in 44 preterm infants with neonatal sepsis was evaluated in a prospective randomized study. All infants received antibiotic therapy and fresh plasma and/or whole blood transfusions. Twenty randomly-chosen infants were allocated to receive 5 ml/kg/d of IgM-enriched immunoglobulin intravenously for three days. Although the mortality rate in preterm infants whose gestational ages were 31-34 weeks in the immunotherapy group was slightly lower than in the control group, the general mortality rate from sepsis in the control group (9/24) and in the immunotherapy group (6/20) showed no statistically significant difference (37.5% vs 30.0%, p < 0.05).\n\n\nTitle 5:\nTreatment of neonatal sepsis with intravenous immune globulin.\nAbstract 5:\nNeonatal sepsis is a major cause of death and complications despite antibiotic treatment. Effective adjunctive treatments are needed. Newborn infants are relatively deficient in endogenous immunoglobulin. Meta-analyses of trials of intravenous immune globulin for suspected or proven neonatal sepsis suggest a reduced rate of death from any cause, but the trials have been small and have varied in quality.\n At 113 hospitals in nine countries, we enrolled 3493 infants receiving antibiotics for suspected or proven serious infection and randomly assigned them to receive two infusions of either polyvalent IgG immune globulin (at a dose of 500 mg per kilogram of body weight) or matching placebo 48 hours apart. The primary outcome was death or major disability at the age of 2 years.\n There was no significant between-group difference in the rates of the primary outcome, which occurred in 686 of 1759 infants (39.0%) who received intravenous immune globulin and in 677 of 1734 infants (39.0%) who received placebo (relative risk, 1.00; 95% confidence interval, 0.92 to 1.08). Similarly, there were no significant differences in the rates of secondary outcomes, including the incidence of subsequent sepsis episodes. In follow-up of 2-year-old infants, there were no significant differences in the rates of major or nonmajor disability or of adverse events.\n Therapy with intravenous immune globulin had no effect on the outcomes of suspected or proven neonatal sepsis.\n\n\nTitle 6:\nMulticenter randomized placebo controlled trial of therapy with intravenous immunoglobulin in decreasing mortality due to neonatal sepsis.\nAbstract 6:\nTo determine whether therapy with intravenous immunoglobulin G (IVIG) would decrease mortality in neonatal sepsis.\n Three tertiary care neonatal intensive care units in the city of Bangalore.\n All neonates admitted to the Neonatal Intensive Care Units with the clinical diagnosis of sepsis and having at least C-reactive protein and one other rapid diagnostic criteria positive were enrolled. Neonates with a birth weight of less than 1000 g and those with any major congenital malformation were excluded. The neonates were randomized to receive 1 g/kg of IVIG on three consecutive days or an equivalent amount of placebo. The rest of the treatment including antibiotics and supportive care was as per the treating physician's decision. The main outcome variable was survival.\n The trial was carried out over a period of 8 months and recruited 58 neonates. Seven neonates who qualified but did not receive either IVIG or placebo were taken into a separate control group, and one baby who received only one dose of IVIG was excluded from the analysis. Twenty-five neonates were enrolled into the IVIG arm and 25 in the placebo arm. The neonates in the therapy and placebo groups were comparable in terms of birth weight (2144+/-675 g vs. 2072+/-682 g), gestation (37.0+/-3.56 vs. 35.8+/-3.52 weeks), sex distribution, duration of stay, and number requiring ventilation. The placebo group had a significantly higher number of babies with positive blood culture. Seven babies in each group died (p>0.05). There was no significant benefit in using IVIG (OR 1.0; 95% CI 0.25-4.07) (p = 0.74).\n In the sample studied therapy with IVIG did not reduce mortality in neonatal sepsis", "role": "user" }, { "content": "In previous reviews, we encouraged researchers to undertake well-designed trials to confirm or refute the effectiveness of IVIG in reducing adverse outcomes in neonates with suspected infection. Such a trial has been undertaken. Results of the INIS trial, which enrolled 3493 infants, carry a heavy weight in the current update of this review, and the undisputed results show no reduction in death or major disability at 2 years of age. Routine administration of IVIG to prevent mortality in infants with suspected or proven neonatal infection is not recommended.", "role": "assistant" } ]

[ { "content": "Answer the following biomedical question based on the given context. Provide only the answer without additional explanation.\n\nQuestion: Which aminoacid position in the human CREB protein is phosphorylated?\n\nContext: pCREB(Ser133) as a model system\nCREB and its activated form pCREB-Ser(133) (pCREB)", "role": "user" }, { "content": "Ser133", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nthese are the malignant neoplasms mainly affecting lymph nodes , spleen and other nonhematopoietic tissues .\nthey are divided into hodgkin 's and non - hodgkin 's subtypes and are of b - cell or t - cell origin .\nthe majority of hodgkin 's lymphomas presents as a nodal disease involving mainly cervical and axillary nodes . among the 40% non - hodgkin 's lymphomas presenting extranodally , gastrointestinal tract , waldeyer 's ring , spleen , salivary gland are the most common sites of occurrence and are rarely seen in the oral cavity .\nit may arise from preexisting low - grade lymphomas or as a de novo neoplasms . in the paraoral and primarily oral lymphomas , diffuse large b - cell lymphomas ( dlbcl ) are most common and is show a male predominance .\nthe most common sites of involvement intraorally are palate , buccal mucosa and tongue with the prevalence of only 35% .\na 79-year - old male patient reported to the department of oral pathology and microbiology with a chief complaint of pain and swelling on the upper left buccal mucosa since 1-month .\nextraorally , facial asymmetry was noticed with diffuse swelling on the left sided cheek region , approximately 3 cm 2 cm in size , irregular in shape , vertically extending from inferior border of zygomatic arch up to 12 cm above corner of mouth and was extending from ala of nose up to tragus of the ear mediolaterally .\non intraoral examination , the swelling was diffuse , soft and roughly oval in shape [ figure 1 ] .\nthe swelling was situated in maxillary buccal vestibule extending anteroposteriorly from 26 to 28 region and mediolaterally from buccal mucosa of left side obliterating the vestibule , crossing the alveolar ridge and extending onto palatal mucosa .\nthe swelling was approximately 4 cm 2 cm in size and was of smooth surface texture .\nclinical image shows diffuse , roughly oval shape swelling situated in maxillary buccal vestibule radiologically , on waters view haziness was noticed in the left maxillary sinus region as compared to the right side , extending from superior border up to inferior border of sinus vertically and extending from medial to the lateral border of sinus mediolaterally [ figure 2 ] .\nradiographic images shows haziness in left maxillary sinus region an incisional biopsy was advised from buccal mucosa of left side under local anesthesia after routine blood investigations , which were within the normal limits . human immunodeficiency virus ( hiv )\non histopathological examination , the hematoxylin and eosin stained tissue section showed diffuse , monotonous proliferation of round cells , in the form of sheets within the loose fibrillar connective tissue stroma [ figure 3 ] .\nthese cells were having large nuclei with a small amount of cytoplasm resembling lymphoid cells .\nit also revealed the presence of cells with large nuclei showing prominent nucleoli arranged at the periphery , exhibiting condensation and vesiculation of chromatin with cellular and nuclear pleomorphism .\nthese cells resembled centroblasts [ figure 4 ] and immunoblastic cells [ figure 5 ] .\nthe adjacent minor salivary gland tissue with mucous acini showed infiltration of these cells , disturbing the normal architecture .\nhistopathological image shows diffuse monotonous proliferation of round cells in the form of sheets within a loose fibrillar stroma ( h&e stain , 100 ) histopathological image shows round centroblastic cells with large nuclei ( h&e stain , 400 ) histopathological image shows round immunoblastic cells ( h&e stain , 400 ) overall histopathological features suggest the diagnosis of atypical lymphoproliferative lesion . for confirmation\non immunohistochemical analysis , cd45 ( leukocyte common antigen ) [ figure 6 ] positivity distinguished malignant lymphomas from other non - lymphoid neoplasms , strong positivity for cd20 ( b - cell marker ) [ figure 7 ] and weak expression of cd3 ( t - cell ) marker suggests the b - cell origin of the lesion and ki-67 ( proliferation marker ) positivity indicates the proliferative potential of the lesion .\nimmunohistochemical image shows strong positivity for cd45 ( ihc stain , 100 ) immunohistochemical image shows strong positivity for cd20 ( ihc stain , 100 )\nin head and neck region , lymphomas are the second most common neoplasms . among 40% extranodal non - hodgkin 's lymphomas majority of cases\nb - cell lymphomas are classified as precursor b - cell neoplasm and peripheral b - cell neoplasm . according to revised european - american lymphoma classification of non - hodgkin 's lymphomas , dlbcl is a peripheral b - cell neoplasm . world health organization in 2008\nfurther categorized aggressive b - cell lymphomas as : \n dlbcl not otherwise specifieddlbcl associated with chronic inflammationlarge b - cell lymphoma arising in human herpes virus ( hhv)-8 associated castelman 's diseaseb - cell lymphoma unclassifiable andburkitt 's lymphoma . \n \ndlbcl not otherwise specified dlbcl associated with chronic inflammation large b - cell lymphoma arising in human herpes virus ( hhv)-8 associated castelman 's disease b - cell lymphoma unclassifiable and burkitt 's lymphoma . the kiel classification subdivided large b - cell lymphomas by pure morphology into centroblastic and immunoblastic lymphomas .\nthe working formulation , on the other hand , subdivided large b - cell lymphomas according to their biological behavior into an intermediate - grade ( large cleaved and large noncleaved ) and a high - grade ( immunoblastic ) category . among dlbcls ,\ndlbcl not otherwise specified is the most common subtype and it accounts for up to 2030% cases seen in elderly , above 70 years of age .\nit is characterized by large neoplastic b lymphocytes diffusely proliferating , with nuclei larger than or equal to normal macrophage nuclei in size , or more than twice the size of normal lymphocyte and are seen arising de novo .\nvarious studies have shown that dlbcls shows an average age of presentation that is above 5055 years with a male predominance .\nthe present case was also reported in elderly ( 79-year - old ) male patient .\ngastrointestinal tract , thyroid , bone , skin and lungs are the most frequent extranodal sites and in orofacial region waldeyer 's ring , salivary gland , tonsils , nasopharynx , base of the tongue are frequently involved .\nintraorally it shows maxillary predominance ( 77% ) and the majority of cases are reported on the palate .\nthis is in accordance with the present case which was also reported in maxillary vestibular region and extended towards the palate .\nhistopathologically , the pattern of invasion in lymph nodes or extranodal sites is diffuse , with frequent peripheral tissue involvement .\nthe plasmablastic form is another morphologic variant but is more commonly associated with epstein - barr virus or anaplastic lymphoma kinase positive b - cell lymphomas . in the present case , there was a presence of diffuse involvement of mucosa and infiltration of adjacent minor salivary glands , main cell types seen in this case were centroblastic and immunoblastic variants showing cells with larger nuclei and prominent nucleoli , chromatin condensation and pleomorphism .\ndifferential diagnosis includes reactive non - neoplastic processes in which aggregates of lymphocytes are evident but they did not show atypical features . in case of burkitt 's lymphoma the cells are of homogeneous size and shape giving starry sky appearance due to presence of macrophages which were absent in this case . in plasmablastic lymphomas\nclassic hodgkin 's lymphoma is predominantly the disease of lymph nodes and rarely affects oral cavity showing reed \nother malignancies such as liposarcoma , round cell type show sheets of poorly differentiated round cells with finely vacuolated or granular cytoplasm and cells may appear epitheloid or pericytoid type .\ncarcinomas of poorly differentiated type show atypical round cells with eosinophilic cytoplasm , but centroblastic and immunoblastic cells are not seen .\nthus , after excluding all these possibilities and the presence of centroblastic and immunoblastic cells a diagnosis of dlbcl was suggested .\nthe beginning ihc panel includes cd20 , cd3 , cd45 and if alteration of b - cell areas are seen then antibodies against cd5 , cd10 , cd23 , cd43 , bcl2 , bcl6 protein , etc . ,\nprevious studies have done an immunohistochemical analysis of leukocyte common antigen ( lca ) , cd20 , cd5 to confirm the diagnosis . here , in the present case ki-67 ( proliferative marker ) , cd45 ( common leukocyte antigen ) , cd20 ( b - cell marker ) analysis were done , which showed strong positivity .\nit can be best treated by surgical excision with adjuvant radiotherapy if the lesion is localized ; chemotherapy is the treatment of choice in case of diffuse and aggressive lesions .\nno significant difference in prognosis has been found between the three major groups : centroblastic , immunoblastic and anaplastic . in diffuse cases and hiv patients ,\nthe prognosis is worse than that in follicular , nodal and hiv - negative cases .\nthe diagnosis of these lesions is challenging due to their resemblance to inflammatory and benign lesions , chances of misdiagnosis are more and the treatment is prolonged . hence , the clinicians must consider it as a possible differential diagnosis since the lesions are aggressive and efforts should be taken to diagnose these lesions as early as possible as they demonstrate fatal outcomes .", "role": "user" }, { "content": "lymphomas are the group of neoplasms originating from lymphoreticular system mainly from lymph nodes , among them up to 40% of non - hodgkin 's lymphomas present extra nodally . in oral cavity , lymphomas are least common and account for 35% of all malignancies , presenting mainly in older age groups with male predominance . according to revised european - american lymphoma classification , among b - cell and t - cell subtypes of non - hodgkin 's lymphomas , diffuse large b - cell lymphoma ( dlbcl ) is the most common , characterized by diffuse proliferation of large neoplastic b lymphoid cells . here we present a case report of dlbcl affecting oral cavity involving left buccal vestibule and extending onto the palate , along with its clinical , histopathologic and immunohistochemical features .", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nAn Unprecedented Dual Antagonist and Agonist of Human Transglutaminase 2\n\nPaper sections:\n\n<p>Transglutaminase 2 (TG2) is the most prevalent member of the mammalian transglutaminase family, with abundant intracellular as well as extracellular expression in most organs. It catalyzes transamidation or deamidation of Gln residues in protein and peptidic substrates, and is regulated by several post-translational mechanisms1. In the absence of guanine nucleotides and presence of Ca2+, TG2 adopts an open, catalytically active conformation2,3. Reduction of an intramolecular, vicinal disulfide bond is also required for enzymatic activity4,5. Whereas the precise biological role of TG2 remains unclear, the protein may play an important role in the pathogenesis of a variety of human diseases. For example, deamidation of selected Gln residues in proteolytically stable peptides derived from dietary gluten is believed to underlie celiac disease pathogenesis6-8. Aberrant TG2 expression and activity is also implicated in the pathogenesis of other disorders, such as cancer, Alzheimer's disease, Parkinson's disease, Huntington's disease, and cystic fibrosis9-13. Thus, TG2 is a target of interest for the development of inhibitors.</p><p>In 2011, we identified acylideneoxoindoles as a new class of reversible inhibitors of TG214. A subset of these molecules exhibited mixed inhibitory behavior, suggesting that this class of TG2 modulating agents bound to an allosteric site on the enzyme. Here, we demonstrate that, at low concentrations of free Ca2+, some of these compounds can augment the activity of TG2. One molecule, CK-IV-55, was capable of activating TG2 in the extracellular matrix of cultured WI-38 fibroblast cells.</p><p>The allele of human TG215 used in this study is the V224 variant. Although our previous studies utilized the G224 form of recombinant human TG216, sequence analysis has demonstrated that Val is the most common residue at this position. Moreover, the V224 variant is reported to have higher Ca2+-sensitivity and activity15.</p><p>To reassess the dependence of TG2 on its allosteric regulators, GTP and Ca2+, a coupled enzymatic assay developed by Keillor and Day17 was employed. In brief, TG2 catalyzes the deamidation of the protected dipeptide substrate Cbz-Gln-Gly (ZQG), releasing ammonia, which is used in the glutamate dehydrogenase-dependent conversion of α-ketoglutarate to glutamate. The latter step utilizes the cofactor, NADH, allowing the reaction to be monitored continuously at 340 nm. Under saturating Ca2+ concentrations, the kcatand KM of the V224 variant were 16.8 ± 0.8 min−1 and 4.7 ± 0.6 mM, respectively, verifying a higher catalytic efficiency compared to the G224 form of the enzyme (Figure S1, Table S1). Lineweaver-Burk analysis (Figure 1A) revealed that Ca2+ acted predominantly as a competitive activator of V224 TG2 (Ka = 0.6 ± 0.3 mM) in contrast to mixed activation of the G224 variant18, and that the stable GTP analog, GMP-PNP, was a competitive inhibitor (Ki = 27 ± 9 μM) of TG2 (Figure 1B).</p><p>As a first step toward broader biological use of our acylideneoxoindole inhibitors, we attempted to block the activity of extracellular TG2 in tissue culture. WI-38 fibroblasts were grown to near-confluence, and exposed to either vehicle (DMSO) or selected inhibitors for 3 h. Cumulative TG2 activity during this period was measured by incorporation of 5-(biotinamido)-pentylamine (5-BP) into proteins of the extracellular matrix, as shown before19-21. Surprisingly, addition of 1 μM CK-IV-55 (Table 1) to this assay system resulted in activation of extracellular TG2 (Figure 2). At higher concentrations of CK-IV-55 (10 μM), TG2 activity was suppressed compared to the 1 μM case. Similar observations were made with a close structural analog, CK-IV-67 (Table 1), although higher absolute concentrations of the latter inhibitor were required to see elevated 5-BP incorporation, presumably due to the weaker affinity of this acylideneoxoindole for TG2 (data not shown). These unexpected results motivated us to reconstitute the dual agonist/antagonist behavior of acylideneoxoindoles in vitro using recombinant human TG2.</p><p>As shown in Figure 3, at a saturating Ca2+ concentration, CK-IV-55 was indeed a non-competitive inhibitor of the V224 variant of TG2 (Ki = 3.3 ± 0.9 μM). However, when catalytic activity of the protein was assessed over a range of sub-saturating Ca2+ concentrations in the presence or absence of CK-IV-55, weak but reproducible agonism was observed between 0.5-0.7 mM Ca2+ (Figure 4A). These titrations were repeated for each inhibitor listed in Table 1. In all cases, weak but measurable agonism was observed at a Ca2+ concentration of 0.6 mM (Figure 4B).</p><p>To assess the effect of CK-IV-55 on the transamidating activity of TG2, a microtiter plate assay was used, where 5-BP is incorporated into immobilized N-N-dimethylcasein and quantified using streptavidin22. Guided by the data shown in Figure 4A, a sub-saturating Ca2+ concentration of 0.6 mM was used in this assay. Whereas agonism was not observed in the presence of Ca2+ alone, CK-IV-55 markedly enhanced the transamidation activity of TG2 in the presence of both 0.6 mM Ca2+ and 100 μM GMP-PNP (Figure 4C). Thus, the observed agonistic activity of CK-IV-55 in cell culture (Figure 2) may reflect the presence of some \"closed conformation\" TG2 in the extracellular matrix of WI-38 fibroblasts, which can be agonized by CK-IV-55 in the presence of sub-saturating (~0.5 mM) concentrations of Ca2+. Whereas GTP-bound TG2 has not been reported in the extracellular environment of mammals, the corresponding closed state of the protein is believed to persist due to other (e.g., proteoglycan) interactions23.</p><p>The non-competitive inhibitory behavior of CK-IV-55 (Figure 3) suggests that acylideneoxoindoles are allosteric modulators of TG2. To interrogate the binding mode of these compounds, we first evaluated whether CK- IV-55 induces a conformational change in the protein, analogous to Ca2+ and GTP. It is known, for example, that the active site-directed irreversible inhibitor Ac-P(DON)LPF-NH2, locks TG2 in the open state2. However, based on native PAGE analysis, the presence of CK-IV-55 did not have a measurable influence on the relative distribution of the open versus closed states of TG2 (Figure S3). Thus, it is unlikely that acylideneoxoindoles bind the enzymatic active site of TG2.</p><p>Structural and mutagenesis studies have shown that the R580 residue contributes significantly to the GTP binding pocket of TG2, as indicated by attenuated GMP-PNP inhibition of the R580A mutant of human TG23,24-26. As shown in Figure 5, the inhibitory potency of CK-IV-55 was unaltered in this TG2 mutant. Moreover, its agonistic effect in the presence of GMP-PNP was also evident in the R580A mutant. Together, these observations suggest that the binding site of CK-IV-55 is distinct from the GTP-binding pocket of TG2.</p><p>The largest of the four domains of human TG2 is its catalytic core; this domain is also the principal site of Ca2+ ion binding. To test whether CK-IV-55 targets the catalytic core of TG2, a truncated form of human TG2 (1-466) lacking both of its C-terminal beta-barrel domains was expressed and purified. This derivative retains deamidating as well as transamidating activity, but lacks the ability to be inhibited by guanine nucleotides27,28. Not only did CK-IV-55 retain its ability to inhibit TG2 (1-466), but it also emerged as a total antagonist of the truncated protein in contrast to its partial inhibitory character on wild-type TG2 (Figure 6). Thus, the binding site of CK-IV-55 lies within the N-terminal domain and/or the catalytic core of TG2.</p><p>Taken together, the above findings led us to speculate that CK-IV-55 may exert its unusual agonist/ antagonist effects by interacting with the binding site(s) of one or more Ca2+ ions. Although these sites have not been crystallographically defined, detailed biochemical and mutagenesis studies by Király et al. have led to a model in which TG2 has one high-affinity (Kd ~ 1 μM) and five lower-affinity (Kd ~ 1 mM) Ca2+ binding sites29. Occupancy of the high-affinity binding site (designated S1) and two of the lower affinity binding sites (S2A and S2B) is insufficient for activating TG2; all of the remaining binding sites (S3, S4, and S5) are critical for maximum catalytic activity. We hypothesized that CK-IV-55 bound to one or both of the S2 sites. To test this hypothesis, we introduced the same deleterious mutants at sites S2A and S2B as reported previously by Kiraly, et al. (E396Q/N398S/D400N for S2A and E447Q/E451Q/E452Q/E454Q for S2B)29. As seen in Figure 7, CK-IV-55 had comparable inhibitory effect on the activity of the S2A mutant as the wild-type enzyme, whereas it had no effect on the S2B mutant. Thus, it appears that this inhibitor and, by inference, all other acylideneoxoindoles in the series, bind to the S2B Ca2+ binding site of the protein.</p><p>A simple mechanistic model for the dual agonist/ antagonist characteristics of CK-IV-55 is proposed in Figure 8. According to this model, CK-IV-55 acts as a partial agonist when it binds to the state of TG2 whose low-affinity Ca2+ binding sites are unoccupied. In contrast, it is an antagonist when it prevents full occupancy of the Ca2+ binding sites of the protein.</p><p>In the context of celiac disease, the discovery of a small organic molecule that is capable of partially agonizing the activity of human TG2 provides a fundamentally new insight of potential relevance to disease pathogenesis. It is well established that TG2-catalyzed deamidation of gluten peptides increases their specificity towards disease associated HLA-DQ2 or HLA-DQ8 molecules7,8. However, the mechanism of TG2 activation in the celiac intestine is unknown. The problem is especially vexing as one considers the patho-physiological basis for the breakdown of oral tolerance to dietary gluten, i.e., during the onset of this autoimmune disorder. The prevalence of celiac is on the rise in developed countries30-32, and there is growing evidence suggesting a role for environmental triggers other than gluten33-35. Many environmental risk factors have been proposed in recent years based on observational studies, including maternal iron use during pregnancy36, infections with rotavirus37 and Campylobacter jejuni38, and exposure to antibiotics39 or to elective Caesarian section40; however, in no instance is a mechanistic relationship between the putative cause and effect obvious. Based on our findings in this report, we speculate that small molecules derived from our diet or our microbiota may elevate the activity of extracellular TG2 in the small intestinal mucosa. If so, then chronically elevated TG2 activity in genetically susceptible individuals may enhance the probability of breaking down oral tolerance to dietary gluten and a concomitant increase in celiac disease prevalence. The discovery of natural and/or man-made products in the human diet or environment that have the ability to mimic the agonistic capacity of CK-IV-55 may promote a better understanding of this major public health concern.</p>", "role": "user" }, { "content": "Transglutaminase 2 (TG2) is a ubiquitously expressed, Ca2+-activated extracellular enzyme in mammals that is maintained in a catalytically dormant state by multiple mechanisms. Although its precise physiological role in the extracellular matrix remains unclear, aberrantly up-regulated TG2 activity is a hallmark of several maladies, including celiac disease. Previously, we reported the discovery of a class of acylideneoxoindoles as potent, reversible inhibitors of human TG2. Detailed analysis of one of those inhibitors (CK-IV-55) led to an unprecedented and striking observation. Whereas this compound was a non-competitive inhibitor (3.3 \\xc2\\xb1 0.9 \\xce\\xbcM) of human TG2 at saturating Ca2+ concentrations, it activated TG2 in the presence of sub-saturating but physiologically relevant Ca2+ concentrations (0.5\\xe2\\x80\\x930.7 mM). This finding was validated in a cellular model of TG2 activation and inhibition. Mutant TG2 analysis suggested that CK-IV-55 and its analogs bound to a low-affinity Ca2+ binding site on the catalytic core of TG2. A mechanistic model for the dual agonistic/antagonistic action of CK-IV-55 on TG2 is presented, and the pathophysiological implications of basal activation of intestinal TG2 by small molecules are discussed.", "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:\nA double blind trial of terfenadine and placebo in hay fever using a substitution technique for non-responders . A double-blind study of terfenadine and placebo in 110 patients suffering from hay fever ( confirmed by skin tests ) was conducted . A novel technique was applied using an escape envelope containing a reference drug which could be taken under controlled conditions if , after 48 hours , the patient experienced no relief . Significantly more patients on placebo opened the envelope than patients taking the active drug . Terfenadine was demonstrated to be an effective drug in hay fever and produced no more drowsiness than placebo .", "role": "user" }, { "content": "{\"Intervention\": [\"placebo\", \"Terfenadine\", \"terfenadine\"], \"Outcome\": [\"relief\", \"opened the envelope\", \"effective drug\", \"drowsiness\"], \"Participant\": [\"hay fever\", \"110\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nDetermination of N2-hydroxymethyl-dG Adducts in Nasal Epithelium and Bone Marrow of Non-human Primates following 13CD2-Formaldehyde Inhalation Exposure\n\nPaper sections:\n\n<p>Formaldehyde is a ubiquitous chemical that is used in a large number of industrial activities and found in many consumer products. In addition to occupational and environmental exposures, formaldehyde is endogenously produced as part of the one carbon pool and is present in the blood at about 0.1 mM (1). IARC has classified formaldehyde as a carcinogen, causing squamous cell carcinoma in nasal tissue of rats, and nasopharyngeal cancer in humans. There is also limited evidence from epidemiological studies for an association with myeloid leukemia (1–3). The US Environmental Protection Agency has recently released its external review draft Toxicological Review of Formaldehyde-Inhalation Assessment, which is currently under expert review by the National Academy of Sciences. Detailed studies of formaldehyde derived DNA damage are needed to better understand the extent of endogenous and exogenous damage in non-human primates.</p><p>Initial investigations into the carcinogenicity of formaldehyde found dramatic increases in the incidence of squamous cell carcinomas following long-term exposure to rats at concentrations higher than 6 ppm (4–6). Additional studies in rodents and primates have investigated formaldehyde damage, finding non-linear increases in markers of toxicity and DNA damage (1;7). Studies in rats have provided extensive information regarding formaldehyde derived DNA damage; however, there are significant differences in the structure of nasal passages and disposition of inhaled chemicals between rodents and primates, including humans (8). These differences and oral/nasal breathing patterns make primates a more appropriate model of human exposure. Several models have been developed to simulate formaldehyde derived damage in rodents, primates and humans (1;9;10).</p><p>Formaldehyde is highly reactive and can covalently bind to both proteins and DNA, forming formaldehyde-DNA monoadducts, DNA-formaldehyde cross-links and DNA-protein cross-links (1;11). The endogenous presence of formaldehyde and the high concentrations normally found in cells result in the endogenous formation of identical DNA adducts, making quantitation of exogenous and endogenous damage problematic. The majority of previous research focused on the detection of DNA-protein cross-links, which primarily relied on physical separation and detection methodologies that either could not adequately differentiate between endogenous and exogenous formaldehyde damage, or could only detect exogenous damage. More recent studies by Lu et al, have utilized a combination of isotope labeled [13CD2]-formaldehyde exposures to rats and quantitation of DNA adducts including N2-hydroxymethyl-dG by mass spectrometry. This allowed unambiguous determinations of exogenous and endogenous formaldehyde derived DNA damage (11). Our laboratory has recently expanded upon these studies, conducting experiments measuring N2-hydroxymethyl-dG using a newly developed more sensitive nano-UPLC-MS/MS method to determine the molecular dosimetry of hydroxymethyl-dG adducts in rats (12). Here, we present the first data using this more sensitive and selective approach for the detection of exogenous and endogenous formaldehyde induced DNA damage in non-human primates.</p><p>Two groups (n = 4 animals per group) of cynomolgus macaques (Macaca fascicularis) were whole body exposed to either 1.9 or 6.1 ppm [13CD2]-formaldehyde for 2 consecutive days (6 hours per day). At the end of exposure on the second day, the primates were euthanized and necropsy performed within 3 hours. The nasal mucosa from maxilloturbinates and bone marrow were collected, flash frozen in liquid nitrogen and stored at −80°C until analysis. DNA was extracted, reduced with NaCNBH3 to convert N2-hydroxymethyl-dG adducts to more stable N2-methyl-dG adducts. Subsequently, 20 fmol of the internal standard (15N513C10-methyl-dG) was added, DNA digested with DNase I, alkaline phosphatase and phosphodiestersase, followed by the separation of N2-methyl-dG by HPLC and drying of fractions under vacuum. Both endogenous and exogenous N2-methyl-dG were detected and quantitated using a sensitive nano-UPLC-MS/MS method employing select reaction monitoring with a limit of detection of 20 amol on column (Figure S1). In bone marrow and nasal tissue, the presence of both endogenous (m/z 282.2 → 166.1) and exogenous (m/z 285.2 → 169.1) N2-hydroxymethyl-dG adducts, along with the internal standard (m/z 297.2 → 176.1) were monitored, as shown in figure 1.</p><p>The endogenous and exogenous N2-hydroxymethyl-dG levels found in both tissues are summarized in Table 1. In the nasal maxilloturbinate DNA, exogenous N2-hydroxymethyl-dG was present at 0.26 ± 0.04 and 0.41 ± 0.05 adducts/107 dG following the 1.9 and 6.1 ppm exposures, respectively. Endogenous N2-hydroxymethyl-dG adducts were present in the nasal DNA of all animals studied, with an average of 2.24 ± 0.50 adducts/107 dG.</p><p>In bone marrow, no exogenous adducts were detected, even though ~10-fold higher amounts of DNA were analyzed. Endogenous N2-hydroxymethyl-dG adducts were present at 17.5 ± 2.6 and 12.4 ± 3.6 adducts/107 dG in bone marrow DNA from the 1.9 and 6.1 ppm exposures, respectively. The lack of exogenous adducts with the corresponding presence of endogenous adducts is clearly shown in Figure 1. In contrast to the nasal tissue, much higher numbers of endogenous N2-hydroxymethyl-dG adducts were present in bone marrow. It is unclear why the numbers of endogenous adducts in primates are high, but preliminary evaluations of other tissues were also much higher than was previously found in rats.</p><p>In a recent study by Lu et al (12), N2-hydroxymethyl-dG exogenous and endogenous adducts were quantified in rats using the same methodology described in this paper following a single 6 hour exposure to labeled formaldehyde. The number of exogenous adducts quantified after a 1 day exposure to rats and a 2 day exposure to monkeys were similar following 1.9 ppm 13CD2O exposure, but were ~2.5 fold lower in primates exposed to 6.1 ppm. This decrease in exogenous adducts, compared to the rat, may be partially explained by the differences in nasal anatomy and breathing patterns between the two species (8). Rats, unlike humans and monkeys are obligate nose breathers, which may explain the higher amounts of exogenous adducts in rat nasal tissue. Additional tissue sites from the nasal and respiratory tract, as well as numerous sites distant to the point of contact were collected at necropsy and will be analyzed for a more comprehensive report on this study to better characterize the distribution of exogenous and endogenous adducts in non-human primates following formaldehyde inhalation exposure.</p><p>Our new nano-UPLC-MS/MS method permits one to calculate the maximum number of exogenous formaldehyde adducts that could have been missed in a sample of bone marrow. For example, in a 312 µg DNA sample, less than 1 exogenous N2-HO13CD2-dG could be present in a sample that had 13,900 identical endogenous formaldehyde adducts. This provides a unique perspective on the plausibility that inhaled formaldehyde gets to bone marrow and is causally associated with the induction of myeloid leukemia. How could that one exogenous adduct have a biological effect, but the other 13,900 do not? Such data demonstrate the utility of conducting stable isotope exposures when a chemical induces DNA adducts that are identical to endogenous adducts. It also strengthens the arguments supporting the need to consider the biology associated with high numbers of endogenous DNA adducts when extrapolating to risks associated with very low exposures to chemicals.</p><p>These data clearly show the formation of exogenous formaldehyde adducts in nasal DNA of primates and the lack of formation of exogenous DNA adducts in the bone marrow. Lower amounts of exogenous adducts were found in the nasal tissues of primates exposed to formaldehyde for 2 days, compared to similar studies conducted in rats exposed for one day. Furthermore, primates had much higher endogenous adducts. Primates will have a lower ratio of exogenous/endogenous adduct arising from inhalation exposures, suggesting that risks from inhaled formaldehyde exposures may also be lower. Additional studies are underway on the expanded list of tissues to better characterize the potential for exogenous DNA damage caused by inhalation exposure to formaldehyde in the respiratory tract and distant tissues.</p>", "role": "user" }, { "content": "The presence of endogenous and exogenous N2-hydroxymethyl-dG adducts in DNA from nasal mucosa and bone marrow of cynomolgus macaques exposed to 1.9 and 6.1 ppm of [13CD2]-formaldehyde for 6 hours a day for 2 consecutive days was investigated using a highly sensitive nano-UPLC-MS/MS method with a Limit of Detection of 20 amol. Both exogenous and endogenous adducts were readily detected and quantified in the nasal tissues of both exposure groups, with an exposure dependent increase in exogenous adducts observed. In contrast, only endogenous adducts were detectable in the bone marrow, even though ~10 times more DNA was analyzed.", "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: Lattice CNNs for Matching Based Chinese Question Answering\n\nShort text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly. In this paper, we propose a novel lattice based CNN model (LCNs) to utilize multi-granularity information inherent in the word lattice while maintaining strong ability to deal with the introduced noisy information for matching based question answering in Chinese. We conduct extensive experiments on both document based question answering and knowledge based question answering tasks, and experimental results show that the LCNs models can significantly outperform the state-of-the-art matching models and strong baselines by taking advantages of better ability to distill rich but discriminative information from the word lattice input.\n\nLattice CNNs\nOur Lattice CNNs framework is built upon the siamese architecture BIBREF5 , one of the most successful frameworks in text matching, which takes the word lattice format of a pair of sentences as input, and outputs the matching score.\n\nLattice based CNN Layer\nAs we mentioned in previous section, we can not directly apply standard CNNs to take word lattice as input, since there could be multiple feature vectors produced for a given word. Inspired by previous lattice LSTM models BIBREF10 , BIBREF11 , here we propose a lattice based CNN layers to allow standard CNNs to work over word lattice input. Specifically, we utilize pooling mechanisms to merge the feature vectors produced by multiple CNN kernels over different context compositions.\nFormally, the output feature vector of a lattice CNN layer with kernel size INLINEFORM0 at word INLINEFORM1 in a word lattice INLINEFORM2 can be formulated as Eq EQREF12 : DISPLAYFORM0 \nwhere INLINEFORM0 is the activation function, INLINEFORM1 is the input vector corresponding to word INLINEFORM2 in this layer, ( INLINEFORM3 means the concatenation of these vectors, and INLINEFORM4 are parameters with size INLINEFORM5 , and INLINEFORM6 , respectively. INLINEFORM7 is the input dim and INLINEFORM8 is the output dim. INLINEFORM9 is one of the following pooling functions: max-pooling, ave-pooling, or gated-pooling, which execute the element-wise maximum, element-wise average, and the gated operation, respectively. The gated operation can be formulated as: DISPLAYFORM0 \nwhere INLINEFORM0 are parameters, and INLINEFORM1 are gated weights normalized by a softmax function. Intuitively, the gates represent the importance of the n-gram contexts, and the weighted sum can control the transmission of noisy context words. We perform padding when necessary.\nFor example, in Figure FIGREF6 , when we consider “citizen” as the center word, and the kernel size is 3, there will be five words and four context compositions involved, as mentioned in the previous section, each marked in different colors. Then, 3 kernels scan on all compositions and produce four 3-dim feature vectors. The gated weights are computed based on those vectors via a dense layer, which can reflect the importance of each context compositions. The output vector of the center word is their weighted sum, where noisy contexts are expected to have lower weights to be smoothed. This pooling over different contexts allows LCNs to work over word lattice input.\nWord lattice can be seen as directed graphs and modeled by Directed Graph Convolutional networks (DGCs) BIBREF12 , which use poolings on neighboring vertexes that ignore the semantic structure of n-grams. But to some situations, their formulations can be very similar to ours (See Appendix for derivation). For example, if we set the kernel size in LCNs to 3, use linear activations and suppose the pooling mode is average in both LCNs and DGCs, at each word in each layer, the DGCs compute the average of the first order neighbors together with the center word, while the LCNs compute the average of the pre and post words separately and add them to the center word. Empirical results are exhibited in Experiments section.\nFinally, given a sentence that has been constructed into a word-lattice form, for each node in the lattice, an LCN layer will produce one feature vector similar to original CNNs, which makes it easier to stack multiple LCN layers to obtain more abstract feature representations.\n\nExperiments\nOur experiments are designed to answer: (1) whether multi-granularity information in word lattice helps in matching based QA tasks, (2) whether LCNs capture the multi-granularity information through lattice well, and (3) how to balance the noisy and informative words introduced by word lattice.\n\nDatasets\nWe conduct experiments on two Chinese question answering datasets from NLPCC-2016 evaluation task BIBREF13 .\nDBQA is a document based question answering dataset. There are 8.8k questions with 182k question-sentence pairs for training and 6k questions with 123k question-sentence pairs in the test set. In average, each question has 20.6 candidate sentences and 1.04 golden answers. The average length for questions is 15.9 characters, and each candidate sentence has averagely 38.4 characters. Both questions and sentences are natural language sentences, possibly sharing more similar word choices and expressions compared to the KBQA case. But the candidate sentences are extracted from web pages, and are often much longer than the questions, with many irrelevant clauses.\nKBRE is a knowledge based relation extraction dataset. We follow the same preprocess as BIBREF14 to clean the dataset and replace entity mentions in questions to a special token. There are 14.3k questions with 273k question-predicate pairs in the training set and 9.4k questions with 156k question-predicate pairs for testing. Each question contains only one golden predicate. Each question averagely has 18.1 candidate predicates and 8.1 characters in length, while a KB predicate is only 3.4 characters long on average. Note that a KB predicate is usually a concise phrase, with quite different word choices compared to the natural language questions, which poses different challenges to solve.\nThe vocabulary we use to construct word lattices contains 156k words, including 9.1k single character words. In average, each DBQA question contains 22.3 tokens (words or characters) in its lattice, each DBQA candidate sentence has 55.8 tokens, each KBQA question has 10.7 tokens and each KBQA predicate contains 5.1 tokens.\n\nImplementation Details\nThe word embeddings are trained on the Baidu Baike webpages with Google's word2vector, which are 300-dim and fine tuned during training. In DBQA, we also follow previous works BIBREF15 , BIBREF16 to concatenate additional 1d-indicators with word vectors which denote whether the words are concurrent in both questions and candidate sentences. In each CNN layer, there are 256, 512, and 256 kernels with width 1, 2, and 3, respectively. The size of the hidden layer for MLP is 1024. All activation are ReLU, the dropout rate is 0.5, with a batch size of 64. We optimize with adadelta BIBREF17 with learning rate INLINEFORM0 and decay factor INLINEFORM1 . We only tune the number of convolutional layers from [1, 2, 3] and fix other hyper-parameters. We sample at most 10 negative sentences per question in DBQA and 5 in KBRE. We implement our models in Keras with Tensorflow backend.\n\nBaselines\nOur first set of baselines uses original CNNs with character (CNN-char) or word inputs. For each sentence, two Chinese word segmenters are used to obtain three different word sequences: jieba (CNN-jieba), and Stanford Chinese word segmenter in CTB (CNN-CTB) and PKU (CNN-PKU) mode.\nOur second set of baselines combines different word segmentations. Specifically, we concatenate the sentence embeddings from different segment results, which gives four different word+word models: jieba+PKU, PKU+CTB, CTB+jieba, and PKU+CTB+jieba.\nInspired by previous works BIBREF2 , BIBREF3 , we also concatenate word and character embeddings at the input level. Specially, when the basic sequence is in word level, each word may be constructed by multiple characters through a pooling operation (Word+Char). Our pilot experiments show that average-pooling is the best for DBQA while max-pooling after a dense layer is the best for KBQA. When the basic sequence is in character level, we simply concatenate the character embedding with its corresponding word embedding (Char+Word), since each character belongs to one word only. Again, when the basic sequence is in character level, we can also concatenate the character embedding with a pooled representation of all words that contain this character in the word lattice (Char+Lattice), where we use max pooling as suggested by our pilot experiments.\nDGCs BIBREF12 , BIBREF18 are strong baselines that perform CNNs over directed graphs to produce high level representation for each vertex in the graph, which can be used to build a sentence representation via certain pooling operation. We therefore choose to compare with DGC-max (with maximum pooling), DGC-ave (with average pooling), and DGC-gated (with gated pooling), where the gate value is computed using the concatenation of the vertex vector and the center vertex vector through a dense layer. We also implement several state-of-the-art matching models using the open-source project MatchZoo BIBREF19 , where we tune hyper-parameters using grid search, e.g., whether using word or character inputs. Arc1, Arc2, CDSSM are traditional CNNs based matching models proposed by BIBREF20 , BIBREF21 . Arc1 and CDSSM compute the similarity via sentence representations and Arc2 uses the word pair similarities. MV-LSTM BIBREF22 computes the matching score by examining the interaction between the representations from two sentences obtained by a shared BiLSTM encoder. MatchPyramid(MP) BIBREF23 utilizes 2D convolutions and pooling strategies over word pair similarity matrices to compute the matching scores.\nWe also compare with the state-of-the-art models in DBQA BIBREF15 , BIBREF16 .\n\nResults\nHere, we mainly describe the main results on the DBQA dataset, while we find very similar trends on the KBRE dataset. Table TABREF26 summarizes the main results on the two datasets. We can see that the simple MatchZoo models perform the worst. Although Arc1 and CDSSM are also constructed in the siamese architecture with CNN layers, they do not employ multiple kernel sizes and residual connections, and fail to capture the relatedness in a multi-granularity fashion.\n BIBREF15 is similar to our word level models (CNN-jieba/PKU/CTB), but outperforms our models by around 3%, since it benefits from an extra interaction layer with fine tuned hyper-parameters. BIBREF16 further incorporates human designed features including POS-tag interaction and TF-IDF scores, achieving state-of-the-art performance in the literature of this DBQA dataset. However, both of them perform worse than our simple CNN-char model, which is a strong baseline because characters, that describe the text in a fine granularity, can relieve word mismatch problem to some extent. And our best LCNs model further outperforms BIBREF16 by .0134 in MRR.\nFor single granularity CNNs, CNN-char performs better than all word level models, because they heavily suffer from word mismatching given one fixed word segmentation result. And the models that utilize different word segmentations can relieve this problem and gain better performance, which can be further improved by the combination of words and characters. The DGCs and LCNs, being able to work on lattice input, outperform all previous models that have sequential inputs, indicating that the word lattice is a more promising form than a single word sequence, and should be better captured by taking the inherent graph structure into account. Although they take the same input, LCNs still perform better than the best DGCs by a margin, showing the advantages of the CNN kernels over multiple n-grams in the lattice structures and the gated pooling strategy.\nTo fairly compare with previous KBQA works, we combine our LCN-ave settings with the entity linking results of the state-of-the-art KBQA model BIBREF14 . The P@1 for question answering of single LCN-ave is 86.31%, which outperforms both the best single model (84.55%) and the best ensembled model (85.40%) in literature.\n\nCase Study\nFigure FIGREF37 shows a case study comparing models in different input levels. The word level model is relatively coarse in utilizing informations, and finds a sentence with the longest overlap (5 words, 12 characters). However, it does not realize that the question is about numbers of people, and the “DaoHang”(navigate) in question is a verb, but noun in the sentence. The character level model finds a long sentence which covers most of the characters in question, which shows the power of fine-granularity matching. But without the help of words, it is hard to distinguish the “Ren”(people) in “DuoShaoRen”(how many people) and “ChuangShiRen”(founder), so it loses the most important information. While in lattice, although overlaps are limited, “WangZhan”(website, “Wang” web, “Zhan” station) can match “WangZhi”(Internet addresses, “Wang” web, “Zhi” addresses) and also relate to “DaoHang”(navigate), from which it may infer that “WangZhan”(website) refers to “tao606 seller website navigation”(a website name). Moreover, “YongHu”(user) can match “Ren”(people). With cooperations between characters and words, it catches the key points of the question and eliminates the other two candidates, as a result, it finds the correct answer.\n\nConclusions\nIn this paper, we propose a novel neural network matching method (LCNs) for matching based question answering in Chinese. Rather than relying on a word sequence only, our model takes word lattice as input. By performing CNNs over multiple n-gram context to exploit multi-granularity information, LCNs can relieve the word mismatch challenges. Thorough experiments show that our model can better explore the word lattice via convolutional operations and rich context-aware pooling, thus outperforms the state-of-the-art models and competitive baselines by a large margin. Further analyses exhibit that lattice input takes advantages of word and character level information, and the vocabulary based lattice constructor outperforms the strategies that combine characters and different word segmentations together.\n\nFigure 1: A word lattice for the phrase “Chinese people have high quality of life.”\n\nQuestion: Which dataset(s) do they evaluate on?", "role": "user" }, { "content": "{\"answer\": [\"DBQA\", \"KBRE\"], \"evidence\": [\"Datasets\", \"We conduct experiments on two Chinese question answering datasets from NLPCC-2016 evaluation task BIBREF13 .\", \"DBQA is a document based question answering dataset. There are 8.8k questions with 182k question-sentence pairs for training and 6k questions with 123k question-sentence pairs in the test set. In average, each question has 20.6 candidate sentences and 1.04 golden answers. The average length for questions is 15.9 characters, and each candidate sentence has averagely 38.4 characters. Both questions and sentences are natural language sentences, possibly sharing more similar word choices and expressions compared to the KBQA case. But the candidate sentences are extracted from web pages, and are often much longer than the questions, with many irrelevant clauses.\", \"KBRE is a knowledge based relation extraction dataset. We follow the same preprocess as BIBREF14 to clean the dataset and replace entity mentions in questions to a special token. There are 14.3k questions with 273k question-predicate pairs in the training set and 9.4k questions with 156k question-predicate pairs for testing. Each question contains only one golden predicate. Each question averagely has 18.1 candidate predicates and 8.1 characters in length, while a KB predicate is only 3.4 characters long on average. Note that a KB predicate is usually a concise phrase, with quite different word choices compared to the natural language questions, which poses different challenges to solve.\"]}", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: A system for efficient inference on mobile devices.\n\nKeyphrases: mobile vision video\n\nDataset descriptions:\nReplay-Mobile: The Replay-Mobile Database for face spoofing consists of 1190 video clips of photo and video attack attempts to 40 clients, under different lighting conditions. These videos were recorded with current devices from the market -- an iPad Mini2 (running iOS) and a LG-G4 smartphone (running Android).\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).\nDPED: A large-scale dataset that consists of real photos captured from three different phones and one high-end reflex camera.\nVeRi-Wild: Veri-Wild is the largest vehicle re-identification dataset (as of CVPR 2019). The dataset is captured from a large CCTV surveillance system consisting of 174 cameras across one month (30× 24h) under unconstrained scenarios.\n\nOptions: A: Replay-Mobile B: UCF101 C: DPED D: VeRi-Wild", "role": "user" }, { "content": "UCF101", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Public health actions, such as social distancing, can make people feel isolated and lonely and can increase stress and anxiety. However, these actions are necessary to reduce the spread of COVID-19. \n\nAbstract:\nBACKGROUND: The Australian and New Zealand governments both initiated strict social distancing measures in response to the COVID-19 pandemic in late March.\nIt remains difficult to quantify the impact this had in reducing the spread of the virus.\nMETHODS: Bayesian structural time series model provide a model to quantify the scenario in which these government-level interventions were not placed.\nOur models predict these strict social distancing measures caused a 79% and 61% reduction in the daily cases of COVID-19 across Australia and New Zealand respectively.\nCONCLUSION: This provides both evidence and impetus for governments considering similar measures in response to COVID-19 and other pandemics.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Our models predict these strict social distancing measures caused a 79% and 61% reduction in the daily cases of COVID-19 across Australia and New Zealand respectively.\"]}", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nCombined toxicity of polycyclic aromatic hydrocarbons and heavy metals to biochemical and antioxidant responses of free and immobilized Selenastrum capricornutum. The aquatic environment often contains different groups of contaminants, but their combined toxicity on microalgae has seldom been reported. The present study compared the toxic effects of combined mixed polycyclic aromatic hydrocarbons (PAHs) and heavy metals on growth and antioxidant responses of free and immobilized microalga, Selenastrum capricornutum. Five PAHs-phenanthrene, fluorene, fluoranthene, pyrene, and benzo[a]pyrene-and four heavy metals at different concentrations-0.05 to 0.1 µg Cd(2+) ml(-1) , 0.05 to 1 µg Cu(2+) ml(-1) , 0.05 to 1 µg Zn(2+) ml(-1) , and 0.5 to 2.5 µg Ni(2+) ml(-1) -were examined. Results showed that the chlorophyll a content of free and immobilized S. capricornutum was not affected by PAHs but was significantly inhibited by heavy metals. Conversely, the antioxidant parameters, including the content of reduced glutathione (GSH) and the activities of superoxide dismutase and peroxidase, were significantly induced by both PAHs and metals. For the combined toxic effects of PAHs and heavy metals, cell growth and antioxidant responses varied with exposure time and contaminants and differed between free and immobilized cells. The effects of cocontaminants on the GSH content in free cells were mainly synergistic but changed to antagonistic in immobilized cells. The toxic effects of cocontamination on free cells were also more obvious than those on immobilized cells. These findings suggest that immobilization offers some protection to microalgal cells against toxic contaminants causing differences in the interaction and responses to combined toxicants between free and immobilized cells. Immobilized cells might be more suitable for treating wastewater containing toxic contaminants than free cells.", "role": "user" }, { "content": "{\"Chemical\": [\"glutathione\", \"GSH\", \"Cu(2+)\", \"Cd(2+)\", \"chlorophyll a\", \"Zn(2+)\", \"phenanthrene\", \"fluorene\", \"polycyclic aromatic hydrocarbons\", \"Ni(2+)\", \"PAHs\", \"superoxide\", \"benzo[a]pyrene\", \"pyrene\", \"fluoranthene\"]}", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nIn this paper, we present a distributional word embedding model trained on one of the largest available Russian corpora: Araneum Russicum Maximum (over 10 billion words crawled from the web). We compare this model to the model trained on the Russian National Corpus (RNC). The two corpora are much different in their size and compilation procedures. We test these differences by evaluating the trained models against the Russian part of the Multilingual SimLex999 semantic similarity dataset. We detect and describe numerous issues in this dataset and publish a new corrected version. Aside from the already known fact that the RNC is generally a better training corpus than web corpora, we enumerate and explain fine differences in how the models process semantic similarity task, what parts of the evaluation set are difficult for particular models and why. Additionally, the learning curves for both models are described, showing that the RNC is generally more robust as training material for this task.\n\nCited Abstract(s):\n[1]: Distributed vector representations for natural language vocabulary get a lot of attention in contemporary computational linguistics. This paper summarizes the experience of applying neural network language models to the task of calculating semantic similarity for Russian. The experiments were performed in the course of Russian Semantic Similarity Evaluation track, where our models took from the 2nd to the 5th position, depending on the task. We introduce the tools and corpora used, comment on the nature of the shared task and describe the achieved results. It was found out that Continuous Skip-gram and Continuous Bag-of-words models, previously successfully applied to English material, can be used for semantic modeling of Russian as well. Moreover, we show that texts in Russian National Corpus (RNC) provide an excellent training material for such models, outperforming other, much larger corpora. It is especially true for semantic relatedness tasks (although stacking models trained on larger corpora on top of RNC models improves performance even more). High-quality semantic vectors learned in such a way can be used in a variety of linguistic tasks and promise an exciting field for further study.\n\n[2]: In this paper we compare the Russian National Corpus to a larger Russian web corpus composed in 2014; the assumption behind our work is that the National corpus, being limited by the texts it contains and their proportions, presents lexical contexts (and thus meanings) which are different from those found ‘in the wild’ or in a language in use.", "role": "user" }, { "content": "The issue of the influence of the training corpora on the performance of word embedding models for Russian was raised in [1] . Among other, they compared the models trained on the RNC and a randomly sampled corpus of Russian web pages, about an order larger than the RNC. They found out that albeit much smaller, the RNC consistently outperformed the web corpus in the performance of the models trained on it. In this research, we move this even further by using the Araneum Maximum web corpus, which is almost two orders larger than the RNC. Additionally, we carefully analyze the errors of the models and their learning curves. We hypothesize that the types of errors can be different, as it is known that the models trained on corpora of different types can reflect different semantic landscapes' (see, among others, [1]2 ).", "role": "assistant" } ]

[ { "content": "Given this abstract, identify all unique entities of these types: [\"AnatomicalEntity\"].\n\nOnly output the JSON object, no other text.\n\nAbstract:\nImpacts of water management options on flows in the Condamine River in Southern Queensland.\nThis paper examines the implications for river flows of a number of water practices and potential management options in the alluvial plains of the Upper Condamine River. It is an intensively cultivated area where irrigation is limited by the availability of water resources. The practice of capturing overland flows was investigated by the development of a model that simulates the performance of clusters of offstream storages up to sub-catchment scale. Management options examined included improvement to on-farm water use efficiency, the suppression of evaporation from open water storages, increasing the depth of those storages, decreasing their number, and improved tailwater return from irrigated land. Impacts of management options were analysed using a catchment scale water allocation model.", "role": "user" }, { "content": "{\"AnatomicalEntity\": []}", "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\n20-Epi analogues of 1, 25-dihydroxyvitamin D3 are highly potent inducers of DRIP coactivator complex binding to the vitamin D3 receptor. 1, 25-Dihydroxyvitamin D3 (1, 25 (OH) 2D3) plays a major role in the stimulation of bone growth, mineralization, and intestinal calcium and phosphate absorption; it also acts as a general inhibitor of cellular proliferation. Several new, clinically relevant compounds dissociate antiproliferative and calcemic activities of 1, 25 (OH) 2D3, but the molecular basis for this has not been clearly elucidated. Here, we tested whether the potency of one class of compounds, 20-epi analogues, to induce myeloid cell differentiation, is because of direct molecular effects on vitamin D receptor (VDR). We report that two 20-epi analogues, MC1627 and MC1288, induced differentiation and transcription of p21 (Waf1, Cip1), a key VDR target gene involved in growth inhibition, at a concentration 100-fold lower than that of 1, 25 (OH) 2D3. We compared this sensitivity to analogue effects on VDR interacting proteins: RXR, GRIP-1, and DRIP205, a subunit of the DRIP coactivator complex. Compared with the interaction of VDR with RXR or GRIP-1, the differentiation dose-response most closely correlated to the ligand-dependent recruitment of the DRIP coactivator complex to VDR and to the ability of the receptor to activate transcription in a cell-free system. These results provide compelling links between the efficiency of the 20-epi analogue in inducing VDR / DRIP interactions, transactivation in vitro, and its enhanced ability to induce cellular differentiation.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [], \"DNA\": [\"Cip1\", \"VDR target gene\", \"Waf1\", \"p21\"], \"Protein\": [\"vitamin D receptor\", \"vitamin D3 receptor\", \"DRIP coactivator complex\", \"GRIP - 1\", \"RXR\", \"DRIP205\", \"VDR\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nsuperior vena cava ( svc ) syndrome is associated with anvanced malignancy and has a poor prognosis1 ) . however\n, a symptomatic svc obstruction can also be caused by benign conditions that do not affect the life expectancy of the patient .\nreported cases of svc syndrome from benign processes include the following : infectious diseases such as tuberculosis , histoplasmosis , and a pyogenic infection ; fibrosing processes either idiopathic or following radiation therapy ; endovascular devices such as transvenous cardiac devices or indwelling catheters ; vascular anomalies , aneurysms , vasculitis as well as a number of other rarer etiologies2 ) . here\nwe report a case of svc syndrome that was caused by soft tissue encircling the svc with thrombus complications along with the accompanying ct findings using a 3-dimensional volume - rendering technique .\na 39-year - old man with no prior medical history presented with a four - week history of facial plethora , headache and dilated veins of the neck with a dark purple color change on the anterior chest wall .\ninterestingly , 16-slice multi - detector computed tomography ( mdct ) of the chest and a 3-dimensional volume - rendering image revealed a severe narrowing of the svc which occurred as a result of tiny encircling soft tissue and collateral vessels ( figure 1 ) .\nan svc angiogram also revealed significant luminal narrowing of the svc ( figure 2 ) .\none day after the svc angiogram , the patient complained of severe headache and facial edema .\na repeat svc angiogram revealed a thrombus at the right brachiocephalic vein and a total occlusion of the svc ( figure 3a ) .\nthe follow - up svc angiogram revealed a decrease in the size of the thrombus and distal venous flow to right atrium ( figure 3b ) .\nthree days later , another follow - up svc angiogram revealed significant luminal narrowing of the svc that was identical to the initial findings ( figure 4a ) .\na 14 60 mm cook zilver stent was deployed in the svc ( figure 4b ) , and the postprocedural ct revealed a wide patency ( figure 5 ) .\nthe patient was discharged after the facial plethora , headache and color change on the anterior chest wall had been relieved .\nsvc syndrome was first described by hunter in 17573 ) . as reported in recent reports ,\n73~93% of all cases of svc syndrome have resulted from either a primary or metastatic malignancy with the remainder of the cases due to benign disease4 - 6 ) .\nmany benign causes have been described including fibrosing mediastinitis and iatrogenic etiologies such as sclerosis and obstructions that are caused by the use of indwelling central venous catheters2 ) .\nhowever , the increase in the implementation of indwelling central venous catheters and permanent pacemakers has resulted in more patients with a superior vena cava obstruction with a benign etiology4 ) . in our case ,\nthe ct and 3-dimensional volume - rendering image showed a small amount of soft tissue encircling the svc .\nit even accurately revealed the extent , level , length of stenosis , the presence of collateral vessels and could confidently differentiate other infiltrative lesions of the mediastinum , such as a lung cancer , a metastatic carcinoma , a lymphoma , and a mediastinal sarcoma .\nalthough the focal type of fibrosing mediastinitis was strongly suspected , there was no calcified mass , which is a typical finding .\ntherefore , fibrosing mediastinitis could not be confidently differentiated from the other lesions and a biopsy was required . however\n, a histological examination could not be carried out because the patient refused surgical sampling and there was a significant risk of hemorrhage during the biopsy .\nin one unusual case report of localized fibrosing mediastinitis , ct and magnetic resonance ( mr ) images of the chest showed an intraluminal mass in the svc without calcification7 ) .\nthese reported images were similar to that seen in our case except for the size of the mass .\nfibrosing mediastinitis is a rare benign disorder caused by the proliferation of acelluar collagen and fibrous tissue within the mediastinum7 ) the svc is most commonly involved , with the fibrosing mediastinitis causing svc syndrome7 ) .\nthese explanations include an immune reaction , chronic inflammation , drugs , familial disorder , malignancy and radiation7 ) .\nthe focal type usually manifests on ct or mr images as a localized , calcified mass in the paratracheal or subcarinal lesions of the mediastinum , or in the pulmonary hila8 ) .\nthe diffuse type manifests on ct or mr images as a diffusely infiltrating , often noncalcified mass , that affects multiple mediastinal compartments8 ) .\nit was remarkable that the thrombosis developed abruptly and a total occlusion of the svc occurred within 1 day after the diagnostic svc angiogram had been performed .\nafter thrombolytic therapy for 3 days , the lesion recovered in a similar way to the initial lesion and a stent was deployed .\nthe treatment for svc syndrome must be tailored to the underlying etiology and work quickly enough to relieve its severity or prevent life - threatening conditions .\nthe treatment of a svc obstruction due to a malignancy includes therapy with diuretics , steroids , and head elevation followed by chemotherapy or radiation therapy , and a subsequent endovascular procedure with angioplasty and stent placement for palliative purposes9 ) .\ntherapy for a svc obstruction due to benign causes should still be aimed at the underlying etiology .\nhowever , the relief of symptoms can be accomplished by relieving the stenosis if medical therapy with anticoagulation agents alone does not sufficiently alleviative the symptoms or there is a stricture or stenosis of the svc .\nhistorically , this has been accomplished by surgery . however , surgery may not be tolerated by patients with unstable conditions and often fails because of a thrombosis of the surgically created graft10 ) .\nit was recently reported that mid - term patency is acceptable in patients undergoing endovascular stent placement in cases of benign disease , and may be a feasible therapeutic option11 ) .", "role": "user" }, { "content": "superior vena cava syndrome can occur from benign conditions that might not alter life expectancy . here \n we present a case of a superior vena cava ( svc ) obstruction caused by soft tissue encircling the svc , which was strongly suspected of being an unusual focal type of fibrosing mediastinitis . \n a 39-year - old man with no prior medical history presented with a four - week history of facial plethora , headache and dilated veins of the neck with a dark purple color change on the anterior chest wall . \n radiology examinations , including venography , and computed tomography with a 3-dimensional volume - rendering image of the chest , had revealed severe narrowing of the svc due to tiny encircling soft tissue and collateral vessels . a total occlusion of the svc occurred as a result of a thrombus that developed within 1 day after the diagnostic svc angiogram . \n the patient underwent stent deployment three days after the administration of thrombolytic therapy .", "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\nEarly on, geriatricians in Israel viewed with increasing alarm the spread of coronavirus disease 2019 (COVID-19). It was clear that this viral disease exhibited a clear predilection for and danger to older persons. Informal contacts began with senior officials from the country's Ministry of Health, the Israel Medical Association, and the country's largest health fund; this was done to plan an approach to the possible coming storm. A group was formed, comprising three senior geriatricians, a former dean, a palliative care specialist, and a lawyer/ethicist. The members made every effort to ensure that their recommendations would be practical while at the same time taking into account the tenets of medical ethics. The committee's main task was to think through a workable approach because intensive care unit/ventilator resources may be far outstripped by those requiring such care. Recommendations included the approach to older persons both in the community and in long-term care institutions, a triage instrument, and palliative care. Patient autonomy was emphasized, with a strong recommendation for people of all ages to update their advance directives or, if they did not have any, to quickly draw them up. Considering the value of distributive justice, with respect to triage, a \"soft utilitarian\" approach was advocated with the main criteria being function and comorbidity. Although chronological age was rejected as a sole criterion, in the case of an overwhelming crisis, \"biological age\" would enter into the triage considerations, but only in the case of distinguishing between people with equal non-age-related deficits. The guideline emphasized that no matter what, in the spirit of beneficence, anyone who fell ill must receive active palliative care throughout the course of a COVD-19 infection but especially at the end of life. Furthermore, in the spirit of nonmaleficence, the frail, very old, and severely demented would be actively protected from dying on ventilation. J Am Geriatr Soc 68:1370-1375, 2020.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\ndental calculus is considered to be a mineralized bacterial plaque , which acts as a secondary etiologic factor in periodontitis , although extremely important in the maintenance and aggravation of the disease.1 due to keeping the plaque in close contact with the gingival tissue , dental calculus creates areas unfavorable to removal by brushing.1,2 professional removal of calculus , plaque , and factors that favor their accumulation is usually performed by scaling and root planning ( srp).3 srp are often time - consuming treatment procedures , whose mechanics can become tire some for the operator.1 a number of instruments in different shapes and angles have been designed to perform satisfactorily the srp procedure.4 gracey curettes are widely used for removal of subgingival calculus and for performing root planning with the removal of contaminated cementum.5,6 curettes can be made of carbon steel ( cs ) , stainless steel ( ss ) and tungsten carbide . among these types of curettes ,\nthose of cs stand outin terms of constant usage for maintaining their cutting ability for a longer time than the other types.4,6,7 tungsten carbide curettes have the disadvantage of being costly and difficult of sharpening , reasons that led these instruments to be no longer marketed.7 sharp curettes are found to be more efficient than blunt one sin obtaining adequate root surface and lesser formation of smear layer.6 sterilization of instruments is a routine in the dental offices , and the most widespread means of sterilization are : oven ( dry heat ) and autoclave ( moist heat ) . in ovens , temperatures ranging from 160c to 170c , for\nat least 2 and 1 h , respectively , must be set in the oven . in this method\n, the heat penetrates unevenly in the instrument and requires greater exposure and high temperatures.8 in the autoclave , temperatures ranging between 121c and 134c are required for 15 - 30 min to achieve the sterilization.3,9 this method is faster and more effective but has the disadvantage of causing corrosion mainly in cs instruments.10 the method for autoclave sterilization is more sensitive , especially when the drying process is not properly completed and the sealing of the instruments is not done with suitable paper .\nsterilization cycles cause undesirable changes in the physical properties of the instruments , such as corrosion , temper shifts and loss of cutting.11,12 these changes cause great inconvenience , either for the time taken for a new sharpening or even for the loss of the instrument.13 - 15 thus , this study evaluated by scanning electron microscopy ( sem ) , the effect of repeated oven and autoclave sterilization cycles on the cutting edge of cs and ss periodontal gracey curettes after srp .\nthis study was approved by the research ethics committee of unitau under protocol # 120 - 03 .\na total of 77 gracey curettes were used in this study . of these , 35 were ss ( trinity ind & com ltda , so paulo , brazil ) and 42 were cs curettes ( g hartzell & son co. , concord , california , usa ) .\nautoclaving was performed at a temperature of 130c for 15 min , followed by drying at 110c for 30 min .\nequip odontolgicos , so paulo , brazil ) was set up and the instruments were placed inside after temperature had reached 170c . then after the temperature was stabilized again , a 60 min countdown began .\nthe sterilization efficacy for both treatments was checked by placing an envelope containing spores of bacillus subtilis and bacillus stearothermophylus in into the oven ( olidef , ind .\nequip odontolgicos , so paulo , brazil ) and autoclave ( dabi atlantis , atlante ind medico dental , so paulo , brazil ) , respectively .\nafter the sterilization cycle , the strip was removed from the equipment and placed in culture medium ( tryptic broth , difco laboratories , detroit , michigan , usa ) .\nafter 24 h , it was possible to verify the efficiency of the sterilization process based on the turbidity of the medium .\nthe oven temperature was monitored continuously using a mercury thermometer , in order to keep it constant .\ncurettes according to treatment types and sterilization . the corrosion inhibitor 2% sodium nitrite ( phloracea , farm manip .\nltda , cuiab , mato grosso , brazil ) was applied to cs curettes prior to autoclaving .\nthe cs curettes were immersed for 2 min in the inhibitor and subsequently sterilized in an autoclave .\nss5 , cs5 and cs6 in three human premolars extracted for orthodontic purposes , which were originated from the bank of teeth of the discipline of endodontics , university of taubate .\n50 short , strong traction movements were performed parallel to the tooth axis in a given area . after this procedure ,\ninitially , curettes were assessed after the use and before sterilization by means of a sem ( leo model 1450 vp , leo - zeiss , england ) . a disc of carborundum was used to separate the blades from the grips of the ss curettes to be observed by sem .\nphotomicrographs of the blades with 60 and 100 magnification and 20 kv potency were taken .\nthe method of analysis followed the methodology proposed by stach et al.16 previously calibrated examiners compared the micrograph of each treatment performed in the curettes with those obtained for the control group and provided scores according to the following scale : ( 1 ) no alteration ; ( 2 ) minor and well - marked alteration ; ( 3 ) moderate to major alteration .\nafter analysis , the median of these indices was determined , and the results were analyzed .\nvisible changes in the edges of the curettes were observed by 10 examiners and classified according to the scale as shown in table 2 .\naverage scores obtained by the 10 calibrated examiners after analysis of the curettes subjected to different treatments . scale for analysis : ( 1 ) no alteration ; ( 2 ) minor alteration ; ( 3 ) moderate to major alteration .\nfigure 1a - k illustrates the conditions of the curettes after the different treatments by the magnification of 100 .\n( a ) carbon steel ( cs ) curette subjected to autoclave sterilization without the use of a corrosion inhibitor ( 100 ) , ( b ) cs curette previously subjected to autoclave sterilization with a corrosion inhibitor ( 100 ) , ( c ) stainless steel ( ss ) curette with early formation of oxides after autoclave sterilization , scaling and root planning ( srp ) ( 100 ) , ( d ) cs curette micrographed ( 100 ) control , ( e ) cs curette micrographed after 10 oven sterilization cycles ( 100 ) , it is noted little or no change in the edges , ( f ) ss curette micrographed ( 100 ) ( control ) , ( g ) ss curette micrographed ( 100 ) after 10 oven sterilization cycles , it is noted discrete presence of oxidation and bending of the tip of the curette with loss of structure , ( h ) ss curette micrographed ( 100 ) after 10 autoclave sterilization cycles , it is noted little or no change in the edges , ( i ) ss curettes micrographed ( 100 ) after 10 oven sterilization cycles , srp , darkening and oxidation of the edges can be noted , ( j ) cs curettes micrographed ( 100 ) after 10 oven sterilization cycles , srp , discrete presence of oxidation products is noted on the edges , ( k ) cs curettes micrographed ( 100 ) after 10 autoclave sterilization cycles ( with previous use of a corrosion inhibitor ) , srp , it is noted the presence of staining and bending of the edges with loss of structure .\nsterilization of instruments is a routine in the dental office , and repeated sterilization cycles can lead to undesirable changes in the physical properties of the instruments , such as corrosion , temper shifts and loss of structure.17 autoclave sterilization is used in most materials , although it is found to cause changes in the physical properties of cs instruments.11 oven sterilization is preferable to maintain the cutting edge of instruments and being microbiologically effective , but it requires high temperatures and long exposure periods.8 there are different types of packaging for sterilization of instruments in oven and autoclave .\nthe corrosion of instruments increases considerably when cs samples are autoclaved in different business envelopes , with an increase in the release of acid radicals of the package .\nsasse15 verified that 100% light cotton fabric was the package that caused the lowest corrosion rates .\nthe present study used the same type of material for the packaging of curettes for sterilization .\nas tal et al.6 reported that the cutting edge of the periodontal instrument was described as a well - defined , sharp edge , with a continuous line formed by two adjacent surfaces .\nthis study found that cs curettes are more resistant to srp procedure than are ss curettes .\nin contrast , cs instruments stand superior with regard to the hardness of the material and maintenance of cutting edge for a longer time . in the present study ,\nsome authors have pointed out that sterilization of cs instruments using saturated vapor causes corrosion due to moisture and heat , that is why an inhibitor of corrosion was used in this study , prior to autoclaving.4,18 in this study , the results showed that the cs curettes , subjected to autoclave sterilization , suffered severe degradation of their cutting edges and oxidation .\nthis might have occurred because cs materials , unlike ss materials , do not have elements like nickel and chromium in their composition , which provide protection against corrosion . however , when an anticorrosive agent was used prior to sterilization , there was discrete oxidation and staining.10 bertolotti and hurst19 studied the effects of corrosion inhibitors ( sodium nitrite , orthophosphate nitrite , and sodium perborate ) applied to drills by dipping for 2 min .\nthe authors concluded that 2% sodium nitrite was the most effective inhibitor against corrosion . according to these authors\n, corrosion is a destructive attack of the metal by an electrochemical reaction with the environment , where iron steel is converted into ferrous oxide ( fe + h2o - fe ( oh)2 + h2 ) in the presence of oxygen and water . the ferrous hydroxide is converted to ferric hydroxide ( 4fe ( oh)2 + o22h2o 4 fe ( oh)3 ) , after drying , the ferric hydroxide is converted to ferric oxide ( 2fe ( oh)3 fe2o3 + h2o ) , which leads to oxidation on the instrument surface . in the present study ,\nthe instruments were immersed for 2 min in a solution of 2% sodium nitrite ; this solution in small amounts is non - toxic and does not interfere with the sterilization process .\nthe ss curettes had their cutting edges deformed before srp , which is inherent to an inadequate manufacturing process .\nbased on the methodology and the results , it was possible to conclude that : \n the edges of the ss curettes suffered little or no alteration after repeated sterilization cycles .\nhowever , after srp , we observed the formation of dark regions ( staining ) and early formation of oxidesss instruments were found to have their edges deformed before srp , which seems to be inherent to the manufacturing processwhen a corrosion inhibitor ( 2% sodium nitrite ) was applied to cs curettes prior to autoclaving , there was a discrete alteration or corrosion compared to autoclaving without using the inhibitorcs instruments subjected to oven sterilization cycles , srp was the group with the lowest alteration of the cutting edges . \n \nthe edges of the ss curettes suffered little or no alteration after repeated sterilization cycles .\nhowever , after srp , we observed the formation of dark regions ( staining ) and early formation of oxides ss instruments were found to have their edges deformed before srp , which seems to be inherent to the manufacturing process when a corrosion inhibitor ( 2% sodium nitrite ) was applied to cs curettes prior to autoclaving , there was a discrete alteration or corrosion compared to autoclaving without using the inhibitor cs instruments subjected to oven sterilization cycles , srp was the group with the lowest alteration of the cutting edges .", "role": "user" }, { "content": "background : repeated sterilizations cycles cause undesirable alterations in the material properties of the instruments , such as corrosion , alterations in the hardness of the metal and the loss of the cutting sharpness of the instrument . \n this research examined the effect of repeated dry heat sterilization and autoclaves cycles on carbon steel ( cs ) and stainless steel ( ss ) curettes during the scaling and root planning.materials and methods : a total of 77 gracey curettes were used in this study . \n of these , 35 were ss and 42 were cs curettes submitted in different process : dry heat , autoclave , inhibition of corrosion and autoclave , scaling , root planning and dry heat , scaling , root planning , inhibition of corrosion and autoclave . \n the inhibition of corrosion used on the carbon curettes ( prior to sterilization in the autoclave ) was sodium nitrite at 2% . \n the curettes received 10 consecutive cycles of sterilization and after that the cutting edges were examined in the electronic microscope , at 60 and 100 magnification times.results:the images were evaluated by three independent examiners , who compared the photographs of each group with the control group.conclusion:the surface corrosion products and a deterioration of the edges were observed and the results showed that the ss curettes suffered little alteration with sterilization , scaling , root planning whereas the cs curettes were visibly affected by sterilization in the autoclave , but when the inhibition of corrosion was used prior to the sterilization , the oxidation was considerably reduced .", "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:\nEffectiveness of an antihistamine-decongestant combination for young children with the common cold: a randomized, controlled clinical trial.\nAbstract 1:\nWe tested the hypothesis that antihistamine-decongestant combinations cause no clinical ly significant relief of the symptoms of upper respiratory tract infections in young children by r and omly assigning 96 children to one of three treatment groups : antihistamine-decongestant , placebo , and no treatment . There were no differences among the three study groups in the proportion of children considered \" better \" overall by the parent 48 hours after the initial assessment ( drug , 67 % ; placebo , 71 % ; no treatment , 57 % ; p = 0.53 ) . There were no differences among groups in individual or composite symptom score changes . Two thirds of parents whose children were eligible for the drug trial believed that their child needed medicine for cold symptoms . In the proportion of parents believing that their child needed medicine , there was no difference between those who consented to participate and those who refused . Parents who wanted medicine at the initial visit reported more improvement at follow-up , regardless of whether the child received drug , placebo , or no treatment . We conclude that there is no clinical ly significant improvement in symptoms of upper respiratory tract infection , including no significant placebo effect , in young children for whom an antihistamine-decongestant is prescribed\n\n\nTitle 2:\nEfficacy of cough suppressants in children.\nAbstract 2:\nTo test the hypothesis that codeine and dextromethorphan are effective in alleviating the symptoms of acute cough , we conducted a r and omized , controlled trial . Eligible patients were children 18 months to 12 years of age , seen in private pediatric practice s , with significant night cough of less than 14 days ' duration . Study patients were r and omly selected to receive codeine , dextromethorphan , or placebo at bedtime for 3 consecutive nights . Outcomes were assessed by the use of a parent question naire rating the severity of symptoms at the initiation of therapy , and after each night of the study . Every patient had a cough score ( range 0 to 4 ) and composite symptom score ( range 0 to 9 ) computed for each day of the study . One hundred forty-one doses of study medication were evaluated in 49 patients , including 13 children receiving placebo , 19 dextromethorphan , and 17 codeine . Mean cough and composite symptom scores decreased in each of the three treatment groups on each day of the study ; there were no significant differences . Regression analysis , with reduction in cough score as the outcome of interest , showed that neither dextromethorphan nor codeine was significantly more effective than placebo ( p = 0.41 and 0.70 , respectively ) . Reduction in cough score was positively correlated with the severity of cough at the start of treatment ( p = 0.007 ) . Our data suggest that , in the doses used , neither codeine nor dextromethorphan is superior to placebo in treating night cough in children\n\n\nTitle 3:\nTape recorder for evaluation of coughs in children.\nAbstract 3:\nOTHER investigators,1 - 6utilizing various techniques , have attempted to determine objective ly the response of cough to antitussive medication . Volunteer adult patients were used almost exclusively in those studies . The techniques employed have consisted of induction of cough by artificial means , such as successive inhalations of an irritant aerosol , and of assay of antitussive activity of cough medications based on reduction in number of coughs provoked by the irritant . The irritant usually was citric acid or acetylcholine . While the data obtained gave a valid indication of a cough-suppressing effect , experimental production of cough by chemical or mechanical irritants is subject to certain limitations and criticisms . First , the healthy volunteer after repeated exposure develops a tolerance to the irritant , especially when the latter is citric acid . Second , the frequency and intensity of artificially induced cough vary with the concentration of the irritant and the interval between challenges . Third , the artificially induced\n\n\nTitle 4:\nIs an antihistamine-decongestant combination effective in temporarily relieving symptoms of the common cold in preschool children?\nAbstract 4:\nOBJECTIVE To determine whether an antihistamine-decongestant combination ( ADC ) is superior to placebo in temporarily relieving symptoms of upper respiratory tract infection ( URI ) in preschool children . DESIGN R and omized , double-blind , placebo-controlled trial . SETTING Four pediatric offices in the Seattle , Wash , area . PARTICIPANTS Children 6 months through 5 years of age with a URI of less than 7 days ' duration . METHODS Children were r and omly assigned to receive an ADC ( brompheniramine maleate-phenylpropanolamine hydrochloride ) or placebo as needed for URI symptoms . Two hours after each dose of study medication , changes in the child 's runny nose , nasal congestion , cough , and sleep status were assessed by means of a st and ardized question naire . RESULTS A total of 175 responses were recorded for 59 patients . There were no statistically significant differences in symptom improvement between the ADC and the placebo group ( runny nose , p = 0.48 ; nasal congestion , p = 0.94 ; cough , p = 0.66 ) . However , the proportion of children asleep 2 hours after receiving the ADC was significantly higher than the proportion receiving placebo ( 46.6 % vs 26.5 % ; p = 0.01 ) . Results were unchanged after control for the correlated nature of repeated responses , age , symptom duration , use of acetaminophen , time that the medication was given , and parental desire for medication . CONCLUSIONS The ADC was equivalent to placebo in providing temporary relief of URI symptoms in preschool children . However , the ADC did have significantly greater sedative effects than did placebo", "role": "user" }, { "content": "Antitussives , antihistamine-decongestant combinations , other fixed drug combinations , and antihistamines were no more effective than placebo in relieving symptoms of acute cough .\nMost drugs appeared to be well tolerated with a low incidence of mostly minor adverse effects .\nCONCLUSION OTC cough medicines do not appear more effective than placebo in relieving symptoms of acute cough .", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\ntwo processes affect the achievement of a bond between the acrylic teeth and denture base resin : ( i ) the polymerizing denture base resin must come into physical contact with the denture tooth resin , and ( ii ) the polymer network of denture base resin must react with the acrylic tooth polymer to form interwoven polymer network .\nthe most common type of denture failure occurs between an acrylic resin tooth and acrylic resin denture base , accounting for approximately 33% of failure .\nit has been estimated that between 22% and 30% of denture repairs involve tooth debonding , usually in the anterior region of the denture .\nthis detachment may be attributed to a lesser ridge lap surface areas available for bonding and the direction of the stresses encountered during function.1 failure of the bond between denture teeth and denture base was mainly adhesive or cohesive failure .\nadhesive failure occurred when there was no trace of denture base material on the ridge laps of the teeth after fracture . on the other hand , failure of the bond\nwas considered cohesion failure when there were remnants of the denture base material on the ridge laps of the teeth after fracture.2 traditionally , acrylic resin denture bases have been fabricated by compression molding technique and processed in brass denture flasks.3 the packed denture flasks are placed in a temperature - controlled water bath for a specified time to polymerize the resin .\nhowever , microwave irradiation , as developed by nishii in 1968 , is popular alternative for polymerization.4 complete polymerization in the microwave produces a smooth denture surface that effectively prevents build - up of plaque ; it also greatly reduces the tendency to discolor as a result of water absorption\n. however , the most common disadvantages of microwave technique were related to the flasks used in processing as they relatively expensive and have a tendency to break down after processing several dentures.5 bond failures at the acrylic teeth and denture base resin interface are still a common clinical problem in prosthodontics , so this study was done to evaluate bond strength of acrylic teeth to denture base using different polymerization techniques and to assess mode of failure of fractured acrylic teeth .\nrepresentative brands of acrylic teeth ( vitapan , vident , california ) were bonded to heat polymerized denture base resin ( dpi heat cure , mumbai , india ) for both water bath polymerization and microwave polymerization .\nconventional metal flask was used for water bath polymerization , and specially fabricated fiber reinforced plastic flask was used for microwave curing .\na total of 40 maxillary central incisors were selected and fixed to a metallic base with wax so that similar angulations were maintained for all teeth .\nthe teeth were surrounded by pvc cylinder of height 7.5 mm and diameter 7.5 mm ( according to ada specification no .\n15 for acrylic teeth ) and were bonded to the base with vinyl acetate ( figure 1 ) .\nafter plaster setting , the each pvc cylinder was separated from the metallic base checked to verify the absence of porosity and residual wax . using the same pvc cylinders ,\nmelted wax was poured to create a virtual space to be filled by denture base resin .\nthe plaster - tooth - wax assemblies were positioned in a muffle base with wax turned upward .\nthe dental plaster was poured up to the plaster - wax border . after mounting specimens were invested in a conventional denture base flask and the microwave flask , respectively , and dewaxing was followed .\nlayout of metallic base and denture tooth placed inside a pvc cylinder , before filling with dental stone .\ncuring cycles followed \n conventional curing cycle : heat - polymerized specimens were processed in a heat curing unit at 74c for 2 h and 100c for 1 h.microwave curing cycle : specimens were processed in a microwave oven for 4 min at 500 w. \n conventional curing cycle : heat - polymerized specimens were processed in a heat curing unit at 74c for 2 h and 100c for 1 h. microwave curing cycle : specimens were processed in a microwave oven for 4 min at 500 w. specimens were deflasked , and the gross adhering of stone was removed with hand instruments .\nspecimens were then stored in distilled water before the bond test has been carried out .\nthe machine used a direct pull on the incisal portion of the lingual surface in a labial direction at a height above the denture base resin bar with a crosshead speed of 0.5 mm / min ( figure 2 ) .\nwithin the limitations of the study , the specimens were prepared , and bond strength of acrylic denture teeth to denture base resin was evaluated .\nall the failure sites were cohesive , that is , within the body of the tooth .\naverages of bond strength ( kgf ) obtained with vitapan teeth for conventional water bath polymerization and microwave polymerization are given in table 1 .\nconventionally cured specimen exhibited statistically significant p < 0.001 higher bond strength than microwave cured specimens ( graph 1 ) .\naverages of bond strength ( kgf ) obtained with vitapan teeth for conventional water bath polymerization and microwave polymerization .\nbond strength ( kgf ) obtained with vitapan teeth for conventional water bath polymerization and microwave polymerization .\nbond failures between tooth and denture base represent a problem for rehabilitation success . in order to minimize these failures\n, many authors described main factors that can influence in bond strength : tooth types and brands , resin types and brands , stress distribution , method of processing , temperature of processing , resin stage , and processing variables.6 there should be good attachment between artificial teeth and denture bases . in case of acrylic teeth bonding between acrylic teeth and denture bases occurs via chemical bond which depends on the softening of the resin at the base of the teeth with monomer from the dough of denture base material .\nwhen a denture tooth is fractured away from a sample of a denture base , the fracture path must not occur along the interface between the tooth and denture base , i.e. the fracture must be cohesive . using this criterion ,\nall denture teeth tested in this study polymerized with either heat or microwave polymerization bonded satisfactorily.7 thean et al .\n, compare bond strength between three different brands of resin teeth to denture base using conventional water bath technique and concluded that bond strength is adequate even without mechanical preparation of the surface since majority of fracture did not occur at tooth - bond interface.8 this finding also seems to concur with huggett et al . , who found that mechanical preparation of bonding surface of tooth did not change the bond strength significantly.9 takahashi et al .\n, concluded that conventional resin teeth possessed higher bond strength than cross - linked denture teeth .\nthe heat - cured denture base resin possesses significantly higher bond strength than the microwave - cured denture base resin .\nboth materials were better than the pour - type resin and the application of dichloromethane improves the bond strength.10 by contrast , greets and jooste compare bond strengths of microwave and water bath cured material and concluded that microwave - cured poly - methyl - methacrylate ( pmma)demonstrated significantly ( p = 0.0001 ) higher bond strengths than conventional pmma , and application of monomer to tooth surface yields significantly higher bond strengths than other surface treatment.11 present study showed that lower bond strength values were recorded between acrylic resin teeth and denture bases cured by microwave than conventional water bath polymerization method and majority of the fractures occur at within the body of the tooth , indicating that method of polymerization affect the bond strength between tooth and denture base .\nin fact , microwave polymerization was reported to have uncontrolled temperature rise , causing the denture base components to heat above the boiling point of the monomer and resulting in the formation of pores.12 thus , increased number of pores reduces the strength of a denture base , which may be generally found after microwave polymerization compared with water bath processing , especially in the thicker part of the denture .\nthis finding is of clinical importance because the thickness of the denture base material in the tooth - bearing areas might promote pore formation .\nwithin the limitations of the study , following conclusions can be drawn : \n polymerization technique affects the bond strength between acrylic teeth and denture base resinconventional water bath polymerization technique possesses higher bond strength than microwave polymerization technique between acrylic teeth and denture basemajority of fracture occur within the body of the tooth rather than tooth acrylic interface . \n \npolymerization technique affects the bond strength between acrylic teeth and denture base resin conventional water bath polymerization technique possesses higher bond strength than microwave polymerization technique between acrylic teeth and denture base majority of fracture occur within the body of the tooth rather than tooth acrylic interface .", "role": "user" }, { "content": "background : acrylic teeth have long been used in the treatment of a complete denture . \n one of the primary advantages of acrylic teeth is their ability to adhesively bond to the denture base resins . \n although the bonding seems satisfactory , however , bond failures at the acrylic teeth and denture base resin interface are still a common clinical problem in prosthodontics . \n the purpose of this study was to evaluate the bond strength of acrylic teeth to denture base using different polymerizing techniques.materials and methods : acrylic resin teeth were bonded to heat cure acrylic resin and were polymerized by conventional water bath and microwave energy . \n the samples are then retrieved from the flask ; trimmed and polished . \n the samples were then subjected to tensile forces till failure by using the instron universal testing machine . \n the machine used a direct pull on the incisal portion of the lingual surface in a labial direction at a height above the denture base resin bar with a crosshead speed of 0.5 mm / min.results : in the present study , it was found that conventionally cured specimens exhibited higher bond strength than microwave cured specimens and majority of fractures occur within the body of the tooth . \n it was found that debonding occurs within the body of the tooth rather than tooth acrylic interface , so there is no need of surface treatment of ridge lap surface.conclusion:conventionally cured specimens possess statistically higher bond strength than microwave cured specimens .", "role": "assistant" } ]

[ { "content": "Summarize the paper:\n\nPaper text:\n\nWe propose a generative adversarial training approach for the problem of clarification question generation.\nOur approach generates clarification questions with the goal of eliciting new information that would make the given context more complete.\nWe develop a Generative Adversarial Network (GAN) where the generator is a sequence-to-sequence model and the discriminator is a utility function that models the value of updating the context with the answer to the clarification question.\nWe evaluate on two datasets, using both automatic metrics and human judgments of usefulness, specificity and relevance, showing that our approach outperforms both a retrieval-based model and ablations that exclude the utility model and the adversarial training.\n\nA goal of natural language processing is to develop techniques that enable machines to process naturally occurring language.\nHowever, not all language is clear and, as humans, we may not always understand each other BID10 ; in cases of gaps or mismatches in knowledge, we tend to ask questions BID9 .\nIn this work, we focus on the task of automatically generating clarification questions: questions that ask for information that is missing from a given linguistic context.\nOur clarification question generation model builds on the sequence-to-sequence approach that has proven effective for several language generation tasks BID37 BID39 BID5 .\nUnfortunately, training a sequence-to-sequence model directly on context/question pairs yields generated questions that are highly generic 1 , corroborating a common finding in dialog systems BID17 .\nOur goal is to be able to generate questions that are useful and specific.To achieve this, we begin with a recent observation of BID30 , who considered the task of question reranking: the system should learn to generate clarification questions whose answers have high utility, which they defined as the likelihood that this question would lead to an answer that will make the context more complete ( §2.3).\nInspired by this, we construct a question generation model that first generates a question given a context, and then generates a hypothetical answer to that question.\nGiven this (context, question, answer) tuple, we train a utility calculator to estimate the usefulness of this question.\nWe then show that this utility calculator can be generalized using ideas for generative adversarial networks BID8 for text BID40 , wherein the utility predictor plays the role of the \"discriminator\" and the question generator is the \"generator\" ( §2.2), which we train using the MIXER algorithm BID29 .We\nevaluate our approach on two question generation datasets: for posts on Stack Exchange and for Amazon product descriptions (Figure 1 ). Using\nboth automatic metrics and human evaluation, we demonstrate that our adversarially trained model generates a more diverse set of questions than all the baseline models. Furthermore\n, we find that although all models generate questions that are relevant to the context at hand, our adversarially-trained model generates questions that are more specific to the context.\nIn this work, we describe a novel approach to the problem of clarification question generation.\nGiven a context, we use the observation of BID30 that the usefulness of a clarification question can be measured by the value of updating the context with an answer to the question.\nWe use a sequence-to-sequence model to generate a question given a context and a second sequenceto-sequence model to generate an answer given the context and the question.\nGiven the (context, predicted question, predicted answer) triple we calculator the utility of this triple and use it as a reward to retrain the question generator using reinforcement learning based MIXER model.\nFurther, to improve upon the utility function, we reinterpret it as a discriminator in an adversarial setting and train both the utility function and the MIXER model in a minimax fashion.\nWe find that our adversarial training approach produces more diverse questions compared to both a model trained using maximum likelihood objective and a model trained using utility reward based reinforcement learning.\nThere are several avenues of future work in this area.\nFollowing BID24 , we could combine text input with image input to generate more relevant questions.\nBecause some questions can be answered by looking at the product image in the Amazon dataset BID22 , this could help generate more relevant and useful questions.\nAs in most One significant research challenge in the space of free text generation problems when the set of possible outputs is large, is that of automatic evaluation BID20 : in our results we saw some correlation between human judgments and automatic metrics, but not enough to trust the automatic metrics completely.\nLastly, integrating such a question generation model into a real world platform like StackExchange or Amazon to understand the real utility of such models and to unearth additional research questions.", "role": "user" }, { "content": "We propose an adversarial training approach to the problem of clarification question generation which uses the answer to the question to model the reward.", "role": "assistant" } ]

[ { "content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Is Ixodes a species of tick?\n\nContext: ixodid ticks\nixodid ticks\nixodid ticks\ntick, Ixodes ricinus\nhard ticks (family Ixodidae)\nThe two enzootic tick vectors, Ixodes affinis and Ixodes minor, rarely bite humans but are more important than the human biting \"bridge\" vector, Ixodes scapularis, in maintaining the enzootic spirochete cycle in nature.\nis more common in coastal habitats, where a greater diversity of Ixodes species ticks are found feeding on small mammal hosts (four species when compared with only I. pacificus in other sampled habitats).\nWe found three of five previously reported tick species as well as a tick resembling the eastern North American tick Ixodes minor Neumann (which we here designate Ixodes \"Mojave morphotype\") on isolated Amargosa voles and Owens Valley voles (Microtus californicus vallicola Bailey) in Inyo County in 2012 and 2014.\nTHODS: We focused on the well-studied tick genus Ixodes from which many species are known to transmit zoonotic diseases to humans. W\nEctoparasites of Microtus californicus and Possible Emergence of an Exotic Ixodes Species Tick in California.\nSince 2007, non-native tick species have been documented in the state every year, including Amblyomma americanum, Dermacentor andersoni, Dermacentor occidentalis, Dermacentor variabilis, Ixodes pacificus, Ixodes ricinus, Ixodes scapularis, Ixodes texanus, and Rhipicephalus sanguineus sensu lato (s.l.).\nin 1.5% of Ixodes species ticks and 3.6% of small mammals.\nData-driven predictions and novel hypotheses about zoonotic tick vectors from the genus Ixodes.\nspirochetes and transmitted by Ixodes species ticks.\nIn this study, cutaneous bite-site lesions were analyzed using Affymetrix mouse genome 430A 2.0 arrays and histopathology at 1, 3, 6, and 12 hours after uninfected Ixodes scapularis nymphal tick attachment.\nThe minimally vegetated, extremely arid desert surrounding the pools is essentially uninhabitable for Ixodes species ticks.\nBiology of Ixodes species ticks in relation to tick-borne zoonoses.\nBorrelia miyamotoi is a newly described emerging pathogen transmitted to people by Ixodes species ticks and found in temperate regions of North America, Europe, and Asia.\nRickettsia conorii was found in virtually all non- Ixodes tick species from Albania and Turkey.\nIxodes anatis is a species of endophilic (nidicolous) tick species parasitizing brown kiwi (Apteryx mantelli). Even\nIxodes ariadnae is a tick species of bats so far reported only in Central Europe, with its description based on the female and nymph. Th\nBACKGROUND: Ixodes collaris Hornok, 2016 is a recently discovered tick species associated with bats\nIxodes holocyclus (Acarina: Ixodidae) and Ixodes cornuatus (Acarina: Ixodidae) are two tick species found in the more densely populated areas of Australia and are known to be the cause of the neurotoxic disease tick paralysis in humans and mammals. Borre\nIxodes affinis Neumann (Acari: Ixodidae) is a hard-bodied tick species distributed throughout much of the southeastern United States. Alt\nixodid tick fauna consists of 241 species in the genus Ixodes and 442 species in the genera Amblyomma, Anomalohimalaya, Bothriocroton, Cosmiomma, Dermacentor, Haemaphysalis, Hyalomma, Margaropus, Nosomma, Rhipicentor and Rhipicephalus in the family Ixodidae, with the genus Boophilus becoming a subgenus of the genus Rhipicephalus. The family Nutt\ne following 16 ixodid tick species were identified: Ixodes fuscipes, Amblyomma auricularium, Amblyomma coelebs, Amblyomma dubitatum, Amblyomma geayi, Amblyomma humerale, Amblyomma latepunctatum, Amblyomma longirostre, Amblyomma naponense, Amblyomma nodosum, Amblyomma oblongoguttatum, Amblyomma ovale, Amblyomma romitii, Amblyomma rotundatum, Amblyomma scalpturatum, and Amblyomma varium. From these, A. aur\nIn 2014, a new tick species, Ixodes inopinatus, was described, which is closely related to Ixodes ricinus. So fa\nontinent. Zoonotic Babesia is vectored by Ixodes ticks and is commonly transmitted in North America by Ixodes scapularis, the tick species responsible for transmitting the pathogens that also cause Lyme disease, Powassan virus, and anaplasmosis in hu\nIn addition to identifying novel, testable hypotheses about intrinsic features driving vectorial capacity across Ixodes tick species, our model identifies particular Ixodes species with the highest probability of carrying zoonotic diseases, offering specific targets for increased zoonotic investigation and surveillance.\nTo date, the tick fauna of this area consists of 117 species in the following families: Argasidae-Argas (7 species), Carios (4 species) and Ornithodoros (2 species); Ixodidae-Amblyomma (8 species), Anomalohimalaya (2 species), Dermacentor (12 species), Haemaphysalis (44 species), Hyalomma (6 species), Ixodes (24 species) and Rhipicephalus (8 species).\nDuring a 3-yr comprehensive study, 196 ixodid ticks (9 species) were collected from 89 passerine birds (32 species) from 25 localities across Canada to determine the distribution of avian-associated tick species and endogenous Lyme disease spirochetes, Borrelia burgdorferi Johnson, Schmid, Hyde, Steigerwalt, and Brenner.\nIn the Polish fauna there are 19 species of ticks (Ixodida) recognized as existing permanently in our country: Argas reflexus, Argas polonicus, Carios vespertilionis, Ixodes trianguliceps, Ixodes arboricola, Ixodes crenulatus, Ixodes hexagonus, Ixodes lividus, Ixodes rugicollis, Ixodes caledonicus, Ixodes frontalis, Ixodes simplex, Ixodes vespertilionis, Ixodes apronophorus, Ixodes persulcatus, Ixodes ricinus, Haemaphysalis punctata, Haemaphysalis concinna, Dermacentor reticulatus.\nOccasionally, alien species of ticks transferred to the territory of Poland are recorded: Amblyomma sphenodonti, Amblyomma exornatum, Amblyomma flavomaculatum, Amblyomma latum, Amblyomma nuttalli, Amblyomma quadricavum, Amblyomma transversale, Amblyomma varanensis, Amblyomma spp., Dermacentor marginatus, Hyalomma aegyptium, Hyalomma marginatum, Ixodes eldaricus, Ixodes festai, Rhipicephalus rossicus, Rhipicephalus sanguineus.\nHaemaphysalis leporispalustris (Packard) (one nymph, 14 larvae); the bird tick Ixodes brunneus Koch (two larvae); the American dog tick, Dermacentor variabilis (Say) (one nymph); and Ixodes affinis Neumann (one larva).\nFour members of the Ixodes ricinus species complex, Ixodes pacificus, Ixodes persulcatus, Ixodes ricinus and Ixodes scapularis, have, between them, a worldwide distribution within the northern hemisphere.\nDiapause in ticks of the medically important Ixodes ricinus species complex.\nHerein, we report these ticks to represent three different species: Ixodes catarinensis n. sp.\nWe found that 430 endemic ticks were from 3 Ixodes species: Ixodes pacificus, Ixodes spinipalpis, and Ixodes angustus, whereas Ixodes scapularis (n = 111) was the most common species among the 119 nonendemic ticks.\nIn total, 549 human-biting Ixodes ticks were submitted comprising both endemic and nonendemic species.\nHuman-Biting Ixodes Ticks and Pathogen Prevalence from California, Oregon, and Washington.\nIn this study, we show that many nonendemic Ixodes ticks (119/549) are most likely acquired from travel to a different geographic region.\nThe Ixodes ricinus species complex is a group of ticks distributed in almost all geographic regions of the world.\nWe report a tick associated with the enhancement of mammalian meat anaphylaxis after tick bite which is novel for both Australia and the world and establishes Ixodes (Endopalpiger) australiensis as a second tick species associated with mammalian meat allergy in Australia.\nAmong the various species of hard ticks, Ixodes ricinus is the most frequently found tick throughout Europe.\nin humans. We aimed to identify intrinsic traits that predict which Ixodes tick species are confirmed or strongly suspected to be vectors of zoonotic pathogens.METHODS: We focused on the well-studied tick genus Ixodes from which many species are known to transmit zoonoti\nA list of the 70 species of Australian ticks; diagnostic guides to and species accounts of Ixodes holocyclus (paralysis tick), Ixodes cornuatus (southern paralysis tick) and Rhipicephalus australis (Australian cattle tick); and consideration of the place of Australia in the evolution of ticks with comments on four controversial ideas.\nDifferentiation of medically important Euro-Asian tick species Ixodes ricinus, Ixodes persulcatus, Ixodes hexagonus, and Dermacentor reticulatus by polymerase chain reaction.\nAll these I. granulatus ticks collected from Taiwan and Japan were genetically affiliated to a monophyletic group with highly homogeneous sequences (95.8-99.5% similarity), and can be discriminated from other species and subgenera of Ixodes ticks with a sequence divergence ranging from 13.6% to 62.9%.\nThe phylogenetic relationships were analyzed by comparing the sequences of mitochondrial 16S ribosomal DNA gene obtained from 19 strains of ticks representing seven species of Ixodes and two outgroup species (Rhipicephalus sanguineus and Haemaphysalis inermis).\ne, I. woyliei n. sp. was only found on two I. o. fusciventer.CONCLUSIONS: Morphological and molecular data have confirmed the first new Australian Ixodes tick species described in ov\nMore than 800 tick species have been reported world-wide however only about 30 tick species feed on humans, among them Ixodes ricinus, which is the most frequent tick species biting humans in Europe.\nDescription of a new tick species, Ixodes collaris n. sp. (Acari: Ixodidae), from bats (Chiroptera: Hipposideridae, Rhinolophidae) in Vietnam.", "role": "user" }, { "content": "yes", "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: Sources of MT include the methylation of sulfide in anoxic habitats, demethiolation of sulfhydryl groups and degradation of sulfur-containing amino acids (Lomans et al., 2001, 2002; Bentley and Chasteen, 2004).", "role": "user" }, { "content": "Background", "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: Baird et al. (2007) hypothesize that symbiont community shuffling to clade D may persist only as a result of enduring changes in environmental conditions, e.g. repeated warm summers.", "role": "user" }, { "content": "Background", "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 Illumina platform and Roche GS-FLX are an effective combination to call SNPs when lacking a reference genome [17–20], but additional labor, time and cost are required to build a rough reference with GS-FLX.", "role": "user" }, { "content": "Method", "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:\nEffect of diltiazem on symptomatic and asymptomatic episodes of ST segment depression occurring during daily life and during exercise . BACKGROUND Silent myocardial ischemia is an adverse prognostic marker in patients with coronary disease ; however , controlled data on the effect of treatment are sparse and contradictory , and the relations among the occurrence of ST segment depression , drug efficacy , and heart rate are unclear . METHODS AND RESULTS Sixty patients with stable coronary artery disease , a positive treadmill exercise test and asymptomatic ST segment depression on ambulatory electrocardiographic recording were assessed in a multicenter , double-blind , placebo-controlled , cross-over trial . Treadmill exercise tests and 72-hour electrocardiographic recordings were obtained at the end of two 2-week treatment periods with sustained-release diltiazem 180 mg b.i.d . or equivalent placebo . Episodes of asymptomatic ST depression decreased by 50 % or more in 70 % of the patients from a median number of 4.5 ( range , 0-19 ) to 1.5 ( range , 0-13 ) ( p = 0.0001 ) ; their cumulative duration also decreased from 78.5 ( range , 0-60 ) to 24.5 ( range , 0-411 ) minutes ( p = 0.001 ) . No circadian variation was found in the efficacy of diltiazem . The occurrence of ischemic type ST segment depression was modulated by changes in heart rate rather than by absolute heart rate . Diltiazem also improved exercise test end points but to a lesser extent . Time to ST segment depression increased to 341 +/- 148 from 296 +/- 154 seconds ( p = 0.005 ) . Although less frequent with diltiazem administration ( 45 versus 54 patients , p less than 0.03 ) , exercise-induced ST depression was more often asymptomatic ( 98 % versus 72 % of patients , p less than 0.0001 ) . CONCLUSIONS Diltiazem reduces the frequency and severity of ischemic type ST depression in patients with stable coronary artery disease .", "role": "user" }, { "content": "{\"Intervention\": [\"Treadmill exercise\", \"diltiazem .\", \"placebo .\", \"sustained-release diltiazem\", \"Diltiazem\", \"placebo-controlled\", \"diltiazem\"], \"Outcome\": [\"Time to ST segment depression\", \"ischemic type ST segment depression\", \"cumulative duration\", \"circadian variation\", \"exercise test end points\", \"72-hour electrocardiographic recordings\", \"exercise-induced ST depression\", \"Episodes of asymptomatic ST depression\", \"ST segment depression\", \"Treadmill exercise tests\", \"changes in heart rate\", \"ischemic type ST depression\"], \"Participant\": [\"asymptomatic ST segment depression\", \"positive treadmill exercise test\", \"Sixty\", \"coronary disease\", \"ST segment depression\", \"stable coronary artery disease\"]}", "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:\nEEG mapping and psychopharmacological studies with denbufylline in SDAT and MID . Computed tomography ( CT ) , electroencephalograms ( EEG ) , clinical and psychometric data were obtained in 96 mildly to moderately demented patients ( 72 women , 24 men ) , aged 61-96 years ( mean 82 ) , diagnosed according to DSM-III criteria . Patients were off drugs for at least 2 weeks and subdiagnosed according to the modified Marshall-Hachinski ischemic score and CT in 45 senile dementia of the Alzheimer type ( SDAT ) and 51 multiinfarct dementia ( MID ) patients . Evaluations were carried out before and 12 weeks after treatment with either 100 mg denbufylline BID or placebo and included EEG mapping , the Sandoz Clinical Assessment Geriatric ( SCAG ) score/factors , the Clinical Global Impression ( CGI ) , the Digit Symbol Substitution Test ( DSST ) , the Trail-Making Test ( TMT ) and the Digit Span Test ( DS ) . Descriptive data analysis including confirmatory statements found delta/theta activity enhanced , alpha and beta activity reduced , total power augmented , and the centroid slowed down over various brain regions in patients as compared with controls . The two subtypes of dementia could be differentiated in some conventional EEG variables but mostly by means of power asymmetry indices . Denbufylline induced a statistically significant and clinically relevant improvement in both SDAT and MID patients , whereas after placebo this was not the case in CGI , the TMT , and the DS , with interdrug differences being significant in all primary target variables such as the CGI , MMS , SCAG , and DSST . Thus , both the degenerative and vascular type of dementia exhibited a therapeutic benefit that could be objectified at the neurophysiological level by EEG mapping in an improvement of vigilance .", "role": "user" }, { "content": "{\"Intervention\": [\"Denbufylline\", \"denbufylline\", \"placebo\"], \"Outcome\": [\"alpha and beta activity\", \"improvement in both SDAT and MID\", \"centroid\", \"delta/theta activity\", \"total power\"], \"Participant\": [\"72\", \"multiinfarct dementia\", \"45\", \"24\", \"SDAT\", \"demented\", \"men\", \"96\", \"Alzheimer type\", \"aged 61-96 years ( mean 82 )\", \"women\", \"MID\", \"51\", \"senile dementia\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nPostsynthetic Metalation of a Robust Hydrogen-Bonded Organic Framework for Heterogeneous Catalysis\n\nPaper sections:\n\n<p>Heterogeneous catalysis plays a dominant role in the chemical and pharmaceutical industry.1 As a result, continuous efforts have been paid toward developing effective methods for synthesizing heterogeneous catalysts with high efficiency and in particular with an easy recovery and recycling nature. In the past several years, by immobilizing homogeneous catalysts inside the porous supports such as zeolites,2 metal–organic frameworks (MOFs),3 and covalent organic frameworks (COFs),4 diverse heterogeneous catalysts with boosted activity and stability have been fabricated. However, the regeneration of these heterogeneous catalysts is still challenging due to their nonrenewable porous supports.</p><p>In the same way as MOFs and COFs, porous hydrogen-bonded organic frameworks (HOFs) are self-assembled from discrete molecular modules as well.5 Despite the outstanding properties of HOFs revealed in the fields of gas storage,6 small-molecule separation,7 sensing,8 and proton conduction,9 reports over HOF-based catalysts still remain unknown, to the best of our knowledge, due to the relatively poor stability associated with the weak hydrogen bonding connection between discrete building blocks in HOFs.5–9 Fortunately, the introduction of additional π−π interactions would significantly enhance the stability when aromatic building blocks are employed for constructing HOFs,5g,6f rendering it possible to fabricate heterogeneous catalysts with robust frameworks as the porous support of homogeneous species. In particular, the excellent recyclability of HOFs through simple recrystallization enables them to be regenerated easily, thus endowing the sustainable advantage to HOF-based catalysts.</p><p>Herein, a novel organic cage of amino-substituted bis(tetraoxacalix[2]arene[2]triazine) (L) composed of five six-membered aromatic rings has been designed and prepared as a building block for assembling HOFs (Figure 1a and Scheme S1, Supporting Information). Depending on the hydrogen bonding between neighboring building blocks with the help of rich π−π interactions between intercage aromatic moieties, the first cage-based HOF (HOF-19) is constructed, and its hydrogen-bonded structure is clearly revealed by single-crystal X-ray diffraction analysis. The N2 sorption measurement at 77 K discloses a Brunauer–Emmett–Teller (BET) surface area of 685 m2 g−1 for activated HOF-19. Postfunctionalization of this HOF with palladium acetate gives a palladium(II)-containing HOF-19⊃Pd(II) with parent hydrogen-bonded structure maintained according to the powder X-ray diffraction (PXRD) analysis, indicating the robustness of HOF-19. Further evidence on the robustness of HOF-19 comes from the excellent stability and recyclability of HOF-19⊃Pd(II) in p-xylene in the presence of potassium carbonate at 150 °C. Under such experimental conditions, the Suzuki–Miyaura coupling reaction is able to be selectively promoted in high isolation yields (96−98%), revealing the predominant catalytic activity of HOF-based materials for the first time. Nevertheless, the catalytic activity of deactivated species, with the 46% isolation yield for the conversion of 4-bromobenzonitrile, is recovered to 92% by simple recrystallization regeneration, revealing the great application potentials of HOF-based catalysts.</p><p>A facile reaction between chloride-substituted bis(tetraoxacalix[2]arene[2]triazine)10 and ammonium hydroxide afforded L (Scheme S1 and Figures S1 and S2, Supporting Information). The slow evaporation of the formic acid solution of L gave single crystals of HOF-19 with poor solubility in common organic solvents (except only DMSO). Single-crystal X-ray diffraction data confirms the three-dimensional (3D) porous structure of HOF-19 (Figure 1; Tables S1 and S2, Supporting Information). As exhibited in Figure 1, depending on the multiple N−H···N hydrogen bonding between intercage 2-aminotriazinyl (AT) groups with the help of π−π interactions from intercage benzene moieties, two-dimensional porous hydrogen-bonded supramolecular structures containing one-dimensional (1D) channels with the size of 8.0 × 13.6 Å along the [010] direction are formed, which are further packed into the 3D architecture of HOF-19 depending on the intercage cofacial π−π interaction between AT groups and C−H···π interaction (actually a kind of π−π interaction). The PLATON calculation discloses 47% void space for HOF-19,11 which should be favorable for the molecular substrate diffusion.</p><p>The bulk material of HOF-19 with good thermal stability was obtained by diffusing acetone into the formic acid solution of L (Figure S3, Supporting Information). Acetone-exchanged HOF-19 was degassed at 25 °C to give an activated sample (HOF-19a). The PXRD pattern of HOF-19a is well consistent with the simulated profile of HOF-19 (Figures S4 and S5, Supporting Information), indicating its robust nature. The N2 sorption measurement at 77 K reveals its type I adsorption curve with a N2 uptake of 287 cm3 g−1 at 1.0 bar (Figure 2). The experimental pore volume of 0.45 cm3 g−1 is well consistent with the theoretical value (0.48 cm3 g−1; Table S1).11 The BET surface area of HOF-19a was calculated to be 685 m2 g−1.</p><p>The multiple hydrogen bonding and π−π interactions between neighboring cages enhance the robustness of HOF-19. The poor solubility of HOF-19 in common organic solvents could effectively stabilize the framework in solution. In addition, abundant triazinyl nitrogen atoms and amino groups inside the pores of HOF-19 provide enough binding sites to incorporate catalytically active metal ions. All these characteristics inspire us to fabricate a heterogeneous catalyst with HOF-19 as the porous support. The immersion of activated HOF in an acetone solution of palladium acetate (0.100 mM) afforded palladium(II)-containing HOF-19⊃Pd(II). Its PXRD pattern matches well with the simulated one for HOF-19 in Figure S6 (Supporting Information), indicating the hydrogen-bonded structure retained by the post-treated species and illustrating the HOF robustness again. Inductively coupled plasma (ICP) analysis gives a Pd content of 3.8 wt % included in HOF-19⊃Pd(II). In the X-ray photoelectron spectrum shown in Figure S7 (Supporting Information), the observation of two peaks with the binding energy of 338.1 and 343.4 eV corresponding to Pd 3d5/2 and Pd 3d3/2, respectively, confirms divalent palladium ions bound by HOF-19. The slight downshift of Pd 3d5/2 and Pd 3d3/2 binding energy for HOF-19⊃Pd(II) relative to that (338.3 and 343.6 eV) of palladium acetate indicates the presence of an interaction between Pd2+ ions and HOF-19.12 The slight upshift for the binding energy of the amino group of HOF-19 after including palladium acetate not only indicates HOF-19 interacting with Pd2+ ions but also suggests the amino groups, instead of the intracage cavity, as active sites to bind the metal ions (Figure S8, Supporting Information). The energy-dispersive spectroscopy (EDS) mapping of HOF-19⊃Pd(II) clearly hints at the homogeneous distribution of the Pd element, excluding the presence of Pd nanoparticles (Figure S9, Supporting Information). After postmodification with Pd(OAc)2 to give HOF-19⊃Pd(II) with palladium ions decorated on the surface of HOF channels, the BET surface area was decreased to 159 m2 g−1, indicating the partial structural collapse of HOF after Pd2+ inclusion.</p><p>To illustrate the proof-of-concept of the HOF-based catalyst, the Suzuki–Miyaura coupling reaction was selected as a model reaction to examine the catalytic activity of HOF-19⊃Pd(II). As can be found in Table 1, in the presence of 0.260 mmol % HOF-19⊃Pd(II), the halogenated benzene substrates (entries 1–6) were successfully transformed to corresponding coupling products in the high isolation yields of 96–98% within a short time of 1.5–2.5 h. In particular, for the conversion of 1-bromo-4-nitrobenzene, only about 0.260% Pd content in HOF-19⊃Pd(II) was revealed to be leached into the filtrate according to the ICP measurement, indicating the strong interaction between Pd2+ and HOF-19. Under the same conditions, the catalytic activity of 0.260 mmol % HOF-19⊃Pd(II) is even comparable to the excellent performance of 0.500 mmol % COF-LZU1⊃Pd(II) catalyst toward the reaction of 1-bromo-4-methoxybenzene with phenylboronic acid,12 indicating the excellent catalytic activity of HOF-19⊃Pd(II) (Table 1). Nevertheless, HOF-19⊃Pd(II) shows a much higher catalytic efficiency in comparison with palladium acetate, a mixture of HOF-19 and palladium acetate, and Pd/C catalyst, confirming the crucial role of palladium(II) ions deposited on the channel surfaces of HOF-19 on the present heterogeneous catalysis of the Suzuki–Miyaura coupling reaction. Interestingly, under the same reaction conditions, the substrates of 4′-bromo-1,1′-biphenyl and 4-methoxy-4′-bromo-1,1′-biphenyl with large molecular size of 7.5 × 13.9 and 7.5 × 16.0 Å, respectively, were converted into the corresponding product only with the isolation yield below 20% even after 4.0 h, which are even much lower than those with Pd(OAc)2 as the catalyst (Table 1 and Table S3, Supporting Information), indicating the presence of pore size selectivity of the HOF-19⊃Pd(II) catalyst.</p><p>The recyclability of HOF-19⊃Pd(II) catalyst was evaluated in the conversion of 4-bromobenzonitrile. HOF-19⊃Pd(II) kept an almost constant catalytic activity and good crystallinity for four cycles of reaction, indicating again the good stability of the HOF-based catalyst (Figures S6 and S10, Supporting Information). The isolated yield for the fifth reaction cycle was reduced to ca. 74%. After the continuous coupling reaction of 4-bromobenzonitrile for 20.0 h, HOF-19⊃Pd(II) was deactivated with the low isolation yield of 46%. However, recrystallization of deactivated catalyst afforded a regenerated crystalline sample (Figure S11, Supporting Information). More importantly, this regenerated catalyst displayed a recovered catalytic activity toward 4-bromobenzonitrile with the 92% isolation yield (Figure S12, Supporting Information), revealing the sustainable advantage of this newly developed HOF-based catalyst.</p><p>In summary, a novel cage-based HOF with permanent porosity has been synthesized for the first time. Multiple hydrogen bonding interactions together with the π−π interactions enhance the stability of HOF. With this porous HOF as a robust support of palladium acetate, a highly efficient and selective HOF-based heterogeneous catalyst has been realized toward the Suzuki–Miyaura coupling reaction. In particular, by utilizing the recycling advantage of HOFs, this HOF-based catalyst could be easily regenerated through simple recrystallization, exhibiting almost recovered activity. These results reveal the great application potentials of HOF-based catalysts. We hope the present result will ignite more research interest toward exploration of HOF-based catalysts and other applications.</p>", "role": "user" }, { "content": "Hydrogen-bonded organic framework (HOF)-based catalysts still remain unreported thus far due to their relatively weak stability. In the present work, a robust porous HOF (HOF-19) with a Brunauer\\xe2\\x80\\x93Emmett\\xe2\\x80\\x93Teller surface area of 685 m2 g\\xe2\\x88\\x921 was reticulated from a cagelike building block, amino-substituted bis(tetraoxacalix[2]arene[2]triazine), depending on the hydrogen bonding with the help of \\xcf\\x80\\xe2\\x88\\x92\\xcf\\x80 interactions. The postsynthetic metalation of HOF-19 with palladium acetate afforded a palladium(II)-containing heterogeneous catalyst with porous hydrogen-bonded structure retained, which exhibits excellent catalytic performance for the Suzuki\\xe2\\x80\\x93Miyaura coupling reaction with the high isolation yields (96\\xe2\\x88\\x9298%), prominent stability, and good selectivity. More importantly, by simple recrystallization, the catalytic activity of deactivated species can be recovered from the isolation yield 46% to 92% for 4-bromobenzonitrile conversion at the same conditions, revealing the great application potentials of HOF-based catalysts.", "role": "assistant" } ]

[ { "content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What is the mechanism of action of Nalmefene?\nContext: Opioids that stimulate the μ-opioid receptor (MOR1) are the most frequently prescribed and effective analgesics. Here we present a structural model of MOR1. Molecular dynamics simulations show a ligand-dependent increase in the conformational flexibility of the third intracellular loop that couples with the G protein complex. These simulations likewise identified residues that form frequent contacts with ligands. We validated the binding residues using site-directed mutagenesis coupled with radioligand binding and functional assays. The model was used to blindly screen a library of ∼1.2 million compounds. From the 34 compounds predicted to be strong binders, the top three candidates were examined using biochemical assays. One compound showed high efficacy and potency. Post hoc testing revealed this compound to be nalmefene, a potent clinically used antagonist, thus further validating the model.\nThe neurobiological mechanism by which opioid modulators affect drinking behavior is based on the strong connection between the endogenous opioid system, the dopamine system and the influence of the CNS stress response.\nNaltrexone- and to a lesser extent nalmefene- is an agent that modulates opioidergic transmission in the CNS and it shows a limited but well-studied efficacy in treating alcohol dependence.\nSeveral derivatives of Naltrexone, Nalmefene (Nal) and JKB-119, exert immunomodulatory activity; however, unlike Nal, JKB-119 does not show significant opioid receptor antagonism.", "role": "user" }, { "content": "Nalmefene shows opioid receptor antagonism, binds the μ-opioid receptor (MOR1) and modulates opioidergic transmission in the CNS.", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nBiophysical Fragment Screening of the β1-Adrenergic Receptor: Identification of High Affinity Arylpiperazine Leads Using Structure-Based Drug Design. Biophysical fragment screening of a thermostabilized β1-adrenergic receptor (β1AR) using surface plasmon resonance (SPR) enabled the identification of moderate affinity, high ligand efficiency (LE) arylpiperazine hits 7 and 8. Subsequent hit to lead follow-up confirmed the activity of the chemotype, and a structure-based design approach using protein-ligand crystal structures of the β1AR resulted in the identification of several fragments that bound with higher affinity, including indole 19 and quinoline 20. In the first example of GPCR crystallography with ligands derived from fragment screening, structures of the stabilized β1AR complexed with 19 and 20 were determined at resolutions of 2.8 and 2.7 Å, respectively.", "role": "user" }, { "content": "{\"Chemical\": [\"Arylpiperazine\", \"arylpiperazine\", \"quinoline\", \"indole\"]}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Genomic DNA Sequences from Mastodon and Woolly Mammoth Reveal Deep Speciation of Forest and Savanna Elephants\nArticle:\nAbstract:\nTo elucidate the history of living and extinct elephantids, we generated 39, 763 bp of aligned nuclear DNA sequence across 375 loci for African savanna elephant, African forest elephant, Asian elephant, the extinct American mastodon, and the woolly mammoth. Our data establish that the Asian elephant is the closest living relative of the extinct mammoth in the nuclear genome, extending previous findings from mitochondrial DNA analyses. We also find that savanna and forest elephants, which some have argued are the same species, are as or more divergent in the nuclear genome as mammoths and Asian elephants, which are considered to be distinct genera, thus resolving a long-standing debate about the appropriate taxonomic classification of the African elephants. Finally, we document a much larger effective population size in forest elephants compared with the other elephantid taxa, likely reflecting species differences in ancient geographic structure and range and differences in life history traits such as variance in male reproductive success.\nIntroduction:\nThe technology for sequencing DNA from extinct species such as mastodons( genus Mammut) and mammoths( genus Mammuthus) provides a powerful tool for elucidating the phylogeny of the Elephantidae, a family that originated in the Miocene and that includes Asian elephants( genus Elephas), African elephants( genus Loxodonta), and extinct mammoths[1]–[8]. In the highest resolution study to date, complete mitochondrial DNA( mtDNA) genomes from three elephantid genera were compared to the mastodon outgroup. The mtDNA analysis suggested that mammoths and Asian elephants form a clade with an estimated genetic divergence time of 5. 8–7. 8 million years ago( Mya), while African elephants diverged from an earlier common ancestor 6. 6–8. 8 Mya[8]. However, mtDNA represents just a single locus in the genome and need not represent the true species phylogeny since a single gene tree can differ from the consensus species tree of the taxa in question[9]–[11]. Generalizing about species relationships based on mtDNA alone is especially problematic for the Elephantidae because their core social groups( “herds”) are matrilocal, with females rarely, if ever, dispersing across groups[12]. This results in mtDNA genealogies in both African[13],[14] and Asian elephants[15] that exhibit deeper divergence and/or different phylogeographic patterns than the nuclear genome. These observed discrepancies between the phylogeographic patterns of nuclear and mtDNA sequences have led to a debate about the appropriate taxonomic status of African elephants. Most researchers have argued, based on morphology and nuclear DNA markers, that forest( Loxodonta cyclotis) and savanna( Loxodonta africana) elephants should be considered separate species[13],[16]–[19]. However, this notion has been contested[20] based on mtDNA patterns, which reveal some haplogroups with coalescent times of less than half a million years[21] that are shared across forest and savanna elephants, indicating relatively recent gene flow among the ancestors of these taxa. Taxonomies for African elephants based on mtDNA phylogeographic patterns have suggested anywhere from one to four species[20],[22],[23], whereas analysis of morphology and nuclear data sets has suggested two species[13],[16]–[19]. The study of large amounts of nuclear DNA sequences has the potential to resolve elephantid phylogeny, but due to technical challenges associated with obtaining homologous data sets from fossil DNA, no sufficiently large nuclear DNA data set has been published to date. Although a draft genome is available for woolly mammoth( Mammuthus primigenius)[5] and savanna elephant( loxAfr; http://www. broadinstitute. org/ftp/pub/assemblies/mammals/elephant/), comparative sequence data are lacking for Asian( Elephas maximus) and forest elephant, as well as for a suitable outgroup like the American mastodon( Mammut americanum). Using a combination of next generation sequencing and targeted multiplex PCR, we obtained the first substantial nuclear data set for comparing these species.\nDiscussion:\nOur study of the extant elephantids provides support for the proposed classification of the Elephantidae by Shoshani and Tassy, which divides them into the tribe Elephantini( including Elephas—the Asian elephant and fossil relatives—and the extinct mammoths Mammuthus) and the tribe Loxodontini( consisting of Loxodonta: African forest and savanna elephants and extinct relatives)[36]. This classification is at odds with previous suggestions that the extinct mammoths may have been more closely related to African than to Asian elephants[37]. Our study also infers a strikingly deep population divergence time between forest and savanna elephant, supporting morphological and genetic studies that have classified forest and savanna elephants as distinct species[13],[16]–. The finding of deep nuclear divergence is important in light of findings from mtDNA, which indicate that the F-haplogroup is shared between some forest and savanna elephants, implying a common maternal ancestor within the last half million years[21]. The incongruent patterns between the nuclear genome and mtDNA( “cytonuclear dissociation”) have been hypothesized to be related to the matrilocal behavior of elephantids, whereby males disperse from core social groups( “herds”) but females do not[13],[38]. If forest elephant female herds experienced repeated waves of migration from dominant savanna bulls, displacing more and more of the nuclear gene pool in each wave, this could explain why today there are some savanna herds that have mtDNA that is characteristic of forest elephants but little or no trace of forest DNA in the nuclear genome[13],[14],[39],[40]. In the future, it may be possible to distinguish between models of a single ancient population split between forest and savanna elephants, or an even older split with longer drawn out gene flow, by applying methods like Isolation and Migration( IM) models to data sets including more individuals[41]. Our present data do not permit such analysis, however, as IM requires multiple samples from each taxon to have statistical power, and we only have 1–2 samples from each taxon. Our study also documents the highly variable population sizes across recent elephantid taxa and in particular indicates that the recent effective population size of forest elephants in the nuclear genome( NF) has been significantly larger than those of the other elephantids( NS, NA, and NM)( Table 5)[13],[17],[19]. This is not likely due to the “out of Africa” migration of the ancestors of mammoths and Asian elephants as these events occurred several Mya[35], and any loss of diversity due to founder effects would have been expected to be offset by subsequent accumulation of new mutations in the populations. The high effective population size in forest elephants could reflect a history of separation of populations into distinct isolated tropical forest refugia during glacial cycles[33], which would have been a mechanism by which ancestral genetic diversity could have been preserved before the population subsequently remixed[1],[2],[23]. A Pleistocene isolation followed by remixing would also be consistent with the patterns observed in Asian elephants, which carry two deep mtDNA clades and where there is intermediate nuclear diversity. Intriguingly, our estimate of recent forest effective population size is on the same order as the ancestral population sizes( NFS, NAM, and NLox-Eur)( Table 5), providing some support for the hypothesis that forest elephant population parameters today may be typical of the ancestral populations( a caveat, however, is that MCMCcoal may overestimate ancestral population sizes since unmodeled sources of variation across loci may inflate estimates of ancestral population size). An alternative hypothesis that seems plausible is that the large differences in intra-species genetic diversity across taxa could reflect differences in the variance of male reproductive success[42]( more male competition in mammoth and savanna elephant than among forest elephants, with the Asian elephant being intermediate[43]). The results of this study are finally intriguing in light of fossil evidence that forest and savanna lineages of Loxodonta may have been geographically isolated until recently. The predominant elephant species in the fossil record of the African savannas for most of the Pliocene and Pleistocene belonged to the genus Elephas[30],[34],[35]. Some authors have suggested that the geographic range of Loxodonta in the African savannas may have been circumscribed by Elephas, until the latter disappeared from Africa towards the Late Pleistocene[30],[34],[35]. We hypothesize that the widespread distribution of Elephas in Africa may have created an isolation barrier that separated savanna and forest elephants, so that gene flow became common only much later, contributing to the patterns observed in mtDNA. Further insight into the dynamics of forest-savanna elephant interaction will be possible once more samples are analyzed from all the taxa, and high-quality whole genome sequences of forest and savanna elephants are available and can be compared with sequences of Asian elephants, mammoths, and mastodons.", "role": "user" }, { "content": "The living elephants are the last survivors of a once highly successful mammalian order , the Proboscidea , which includes extinct species such as the iconic woolly mammoth ( Mammuthus primigenius ) and the American mastodon ( Mammut americanum ) . Despite numerous studies , the phylogenetic relationships of the modern elephants to the woolly mammoth , as well as the taxonomic status of the African elephants of the genus Loxodonta , remain controversial . This is in large part due to the fact that both the woolly mammoth and the American mastodon ( the closest outgroup to elephants and mammoths available for genetic studies ) are extinct , posing considerable technical hurdles for comparative genetic analysis . We have used a combination of modern DNA sequencing and targeted PCR amplification to obtain a large data set for comparing American mastodon , woolly mammoth , Asian elephant , African savanna elephant , and African forest elephant . We unequivocally establish that the Asian elephant is the sister species to the woolly mammoth . A surprising finding from our study is that the divergence of African savanna and forest elephants—which some have argued to be two populations of the same species—is about as ancient as the divergence of Asian elephants and mammoths . Given their ancient divergence , we conclude that African savanna and forest elephants should be classified as two distinct species .", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nThe Arabidopsis Nucleosome Remodeler DDM1 Allows DNA Methyltransferases to Access H1-Containing Heterochromatin. Nucleosome remodelers of the DDM1/Lsh family are required for DNA methylation of transposable elements, but the reason for this is unknown. How DDM1 interacts with other methylation pathways, such as small-RNA-directed DNA methylation (RdDM), which is thought to mediate plant asymmetric methylation through DRM enzymes, is also unclear. Here, we show that most asymmetric methylation is facilitated by DDM1 and mediated by the methyltransferase CMT2 separately from RdDM. We find that heterochromatic sequences preferentially require DDM1 for DNA methylation and that this preference depends on linker histone H1. RdDM is instead inhibited by heterochromatin and absolutely requires the nucleosome remodeler DRD1. Together, DDM1 and RdDM mediate nearly all transposon methylation and collaborate to repress transposition and regulate the methylation and expression of genes. Our results indicate that DDM1 provides DNA methyltransferases access to H1-containing heterochromatin to allow stable silencing of transposable elements in cooperation with the RdDM pathway.", "role": "user" }, { "content": "{\"Chemical\": []}", "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: The purpose of this paper is to solve the problem of data-\n\nKeywords: generative low-bitwidth data free quantization\n\nDataset descriptions:\nAQUA-RAT: Algebra Question Answering with Rationales (AQUA-RAT) is a dataset that contains algebraic word problems with rationales. The dataset consists of about 100,000 algebraic word problems with natural language rationales.\nMathQA: MathQA significantly enhances the AQuA dataset with fully-specified operational programs.\nLS3D-W: A 3D facial landmark dataset of around 230,000 images.\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).\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.\nObstacle Tower: Obstacle Tower is a high fidelity, 3D, 3rd person, procedurally generated environment for reinforcement learning. An agent playing Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal.\n\nOptions: A: AQUA-RAT B: MathQA C: LS3D-W D: CIFAR-10 E: ImageNet F: Obstacle Tower", "role": "user" }, { "content": "[\"CIFAR-10\", \"ImageNet\"]", "role": "assistant" } ]

[ { "content": "Based on the following biomedical documents, answer the question with either yes or no.\n\nQuestion: Do circRNAs remain untranslated?\n\nContext: We demonstrate that the circular RNA circ-Foxo3 was highly expressed in non-cancer cells and were associated with cell cycle progression\nEctopic expression of circ-Foxo3 repressed cell cycle progression by binding to the cell cycle proteins cyclin-dependent kinase 2 (also known as cell division protein kinase 2 or CDK2) and cyclin-dependent kinase inhibitor 1 (or p21), resulting in the formation of a ternary complex.\nMicroRNAs (miRNAs) are important post-transcriptional regulators of gene expression that act by direct base pairing to target sites within untranslated regions of messenger RNAs.\nWe further show that the testis-specific circRNA, sex-determining region Y (Sry), serves as a miR-138 sponge, suggesting that miRNA sponge effects achieved by circRNA formation are a general phenomenon. This study serves as the first, to our knowledge, functional analysis of a naturally expressed circRNA.\nNumerous circRNAs were specifically expressed at different lactation stages, and only 1,314 circRNAs were detected at both lactation stages.\nA significantly positive correlation was observed for the expression profiles of some circRNAs and their parent genes.\nThe resulting circRNA can be translated to generate functional proteins.\nIn total, 80 circRNAs were identified from these 4 genes; circRNAs from CSN1S1 had very high abundance, and 3 of them accounted for 36% of all the circRNAs expressed in the mammary gland on lactation d 90.\nA total of 4,804 and 4,048 circRNAs were identified in the cow mammary gland on d 90 and 250 postpartum, respectively, of which only 2,231 circRNAs were co-expressed at both lactation stages, suggesting high stage specificity in the circRNAs.\nArraystar circRNA Microarray Technology (KANGCHEN, Shanghai, China) was used to analyze the differential expression of circRNAs.\nThe aim of study was to identify circRNA expression in articular cartilage and to explore the function of chondrocyte extracellular matrix (ECM)-related circRNAs (circRNA-CER) in cartilage.\nWe also validated that P. falciparum produces circRNAs, which is notable given the lack of RNA interference in the organism, and discovered that a highly expressed, five-exon antisense RNA is poised to regulate P. falciparum gametocyte development 1 (PfGDV1), a gene required for early sexual commitment events.\nCircRNA expression pattern and circRNA-miRNA-mRNA network in the pathogenesis of nonalcoholic steatohepatitis.\nCircRNAs are abundantly expressed also in the hematopoietic compartment.", "role": "user" }, { "content": "no", "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:\nIodine-129 microdosing for protein and peptide drug development: erythropoietin as a case study. BACKGROUND: Microdosing is a technique for studying the behavior of compounds in vivo at 1/100th of the dose of a test substance calculated, based on animal data, to yield a pharmacologic effect. In microdosing, use is made of accelerator MS (AMS). In this study, we investigated whether (129) I-labeling of proteins with subsequent AMS measurements is a suitable method to perform microdose studies with therapeutic proteins. We used erythropoietin (EPO) as a case study. RESULTS: In an animal study with (129) I-labeled EPO in Han-Wistar rats, an increase of (129) I-EPO is observed after dose administration. The half-life was found to be 2 and 5.5 h for two different EPOs. These results are in accordance with expected values. CoNCLUSION: Although further research is required, (129) I-labeling of proteins seems a feasible method for AMS microdose studies with peptide and protein drugs, such as biosimilars.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Read this passage from a research paper and answer the question.\n\nContext: Figure 3 shows the effect of classifier-free guidance (Ho and Salimans, 2021) on a text-conditioned video model. Similar to what was observed in other work that used classifier-free guidance on text-conditioned image generation (Nichol et al., 2021) and class-conditioned image generation (Ho and Salimans, 2021; Dhariwal and Nichol, 2021), adding guidance increases the sample fidelity of each individual image and emphases the effect of the conditioning signal. Our goal with this work is to advance research on methods in generative modeling, and our methods have the potential to positively impact creative downstream applications. As with prior work in generative modeling, however, our methods have the potential for causing harmful impact and could enhance malicious or unethical uses of generative models, such as fake content generation, harassment, and misinformation spread, and thus we have decided not to release our models. Like all generative models, our models reflect the biases of their training datasets and thus may require curation to ensure fair results from sampling. In particular, our text-to-video models inherit the challenges faced by prior work on text-to-image models, and our future work will involve auditing for forms of social bias, similar to Buolamwini and Gebru (2018); Burns et al. (2018); Steed and Caliskan (2021); Cho et al. (2022) for image-to-text and image labeling models. We see our work as only a starting point for further investigation on video diffusion models and investigation into their societal implications, and we will aim to explore benchmark evaluations for social and cultural bias in the video generation setting and make the necessary research advances to address them.\n\nQuestion: What does it mean to perform better in Text-to-Video generation? Does it mean that generated videos are aligned well with the text description?", "role": "user" }, { "content": "The higher performance in Text-to-Video Generation requires not only excellent fidelity of video samples but also good handling of social bias in text-description given as a condition.", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Identification of the UBP1 Locus as a Critical Blood Pressure Determinant Using a Combination of Mouse and Human Genetics\nArticle:\nAbstract:\nHypertension is a major health problem of largely unknown genetic origins. To identify new genes responsible for hypertension, genetic analysis of recombinant inbred strains of mice followed by human association studies might prove powerful and was exploited in our current study. Using a set of 27 recombinant BXD strains of mice we identified a quantitative trait locus( QTL) for blood pressure( BP) on distal chromosome 9. The association analysis of markers encompassing the syntenic region on human chromosome 3 gave in an additive genetic model the strongest association for rs17030583 C/T and rs2291897 G/A, located within the UBP1 locus, with systolic and diastolic BP( rs17030583: 1. 3±0. 4 mmHg p<0. 001, 0. 8±0. 3 mmHg p = 0. 006, respectively and rs2291897: 1. 5±0. 4 mmHg p<0. 001, 0. 8±0. 3 mmHg p = 0. 003, respectively) in three separate studies. Our study, which underscores the marked complementarities of mouse and human genetic approaches, identifies the UBP1 locus as a critical blood pressure determinant. UBP1 plays a role in cholesterol and steroid metabolism via the transcriptional activation of CYP11A, the rate-limiting enzyme in pregnenolone and aldosterone biosynthesis. We suggest that UBP1 and its functional partners are components of a network controlling blood pressure.\nIntroduction:\nElevated arterial blood pressure is a major health problem accounting for a large proportion of cardiovascular morbidity and mortality world-wide. It is estimated that over one billion people are hypertensive, and its prevalence is continuously increasing[1]. Elevated BP is a major risk factor for the development of cardiovascular disease, including coronary heart disease, congestive heart failure, ischemic and hemorrhagic stroke, renal failure, and peripheral arterial disease[2]. BP is modulated by both genetic and environmental factors, including NaCl intake, alcohol consumption, physical inactivity, and stress. Several genes responsible for rare Mendelian forms of hypertension have been identified( CYP11B1, CYP11B2, HSD11B1, MR, SCNN1B, SCNN1G, WNK1, WNK4) and shown to play a significant role in the renal control of BP[3]–[9]. In addition, rare independent mutations in salt handling genes SLC2A3, SLC12A1 and KCNJ1 have been shown to reduce BP and protect from the development of hypertension[10]. However, common genetic variants that are associated with BP remain to be identified. Using a set of recombinant BXD strains of mice we identified a quantitative trait locus for blood pressure. To validate the role of this QTL in blood pressure control in man we used an association analysis of markers encompassing the syntenic region in humans and confirmed UBP1 locus as a critical blood pressure determinant.\nDiscussion:\nWe have mapped an interval on chromosome 9 between 113. 2 and 113. 9 Mb as contributing to the BP variation in a BXD panel of mice. The relatively small size of this chromosomal region can be explained by a high frequency of recombination achieved in the recombinant inbred mouse lines. The identified mouse chromosome 9 band F3( 9F3) region is syntenic to rat chromosome 8q32 to which a BP QTL was previously mapped[23]. The corresponding human chromosome band is 3p22. 3, remarkably enough also within a known susceptibility locus for arterial pulse pressure—the difference between systolic BP and diastolic BP[24]. These data indicate that in three species an orthologous region modulates BP. Our SNP analysis of the syntenic region in humans( human chromosome 3, 33. 2–33. 9 Mb region) revealed that rs17030583, UBP1, intron 11, C/T and rs2291897, FBXL2, intron 11, G/A gave the most significant P values for an association with BP levels under the additive model in the EUGENE2 Study. The FBXL2/UBP1 gene locus( Figure 3) belongs to a haploblock including also other genes( CLASP2, PDC61P, SUSD5). Therefore, we genotyped in the METSIM cohort those SNPs of CLASP2( rs9841066), PDC61P( rs9311032, rs9858195), and SUSD5( rs4678778, rs9836433, rs10222597) which gave the most significant P values in the EUGENE2 Study. We did not find any significant associations of these SNPs either with systolic or diastolic BPs in the METSIM Study suggesting that the FBXL2/UBP1 locus represents the best association signal with systolic and diastolic BPs from that gene region. SNP rs2291897 is located on Chr 3( position 33394426) in intron 11 of FBXL2, and is almost in complete linkage disequilibrium( 99. 6%) with rs2272152 located 23 bp from the acceptor site of exon 4 of UBP1. Because we also found a significant association of rs17030583 of UBP1 with systolic BP it is likely that our findings in the haploblock are explained by a signal from the FBXL2/UBP1 region( linkage disequilibrium between rs2291897 and rs17030583 was 75% in the EUGENE2 Study). However, we cannot rule out the possibility that our findings are explained by another gene locus at linkage disequilibrium with the FBXL2/UBP1 region. It remains to be determined whether these SNPs are replicated in other population-based studies including individuals ≤55 years and whether these SNPs have functional consequences on UBP1 splicing and/or mRNA generation. Two recent meta-analyses did not report an association of these SNPs with high systolic or diastolic BPs[25],[26], which might be due to higher age range when compared to our study( <70 years in[25]; <85 years in[26]). We found a strong interaction of rs17030583 and rs2291897 with age on their effects on systolic BP, which might indicate that these associations are observed only in middle-aged and younger individuals. UBP1 regulates expression of CYP11A, the gene encoding the rate-limiting enzyme in steroidogenesis, and is expressed in placenta and adult adrenals[27]. An adrenal steroid biosynthesis alteration via CYP11A and the 3β-HSD2, CYP21, CYP11B2 cascade is hypothesized to lead to increased aldosterone secretion, expanded plasma volume, and hypertension. Furthermore, UBP1 is also expressed in mouse heart and aorta[28]( GEO profiles, www. ncbi. nlm. nih. gov/sites/entrez). However, the role of CYP11A, 3β-HSD2, CYP21 and CYP11B2 in human heart and aorta is a matter of debate[29],[30]. If UBP1 could also transactivate the CYP11A promoter in heart and aorta, UBP1 might drive the cardiac remodeling via control of aldosterone levels. The closest UBP1 gene homologue, TFCP2L1( also known as LBP-9), suppresses CYP11A transcriptional activity in placental cells[27] and LBP-9 gene-trapped mice die postnatally with a dramatically decreased expression of kidney salt handling genes or survive with a mild polyuria and an increased net electrolyte excretion[31]. The antagonistic actions of LBP-9 and UBP1 on the CYP11A expression suggests that these two genes could play a counterbalancing role in blood pressure control. Approaches aimed at modulation of UBP1 activity and targeting the UBP1 driven genes could represent novel therapeutic approaches to treat hypertension and eventually other cardiovascular diseases.", "role": "user" }, { "content": "To identify new genes responsible for hypertension , a major health problem , we performed a genetic analysis of recombinant inbred strains of mice followed by human association studies . Using a set of 27 recombinant BXD strains of mice , we identified a quantitative trait locus for blood pressure ( BP ) on distal chromosome 9 encompassing the UBP1 gene locus . In three subsequent human genetic studies , the syntenic locus was shown to be associated with systolic and diastolic BP , identifying the UBP1 locus as a critical blood pressure determinant . UBP1 is a transcription factor , known to control the expression of CYP11A , the rate-limiting enzyme in pregnenolone and aldosterone biosynthesis , suggesting that it controls blood pressure via this pathway . Our study furthermore underscores the marked complementarities of mouse and human genetic approaches", "role": "assistant" } ]

[ { "content": "You will be presented with the full text of a scientific research paper. Write an abstract summarizing the key points. Your response should contain only the abstract without any other text.\n\nArticle text:\nthe @xmath4 dependence of the structure functions in deep inelastic scattering ( dis ) as well as in other related processes ( _ e.g. _ drell - yan ) can be described accurately within perturbative qcd ( pqcd ) up to nlo provided one confines calculations to the kinematical region of @xmath5 and bjorken @xmath2 : @xmath6 ( corresponding to high values of the invariant mass squared : @xmath7 ) . at the border of this kinematical region\nthe agreement between pqcd calculations and experiment is no longer accurate nor unambigous because of the increasing importance of non - perturbative ( np ) physics . at large @xmath2\nthe agreement with the data is known to improve by including power corrections @xcite . aside from parton model\nbased phenomenological interpretations , the presence of power corrections still constitutes a rather elusive problem for theory .\ncanonical methods such as the hard scattering factorization ( hsf ) or ope ( for a review see @xcite and references therein ) , are hampered by the large and hard - to - classify number of operators .\ncomparison with data does not allow yet to distinguish among different higher twist contributions ( see _ e.g. _ @xcite ) .\nmore recently the idea has been developed that a one to one correspondence can be defined between the dynamically generated higher twist terms and the ambiguities in the resummation of the asymptotic pqcd series , or renormalons ( @xcite and references therein ) .\nas for np methods , there seems to be indications from lattice studies that power corrections do surface though not seemingly directly related to renormalons @xcite .\na preliminary step in order to test recent developments is to explore whether , given the accuracy and kinematical coverage of present data , power corrections can be separated unambigously and their actual size determined , from nlo and higher order terms , and from a number of other non - qcd contributions . with the aim of achieving a clear - cut answer , we started our analysis from the most well known structure function , @xmath1 . \n? = ? [ cols=\"^,^,^,^\",options=\"header \" , ] we constructed moments , @xmath8 from the nmc , bcdms and slac data sets . differently from previous analyses , we set no lower limit on the final state invariant mass , thus extending the kinematical domain in @xmath2 up to @xmath9 and @xmath10\n. moments are more directly connected to ope , they can be calculated in principle using non - perturbative methods and , on the practical side , they are the only way to include data at large @xmath2 without getting into the complications of the resonance structure\n. we performed a fit of the following expression @xmath11 where the @xmath4 dependence of @xmath12 , @xmath13 being a given scale , was considered up to nlo .\nfurthermore , since we are interested in the large @xmath2 behavior , we restricted the analysis to the non singlet ( ns ) contribution therefore avoiding ambiguities associated with the gluon distribution .\nthe subtraction of the singlet contribution introduces some error .\nhowever , based on current parametrizations we estimated it to be @xmath14 of the total moment for @xmath15 and @xmath16 and to be less then @xmath17 for @xmath18 .\nfurther sources of systematic error arise from the extrapolation to regions where no data are available which constitute @xmath19 and @xmath20 of the whole kinematic domain contributing to @xmath21 at @xmath15 and @xmath18 , respectively , and from target mass corrections ( tmc ) which display an inverse power - like behavior and increase with @xmath3 @xcite . in order to be able to compare with previous extractions we will show here results obtained in the `` factorized '' approximation , _\ni.e. _ @xmath22 corresponding to @xmath23 etc . , where the @xmath3 dependence of the power corrections is included in the functions @xmath24 , @xmath25 ; @xmath26 and @xmath27 are the parameters to be determined by the fit , besides the pqcd ones ; no @xmath4 dependence is assumed for @xmath28 .\npower corrections of order higher than @xmath29 are found to be negligible for @xmath30 . in order to compare with similar recent extractions @xcite\n, we set in eqs.([twist ] ) and ( [ fac ] ) : @xmath31 , and @xmath32 .\nour results can be also anti - mellin transformed to reconstruct @xmath33 , by using the properties of the mellin transforms .\nsince the @xmath3 dependence found in different models is rather simple , no polynomial technique was found to be necessary at this level .\nour results for the parameters @xmath0 and @xmath26 are given in table [ results ] and compared with the ones obtained in previous extractions . since recent analyses used directly @xmath33 , giving @xmath2-dependent power correction coefficients , @xmath34 , we calculated the values of @xmath26 shown in the table by performing mellin transforms of @xmath34 , times the correspondong pqcd structure functions parametrizations .\nthe form @xmath35 , transforming into @xmath36 at large @xmath2 was used consistently .\nthe first line of table [ results ] was included in order to show the highly enhanced accuracy provided by the nmc , bcdms and slac set of data where it is now possible to perform a more careful extraction of power corrections .\nan anti - correlation clearly emerges from our fits between the parameters of pqcd , _ e.g. _\n@xmath37 , and the coefficients of the power corrections .\nwe studied this correlation ; details of our study are presented in @xcite . here\nit suffices to say that it originates from a region in @xmath4 ( @xmath38 ) where neither the lo , simply logarithmic pqcd behavior , nor the pure power correction terms are dominant , whereas a mixture of higher order and @xmath39 terms are simultaneously present .\nwe dealt with this problem by extracting @xmath37 using only data at @xmath40 and by including lower values of @xmath4 stepwise in the fit , at the fixed value of @xmath37 .\nthe value of @xmath37 we found is consistent with @xmath41 mev _\ni.e. _ the value previously found in @xcite .\nthe results presented in table [ results ] are therefore clear - cut in predicting that , for similar values of @xmath37 , we find a contribution from power corrections which is about _\ntwice _ as large as in the previous qcd analysis .\nwe seem however to find a contradiction with the analysis using neutrino data in that these show both a larger value of @xmath37 and a slightly enhanced value of @xmath26 . by including the @xmath29 term and by using our approach of lowering the @xmath4 threshold from above\n, we found out that @xmath42 within error bars until one reaches the value of @xmath43 .\nfinally , @xmath26 and @xmath27 are also anti - correlated . by including in the fit both parameters , @xmath26 and @xmath27 with the lowest allowed threshold , @xmath44 , we are able to fit the data with negative values of @xmath27 and @xmath45 , _ i.e. _ consistent with the value obtained at a higher threshold .\nwe would like to point out however that due to the anti - correlation between the two parameters , by performing a general fit to the data regardless of @xmath4 `` thresholds '' , large positive values of @xmath27 and small values of @xmath26 can be also found @xcite ; such results are to be interpreted as a manifestation of the anti - correlation between parameters .\n-.6truecm with a firm understanding of the different @xmath4 dependent contributions at intermediate and low @xmath4 , one can subsequently investigate the renormalon hypothesis .\nwe present here results of our study of the @xmath3-dependence of the coefficient of the @xmath39 term , @xmath46 , in eq.([fac ] ) . in figure 1\nwe repeated our fits using the forms : @xmath47 , @xmath48 , corresponding to the dominance of two - quark and four - quark higher twist diagrams , respectively , in _\ne.g. _ hsf models and we compared them to fits using the @xmath3-dependence predicted by renormalon calculations ( for details see references [ 9 ] and [ 10 ] in @xcite ) .\nsince in all predictions the @xmath3-dependent term is factored out from an unknown constant term , one can discriminate `` models '' based on the `` flatness '' of the @xmath3 behavior extracted from the data . from figure 1 one can see that the renormalon model gives clearly a better interpretation than the widely used assumption , @xmath35 .\nour initial study of power corrections in dis is meant to be an exploratory one centered around two points : we first addressed the question of whether there is at all a direct and clear evidence of power corrections in the data , and if their actual magnitude can be extracted ; we then moved on to a phenomeonological study of their nature , namely whether they can be associated to long distance features of pqcd ( renormalon models ) or if other dynamical mechanisms pertinent to dis only , such as final state rescatterings should be taken into account .\nour main conclusions on the first part are that indeed power corrections can be separated out from present data by using an approach in which different portions of the @xmath4 domain ( proceeding from high to low @xmath4 values ) are analyzed separetely .\nthe magnitude of the @xmath49 coefficient is @xmath50 , which will need to be systematically compared with power corrections extracted from other reactions in further investigations , to test the presence of a universal scale .\nan important outcome of our study is also that , within the present accuracy and kinematical coverage of the data , meaningful results should be presented including the correlation between the different parameters of the fit .\nour extractions seem to be consistent with renormalon calculations\n. more detailed knowledge on the nature of power corrections can be sought in principle by using nuclear targets . by assuming the validity of ia , _\ni.e. _ by disregarding nucleon rescattering effects , one obtains a factorization of the @xmath51 and @xmath4 dependences of the moments @xcite @xmath52 deviations from such a factorization would correspond to to a breakdown of ia and they would therefore signal the presence of rescattering effects . as shown in @xcite\npresent data on nuclear targets are not accurate enough to observe any feature in the ratio of moments and they support the ia hypothesis .\nmore detailed studies , together with higher accuracy nuclear dis data might be able to reveal an underlying structure @xcite . at present , by adopting the factorized form , eq.([moma ] ) , we can extract the value of @xmath26 for a nucleon .\nresults are presented in figure 2 and compared with the proton values . from the figure\nwe can see that the proton and nucleon results are consitent with one another , _\ni.e. _ no difference is seen in the neutron contribution .\ni thank the institute of nuclear and particle physics at the university of virginia for support and the argonne national laboratory nuclear theory group where part of this contribution was written .\ni also thank lech mankiewicz for discussions .\n9 m. arneodo _\n_ , nucl.phys\n. * b483 * ( 1997 ) 3 , _ ibid _ * b364 * ( 1995 ) 107 . m. virchaux and a. milzstajn , phys.lett . *\nb274 * ( 1992 ) 221 .\nqiu and g. sterman , nucl.phys . *\nb353 * ( 1991 ) 105 ; _ ibid _ p.137 .\net al . _ ,\n* b312 * ( 1993 ) 351 .\nbraun , nordita-97 - 53-p , apr 1997 ( hep - ph/9708386 ) ; m. beneke , v.m .\nbraun , n. kivel , phys .\n* b404 * ( 1997 ) 315 . c. parrinello , these proceedings .\n_ , z.phys . * c41 * ( 1988 ) 247 ; phys . rev .\n* d40 * ( 1989 ) 2184 .\ns. liuti , _ in preparation_. m.r . pennington and g.g .\nross , nucl .\nb179 * ( 1981 ) 324 . l.w .\net al _ phys.lett .\n* b282 * ( 1992 ) 475 ; l.w .\nwhitlow , ph.d .\nthesis , slac - report 357 ( 1990 ) .\nseligman , phys.rev.lett .\n* 79 * ( 1997 ) 1213 .\nk. varvell et al .\n* c36 * ( 1987 ) 1 .\ni. niculescu , c. keppel , s. liuti and g. niculescu , submitted for publication in phys.rev . * d*. c.d .\ncothran , d.b .\nday , s. liuti , phys.lett . *\nb421 * ( 1998 ) 46 .", "role": "user" }, { "content": "by performing an analysis in moment space using high statistics dis world data , we extract the values of both the qcd parameter @xmath0 up to nlo and of the power corrections to the proton structure function , @xmath1 . at variance with previous analyses , \n the use of moments allows us to extend the kinematical range to larger values of @xmath2 , where we find that power corrections are quantitatively more important . \n our results are consistent with the @xmath3 dependence predicted by ir renormalon calculations . \n we discuss preliminary results on nuclear targets with the intent of illustrating a possible strategy to disentangle power corrections ascribed to ir renormalons from the ones generated dynamically _ \n e.g. _ from rescattering in the final state . \n the latter appear to be modified in nuclear targets . \n inpp - uva-98 - 06 + * a systematic study of power corrections from world deep inelastic scattering measurements . \n * + + * abstract * by performing an analysis in moment space using high statistics dis world data , we extract the values of both the qcd parameter @xmath0 up to nlo and of the power corrections to the proton structure function , @xmath1 . at variance with previous analyses , \n the use of moments allows us to extend the kinematical range to larger values of @xmath2 , where we find that power corrections are quantitatively more important . \n our results are consistent with the @xmath3 dependence predicted by ir renormalon calculations . \n we discuss preliminary results on nuclear targets with the intent of illustrating a possible strategy to disentangle power corrections ascribed to ir renormalons from the ones generated dynamically _ \n e.g. _ from rescattering in the final state . \n the latter appear to be modified in nuclear targets . \n talk given at + + montpellier , july 2nd-8th , 1998 + +", "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 will write a brief, single-sentence summary of your paper.\n\nKeywords: question generation text paragraph-level\n\nDataset descriptions:\nKuzushiji-Kanji: Kuzushiji-Kanji is an imbalanced dataset of total 3832 Kanji characters (64x64 grayscale, 140,426 images), ranging from 1,766 examples to only a single example per class. Kuzushiji is a Japanese cursive writing style.\nSQuAD: The Stanford Question Answering Dataset (SQuAD) is a collection of question-answer pairs derived from Wikipedia articles. In SQuAD, the correct answers of questions can be any sequence of tokens in the given text.\nMEDIQA-AnS: The first summarization collection containing question-driven summaries of answers to consumer health questions. This dataset can be used to evaluate single or multi-document summaries generated by algorithms using extractive or abstractive approaches.\nXSum: The Extreme Summarization (XSum) dataset is a dataset for evaluation of abstractive single-document summarization systems. The goal is to create a short, one-sentence new summary answering the question “What is the article about?”.\nConvAI2: The ConvAI2 NeurIPS competition aimed at finding approaches to creating high-quality dialogue agents capable of meaningful open domain conversation. The ConvAI2 dataset for training models is based on the PERSONA-CHAT dataset.\nNewsQA: The NewsQA dataset is a crowd-sourced machine reading comprehension dataset of 120,000 question-answer pairs. Documents are CNN news articles.\n\nOptions: A: Kuzushiji-Kanji B: SQuAD C: MEDIQA-AnS D: XSum E: ConvAI2 F: NewsQA", "role": "user" }, { "content": "[\"SQuAD\", \"NewsQA\"]", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nDMAP1 is an essential regulator of ATM activity and function. The hereditary autosomal recessive disease ataxia telangiectasia (A-T) is caused by mutation in the DNA damage kinase ATM. ATM's main function is to orchestrate DNA repair, thereby maintaining genomic stability. ATM activity is increased in response to several stimuli, including ionising radiation (IR) and hypotonic stress. DNMT1-associated protein 1 (DMAP1) is a member of the TIP60-p400 histone acetyl transferase (HAT) complex, which acetylates histone H4 at lysine 16 (H4K16) to affect chromatin relaxation and modulate ATM activation. Here we demonstrate that DMAP1 is required for both modes of ATM activation. Knockdown of DMAP1 impaired IR-induced ATM activation and consequently resulted in radiosensitivity and impaired the G2/M checkpoint. Moreover, DMAP1 was also required for efficient ATM signalling in response to hypotonic stress. Overexpression of DMAP1 increased IR-induced ATM substrate phosphorylation, suggesting that DMAP1 function is rate limiting for ATM signalling. DMAP1 associated with TIP60-dependent HAT activity, and depletion of DMAP1 reduced H4K16 acetylation in response to DNA damage. Treatment with histone deacetylase inhibitors rescued IR-induced ATM signalling in Dmap1-depleted cells. These results suggest that DMAP1 is a critical regulator of ATM activity and function.Oncogene advance online publication, 14 January 2013; doi:10.1038/onc.2012.597.", "role": "user" }, { "content": "{\"Chemical\": [\"lysine\", \"acetyl\"]}", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Blockchain Applications for Industry 4.0 and Industrial IoT: A Review \nChapter Title: 2) SECURITY AND PRIVACY \n1. Abstract of Cited Paper (BIB001): Fog/edge computing has been proposed to be integrated with Internet of Things (IoT) to enable computing services devices deployed at network edge, aiming to improve the user’s experience and resilience of the services in case of failures. With the advantage of distributed architecture and close to end-users, fog/edge computing can provide faster response and greater quality of service for IoT applications. Thus, fog/edge computing-based IoT becomes future infrastructure on IoT development. To develop fog/edge computing-based IoT infrastructure, the architecture, enabling techniques, and issues related to IoT should be investigated first, and then the integration of fog/edge computing and IoT should be explored. To this end, this paper conducts a comprehensive overview of IoT with respect to system architecture, enabling technologies, security and privacy issues, and present the integration of fog/edge computing and IoT, and applications. Particularly, this paper first explores the relationship between cyber-physical systems and IoT, both of which play important roles in realizing an intelligent cyber-physical world. Then, existing architectures, enabling technologies, and security and privacy issues in IoT are presented to enhance the understanding of the state of the art IoT development. To investigate the fog/edge computing-based IoT, this paper also investigate the relationship between IoT and fog/edge computing, and discuss issues in fog/edge computing-based IoT. Finally, several applications, including the smart grid, smart transportation, and smart cities, are presented to demonstrate how fog/edge computing-based IoT to be implemented in real-world applications. \n2. Abstract of Cited Paper (BIB002): As the most successful cryptocurrency to date, Bitcoin constitutes a target of choice for attackers. While many attack vectors have already been uncovered, one important vector has been left out though: attacking the currency via the Internet routing infrastructure itself. Indeed, by manipulating routing advertisements (BGP hijacks) or by naturally intercepting traffic, Autonomous Systems (ASes) can intercept and manipulate a large fraction of Bitcoin traffic. ::: This paper presents the first taxonomy of routing attacks and their impact on Bitcoin, considering both small-scale attacks, targeting individual nodes, and large-scale attacks, targeting the network as a whole. While challenging, we show that two key properties make routing attacks practical: (i) the efficiency of routing manipulation; and (ii) the significant centralization of Bitcoin in terms of mining and routing. Specifically, we find that any network attacker can hijack few (<100) BGP prefixes to isolate ~50% of the mining power---even when considering that mining pools are heavily multi-homed. We also show that on-path network attackers can considerably slow down block propagation by interfering with few key Bitcoin messages. ::: We demonstrate the feasibility of each attack against the deployed Bitcoin software. We also quantify their effectiveness on the current Bitcoin topology using data collected from a Bitcoin supernode combined with BGP routing data. ::: The potential damage to Bitcoin is worrying. By isolating parts of the network or delaying block propagation, attackers can cause a significant amount of mining power to be wasted, leading to revenue losses and enabling a wide range of exploits such as double spending. To prevent such effects in practice, we provide both short and long-term countermeasures, some of which can be deployed immediately. \n3. Abstract of Cited Paper (BIB003): Since its inception, the blockchain technology has shown promising application prospects. From the initial cryptocurrency to the current smart contract, blockchain has been applied to many fields. Although there are some studies on the security and privacy issues of blockchain, there lacks a systematic examination on the security of blockchain systems. In this paper, we conduct a systematic study on the security threats to blockchain and survey the corresponding real attacks by examining popular blockchain systems. We also review the security enhancement solutions for blockchain, which could be used in the development of various blockchain systems, and suggest some future directions to stir research efforts into this area. \n4. Abstract of Cited Paper (BIB004): The inherent immutability offered by Blockchains (BC) ensures resilience against modification or removal of the stored data. In large scale networks like the Internet of Things (IoT), however, this feature significantly increases BC storage size and raises privacy concerns. In this paper, we propose a Memory Optimized and Flexible BC (MOF-BC) that enables the IoT users and service providers to remove or summarize their transactions and age their data and thus exercise their “right to be forgotten”. To increase privacy, a user may employ multiple keys for different transactions. However, to facilitate removal of the stored transactions in the future, all keys would need to be stored which complicates key management and storage. MOF-BC introduces the notion of a Generator Verifier (GV) which is a signed hash of a Generator Verifier Secret (GVS). The GV changes for each transaction to provide privacy yet is signed by a unique key, thus minimizing the information that needs to be stored. A flexible transaction fee model and a reward mechanism is proposed to incentivize users to participate in optimizing memory consumption. We propose MOF-BC as a generalized solution, which can be implemented on top of any existing or future BC instantiation. Qualitative security and privacy analysis demonstrates that MOF-BC is resilient against several security attacks. Evaluation results show that MOF-BC decreases BC memory consumption by up to 25% and the cost incurred by users by more than two orders of magnitude compared to conventional BC instantiations. ::: ::: Keywords ::: Blockchain; Auditing; Privacy; Internet of Things\n\nLiterature Review:", "role": "user" }, { "content": "IoT networks are already prone to various security attacks like replay attacks BIB002 and eavesdropping attacks BIB001 . Along with these security risks, blockchains bring their own set of security vulnerabilities. Some of the known security vulnerabilities in blockchain technology are smart contract program vulnerabilities BIB004 , message hijack BIB003 , etc. Privacy leakage is another concern in blockchains, as shown VOLUME 7, 2019 in (e.g. there is a risk of potential privacy breach with transaction data being stored on the blockchain BIB005 ).", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nA calibrated human Y-chromosomal phylogeny based on resequencing. We have identified variants present in high-coverage complete sequences of 36 diverse human Y chromosomes from Africa, Europe, South Asia, East Asia, and the Americas, representing eight major haplogroups. After restricting our analysis to 8.97 Mb of the unique male-specific Y sequence, we identified 6662 high-confidence variants, including single-nucleotide polymorphisms (SNPs), multi-nucleotide polymorphisms (MNPs), and indels. We constructed phylogenetic trees using these variants, or subsets of them, and recapitulated the known structure of the tree. Assuming a male mutation rate of 1 × 10(-9) per base pair per year, the time depth of the tree (haplogroups A3-R) was ~101,000-115,000 yr, and the lineages found outside Africa dated to 57,000-74,000 yr, both as expected. In addition, we dated a striking Paleolithic male lineage expansion to 41,000-52,000 yr ago and the node representing the major European Y lineage, R1b, to 4000-13,000 yr ago, supporting a Neolithic origin for these modern European Y chromosomes. In all, we provide a nearly 10-fold increase in the number of Y markers with phylogenetic information, and novel historical insights derived from placing them on a calibrated phylogenetic tree.", "role": "user" }, { "content": "{\"Chemical\": []}", "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:\nA randomized clinical trial of repetitive transcranial magnetic stimulation in patients with refractory epilepsy\nAbstract 1:\nTo study the antiepileptic effects of rTMS in patients with refractory epilepsy and malformations of cortical development in a r and omized , double‐blind , sham‐controlled trial\n\n\nTitle 2:\nThe impact of outcome reporting bias in randomised controlled trials on a cohort of systematic reviews\nAbstract 2:\nObjective To examine the prevalence of outcome reporting bias — the selection for publication of a subset of the original recorded outcome variables on the basis of the results — and its impact on Cochrane review s. Design A nine point classification system for missing outcome data in r and omised trials was developed and applied to the trials assessed in a large , unselected cohort of Cochrane systematic review s. Research ers who conducted the trials were contacted and the reason sought for the non-reporting of data . A sensitivity analysis was undertaken to assess the impact of outcome reporting bias on review s that included a single meta- analysis of the review primary outcome . Results More than half ( 157/283 ( 55 % ) ) the review s did not include full data for the review primary outcome of interest from all eligible trials . The median amount of review outcome data missing for any reason was 10 % , whereas 50 % or more of the potential data were missing in 70 ( 25 % ) review s. It was clear from the publications for 155 ( 6 % ) of the 2486 assessable trials that the research ers had measured and analysed the review primary outcome but did not report or only partially reported the results . For reports that did not mention the review primary outcome , our classification regarding the presence of outcome reporting bias was shown to have a sensitivity of 88 % ( 95 % CI 65 % to 100 % ) and specificity of 80 % ( 95 % CI 69 % to 90 % ) on the basis of responses from 62 trialists . A third of Cochrane review s ( 96/283 ( 34 % ) ) contained at least one trial with high suspicion of outcome reporting bias for the review primary outcome . In a sensitivity analysis undertaken for 81 review s with a single meta- analysis of the primary outcome of interest , the treatment effect estimate was reduced by 20 % or more in 19 ( 23 % ) . Of the 42 meta-analyses with a statistically significant result only , eight ( 19 % ) became non-significant after adjustment for outcome reporting bias and 11 ( 26 % ) would have overestimated the treatment effect by 20 % or more . Conclusions Outcome reporting bias is an under-recognised problem that affects the conclusions in a substantial proportion of Cochrane review s. Individuals conducting systematic review s need to address explicitly the issue of missing outcome data for their review to be considered a reliable source of evidence . Extra care is required during data extraction , review ers should identify when a trial reports that an outcome was measured but no results were reported or events observed , and contact with trialists should be encouraged\n\n\nTitle 3:\nTheta Burst Stimulation of the Human Motor Cortex\nAbstract 3:\nIt has been 30 years since the discovery that repeated electrical stimulation of neural pathways can lead to long-term potentiation in hippocampal slices . With its relevance to processes such as learning and memory , the technique has produced a vast literature on mechanisms of synaptic plasticity in animal models . To date , the most promising method for transferring these methods to humans is repetitive transcranial magnetic stimulation ( rTMS ) , a noninvasive method of stimulating neural pathways in the brain of conscious subjects through the intact scalp . However , effects on synaptic plasticity reported are often weak , highly variable between individuals , and rarely last longer than 30 min . Here we describe a very rapid method of conditioning the human motor cortex using rTMS that produces a controllable , consistent , long-lasting , and powerful effect on motor cortex physiology and behavior after an application period of only 20 - 190\n\n\nTitle 4:\nSlow repetitive TMS for drug-resistant epilepsy: clinical and EEG findings of a placebo-controlled trial.\nAbstract 4:\nPURPOSE To assess the effectiveness of slow repetitive transcranial magnetic stimulation ( rTMS ) as an adjunctive treatment for drug-resistant epilepsy . METHODS Forty-three patients with drug-resistant epilepsy from eight Italian Centers underwent a r and omized , double-blind , sham-controlled , crossover study on the clinical and EEG effects of slow rTMS . The stimulus frequency was 0.3 Hz . One thous and stimuli per day were given at the resting motor threshold intensity for 5 consecutive days , with a round coil at the vertex . RESULTS \" Active \" rTMS was no better than placebo for seizure reduction . However , it decreased interictal EEG epileptiform abnormalities significantly ( p < 0.05 ) in one-third of the patients , which supports a detectable biologic effect . No correlation linked the rTMS effects on seizure frequency to syndrome or anatomic classification , seizure type , EEG changes , or resting motor threshold ( an index of motor cortex excitability ) . CONCLUSIONS Although the antiepileptic action was not significant ( p > 0.05 ) , the individual EEG reactivity to \" active \" rTMS may be encouraging for the development of more-powerful , noninvasive neuromodulatory strategies\n\n\nTitle 5:\nAntiepileptic effects of low-frequency repetitive transcranial magnetic stimulation by different stimulation durations and locations\nAbstract 5:\nOBJECTIVE To evaluate the antiepileptic effect of low-frequency rTMS ( repetitive transcranial magnetic stimulation ) in the patients with intractable epilepsy . METHODS We enrolled 35 patients with localization-related epilepsy who had experienced at least one complex partial seizure or a secondarily generalized seizure per week on a constant antiepileptic drug regimen over an 8-week period . rTMS was administered using a Rapid(2 ) magnetic stimulator with an air-cooled coil at 0.5Hz for 5 consecutive days at 100 % of rMT ( resting motor threshold ) . Patients were divided into a focal stimulation group with a localized epileptic focus , or a non-focal stimulation group with a non-localized or multifocal epileptic focus . These two groups were then r and omly subdivided into four subgroups depending on the total number of stimulations administered , i.e. , 3000 pulse and 1500 pulse subgroups . Weekly seizure frequencies were determined for 8 weeks before and after rTMS . To compare the number of interictal spikes before and after rTMS , EEG was recorded twice before ( 1st day ) and after rTMS ( 5th day ) . RESULTS Mean weekly seizure frequency was non-significantly decreased after rTMS ( 8.4 - ->6.8/week , -13.9 % ) . Longer stimulation subgroups ( 3000 pulses , -23.0 % ) tended to have fewer seizures than shorter stimulation subgroups ( 1500 pulses , -3.0 % ) , without statistical significance . TMS stimulation site and structural brain lesions did not influence seizure outcome . However , interictal spikes significantly decreased ( -54.9 % , P=0.012 ) after rTMS and they totally disappeared in 6 patients ( 17.1 % , 6/35 ) . CONCLUSIONS Low-frequency rTMS reduced interictal spikes , but its effect on seizure outcome was not significant . Focal stimulation for a longer duration tended to further reduce seizure frequency . SIGNIFICANCE These findings may help clinicians to further investigate the therapeutic potential of the rTMS for patients with intractable epilepsy\n\n\nTitle 6:\nCan epilepsies be improved by repetitive transcranial magnetic stimulation?--interim analysis of a controlled study.\nAbstract 6:\nPublisher Summary Based on the findings that the effects of repetitive transcranial magnetic stimulation ( rTMS ) last beyond the period of stimulation itself , therapeutical antiepileptic potential of low-frequency rTMS was hypothesized . This chapter presents an interim analysis of an ongoing placebo-controlled trial . The results are discussed on the bases of the existing rTMS literature regarding the treatment of epilepsies in humans . The results presented in this chapter are interim analyses of the first crossover placebo-controlled investigation on the antiepileptic efficacy of low-frequency rTMS . Although a significant difference to placebo could not be demonstrated in this patient group , the data seem to be in line with the results of the first open pilot study on nine patients who showed reduction in seizure frequency within a similar range over a 4-week period . The results were supplemented by a case report on a patient with focal dysplasia by another group : biweekly treatment with 100 stimuli at 0.5 Hz and 95 % motor threshold intensity using an unfocal coil placed over the area of dysplasia reduced seizure frequency by 70 % over a 4-weeks period of treatment\n\n\nTitle 7:\nLow-frequency repetitive transcranial magnetic stimulation for the treatment of refractory partial epilepsy: a controlled clinical study.\nAbstract 7:\nPURPOSE This study was design ed to evaluate the therapeutic effect of low-frequency repetitive transcranial magnetic stimulation ( rTMS ) on patients with refractory partial epilepsy . METHODS Sixty-four patients with refractory focal epilepsy were screened and 60 patients were r and omly divided into two groups by stimulation intensity : 90 % ( group 1 ) or 20 % ( group 2 ) of resting motor threshold ( rMT ) . Seizure frequency and interictal EEG epileptic discharges were compared between the baseline and follow-up periods . KEY FINDINGS Seizures significantly decreased following 2-weeks high intensity ( 90 % rMT ) rTMS treatment compared with baseline level ( p < 0.05 ) . rTMS also decreased interictal epilepsy discharges and improved the scales of Symptom Checklist-90 significantly ( p < 0.05 ) . Seizures and spikes in the follow-up period in the patients who received low intensity ( 20 % rMT ) rTMS did not show any difference compared with baseline data ( p > 0.05 , respectively ) . SIGNIFICANCE Low-frequency high intensity rTMS ( 90 % rMT ) delivered into the epileptogenic zone had a significant antiepileptic effect on patients with refractory partial seizures . rTMS treatment can also reduce the interictal epileptic discharge frequency and improve the psychological condition of these patients\n\n\nTitle 8:\nTranscranial magnetic stimulation for the treatment of seizures: A controlled study\nAbstract 8:\nObjective To perform a controlled trial of transcranial magnetic stimulation ( TMS ) . Methods Twenty-four patients with localization-related epilepsy were r and omized to blinded active or placebo stimulation . Weekly seizure frequency was compared for 8 weeks before and after 1 week of 1-Hz TMS for 15 minutes twice daily . Results When the 8-week baseline and post-stimulation periods were compared , active patients had a mean seizure frequency reduction of 0.045 ± 0.13 and sham-stimulated control subjects −0.004 ± 0.20 . Over 2 weeks , actively treated patients had a mean reduction in weekly seizure frequency of 0.16 ± 0.18 and sham-stimulated control subjects 0.01 ± 0.24 . Neither difference was significant . Conclusion The effect of TMS on seizure frequency was mild and short lived", "role": "user" }, { "content": "Adverse effects were uncommon among the studies and typically involved headache , dizziness , and tinnitus .\nThere is evidence that rTMS is safe and not associated with any adverse events , but given the variability in technique and outcome reporting that prevented meta- analysis , the evidence for efficacy of rTMS for seizure reduction is still lacking despite reasonable evidence that it is effective at reducing epileptiform discharges", "role": "assistant" } ]

[ { "content": "Answer the following question using the provided context. Only provide the answer without any additional text.\n\nQuestion: What can we measure with the TSA-Seq method?\nContext: Mapping 3D genome organization relative to nuclear compartments using TSA-Seq as a cytological ruler.\nTSA-Seq, a new mapping method capable of providing a \"cytological ruler\" for estimating mean chromosomal distances from nuclear speckles genome-wide and for predicting several Mbp chromosome trajectories between nuclear compartments without sophisticated computational modeling.", "role": "user" }, { "content": "TSA-Seq, a new mapping method capable of providing a \"cytological ruler\" for estimating mean chromosomal distances from nuclear speckles genome-wide and for predicting several Mbp chromosome trajectories between nuclear compartments without sophisticated computational modeling. Mapping 3D genome organization relative to nuclear compartments using TSA-Seq as a cytological ruler.", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Direct live imaging of cell–cell protein transfer by transient outer membrane fusion in Myxococcus xanthus\nArticle:\nAbstract:\nIn bacteria, multicellular behaviors are regulated by cell–cell signaling through the exchange of both diffusible and contact-dependent signals. In a multicellular context, Myxococcus cells can share outer membrane( OM) materials by an unknown mechanism involving the traAB genes and gliding motility. Using live imaging, we show for the first time that transient contacts between two cells are sufficient to transfer OM materials, proteins and lipids, at high efficiency. Transfer was associated with the formation of dynamic OM tubes, strongly suggesting that transfer results from the local fusion of the OMs of two transferring cells. Last, large amounts of OM materials were released in slime trails deposited by gliding cells. Since cells tend to follow trails laid by other cells, slime-driven OM material exchange may be an important stigmergic regulation of Myxococcus social behaviors.\nIntroduction:\nMyxococcus xanthus, a gram negative deltaproteobacterium, displays complex multicellular behaviors in response to environmental cues such as the presence of prey bacteria or starvation( Zhang et al., 2012). In particular, starvation triggers a developmental program where thousands of cells coordinate their motility, moving into aggregation centers to build multicellular fruiting bodies where the cells form metabolically-inert spores. This multicellular response requires an arsenal of intercellular signals, including diffusible long-range signals as well as contact-dependent signals( Konovalova et al., 2010; Mauriello et al., 2009). One intriguing cell–cell communication mechanism involves the cell-to-cell transfer of outer membrane( OM) proteins between Myxococcus cells. This phenomenon was originally unmasked by mixing experiments where certain motility mutants were shown to rescue other motility mutants in a process called stimulation( Nudleman et al., 2005). Stimulatable mutants all carried mutations in genes encoding predicted OM proteins( termed cgl or tgl). Experiments with the Tgl and the CglB OM lipoproteins suggested that stimulation is transient and does not involve the exchange of genetic material, but results from the physical transfer of Tgl/Cgl proteins from donor Tgl+/Cgl+ cells to recipient Tgl−/Cgl− cells( Nudleman et al., 2005). Remarkably, OM protein exchange is not restricted to motility proteins and virtually any OM protein and even lipid can be exchanged between cells( Wei et al., 2011; Pathak et al., 2012). Gliding( A−) motility has been shown to be important for transfer, but rather indirectly by promoting the formation of dense regions of aligned cells and favoring intimate cell–cell contacts( Nudleman et al., 2005; Pathak et al., 2012). The transfer process itself depends on two specific proteins, TraA and TraB( Pathak et al., 2012). TraA is a protein with hallmarks of yeast floculins, a class of cell surface adhesins that mediate cell–cell interactions leading to flocculation( Smukalla et al., 2008) and TraB is a secreted protein of unknown function with a possible peptidoglycan-binding domain. TraA and TraB must be expressed both by donor and recipient cells for transfer to occur. Consequently, Wall and colleagues proposed that when adjacent cells engage Tra-dependent surface interactions( i. e., homotypic interactions or interactions with other surface ligands), the OMs fuse locally and OM materials are exchanged( Wei et al., 2011; Pathak et al., 2012). However, because transfer was studied in bulk assays this hypothesis could not be tested directly. Therefore, other mechanisms remained possible, for example long-range exchange of OM vesicles or even local cell lysis. In this study, we investigated the transfer mechanism at the single cell level to gain more insights into the transfer mechanism.\nDiscussion:\nDirect imaging of OM protein transfer between Myxococcus cells uncovers critical aspects of the cell biology and kinetics of transfer. Specifically, we found that the physical contact between two adjacent cells is sufficient to promote transfer of OM proteins and lipids at high efficiency. This explains the results from bulk transfer experiments( from previous works and reported herein) suggesting that transfer is a remarkably efficient process. The formation of transient OM tubes between cells is a major indication that transfer indeed occurs by OM fusion: the tubes are continuous extension of cell OM, they form between transferring cells and allow the rapid exchange of lipids. Importantly, the Myxococcus OM transfer system is distinct from reported bacterial nanotubes, which seem to connect the cytosolic contents of connected cells and involve a yet uncharacterized machinery( Dubey and Ben-Yehuda, 2011). In Myxococcus, the transfer process is restricted to OM proteins and lipids. Transfer only occurs in a subset of cell contact events, suggesting that it is provoked by specific contacts, for example if TraA interactions brought OMs in close apposition locally. OMsfGFP/OMmCherry are fused to type II signal sequences and thus insert in the OM as OM lipoproteins. Since, OM lipoproteins are inserted in the inner leaflet of the OM( Nakayama et al., 2012), transfer must involve the fusion of both leaflets of the OM membrane, suggesting that the entire OM is exchanged locally between cells. The formation of OM synapses must therefore create continuity between the periplasmic content of transferring cells. The size of the OM synapse may be estimated from the size of the tubes( ∼50 nm), suggesting that the diameter of the periplasmic lumen may reach up to 20 nm( for an OM of 10–15 nm thickness[Bayer, 1991; Palsdottir et al., 2009]), providing ample space for periplasmic exchange. However, the PERImCherry probe was poorly if at all exchanged and there is currently no evidence for the physiological transfer of periplasmic proteins, suggesting that OM synapses are not very permeable to periplasmic proteins. Our results also suggest that gliding motility may facilitate transfer by promoting cell–cell alignment but also when cells follow slime trails by incorporating membrane materials embedded in the slime polymer. The shedding of large amounts of membrane materials on the underlying substrate is a common byproduct of surface motility both in eukaryotic and prokaryotic cells. For example, crawling keratinocytes also deposit their plasma membrane due to the activity of acto-myosin motors in focal adhesions( Kirfel et al., 2003). In Myxococcus, gliding( A−) motility is thought to involve OM dynamics in the form of energized deformations and/or protein movements( Nan et al., 2010; Luciano et al., 2011; Nan et al., 2011; Sun et al., 2011). Thus, OM fragments may detach to the substrate due to the interaction between the motility machinery and slime. It is possible that acquisition of the traAB genes allowed Myxococcus cells to recycle this ‘waste’ and co-opt it for cell–cell signaling. A tantalizing possibility would be that slime embedded vesicles contain signals that promote specific recognition, facilitate trail following and promote colony expansion in response to environmental changes. The Myxococcus Tra-dependent cell–cell transfer of OM proteins is a novel mode of bacterial communication that adds to the growing repertoire of bacterial contact-dependent signaling mechanisms. Contrary to known contact dependent protein transfer systems, the type VI secretion( Silverman et al., 2012) or intercellular nanotubes( Dubey and Ben-Yehuda, 2011), the distribution of TraA suggests that Tra-dependent OM fusion is restricted to the deltaproteobacteria( Figure 6A and Figure 6—figure supplement 1). Interestingly, even in Myxococcus xanthus strains, the predicted extracellular N-terminal PA14 domain of TraA shows variability, while the C-terminal region, presumably involved in anchoring to the cell surface is highly conserved( Figure 6B—figure supplement 2). Importantly, TraA acts as both key and lock for transfer to occur( Pathak et al., 2012). Therefore, as already suggested, OM-transfer may have evolved to regulate interactions between cells of the same kin. tra mutants do not show motility or developmental defects in pure culture and thus the contribution of OM transfer to Myxococcus social behaviors is unclear( Pathak et al., 2012). Interestingly however, mixing tra mutants with WT cells perturbs motility and development profoundly, consistent with a role in the control population dynamics( Pathak et al., 2012). OM exchange by transient fusion may be more widespread than suspected, especially because it is not easily unmasked and likely does not employ a conserved molecular system. Indeed, membrane vesicles and tubes have been observed in other biofilm-forming proteobacteria( Schooling and Beveridge, 2006; Schooling et al., 2009) and could well be involved in OM exchange behaviors. 10. 7554/eLife. 00868. 020Figure 6. Distribution of TraA is restricted to the deltaproteobacteria.( A) TraA homologues in Myxococcus xanthus DK1622( gi|108763680), Myxococcus stipitatus( gi|442324418), Corallococcus coralloides( gi|383459429), Myxococcus fulvus( gi|338532052), Stigmatella aurantiaca( gi|310818240), Cystobacter fuscus( gi|444910311), Haliangium Ochraceum( gi|262197466), Sorangium Cellulosum( gi|162451690).( B) The PA-14 domain is variable in Myxococcus xanthus strains. The conservation of the Ct domain is shown for comparison. Sequence database access numbers are shown to the left. DOI: http://dx. doi. org/10. 7554/eLife. 00868. 02010. 7554/eLife. 00868. 021Figure 6—figure supplement 1. TraA homologues in deltaproteobacteria. ClustalW alignment of TraA homolog: Myxococcus xanthus DK1622( gi|108763680), Myxococcus stipitatus( gi|442324418), Corallococcus coralloides( gi|383459429), Myxococcus fulvus( gi|338532052), Stigmatella aurantiaca( gi|310818240), Cystobacter fuscus( gi|444910311), Haliangium Ochraceum( gi|262197466), Sorangium Cellulosum( gi|162451690). DOI: http://dx. doi. org/10. 7554/eLife. 00868. 02110. 7554/eLife. 00868. 022Figure 6—figure supplement 2. ClustalW alignment of TraA in Myxococcus xanthus strains. Note that most amino acids variations are localized in the first 300 N-terminal residues region encompassing the so-called PA14 domain. DOI: http://dx. doi. org/10. 7554/eLife. 00868. 022", "role": "user" }, { "content": "Bacteria studied in the laboratory are , in general , readily amenable to culture , and they easily form colonies when grown on agar plates . In the wild , however , many bacteria exhibit a range of more complex behaviors , including the growth of super-organisms that contain many cells . The bacterium Myxococcus xanthus can exist either as single cells or as a super-organism . Each cell has an inner and outer plasma membrane separated by a periplasmic space . Previous work has found that individual cells communicate with each other by exchanging the contents of their outer membranes , and that these swaps can govern multicellular behavior . Membrane exchange is known to depend on both donor and recipient cells having the proteins TraA and TraB . TraA proteins are similar to the adhesion factors that hold cells together , and they are found in many species: this suggests that TraA therefore might help the outer membranes of cells to fuse so that they can swap materials . The role of TraB is not known at present . To investigate membrane exchange more closely , Ducret et al . measured the transfer of fluorescent proteins from the periplasm and the inner and outer membranes of the donor cell to the recipient cell , as well as the transfer of fluorescent lipids from the donor’s outer membrane . Both proteins and lipids from the outer membrane were transferred rapidly ( within minutes ) ; although a small amount of protein transfer from the periplasmic space was observed after 36 hr , there was no transfer from the inner membrane . As in previous studies , exchange depended on the presence of TraA . Ducret et al . observed that contact between two cells was sufficient to stimulate transfer of proteins and lipids from the outer membrane . But not all contacts led to a transfer . Importantly , when cells that had swapped fluorescent membrane components moved apart , they appeared to remain connected by tubular structures , suggesting that an inter-membrane junction must form to allow proteins and lipids to be transferred between the cells . This junction is referred to as an outer-membrane synapse . Ducret et al . also noted another phenomenon: cells shed pieces of membrane as they moved across surfaces or separated after outer membrane exchange . This suggests that both synapse formation after direct cell-to-cell contact and the shedding of membrane components can help to propagate bacterial signals , enabling population-wide behavioral changes , including the formation or collapse of super-organisms .", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: Social distancing encouraged: As one of the first interventions against the spread of the COVID-19\npandemic, many governments have published advice on social distancing including the\nrecommendation to work from home wherever possible, reducing use ofpublictransport and all other\nnon-essential contact. The dates used are those when social distancing has officially been\nrecommended by the government; the advice may include maintaining a recommended physical\ndistance from others. Lockdown decreed: There are several different scenarios that the media refers to as lockdown. As an\noverall definition, we consider regulations/legislations regarding strict face-to-face social interaction:\nincluding the banning of any non-essential public gatherings, closure of educational and\n\npublic/cultural institutions, ordering people to stay home apart from exercise and essential tasks. We\ninclude special cases where these are not explicitly mentioned on government websites but are\nenforced by the police (e.g. France). The dates used are the effective dates when these legislations\nhave been implemented. We note that lockdown encompasses other interventions previously\nimplemented. First intervention: As Figure 1 shows, European governments have escalated interventions rapidly,\nand in some examples (Norway/Denmark) have implemented these interventions all on a single day. Therefore, given the temporal autocorrelation inherent in government intervention, we include a\nbinary covariate for the first intervention, which can be interpreted as a government decision to take\nmajor action to control COVID-19. A full list of the timing of these interventions and the sources we have used can be found in Appendix\n8.6. 6 Methods Summary\n\nA Visual summary of our model is presented in Figure 5 (details in Appendix 8.1 and 8.2). Replication\ncode is available at https://github.com/|mperia|CollegeLondon/covid19model/releases/tag/vl.0\n\nWe fit our model to observed deaths according to ECDC data from 11 European countries. The\nmodelled deaths are informed by an infection-to-onset distribution (time from infection to the onset\nof symptoms), an onset-to-death distribution (time from the onset of symptoms to death), and the\npopulation-averaged infection fatality ratio (adjusted for the age structure and contact patterns of\neach country, see Appendix). Given these distributions and ratios, modelled deaths are a function of\nthe number of infections. The modelled number of infections is informed by the serial interval\ndistribution (the average time from infection of one person to the time at which they infect another)\nand the time-varying reproduction number. Finally, the time-varying reproduction number is a\nfunction of the initial reproduction number before interventions and the effect sizes from\ninterventions. Figure 5: Summary of model components. Following the hierarchy from bottom to top gives us a full framework to see how interventions affect\ninfections, which can result in deaths. We use Bayesian inference to ensure our modelled deaths can\nreproduce the observed deaths as closely as possible. From bottom to top in Figure 5, there is an\nimplicit lag in time that means the effect of very recent interventions manifest weakly in current\ndeaths (and get stronger as time progresses). To maximise the ability to observe intervention impact\non deaths, we fit our model jointly for all 11 European countries, which results in a large data set. Our\nmodel jointly estimates the effect sizes of interventions. We have evaluated the effect ofour Bayesian\nprior distribution choices and evaluate our Bayesian posterior calibration to ensure our results are\nstatistically robust (Appendix 8.4). 7 Acknowledgements\n\nInitial research on covariates in Appendix 8.6 was crowdsourced; we thank a number of people\nacross the world for help with this. This work was supported by Centre funding from the UK Medical\nResearch Council under a concordat with the UK Department for International Development, the\nNIHR Health Protection Research Unit in Modelling Methodology and CommunityJameel. 8 Appendix: Model Specifics, Validation and Sensitivity Analysis\n8.1 Death model\n\nWe observe daily deaths Dam for days t E 1, ...,n and countries m E 1, ...,p. These daily deaths are\nmodelled using a positive real-Valued function dam = E(Dam) that represents the expected number\nof deaths attributed to COVID-19. Dam is assumed to follow a negative binomial distribution with\n\n\nThe expected number of deaths (1 in a given country on a given day is a function of the number of\ninfections C occurring in previous days. At the beginning of the epidemic, the observed deaths in a country can be dominated by deaths that\nresult from infection that are not locally acquired. To avoid biasing our model by this, we only include\nobserved deaths from the day after a country has cumulatively observed 10 deaths in our model. To mechanistically link ourfunction for deaths to infected cases, we use a previously estimated COVID-\n19 infection-fatality-ratio ifr (probability of death given infection)9 together with a distribution oftimes\nfrom infection to death TE. The ifr is derived from estimates presented in Verity et al11 which assumed\nhomogeneous attack rates across age-groups. To better match estimates of attack rates by age\ngenerated using more detailed information on country and age-specific mixing patterns, we scale\nthese estimates (the unadjusted ifr, referred to here as ifr’) in the following way as in previous work.4\nLet Ca be the number of infections generated in age-group a, Na the underlying size of the population\nin that age group and AR“ 2 Ca/Na the age-group-specific attack rate. The adjusted ifr is then given\n\nby: ifra = fififié, where AR50_59 is the predicted attack-rate in the 50-59 year age-group after\n\nincorporating country-specific patterns of contact and mixing. This age-group was chosen as the\nreference as it had the lowest predicted level of underreporting in previous analyses of data from the\nChinese epidemic“. We obtained country-specific estimates of attack rate by age, AR“, for the 11\nEuropean countries in our analysis from a previous study which incorporates information on contact\nbetween individuals of different ages in countries across Europe.12 We then obtained overall ifr\nestimates for each country adjusting for both demography and age-specific attack rates. Using estimated epidemiological information from previous studies,“'11 we assume TE to be the sum of\ntwo independent random times: the incubation period (infection to onset of symptoms or infection-\nto-onset) distribution and the time between onset of symptoms and death (onset-to-death). The\ninfection-to-onset distribution is Gamma distributed with mean 5.1 days and coefficient of variation\n0.86. The onset-to-death distribution is also Gamma distributed with a mean of 18.8 days and a\ncoefficient of va riation 0.45. ifrm is population averaged over the age structure of a given country. The\ninfection-to-death distribution is therefore given by:\n\num ~ ifrm ~ (Gamma(5.1,0.86) + Gamma(18.8,0.45))\n\nFigure 6 shows the infection-to-death distribution and the resulting survival function that integrates\nto the infection fatality ratio. Figure 6: Left, infection-to-death distribution (mean 23.9 days). Right, survival probability of infected\nindividuals per day given the infection fatality ratio (1%) and the infection-to-death distribution on\nthe left. Using the probability of death distribution, the expected number of deaths dam, on a given day t, for\ncountry, m, is given by the following discrete sum:\n\n\nThe number of deaths today is the sum of the past infections weighted by their probability of death,\nwhere the probability of death depends on the number of days since infection. 8.2 Infection model\n\nThe true number of infected individuals, C, is modelled using a discrete renewal process. This approach\nhas been used in numerous previous studies13'16 and has a strong theoretical basis in stochastic\nindividual-based counting processes such as Hawkes process and the Bellman-Harris process.”18 The\nrenewal model is related to the Susceptible-Infected-Recovered model, except the renewal is not\nexpressed in differential form. To model the number ofinfections over time we need to specify a serial\ninterval distribution g with density g(T), (the time between when a person gets infected and when\nthey subsequently infect another other people), which we choose to be Gamma distributed:\n\ng ~ Gamma (6.50.62). The serial interval distribution is shown below in Figure 7 and is assumed to be the same for all\ncountries. Figure 7: Serial interval distribution g with a mean of 6.5 days. Given the serial interval distribution, the number of infections Eamon a given day t, and country, m,\nis given by the following discrete convolution function:\n\n_ t—1\nCam — Ram ZT=0 Cr,mgt—‘r r\nwhere, similarto the probability ofdeath function, the daily serial interval is discretized by\n\nfs+0.5\n\n1.5\ngs = T=s—0.Sg(T)dT fors = 2,3, and 91 = fT=Og(T)dT. Infections today depend on the number of infections in the previous days, weighted by the discretized\nserial interval distribution. This weighting is then scaled by the country-specific time-Varying\nreproduction number, Ram, that models the average number of secondary infections at a given time. The functional form for the time-Varying reproduction number was chosen to be as simple as possible\nto minimize the impact of strong prior assumptions: we use a piecewise constant function that scales\nRam from a baseline prior R0,m and is driven by known major non-pharmaceutical interventions\noccurring in different countries and times. We included 6 interventions, one of which is constructed\nfrom the other 5 interventions, which are timings of school and university closures (k=l), self—isolating\nif ill (k=2), banning of public events (k=3), any government intervention in place (k=4), implementing\na partial or complete lockdown (k=5) and encouraging social distancing and isolation (k=6). We denote\nthe indicator variable for intervention k E 1,2,3,4,5,6 by IkI’m, which is 1 if intervention k is in place\nin country m at time t and 0 otherwise. The covariate ”any government intervention” (k=4) indicates\nif any of the other 5 interventions are in effect,i.e.14’t’m equals 1 at time t if any of the interventions\nk E 1,2,3,4,5 are in effect in country m at time t and equals 0 otherwise. Covariate 4 has the\ninterpretation of indicating the onset of major government intervention. The effect of each\nintervention is assumed to be multiplicative. Ram is therefore a function ofthe intervention indicators\nIk’t’m in place at time t in country m:\n\nRam : R0,m eXp(— 212:1 O(Rheum)-\n\nThe exponential form was used to ensure positivity of the reproduction number, with R0,m\nconstrained to be positive as it appears outside the exponential. The impact of each intervention on\n\nRam is characterised by a set of parameters 0(1, ...,OL6, with independent prior distributions chosen\nto be\n\nock ~ Gamma(. 5,1). The impacts ock are shared between all m countries and therefore they are informed by all available\ndata. The prior distribution for R0 was chosen to be\n\nR0,m ~ Normal(2.4, IKI) with K ~ Normal(0,0.5),\nOnce again, K is the same among all countries to share information. We assume that seeding of new infections begins 30 days before the day after a country has\ncumulatively observed 10 deaths. From this date, we seed our model with 6 sequential days of\ninfections drawn from cl’m,...,66’m~EXponential(T), where T~Exponential(0.03). These seed\ninfections are inferred in our Bayesian posterior distribution. We estimated parameters jointly for all 11 countries in a single hierarchical model. Fitting was done\nin the probabilistic programming language Stan,19 using an adaptive Hamiltonian Monte Carlo (HMC)\nsampler. We ran 8 chains for 4000 iterations with 2000 iterations of warmup and a thinning factor 4\nto obtain 2000 posterior samples. Posterior convergence was assessed using the Rhat statistic and by\ndiagnosing divergent transitions of the HMC sampler. Prior-posterior calibrations were also performed\n(see below). 8.3 Validation\n\nWe validate accuracy of point estimates of our model using cross-Validation. In our cross-validation\nscheme, we leave out 3 days of known death data (non-cumulative) and fit our model. We forecast\nwhat the model predicts for these three days. We present the individual forecasts for each day, as\nwell as the average forecast for those three days. The cross-validation results are shown in the Figure\n8. Figure 8: Cross-Validation results for 3-day and 3-day aggregatedforecasts\n\nFigure 8 provides strong empirical justification for our model specification and mechanism. Our\naccurate forecast over a three-day time horizon suggests that our fitted estimates for Rt are\nappropriate and plausible. Along with from point estimates we all evaluate our posterior credible intervals using the Rhat\nstatistic. The Rhat statistic measures whether our Markov Chain Monte Carlo (MCMC) chains have\n\nconverged to the equilibrium distribution (the correct posterior distribution). Figure 9 shows the Rhat\nstatistics for all of our parameters\n\n\nFigure 9: Rhat statistics - values close to 1 indicate MCMC convergence. Figure 9 indicates that our MCMC have converged. In fitting we also ensured that the MCMC sampler\nexperienced no divergent transitions - suggesting non pathological posterior topologies. 8.4 SensitivityAnalysis\n\n8.4.1 Forecasting on log-linear scale to assess signal in the data\n\nAs we have highlighted throughout in this report, the lag between deaths and infections means that\nit ta kes time for information to propagate backwa rds from deaths to infections, and ultimately to Rt. A conclusion of this report is the prediction of a slowing of Rt in response to major interventions. To\ngain intuition that this is data driven and not simply a consequence of highly constrained model\nassumptions, we show death forecasts on a log-linear scale. On this scale a line which curves below a\nlinear trend is indicative of slowing in the growth of the epidemic. Figure 10 to Figure 12 show these\nforecasts for Italy, Spain and the UK. They show this slowing down in the daily number of deaths. Our\nmodel suggests that Italy, a country that has the highest death toll of COVID-19, will see a slowing in\nthe increase in daily deaths over the coming week compared to the early stages of the epidemic. We investigated the sensitivity of our estimates of starting and final Rt to our assumed serial interval\ndistribution. For this we considered several scenarios, in which we changed the serial interval\ndistribution mean, from a value of 6.5 days, to have values of 5, 6, 7 and 8 days. In Figure 13, we show our estimates of R0, the starting reproduction number before interventions, for\neach of these scenarios. The relative ordering of the Rt=0 in the countries is consistent in all settings. However, as expected, the scale of Rt=0 is considerably affected by this change — a longer serial\ninterval results in a higher estimated Rt=0.\nQuestion: Example of social distancing", "role": "user" }, { "content": "reducing use ofpublictransport", "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: We propose a novel method for the automatic segmentation of vessel trees in retinal fundus images.\n\nKeywords: retinal vessel segmentation fundus images\n\nDataset descriptions:\nRITE: The RITE (Retinal Images vessel Tree Extraction) is a database that enables comparative studies on segmentation or classification of arteries and veins on retinal fundus images, which is established based on the public available DRIVE database (Digital Retinal Images for Vessel Extraction). RITE contains 40 sets of images, equally separated into a training subset and a test subset, the same as DRIVE.\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.\nCHASE_DB1: CHASE_DB1 is a dataset for retinal vessel segmentation which contains 28 color retina images with the size of 999×960 pixels which are collected from both left and right eyes of 14 school children. Each image is annotated by two independent human experts.\nSTARE: The STARE (Structured Analysis of the Retina) dataset is a dataset for retinal vessel segmentation. It contains 20 equal-sized (700×605) color fundus images.\nORVS: The ORVS dataset has been newly established as a collaboration between the computer science and visual-science departments at the University of Calgary. This dataset contains 49 images (42 training and seven testing images) collected from a clinic in Calgary-Canada.\nROSE: Retinal OCTA SEgmentation dataset (ROSE) consists of 229 OCTA images with vessel annotations at either centerline-level or pixel level.\n\nOptions: A: RITE B: DRIVE C: CHASE_DB1 D: STARE E: ORVS F: ROSE", "role": "user" }, { "content": "[\"DRIVE\", \"CHASE_DB1\", \"STARE\"]", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: This is a dataset of over 2.5 million questions, annotated with 15\n\nKeyphrases: top-k assignment query text\n\nDataset descriptions:\nSo2Sat LCZ42: So2Sat LCZ42 consists of local climate zone (LCZ) labels of about half a million Sentinel-1 and Sentinel-2 image patches in 42 urban agglomerations (plus 10 additional smaller areas) across the globe. This dataset was labeled by 15 domain experts following a carefully designed labeling work flow and evaluation process over a period of six months.\nBREAK: Break is a question understanding dataset, aimed at training models to reason over complex questions. It features 83,978 natural language questions, annotated with a new meaning representation, Question Decomposition Meaning Representation (QDMR).\nJester: 6.5 million anonymous ratings of jokes by users of the Jester Joke Recommender System.\nAVA: AVA is a project that provides audiovisual annotations of video for improving our understanding of human activity. Each of the video clips has been exhaustively annotated by human annotators, and together they represent a rich variety of scenes, recording conditions, and expressions of human activity.\n\nOptions: A: So2Sat LCZ42 B: BREAK C: Jester D: AVA", "role": "user" }, { "content": "Jester", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: An Overview on Thermal Safety Issues of Lithium-ion Batteries for Electric Vehicle Application \nChapter Title: 1) ARC-BASED EXPERIMENTS \n1. Abstract of Cited Paper (BIB001): Electrochemical-calorimetric measurements, in combination with the dc current interruption technique, were used to determine the change of entropy during discharge and charge of the Panasonic Li-ion cell CGR 18650H. The entropy coefficient dE eq /dT was found to vary from -0.6 mV K -1 in the discharged state to -0.1 mV K -1 in the fully charged state. An unexpected variation of large amplitude (from -0.1 to 0.25 and -0.75 back to -0.1 mV K -1 ) was observed in a narrow range of depth of discharge (DOD) near 0.23, between 3.95 and 4.10 V, curing charge as well as discharge. Thus, changes in the reversible heat, TAS, appear to be mainly responsible for the transient endothermic heat effect observed during discharge of these Li-ion cells, near DOD 0.23, between 4.035 and 3.975 V. This interpretation of the calorimetric measurements is confirmed by the fact that dE eq /dT measured at 4.0 V was positive (0.14 mV K -1 ). The unexpected strong variation of dE eq /dT near DOD 0.23 is due to the nearly simultaneous occurrence of a phase change in the cathode and a structural transformation (quasi-phase change) in the graphite anode. \n2. Abstract of Cited Paper (BIB002): Abstract In this paper, the thermal runaway features of a 25 Ah large format prismatic lithium ion battery with Li(NixCoyMnz)O2 (NCM) cathode are evaluated using the extended volume-accelerating rate calorimetry (EV-ARC). 4 thermocouples are set at different positions of the battery. The temperature inside the battery is 870 °C or so, much higher than that outside the battery. The temperature difference is calculated from the recorded data. The temperature difference within the battery stays lower than 1 °C for 97% of the test period, while it rises to its highest, approximately 520 °C, when thermal runaway happens. The voltage of the battery is also measured during the test. It takes 15–40 s from the sharp drop of voltage to the instantaneous rise of temperature. Such a time interval is beneficial for early warning of the thermal runaway. Using a pulse charge/discharge profile, the internal resistance is derived from the quotient of the pulse voltage and the current during the ARC test. The internal resistance of the battery increases slowly from 20 mΩ to 60 mΩ before thermal runaway, while it rises to 370 mΩ when thermal runaway happens indicating the loss of the integrity of the separator or the battery swell. \n3. Abstract of Cited Paper (BIB003): Abstract In-situ determination of the battery thermal parameters is important to provide accurate inputs for battery thermal models. This paper develops a method to estimate the multiple thermal parameters of large-format laminated lithium-ion batteries both simultaneously and in-situ. The central area of one battery surface is heated with a circular planar heater, while the temperature responses on the opposite surface at multiple strategically-chosen locations are recorded with the attached thermocouples. This thermal system is modeled in COMSOL v4.2 using a two-dimensional axially-symmetric thermal conduction equation containing thermal parameters such as the thermal capacity, anisotropic thermal conductivities, and thermal interfacial conductance between the Al-plastic film package and the electrode core. Using optimization techniques, these thermal parameters are adjusted step by step till the difference between the simulated and the experimental temperature responses at the corresponding locations reaches a minimum. As one validation of the developed method, the estimated specific heat capacity agreed with the value measured with an accelerating rate calorimeter within 10%. The proposed method can be applied to simultaneously determine the thermal parameters of generic objects consisting of anisotropic internal materials and an outer packaging made of different material. \n4. Abstract of Cited Paper (BIB004): The heat generation rate of a large-format 25 Ah lithium-ion battery is studied through estimating each term of the Bernardi model. The term for the reversible heat is estimated from the entropy coefficient and compared with the result from the calorimetric method. The term for the irreversible heat is estimated from the intermittent current method, the V–I characteristics method and a newly developed energy method. Using the obtained heat generation rates, the average cell temperature rise under 1C charge/discharge is calculated and validated against the results measured in an accelerating rate calorimeter (ARC). It is found that the intermittent current method with an appropriate interval and the V–I characteristics method using a pouch cell yield close agreement, while the energy method is less accurate. A number of techniques are found to be effective in circumventing the difficulties encountered in estimating the heat generation rate for large-format lithium-ion batteries. A pouch cell, using the same electrode as the 25 Ah cell but with much reduced capacity (288 mAh), is employed to avoid the significant temperature rise in the V–I characteristics method. The first-order inertial system is utilized to correct the delay in the surface temperature rise relative to the internal heat generation. Twelve thermocouples are used to account for the temperature distribution. \n5. Abstract of Cited Paper (BIB005): Quantitative data on the thermal behavior of lithium ion batteries under charging and discharging conditions are essential for designing thermal management systems and improving battery safety. In this work, commercial 40 Ah lithium ion pouch cells with Li(Ni1/3Mn1/3Co1/3)O2 cathodes were tested under isoperibolic and adiabatic conditions in an Accelerating Rate Calorimeter at different charging/discharging currents from 5 A to 40 A. Adiabatic tests simulate the worst-case scenario of a battery pack without cooling. For charging and discharging an overall exothermic behavior was found and a total temperature increase for one half cycle between 3 and 11 K. Isoperibolic tests simulate a single cell under constant environmental temperature. Here an exothermic behavior for discharging and an endothermic behavior for charging were observed. To transfer the measured temperature changes into heat data, the effective specific heat capacity and the heat transfer coefficient were determined. For the first time the heat generation data for a large format pouch cell have been determined using both isoperibolic and adiabatic conditions. These data were compared with the total heat data calculated as the sum of reversible and irreversible heat that were measured by potentiometric and current interruption techniques respectively. A good agreement was found between all three heat generation determination methods.\n\nLiterature Review:", "role": "user" }, { "content": "ARC is a thermal analyzing instrument/method for heat generation determination. It can measure the generated heat of an object by establishing an adiabatic environment. Traditional ARCs are proper and convenient for a small dose of chemicals. However, in order to test LIBs, especially large-format ones, large-scale ARCs are being developed and employed BIB003 . Heat generation rate can be calculated by the following energy balance equation as The left-hand term is the amount of heat generated by a battery cell or module. The first term on the right-hand is the heat stored in the measured object, and the last term is the heat convection between the surface of the measured object and the calorimeter well. Hong et al. BIB001 established an accelerated rate calorimeter-cycler test bench to analyze the thermal behavior of a commercial 18650 lithium-ion cell, and collected experimental data of heat dissipation during discharge and charge at various rates. Al Hallaj et al. BIB002 , presented an electrochemical calorimetric test method (ARC-Arbin) to conduct experiments on several LIBs with different chemistries. They acquired instantaneous heat generation rate and defined its correlation with cell impedance and discharge rate. Zhang et al. BIB004 utilized the ARC to measure the specific heat capacity of a battery cell and validated various heat generation estimation methods for large-format pouch cells based on the ARC result of battery heat generation rate BIB005 . Schuster et al. BIB006 tested 40Ah commercial NCM pouch cells under the adiabatic environment created with an ARC at various charging/discharging rates. The adiabatic tests were designed to simulate extreme heat generation conditions without cooling in order to maximize the self-heating effects.", "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: Iterative rounds of model building with COOT and TLS-refinement and restrained maximum-likelihood refinement with REFMAC resulted in the final model at 1.55 AÃä resolution described in Table 1.", "role": "user" }, { "content": "Method", "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\nBACKGROUND: Cardiac injury and myocarditis have been described in adults with coronavirus disease 2019 (COVID-19). Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in children is typically minimally symptomatic. We report a series of febrile pediatric patients with acute heart failure potentially associated with SARS-CoV-2 infection and the multisystem inflammatory syndrome in children as defined by the US Centers for Disease Control and Prevention. METHODS: Over a 2-month period, contemporary with the SARS-CoV-2 pandemic in France and Switzerland, we retrospectively collected clinical, biological, therapeutic, and early outcomes data in children who were admitted to pediatric intensive care units in 14 centers for cardiogenic shock, left ventricular dysfunction, and severe inflammatory state. RESULTS: Thirty-five children were identified and included in the study. Median age at admission was 10 years (range, 2-16 years). Comorbidities were present in 28%, including asthma and overweight. Gastrointestinal symptoms were prominent. Left ventricular ejection fraction was <30% in one-third; 80% required inotropic support with 28% treated with extracorporeal membrane oxygenation. Inflammation markers were suggestive of cytokine storm (interleukin-6 median, 135 pg/mL) and macrophage activation (D-dimer median, 5284 ng/mL). Mean BNP (B-type natriuretic peptide) was elevated (5743 pg/mL). Thirty-one of 35 patients (88%) tested positive for SARS-CoV-2 infection by polymerase chain reaction of nasopharyngeal swab or serology. All patients received intravenous immunoglobulin, with adjunctive steroid therapy used in one-third. Left ventricular function was restored in the 25 of 35 of those discharged from the intensive care unit. No patient died, and all patients treated with extracorporeal membrane oxygenation were successfully weaned. CONCLUSIONS: Children may experience an acute cardiac decompensation caused by severe inflammatory state after SARS-CoV-2 infection (multisystem inflammatory syndrome in children). Treatment with immunoglobulin appears to be associated with recovery of left ventricular systolic function.", "role": "user" }, { "content": "[\"Treatment\"]", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nThis paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the distribution of the returns (return uncertainty). We identify methods to learn these distributions with deep neural networks, where we estimate parametric uncertainty with Bayesian drop-out, while return uncertainty is propagated through the Bellman equation as a Gaussian distribution. Then, we identify that both can be jointly estimated in one network, which we call the Double Uncertain Value Network. The policy is directly derived from the learned distributions based on Thompson sampling. Experimental results show that both types of uncertainty may vastly improve learning in domains with a strong exploration challenge.\n\nCited Abstract(s):\n[1]: Formulae are presented for the variance and higher moments of the present value of single-stage rewards in a finite Markov decision process. Similar formulae are exhibited for a semi-Markov decision process. There is a short discussion of the obstacles to using the variance formula in algorithms to maximize the mean minus a multiple of the standard deviation.\n\n[2]: We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudopolynomial exact and approximation algorithms.", "role": "user" }, { "content": "While the distributional Bellman equation (Eq. ) is certainly not new [1] [2] , nearly all RL research has focussed on the mean action-value. Most papers that do study the underlying return distribution study the 'variance of the return'. learned the distribution of the return with Gaussian Processes, but did not use it for exploration. studied the variance of the return with linear function approximation. theoretically studies policies that bound the variance of the return.", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below. Your response should only include the abstract and no additional text.\n\nArticle text:\ndeep - inelastic diffractive scattering is one of the important scattering processes in high - energy @xmath4 scattering at hera . in the small-@xmath5 domain @xmath6 of the events\nare due to this process .\nit is characterized by inclusive hadron - production with a large rapidity gap between the outgoing proton and all the remainder hadrons . in refs .\n@xcite two of the present authors developed a description for this process based on the compton operator and using techniques known in non - forward scattering , cf .\n@xcite , for the case that the momentum transfer @xmath1 between the incoming and the outgoing proton and target masses can be neglected . in the region of smaller values of @xmath3 and\nlarge values of @xmath7 one expects both finite @xmath1 and @xmath8 effects which were worked out in @xcite based on related investigations for the non - forward case @xcite , see also @xcite . in this paper\nwe summarize the main findings of these analyzes , cf .\nalso @xcite .\nthe hadronic tensor of the process is determined by three vectors @xmath9 , the incoming and outgoing proton momentum and the momentum transfer in the unpolarized case supplemented by the spin vector of the initial proton @xmath10 in the polarized case .\nthe following invariants are formed @xmath11 the hadronic tensors in case of the unpolarized and polarized cases are of the following form , @xcite @xmath12 @xmath13 \\varepsilon_{p_1,p_2,q , s } & \\frac{{\\hat{w}_1}}{m^6}&~~ & + & ~~ i \\left [ \\hat{p}_{1\\mu } \\varepsilon_{\\nu s p_1 q } - \\hat{p}_{1\\nu } \\varepsilon_{\\mu s p_1 q } \\right ] & \\frac{{\\hat{w}_2}}{m^4 } & \\nonumber \\\\ & + & ~~ i \\left [ \\hat{p}_{2\\mu } \\varepsilon_{\\nu s p_1 q } - \\hat{p}_{2\\nu } \\varepsilon_{\\mu s p_1 q } \\right ] & \\frac{{\\hat{w}_3}}{m^4}&~~ & + & ~~ i \\left [ \\hat{p}_{1\\mu } \\varepsilon_{\\nu s p_2 q } - \\hat{p}_{1\\nu } \\varepsilon_{\\mu s p_2 q } \\right ] & \\frac{{\\hat{w}_4}}{m^4 } & \\nonumber \\\\ & + & ~~ i \\left [ \\hat{p}_{2\\mu } \\varepsilon_{\\nu s p_2 q } - \\hat{p}_{2\\nu } \\varepsilon_{\\mu s p_2 q } \\right ] & \\frac{{\\hat{w}_5}}{m^4}&~~ & + & ~~ i \\left [ \\hat{p}_{1\\mu } \\hat{\\varepsilon}_{\\nu p_1 p_2 s } - \\hat{p}_{1\\nu } \\hat{\\varepsilon}_{\\mu p_1 p_2 s } \\right ] & \\frac{{\\hat{w}_6}}{m^4 } & \\nonumber\\\\ & + & ~~ i \\left [ \\hat{p}_{2\\mu } \\hat{\\varepsilon}_{\\nu p_1 p_2 s } - \\hat{p}_{2\\nu } \\hat{\\varepsilon}_{\\mu p_1 p_2 s } \\right ] & \\frac{{\\hat{w}_7}}{m^4}&~~ & + & ~~ i \\varepsilon_{\\mu \\nu q s } & \\frac{{\\hat{w}_8}}{m^2}&~. \\nonumber\\end{aligned}\\ ] ] with @xmath14 , etc . the corresponding gauge - invariant completions . in general\nthere are 4 unpolarized and 8 polarized structure functions in case of pure photon exchange .\nthe twist2 contributions can be described applying the factorization theorem .\nmoreover , a. mueller s generalized optical theorem allows to turn the isolated final state proton into an initial state anti - proton , being separated from the proton by @xmath1 . in this way\nthe _ diffractive state _ is formed , from which the hadronic tensor is obtained taking the forward expectation value of the compton - tensor . evaluating the process further using the above kinematic variables we are led to a description of the diffractive scattering cross section which does not require any reference to a pomeron picture , but is solely based on the presence of a large rapidity gap .\nin this approximation the number of structure functions reduces to two unpolarized and two polarized ones , because of the collinearity of @xmath15 and @xmath16 , @xcite . due to this the diffractive state simplifies and leads to a lorentz structure with lower complexity . for pure photon exchange only the structure functions @xmath17 resp .\n@xmath18 contribute , which in the twist-2 approximation obey a modified callan gross relation @xmath19 and the wandzura - wilczek , respectively . as shown in @xcite , the evolution equations , changing @xmath20 are the same as for inclusive deep \ninelastic scattering . to derive the diffractive evolution equations one considers the evolution equations for non forward scattering ref .\n[ 2b ] @xmath21 which turn into @xmath22 in the case @xmath23 .\nthe value of @xmath24 is determined by the absorptive condition as @xmath25 .\nat low values of @xmath3 and large values of @xmath2 both target mass and finite @xmath1effects become important . as shown in ref .\n@xcite , following @xcite , these effects have to be dealt with together .\nthe method is a generalization of the treatment of target mass effects in @xcite to the non forward case .\nthe now more complicated diffractive states @xmath26 imply that the pre - parton densities emerging in this case depend on two light \ncone variables @xmath27 , non of which can be integrated out . for further treatment\nwe define the variables @xmath28 the presence of the variable @xmath29 implies that the full lorentz structure outlined above contributes , assuming azimuthal angular integrals are not carried out .\nfour unpolarized and eight polarized structure functions contribute .\nthe partonic description being possible in the case @xmath30 at the level of observables does not hold anymore in this case , since @xmath15 and @xmath16 are no longer collinear .\ninstead , one has to perform definite integrals ( the @xmath29-integrals in @xcite ) over pre - partonic two - particle correlation functions , which can not be determined by experiment directly .\nthe absorptive condition in the present case is given by @xmath31 here @xmath32 takes the role of the nucleon mass in the case of forward scattering .\nit holds @xmath33 . as an example , we present the @xmath8 and @xmath1 corrections for the un - integrated unpolarized structure functions @xmath34\n@xcite : @xmath35^{1/2 } } \\phi_a^{(1)}(\\vartheta , \\zeta ) + \\frac{\\kappa^2 [ { \\cal p}^2]^2}{(q{\\cal p})^2-q^2{\\cal p}^2 } \\phi_a^{(2)}(\\vartheta , \\zeta ) \\nonumber\\\\ \\label{f2x } % ------------------------------------------------------------------------------ % ------------------------------------------------------------------------------ f^a_2(\\vartheta,\\zeta ) & \\equiv & % \\bigg [ \\phi_a^{(0)}(\\vartheta,\\zeta ) + \\frac{3\\kappa { \\cal p}^2}{[(q{\\cal p})^2-q^2{\\cal p}^2]^{1/2 } } \\phi_a^{(1)}(\\vartheta,\\zeta ) + \\frac{3\\kappa^2 [ { \\cal p}^2]^2}{(q{\\cal p})^2-q^2{\\cal p}^2 } \\phi_a^{(2)}(\\vartheta,\\zeta ) % \\bigg ] % \\\\ \\nonumber\\end{aligned}\\ ] ] here the @xmath36dependent distribution functions @xmath37 are iterated integrals of the correlation function @xmath38 , cf .\n@xmath39 denotes the respective kinematic invariant , implying kinematic dependences in general .\nalthough no partonic description is obtained one still may study , whether twist2 relations between structure functions exist . in case of the callan \ngross relation this is not expected , since it is absent also for forward scattering @xcite . however , the wandzura wilczek relation between the twist2 contributions of the polarized structure functions @xmath40 and @xmath41 holds also in the diffractive case for finite values @xmath42 , as in many other cases @xcite . here\nthe @xmath36integral can be carried out .\nthis is not the case for other structure functions . below this integral ,\nhowever , all the different structure functions can be represented by a _ single _\n@xmath36dependent two particle distribution function in the unpolarized and polarized case , respectively .\nthe different @xmath36dependence of the respective pre - factors and the fact that the @xmath36integral is definite prevents to access the corresponding pre \nparton distribution functions . at the twist2 level\ndiffractive parton distributions exist whenever the @xmath43 approximation holds . for large values of @xmath2 and small values of @xmath3\nthis is not the case .\nthis is also the kinematic region in which one expects higher twist operators to contribute in the light cone expansion .\nthe twist2 scaling violations of the diffractive structure functions in case of @xmath42 being finite are different from those in the limit @xmath44 .\nunlike the case there , the non forward evolution equations do not simplify in the same way and the @xmath36dependence will remain here too .\ndeep - inelastic diffractive scattering can be described taking the expectation value of the compton operator between the diffractive states @xmath45 obtained by applying a. mueller s generalized optical theorem . in the limit @xmath43\n, two polarized and two unpolarized structure functions contribute to the scattering cross section at twist @xmath46 .\nthey are related by a modified callan - gross relation ( in lowest order ) , resp .\nthe wandzura - wilzcek relation in all orders . target mass corrections accounting for all @xmath47-effects are required in the region of large values of @xmath2 and low values of @xmath3 .\nthe set of genuine diffractive structure functions becomes larger due to these effects : four unpolarized structure functions and eight polarized structure functions ( with one relation ) contribute .\nthese structure functions can be decomposed into generally different diffractive parton densities due to the @xmath29integral . in the case of @xmath43\nthe scaling violations of the twist @xmath46 contribution to the diffractive structure functions are described by the evolution equations for forward scattering replacing @xmath20 .\nthe present approach results into a thorough description demanding a rapidity gap without any need to invoke a `` pomeron '' .\n99 j. blmlein and d. robaschik , phys .\nb * 517 * ( 2001 ) 222 .\nd * 65 * ( 2002 ) 096002 .\nd. mller , d. robaschik , b. geyer , f. m. dittes and j. horejsi , fortsch .\n* 42 * ( 1994 ) 101 .\nj. blmlein , b. geyer and d. robaschik , nucl . phys .\nb * 560 * ( 1999 ) 283 ; + a. v. belitsky and a. v. radyushkin , phys .\n* 418 * ( 2005 ) 1 .\nj. blmlein , b. geyer and d. robaschik , nucl .\nb * 755 * ( 2006 ) 112 .\nb. geyer , d. robaschik and j. eilers , nucl .\nb * 704 * ( 2005 ) 279 .\na. v. belitsky and d. mller , phys .\nb * 507 * ( 2001 ) 173 .\nslides : ` http://indico.cern.ch/contributiondisplay.py?contribid=133&sessionid=4&confid=9499 ` h. georgi and h. d. politzer , phys .\nd * 14 * ( 1976 ) 1829 .\nj. blmlein and n. kochelev , phys .\nb * 381 * ( 1996 ) 296 ; nucl .\nb * 498 * ( 1997 ) 285 .\nj. blmlein and a. tkabladze , nucl .\nb * 553 * ( 1999 ) 427 .\nj. d. jackson , g. g. ross and r. g. roberts , phys .\nb * 226 * ( 1989 ) 159 ; + a. piccione and g. ridolfi , nucl .\nb * 513 * ( 1998 ) 301 ; + j. blmlein and d. robaschik , nucl .\nb * 581 * ( 2000 ) 449 ; + b. geyer and m. lazar , phys .\nd * 63 * ( 2001 ) 094003 ; + j. blmlein , v. ravindran and w. l. van neerven , phys .\nd * 68 * ( 2003 ) 114004 ; + b. geyer and d. robaschik , phys .\nd * 71 * ( 2005 ) 054018 .\nk. golec - biernat and a. luszczak , arxiv:0704.1608 [ hep - ph ] .", "role": "user" }, { "content": "we describe the twist-2 contributions to inclusive unpolarized and polarized deep - inelastic diffractive scattering in an operator approach . \n the representation refers to the observed large rapidity gap but does not require reference to a pomeron picture . \n we discuss both the case of vanishing target mass @xmath0 and momentum transfer @xmath1 as well as the effects at finite @xmath1 and @xmath0 , which lead to modifications at large @xmath2 and low values of @xmath3 .", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Regulated Erlin-dependent release of the B12 transmembrane J-protein promotes ER membrane penetration of a non-enveloped virus\nArticle:\nAbstract:\nThe molecular mechanism by which non-enveloped viruses penetrate biological membranes remains enigmatic. The non-enveloped polyomavirus SV40 penetrates the endoplasmic reticulum( ER) membrane to reach the cytosol and cause infection. We previously demonstrated that SV40 creates its own membrane penetration structure by mobilizing select transmembrane proteins to distinct puncta in the ER membrane called foci that likely function as the cytosol entry sites. How these ER membrane proteins reorganize into the foci is unknown. B12 is a transmembrane J-protein that mobilizes into the foci to promote cytosol entry of SV40. Here we identify two closely related ER membrane proteins Erlin1 and Erlin2( Erlin1/2) as B12-interaction partners. Strikingly, SV40 recruits B12 to the foci by inducing release of this J-protein from Erlin1/2. Our data thus reveal how a non-enveloped virus promotes its own membrane translocation by triggering the release and recruitment of a critical transport factor to the membrane penetration site.\nIntroduction:\nMembrane penetration represents a decisive event during virus infection. For enveloped viruses, fusion between the viral and host membranes delivers the core viral particle into the host cytosol[1, 2]. By contrast, because a non-enveloped virus lacks a surrounding lipid bilayer, its membrane transport process must be distinct from an enveloped virus. Indeed, membrane penetration by the non-enveloped virus families is not fully understood to date[1–3]. A central enigma that challenges this field is whether a non-enveloped virus hijacks pre-existing channels in the limiting membrane in order to enter the host, or if it generates a membrane transport portal de novo and subsequently crosses this structure to reach the host cytosol. Intriguingly, recent reports suggest that the non-enveloped polyomavirus( PyV) creates its own membrane transport structure to enter the host cell and cause infection[4–6], although aspects of this process remain to be clarified. PyV is a non-enveloped DNA tumor virus known to cause debilitating human diseases especially in immunocompromised individuals. For instance, the human JC PyV is responsible for the fatal demyelinating central nervous system disease progressive multifocal leukoencephalopathy, the BK PyV for BK-associated nephropathy and hemorrhagic cystitis, and the Merkel cell PyV for the aggressive skin cancer Merkel cell carcinoma[7, 8]. Structurally, a PyV particle is composed of 72 pentamers of the coat protein VP1, with each pentamer harboring either the internal hydrophobic protein VP2 or VP3[9–11]. The VP1 pentamers form the outer shell of the virus which in turn encases the 5 kilobase viral DNA genome. A complex network of disulfide bonds, in concert with VP1 C-terminal arms emanating from a pentamer that invade neighboring VP1 pentamers, stabilize the overall viral architecture[10, 11]. Because simian PyV SV40 displays both structural and genetic similarities to human PyVs such as JC and BK PyVs, studies of the SV40 infection pathway have historically illuminated human PyV infection pathways. To cause infection at the cellular level, SV40 binds to the ganglioside GM1 receptor on the plasma membrane[12, 13], entering the host cell via receptor-mediated endocytosis. Upon entry, the virus is initially sorted to endolyososomes[14, 15] before being routed to the endoplasmic reticulum( ER)[13, 16, 17]. Here the virus undergoes conformational changes imparted by ER-resident protein disulfide isomerase( PDI) family members[18, 19]. These reactions expose VP2 and VP3, generating a hydrophobic particle that physically binds to and integrates into the ER membrane[5]. The membrane-embedded virus is initially recognized by the ER membrane protein BAP31[5], transiently stabilized by the transmembrane protein EMC1[20], and eventually ejected into the cytosol by the Hsc70-SGTA-Hsp105 cytosolic extraction machinery[6, 21]. This machinery is associated with the cytosolic side of the ER membrane via interaction with three different ER membrane J-proteins called DNAJB12( B12), DNAJB14( B14) and DNAJC18( C18)[4, 6, 21, 22]. A J-protein typically binds to Hsp70 family proteins and stimulates their ATPase activity, enabling the Hsp70 proteins to efficiently capture their clients[23]. From the cytosol, the virus is further transported to the nucleus to cause lytic infection or cell transformation. Strikingly, prior to ER-to-cytosol membrane penetration, SV40 dynamically recruits B12, B14, and C18( as well as other membrane components) into discrete puncta in the ER membrane called foci[4, 6, 21]. The kinesin-1 motor promotes maturation of the foci[24]. Because the foci structures are postulated to function as the viral cytosol entry sites[5, 6, 21], SV40-triggered foci formation represents the first example of a non-enveloped virus creating its own membrane transport portal. What remains a major conundrum is how SV40 induces the reorganization of these membrane J-proteins into the foci. Using an unbiased proteomics approach, we identify two closely related ER membrane proteins Erlin1 and Erlin2( Erlin1/2), which preferentially localize in detergent-resistant membranes and hetero-oligomerize to form a massive protein complex[25–28], as B12-interacting partners. Erlin1/2 support SV40-induced foci formation, and promote virus ER-to-cytosol transport, and infection. However, Erlin1/2 themselves do not mobilize into the foci. Instead, our results indicate that these ER membrane proteins bind to and likely anchor B12 in the ER, releasing B12 into the foci upon SV40 infection. Our study thus pinpoints Erlin1/2-dependent release as a key regulatory event enabling B12 to efficiently reorganize into the foci, where this J-protein facilitates virus ER membrane penetration leading to successful infection.\nDiscussion:\nMembrane penetration by non-enveloped viruses remains an enigmatic process. One key question is whether the viral particle hijacks pre-existing protein-conducting channels embedded in the limiting membrane that would support the transport process, or if the virus creates de-novo membrane transport structures that facilitate membrane translocation. In the case of the non-enveloped SV40, where translocation across the ER membrane represents the decisive infection step, increasing evidence suggest that this virus does not exploit a pre-existing channel such as the ER membrane-bound E3 ubiquitin ligase Hrd1[5, 37, 38]. Hrd1 is the central component of the retro-translocation channel that translocates misfolded ER proteins to the cytosol for proteasomal degradation in a pathway called ER-associated degradation( ERAD;[39]). Instead, SV40 induces reorganization of select ER membrane components into distinct puncta in the ER membrane called foci that are postulated to serve as the cytosol entry sites[4–6, 21]. This represents the only example of a non-enveloped virus constructing its own membrane transport portal during entry. The J-protein B12 is one of the ER membrane proteins that mobilizes into the foci during SV40 infection[6]. In the foci, B12 assists in the recruitment of a cytosolic chaperone complex that ejects the virus into the cytosol in coordination with the two other transmembrane J-proteins B14 and C18[4, 6, 21]. However, the molecular basis by which B12 mobilizes into the foci and the host factors co-opted to regulate this process remain unknown. In this study, we identified two closely related ER membrane proteins Erlin1 and Erlin2( Erlin1/2) as cellular components that bind to B12 and facilitate B12’s reorganization into the SV40-induced foci. As proposed in a model depicted in Fig 9, we envision that Erlin1/2, which normally hetero-oligomerize, restrict B12 in the ER membrane by associating with B12. Upon arrival of SV40 to the ER lumen from the cell surface, it induces the release of B12 from the Erlin1/2 complex( step 1). The disengaged B12 in turn reorganizes into the foci in order to support ER-to-cytosol transport of SV40( step 2). At present, how SV40 triggers B12’s release from Erlins is unclear. It is possible that SV40 directly interacts with and induces conformational changes to either B12 or Erlin1/2, causing these components to lose affinity for each other. Alternatively, during SV40 infection, B12 might attract other ER or cytosolic factors that competitively interfere with binding to the Erlin proteins. Future experiments are needed to clarify this important point. Regardless of the mechanism, the release step is required for B12’s mobilization into the foci where it promotes virus infection as artificially locking B12 to Erlin2 prevents these downstream events from occurring. When Erlin1/2 is depleted, we found that endogenous B12 can mislocalize to the nucleus( Fig 9), suggesting that Erlins act as anchors, restricting B12 in the ER. Because Erlin1/2 have been shown to hetero-dimerize and form massive megadalton protein complexes[26–28], this intrinsic property may enable them to function as efficient anchoring factors. Consistent with this, another group demonstrated that overexpressed WT B12 similarly mislocalizes to the nucleus and forms nuclear globular structures termed DJANGOS[35], presumably due to insufficient levels of Erlins that are required to restrict the overexpressed proteins in the ER. The observation that an ER membrane protein such as B12 can localize incorrectly to the nucleus is not surprising since the ER membrane is topologically contiguous with the outer nuclear membrane. B14 and C18 also promote SV40 ER membrane penetration and infection[20, 22]. Intriguingly, both of these proteins reorganize into the foci in a virus-dependent manner[4, 6]. Because B14 does not bind to Erlin1/2, the mechanism by which it is recruited into the foci must be different than B12. However, as we previously demonstrated that C18 engages Erlin1/2[20], C18’s mechanism of release/recruitment into the foci might be similar to B12. Erlin1/2-dependent restriction of B12 in the ER is highly reminiscent of the mechanism by which Erlin1/2 restricts the ER membrane protein sterol-regulated element binding protein( SREBP) in the ER through a direct interaction with the SREBP-SCAP complex[40]. SREBP is normally kept in the ER but must mobilize to the Golgi when the cholesterol level is low. In the Golgi, SREBP is cleaved to generate an active transcription factor, which in turn moves to the nucleus to upregulate genes responsible for cholesterol synthesis[41]. The parallel finding that Erlins anchor yet another transmembrane protein in the ER suggests that Erlins might function as a general ER-anchoring factor. Moreover, given that Erlins have been shown to play a poorly-defined role in ERAD[39], the possibility that Erlins might act to restrict various ERAD membrane components in the ER should now be explored.", "role": "user" }, { "content": "Polyomavirus ( PyV ) is a non-enveloped DNA tumor virus that causes debilitating human diseases especially in immunocompromised individuals . At the cellular level , PyVs such as the simian PyV SV40 must enter a host cell and penetrate the ER membrane to reach the cytosol in order to cause infection . Prior to ER membrane transport , SV40 reorganizes select ER membrane proteins including the J-protein B12 to potential membrane penetration sites on the ER membrane called foci where B12 facilitates virus extraction into the cytosol . How B12 reorganizes into the foci is unclear . Here we find that two closely related ER membrane proteins Erlin1 and Erlin2 ( Erlin1/2 ) bind to B12 . During infection , SV40 induces release of this J-protein from Erlin1/2 to enable B12 to reorganize into the foci . Our data reveal how a non-enveloped virus mobilizes a specific ER membrane component to a membrane penetration structure to promote its own membrane transport .", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Survey: Motion planning algorithms for molecular simulations: A survey \nChapter Title: Energy Computation \n1. Abstract of Cited Paper (BIB001): Publisher Summary The chapter focuses on a general description of the force fields that are most commonly used at present, and it gives an indication of the directions of current research that may yield better functions in the near future. After a brief survey of current models, mostly generated during the 1990s, the focus of the chapter is on the general directions the field is taking in developing new models. The most commonly used protein force fields incorporate a relatively simple potential energy function: The emphasis is on the use of continuum methods to model the electrostatic effects of hydration and the introduction of polarizability to model the electronic response to changes in the environment. Some of the history and performance of widely used protein force fields based on an equation on simplest potential energy function or closely related equations are reviewed. The chapter outlines some promising developments that go beyond this, primarily by altering the way electrostatic interactions are treated. The use of atomic multipoles and off-center charge distributions, as well as attempts to incorporate electronic polarizability, are also discussed in the chapter. \n2. Abstract of Cited Paper (BIB002): Empirical force field-based studies of biological macromolecules are becoming a common tool for investigating their structure-activity relationships at an atomic level of detail. Such studies facilitate interpretation of experimental data and allow for information not readily accessible to experimental methods to be obtained. A large part of the success of empirical force field-based methods is the quality of the force fields combined with the algorithmic advances that allow for more accurate reproduction of experimental observables. Presented is an overview of the issues associated with the development and application of empirical force fields to biomolecular systems. This is followed by a summary of the force fields commonly applied to the different classes of biomolecules; proteins, nucleic acids, lipids, and carbohydrates. In addition, issues associated with computational studies on \"heterogeneous\" biomolecular systems and the transferability of force fields to a wide range of organic molecules of pharmacological interest are discussed. \n3. Abstract of Cited Paper (BIB003): Coarse-grained models for proteins and biomolecular aggregates have recently enjoyed renewed interest. Coarse-grained representations combined with enhanced computer power currently allow the simulation of systems of biologically relevant size (submicrometric) and timescale (microsecond or millisecond). Although these techniques still cannot be considered as predictive as all-atom simulations, noticeable advances have recently been achieved, mainly concerning the use of more rigorous parameterization techniques and novel algorithms for sampling configurational space. Moreover, the simulation size scales and timescales coincide with those that can be reached with the most advanced spectroscopic techniques, making it possible to directly compare simulation and experiment. \n4. Abstract of Cited Paper (BIB004): Many biologically interesting phenomena occur on a time scale that is too long to be studied by atomistic simulations. These phenomena include the dynamics of large proteins and self-assembly of biological materials. Coarse-grained (CG) molecular modeling allows computer simulations to be run on length and time scales that are 2–3 orders of magnitude larger compared to atomistic simulations, providing a bridge between the atomistic and the mesoscopic scale. We developed a new CG model for proteins as an extension of the MARTINI force field. Here, we validate the model for its use in peptide-bilayer systems. In order to validate the model, we calculated the potential of mean force for each amino acid as a function of its distance from the center of a dioleoylphosphatidylcholine (DOPC) lipid bilayer. We then compared amino acid association constants, the partitioning of a series of model pentapeptides, the partitioning and orientation of WALP23 in DOPC lipid bilayers and a series of KALP peptides in dimyris...\n\nLiterature Review:", "role": "user" }, { "content": "As mentioned in Section 2.2.1, there is a high similarity between the representation of robot configurations and molecular conformations. Yet, there is a fundamental difference that needs to be taken into account whenever dealing with molecules, which is the potential energy associated to conformations. Each molecular conformation has an energy level that depends on the interactions between its constituent atoms and with the surrounding molecules (e.g. the solvent). This energy is an indicator of how likely it is for the molecule to adopt this conformation (conformations with low energy are naturally preferred over conformations with high energy). Hence, the conformational space of the protein is not a binary space with only valid or invalid conformations, but a continuous space with conformations that are more or less likely to occur. For many applications, the algorithms must be able to find least energy paths rather than geometrically valid ones. Therefore, sampling-based algorithms need to be adjusted to cope with this by accepting or rejecting new conformations based on their energy level, and by associating transition probabilities between conformations based on the energy difference between them. The energy of a conformation can be computed with high precision using quantum mechanics ; however, it is highly time consuming and can be even intractable in large molecules, since it deals directly with the electronic structure of the molecule. Molecular mechanics is usually used to provide approximate energy values of protein conformations. Functions that compute energy based on molecular mechanics are usually called molecular force fields. They take as input the atom positions and evaluate energy based on different terms that vary from one force field to another. Yet, these terms usually include: changes in bond lengths and bond angles, bond torsions, Van der Waals interactions and electrostatic interactions. The choice of the terms and the shape of the function affect the accuracy of the computation, its speed, and its suitability to some types of molecular systems or applications. See BIB002 BIB003 for reviews on force fields and software packages that are widely used in the study of proteins. The drawback of using such all-atom force fields is that they are still computationally expensive, and thus, their usage can limit the size of the studied molecules and the time-scale of the performed simulations. This has motivated the introduction of coarse-grained force fields BIB004 . These force fields measure interactions between blocks of functional groups rather than between the individual atoms. This leads to a rough approximation of the actual force field, but also to a significant performance gain. Some examples of coarse-grained force fields are MARTINI BIB005 and OPEP BIB001 .", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: A framework for learning sparse topic representations from relational document networks.\n\nKeyphrases: link prediction\n\nDataset descriptions:\nAMiner: The AMiner Dataset is a collection of different relational datasets. It consists of a set of relational networks such as citation networks, academic social networks or topic-paper-autor networks among others.\nCC100: This corpus comprises of monolingual data for 100+ languages and also includes data for romanized languages. This was constructed using the urls and paragraph indices provided by the CC-Net repository by processing January-December 2018 Commoncrawl snapshots.\nKdConv: KdConv is a Chinese multi-domain Knowledge-driven Conversation dataset, grounding the topics in multi-turn conversations to knowledge graphs. KdConv contains 4.5K conversations from three domains (film, music, and travel), and 86K utterances with an average turn number of 19.0.\nCora: The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links.\n\nOptions: A: AMiner B: CC100 C: KdConv D: Cora", "role": "user" }, { "content": "Cora", "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:\nmTOR Regulates Nox4-Mediated Podocyte Depletion in Diabetic Renal Injury. Podocyte apoptosis is a critical mechanism for excessive loss of urinary albumin that eventuates in kidney fibrosis. Pharmacological doses of the mTOR inhibitor rapamycin reduce albuminura in diabetes. We explored the hypothesis that mTOR mediates podocyte injury in diabetes. High glucose (HG) induces apoptosis of podocytes, inhibits AMPK activation, inactivates tuberin and activates mTOR. HG also increases the levels of Nox4 and Nox1 and NADPH oxidase activity. Inhibition of mTOR by low dose rapamycin decreases HG-induced Nox4 and Nox1, NADPH oxidase activity and podocyte apoptosis. Inhibition of mTOR had no effect on AMPK or tuberin phosphorylation indicating that mTOR is downstream of these signaling molecules. In isolated glomeruli of OVE26 mice, there is similar decrease in the activation of AMPK and tuberin and activation of mTOR with increase in Nox4 and NADPH oxidase activity. Inhibition of mTOR by small dose of rapamycin reduces podocyte apoptosis, attenuates glomerular injury and albuminuria. Our data provide evidence for a novel function of mTOR in Nox4-derived ROS generation and podocyte apoptosis that contributes to urinary albumin excretion in type 1 diabetes. Thus mTOR and or NADPH oxidase inhibition may represent a therapeutic modality of diabetic kidney disease.", "role": "user" }, { "content": "[[\"rapamycin\", \"INHIBITOR\", \"NADPH oxidase\"], [\"glucose\", \"DOWNREGULATOR\", \"tuberin\"], [\"rapamycin\", \"INHIBITOR\", \"mTOR\"], [\"glucose\", \"INHIBITOR\", \"AMPK\"], [\"rapamycin\", \"INDIRECT-DOWNREGULATOR\", \"Nox1\"], [\"glucose\", \"ACTIVATOR\", \"mTOR\"], [\"rapamycin\", \"INDIRECT-DOWNREGULATOR\", \"Nox4\"]]", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to develop an object tracker for videos.\n\nKeyphrases: object tracking video\n\nDataset descriptions:\nCOCO-Tasks: Comprises about 40,000 images where the most suitable objects for 14 tasks have been annotated.\nCDTB: dataset is recorded by several passive and active RGB-D setups and contains indoor as well as outdoor sequences acquired in direct sunlight. The sequences were recorded to contain significant object pose change, clutter, occlusion, and periods of long-term target absence to enable tracker evaluation under realistic conditions.\nVOT2016: VOT2016 is a video dataset for visual object tracking. It contains 60 video clips and 21,646 corresponding ground truth maps with pixel-wise annotation of salient objects.\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: COCO-Tasks B: CDTB C: VOT2016 D: SNIPS", "role": "user" }, { "content": "VOT2016", "role": "assistant" } ]

[ { "content": "Answer the question with YES, NO, or MAYBE based on the abstract.\n\nAbstract:\n(OBJECTIVES) Currently, a 'pedagogical gap' exists in distributed medical education in that distance educators teach medical students but typically do not have the opportunity to assess them in large-scale examinations such as the objective structured clinical examination (OSCE). We developed a remote examiner OSCE (reOSCE) that was integrated into a traditional OSCE to establish whether remote examination technology may be used to bridge this gap. The purpose of this study was to explore whether remote physician-examiners can replace on-site physician-examiners in an OSCE, and to determine the feasibility of this new examination method.\n(METHODS) Forty Year 3 medical students were randomised into six reOSCE stations that were incorporated into two tracks of a 10-station traditional OSCE. For the reOSCE stations, student performance was assessed by both a local examiner (LE) in the room and a remote examiner (RE) who viewed the OSCE encounters from a distance. The primary endpoint was the correlation of scores between LEs and REs across all reOSCE stations. The secondary endpoint was a post-OSCE survey of both REs and students.\n(RESULTS) Statistically significant correlations were found between LE and RE checklist scores for history taking (r = 0.64-r = 0.80), physical examination (r = 0.41-r = 0.54), and management stations (r = 0.78). Correlations between LE and RE global ratings were more varied (r = 0.21-r = 0.77). Correlations on three of the six stations reached significance. Qualitative analysis of feedback from REs and students showed high acceptance of the reOSCE despite technological issues.\n\nQuestion:\nThe objective structured clinical examination: can physician-examiners participate from a distance?\n\nAnswer:", "role": "user" }, { "content": "YES", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nMicro/nanostructured hyaluronic acid matrices with tuned swelling and drug release properties. Hyaluronic acid (HA) hydrogels were structured in the form of porous monoliths by means of the ice-segregation-induced self-assembly (ISISA) method coupled with freeze-drying. Physical and chemical parameters were explored in order to fine-tune the microstructure and the incidence on both swelling and dissolution behavior in aqueous media. Gentamicin-loaded HA matrices with tuned drug release properties were also prepared; their inherent properties and behavior in solution are discussed in the framework of thermal analysis and scanning electron microscopy inspection.", "role": "user" }, { "content": "{\"Chemical\": [\"Gentamicin\"]}", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nPlatinum folate nanoparticles toxicity: cancer vs. normal cells. Almost for two decades metallic nanoparticles are successfully used for cancer detection, imaging and treatment. Due to their high electron density they can be easily observed by electron microscopy and used in laser and radiofrequency therapy as energy releasing agents. However, the limitation for this practice is an inability to generate tumor-specific heating in a minimally invasive manner to the healthy tissue. To overcome this restraint we proposed to use folic acid coated metallic nanoparticles and determine whether they preferentially penetrate cancer cells. We developed technique for synthesizing platinum nanoparticles using folic acid as stabilizing agent which produced particles of relatively narrow size distribution, having d=2.3 ± 0.5 nm. High resolution TEM and zeta potential analysis indicated that the particles produced by this method had a high degree of crystalline order with no amorphous outer shell and a high degree of colloidal stability. The keratinocytes and mammary breast cells (cancer and normal) were incubated with platinum folate nanoparticles, and the results showed that the IC50 was significantly higher for the normal cells than the cancer cells in both cases, indicating that these nanoparticles preferentially target the cancer cells. TEM images of thin sections taken from the two types of cells indicated that the number of vacuoles and morphology changes after incubation with nanoparticles was also larger for the cancer cells in both types of tissue studied. No preferential toxicity was observed when folic acid receptors were saturated with free folic acid prior to exposure to nanoparticles. These results confirm our hypothesis regarding the preferential penetration of folic acid coated nanoparticles to cancer cells due to receptor mediated endocytosis.", "role": "user" }, { "content": "{\"Chemical\": [\"platinum folate\", \"Platinum folate\", \"folic acid\", \"platinum\"]}", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Survey on cooperative medium access control protocols \nChapter Title: F. Security Issues for Cooperative MAC Protocols \n1. Abstract of Cited Paper (BIB001): While the fundamental premise of peer-to-peer (P2P) systems is that of voluntary resource sharing among individual peers, there is an inherent tension between individual rationality and collective welfare that threatens the viability of these systems. This paper surveys recent research at the intersection of economics and computer science that targets the design of distributed systems consisting of rational participants with diverse and selfish interests. In particular, we discuss major findings and open questions related to free-riding in P2P systems: factors affecting the degree of free-riding, incentive mechanisms to encourage user cooperation, and challenges in the design of incentive mechanisms for P2P systems.\n\nLiterature Review:", "role": "user" }, { "content": "As cooperative transmission involves not only the source node and the destination node but also helper nodes. Despite the promising performance enhancement, security is an important aspect that may restrict the application of cooperative transmission in the real world. The security issue has been extensively studied in the multi-hop ad hoc network, which has a topology similar to that of a cooperative network BIB001 . However, the existing security solutions need to be extended when applied to a general cooperative network 55] . From the MAC-layer perspective, there are typical misbehaviors that may lead to security threats. • Selfish. In this case, an isolated node does not respond to any cooperation request even if the system performance can be improved. This case is not strictly a security issue, and a well-designed stimulation strategy as discussed in Section IV-E may properly address that. In the other case, there is a potential security risk since a free-riding node tends to request cooperation from others to transmit its packets but usually declines to help others BIB002 . A secure cooperative MAC protocol should be able to detect such behavior and alleviate its impact via some kind of punishment for example. • Obstructing. There are three common misbehaviors of an obstructing node. The first one is a lying node that gives false feedback. For example, a helper node may pretend to be an optimal choice but not cooperate at all. A credit list of reliable helpers, or a blacklist of notorious helpers can be 20 maintained to prevent liars. It is worth noting that incorrect feedback may also be caused by mobility or fading. As a result, a node that feeds back incorrect information is not necessarily a lying node. A secure cooperative MAC protocol should distinguish between them. The second case is a cheating helper that tampers the content of a relaying packet for its own benefit. To prevent this type of cheating, the destination entity can provide direct feedback to the source, so that the source and the destination can identify a cheating node by checking with each other. However, this is not feasible for a pure relay solution such as in ADC-MAC, in which the feedback from the destination is also relayed by the cheating helper who may modify the content of the feedback as well. To prevent cheating in a pure relay case, the destination can randomly choose another neutral helper to relay the feedback and check the credibility of the previous helper. The third type of misbehavior is called jamming, which exists in the diversity scenario with multiple helpers. A jamming helper may intentionally transmit wrong signals to interfere with the receiving of the destination. Jamming can be even more complicated than the first two cases, since multiple helpers are involved. Both the source and the destination need to cooperate so as to detect a jamming helper. For example, a blacklist could be provided by the source. By checking each one in the blacklist, a jamming helper may be investigated. • Spying. Spying nodes are not the destinations but attempt to probe the content of a packet. Although it is a common security issue in both wired and wireless networks, it cannot be easily solved for cooperative wireless networks. This is because the helpers need to be authorized to examine some information in the packet to properly forward it. Meanwhile, the confidential information in the packet can be encrypted and made only available to the source and the destination to protect user privacy.", "role": "assistant" } ]