Datasets:

---

kejian

/

SciRIFF-4096-0214-v1

like 0

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nDisulfide bond mapping of Pfs25, a recombinant malaria transmission blocking vaccine candidate\n\nPaper sections:\n\n<p>The Plasmodium falciparum surface protein Pfs25 [1], [2], [3], has long been presented as a potential transmission-blocking vaccine (TBV) candidate for parasite elimination [4], [5], [6] and control of malaria. The expression, purification, and characterization of the Pfs25 antigen has also been well presented from various heterologous expression systems including yeast [7], [8], [9], E. coli\n[10], plant [11], algae [12], and recently baculovirus [13]. An important consideration in the selection of expression system and production of recombinant proteins is maintaining the native presentation and conformation of the molecule to raise antibodies that would recognize (and interfere) with those proteins found on the parasite itself. The proper disulfide bond formation of the molecule would be critical not only for proper protein folding but also for the stabilization of the molecule including its tertiary structure. This is especially true for the development of TBV candidates, where the native proteins are often complex, disulfide-rich molecules, where native conformation would be required to elicit the proper antibody response to block the parasite [14]. The importance of disulfide pairing has been demonstrated in a reduction alkylation experiment, which abolished the functional activity of Pfs25 [13],</p><p>However, methods to effectively map the eleven disulfide bonds present in Pfs25 and confirm proper pairing had yet to be reported, an important step in the development of recombinant vaccine antigens. The effort by Gregory et al. [12] was the last reported attempt to disulfide bond map Pfs25. When the disulfide bonds from algae Pfs25 were identified and compared to the yeast-produced homologue Pvs25 [15], they found that disulfide bonds one, four, and six were intact; however, disulfide bonds two, seven, eight, ten, and eleven may not have been completely formed [12]. The complex, compact and unusual structure of Pfs25 [2], [16] may have contributed to difficulties in prior attempts to analyze the disulfide pairs of Pfs25. Here, we report an optimized digestion and analysis methodology to confirm the 22 cysteines are arranged in 11 disulfide pairs in our baculovirus-expressed Pfs25 [13].</p><p>In this study, we first utilized a plant-produced Pfs25 [11] to optimize the digestion and analysis methodology. The plant based Pfs25 was selected for method development, as this protein had served as reference standard during the development of baculovirus derived Pfs25 [13], including its efficacy and transmission-reducing activity previously demonstrated [11], [13]. Given that the molecule was previously established (both in biochemical and in vivo) characterization prior to the development of our baculovirus Pfs25, it was thought to serve as a suitable control for method development while the baculovirus Pfs25 was undergoing process development. Initially TCEP (Tris-2 carboxyethyl phosphine HCl) followed by Trypsin and Glu-C digestion was employed. Given difficulties, due to the compact nature of the molecule [2], [16], a portion of the structure may not have been accessible to proteolytic digestion and attempts were made to optimize digestion using Lys-C (data not shown). The enzyme mixture (Trypsin/Lys-C), combined with overnight digest, followed by an additional enzymatic digestion the subsequent day, significantly improved digestion and resulted in a higher intensity for the MS/MS (MSE) fragments (data not shown).</p><p>The optimized denaturation and digestion was applied to the baculovirus-expressed Pfs25, which we previously reported as a pure, stable, and well characterized protein with no free thiol as determined by Measure iT [13]. A total of 100 μL Pfs25 (1 mg/mL in 20 mM HEPES, 150 mM NaCl, pH 7.0 [13]) was denatured at 80 °C for 30 min then diluted with 100 μL of 1 M Tris-HCl pH 8.0 buffer (Sigma-Aldrich; St. Louis, MO). A total of 20 μL trypsin/Lys-C mix (Promega; Madison, WI) at 1 μg/μL was added and the sample incubated at 37 °C overnight. An additional 20 μL of trypsin/Lys-C was added the following day and the sample further incubated at 37 °C for 3–4 h.</p><p>Method for separation and ESI-MS conditions for Pfs25.</p><p>Trifluoroacetic acid.</p><p>Acetonitrile.</p><p>For mass spectrometric (MS) analysis, a QTOF Premier mass spectrometer (Waters Corporation; Milford, MA) equipped with an electrospray source and lock spray run in positive mode (ES+) was used. MS data was acquired in MSE mode using MassLynx v4.1 (Waters Corporation; Milford, MA). Tuning mix solution (Agilent ESI-L Tuning Mix, Cat# G1969-85000; diluted 1:10 in acetonitrile) was infused into the ion source at a flow rate of 1–15 μL/min in the reference channel at 10 s intervals. Full conditions are presented in Table 1.</p><p>The mass spectral data was analyzed using BiopharmaLynx 1.3 (Waters Corporation; Milford, MA). The theoretical disulfide bonds were entered into the sequence editor and observed mass spectral peaks compared to the theoretical digests. MassLynx was utilized to validate the observed peptide linkage mass (precursor ion) and BiopharmaLynx was used to confirm disulfide bond linkages by evaluating the observed MSE fragmentation patterns (product ion) against the theoretical patterns based on the sequence and disulfide bonds linked in the editor. The BiopharmaLynx data analysis included an evaluation of scrambled disulfide bonds.</p><p>Pfs25 disulfide pairing as experimentally confirmed by LC-MS/MS. Amino acid sequence of baculovirus-expressed Pfs25 indicating disulfide bond locations and cysteine pairing. Cysteine locations are indicated in red, with disulfide pairs indicated by superscript number and brackets (or arrows) as experimentally confirmed in this study. Digested peptides are indicated by T#. Mutations from asparagine to glutamine are indicated in orange. A residual aspartic acid (underline) on the N-terminus is from the Honeybee Melittin secretion signal sequence. C-terminal six histidine affinity tag indicated by (Blue underline).</p><p>Disulfide bond (SS1 Cys10-Cys24) linked peptides T2 and T4 with a theoretical peptide mass of 2323.1375 Da and an observed mass of 2323.1152 (m/z 775.3790 for the 3+ charge state). Twenty fragment ions supported the elucidation of disulfide bond SS1 (See Table 3, Fig. 1 in Ref. [17]).</p><p>Disulfide bond (SS2 Cys26-Cys38) was an internal linkage of peptide T5 with a theoretical mass of 1863.7866 Da and an observed mass of 1863.7752 Da (m/z 932.8949 for the 2+ charge state). Thirty-six fragment ions supported the elucidation of disulfide bond SS2 (See Table 4, Fig. 2 in Ref. [17]).</p><p>Disulfide bond (SS3 Cys45-Cys60) linked peptides T7 and T9 with a theoretical mass of 853.3674 Da and an observed mass of 853.3656 Da (m/z 854.3729 for the 1+ charge state). Six fragment ions supported the elucidation of disulfide bond SS3 (See Table 5, Figure 3 in Ref. [17]).</p><p>Disulfide bond (SS4 Cys54-Cys72) linked peptides T8 and T10 with a theoretical mass of 2358.0670 Da and an observed mass of 2358.0799 Da (m/z 787.0339 for the 3+ charge state). Forty-five fragment ions supported the elucidation of disulfide bond SS4 (See Table 6, Figure 4 in Ref. [17]).</p><p>Disulfide bond (SS5 Cys74-Cys85) was an internal disulfide bond of peptide T11 and (SS6 Cys90-Cys100) linked peptides T11 and T13. The theoretical mass of this peptide was 3112.3796 Da and an observed mass of 3112.3534 Da reported herein (m/z 1038.4584 for the 3+charge state). Four fragment ions were consistent with the internal SS5 and 33 fragment ions supported SS6. An additional 44 fragment ions supported the combined linkage of SS5 and SS6 (See Table 7, Figure 5 in Ref. [17]).</p><p>Disulfide bond (SS7 Cys95-Cys113) linked peptides T12 and T14 and (SS8 Cys115-Cys129) linked peptides T14 and T16, resulting in three peptide linkages in the digest. The theoretical mass for the peptide linking T12, T14, and T16 was 2117.9326 Da and an observed mass of 2117.9182 Da reported herein (m/z 706.9800 for the 3+ charge state). Three fragment ions were specific to the linkage between T12 and T14 and confirmed SS7. Four fragment ions were specific to the linkage between T14 and T16 and confirmed SS8. An additional 21 fragment ions were consistent with the linkage of T12, T14 and T16 (See Table 8, Figure 6 in Ref. [17]).</p><p>Disulfide bond (SS9 Cys137-Cys148) linked peptides T18 and T20 with a theoretical mass of 1169.5056 Da and an observed mass of 1169.4970 Da (m/z 585.7558 for the 2+ charge state). Twenty-five fragment ions supported the elucidation of disulfide bond SS9 (See Table 9, Figure 7 in Ref. [17]).</p><p>Disulfide bond (SS10 Cys141-Cys157) linked peptides T19 to T22 and disulfide bond (SS11 Cys159-Cys172) linked peptide T22 to T23. The theoretical mass for this tri-peptide was 3074.3003 Da and an observed mass of 3074.2795 Da reported herein (m/z 1025.7671 for the 3+ charge state). Eleven fragment ions were specific to the linkage of T19 and T22 and confirmed SS10. Three fragment ions were specific to the linkage between peptides T22 and T23 and confirmed SS11. An additional 32 fragment ions were consistent with the linkage of T19, T22 and T23 (See Table 10, Figure 8 in Ref. [17]).</p><p>In this study, we described a novel methodology that supported elucidation of the complex disulfide bonding pattern of Pfs25. These data are consistent with our previous report that the final purified protein adopted a fully oxidized form, with all 22 cysteines arranged in disulfide pairs [13]. Further, the data is consistent with the predicted disulfide bond formation for Pfs25 based on x-ray crystallography analysis of the homologue, Pvs25 [15].</p><p>While the transmission-reducing efficacy of Pfs25 has been demonstrated in a variety of studies, including algae [12] initially with Freund's adjuvant (and later with four additional adjuvants including aluminum hydroxide) [18] and our own [13] baculovirus Pfs25 with ISA720, the two were not directly compared in a single study with harmonized doses, routes and animal models. Therefore, we cannot extrapolate the importance of proper disulfide bond formation in eliciting transmission-reducing activity, but have previously shown that when disulfide bonds are broken, transmission-reducing activity is abolished [13].</p><p>This analysis is the first known and reported disulfide mapping of a recombinant Pfs25 with proper bond formation (according to the Pvs25 structure) and provides a methodology that may be applicable to other complex, heavily disulfide-linked Plasmodium proteins.</p>\n\nFunding\n<p>The work was supported by the Bill & Melinda Gates Foundation. The views expressed herein are solely those of the authors and do not necessarily reflect the views of the Foundation.</p>\n\nConflict of interest disclosure\n<p>None. The authors' declare they have no competing interests.</p>", "role": "user" }, { "content": "A liquid chromatography tandem-mass spectrometry method was developed to map the eleven disulfide bonds in Pfs25, a malaria transmission-blocking vaccine candidate. The compact and complex nature of Pfs25 has led to difficulties in prior peptide mapping efforts. Here, we report confirmation of proper disulfide pairing of a recombinant Pfs25, by optimizing denaturation and digestion with trypsin/Lys-C. The digested peptides were separated by reversed phase HPLC to obtain the peptide map and elucidate the disulfide linkages. MSE fragmentation confirmed the digested peptides and disulfide bonds. The eleven disulfide bonds and locations matched the predicted Pvs25 crystal structure, a Pfs25 homologue.", "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:\nUric Acid Levels Are Relevant in Patients With Stroke Treated With Thrombolysis\nAbstract 1:\nBackground and Purpose — Uric acid ( UA ) is a neuroprotective antioxidant that improves the benefits of alteplase in experimental ischemia . However , it is unknown whether endogenous UA also influences the response to thrombolysis in patients with stroke . Methods — A total of 317 consecutive patients treated with thrombolysis were included in a prospect i ve stroke registry . Demographics , laboratory data , neurological course , and infa rct ion volume were prospect ively collected . Excellent outcome was defined as achieving a modified Rankin Scale score < 2 at 90 days . Binary and ordinal logistic regression models were used to analyze modified Rankin Scale score at 90 days . Results — UA levels were significantly higher in patients with an excellent outcome than in patients with a poor outcome ( 5.82 [ 1.39 ] versus 5.42 [ 1.81 ] , P=0.029 ) . In multivariate models , increased UA levels ( OR , 1.23 ; 95 % CI , 1.03 to 1.49 ; P=0.025 ) were associated with an excellent outcome and with an increased risk of shifting to a better category across the modified Rankin Scale ( OR , 1.19 ; 95 % CI , 1.04 to 1.38 ; P=0.014 ) independently of the effect of confounders . The levels of UA and the volume of final infa rct ion were inversely correlated ( r=−0.216 , P<0.001 ) and the inverse correlation remained after adjustment for age , sex , and baseline National Institutes of Health Stroke Scale score ( t value=−2.54 , P=0.01 ) . Significantly lower UA levels were found in patients with malignant middle cerebral artery infa rct ion and parenchymal hemorrhage postthrombolysis . Conclusions — Increased UA serum levels are associated with better outcome in patients with stroke treated with reperfusion therapies . These results support the assessment of the potential neuroprotective role of the exogenous administration of UA in patients with stroke treated with thrombolysis\n\n\nTitle 2:\nSafety and efficacy of uric acid in patients with acute stroke (URICO-ICTUS): a randomised, double-blind phase 2b/3 trial\nAbstract 2:\nINTRODUCTION Uric acid is an antioxidant with neuroprotective effects in experimental models of stroke . We assessed whether uric acid therapy would improve functional outcomes at 90 days in patients with acute ischaemic stroke . METHODS URICO-ICTUS was a r and omised , double-blind , placebo-controlled , phase 2b/3 trial that recruited patients with acute ischaemic stroke admitted to ten Spanish stroke centres . Patients were included if they were aged 18 years or older , had received alteplase within 4·5 h of symptom onset , and had an eligible National Institutes of Health Stroke Scale ( NIHSS ) score ( > 6 and ≤25 ) and premorbid ( assessed by anamnesis ) modified Rankin Scale ( mRS ) score ( ≤2 ) . Patients were r and omly allocated ( 1:1 ) to receive uric acid 1000 mg or placebo ( both infused intravenously in 90 min during the infusion of alteplase ) , stratified by centre and baseline stroke severity . The primary outcome was the proportion of patients with excellent outcome ( ie , an mRS score of 0 - 1 , or 2 if premorbid score was 2 ) at 90 days , analysed in the target population ( all r and omly assigned patients who had been correctly diagnosed with ischaemic stroke and had begun study medication ) . The study is registered with Clinical Trials.gov , number NCT00860366 . FINDINGS Between July 1 , 2011 , and April 30 , 2013 , we r and omly assigned 421 patients , of whom 411 ( 98 % ) were included in the target population ( 211 received uric acid and 200 received placebo ) . 83 ( 39 % ) patients who received uric acid and 66 ( 33 % ) patients who received placebo had an excellent outcome ( adjusted risk ratio 1·23 [ 95 % CI 0·96 - 1·56 ] ; p=0·099 ) . No clinical ly relevant or statistically significant differences were reported between groups with respect to death ( 28 [ 13 % ] patients who received uric acid vs 31 [ 16 % ] who received placebo ) , symptomatic intracerebral haemorrhage ( nine [ 4 % ] vs six [ 3 % ] ) , and gouty arthritis ( one [ < 1 % ] vs four [ 2 % ] ) . 516 adverse events occurred in the uric acid group and 532 in the placebo group , of which 61 ( 12 % ) and 67 ( 13 % ) , respectively , were serious adverse events ( p=0·703 ) . INTERPRETATION The addition of uric acid to thrombolytic therapy did not increase the proportion of patients who achieved excellent outcome after stroke compared with placebo , but it did not lead to any safety concerns . FUNDING Institute of Health Carlos III of the Spanish Ministry of Health and Fundación Doctor Melchor Colet\n\n\nTitle 3:\nAntioxidant Profile and Early Outcome in Stroke Patients\nAbstract 3:\nBackground and Purpose Experimental studies provide evidence of an association between ischemic stroke and increased oxidative stress , but data in humans are still limited and controversial . The purpose of this study was to investigate the time course of plasma antioxidant changes in ischemic stroke patients . Methods Plasma antioxidants , including water-soluble ( vitamin C and uric acid ) and lipid-soluble ( vitamins A and E ) compounds as well as antioxidant enzyme activities in plasma ( superoxide dismutase [ SOD ] and glutathione peroxidase ) and erythrocytes ( SOD ) , were measured by high-performance liquid chromatography ( antioxidant vitamins ) and by spectrophotometry ( antioxidant enzymes ) in 38 subjects ( 25 men and 13 women aged 77.2±7.9 years ) with acute ischemic stroke of recent onset ( < 24 hours ) on admission , after 6 and 24 hours , and on days 3 , 5 , and 7 . Antioxidant levels in patients on admission were compared with those of age- and sex-matched controls . Results Mean antioxidant levels and activities in patients on admission were lower than those of controls and showed a gradual increase over time . Patients with the worst early outcome ( death or functional decline ) had higher vitamin A and uric acid plasma levels and lower vitamin C levels and erythrocyte SOD activity than those who remained functionally stable . Conclusions These results suggest that the majority of antioxidants are reduced immediately after an acute ischemic stroke , possibly as a consequence of increased oxidative stress . A specific antioxidant profile is associated with a poor early outcome\n\n\nTitle 4:\nThe Urico-Ictus Study, a Phase 3 Study of Combined Treatment with Uric Acid and rtPA Administered Intravenously in Acute Ischaemic Stroke Patients within the First 4.5 H of Onset of Symptoms\nAbstract 4:\nRationale Oxidative stress is a major contributor to brain damage in patients with ischaemic stroke . Uric acid ( UA ) is a potent endogenous antioxidant molecule . In experimental ischaemia in rats , the exogenous administration of uric acid is neuroprotective and enhances the effect of rtPA . Moreover , in acute stroke patients receiving rtPA within 3 h of stroke onset , the intravenous administration of uric acid is safe , prevents an early decline in uric acid levels and reduces an early increase in oxidative stress markers and in active matrix metalloproteinase nine levels . Aim To determine whether the combined treatment with uric acid and rtPA is superior to rtPA alone in terms of clinical efficacy in acute ischaemic stroke patients treated within the first 4.5 h of onset of symptoms . Study design Multicentre , interventional , r and omised , double-blind and vehicle-controlled efficacy study with parallel assignment ( 1:1 ) . Estimated enrolment : 420 patients over 3 years , starting in January 2010 . Treatment arms included patients will receive a single intravenous infusion of 1 g of UA dissolved in a vehicle ( 500 ml of 0.1 % lithium carbonate and 5 % mannitol ) ( n = 210 ) or vehicle alone ( n = 210 ) . Inclusion and exclusion criteria : the study will include patients older than 18 years , treated with rtPA within the first 4.5 h of clinical onset and with a baseline National Institute of Health Stroke Scale score > 6 and < 25 and a modified Rankin Scale score ≤ 2 before the ischaemic event . Patients with renal insufficiency , gout or asymptomatic hiperuricaemia treated with allopurinol will be excluded . Study outcomes The primary outcome measure is the proportion of patients achieving an modified Rankin Scale of 0 to 1 at 3 months after treatment or two in those patients with a prior qualifying modified Rankin Scale of 2 . Secondary outcome measures include the final infa rct ion volume measured at 72 h and the proportion of patients with symptomatic intracranial haemorrhage ( ≥ 4 points of increase in the National Institute of Health Stroke Scale score )\n\n\nTitle 5:\nUrate predicts subsequent cardiac death in stroke survivors.\nAbstract 5:\nAIMS To test the hypothesis that urate predicts cardiac death after stroke independent of conventional risk factors of atherosclerosis , creatinine and diuretic use . METHODS AND RESULTS Serum urate concentration was measured in an unselected cohort of 354 stroke survivors who were followed-up for a median of 2.8 years . Cardiac death was the primary end-point . Urate was associated with a statistically significant threefold increase in relative risk of cardiac death even after adjustment for other conventional risk factors . In the subgroup of patients who were not on diuretics , raised urate was associated with a 12-fold significant increase in relative risk of cardiac death after adjusting for renal function and other conventional risk factors . A urate concentration of greater than 0.31 mmol . l(-1 ) was 78 % sensitive at predicting cardiac death within 5 years after stroke , but was only 54 % specific . If urate exceeded 0.38 mmol . l(-1 ) , specificity of predicting cardiac death within 5 years after stroke was 88 % . CONCLUSIONS Elevated serum urate concentration may be used to stratify risk of future cardiac death after stroke . This appeared to be true even in stroke survivors who were not on diuretic therapy\n\n\nTitle 6:\nIs uric acid protective or deleterious in acute ischemic stroke? A prospective cohort study.\nAbstract 6:\nContrasting observations have been made between serum urate and ischemic stroke outcomes in studies involving Caucasian population s. To assess the hypothesis that urate is associated with stroke outcomes , a prospect i ve follow-up study was performed in a cohort of Asian patients with ischemic stroke . Patients diagnosed with transient ischemic attack , first or recurrent ischemic stroke were included in this study . Serum urate , measured using high-performance liquid chromatography , was correlated with 12-month functional and vascular stroke outcomes . Poor functional outcome was defined as a modified Rankin scale exceeding 2 and vascular outcome was defined as a composite of recurrent stroke , myocardial infa rct ion or vascular death during the study period . A total of 503 patients of mean age 63 ( SD 12 ) years were included . A U-shaped relationship between urate quartiles and poor functional outcomes was demonstrated . More patients with low ( < 280microM ) and high ( > 410microM ) urate levels had poor functional outcomes ( 36 % and 27 % respectively ) , compared to those with urate levels between 340 and 410microM ( 14 % ) . No significant relationship was observed between urate and vascular outcomes . Depending on its level , serum urate may exhibit protective and deleterious effects on stroke outcomes", "role": "user" }, { "content": "This meta- analysis supports that serum uric acid level has a protective effect on neurological outcome after acute ischemic stroke .\nHigh uric acid level at the onset is a biomarker of better prognosis in patients with acute ischemic stroke", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: A system for learning disentangled representations that encode descriptive characteristics of the data distribution.\n\nKeyphrases: data representation learning images top-down maps autonomous driving\n\nDataset descriptions:\nSentEval: SentEval is a toolkit for evaluating the quality of universal sentence representations. SentEval encompasses a variety of tasks, including binary and multi-class classification, natural language inference and sentence similarity.\nirc-disentanglement: This is a dataset for disentangling conversations on IRC, which is the task of identifying separate conversations in a single stream of messages. It contains disentanglement information for 77,563 messages or IRC.\nCUB-200-2011: The Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset is the most widely-used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds, 5,994 for training and 5,794 for testing.\nCelebA: CelebFaces Attributes dataset contains 202,599 face images of the size 178×218 from 10,177 celebrities, each annotated with 40 binary labels indicating facial attributes like hair color, gender and age.\n\nOptions: A: SentEval B: irc-disentanglement C: CUB-200-2011 D: CelebA", "role": "user" }, { "content": "CelebA", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: A joint Bayesian convolutional sparse coding approach to image super-resolution.\n\nKeyphrases: super resolution\n\nDataset descriptions:\nOST300: OST300 is an outdoor scene dataset with 300 test images of outdoor scenes, and a training set of 7 categories of images with rich textures.\nSet5: The Set5 dataset is a dataset consisting of 5 images (“baby”, “bird”, “butterfly”, “head”, “woman”) commonly used for testing performance of Image Super-Resolution models.\nDIV2K: DIV2K is a popular single-image super-resolution dataset which contains 1,000 images with different scenes and is splitted to 800 for training, 100 for validation and 100 for testing. It was collected for NTIRE2017 and NTIRE2018 Super-Resolution Challenges in order to encourage research on image super-resolution with more realistic degradation.\nBSD: BSD is a dataset used frequently for image denoising and super-resolution. Of the subdatasets, BSD100 is aclassical image dataset having 100 test images proposed by Martin et al..\n\nOptions: A: OST300 B: Set5 C: DIV2K D: BSD", "role": "user" }, { "content": "Set5", "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:\nStandardized treatment of Chinese medicine decoction for cancer pain patients with opioid-induced constipation : a multi-center prospective randomized controlled study . OBJECTIVE To observe the efficacy and the influence on quality of life ( QOL ) of syndrome differentiation treatment with Chinese medicine ( CM ) for opioid-induced constipation as well as the safety and influence on analgesic effect of opioids . METHODS Totally 406 cases enrolled from 53 collaborating medical centers were randomly assigned to a CM group and a control group . The CM group were treated with CM decoction based on syndrome differentiation , and the control group were treated with Phenolphthalein Tablet . Both groups were treated for 14 days . Cleveland constipation score ( CCS ) , numerical rating scale ( NRS ) of pain and Chinese version of European Organisation for Research and Treatment of Cancer , Quality of Life Questionnaire-C30 V3.0 ( EORTC QLQ-C30 V3.0 ) were used to evaluate the efficacy , pain controlled and QOL status . RESULTS The comparisons of CCS score reduction and QOL between the two groups after treatment suggested that the improvements of constipation and QOL in the CM group were better than that in the control group ( P < 0.05 ) . The total efficiency of the CM group was better than the control group ( 93.5 % vs. 86.4 % , P < 0.05 ) . There was no significant difference in NRS scores between before and after treatment in both groups . There was no serious drug-related adverse event during the course of study . CONCLUSION CM decoction could effectively treat opioid-induced constipation and improve patients ' QOL at the same time . It is safe and does n't affect the analgesic effect of opioids when treating constipation .", "role": "user" }, { "content": "{\"Intervention\": [\"Phenolphthalein Tablet\", \"Chinese medicine decoction\", \"CM decoction\", \".\", \"Chinese medicine ( CM )\", \"CM\"], \"Outcome\": [], \"Participant\": [\"406 cases\", \"cancer pain patients with opioid-induced constipation :\", \"opioid-induced constipation\"]}", "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:\nmethod\n\nContext before:\nconverted to numerical features using the standard technique of binarization, and we split values of the FEATS field into its atomic components.4 For some languages, we divide the training data into smaller sets, based on some feature s (normally the CPOS or POS of the next input token), which may reduce training times without a significant loss in accuracy (Yamada and Matsumoto, 2003). 3We also ran preliminary experiments with memory-based learning but found that this gave consistently lower accuracy. 2The fields PHEAD and PDEPREL have not been used at all, since we rely on pseudo-projective parsing for the treatment of non-projective structures.\n\nCitation:\nconverted to numerical features using the standard technique of binarization , and we split values of the FEATS field into its atomic components .4 For some languages , we divide the training data into smaller sets , based on some feature s ( normally the CPOS or POS of the next input token ) , which may reduce training times without a significant loss in accuracy ( Yamada and Matsumoto , 2003 ) .\n\nContext after:\nTo avoid too small training sets, we pool together categories that have a frequency below a certain threshold t.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Extract entities of these types from the text: [\"Chemical\", \"Protein\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values.\n\nText:\nThe clinical profile of the angiotensin II receptor blocker eprosartan.\nAngiotensin II receptor antagonists block angiotensin II type 1 (AT1) receptors and reduce the pressor effects of angiotensin in the vasculature. By this mechanism, they induce similar pharmacological effects to angiotensin-converting enzyme (ACE) inhibitors, resulting in a lowering of blood pressure (BP). However, AT1 antagonists differ from ACE inhibitors with respect to side effects, and induce less cough, which is related to bradykinin activation. Within the class of angiotensin II antagonists, eprosartan differs from other currently clinically available agents in terms of its chemical structure and its dual pharmacological mode of action. Eprosartan acts not only at vascular AT1 receptors but also at presynaptic AT1 receptors, causing inhibition of sympathetically stimulated noradrenaline release. Eprosartan is not metabolized by cytochrome P450 enzymes and therefore has a low potential for metabolic drug interactions, which may be of importance when treating the elderly and patients on multiple drugs. In clinical trials eprosartan has proven to be at least as effective as the ACE inhibitor enalapril in reducing BP, but with a significantly lower incidence of side effects. Eprosartan is safe, effective and well tolerated in long-term treatment, either as monotherapy or in combination with other antihypertensive drugs such as hydrochlorothiazide.", "role": "user" }, { "content": "{\"Chemical\": [\"Eprosartan\", \"eprosartan\", \"angiotensin II\", \"hydrochlorothiazide\", \"Angiotensin II\", \"noradrenaline\", \"angiotensin\"], \"Protein\": [\"ACE\", \"angiotensin II\", \"angiotensin II receptor\", \"angiotensin-converting enzyme\", \"bradykinin\", \"cytochrome P450\", \"Angiotensin II receptor\", \"AT1\", \"angiotensin II type 1 (AT1) receptors\", \"angiotensin\"]}", "role": "assistant" } ]

[ { "content": "Given the full text of a scientific research paper, write an abstract section for the paper. Your response should contain only the abstract without any other text.\n\nArticle text:\nit remains an open question whether massive neutrinos are majorana particles , whose antiparticles are themselves @xcite . the final answer to this fundamental question will tell us whether the lepton number is conserved or not in nature , and help us explore the origin of neutrino masses .\ncurrently , the most promising way to answer if massive neutrinos are their own antiparticles is to observe the @xmath0 decays @xmath19 , where @xmath20 and @xmath21 stand respectively for the atomic and mass numbers of a nuclear isotope @xmath22 @xcite . over the last few decades\n, a great number of dedicated experiments have been carried out to search for this kind of decays @xcite .\nso far , we have not observed any positive signals , and a lower bound on the half - life of the implemented nuclear isotope can be drawn from experimental data .\nthe gerda phase - i experiment @xcite has disproved the signals of @xmath23 decays claimed by the heidelberg - moscow experiment @xcite , and the joint lower bound from all the previous @xmath24-based experiments on the half - life turns out to be @xmath25 at the @xmath26 confidence level @xcite . for @xmath27-based experiments ,\na combined analysis of the exo-200 @xcite and kamland - zen phase - i data @xcite gives rise to a lower bound @xmath28 at the @xmath26 confidence level .\nmore recently , kamland - zen announced their phase - ii result @xcite , and improved the lower bound to @xmath29 at the @xmath26 confidence level with both phase - i and phase - ii data .\nif neutrino mass ordering is inverted ( i.e. , @xmath30 ) , the next - generation @xmath23 experiments with a few tons of target mass will be able to discover a remarkable signal in the near future @xcite .\nthe schechter - valle theorem @xcite states that a clear signal of @xmath23 decays will unambiguously indicate a finite majorana mass of neutrinos , if neither a fine - tuning among parameters nor a cancellation among different contributions is assumed .\ndecay rate remains nonzero as the nuclear medium effects on quarks may break any intricate cancellation .\n] obviously , this theorem signifies the physical importance of searching for @xmath23 decays experimentally .\nthe quantitative impact of the schechter - valle theorem has already been studied by duerr , lindner and merle in ref .\n@xcite , where it is found that the majorana neutrino masses implied by the schechter - valle theorem are too small to explain neutrino oscillations .\nexplicitly , assuming one short - range operator to be responsible for @xmath23 decays , they find that current experimental lower bounds on the half - lives of @xmath23-decaying isotopes indicate an upper bound on the majorana neutrino mass @xmath31 , where @xmath32 denotes the effective neutrino mass term associated with @xmath33 for @xmath34 . in this paper\n, we reexamine this problem , and obtain an upper bound @xmath35 that agrees with the above result from ref .\n@xcite on the order of magnitude .\nfurthermore , we generalize the analysis of @xmath0 decays to that of the lnv rare decays of @xmath15 , @xmath13 and @xmath36 mesons .\nfor instance , we obtain @xmath37 , @xmath38 and @xmath39 from current upper bounds on the lnv rare decays of @xmath36 mesons .\nthe radiative majorana neutrino masses related to other lnv decays are also tabulated .\ntherefore , we confirm the conclusion from ref .\n@xcite that although the schechter - valle theorem in general implies a tiny majorana neutrino mass , we have to explore other mechanisms to generate the observed neutrino masses at the sub - ev level .\nthe remaining part of this work is organized as follows . in sec . 2\n, we recall the calculation of majorana neutrino masses from the four - loop diagram mediated by the effective operator , which is also responsible for the @xmath0 decays .\nthe generalization to the lnv meson decays is performed in sec . 3 , where the corresponding majorana masses are computed .\nfinally , we summarize our main conclusions in sec . 4 .\nin this section , we present a brief review on the calculation of majorana neutrino masses radiatively generated from the operator that leads to the @xmath0 decays , following ref .\n@xcite closely .\nsuch a calculation can be readily generalized to the case of majorana neutrino masses induced by the lnv meson decays , as shown in the next section . at the elementary - particle level\n, the @xmath0 decays can be expressed as @xmath40 , where the up quark @xmath41 , the down quark @xmath42 and the electron @xmath43 are all massive fermions .\nif the @xmath0 decays take place , they can be effectively described by the lnv operator @xmath44 , in which the chiralities of charged fermions have been omitted and will be specified later . as already pointed out by schechter and valle @xcite\n, this operator will unambiguously result in a majorana neutrino mass term @xmath45 .\nthe relevant feynman diagrams are given in fig .\n[ fig:0n2b ] .\nit is worthwhile to notice that quark and charged - lepton masses are indispensable for the schechter - valle theorem to be valid , as emphasized in ref .\n@xcite . in the standard model ( sm ) ,\nonly left - handed neutrino fields participate in the weak interactions , so the electron masses can be implemented to convert the right - handed electron fields into the left - handed ones , which are then coupled to left - handed neutrino fields via the charged weak gauge boson @xmath46 .\nthis does make sense , since the chirality of electrons in the operator @xmath47 can in general be either left - handed or right - handed . for the same reason , quark masses are also required to realize the hadronic charged - current interactions in the sm . in this case , the operator @xmath48 in fig .\n[ fig:0n2b](a ) can be attached to the left - handed neutrinos through two propagators of @xmath46 , leading to the neutrino self - energy diagram in fig .\n[ fig:0n2b](b ) . assuming that @xmath0 decays are mediated by short - range interactions\n, one can write down the most general lorentz - invariant lagrangian that contains various point - like operators as follows @xcite @xmath50 where @xmath51 and @xmath52 denote respectively the fermi constant and the proton mass , and @xmath53 ( for @xmath54 ) are effective coupling constants . in eq .\n( [ eq : operators ] ) , the hadronic currents are defined as @xcite @xmath55 ( 1 \\pm \\gamma_5^ { } ) d \\ ; , \\end{aligned}\\ ] ] while the leptonic currents are given by @xmath56 ( 1 \\pm \\gamma_5^ { } ) e^{\\rm c } \\\n; , \\end{aligned}\\ ] ] where @xmath57 with @xmath58 is the charge - conjugated electron field .\naccording to @xmath59 and the fact that fermion fields are grassmann numbers , one can immediately verify that the tensor leptonic current @xmath60 automatically vanishes .\ndifferent chiralities of hadronic and leptonic currents in eqs .\n( [ eq : hadronic ] ) and ( [ eq : leptonic ] ) should be distinguished by the left- and right - handed projection operators @xmath61 .\nfor instance , we have defined @xmath62 , and similarly for the other types of currents in eqs .\n( [ eq : hadronic ] ) and ( [ eq : leptonic ] ) , in which the corresponding subscripts \nl \" or r \" are omitted without causing any confusions . in this connection\n, the effective coupling constants @xmath53 should also be regarded as @xmath63 ( for x , y , z = l , r ) , which are carrying the superscripts for different chiralities of hadronic and leptonic currents .\ngiven one of the five operators in eq .\n( [ eq : operators ] ) , one can set an upper limit on their coupling @xmath64 by assuming that it is responsible for the @xmath65 decay and saturates the experimental lower bound on the half - life , as done in ref .\nrecently , some of those limits have been recalculated in ref .\n@xcite , using more recent results for the nuclear matrix elements .\nthe effective coupling constants for the operators @xmath66 and @xmath67 have been found to be @xmath68 and @xmath69 , respectively .\nhaving obtained these couplings , we are then ready to evaluate the induced neutrino mass by inserting the dimension - nine effective operators into the butterfly diagram , as depicted in fig .\n[ fig:0n2b ] .\nthe authors of ref .\n@xcite have demonstrated that the operator @xmath66 leads to a vanishing neutrino mass term via the butterfly diagram , while the other one @xmath70 does lead to a tiny majorana neutrino mass , which will be revisited below .\nnow that the operator @xmath71 is responsible for the @xmath0 decays , the radiatively induced majorana mass term for electron neutrinos can be extracted from the self - energy in fig . [\nfig:0n2b](b ) by setting the external momentum to zero as @xcite , @xmath72 where @xmath73 is the weak gauge coupling , and @xmath74 and @xmath75 are the up - quark , down - quark and electron masses , respectively .\nin addition , the loop integral is given by @xmath76 ^ 2_{}$ ] with @xmath77 ( q_1 ^ 2 - m_d^2 ) ( k_1 ^ 2-m_{w}^2 ) } \\ ; , \\end{aligned}\\ ] ] where @xmath78 is the @xmath79-boson mass , @xmath80 and @xmath81 stand for the four - momenta of internal particles running in the loop and can be easily identified via the integrand on the right - hand side of eq .\n( 5 ) and from fig .\n[ fig:0n2b](b ) . to evaluate this integral\n, we employ the technique for massive two - loop diagrams in ref .\n@xcite and arrive at @xmath82 with @xmath83 as usually introduced in the dimensional regularization and @xmath6 being the renormalization scale .\nthe relevant function reads as @xcite @xmath84 [ ( p+q)^2 + m_k^2 ] } \\\\ & = & \\pi^4 ( \\pi m_i^2)^{n-4 } \\frac{\\gamma(2-\\frac{1}{2}n)}{\\gamma(3-\\frac{1}{2}n ) } \\int_0 ^ 1 { \\rm d}x \\int_0 ^ 1 { \\rm d}y ~ [ x ( 1-x)]^{\\frac{1}{2}n-2 } y ( 1-y)^{2-\\frac{1}{2}n } \\nonumber \\\\ & & \\times \\left\\ { \\frac{(y^2 \\kappa^2 + \\eta^2)\\gamma(5-n)}{[y(1-y)\\kappa^2 + y + ( 1-y)\\eta^2 ] ^{5-n } } + \\frac{n}{2 } \\frac{\\gamma(4-n)}{[y(1-y)\\kappa^2 + y + ( 1-y)\\eta^2 ] ^{4-n } } \\right \\},\\end{aligned}\\ ] ] with @xmath85 as usual , the integral is expanded with respect to @xmath86 in the limit of @xmath87 and the ultraviolet divergences can be separated as inverse powers of @xmath88 . since the loop integral involves the divergent terms proportional to @xmath89 and @xmath90 , we need to keep the terms up to @xmath91 in @xmath92 , namely , @xmath93 so as to obtain all the finite parts of @xmath94 . in our numerical calculations , we have adopted the renormalization scale of @xmath95 , which is a characteristic scale of typical energy transfer in nuclear processes .\nthe other implemented parameters can be found in table [ tb : constants ] . in the scheme of minimal subtraction , we finally get the induced neutrino mass from eq .\n( [ eq : sigmap ] ) as latexmath:[\\[\\begin{aligned } which agrees with the result @xmath31 from ref .\n@xcite on the order of magnitude .\nsince this mass is extremely small , one has to implement other mechanisms to account for neutrino masses . in this sense , the main conclusion in ref .\n@xcite is still valid that the schechter - valle theorem is qualitatively correct , but quantitatively irrelevant for the neutrino mass - squared differences required for neutrino oscillation experiments .", "role": "user" }, { "content": "the schechter - valle theorem states that a positive observation of neutrinoless double - beta ( @xmath0 ) decays implies a finite majorana mass term for neutrinos when any unlikely fine - tuning or cancellation is absent . in this note , we reexamine the quantitative impact of the schechter - valle theorem , and find that current experimental lower limits on the half - lives of @xmath0-decaying nuclei have placed a restrictive upper bound on the majorana neutrino mass @xmath1 radiatively generated at the four - loop level . furthermore , we generalize this quantitative analysis of @xmath0 decays to that of the lepton - number - violating ( lnv ) meson decays @xmath2 ( for @xmath3 , @xmath4 = @xmath5 or @xmath6 ) . \n given the present upper limits on these rare lnv decays , we have derived the loop - induced majorana neutrino masses @xmath7 , @xmath8 and @xmath9 from @xmath10 , @xmath11 and @xmath12 , respectively . \n a partial list of radiative neutrino masses from the lnv decays of @xmath13 , @xmath14 and @xmath15 mesons is also given . \n * majorana neutrino masses from neutrinoless double - beta decays and lepton - number - violating meson decays * * jun - hao liu @xmath16 * + @xmath17institute of high energy physics , chinese academy of sciences , beijing 100049 , china + @xmath18center for high energy physics , peking university , beijing 100871 , china pacs number(s ) : 11.30.fs , 12.15.lk , 14.60.lm", "role": "assistant" } ]

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

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nDesign, Synthesis and Biological Evaluation of Trimethine Cyanine Dyes as Fluorescent Probes for the Detection of Tau Fibrils in Alzheimer's Disease Brain and Olfactory Epithelium. Shedding light on grey matter: Fluorescent trimethine cyanines were evaluated as imaging probes for neurofibrillary tangles in post-mortem brain sections of Alzheimer's disease patients. These probes bind to neurofibrillary tangles with high contrast and selectivity over amyloid β plaques.", "role": "user" }, { "content": "{\"Chemical\": [\"Trimethine Cyanine\", \"trimethine cyanines\"]}", "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:\nNo beneficial effect of low-dose fetal intravenous gammaglobulin administration in combination with intravascular transfusions in severe Rh D haemolytic disease.\nAbstract 1:\nRecent observations have shown that treatment with high-dose intravenous gammaglobulin (IVIgG) given to the mother may improve fetal outcome in cases of severe Rh D alloimmunization. Unfortunately, the costs of this new method of treatment are too high for routine use. Therefore, we decided to apply this treatment to the fetus and to investigate whether the effect of IVIgG might be attributable to blockade of the fetal mononuclear phagocyte system. We have performed a randomized study in which 20 fetuses with severe Rh D-haemolytic disease (HDN) were treated with intrauterine intravascular red cell transfusions (IUT). In 10 of these 20 cases transfusions were followed by administration to the fetus of low-dose IVIgG (85.7 +/- 11.6 mg/kg by ultrasound-estimated fetal weight because of fetal vascular volume considerations). We compared the number of IUTs, postnatal exchange transfusions, haematocrit (Ht) and haemoglobulin (Hb) values before and after transfusion (s) needed by the newborns of the two groups. No significant differences in the transfusion requirements of the fetuses and in the clinical outcome could be demonstrated. However, the 95% confidence interval for the difference in the improvement of cord blood Ht was too wide for any conclusions. The 95% confidence interval for the difference in the improvement of Hb levels suggests that any clinically relevant advantage of IVIgG on Hb is unlikely.", "role": "user" }, { "content": "There is little available high quality information from randomised controlled trials to inform the optimal procedural technique when performing fetal intrauterine fetal blood transfusions for women with an anaemic fetus due to red cell alloimmunisation. Further research evaluating the benefits and harms associated with different techniques is required.", "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:\nDouble-blind comparison of cabergoline and bromocriptine in Parkinson's disease patients with motor fluctuations.\nAbstract 1:\nIn the present study we compared the efficacy and safety of the new dopamine agonist cabergoline (CBG) with bromocriptine (BCR) in Parkinson's disease (PD). CBG has a very long half-life and can be administered as a single daily dose. Forty-four PD patients with uncontrolled motor fluctuations participated in the study. Patients were randomly and blindly assigned to equivalent doses of either CBG or BCR in addition to preexisting levodopa. Dosage was titrated to optimal, using up to 6 mg of CBG or 40 mg of BCR daily. CBG was given as a single morning dose whereas BCR was administered tid. Sixteen patients were followed for 1 year and 16 additional patients for 6 months. The mean follow-up duration was 9 +/- 5 months. The main effect of both drugs was observed on motor UPDRS scores, rigidity, bradykinesia items, and the percentage of awake hours spent during \"on\" and \"off\". In general, the effect of CBG was similar to that of BCR. The percentage of awake hours spent during \"on\" was higher with CBG as compared with BCR. Adverse events included dyskinesias, orthostatism, confusion, edema, and paresthesias in limbs. These effects were seen at similar frequencies with both drugs. The study shows that CBG given as a single morning dose is at least as efficacious as BCR given tid. CBG is a promising dopamine agonist for the treatment of motor fluctuations in PD.", "role": "user" }, { "content": "Cabergoline produces similar benefits to bromocriptine in off time reduction, motor impairment and disability ratings, and levodopa dose reduction over the first three months of therapy. Dyskinesia and confusion were increased with cabergoline but otherwise the frequency of adverse events and withdrawals from treatment were similar with the two agonists.", "role": "assistant" } ]

[ { "content": "Summarize the paper:\n\nPaper text:\n\nModel-free deep reinforcement learning approaches have shown superhuman performance in simulated environments (e.g., Atari games, Go, etc).\nDuring training, these approaches often implicitly construct a latent space that contains key information for decision making.\nIn this paper, we learn a forward model on this latent space and apply it to model-based planning in miniature Real-time Strategy game with incomplete information (MiniRTS).\nWe first show that the latent space constructed from existing actor-critic models contains relevant information of the game, and design training procedure to learn forward models.\nWe also show that our learned forward model can predict meaningful future state and is usable for latent space Monte-Carlo Tree Search (MCTS), in terms of win rates against rule-based agents.\nModel-free deep reinforcement learning (DRL) approaches (e.g., deep Q-learning BID14 ], DDPG BID12 ], A3C BID16 ], etc) have been applied extensively in many simulated environments with complete information and relatively simple game dynamics (e.g., Atari games, Go ], Doom, etc).\nThe learned agent, which acts reactively based on the current game situation, can even achieve superhuman performance.However, for complicated environments, planning ahead (or \"predicting the future\") before making an actual decision is important.\nSuch a planning procedure requires a forward model that estimates the next state s t+1 given the current state s t and action a t , which is in general non-trivial to construct and estimate from the high-dimensional raw input.\nFor partially observable environments (e.g., Real-time Strategy Games like StarCraft), constructing a forward model is more difficult even with a perfect domain knowledge of the game, due to the deliberate concealing of information and the additional requirement to capture the belief of the unknown for the agent.A natural question now arises.\nCould we borrow the success of model-free approach to learn a forward model?\nNote that in model-free approaches, a single shared network (called \"trunk\") is often used to extract features from the input game situation to obtain a latent representation.\nFrom the latent space, multiple reinforcement learning quantities (Q-function, value function V , advantage function A, etc) are predicted via simple linear transformations and used for decision making.\nStrong performance of these approaches indicates that the learned latent space must have captured key ingredients of the input situation and remains low-dimensional.\nTherefore, it is an excellent candidate for the state representation of a forward model.In this paper, we study whether it is possible to use the latent space learned by model-free approaches to construct forward models.\nWe use MiniRTS ], an efficient and simple twoplayer Real-time Strategy (RTS) game.\nMiniRTS captures the basic dynamics of its kind: the agent builds units (workers and troops) that consume resources, gathers resources, explores regions out of sights (\"fog of war\"), defends enemy's attack, and invades enemy's base.\nThis game is incomplete information, because the agent can only see within its sight, and does not know the action of its opponent by default.\nRather than unit based control as in ; ; ], the agent uses 9 discrete actions to control the overall strategy (e.g., build a particular kind of troops, attack or defend).Our\ncontributions are three-fold: First, we propose to study the relationship between the latent space learned by model-free approaches and the state representation of forward models. Very\nfew works (e.g, DARLA BID10 ], DQN BID15 ]) in model-free RL study these properties in depth, let alone using the latent state in model-based approaches for incomplete information game. To our\nknowledge, we are one of the first works to explore such directions. Second\n, we improve the performance of model-based agent in MiniRTS by input feature design and show that the latent space learned from actor-critic models BID16 ] can reconstruct critical information of the game, e.g., Hit Point of the base and available resources. Finally\n, we propose novel algorithms that learn a forward model that maps a latent state h t to its future counterpart h t (t > t) with reduced drifting. Such a\nforward model enables us to use model-based planning such as Monte-Carlo Tree Search (MCTS) in incomplete information games. We show\npositive performance (8% higher than random planning) in terms of win rates against rule-based agents.\nLatent space learned by model-free reinforcement learning encodes important information for an agent to make sensible decisions to maximize the reward in a complicated simulated environment.\nIn this paper, we verify the power of latent space of successfully trained model-free agent, and propose several methods to learn forward models on this space, in a real-time strategy game with incomplete information.\nDespite an extremely hard problem, we learn forward models that make it possible to use planning approaches such as Monte Carlo Tree Search, and show consistently positive gains over baselines.A lot of future works follow.\nAs a first step, although we show that it is possible to learn a forward model for incomplete information Real-time Strategy games to enable model-based planning in the latent space, it remains an open problem how to improve its performance.\nIt is possible that despite a good forward model is learned, the value function is not good enough, e.g., putting too much focus on the on-policy trajectory, for Monte-Carlo Tree Search.\nAlso, in this paper we use predefined 9 global actions for the game.\nHow to automatically learn global actions from unit-based commands that are exponentially large, is still an challenging issue to solve.", "role": "user" }, { "content": "The paper analyzes the latent space learned by model-free approaches in a miniature incomplete information game, trains a forward model in the latent space and apply it to Monte-Carlo Tree Search, yielding positive performance.", "role": "assistant" } ]

[ { "content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Amaximumscoreof60swasgivenifananimaldidnotfall.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Pan-cancer association of a centrosome amplification gene expression signature with genomic alterations and clinical outcome\nArticle:\nAbstract:\nCentrosome amplification( CA) is a common feature of human tumours and a promising target for cancer therapy. However, CA’s pan-cancer prevalence, molecular role in tumourigenesis and therapeutic value in the clinical setting are still largely unexplored. Here, we used a transcriptomic signature( CA20) to characterise the landscape of CA-associated gene expression in 9, 721 tumours from The Cancer Genome Atlas( TCGA). CA20 is upregulated in cancer and associated with distinct clinical and molecular features of breast cancer, consistently with our experimental CA quantification in patient samples. Moreover, we show that CA20 upregulation is positively associated with genomic instability, alteration of specific chromosomal arms and C>T mutations, and we propose novel molecular players associated with CA in cancer. Finally, high CA20 is associated with poor prognosis and, by integrating drug sensitivity with drug perturbation profiles in cell lines, we identify candidate compounds for selectively targeting cancer cells exhibiting transcriptomic evidence for CA.\nIntroduction:\nThe centrosome, an organelle composed of two centrioles surrounded by a pericentriolar protein matrix, is the major microtubule-organising centre of animal cells, hence being pivotal for several fundamental cellular processes, including signalling, cell polarity, division and migration[1–4]. Each centrosome duplicates once per cell cycle to ensure bipolar spindle assembly and successful chromosome segregation[5, 6]. Centrosomes are thus implicated in the maintenance of genome stability. Centrosome amplification( CA) –the presence of more than two centrosomes—is a common feature in cancer[7]. Supernumerary centrosomes generate multipolar mitosis and consequent genome instability[6, 8–10], they can accelerate and promote tumourigenesis in vivo[11–13] and promote cellular invasion and metastatic behaviour[14–17]. However, CA’s pan-cancer prevalence, molecular role in tumourigenesis and therapeutic value remain poorly understood, largely due to the technical challenges associated with profiling such small cellular structures in human cancer tissues. For instance, quantifying centrosome numbers and abnormalities is often hampered by the limited thickness of formalin-fixed and paraffin-embedded tissue sections, preventing the imaging of entire cells[18]. In addition, three-dimensional imaging and analysis are mandatory, but cumbersome and time consuming[19]. To at least partially circumvent those challenges, we propose the estimation of CA based on the expression levels of CA-associated genes. Recently, proof-of-principle gene-expression-based CA signatures have been developed[20–23], the most comprehensive one being CA20, based on the expression of TUBG1, which encodes the most abundant centrosomal protein, and 19 other genes whose overexpression has been experimentally shown to induce CA[23]. This signature was proposed to reflect CA levels in tumour samples and shown to have a prognostic value in two independent breast cancer cohorts[23]. In the present study, we used CA20 to estimate relative CA levels across 9, 721 tumour and 725 matched-normal samples of 32 cancer types from The Cancer Genome Atlas( TCGA), thereby revealing the first pan-cancer landscape of CA-associated gene expression. We show the association of CA20 with distinct breast cancer clinical and molecular features. We also break down the independent associations of CA20 with different sorts of genomic instability across cancer types. Finally, we show that high CA20 is associated with poor clinical outcome in different cancer types, having identified candidate compounds for selectively targeting cancer cells exhibiting transcriptomic evidence for this hallmark of cancer.\nDiscussion:\nCA is known to promote tumourigenesis but its molecular role therein remains elusive and, although it is also suggested to be a promising target for cancer therapy, CA’s prevalence in different types of cancer and therapeutic value in the clinic are still pretty much unprobed. Using the CA20 signature and TCGA RNA-seq data, we characterise the landscape of CA-associated gene expression in a broad range of cancer types, thereby demonstrating the potential of using gene expression-based signatures in multi-omic and clinical data integrative approaches to investigate the biological and medical relevance of their respective cellular and molecular processes. Despite the lack of a full direct experimental validation of CA20 as a surrogate of CA levels, our observations are very consistent with known CA’s features, namely CA20’s upregulation in cancer[7] and in basal-like breast tumours[26], and its association with the knock-down of centriole duplication factors, genomic instability[11], loss of p53[6, 7, 35] and pRB[44], hypoxia[54, 55] and worse patient’s prognosis[7]. In addition, we found that luminal B breast tumours have higher prevalence of CA than luminal A ones, concordantly with the observed differences in the CA20 score between the two molecular subtypes in two independent cohorts. Finally, we have analysed two transcriptomic datasets of multiciliogenesis, where cells escape centriole number regulation to generate hundreds of centrioles during differentiation[61], and found that CA20 increases during the centriole overduplication stage, resuming basal levels afterwards( S17 Fig), suggesting CA20 as a marker of active amplification. These observations vouch for the present proof-of-concept study to pave the way for more in-depth and bona fide findings when CA’s transcriptomic signature is experimentally refined. Moreover, here we already propose novel hypotheses that will trigger studies aiming at a more comprehensive understanding of the role of CA in cancer. We observed higher CA-associated gene expression in cancer samples of squamous cell origin than in adenocarcinomas, suggesting that their different cell types of origin can have different CA’s prevalence and/or ways to cope with this abnormality. Previous work has indeed shown that CA triggers spontaneous squamous cell carcinomas, lymphomas and sarcomas, but not adenocarcinomas, in mice[11]. We also show that breast invasive carcinoma samples have high variability on CA20, concordantly with previous observations[7, 25], that is related to their distinct clinical and molecular features. We had recently shown that basal-like breast carcinomas have higher CA than luminal tumours[26], but here we report for the first time an upregulation of CA-associated genes in tumours from both invasive ductal histologic subtype and luminal B molecular subtype. We validated the CA20-based predictions by quantitatively analysing centrosome numbers in human breast carcinoma samples, where we found that indeed CA is more prevalent in luminal B than luminal A tumours, providing a novel insight into the differences between these two hormone-receptor positive molecular subtypes. Given the limited number of luminal B samples in our cohort, more extensive analyses are necessary to confirm this association. Our data show that centrosome amplification is associated with breast cancer clinical features and endorses the potential of using a gene-expression-based signature for patient stratification. CA-associated gene expression upregulation is positively correlated with different types of genomic instability, like aneuploidy, mutation burden, CNA and tumour heterogeneity. In particular, CA20 is more strongly associated with chromosomal deletions than amplifications, independently of TP53 mutations. We speculate that this association may be due to the impact of CA in cellular genomic stability having non-random genomic “hot spots”. In fact, through a more detailed analysis, we found an association with alterations in specific chromosomal arms, that may be due to the localisation of genes encoding for regulators of CA20 genes therein and/or to those arms’ higher susceptibility to the genomic instability triggered by centrosome abnormalities. The latter is supported by recent work showing that human chromosome mis-segregation is not random and can be biased by inherent properties of individual chromosomes[62], and also by our observation that normal samples whose matched tumours lost 5q or 16p have higher CA20 predictive of those deletions( S6 Fig). Moreover, we characterised the DNA mutation spectrum associated with CA20 and found it to be enriched in C>T mutations, a signature characteristic of ageing, with which centrosome aberrations have also been associated[63–67]. Genes whose mutations are associated with CA20 are enriched in cancer driver genes, and particularly in Wnt/β-catenin signalling. Wnt/β-catenin signalling components interact with the centrosome[68] and a previous study has demonstrated that mutant β-catenin induces centrosome aberrations in normal epithelial cells and is required for CA in cancer cells[69]. Our results extend this previous association to human cancer samples, suggesting mutations in β-catenin might contribute to the observed CA in cancer. Finally, we show the usefulness of a novel approach whereby we integrated information on genes whose somatic mutations are associated with CA20 in TCGA tumour samples with the impact of their knock-downs on the CA20 expression in human cancer cell lines, aiming at unveiling candidate molecular players in CA in cancer. Concordantly with previous work on CA[7], we observed that high CA20 is associated with poor patient’s survival in several cancer types. Furthermore, we found a positive correlation between CA20 and hypoxic levels in glioblastoma multiforme that is particularly interesting, due to its highly hypoxic microenvironment and HIF-1α levels[70], also shown to enhance migration and invasion of its tumour cells[71, 72]. Given the observed association between CA and invasion of tumour cells[15, 17], an exciting hypothesis is hypoxia-induced invasion being mediated through CA. When looking at the tumour cellular composition, we found that tumours with high CA20 have lower stromal and immune cell infiltration, although the latter is not independent of tumour genomic instability and proliferation rate. Detailed studies aiming to decouple these effects could provide relevant molecular insights when considering immunotherapy, alone or in combination with genotoxic and/or anti-proliferative therapeutic approaches. Moreover, by pioneering the integration of drug sensitivity with drug perturbation profiles in human cancer cell lines, we identify candidate compounds for selectively targeting cancer cells exhibiting transcriptomic evidence for CA. These compounds could be particularly useful in the treatment of cancer types we identified as having high CA and to whose current therapy patients respond poorly. For instance, their potential in specifically targeting basal-like and luminal B breast tumours could be assessed by taking advantage of resources like patient-derived tumour xenografts[73]. The observed ability of cells carrying extra centrosomes to manipulate the surrounding tumour cells and promote their invasiveness[15, 17] suggests that targeting the former may be clinically more impactful. Given CA’s cancer-specificity, the compounds identified herein could underlie the development of novel targeted cancer therapeutic options.", "role": "user" }, { "content": "Centrosome amplification , i . e . an increased number of centrosomes—structures that exist inside cells , is a hallmark of cancer cells and therefore an Achilles' heel for the development of innovative therapies that specifically target tumour cells , sparing healthy ones . To exploit centrosome amplification’s clinical potential , it is crucial to understand its role in cancer development and to identify compounds for its selective targeting . These are challenging tasks due to the technical difficulty of profiling centrosome amplification in cells . In this study , we circumvent those challenges by computationally analysing the expression of 20 genes known to promote centrosome amplification across nearly 10 , 000 tumours of over 30 cancer types , thereby estimating their relative centrosome amplification levels . We found that those genes are indeed highly active in tumours and associated with prognosis in different cancer types . We also show that those genes’ expression is associated with instability in the structure of cancer cells’ chromosomes and identify candidate drugs for selectively targeting those cells . Our work therefore demonstrates the potential of computational analyses of large volumes of cancer molecular and clinical data to elucidate cellular and molecular mechanisms of tumour development and propose novel therapeutic options in oncology .", "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 large majority of T6SS genes (12 out of 17), including VipA, VipB, ClpV, VasF and VasK, are required for Hcp secretion, killing of amoeba and bacteria and are predicted to encode structural T6SS components [9,12,20].", "role": "user" }, { "content": "Background", "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:\nclassical cepheids , also known as @xmath1 cep - type stars or just cepheids , are population i instability strip pulsators crucial for understanding stellar structure and evolution .\nmost galactic cepheids pulsate in one mode with remarkably stable amplitudes and periods , although space - based photometry reveals that they are not entirely regular clocks .\nobservations with _\ncorot , kepler _ and _ most _ detect short - term , low - amplitude irregular variability or `` jitter '' in the pulsation cycles of some classical cepheids @xcite .\none exception is v473 lyrae ( @xmath2 = 19@xmath315@xmath45949 , @xmath5 = + 2755346 , @xmath6 = 6.18 mag ) , the only known classical cepheid in the galaxy that undergoes strong amplitude and phase modulations .\nthe changes in the pulsation amplitude were first noted by @xcite .\n@xcite estimated the modulation period to be 3.33.4 years , which was later measured to be 1210 d by @xcite , and 1258 d by @xcite , respectively .\nthe origin of this modulation was extensively discussed in the literature , with theories ranging from mode beating @xcite to magneto - convective cycles @xcite .\na recent analysis of extensive ground - based observations collected during 19662011 @xcite confirmed that v473 lyrae pulsates in the second overtone , modulated with a primary period of @xmath7 d. @xcite also discovered a second , longer modulation cycle with a period of @xmath8 d , and concluded that the modulation closely resembles the blazhko effect seen in rr lyrae stars .\nv473 lyrae is unique among galactic cepheids : the closest counterparts are v1154 cyg , in which the _ kepler _ space telescope detected modulation but with a very low amplitude @xcite and sv vul , with a suspected , much longer modulation period of order 30 yr @xcite . beyond our galaxy ,\nstrong amplitude modulation was recently found in three classical cepheids in the magellanic clouds @xcite .\nalthough modulation appears to be very rare among cepheids , the phenomenological properties of the light variations of v473 lyr closely resemble the blazhko effect , a common feature among rr lyrae stars .\nthanks to space - based photometry , we now know that many modulated rr lyrae stars show low - amplitude additional modes and/or alternating high- and low - amplitude cycles known as period doubling @xcite .\nnumerical models suggest that mode resonances that generate the period doubling can also be responsible for the modulation itself @xcite .\nit is not unreasonable , therefore , to postulate that similar mechanisms could operate in modulated cepheids too .\nunfortunately , the pulsation period of v473 lyr ,\n@xmath9 = 1.4909d , means that one can not observe consecutive pulsation maxima from a single ground - based site .\nthis makes it virtually impossible to detect period doubling , a challenge also faced in ground - based rr lyrae observations .\ntherefore , we proposed to gather continuous observations of the star with the _ most _ space telescope for a timespan of one month in order to search for cycle - to - cycle variations .\n_ most _ serendipitously also observed another cepheid , u tra , just before the run that targeted v473 lyr . a campaign aimed at the wolf - rayet star wr 71 included this beat cepheid within the same field of view .\nu tra ( @xmath2 = 16@xmath307@xmath41901 , @xmath5 = 6254380 , @xmath6 = 7.89 mag ) , along with tu cas were the first cepheids in which beating ( the characteristic feature caused by double - mode pulsation ) was observed @xcite .\nu tra pulsates in the fundamental mode and the first overtone , with periods @xmath10d and @xmath11d @xcite . after an investigation of the relative amplitudes of the pulsation\nmodes over time , @xcite proposed that pulsation energy may have been redistributed from the fundamental mode to the first overtone , an intriguing concept that can be tested with new measurements . together with earlier observations of rt aur and sz tau @xcite ,\n_ most _ s cepheid sample now totals 4 stars .\nthis paper is structured as follows : section [ sec2 ] describes the various observations we carried out ; sections [ secv473 ] and [ secutra ] include the analysis and obtained results for v473 lyr and u tra , respectively ; section [ secsum ] closes with discussion and summary of the findings presented in the paper .\nthe stars were observed by the _ most _ ( microvariability & oscillations of stars ) space telescope : a canadian microsatellite designed to observe bright stellar targets continuously for up to 2 months at a time @xcite .\nwe also obtained spectroscopy for both stars with various ground - based instruments . in the case of u tra , in the field of the _\nmost _ primary science target wr 71 , each orbit was shared with another primary science field .\nu tra was observed for 28 days during 29 may 25 june 2014 .\nas _ most _ has to use the science ccd for guiding purposes too , it takes short individual exposures that are stacked on - board to boost the stellar signals .\nthe sampling cadence is 123.8 sec . in the case of v473 lyrae ,\nthe star is located in the sky where _ most _ must point at too large an angle relative to the sun , heating the satellite beyond the thermal limits for its battery .\nbut the v473 lyrae run coincided with the eclipse season \" for _ most _ , when the sun skims briefly below the earth horizon once per orbit for a few minutes .\nit was possible to point _ most _ at v473 lyrae for a few minutes per orbit , leading to an effective sampling cadence of 101 minutes .\neach orbit contains 210 measurements , with a cadence of 62.2 sec .\nthe star was observed for 27 days during 28 june \n23 july 2014 , but communication problems with the satellite and deliberate interruptions to observe other targets introduced some longer gaps .\nwe have data from 57 per cent of the _ most _ orbits in the overall run .\nmost photometric reduction processes are well established ( see , e.g. , * ? ? ?\n* ; * ? ? ?\n* ) and have recently been successfully applied to other cepheids @xcite .\n_ most _ data experience modulation of scattered earthshine with the 101-min orbital period .\nalso , as the instrument regains thermal equilibrium after switching from two widely - separated points in the sky , there are short - lived trends after switching from one field to another .\nstray light modulation is filtered in the reduction process ; extreme outliers were removed by sigma - clipping the flux values . in instances of substantially poor pointing , data were filtered by sigma - clipping outliers in the pointing positions and the measured flux values . to preserve the intrinsic cepheid variations ,\nslow trends were filtered from the data and clipping applied to the residuals .\nthe filtered data were phased with the orbital period and averaged in bins to remove modulations caused by stray light .\nwe note that v473 lyr is much less affected by stray light than u tra as it was only observed when _ most _ was in the shadow of the earth .\nfinally , the large - amplitude variation was restored to the data .\nany remaining slow trends were then subtracted by a simple linear fit .\nthe final light curves ( times , magnitudes and errors ) are shown in fig .\n[ most - lc ] .\n@xmath12konkoly observatory , mta csfk , konkoly thege mikls t 15 - 17 , h-1121 budapest , hungary + @xmath13elte gothard astrophysical observatory , h-9704 szombathely , szent imre herceg t 112 , hungary + @xmath14department of physics and astronomy , university of british columbia , 6224 agricultural road , vancouver , bc v6 t 1z1 , canada + @xmath15department of mathematics , physics & geology , cape breton university , 1250 grand lake road , sydney , nova scotia , canada , b1p\n6l2 + @xmath16canadian coast guard college , dept . of arts , sciences , and languages ,\nsydney , nova scotia , b1r 2j6 , canada + @xmath17dpartement de physique and centre de recherche en astrophysique du qubec ( craq ) , universit de montral , c.p .\n6128 , succ .\ncentre - ville , montral , qubec , h3c 3j7 , canada + @xmath18ritter observatory , department of physics and astronomy , university of toledo , toledo , oh 43606 - 3390 , usa + @xmath19department of physical sciences , kutztown university , kutztown , pa 19530 ,\nusa + @xmath20barfold observatory , glenhope , victoria 3444 , australia + @xmath21saser the southern astro spectroscopy email ring + @xmath22international centre for radio astronomy research , university of western australia , 35 stirling hwy , crawley , wa 6009 , australia + @xmath23harvard - smithsonian center for astrophysics , 60 , garden street , cambridge ma 02138 , usa + @xmath24instituut voor sterrenkunde , celestijnenlaan 200d , b-3001 leuven , belgium + @xmath25department of physics , university of antwerp , groenenborgerlaan 171 , 2020 antwerp , belgium + @xmath26department of physics and astronomy , university of louisville , louisville , ky 40292 , usa + @xmath27department of physics and astronomy , vanderbilt university , nashville , tn 37235 , usa + @xmath28department of physics , lehigh university , bethlehem , pa 18015 , usa + @xmath29department of physics , fisk university , 1000 17th avenue north , nashville , tn 37208 , usa + @xmath30las cumbres obs\n. global telescope network , 6740 cortona dr .\n, suite 102 , santa barbara , ca 93117 , usa + @xmath31american association of variable star observers , cambridge , ma 02138 , usa + @xmath32center for theoretical physics of the polish academy of sciences , al .\nlotnikow 32/46 , 02 - 668 warsaw , poland + @xmath33faculty of physics , university of warsaw , pasteura 5 , 02 - 093 warszawa , poland + @xmath34national centre for nuclear research , hoa 69 , 00 - 681 warsaw , poland + @xmath35international centre for radio astronomy research ( icrar ) , curtin university , gpo box u1987 , perth , wa 6845 , australia + @xmath36institute for computational astrophysics , department of astronomy and physics , saint mary s university , halifax , ns b3h 3c3 , canada + @xmath37institut fr astronomie , universitt wien , trkenschanzstrasse 17 , a-1180 wien , austria + @xmath38department of astronomy and astrophysics , university of toronto , toronto , on m5s 3h4 , canada + [ lastpage ]", "role": "user" }, { "content": "space - based photometric measurements first revealed low - amplitude irregularities in the pulsations of cepheid stars , but their origins and how commonly they occur remain uncertain . to investigate this phenomenon , we present _ most _ space telescope photometry of two cepheids . \n v473 lyrae is a second - overtone , strongly modulated cepheid , while u trianguli australis is a cepheid pulsating simultaneously in the fundamental mode and first overtone . \n the nearly continuous , high - precision photometry reveals alternations in the amplitudes of cycles in v473 lyr , the first case of period doubling detected in a classical cepheid . in u tra , we tentatively identify one peak as the @xmath0 or 0.61type mode often seen in conjunction with the first radial overtone in cepheids , but given the short length of the data , we can not rule out that it is a combination peak instead . \n ground - based photometry and spectroscopy were obtained to follow two modulation cycles in v473 lyr and to better specify its physical parameters . \n the simultaneous data yield the phase lag parameter ( the phase difference between maxima in luminosity and radial velocity ) of a second - overtone cepheid for the first time . \n we find no evidence for a period change in u tra or an energy exchange between the fundamental mode and the first overtone during the last 50 years , contrary to earlier indications . \n period doubling in v473 lyr provides a strong argument that mode interactions do occur in some cepheids and we may hypothesise that it could be behind the amplitude modulation , as recently proposed for blazhko rr lyrae stars . \n [ firstpage ] stars : variables : cepheids stars : individual : v473 lyrae stars : individual : u tra", "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:\nIt provides a fine grained NE recognition covering 100 different NE types (Sekine, 2008). OAK7 is a rule based English analyser that includes many functionalities (POS tagger, stemmer, chunker, Named Entity (NE) tagger, dependency analyser, parser, etc). Three types of entities were extracted: person, location and organisation.\n\nCitation:\nIt provides a fine grained NE recognition covering 100 different NE types ( Sekine , 2008 ) .\n\nContext after:\nGiven the sparseness of most of these fine-grained NE types, we have merged them in coarser groups: event, facility, location, person, organisation, product, periodx, timex and numex. We have also used the results of a baseline NE recognition for comparison purposes. This method detects sequences of two or more uppercased tokens in the text, and discards those that are found lowercased in the same document or that are composed solely of stopwords. Other features are: emails, outgoing links found in the web pages and two boolean flags that indicate whether a pair of documents is linked or belongs to the same domain.", "role": "user" }, { "content": "Uses", "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:\ntwitter and other social media have become important communication channels for the general public .\nit is thus not surprising that various stakeholder groups in science also participate on these platforms .\nscientists , for instance , use twitter for generating research ideas and disseminating and discussing scientific results @xcite .\nmany biomedical practitioners use twitter for engaging in continuing education ( e.g. , journal clubs on twitter ) and other community - based purposes @xcite .\npolicy makers are active on twitter , opening lines of discourse between scientists and those making policy on science @xcite .\nquantitative investigations of scholarly activities on social media often called altmetrics can now be done at scale , given the availability of apis on several platforms , most notably twitter @xcite .\nmuch of the extant literature has focused on the comparison between the amount of online attention and traditional citations collected by publications , showing low levels of correlation .\nsuch low correlation has been used to argue that altmetrics provide alternative measures of impact , particularly the broader impact on the society @xcite , given that social media provide open platforms where people with diverse backgrounds can engage in direct conversations without any barriers .\nhowever , this argument has not been empirically grounded , impeding further understanding of the validity of altmetrics and the broader impact of articles . a crucial step towards empirical validation of\nthe broader impact claim of altmetrics is to identify scientists on twitter , because altmetric activities are often assumed to be generated by the public \" rather than scientists , although it is not necessarily the case . to verify this\n, we need to be able to identify scientists and non - scientists .\nalthough there have been some attempts , they suffer from a narrow disciplinary focus @xcite and/or small scale @xcite .\nmoreover , most studies use purposive sampling techniques , pre - selecting candidate scientists based on their success in other sources ( e.g. , highly cited in web of science ) , instead of organically finding scientists from the twitter platform itself . such reliance on bibliographic databases binds these studies to traditional citation indicators and thus introduces bias . for instance , this approach overlooks early - career scientists and favors certain disciplines . here we present the first large - scale and systematic study of scientists across many disciplines on twitter . as our method does not rely on external bibliographic databases and is capable of identifying any user types that are captured in twitter list , it can be adapted to identify other types of stakeholders , occupations , and entities .\nwe study the demographics of the set of scientists in terms of discipline and gender , finding over - representation of social scientists , under - representation of mathematical and physical scientists , and a better representation of women compared to the statistics from scholarly publishing .\nwe then analyze the sharing behaviors of scientists , reporting that only a small portion of shared urls are science - related .\nfinally , we find an assortative mixing with respect to disciplines in the follower , retweet , and mention networks between scientists .\nour study serves as a basic building block to study scholarly communication on twitter and the broader impact of altmetrics .\nwe classify current literature into two main categories , namely _ product_- vs. _ _ producer-__centric perspectives .\nthe former examines the sharing of scholarly papers in social media and its impact , the latter focuses on who generates the attention . * product - centric perspective . *\npriem and costello formally defined twitter citations as direct or indirect links from a tweet to a peer - reviewed scholarly article online \" and distinguished between first- and second - order citations based on whether there is an intermediate web page mentioning the article @xcite .\nthe accumulation of these links , they argued , would provide a new type of metric , coined as altmetrics , \" which could measure the broader impact beyond academia of diverse scholarly products @xcite .\nmany studies argued that only a small portion of research papers are mentioned on twitter @xcite .\nfor instance , a systematic study covering @xmath0 million papers indexed by both pubmed and web of science found that only @xmath1 of them have mentions on twitter @xcite , yet this is much higher than other social media metrics except mendeley .\nthe coverages vary across disciplines ; medical and social sciences papers that may be more likely to appeal to a wider public are more likely to be covered on twitter @xcite .\nmixed results have been reported regarding the correlation between altmetrics and citations @xcite .\na recent meta - analysis showed that the correlation is negligible ( @xmath2 ) @xcite ; however , there is dramatic differences across studies depending on disciplines , journals , and time window .\n* producer - centric perspective .\n* survey - based studies examined how scholars present themselves on social media @xcite . a large - scale survey with more than @xmath3 responses conducted by _ nature _ in @xmath4 revealed that more than @xmath5 were aware of twitter , yet only @xmath6 were regular users @xcite . a handful of studies analyzed how twitter is used by scientists .\npriem and costello examined @xmath7 scholars to study how and why they share scholarly papers on twitter @xcite .\nan analysis of @xmath8 emergency physicians concluded that many users do not connect to their colleagues while a small number of users are tightly interconnected @xcite .\nholmberg and thelwall selected researchers in @xmath9 disciplines and found clear disciplinary differences in twitter usages , such as more retweets by biochemists and more sharing of links for economists @xcite . note that these studies first selected scientists outside of twitter and then manually searched their twitter profiles .\ntwo limitations thus exist for these studies .\nfirst , the sample size is small due to the nature of manual searching @xcite .\nsecond , the samples are biased towards more well - known scientists .\none notable exception is a study by hadgu and jschke , who presented a supervised learning based approach to identifying researchers on twitter , where the training set contains users who were related to some computer science conference handles @xcite .\nalthough this study used a more systematic method , it still relied on the dblp , an external bibliographic dataset for computer science , and is confined in a single discipline .\ndefining science and scientists is a herculean task and beyond the scope of this paper .\nwe thus adopt a practical definition , turning to the @xmath10 standard occupational classification ( soc ) system ( http://www.bls.gov/soc/ ) released by the bureau of labor statistics , united states department of labor .\nwe use soc because not only it is a practical and authoritative guidance for the definition of scientists but also many official statistics ( e.g. , total employment of social scientists ) are released according to this classification system .\nsoc is a hierarchical system that classifies workers into @xmath11 major occupational groups , among which we are interested in two , namely ( 1 ) computer and mathematical occupations ( code 15 - 0000 ) and ( 2 ) life , physical , and social science occupations ( code 19 - 0000 ) . from the two groups , we compile @xmath7 scientist occupations ( supporting table s1 ) .\nalthough authoritative , the soc does not always meet our intuitive classifications of scientists .\nfor instance , \nbiologists \" is not presented in the classification .\nwe therefore consider another source \nwikipedia to augment the set of scientist occupations . in particular , we add the occupations listed at http://en.wikipedia.org/wiki/scientist#by_field .\nwe then compile a list of scientist titles from the two sources .\nthis is done by combining titles from soc , wikipedia , and illustrative examples under each soc occupation .\nwe also add two general titles : scientists \" and researchers . \" for each title , we consider its singular form and the core disciplinary term .\nfor instance , for the title clinical psychologists , \" we also consider clinical psychologist , \" psychologists , \" and psychologist .\n\" we assemble a set of @xmath12 scientist titles using this method .\nour method of identifying scientists is inspired by a previous study that used twitter _\nlists _ to identify user expertise @xcite .\na twitter _ list _ is a set of twitter users that can be created by any twitter user .\nthe creator of a list needs to provide a name and optional description .\nalthough the purpose of lists is to help users organize their subscriptions , the names and descriptions of lists can be leveraged to infer attributes of users in the lists .\nimagine a user creating a list called economist \" and putting http://twitter.com/betseystevenson[@betseystevenson ] in it ; this signals that @betseystevenson may be an economist . if @betseystevenson is included in numerous lists all named economist , \" which means that many independent twitter users classify her as an economist , it is highly likely that @betseystevenson is indeed an economist .\nthis is illustrated in fig [ fig : list - name - wordcloud ] where the word cloud of the names of twitter lists containing @betseystevenson is shown .\nwe can see that \neconomist \" is a top word frequently appeared in the titles , signaling the occupation of this user .\nin other words , we\n crowdsource \" the identity of each twitter user . .\n] in principle , we could use twitter s ` memberships ` api ( https://dev.twitter.com/rest/reference/get/lists/memberships ) , for each user , to get all the lists containing this user , and then infer whether this user is a scientist by analyzing the names and descriptions of these lists .\nhowever , this method is highly infeasible , because ( 1 ) most users are not scientists , ( 2 ) the distribution of listed counts is right - skewed : lady gaga , for example , is listed more than @xmath13 times ( https://www.electoralhq.com/twitter-users/most-listed ) , and ( 3 ) twitter api has rate limits .\nwe instead employ a previously introduced list - based snowball sampling method @xcite that starts from a given initial set of users and expands to discover more .\nwe improve this approach by more systematically obtaining the job title lexicon and the seed user set ( supporting text ) .\nwe use the snowball sampling ( breadth - first search ) on twitter lists .\nwe first identify seed users ( supporting text ) and put them into a queue . for each public user in the queue , we get all the lists in which the user appears , using the twitter ` memberships ` api\n. then , for each public list in the subset resulting lists whose name contains at least one scientist title , we get its members using the twitter ` members ` api ( https://dev.twitter.com/rest/reference/get/lists/members ) and put those who have not been visited into the queue .\nthe two steps are repeated until the queue is empty , which completes the sampling process .\nnote that to remove many organizations and anonymous users as well as to speed up the sampling , we only consider users whose names contain spaces .\nwe acknowledge that this may drop many users with non - english names or the ones who do not disclose their names in a standard way .\nalso note that this procedure is inherently blind towards those scientists who are not listed . from the sampling procedure ,\nwe get @xmath14 users appearing in @xmath15 lists whose names contain scientist titles .\nto increase the precision of our method , the final dataset contains those users whose profile descriptions also contain scientist titles .\na total number of @xmath16 users are found .\ntable [ tab : top - listed ] shows the top @xmath17 scientists based on number of lists whose names contain scientist titles , suggesting that our sampling method can identify scientists in diverse disciplines .\nthese top scientists have very different levels of popularities , with the most followed scientist neil degrasse tyson attracting more than @xmath18 million followers while miles kimball has @xmath19 thousand followers .\n-2.25in0 in .*top 30 scientists based on the number of twitter lists whose names contain scientist titles . * [ cols=\"<,>,>,>,<,>,>,>\",options=\"header \" , ] [ tab : community - top - nodes ]\n1 m. gabielkov , a. rao , and a. legout .\nstudying social networks at scale : macroscopic anatomy of the twitter social graph . in _ proc .\nof the 2014 acm international conference on measurement and modeling of computer systems _ , pages 277288 , 2014 .\nn. k. sharma , s. ghosh , f. benevenuto , n. ganguly , and k. gummadi . inferring who - is -\nwho in the twitter social network . in _ proc . of the 2012 acm workshop on online social networks _ , pages 5560 , 2012 .", "role": "user" }, { "content": "metrics derived from twitter and other social media often referred to as altmetrics are increasingly used to estimate the broader social impacts of scholarship . \n such efforts , however , may produce highly misleading results , as the entities that participate in conversations about science on these platforms are largely unknown . for instance , if altmetric activities are generated mainly by scientists , does it really capture broader social impacts of science ? here we present a systematic approach to identifying and analyzing scientists on twitter . \n our method can be easily adapted to identify other stakeholder groups in science . \n we investigate the demographics , sharing behaviors , and interconnectivity of the identified scientists . \n our work contributes to the literature both methodologically and conceptually we provide new methods for disambiguating and identifying particular actors on social media and describing the behaviors of scientists , thus providing foundational information for the construction and use of indicators on the basis of social media metrics .", "role": "assistant" } ]

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nMany research questions can be answered quickly and efficiently using data already collected for previous research. This practice is called secondary data analysis (SDA), and has gained popularity due to lower costs and improved research efficiency. In this paper we propose DFS, a file system to standardize the metadata representation of datasets, and DDU, a scalable architecture based on DFS for semi-automated metadata generation and data recommendation on the cloud. We discuss how DFS and DDU lays groundwork for automatic dataset aggregation, how it integrates with existing data wrangling and machine learning tools, and explores their implications on datasets stored in digital libraries.\n\nCited Abstract(s):\n[1]: The relative ease of collaborative data science and analysis has led to a proliferation of many thousands or millions of versions of the same datasets in many scientific and commercial domains, acquired or constructed at various stages of data analysis across many users, and often over long periods of time. Managing, storing, and recreating these dataset versions is a non-trivial task. The fundamental challenge here is the storage-recreation trade-off: the more storage we use, the faster it is to recreate or retrieve versions, while the less storage we use, the slower it is to recreate or retrieve versions. Despite the fundamental nature of this problem, there has been a surprisingly little amount of work on it. In this paper, we study this trade-off in a principled manner: we formulate six problems under various settings, trading off these quantities in various ways, demonstrate that most of the problems are intractable, and propose a suite of inexpensive heuristics drawing from techniques in delay-constrained scheduling, and spanning tree literature, to solve these problems. We have built a prototype version management system, that aims to serve as a foundation to our DataHub system for facilitating collaborative data science. We demonstrate, via extensive experiments, that our proposed heuristics provide efficient solutions in practical dataset versioning scenarios.", "role": "user" }, { "content": "Another study [1] provides a storage-efficient approach to provide version control to datasets. They state that the amount of storage used is proportional to the speed of recreating or retrieving dataset versions. A suite of inexpensive heuristics were created based on techniques in delay-constrained scheduling, and spanning tree literature. Results show that these heuristics provide efficient solutions in practical dataset versioning scenarios.", "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: A CNN-based domain adaptation tracker based on the CNNs.\n\nKeywords: domain adaptation video\n\nDataset descriptions:\nOTB: Object Tracking Benchmark (OTB) is a visual tracking benchmark that is widely used to evaluate the performance of a visual tracking algorithm. The dataset contains a total of 100 sequences and each is annotated frame-by-frame with bounding boxes and 11 challenge attributes.\nAFLW2000-3D: AFLW2000-3D is a dataset of 2000 images that have been annotated with image-level 68-point 3D facial landmarks. This dataset is used for evaluation of 3D facial landmark detection models.\nVOT2017: VOT2017 is a Visual Object Tracking dataset for different tasks that contains 60 short sequences annotated with 6 different attributes.\nMcMaster: The McMaster dataset is a dataset for color demosaicing, which contains 18 cropped images of size 500×500.\nLAG: Includes 5,824 fundus images labeled with either positive glaucoma (2,392) or negative glaucoma (3,432).\nMMED: Contains 25,165 textual news articles collected from hundreds of news media sites (e.g., Yahoo News, Google News, CNN News.) and 76,516 image posts shared on Flickr social media, which are annotated according to 412 real-world events.\n\nOptions: A: OTB B: AFLW2000-3D C: VOT2017 D: McMaster E: LAG F: MMED", "role": "user" }, { "content": "[\"OTB\", \"VOT2017\"]", "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 of rimonabant, a cannabinoid-1 receptor blocker, on weight and cardiometabolic risk factors in overweight or obese patients: RIO-North America: a randomized controlled trial.\nAbstract 1:\nRimonabant, a selective cannabinoid-1 receptor blocker, may reduce body weight and improve cardiometabolic risk factors in patients who are overweight or obese.\n To compare the efficacy and safety of rimonabant with placebo each in conjunction with diet and exercise for sustained changes in weight and cardiometabolic risk factors over 2 years.\n Randomized, double-blind, placebo-controlled trial of 3045 obese (body mass index > or =30) or overweight (body mass index >27 and treated or untreated hypertension or dyslipidemia) adult patients at 64 US and 8 Canadian clinical research centers from August 2001 to April 2004.\n After a 4-week single-blind placebo plus diet (600 kcal/d deficit) run-in period, patients were randomized to receive placebo, 5 mg/d of rimonabant, or 20 mg/d of rimonabant for 1 year. Rimonabant-treated patients were rerandomized to receive placebo or continued to receive the same rimonabant dose while the placebo group continued to receive placebo during year 2.\n Body weight change over year 1 and prevention of weight regain during year 2. Additional efficacy measures included changes in waist circumference, plasma lipid levels, and other cardiometabolic risk factors.\n At year 1, the completion rate was 309 (51%) patients in the placebo group, 620 (51%) patients in the 5 mg of rimonabant group, and 673 (55%) patients in the 20 mg of rimonabant group. Compared with the placebo group, the 20 mg of rimonabant group produced greater mean (SEM) reductions in weight (-6.3 [0.2] kg vs -1.6 [0.2] kg; P<.001), waist circumference (-6.1 [0.2] cm vs -2.5 [0.3] cm; P<.001), and level of triglycerides (percentage change, -5.3 [1.2] vs 7.9 [2.0]; P<.001) and a greater increase in level of high-density lipoprotein cholesterol (percentage change, 12.6 [0.5] vs 5.4 [0.7]; P<.001). Patients who were switched from the 20 mg of rimonabant group to the placebo group during year 2 experienced weight regain while those who continued to receive 20 mg of rimonabant maintained their weight loss and favorable changes in cardiometabolic risk factors. Use of different imputation methods to account for the high rate of dropouts in all 3 groups yielded similar results. Rimonabant was generally well tolerated; the most common drug-related adverse event was nausea (11.2% for the 20 mg of rimonabant group vs 5.8% for the placebo group).\n In this multicenter trial, treatment with 20 mg/d of rimonabant plus diet for 2 years promoted modest but sustained reductions in weight and waist circumference and favorable changes in cardiometabolic risk factors. However, the trial was limited by a high drop-out rate and longer-term effects of the drug require further study. Clinical Trials Registration ClinicalTrials.gov Identifier: NCT00029861.\n\n\nTitle 2:\nEffects of rimonabant on metabolic risk factors in overweight patients with dyslipidemia.\nAbstract 2:\nRimonabant, a selective cannabinoid-1 receptor (CB1) blocker, has been shown to reduce body weight and improve cardiovascular risk factors in obese patients. The Rimonabant in Obesity-Lipids (RIO-Lipids) study examined the effects of rimonabant on metabolic risk factors, including adiponectin levels, in high-risk patients who are overweight or obese and have dyslipidemia.\n We randomly assigned 1036 overweight or obese patients (body-mass index [the weight in kilograms divided by the square of the height in meters], 27 to 40) with untreated dyslipidemia (triglyceride levels >1.69 to 7.90 mmol per liter, or a ratio of cholesterol to high-density lipoprotein [HDL] cholesterol of >4.5 among women and >5 among men) to double-blinded therapy with either placebo or rimonabant at a dose of 5 mg or 20 mg daily for 12 months in addition to a hypocaloric diet.\n The rates of completion of the study were 62.6 percent, 60.3 percent, and 63.9 percent in the placebo group, the group receiving 5 mg of rimonabant, and the group receiving 20 mg of rimonabant, respectively. The most frequent adverse events resulting in discontinuation of the drug were depression, anxiety, and nausea. As compared with placebo, rimonabant at a dose of 20 mg was associated with a significant (P<0.001) mean weight loss (repeated-measures method, -6.7+/-0.5 kg, and last-observation-carried-forward analyses, -5.4+/-0.4 kg), reduction in waist circumference (repeated-measures method, -5.8+/-0.5 cm, and last-observation-carried-forward analyses, -4.7+/-0.5 cm), increase in HDL cholesterol (repeated-measures method, +10.0+/-1.6 percent, and last-observation-carried-forward analyses, +8.1+/-1.5 percent), and reduction in triglycerides (repeated-measures method, -13.0+/-3.5 percent, and last-observation-carried-forward analyses, -12.4+/-3.2 percent). Rimonabant at a dose of 20 mg also resulted in an increase in plasma adiponectin levels (repeated-measures method, 57.7 percent, and last-observation-carried-forward analyses, 46.2 percent; P<0.001), for a change that was partly independent of weight loss alone.\n Selective CB1-receptor blockade with rimonabant significantly reduces body weight and waist circumference and improves the profile of several metabolic risk factors in high-risk patients who are overweight or obese and have an atherogenic dyslipidemia.\n Copyright 2005 Massachusetts Medical Society.\n\n\nTitle 3:\nEffects of the cannabinoid-1 receptor blocker rimonabant on weight reduction and cardiovascular risk factors in overweight patients: 1-year experience from the RIO-Europe study.\nAbstract 3:\nIn animal models, cannabinoid-1 receptor (CB1) blockade produces a lean phenotype, with resistance to diet-induced obesity and associated dyslipidaemia. We assessed the effect of rimonabant, a selective CB1 blocker, on bodyweight and cardiovascular risk factors in overweight or obese patients.\n patients with body-mass index 30 kg/m2 or greater, or body-mass index greater than 27 kg/m2 with treated or untreated dyslipidaemia, hypertension, or both, were randomised to receive double-blind treatment with placebo, 5 mg rimonabant, or 20 mg rimonabant once daily in addition to a mild hypocaloric diet (600 kcal/day deficit). The primary efficacy endpoint was weight change from baseline after 1 year of treatment in the intention-to-treat population.\n Weight loss at 1 year was significantly greater in patients treated with rimonabant 5 mg (mean -3.4 kg [SD 5.7]; p=0.002 vs placebo) and 20 mg (-6.6 kg [7.2]; p<0.001 vs placebo) compared with placebo (-1.8 kg [6.4]). Significantly more patients treated with rimonabant 20 mg than placebo achieved weight loss of 5% or greater (p<0.001) and 10% or greater (p<0.001). Rimonabant 20 mg produced significantly greater improvements than placebo in waist circumference, HDL-cholesterol, triglycerides, and insulin resistance, and prevalence of the metabolic syndrome. The effects of rimonabant 5 mg were of less clinical significance. Rimonabant was generally well tolerated with mild and transient side effects.\n CB1 blockade with rimonabant 20 mg, combined with a hypocaloric diet over 1 year, promoted significant decrease of bodyweight and waist circumference, and improvement in cardiovascular risk factors.", "role": "user" }, { "content": "The use of rimonabant after one year produces modest weight loss of approximately 5%. Even modest amounts of weight loss may be potentially beneficial. The observed results should be interpreted with some caution, though, since the evaluated studies presented some deficiencies in methodological quality. Studies with longer follow-ups after the end of treatment and of more rigorous quality should be done before definitive recommendations can be made regarding the role of this new medication in the management of overweight or obese patients.", "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: In the fast-twitch muscle of hypothyroid rats, shifting to a slow direction by CLFS increased the expression of myogenin with unaltered MyoD levels (37).", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Modulation of the Disordered Conformational Ensembles of the p53 Transactivation Domain by Cancer-Associated Mutations\nArticle:\nAbstract:\nIntrinsically disordered proteins( IDPs) are frequently associated with human diseases such as cancers, and about one-fourth of disease-associated missense mutations have been mapped into predicted disordered regions. Understanding how these mutations affect the structure-function relationship of IDPs is a formidable task that requires detailed characterization of the disordered conformational ensembles. Implicit solvent coupled with enhanced sampling has been proposed to provide a balance between accuracy and efficiency necessary for systematic and comparative assessments of the effects of mutations as well as post-translational modifications on IDP structure and interaction. Here, we utilize a recently developed replica exchange with guided annealing enhanced sampling technique to calculate well-converged atomistic conformational ensembles of the intrinsically disordered transactivation domain( TAD) of tumor suppressor p53 and several cancer-associated mutants in implicit solvent. The simulations are critically assessed by quantitative comparisons with several types of experimental data that provide structural information on both secondary and tertiary levels. The results show that the calculated ensembles reproduce local structural features of wild-type p53-TAD and the effects of K24N mutation quantitatively. On the tertiary level, the simulated ensembles are overly compact, even though they appear to recapitulate the overall features of transient long-range contacts qualitatively. A key finding is that, while p53-TAD and its cancer mutants sample a similar set of conformational states, cancer mutants could introduce both local and long-range structural modulations to potentially perturb the balance of p53 binding to various regulatory proteins and further alter how this balance is regulated by multisite phosphorylation of p53-TAD. The current study clearly demonstrates the promise of atomistic simulations for detailed characterization of IDP conformations, and at the same time reveals important limitations in the current implicit solvent protein force field that must be sufficiently addressed for reliable description of long-range structural features of the disordered ensembles.\nIntroduction:\nCellular signaling and regulation are frequently mediated by proteins that, in part or as a whole, lack stable structures under physiological conditions[1–3]. Such intrinsically disordered proteins( IDPs) are over-represented in disease pathways[4, 5]. About ~25% of disease- associated missense mutations can be mapped into predicted disordered regions[6]( although cancer mutations appear to prefer ordered regions[7]). Many disease mutations in disordered regions have been predicted to alter the residual structure level[8], which could potentially perturb interaction networks and lead to mis-signaling and mis-regulation. Establishing the biophysical basis of how disease mutants affect the “structure”-function relationship of IDPs is a formidable task. It requires detailed characterization of the disordered conformational ensembles, which are not amenable to traditional structural determination using either X-ray crystallography or nuclear magnetic resonance( NMR) spectroscopy[9–11]. For disordered protein states, only ensemble-averaged properties are generally measured[12, 13], and single-molecule techniques are often limited by low spatial resolution and labeling complications[14–16]. Recovering the underlying structural heterogeneity using ensemble-averaged properties is fundamentally underdetermined; there is not sufficient constraint( or information) to uniquely define the structure ensemble based on averaged properties alone. A possible strategy to overcome this fundamental limitation is to leverage significant recent advances in physics-based protein force fields and enhanced sampling techniques to calculate de novo structural ensembles[10, 17]. Structural data from NMR and other biophysical experiments can be then used for independent validation, but not as structural restraints during the ensemble calculation. This strategy has proven effective enough to provide useful insights on studies of several relatively small IDPs[18–23]. An important caveat is, however, de novo ensembles will inevitably contain artifacts due to persisting limitations in the current protein force fields as well as conformational sampling capability. Nonetheless, certain systematic artifacts could be suppressed by examining how the calculated ensembles depend on sequence variations, post-translational modifications, and/or solution conditions[23, 24]. To assess the efficacy of atomistic simulations for understanding the mutant-structure-function relationship of IDPs, we exploit the intrinsically disordered transactivation domain( TAD) of the tumor suppressor p53 and its cancer-associated mutations as a model system of great biological and biomedical significance. p53 is the most frequently mutated protein in cancer[25, 26]. The p53 levels are kept low in unstressed cells through continuous proteasomal degradation. Cellular stresses such as DNA damage, initiate a cascade of phosphorylation events that stabilize and activate the p53 protein[27]. Accumulation of activated p53 induces the transcription of genes involved in cell cycle arrest and apoptosis, thus suppressing cell transformation and tumor formation[28]. Most human cancers exhibit defects in the p53-signaling pathway, over 50% of which involve inactivated p53 due to various mutations[29, 30]. Clinical studies of breast cancer have indicated that the type of p53 mutation can be linked to cancer prognosis and response to drug[31]. It is thus crucial to determine the molecular basis of p53 inactivation by various types of mutations, so as to understand the biological consequences and predict potential treatment responses and patient survival. The p53 protein contains several distinct functional domains( Fig 1A). The core DBD domain binds to the regulatory regions of target genes, and the terminal domains interact with many proteins that together tightly regulate the p53 protein level, localization, oligomerization and activity[26]. The primary focus of existing structural and functional studies has been on cancer mutants in DBD[32], which harbors over 80% of p53 cancer mutations including established cancer “hot spots”[33]. Aided by several crystal structures[34, 35], the molecular basis for p53 inactivation of DBD cancer mutants can be understood in terms of either disrupting DNA contacts, perturbing the structure of DNA-binding interface, or affecting the DBD stability[32]. In contrast, very little is known about the structural and functional impacts of cancer mutants in the regulatory domains and particularly TAD. This could be attributed to much lower prevalence, and thus perceived importance, of cancer mutants outside of DBD( e. g., ~1 per residue in TAD vs. ~6 per residue in DBD)[33]. Nonetheless, TAD cancer mutants appear to be frequently associated with some cancers. Two out of the thee documented female genital cancers contain mutants in TAD( E17D and K24N); over 5% nasal cavity, tonsil, salivary gland and parotid gland cancers involve mutated TAD( statistics extracted from the IRAC TP53 mutation database, version R15[33]). At present, available functional knowledge of all known TAD cancer mutants( see Fig 1A) largely comes from a single yeast-based transcriptional activity essay study of all possible point mutations in the entire coding region of p53 gene[36]( with a few exceptions[30, 33]). Moreover, no structural or molecular interaction data is available on any TAD cancer mutants except K24N[37]. A key complication in molecular studies of p53 TAD cancer mutants is that, in contrast to DBD with a stable fold, TAD is an IDP and must be described by heterogeneous structure ensembles[38–43]. In this work, we exploit the recently developed replica exchange with guided annealing( RE-GA) enhanced sampling technique[44, 45] to calculate disordered ensembles of p53-TAD at atomistic level and examine how cancer-associated mutations could modulate the disordered ensembles to potentially disturb p53’s interactions with key regulatory proteins. RE-GA extends the popular temperature replica exchange( T-RE) method by introducing annealing cycles, during which the temperature exchange attempt patterns are modified for a selected replica to guide its diffusion through the temperature ladder more rapidly. The GA cycles help to overcome the limitation of RE in accelerating entropically limited cooperative conformational transitions[46–48], albeit at the expense of compromising the detailed balance for systems with large activation enthalpies[44]. For IDPs with relatively small conformational transition barriers, numerical experiments and atomistic simulations of a small 28-residue IDP have demonstrated that RE-GA introduces minimal conformational biases and could generate converged ensembles with 3–5 fold speedup compared to T-RE[44]. The convergence of RE-GA simulations will be carefully examined by comparing results from independent simulations initiated from contrasting structures. The quality of simulated ensembles will be critically assessed by direct comparison with a wide range of existing data that provide structural information on both the secondary and tertiary levels for the wild-type protein and one of its mutants[37, 39, 40, 43]. Further analysis of all resulting atomistic ensembles will then be performed to obtain a preliminary understanding of how cancer-associated mutations may introduce both local and long-range structural changes in unbound p53-TAD, which could have functional consequences on how p53-TAD may differentially interact with key regulatory pathways and on how these differential interactions may be regulated through multi-site phosphorylations.\nDiscussion:\nThe p53 protein level and activity are tightly regulated through coordinated interactions of TAD with negative regulators MDM2 and MDMX( mouse double minute 2 and 4) and the general transcriptional coactivators CBP and p300[63]( see Fig 1B). Unphosphorylated p53-TAD binds to MDM2 with sub-micromolar affinity, which promotes polyubiquitination and degradation of p53 through MDM2’s E3 ubiquitin ligase activity[64, 65]. Recent NMR and calorimetry studies showed that multisite phosphorylation of TAD reduced binding to MDM2( by up to 24X, or ΔΔG ~ −1. 9 kcal/mol), and at the same time provided graded enhancement of binding to CBP/p300 domains( by up to 80X, or ΔΔG ~ +2. 6 kcal/mol)[66–68]. These effects together dramatically shift the balance towards favoring binding to CBP/p300, up to 1000-fold. The graded dependence on the extent of p53 phosphorylation provides a mechanism for gradually increasing p53 response under prolonged genotoxic stress[69]. Nonetheless, precisely how phosphorylation regulates the binding affinities is not entirely clear. Phosphorylation may simply provide a new interaction site and/or disrupt the binding interface. However, available structures of complexes involving p53-TAD[70–73] show that TAD interacts with other proteins mainly via two short helices( see Fig 1A). The simple interaction or interface interruption mechanism thus cannot explain the effects of phosphorylation at several sites outside of the helical segments. Instead, the unbound state of p53-TAD must also be considered. Specifically, the disordered ensemble of free TAD is highly susceptible to post-translational modifications, which could alter the level of residual structures and modulate the entropy cost of folding upon specific binding to regulate the binding affinity. Such a mechanism has been demonstrated in our previous study of the CREB/CBP interaction[19]. The molecular mechanism of p53 activation by multisite phosphorylation is highly relevant for understanding how TAD cancer mutants may alter the spectrum of target gene transactivation[74] and contribute to the gradient of p53 tumor suppression function in cancers[75]. In particular, the current simulations strongly support that TAD cancer mutants can significantly modulate the unbound conformational ensembles, which could in turn disturb the balance between binding to MDM2 and CBP and further alter how the balance is regulated by multisite phosphorylation of TAD. Establishing the functional implications of the predicted cancer mutant modulation of the disordered ensembles will require additional experimental characterization of TAD cancer mutant structural properties as well as new biochemical and biophysical measurements of p53 binding thermodynamics with key regulatory proteins. The success of the current simulations demonstrates the feasibility and promise of combining advanced sampling techniques and modern atomistic force fields, particularly with implicit solvent, for effective IDP simulations. Coupled with appropriate structural and biophysical experiments, de novo atomistic simulations could provide a general framework for comparatively assessing the effects of disease-related mutations as well as post-translational modifications on IDP structure and interaction. At the same time, important limitations remain in implicit solvent protein force fields, and the simulated ensembles are overly compact. This has proven to be a key artifact that not only severely hinders our ability to generate highly converged ensembles but also greatly compromises reliable interpretation of predicted structural impacts of mutations. The current study thus also underpins the importance of continual development and optimization of implicit solvent protein force fields.", "role": "user" }, { "content": "Tumor suppressor p53 is the most frequently mutated protein in human cancers . Clinical studies have suggested that the type of p53 mutation can be linked to cancer prognosis , response to drug treatment , and patient survival . It is thus crucial to understand the molecular basis of p53 inactivation by various types of mutations , so as to understand the biological outcomes and assess potential cancer intervention strategies . Here , we utilize a recently developed replica exchange with guided annealing enhanced sampling technique to calculate well-converged atomistic conformational ensembles of the intrinsically disordered transactivation domain ( TAD ) of tumor suppressor p53 and several cancer-associated mutants in an implicit solvent protein force field . The calculated ensembles are in quantitative agreement with several types of existing NMR data on the wild-type protein and the K24N mutant . The results suggest that , while all sequences sample a similar set of conformational substates , cancer mutants could introduce both local and long-range structural modulations and in turn perturb the balance of p53 binding to various regulatory proteins and further alter how this balance is regulated by multisite phosphorylation of p53-TAD . The study also reveals important limitations in implicit solvent for simulations of disordered proteins like p53-TAD .", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nThe outbreak of the novel coronavirus that began in late December 2019 was announced as a pandemic by the World Health Organization as the number of cases is increasing exponentially throughout the globe. We presented a patient with confirmed SARS-CoV-2 pneumonia developing symmetric polyneuropathy. To our knowledge, extrapulmonary clinical presentations of 2019 novel coronavirus disease (COVID-19) have rarely been reported. This case highlights the possible association between SARS-CoV-2 infection and nervous system involvement.", "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 conditions of the incubation reactions as well as the concentration of the substrate reaction probes utilized were established based on previous CYP450 inhibition studies by our group in human liver microsomes [20–24].", "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\nThere are no proven safe and effective therapies for children who develop life-threatening complications of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Convalescent plasma (CP) has demonstrated potential benefit in adults with SARS-CoV-2, but has theoretical risks.We present the first report of CP in children with life-threatening coronavirus disease 2019 (COVID-19), providing data on four pediatric patients with acute respiratory distress syndrome. We measured donor antibody levels and recipient antibody response prior to and following CP infusion. Infusion of CP was not associated with antibody-dependent enhancement (ADE) and did not suppress endogenous antibody response. We found CP was safe and possibly efficacious. Randomized pediatric trials are needed.", "role": "user" }, { "content": "[\"Treatment\"]", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nWithin a few months, coronavirus disease 2019 (COVID-19) has become a pandemic with more than 2 million patients infected and a high mortality rate. Early detection of COVID-19 in oncologic patients is crucial in order to rapidly apply isolation measures and avoid nosocomial spread. However, early diagnosis may be challenging, especially in cancer patients under treatment with immunotherapy as drug-induced pneumonitis can present similar clinical and radiological features. We describe the findings of a SARS-CoV-2 infection on PET/CT with F-FDG in a 51-year-old man with metastatic renal cell carcinoma under treatment with nivolumab.", "role": "user" }, { "content": "[\"Case Report\"]", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nextramammary paget 's disease ( empd ) is a rare epidermal carcinoma that most often appears in the anogenital region .\nit resembles paget 's disease of the nipple in appearing as isolated paget cells or small groups of paget cells rather than as a continuous mass [ 2 , 3 ] .\nthe presence of sialomucin is one way of distinguishing malignant paget cells from benign toker cells and from the malignant cells of bowen 's disease [ 1 , 7 , 8 ] .\nall three cell types appear as groups of 150 large cells with enlarged nuclei and pale cytoplasm in h&e or trichrome preparations ; they can be confused if the diagnosis is made on the basis of morphology alone .\nan immunohistochemical re - evaluation of morphological diagnoses of extra - mammary paget 's disease , bowen 's disease and superficial spreading malignant melanoma found a 5% error rate in the original diagnoses .\nthe risks of such a mistake are serious : toker cells are a common benign anomaly [ 6 , 10 , 11 ] , and bowen 's disease can usually be treated with topical chemotherapy alone [ 12 , 13 ] , but empd usually requires surgery [ 14 , 15 ] or prolonged radiotherapy . sialomucins are easily stained with zirconyl haematoxylin or alcian blue .\nthe occasional absence of mucin in empd has led to the suggestion that mucin staining should be supplemented by at least one immunohistochemical stain in all cases of suspected empd [ 17 , 18 ] .\nthe presence of cytokeratin 7 usually distinguishes empd from bowen 's disease [ 19 , 20 ] , but not from toker cells .\nthe recent availability of antibodies to human mucin core proteins has led to a search for specific mucin markers to distinguish empd from similar skin lesions and to determine the extent of empd .\nmucous neck cell - type mucin ( muc6 ) has never been found in paget cells [ 5 , 22 , 23 ] .\nintestinal type mucin ( muc2 ) has only rarely been found in paget cells [ 5 , 23 ] .\ngastric surface - type mucin ( muc5ac ) is often found in empd [ 5 , 22 , 23 ] .\nepithelial membrane antigen ( ema ) , also known as episialin or muc1 , has the chemical structure of a mucin , but it is normally a transmembrane glycoprotein rather than a secreted glycoprotein [ 24 , 25 , 26 ] .\npaget cells usually contain sialylated intracellular ema in both extramammary and mammary paget 's disease .\nema is weakly expressed in bowen 's disease , and it is usually confined to the cell membrane [ 27 , 28 ] . unlike the sialylated ema usually found in empd , the ema found in bowen 's disease usually has little or no sialic acid and does not stain with alcian blue .\nrarely , the diagnosis of extramammary paget 's disease is complicated by the absence of sialomucins from the paget cells . finding a case of non - mucin - secreting empd led us to ask if the mucin core proteins might be present without their oligosaccharide side chains .\nslides of formalin - fixed paraffin - embedded sections of two cases of empd of the vulva were obtained from the co - operative human tissue network .\npieces of labia minora from two patients , pieces of perineal skin from two female patients and a fragment of skin from the medial thigh from one male patient were fixed in 10% formalin , embedded in paraffin , and cut at 7 m . a slide from each case\nwas stained with ehrlich 's haematoxylin and eosin y , zirconyl haematoxylinand methylene green , alcian blue at ph 2.5 and kernechtrot and the pas reaction .\ntwo sections from each case of empd were de - paraffinized , heated to 95c for 40 min . in 0.10 m ph 6.0 citrate buffer to retrieve the antigen , treated with 0.3% hydrogen peroxide in methanol for 30 min . to quench endogenous peroxidase activity , followed by 1.5% normal horse serum ( vector ) in pbs for 20 min . , incubated 6 hr at 23c in a 1:200 dilution of mouse monoclonal antibodies ( clone mab 2011 , chemicon , temecula , ca ) to muc5ac in 1.5% normal horse serum , washed in pbs , incubated 30 min in 0.5% biotinylated horse anti - mouse immunoglobulin ( vector ) in pbs , washed in pbs , treated with avidin - conjugated horseradish peroxidase ( vector abc kit ) for 30 min . and washed in pbs .\none section was stained with vector 's nova red for 5 min . and counterstained in haematoxylin ; the second section was stained with vector 's vip for 2 min . and counterstained in kernechtrot .\none section from each of the five normal control tissues was incubated in the same way and stained with nova red .\nall sections were dehydrated , cleared and mounted in permount ( fisher , atlanta , ga ) .\na control section from each case of empd was treated similarly with the omission of the mouse antibodies to muc5ac and stained with nova red .\nthe mouse antibodies to muc5ac were raised against a synthetic polypeptide of the consensus tandem repeat of human muc5ac core protein : threonine - threonine - serine - threonine - threonine - serine - alanine - proline [ 33 , 34 , 35 ] .\none section from each case was de - paraffinized , blocked with 0.3% hydrogen peroxide in methanol for 30 min .\nfollowed by 1.5% normal horse serum ( vector , burlingame , ca ) in pbs for 20 min . , incubated 30 min . at 23c in a 1:100 dilution of mouse monoclonal antibodies ( clone zce 113 , zymed , san francisco , ca ) to human ema in 1.5% normal horse serum ( vector ) , washed in pbs , incubated 30 min .\nin 0.5% biotinylated horse antimouse immunoglobulin ( vector ) , treated with avidin - conjugated horseradish peroxidase ( vector abc kit ) for 30 min . , stained with vector 's nova red for 15 min . , counterstained in haematoxylin , dehydrated , cleared and mounted in permount .\none section from each of the five normal control tissues was treated the same way .\nanother section from each case of empd was treated similarly with the omission of the mouse antibodies to ema .\nthe mouse antibodies to ema were raised against cream from human milk , which contained membrane - bounded fat globules .\nboth cases of empd showed many cells with typical paget cell morphology ( enlarged cells with an enlarged nucleus and pale cytoplasm ) in the epidermis of sections stained with haematoxylinand eosin the paget cells in slides from the typical case stained with zirconyl haematoxylin ( fig .\nthe paget cells in slides from the other case did not stain at all with zirconyl haematoxylin ( fig .\nthey did not stain with the pas reaction , showing the absence of any kind of mucin .\nnormal keratinocytes in both cases of empd and in the control tissues did not stain with zirconyl haematoxylin or alcian blue , but they did stain faintly with pas .\nsialomucin in typical paget cells stains purple with zirconyl haematoxylin . the nuclei stain with methylene green .\npaget cells in mucin - negative extramammary paget 's disease fail to stain with zirconyl haematoxylin .\n4 ) case reacted with monoclonal antibody to muc5ac mucin core polypeptide . in both cases ,\na few cells that did not have a paget cell morphology reacted with antibody to muc5ac polypeptide .\npaget cells in mucin - positive extramammary paget 's disease contain muc5ac core protein ( red brown reaction product ) .\nmany paget cells in mucin - negative extramammary paget 's disease contain muc5ac core protein ( red brown reaction product ) .\na morphologically normal cell ( arrow ) also contains muc5ac core protein ( red brown reaction product ) .\nlive keratinocytes in the control tissues never stained with antibody to muc5ac , but light background staining was often seen in the stratum corneum ( fig .\nmelanin in the stratum basale is grey brown unlike the red brown of nova red .\nalmost all paget cells in both cases reacted strongly with monoclonal antibody to ema ( figs .\na few cells that did not have paget cell morphology reacted with antibody to ema .\ncontrol slides of paget 's disease with the antibody omitted did not stain . mucin - negative extramammary paget 's disease .\nthe paget cells and two morphologically normal cells ( arrows ) contain epithelial membrane antigen ( red brown reaction product ) . mucin - positive extramammary paget 's disease .\nthe paget cells and two morphologically normal cells ( arrows ) contain epithelial membrane antigen ( red brown reaction product ) .\nno cells in the control skin from the thigh or from the perineum reacted with antibody to ema .\nsebaceous glands in both control labia minora reacted strongly with antibody to ema ; keratinocytes did not react ( fig . 8) .\neven the epithelium around a microscopic condyloma in one labium minus did not react with antibodies to ema .\n( the patient was referred to her gynaecologist for treatment of the underlying human papilloma virus infection . )\nnote the difference between the red brown stain in the sebaceous gland and the grey brown melanin in the stratum basale .\nit is common knowledge that normal epidermis does not contain sialomucins [ 1 , 4 , 5 ] .\nwhere normal skin has been used as a control , neither muc5ac and ema core proteins have been noticed in the epidermis .\nthis study searched for muc5ac and ema core proteins in normal epidermis and found neither .\nit is notable that the non - mucinsecreting paget cells contained less glycogen than the surrounding normal keratinocytes .\nour antibody ( from chemicon ) and their antibody ( from novocastra ) were both monoclonal antibodies to synthetic polypeptides with the same amino acid sequence .\nnevertheless , our antibody bound more quickly and less specifically than theirs , forcing us to use a shorter incubation time to eliminate background staining .\nliegl et al . , using twice our antibody concentration , found that their antibody ( from eubio ) bound to paget cells in less than half their cases .\nthe wide variation in the experience of different research groups suggests that muc5ac core protein is not a reliable marker for the diagnosis of extramammary paget 's disease .\nthe failure of some paget cells in our cases to bind muc5ac antibody also suggests that muc5ac core protein would not be a reliable marker for mapping the extent of empd .\nthe staining of mucin - negative paget cells with antibodies to ema , that is muc1 , raised against human milk fat globules confirms previous observations [ 36 , 37 ] that many antibodies generated against the complete glycoprotein bind to the core protein .\nit is believed that the most antigenic portion of the complete glyco - protein is the 20 amino acid tandem repeat polypeptide .\n( it has been suggested that paget cells may be malignantly transformed toker cells [ 10 , 11 ] .\nthe appearance of antigens typical of paget cells in cells that resemble keratinocytes rather than toker cells , suggests that paget cells arise from keratinocytes rather than toker cells . )\nalthough neither sialic acid residues nor the distribution pattern of ema core protein are infallible markers for the diagnosis of empd , each is useful when used separately and , when used together , greatly enhance the accuracy of diagnosis .\nthe almost universal presence of ema in paget cells ( 5 , 22 ) makes it a good marker for determining the extent of the disease\nthe presence of ema and muc5ac core protein in a few cells that did not have the morphology of paget cells suggests the possibility that they may be incipient paget cells .\nif so , extramam - mary paget 's disease arises from many cells and removal of all cells with paget cell morphology often leaves some incipient paget cells behind .\nthis would account for the high rate of recurrences after surgical excision of empd [ 4042 ] .\nif our surmise is correct , mapping the margins of extramammary paget 's disease with antibodies to ema should reduce the rate of recurrence after surgical excision .\n( by detecting incipient paget cells before they attain paget cell morphology , immunohistochemical detection of epithelial membrane antigen could make surgical margins more accurate and sharply reduce the rate of recurrence . )", "role": "user" }, { "content": "abstractextramammary paget 's disease ( empd ) is a rare skin cancer of the genital region in which cancer cells with enlarged nuclei and pale cytoplasm are scattered singly in the affected epidermis . \n these cancer cells , called paget cells , contain mucin , which is never found in normal epidermis . the oligosaccharide side chains of paget cell mucin end with sialic acid . sialic acid \n is easily detected by zirconyl haematoxylin or alcian blue . \n the other sugars in the oligosaccharide chains can be detected by the periodic acid - shiff reaction . rarely , the diagnosis of empd is complicated by the absence of mucin from the paget cells . \n we have examined such an atypical case . \n the oligosaccharide side chains , including the sialic acids , are absent . in both this case and a typical case , the paget cells contain epithelial membrane antigen mucin ( muc1 ) core protein and usually contain gastric surface - type mucin ( muc5ac ) core protein , which can be stained by antibodies . since neither core protein \n is found in normal epidermis , epithelial membrane antigen core protein may be the most reliable diagnostic marker for extramammary paget 's disease . in both the atypical case and the typical case of paget 's diseas , some cells that look like \n keratinocytes contain mucin core proteins \n . these may be incipient paget cells . \n we suggest that using th epithelial membrane antigen core protein as a marker for the true extent of extramammary paget 's disease could facilitate complete excision and reduce the rate of recurrence .", "role": "assistant" } ]

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

[ { "content": "Write a Related Work section based on these abstracts. Use numerical citations like [1], [2], etc.\n\nMain Abstract:\nRecently, it has been shown that deep neural networks (DNN) are subject to attacks through adversarial samples. Adversarial samples are often crafted through adversarial perturbation, i.e., manipulating the original sample with minor modifications so that the DNN model labels the sample incorrectly. Given that it is almost impossible to train perfect DNN, adversarial samples are shown to be easy to generate. As DNN are increasingly used in safety-critical systems like autonomous cars, it is crucial to develop techniques for defending such attacks. Existing defense mechanisms which aim to make adversarial perturbation challenging have been shown to be ineffective. In this work, we propose an alternative approach. We first observe that adversarial samples are much more sensitive to perturbations than normal samples. That is, if we impose random perturbations on a normal and an adversarial sample respectively, there is a significant difference between the ratio of label change due to the perturbations. Observing this, we design a statistical adversary detection algorithm called nMutant (inspired by mutation testing from software engineering community). Our experiments show that nMutant effectively detects most of the adversarial samples generated by recently proposed attacking methods. Furthermore, we provide an error bound with certain statistical significance along with the detection.\n\nCited Abstract(s):\n[1]: Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. Most existing approaches for crafting adversarial examples necessitate some knowledge (architecture, parameters, etc.) of the network at hand. In this paper, we focus on image classifiers and propose a feature-guided black-box approach to test the safety of deep neural networks that requires no such knowledge. Our algorithm employs object detection techniques such as SIFT (Scale Invariant Feature Transform) to extract features from an image. These features are converted into a mutable saliency distribution, where high probability is assigned to pixels that affect the composition of the image with respect to the human visual system. We formulate the crafting of adversarial examples as a two-player turn-based stochastic game, where the first player's objective is to minimise the distance to an adversarial example by manipulating the features, and the second player can be cooperative, adversarial, or random. We show that, theoretically, the two-player game can con- verge to the optimal strategy, and that the optimal strategy represents a globally minimal adversarial image. For Lipschitz networks, we also identify conditions that provide safety guarantees that no adversarial examples exist. Using Monte Carlo tree search we gradually explore the game state space to search for adversarial examples. Our experiments show that, despite the black-box setting, manipulations guided by a perception-based saliency distribution are competitive with state-of-the-art methods that rely on white-box saliency matrices or sophisticated optimization procedures. Finally, we show how our method can be used to evaluate robustness of neural networks in safety-critical applications such as traffic sign recognition in self-driving cars.\n\n[2]: Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN-driven autonomous cars that, using sensors like camera, LiDAR, etc., can drive without any human intervention. Most major manufacturers including Tesla, GM, Ford, BMW, and Waymo Google are working on building and testing different types of autonomous vehicles. The lawmakers of several US states including California, Texas, and New York have passed new legislation to fast-track the process of testing and deployment of autonomous vehicles on their roads. However, despite their spectacular progress, DNNs, just like traditional software, often demonstrate incorrect or unexpected corner case behaviors that can lead to potentially fatal collisions. Several such real-world accidents involving autonomous cars have already happened including one which resulted in a fatality. Most existing testing techniques for DNN-driven vehicles are heavily dependent on the manual collection of test data under different driving conditions which become prohibitively expensive as the number of test conditions increases. In this paper, we design, implement and evaluate DeepTest, a systematic testing tool for automatically detecting erroneous behaviors of DNN-driven vehicles that can potentially lead to fatal crashes. First, our tool is designed to automatically generated test cases leveraging real-world changes in driving conditions like rain, fog, lighting conditions, etc. DeepTest systematically explores different parts of the DNN logic by generating test inputs that maximize the numbers of activated neurons. DeepTest found thousands of erroneous behaviors under different realistic driving conditions (e.g., blurring, rain, fog, etc.) many of which lead to potentially fatal crashes in three top performing DNNs in the Udacity self-driving car challenge.\n\n[3]: Deep learning (DL) systems are increasingly deployed in safety- and security-critical domains including self-driving cars and malware detection, where the correctness and predictability of a system's behavior for corner case inputs are of great importance. Existing DL testing depends heavily on manually labeled data and therefore often fails to expose erroneous behaviors for rare inputs. We design, implement, and evaluate DeepXplore, the first whitebox framework for systematically testing real-world DL systems. First, we introduce neuron coverage for systematically measuring the parts of a DL system exercised by test inputs. Next, we leverage multiple DL systems with similar functionality as cross-referencing oracles to avoid manual checking. Finally, we demonstrate how finding inputs for DL systems that both trigger many differential behaviors and achieve high neuron coverage can be represented as a joint optimization problem and solved efficiently using gradient-based search techniques. DeepXplore efficiently finds thousands of incorrect corner case behaviors (e.g., self-driving cars crashing into guard rails and malware masquerading as benign software) in state-of-the-art DL models with thousands of neurons trained on five popular datasets including ImageNet and Udacity self-driving challenge data. For all tested DL models, on average, DeepXplore generated one test input demonstrating incorrect behavior within one second while running only on a commodity laptop. We further show that the test inputs generated by DeepXplore can also be used to retrain the corresponding DL model to improve the model's accuracy by up to 3 .\n\n[4]: Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated using machine-learning. However, deep neural networks are opaque to human engineers, rendering their correctness very difficult to prove manually; and existing automated techniques, which were not designed to operate on neural networks, fail to scale to large systems. This paper focuses on proving the adversarial robustness of deep neural networks, i.e. proving that small perturbations to a correctly-classified input to the network cannot cause it to be misclassified. We describe some of our recent and ongoing work on verifying the adversarial robustness of networks, and discuss some of the open questions we have encountered and how they might be addressed.\n\n[5]: \n\n[6]: Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems. However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their behavior. We present a novel, scalable, and efficient technique for verifying properties of deep neural networks (or providing counter-examples). The technique is based on the simplex method, extended to handle the non-convex Rectified Linear Unit (ReLU) activation function, which is a crucial ingredient in many modern neural networks. The verification procedure tackles neural networks as a whole, without making any simplifying assumptions. We evaluated our technique on a prototype deep neural network implementation of the next-generation airborne collision avoidance system for unmanned aircraft (ACAS Xu). Results show that our technique can successfully prove properties of networks that are an order of magnitude larger than the largest networks verified using existing methods.", "role": "user" }, { "content": "There are some relevant research in the software engineering community as well. Both white-box and black-box testing strategies have been proposed to generate adversarial data more efficiently [3] [1] [2] . There are also attempts to formally verify the DNN to provide safety and security guarantees [3]1 [2]1 [4] , which are however proven to be too computationally expensive and not scalable to large DNN.", "role": "assistant" } ]

[ { "content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: HGisastraininwhichthehgdeletionhasbeenintrogressedontoaB6background,thereforetheonlygeneticdifferencesbetweenthestrainswouldbethehglocus,tightlylinkedallelesfromtheoutbredstrainonwhichhgaroseandcontaminatingallelesremainingaftertheninebackcrossesandfixedduringinbreeding.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Classify the intent of this citation from an NLP research paper. \n\nYour answer must be one word from: [\"Background\", \"Extends\", \"Uses\", \"Motivation\", \"CompareOrContrast\", \"FutureWork\"]. No other text allowed.\n\nSection Title:\nintroduction\n\nContext before:\nOpposition (called &quot;adversative&quot; or &quot;contrary-to-expectation&quot; by Halliday and Hasan 1976; cfXXX also Quirk et al. 1972, p. 672). 1. However, &quot;but&quot; does not behave quite like the other two—semantically, &quot;but&quot; signals a contradiction, and in this role it seems to have three subfunctions: \u0000\u0000\u0000\u0000\u0000\u0000\n\nCitation:\nOpposition ( called `` adversative '' or `` contrary-to-expectation '' by Halliday and Hasan 1976 ; cfXXX also Quirk et al. 1972 , p. 672 ) .\n\nContext after:\nThe ship arrived but the passengers could not get off. The yacht is cheap but elegant. 2. Comparison.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Answer the following biomedical question based on the given context. Provide only the answer without additional explanation.\n\nQuestion: What does polyadenylate-binding protein 4 (PABP4) bind to?\n\nContext: RNA binding proteome\nIn vertebrates, poly(A) binding protein (PABP) is known to exist in five different isoforms.\nCytoplasmic poly(A)-binding proteins (PABPs) regulate mRNA stability and translation.\npoly(A) binding proteins 1 and 4 (PABPC1 and PABPC4)\nCytoplasmic poly(A) binding protein 4 (PABPC4) is an RNA-processing protein that plays an important role in the regulation of gene expression.\nCytoplasmic poly(A) binding protein 4\npoly(A)-binding protein (PABP)\nPoly(A) binding protein (PABP) binds mRNA poly(A) tails\nUsing mass spectrometry sequencing we identified poly(A) binding proteins-1 and -4 (PABP1 and PABP4)\nThe poly(A)-binding protein (PABP) is an important translation initiation factor that binds to the polyadenylated 3' end of mRNA.\nA family of cytoplasmic poly(A)-binding proteins (PABPs) bind the poly(A) tail and can regulate mRNA translation and stability.\nHuman PABP binds AU-rich RNA via RNA-binding domains 3 and 4.", "role": "user" }, { "content": "PABP4 binds mRNA poly(A) tails.", "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: Similar observations have been made in the USA, where gonorrhoea and other sexually transmitted infections (STIs) have been shown in multiple studies to be concentrated in certain geographical areas (Rothenberg 1983; Potterat et al. 1985; Bernstein et al. 2004; Kerani et al. 2005).", "role": "user" }, { "content": "Result", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nNovel Hypoglycemic Dihydropyridones Serendipitously Discovered from O-versus C-Alkylation in The Synthesis of VMAT2 Antagonists\n\nPaper sections:\n\n<p>Diabetes mellitus is a growing epidemic affecting hundreds of millions worldwide.1 Despite a recent explosion of new classes of hypoglycemic agents, the medical need remains largely unmet and innovative diagnostics and therapeutics are still urgently needed. We have been particularly interested in the vesicular monoamine transporter type 2 (VMAT2) as a potential diagnostic and therapeutic target for diabetes.</p><p>VMAT is a member of the vesicular transporter family responsible for the uptake and secretion of monoamine neurotransmitters in neurons and endocrine cells.2 Two isoforms of VMAT (type 1 and 2) have been cloned, and interestingly, the insulin-producing beta cells in the pancreas only express the VMAT2 isoform.3 We recently have demonstrated the feasibility of noninvasive measurement of beta cell mass both in humans and rodents by positron emission tomography (PET) using VMAT2 as the biomarker and its specific antagonist dihydrotetrabenazine (DTBZ) as the tracer.4,5 More strikingly, our studies have further shown that VMAT2 plays an important functional role in the regulation of insulin secretion in beta cells.6 VMAT2 antagonist tetrabenazine (TBZ) and its active metabolite DTBZ (Figure 1) are potent hypoglycemic agents that stimulate insulin secretion in vitro and improve glucose tolerance in normal and diabetic rats.6 VMAT2 antagonists, therefore, have both diagnostic and therapeutic potential in the management of diabetes mellitus.</p><p>In an effort to generate novel VMAT2 antagonists, we attempted to synthesize compound 1(Figure 1), a simplified analog of DTBZ. As shown in Scheme 1, veratraldehyde 2 was treated with ammonium acetate and converted into β-amino acid 3 by condensation with malonic acid. Protection with Boc anhydride and subsequent condensation with potassium malonate methyl ester led to β-keto ester 4. Alkylation with isobutyl bromide in the presence of potassium carbonate afforded a mixture of 5 and 6 in moderate yield. After removal of the Boc group, the mixture was treated with sodium bicarbonate in methanol to yield the cyclized products 7 and 8 quantitatively. Compound 9 were obtained from reduction of 7 with sodium borohydride and then further converted to 1 and its diasteroisomers with lithium aluminum hydride.</p><p>Racemic compound 1 and its diastereoisomers were evaluated for their ability to improve glucose tolerance by intraperitoneal glucose tolerance tests (IPGTT)7 in rats. The new analogs were less potent than TBZ possibly due to diminished affinity for VMAT2 (Figure 2). This poor result halted our further study of compound 1. However, during random screens of intermediates generated in the course of the synthesis of 1, we found that compound 8, a novel dihydropyridone resulted from the competing O-versus C-alkylation of enolic β-keto ester 4 followed by cyclization, showed potent hypoglycemic effect. As illustrated in Figure 2, compound 8 decreased by 45% the AUC IPGTT (the area under the blood glucose concentration-time curve) at the dose of 2mg/kg compared to 26% for TBZ.</p><p>Prompted by this surprising result, we designed and synthesized several analogs of 88. As outlined in Scheme 2, veratraldehyde 2 was first condensed with ethyl acetoacetate and spontaneous cyclization yielded lactone 10. Using potassium carbonate as the base, O-alkylation of 10 with methyl bromide or isobutyl bromide provided 11 and 12. Similarly, 15 and 16 were prepared from dihydroisoquinoline 13 via condensation with dimethyl 1,3-acetonedicarboxylate followed by cyclization and alkylation. DDQ-induced aromatization and acidic hydrolysis of 8 afforded 17 and 18 respectively. Analogs prepared as above were tested for their hypoglycemic activities in rats using the IPGTT protocol. Interestingly, the hypoglycemic effects of these compounds were only seen following glucose stimulation. Results in Figure 2 demonstrated that the dihydropyridone scaffold in 8 is essential to the hypoglycemic activity. Replacement with dihydropyrone (11, 12), oxidation or hydrolysis of 8 (17, 18) resulted in total loss of activities. Interestingly, the rigid derivatives 15 and 16 were active but less potent in opposition to the SAR trend seen in compound 1 and DTBZ.</p><p>To test whether the strong hypoglycemic effect of 8 is conferred by binding to VMAT2 in beta cells, we performed a PET study in rats.9 The animals were treated with radiolabeled DTBZ and the uptake of [11C] DTBZ in pancreas was monitored by PET scan in the presence of excess of 8. Contrary to our expectation, 8 did not significantly displace [11C]DTBZ in the endocrine pancreas (Figure 3), suggesting a weak binding of 8 to VMAT2 relative to DTBZ. VMAT2 is known to possess multiple binding sites.10 Our results don't rule out the possibility that 8 binds to VMAT2 at different binding site. We have previously shown that TBZ and DTBZ act directly on beta cells of the endocrine pancreas to increase insulin secretion following glucose challenge 6, and give rise to a hypoglycemic activity, but due to abundant expression of VMAT2 in brain, these compounds also cause central nervous system side effects. Interestingly, we observed that the treatment with 8 (at 2 mg/Kg) was devoid of tonic seizure commonly associated with equal doses of TBZ or DTBZ, supporting that compound 8 works through a different mechanism. Another possibility consistent with our observations is that 8 may act as a competitive inhibitor of dopamine at VMAT2 on beta cell vesicles. DTBZ and its analogs are structurally similar to a class of quinolizine alkaloids previously shown to inhibit dipeptidyl peptidase IV (DPP-IV),11 but 8 tested negative against DPP-IV in vitro at concentrations up to 10μM (data not shown).12 Therefore the mechanism underlying the anti-hyperglycemic effect of 8 remains to be determined.</p><p>In summary, we have completed the synthesis of a novel analog of VMAT2 antagonist DTBZ (Compound 1). Despite the disappointing results of 1, a highly potent hypoglycemic agent (compound 8) was serendipitously discovered. Subsequent modification revealed the requirement of a novel dihydropyridone core structure for the activity. Mechanism studies show that compound 8 may not work through VMAT2 and DPP-IV. More detailed studies of 8 are currently being pursued.</p>", "role": "user" }, { "content": "Vesicular monoamine transporter type 2 (VMAT2) is a newly emerging target for both diagnostic and therapeutic applications in diabetes mellitus. In pursuit of novel VMAT2 antagonists, we identified a potent hypoglycemic agent with a novel dihydropyridone scaffold. Several analogs were designed and synthesized. A preliminary structure activity relationship (SARs) showed that the dihydropyridone scaffold is required for the activity.", "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:\nrecent theoretical and experimental efforts have focused on the mechanism of electron trapping in dielectric materials .\nthe space charge model @xcite based on the concept of polaron @xcite has been developed to explain trapping and its consequences from an energetic point of view .\nthe main underlying idea is that electrons trapped into the lattice build up a space charge simultaneously generating a mechanical deformation ( polaron ) .\nenergy is stored both in electrostatic ( coupling ) and in mechanical ( internal ) forms @xcite . beyond a critical concentration of trapped electrons , dielectric breakdown or\nflashover occurs . the mechanical part of the energy is then released in the form of a thermal shock wave that produces a local heating large enough to create a plasma , eventually leading to the rupture of the material .\none of the main consequences is that dielectric breakdown would not arise because of an external driving force ( e.g. a high voltage difference between the electrodes ) , but because of the internal stress caused by the accumulation of the trapped charges .\nthorough investigations have shown that electrons can be trapped in a lattice as soon as a local variation of the dielectric susceptibility occurs .\nthis variation can be either due to defects ( vacancies , impurities , interfaces , etc ... ) or to crystallographic dissymetry . once the charge is trapped the lattice is distorted and polarized .\nthe energy involved in this process has been evaluated within some realistic approximation , and it has been shown that an energy of at least 5 ev is stored upon electron trapping . on the other hand , trapping has been studied experimentally using the mirror method @xcite .\nit has been shown that trapping can occur in pure sapphire ( single - crystals ) only for temperatures lower than 250 @xmath0 , but the trapping / detrapping dynamics in this kind of materials is not yet fully understood . in particular , the dynamic behavior in the range of pico - second to femto - second can not be observed in real experiments , while it is crucial to elucidate the charge trapping mechanisms . in this work\nwe apply molecular dynamics technique ( md ) , which has widely proven efficiency in reproducing the properties of real materials @xcite , to explore these aspects of electron trapping in .\nionic polarization has been described in terms of a shell model which is briefly outlined in the following section .\nwe then show how the solvated electron can stay firmly in some specific lattice sites at low temperature producing a local polarization and how , despite the fact that the potential turns out to be quite deep , the electron can self - detrap at moderate temperatures .\nthe potential used for corundum was based on the assumption of a fully ionic model @xcite .\nionic polarization was introduced through a modified shell model . in the shell model introduced by dick and overhauser @xcite ,\neach ion is represented by a massive core and a massless shell which simulates the valence electrons .\nthe total ionic charge divides amongst core and shell , the core - shell interactions being described by harmonic springs . in this work\nwe use a modified shell model due to catlow and stoneham @xcite .\nthe assumption of massless shells is a way to introduce the adiabatic ( born - oppenheimer ) approximation in the context of the shell model .\nit means that shells have to adjust instantaneously to the present configuration of the cores .\nthis implies that a full relaxation of the shells is needed at each step of the md simulation . in practice\n, full relaxation is very difficult and costly to achieve , but if a less strict convergence is required , a systematic error is accumulated during the simulation that unphysically damps the motion of the cores @xcite .\nthe slight inconsistency between force and energy translates into a continuous and systematic energy loss . to avoid this problem we adopted a car - parrinello - like strategy by assigning a small , but finite mass to the shells , and by treating them as dynamical variables evolving according to their own ( fictitious ) equations of motion @xcite .\nthis approach proved to be very efficent in the context of ab initio md , and the reason is that a second order dynamics for the shells gives rise to oscillating fictitious forces on the cores that average out during the slow dynamics of the cores .\nwe have chosen a mass of 10% the proton mass , so ensuring energy conservation to high accuracy . the coulombic contribution to the interionic potential\nis calculated by the ewald summation technique @xcite .\nnon - coulombic , short - range interactions between shells are described by the buckingham potential @xcite , i.e. @xmath1 the sets of parameters a@xmath2 , c@xmath2 , and @xmath3 for each pair of ionic species are displayed in table i , and the values of the spring constant and the partial charges for cores and shells in table ii .\nall values have been taken from ref .\n@xcite , except for the al@xmath4 core - shell spring constant which was adjusted to fit the dielectric constant of computed from the simulation to the experimental value ( @xmath5 ) .\nthe simulation has been performed on a system of 120 ions at constant number , volume and temperature ( canonical ensemble ) .\nwe have placed the particles into an orthorhombic simulation box of experimental lattice constants , and replicated using periodic boundary conditions .\nverlet algorithm was used to integrate the equations of motion .\na time step of 0.1 fs had to be used in order to integrate properly the equations of motion for the shells , due to their small mass .\nsimulations were started with all ions at their equilibrium positions , and velocities taken at random from a maxwell - boltzmann distribution at the desired temperature . before simulating the charge trapping\nwe have verified the accuracy of the model on reproducing the physical properties of pure , namely the lattice energy and the mean square displacement .\nwe have found a value of -160 ev at @xmath6 , compared to -160.4 ev from experiment @xcite and -160.24 ev from catlow and al .\nthe mean square displacement also compared reasonably with experimental measurements at @xmath7 and @xmath8 @xcite , as shown in figs . 1 and 2 . these results obtained with our modified shell model gave us confidence to continue the study of charge trapping by introducing an excess electron into the corundum lattice .\nthe lattice of alumina can be described as a succession of anionic and cationic planes with hexagonal in - plane ordering . the o@xmath9 ions form an hexagonal compact stacking , slightly distorted in order to make room for the larger al@xmath4 ions .\nall sites of the crystallographic arrangement are non - equivalent @xcite .\nwe first run the simulation for a perfect crystal of 120 ions for 10000 time steps ( equal to 1 ps ) to ensure thermal equilibration . to obtain a hint on possible trapping sites\nwe have computed the ( unrelaxed ) potential energy surface at the ( 001 ) plane that contains the o@xmath9 ions .\nthe potential of the uncharged lattice at a generic point ( x , y ) in the ( 001 ) plane is given by the coulomb interaction between the ions in the crystal and a test particle of charge unity placed at that point . since the test particle is a hypothetical object , the potential has to be computed with all ions in the equilibrium positions of the uncharged lattice .\nthe resulting surface is shown in fig .\nit can be osverved the existence of local minima where the electron can be trapped .\nwe have chosen the position of one of these potential wells as the initial position for the excess electron in our simulation . in this first approach to the problem of electron dynamics in dielectrics we have considered the electron as a purely classical particle .\nthe interaction potential between the electron and o@xmath9 was modelled by a pure coulomb repulsion at all distances .\n@xmath10 the e@xmath11al@xmath4 interaction was instead described in terms of short - range repulsion , as though the excess electron was an oxygen shell , but of charge unity and finite mass ( the electron mass ) .\nwe have performed simulations at several different temperatures up to 300 @xmath0 .\n4 shows the path of the ( classical ) electron at 300 @xmath0 , and fig .\n5 corresponds to 200 @xmath0 .\nalso the potential energy surface in the ( 001 ) plane is shown in the plots . in fig .\n6 we plot the mean square distance traveled by the electron as a function of time .\nit is clearly apparent that at 300 @xmath0 the electron escapes from the initial trapping site , while at 200 @xmath0 it stays close to the bottom of the potential well .\nthe transition from one regime to the other has been located around 250 @xmath0 .\nbelow this temperature the excess electron solvates , and above it jumps from one well to another .\nthese results are in good agreement with experimental data obtained by the mirror method @xcite . in no case\nthe kinetic energy of the ions is sufficient to overcome the barriers present , but at high temperatures the ions in the polarization cloud can respond more rapidly by lowering the barriers in a dynamical way .\nindeed , the active presence of the excess electron has an important backreaction effect onto the neighboring ions .\nwhen the excess electron is trapped , it attracts the positive al@xmath4 ions and repels the negative o@xmath9 ions causing a lattice distortion and a dielectric polarization . despite the limited size of our system\nwe have been able to determine the main features and magnitude of the ionic dispacements .\nthe six nearest oxygen ions moved significantly outwards , away from their equilibrium positions , typically between 0.17 and 0.27 .\nthe displacement pattern of the al@xmath4 ions is more complicated .\nthe two first neighbors are very stable , with an average vibration of 0.025 .\nthis is because these two ions are strongly attracted towards the tapped electron , and hence they behave as though their mass were renormalized by the interaction .\nthe next two al@xmath4 neighbors are also largely attracted towards the trap , because the outwards motion of the o@xmath9 ions leaves enough place for them to move in .\nthe average fluctuation of the al@xmath4 ions is about @xmath12 .\nthe outer al@xmath4 ions do not experience any significant force , as a consequence of the short range of the e@xmath11al@xmath4 interaction . according to this pattern of distortions\n, we estimate the size of the polaron in about 4.8 . we have computed the potential energy surface for the charged lattice at @xmath13 , and we show it in fig .\n7 compared to the uncharged potential .\nthe former was calculated with the ions in their displaced positions after the introduction of the excess electron , but only the potential felt by the test charge was computed , in order to compare with the uncharged lattice .\nthe bottom of the potential well turns out to be 4.7 ev lower in energy in the case of the deformed ( charged ) lattice .\ntherefore , the effective presence of the electron further stabilizes the trap by increasing the depth of the potential well .\nthese results are consistent with experiments showing that the energy necessary to detrap charging electrons is larger than the energy gained upon trapping them @xcite .\nthe total energy of the lattice increases about 4 - 5 ev upon electron implantation , so that this number represents the energy of formation of the polaron in .\nthis value is consistent with the estimation done using the space charge model @xcite .\npart of the energy is stored as mechanical energy and , when dielectric breakdown occurs , it is supposed to be released in the form of a shock thermal wave that eventually leads to fracture .\nin this paper we have investigated the phenomenon of electron trapping in the corundum ( ) lattice . our simulation revealed that electrons can only be trapped at temperatures lower than @xmath14 .\nthis is in good agreement with experimental results obtained using the mirror method .\ntrapping turns out to be possible only at lattice sites where the potential surface of the uncharged lattice exhibits a minimum .\nthis is in agreement with the space charge model , as these sites appear to be polarizability defects due to crystallographic dissymetry .\nalthough our simulations reproduce the main features of electron trapping at a semiquantitative level , further improvement is needed in two directions : ( a ) modelling of the short - range interaction of the electron with the ionic species , and ( b ) quantum treatment of the electronic dynamics .\nwork is in progress along these two lines .\nthe authors are grateful to e. smargiassi for many useful suggestions , in particular on the establishment of the shell model .\n: values of the parameters used for the short - range interactions ( * values from catlow et al .\n@xcite ) .\n99 g. blaise and c. le gressus , _ charge trapping - detrapping process and related breakdown phenomena _ ,\ndielectric characterization , ed .\nlatham , plenum .\ng. blaise , _\nle vide , les couches minces _ ,\nsupplment au n. 269 , janvier - fvrier 1992 . n. f. mott , trans .\nfaraday soc .\n* 34 * , 500 ( 1938 ) .\nj. bigarre , s. fayeulle and d. treheux , 1994 , ceidp , annual report 1994 , p304 . b. vallayer , thse , e.c.l . , n. 95 - 14 , 1995 .\nb. vallayer , 1994 , ceidp , annual report 1994 . y. a. nga and c. k. ong , phys .\nb * 46 * , 10547 ( 1992 ) . c. r. a. catlow and a. m. stoneham , j. phys.c . :\nsolid state phys .\n* 16 * , 4321 ( 1983 )\n. b. g. dick and a. w. overhauser , phys .\nrev . * 112 * , 90 ( 1958 ) .\nd. k. remler and p. a. madden , mol . phys . * 70 * , 921 ( 1990 ) .\nr. car and m. parrinello , phys .\nlett . * 55 * , 2471 ( 1985 ) . j .-\nhansen in _ molecular dynamics simulation of statistical mechanical systems _\ng. ciccotti and w. g. hoover ( north holland , amsterdam , 1986 ) . m. m. allen , d. j. tildesley , _ computer simulation of liquids _\n( oxford , uk , 1987 ) . a. m. stoneham and j. h. harding , ann\nphys . chem . *\n379 * , 53 ( 1986 ) . c. r. a. catlow , r. james , w. c. mackrodt , and r. f. stewart , phys .\nb * 25 * , 1006 ( 1982 ) . g. v. samsonov , _ the oxide handbook _ ( ifi / plenum , new york , 1973 ) .\nesnouf , private communication .\ns. geshwind and j. p. remeika , phys .\nrev , * 122 * , 757 ( 1961 ) .", "role": "user" }, { "content": "energy storage and release in dielectric materials can be described on the basis of the charge trapping mechanism . \n most phenomenological aspects have been recently rationalized in terms of the space charge model @xcite . \n dynamical aspects are studied here by performing molecular dynamics simulations . \n we show that an excess electron introduced into the sapphire lattice ( ) can be trapped only at a limited number of sites . \n the energy gained by allowing the electron to localize in these sites is of the order of 4 - 5 ev , in good agreement with the results of the space charge model . \n displacements of the neighboring ions due to the implanted charge are shown to be localized in a small region of about 5 . \n detrapping is observed at 250 @xmath0 . \n the ionic displacements turn out to play an important role in modifying the potential landscape by lowering , in a dynamical way , the barriers that cause localization at low temperature .", "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\nToday it remains unclear why children seem to be less likely to get infected by COVID-19 or why they appear to be less symptomatic after infections. All individuals, especially children, are exposed to various viruses including human coronavirus (CoVs) that can generally lead to respiratory infections. We hypothesize that recurrent CoVs exposure may induce an effective antiviral B and T-cell-mediated adaptive immune response, which could also be protective against COVID-19. Based on the high-homology between the Spike protein epitopes of taxonomically-related coronaviruses, we theorize that past/recurrent contact with CoVs might shield children also against the circulating COVID-19 through a possible neutralizing antibody response previously CoVs-induced. This would open up possible lines of research for the development of live-attenuated virus vaccines from CoVs. Future research is desirable to confirm or disprove such hypothesis.", "role": "user" }, { "content": "[\"Treatment\", \"Mechanism\"]", "role": "assistant" } ]

[ { "content": "Extract drug combinations from this sentence and classify each combination into one of these categories:\n- POS: Positive interaction between drugs\n- NEG: Negative interaction between drugs\n- COMB: Drugs used together with unknown interaction type\n\nOutput only a JSON array where each entry is [drug_1, drug_2, ..., drug_n, category].\n\nparagraph: Hypoxia-induced resistance to anticancer drugs is associated with decreased senescence and requires hypoxia-inducible factor-1 activity. Hypoxia in solid tumors is associated with the development of chemoresistance. Although many studies have focused on the effect of hypoxia on drug-induced apoptosis, the effect of nonapoptotic pathways on hypoxia-induced drug resistance has not been previously investigated. Here, we determined the effects of hypoxia on multiple forms of drug-induced death in human MDA-MB-231 breast carcinoma cells. Clonogenic assays showed that preexposure to hypoxia leads to resistance to various classes of chemotherapeutic agents , including anthracyclines ( daunorubicin and doxorubicin ) , epipodophyllotoxins ( etoposide ) , and anthracenediones ( mitoxantrone ) . Results revealed a high degree of heterogeneity in nuclear and cytoplasmic alterations in response to acute drug exposure; however, the majority of exposed cells displayed morphologic and biochemical changes consistent with drug-induced senescence. Hypoxia decreased only the proportion of cells in the senescent population, whereas the small proportion of cells exhibiting features of apoptosis or mitotic catastrophe were unaffected. Similar results were obtained with human HCT116 colon carcinoma cells, indicating that the protective effect of hypoxia on drug-induced senescence is not unique to MDA-MB-231 cells. Treatment of MDA-MB-231 cells with small interfering RNA targeting the alpha-subunit of hypoxia-inducible factor-1 (HIF-1), a key regulator of cellular adaptations to hypoxia, prevented hypoxia-induced resistance. HIF-1alpha small interfering RNA also selectively abolished the hypoxia-induced changes in the senescent population, indicating that the increased survival was due to protection against drug-induced senescence. These results support a requirement for HIF-1 in the adaptations leading to drug resistance and reveal that decreased drug-induced senescence is also an important contributor to the development of hypoxia-induced resistance.\n\nsentence: Clonogenic assays showed that preexposure to hypoxia leads to resistance to various classes of chemotherapeutic agents , including anthracyclines ( daunorubicin and doxorubicin ) , epipodophyllotoxins ( etoposide ) , and anthracenediones ( mitoxantrone ) .", "role": "user" }, { "content": "[]", "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\nDNA-binding studies of the Epstein-Barr virus nuclear antigen 2 (EBNA-2): evidence for complex formation by latent membrane protein gene promoter-binding proteins in EBNA-2-positive cell lines. The Epstein-Barr virus (EBV) nuclear antigen 2 (EBNA-2) protein is essential for the immortalization of human primary B cells by EBV. EBNA-2 trans-activates cellular and viral genes like CD23, c-fgr, latent membrane protein 1 (LMP1) and terminal protein 1 (TP1). Trans-activation of the TP1 promoter and of the BamHI C promoter has already been investigated in detail and appears to be mediated via protein-protein interactions and not by direct binding of EBNA-2 type A (of EBV type 1) to the DNA. EBNA-2 is able to trans-activate the expression of the LMP gene in several cell lines. Various reports have delineated the cis-acting elements of the LMP promoter through which EBNA-2 mediates trans-activation. To determine whether EBNA-2 also trans-activates the LMP promoter by protein-protein interactions, we performed a series of gel retardation assays and competition experiments with LMP promoter fragments of different sizes. We determined that the protein-binding region on the LMP promoter was within a 42 bp fragment encompassing nucleotides-135 to-176 relative to the LMP transcriptional start site. None of the DNA fragments investigated indicated interaction of EBNA-2 with the DNA via protein-protein interactions. No significant differences between EBNA-2-positive and EBNA-2-negative nuclear extracts could be seen in the gel retardation assay under conditions that clearly showed binding of EBNA-2A to the TP1 promoter. However, analysis of sucrose gradient fractions in the gel retardation assay provided evidence that the LMP promoter-binding proteins form a complex of higher M (r) in EBNA-2-positive cell extracts. These complexes were destroyed by detergent. We deduce from these results that EBNA-2-positive cells might indeed contain specific complexes bound to the LMP promoter which are, however, too labile to be detected in a standard gel retardation assay.", "role": "user" }, { "content": "{\"CellLine\": [\"EBNA - 2 - positive cell lines\", \"EBNA - 2 - positive cells\"], \"CellType\": [\"human primary B cells\", \"EBNA - 2 - positive cell\"], \"DNA\": [\"42 bp fragment\", \"cellular and viral genes\", \"LMP gene\", \"LMP transcriptional start site\", \"TP1 promoter\", \"BamHI C promoter\", \"cis - acting elements\", \"CD23\", \"protein - binding region\", \"c - fgr\", \"nucleotides - 135 to - 176\", \"LMP promoter\", \"LMP promoter fragments\"], \"Protein\": [\"specific complexes\", \"the LMP promoter\", \"the LMP promoter - binding proteins\", \"LMP1\", \"latent membrane protein gene promoter - binding proteins\", \"EBNA - 2\", \"TP1\", \"Epstein - Barr virus nuclear antigen 2\", \"EBNA - 2 type A\", \"terminal protein 1\", \"EBNA - 2A\", \"LMP promoter - binding proteins\", \"Epstein - Barr virus (EBV) nuclear antigen 2\", \"latent membrane protein 1\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Read this passage from a research paper and answer the question.\n\nContext: Much of the recent research on deep convolutional neural networks (CNNs) has focused on increasing accuracy on computer vision datasets.For a given accuracy level, there typically exist multiple CNN architectures that achieve that accuracy level.Given equivalent accuracy, a CNN architecture with fewer parameters has several advantages:\\bulletMore efficient distributed training.Communication among servers is the limiting factor to the scalability of distributed CNN training.For distributed data-parallel training, communication overhead is directly proportional to the number of parameters in the model Iandola et al. (2016).In short, small models train faster due to requiring less communication.\\bulletLess overhead when exporting new models to clients. For autonomous driving, companies such as Tesla periodically copy new models from their servers to customers’ cars. This practice is often referred to as an over-the-air update. Consumer Reports has found that the safety of Tesla’s Autopilot semi-autonomous driving functionality has incrementally improved with recent over-the-air updates Consumer Reports (2016). However, over-the-air updates of today’s typical CNN/DNN models can require large data transfers. With AlexNet, this would require 240MB of communication from the server to the car. Smaller models require less communication, making frequent updates more feasible.\\bulletFeasible FPGA and embedded deployment. FPGAs often have less than 10MB111For example, the Xilinx Vertex-7 FPGA has a maximum of 8.5 MBytes (i.e. 68 Mbits) of on-chip memory and does not provide off-chip memory. of on-chip memory and no off-chip memory or storage. For inference, a sufficiently small model could be stored directly on the FPGA instead of being bottlenecked by memory bandwidth Qiu et al. (2016), while video frames stream through the FPGA in real time.Further, when deploying CNNs on Application-Specific Integrated Circuits (ASICs), a sufficiently small model could be stored directly on-chip, and smaller models may enable the ASIC to fit on a smaller die.\n\nQuestion: What is an example of an autonomous car that uses CNN?", "role": "user" }, { "content": "Tesla ( Model S for example ) autopilot system uses a convolutional neural network to detect objects on its way.", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nThe COVID-19 pandemic is taking a colossal toll in human suffering and lives. A significant amount of new scientific research and data sharing is underway due to the pandemic which is still rapidly spreading. There is now a growing amount of coronavirus related datasets as well as published papers that must be leveraged along with artificial intelligence (AI) to fight this pandemic by driving news approaches to drug discovery, vaccine development, and public awareness. AI can be used to mine this avalanche of new data and papers to extract new insights by cross-referencing papers and searching for patterns that AI algorithms could help discover new possible treatments or help in vaccine development. Drug discovery is not a trivial task and AI technologies like deep learning can help accelerate this process by helping predict which existing drugs, or brand-new drug-like molecules could treat COVID-19. AI techniques can also help disseminate vital information across the globe and reduce the spread of false information about COVID-19. The positive power and potential of AI must be harnessed in the fight to slow the spread of COVID-19 in order to save lives and limit the economic havoc due to this horrific disease.", "role": "user" }, { "content": "[\"Treatment\"]", "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 phase 3 study of deferasirox (ICL670), a once-daily oral iron chelator, in patients with beta-thalassemia.\nAbstract 1:\nDeferasirox (ICL670) is a once-daily oral iron chelator developed for the treatment of chronic iron overload from blood transfusions. A comparative phase 3 trial was conducted to demonstrate the efficacy of deferasirox in regularly transfused patients with beta-thalassemia aged 2 years or older. Patients were randomized and received treatment with deferasirox (n = 296) or deferoxamine (n = 290), with dosing of each according to baseline liver iron concentration (LIC). The primary endpoint was maintenance or reduction of LIC; secondary endpoints included safety and tolerability, change in serum ferritin level, and net body iron balance. In both arms, patients with LIC values of 7 mg Fe/g dry weight (dw) or higher had significant and similar dose-dependent reductions in LIC and serum ferritin, and effects on net body iron balance. However, the primary endpoint was not met in the overall population, possibly due to the fact that proportionally lower doses of deferasirox relative to deferoxamine were administered to patients with LIC values less than 7 mg Fe/g dw. The most common adverse events included rash, gastrointestinal disturbances, and mild nonprogressive increases in serum creatinine. No agranulocytosis, arthropathy, or growth failure was associated with deferasirox administration. Deferasirox is a promising once-daily oral therapy for the treatment of transfusional iron overload.\n\n\nTitle 2:\nSafety, tolerability, and pharmacokinetics of ICL670, a new orally active iron-chelating agent in patients with transfusion-dependent iron overload due to beta-thalassemia.\nAbstract 2:\nICL670 is an orally active representative of a new class of tridentate iron chelator developed for the treatment of blood transfusion-dependent iron overload in chronic anemias. In this randomized, double-blind study, patients with transfusion-dependent beta-thalassemia received single oral doses of ICL670 ranging from 2.5 to 80 mg/kg to investigate its safety, tolerability, and pharmacokinetics and to obtain preliminary information on pharmacodynamic effects. ICL670 was well tolerated, and no safety problems occurred up to 80 mg/kg. A plasma half-life of 11 to 19 hours was found for ICL670, supporting once-daily oral administration. AUC0-24 h and Cmax of ICL670 increased nearly proportionally with the dose. The urinary excretion of ICL670 and its iron complex was less than 0.1% of the dose, and this was in accordance with the expected predominant iron fecal excretion induced by ICL670 (based on preclinical experiments). Notwithstanding, a positive trend toward increased amounts of urinary excreted iron was observed when the AUC0-24 h of ICL670 and the iron complex exceeded specific threshold values at the 40- and 80-mg/kg dose levels.\n\n\nTitle 3:\nEffectiveness and safety of ICL670 in iron-loaded patients with thalassaemia: a randomised, double-blind, placebo-controlled, dose-escalation trial.\nAbstract 3:\nTransfusional iron overload is a potentially fatal complication of the treatment of thalassaemia. We aimed to investigate short-term efficacy, pharmacokinetic/pharma- codynamic (PK/PD) relations, and safety of ICL670, a novel, tridentate, orally active iron chelator.\n We enrolled 24 patients and divided them into three cohorts consisting of a minimum of seven individuals. Patients were admitted to a metabolic unit and consumed a diet with a defined content of iron. Two patients in each cohort were randomly allocated placebo. Five or more patients received one daily dose of ICL670 at 10, 20, or 40 mg x kg(-1) x day(-1), from day 1 to 12. Net iron excretion (NIE) was measured between days 1 and 12. Primary objectives included assessment of safety and tolerability (measured by adverse events and clinical laboratory monitoring), pharmacokinetics (measured as drug and drug-iron complex), and cumulative net iron excretion (measured by faecal and urine output minus food input). Analysis was for efficacy.\n ICL670 was absorbed promptly and was detectable in the blood for 24 h. Exposure (area under the curve of plasma concentration) to ICL670 at pharmacokinetic steady state was proportional to dose. All three doses resulted in positive NIE. The NIE achieved at 20mg x kg(-1) day(-1) would prevent net iron accumulation in most patients transfused with 12-15 mL packed red-blood-cells kg(-1) month(-1), equivalent to 0.3-0.5 mg iron kg(-1) x day(-1). A linear relation (PK/PD) was recorded between exposure to ICL670 and total iron excretion, by contrast with placebo (r2=0.54, p<0.0001). Skin rashes were noted in four patients treated at 20 and 40 mg x kg(-1) x day(-1), and one patient also developed grade 2 transaminitis.\n ICL670 given once daily at 20 mg/kg seems to be an effective orally active iron chelator and is reasonably well tolerated. Long-term studies are now necessary to establish the practical contribution of this drug.\n\n\nTitle 4:\nRandomized phase II trial of deferasirox (Exjade, ICL670), a once-daily, orally-administered iron chelator, in comparison to deferoxamine in thalassemia patients with transfusional iron overload.\nAbstract 4:\nIron accumulation is an inevitable consequence of chronic blood transfusions and results in serious complications in the absence of chelation treatment to remove excess iron. Deferoxamine (Desferal, DFO) reduces morbidity and mortality although the administration schedule of slow, parenteral infusions several days each week limits compliance and negatively affects long-term outcome. Deferasirox (Exjade, ICL670) is an oral chelator with high iron-binding potency and selectivity. In a phase II study, the tolerability and efficacy of deferasirox were compared with those of DFO in 71 adults with transfusional hemosiderosis.\n Patients were randomized to receive once-daily deferasirox (10 or 20 mg/kg; n=24 in both groups) or DFO (40 mg/kg, 5 days/week; n=23) for 48 weeks. Results. Both treatments were well tolerated and no patient discontinued deferasirox due to drug-related adverse events. The reported frequency of transient, mild to moderate gastrointestinal disturbances was higher in the deferasirox group than in the DFO group, but these disturbances settled spontaneously without dose interruption in all patients. Decreases in liver iron concentration (LIC) were comparable in the deferasirox 20 mg/kg/day and DFO groups; baseline values of 8.5 and 7.9 mg Fe/g dw fell to 6.6 and 5.9 mg Fe/g dw, respectively, by week 48. Deferasirox showed a plasma elimination half-life of 8-16 hours, supporting its once-daily administration.\n Deferasirox at daily doses of 10 or 20 mg/kg was well tolerated and, at 20 mg/kg, showed similar efficacy to DFO 40 mg/kg in terms of decreases in LIC.", "role": "user" }, { "content": "Deferasirox offers an important alternative line of treatment for people with thalassaemia and secondary iron overload. Based on the available data, deferasirox does not seem to be superior to deferoxamine at the usually recommended ratio of 1 mg of deferasirox to 2 mg of deferoxamine. However, similar efficacy seems to be achievable depending on the dose and ratio of deferasirox compared to deferoxamine. Whether this will result in similar efficacy in the long run and will translate to similar benefits as has been shown for deferoxamine, needs to be confirmed. Data on safety, particularly on rare toxicities and long-term safety, are still limited.\nTherefore, we think that deferasirox should be offered as an alternative to all patients with thalassaemia who either show intolerance to deferoxamine or poor compliance with deferoxamine. In our opinion, data are still too limited to support the general recommendation of deferasirox as first-line treatment instead of deferoxamine. If a strong preference for deferasirox is expressed, it could be offered as first-line option to individual patients after a detailed discussion of the potential benefits and risks.", "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\nPersonal hygiene is critical for preventing the spread of infection. One important component of personal hygiene is handwashing. This review summarizes research on behavioral strategies to address handwashing in children, offers areas for additional research, and suggests a treatment package to teach handwashing to young children.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nResin acid conversion with CYP105A1: an enzyme with potential for the production of pharmaceutically relevant diterpenoids. Cytochrome P450s are very versatile enzymes with great potential for biotechnological applications because of their ability to oxidize unactivated CH bonds. CYP105A1 from Streptomyces griseolus was first described as a herbicide-inducible sulfonylurea hydroxylase, but it is also able to convert other substrates such as vitamin D(3) . To extend the substrate pool of this interesting enzyme further, we screened a small diterpenoid compound library and were able to show the conversion of several resin acids. Binding of abietic acid, dehydroabietic acid, and isopimaric acid to the active site was assayed, and V(max) and K(m) values were calculated. The products were analyzed by NMR spectroscopy and identified as 15-hydroxyabietic acid, 15-hydroxydehydroabietic acid, and 15,16-epoxyisopimaric acid. As the observed products are difficult to obtain by chemical synthesis, CYP105A1 has proved to be a promising candidate for biotechnological applications that combine bioconversion and chemical synthesis to obtain functionalized resin acids.", "role": "user" }, { "content": "{\"Chemical\": [\"resin acids\", \"diterpenoids\", \"15,16-epoxyisopimaric acid\", \"15-hydroxyabietic acid\", \"sulfonylurea\", \"dehydroabietic acid\", \"isopimaric acid\", \"15-hydroxydehydroabietic acid\", \"abietic acid\", \"vitamin D(3)\", \"C\\uf8ffH\", \"diterpenoid\", \"Resin acid\"]}", "role": "assistant" } ]

[ { "content": "Read this passage from a research paper and answer the question.\n\nContext: A second approach we use is the mixed word/character model.As in a word model, we keep a fixed-size word vocabulary.However, unlike in a conventional word model where OOV words are collapsedinto a single UNK symbol, we convert OOV words into the sequence of itsconstituent characters.Special prefixes are prepended to the characters, to 1) show the location ofthe characters in a word, and 2) to distinguish them from normal in-vocabularycharacters. There are threeprefixes: <B>,<M>, and <E>, indicating beginning of the word, middleof the word and end of the word, respectively. For example, let’s assume theword Miki is not in the vocabulary. It will be preprocessed into asequence of special tokens: <B>M <M>i <M>k <E>i. The process isdone on both the source and the target sentences. During decoding, theoutput may also contain sequences of special tokens. With theprefixes, it is trivial to reverse the tokenization to the original words aspart of a post-processing step. The mixed word-character model is similar to the word model, except theout-of-vocabulary (OOV) words are converted into sequences ofcharacters with special delimiters around them as described in section4.2 in more detail. Inour experiments, the vocabulary size for the mixed word-charactermodel is 32K. For the pure character model, we simply split all wordsinto constituent characters, resulting typically in a few hundred basiccharacters (including special symbols appearing in the data). For thewordpiece models, we train 3 different models with vocabulary sizes of8K, 16K, and 32K. The pure character model (char input, char output) works surprisinglywell on this task, not much worse than the best wordpiece models in BLEUscore. However, these models are rather slow to train and slow to use as thesequences are much longer.\n\nQuestion: How is “character”-delimited models different from “word”-delimited models?", "role": "user" }, { "content": "character-delimited models takes characters as input and outputs characters, the words spitted into constituent characters, resulting typically in a few hundred basic characters including special characters appeared in the data. While in word-delimited models OOv words are collapsed into a single UNK symbols.", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\npancreatic endocrine tumours are rare tumours , and may produce a variety of hormones including insulin , gastrin , glucagon , pancreatic polypeptide , vasoactive intestinal peptide and somatostatin .\nthe most common pancreatic endocrine tumours are insulinomas and gastrinomas , which are respectively found within the pancreas and the gastrinoma triangle formed by the junction of the cystic and common bile ducts superiorly , the junction of the second and third portions of the duodenum inferiorly , and the junction of the neck and body of the pancreas medially\n. the tumors may be functional or non - functional , and may be benign or malignant .\nduodenopancreatic neuroendocrine tumors are rare , although current epidemiological studies worldwide suggest an incidence rate increase .\nit was assessed the pathological incidence of duodenopancreatic neuroendocrine tumors for 18 years in the netherlands .\nstandardized excerpts from pathological reports of all patients who had a diagnosis of duodenopancreatic neuroendocrine tumors from 1991 until 2009 were collected from the pathologisch anatomisch landelijk geautomatiseerd archief and reviewed .\nthis nationwide network and registry of histopathological and cytopathological data covers 100 percent of the pathological reports in the netherlands .\nit was identified 905 patients with pancreatic ( n=692 ) or duodenal ( n=213 ) neuroendocrine tumors .\nthe mean annual incidence rates per 1,000,000 persons over 1991 to 2009 were 2.54 for pancreatic and 0.81 for duodenal neuroendocrine tumors .\nthe endocrine pancreas is central in the physiopathology of diabetes mellitus . nutrients and hormones control endocrine pancreatic function and the secretion of insulin and other pancreatic islet hormones .\nalthough the pancreas is not usually considered as a target of steroids , increasing evidence indicates that sex steroid hormones modify pancreatic islet function .\nthe biological effects of steroid hormones are transduced by both , classical and non - classical steroid receptors that in turn produce slow genomic and rapid non - genomic responses . in a review ,\nit was focused on the effects of sex steroid hormones on endocrine pancreatic function , with special emphasis in animal studies .\nto determine if serotonin production by pancreatic endocrine neoplasms is associated with the pancreatic duct stenosis seen in patients with stenosis that is out of proportion to the size of the tumors seen on computed tomographic images an institutional approval was obtained for a study .\ntissue microarrays constructed from 47 pancreatic endocrine neoplasms from the institutional tissue bank served as controls .\nonly one of the six study patients had a large dominant tumor ( 4 cm in the pancreatic head ) .\nfour of the six pancreatic endocrine neoplasms with associated pancreatic duct stricture had prominent stromal fibrosis .\nserotonin immunoreactivity was present in five ( 83 % ) patients , and this labeling was strong and diffuse in the four patients with prominent fibrosis .\nby contrast , stromal fibrosis was minimal in the nonimmunoreactive case . only three ( 6 % ) of the 47 control pancreatic endocrine neoplasms were immunoreactive for serotonin .\nit was concluded that these data suggest that serotonin produced by pancreatic endocrine neoplasms may be associated with local fibrosis and stenosis of the pancreatic duct .\nclinicians should be aware that small pancreatic endocrine neoplasms can produce pancreatic duct stenosis resulting in ductal dilatation and/or upstream pancreatic atrophy out of proportion to the size of the tumor .\nit was presented an update on molecular and clinical genetics of solid tumors associated with the various multiple endocrine neoplasias ( men ) syndromes .\nmen type 1 ( men1 ) describes the association of pituitary , parathyroid , and pancreatic islet cell tumors with a variety of many other lesions .\nmen type 2 ( men2 ) conditions represent at least four different syndromes that associate pheochromocytoma with medullary thyroid carcinoma , hyperparathyroidism , and a number of other manifestations .\nother pheochromocytoma - associated syndromes include von hippel - lindau disease ; neurofibromatosis 1 ; the recently defined paraganglioma syndromes type 1 , 3 , and 4 ; carney - stratakis syndrome ; and the carney triad .\ncarney - stratakis syndrome is characterized by the association of paragangliomas and familial gastrointestinal stromal tumors . in the carney triad\n, patients can manifest gastrointestinal stromal tumors , lung chondroma , paraganglioma , adrenal adenoma and pheochromocytoma , esophageal leiomyoma , and other conditions .\nthe carney complex is yet another form of men that is characterized by skin tumors and pigmented lesions , myxomas , schwannomas , and various endocrine neoplasias . to identify gene expression alterations associated with insulinoma formation and progression in 2 mouse models of multiple endocrine neoplasia type 1 mice\nwere killed at 12 or 16 months , and pancreatic islets were isolated by enzymatic and physical disruption .\nislets were separated by size representing control , normal , hyperplastic , and adenomous islets .\nrna was isolated from these islets and profiled on sentrix mouse-6 expression version 1 beadchips .\none hundred and one genes that were significantly altered in hyperplastic islets and insulinomas compared with normal islets were identified . of these ,\n64 gene elements showed reduced messenger rna levels and 37 gene elements had increased gene expression compared with control islets .\naltered expression of 3 genes , namely , gata6 , tspan8 , and s100a8 , was confirmed by quantitative reverse transcription - polymerase chain reaction , and aberrant levels of tspan8 and lmo2 protein measured by western blot correlated with the changes in messenger rna levels .\nit was concluded that these results suggest that alterations in gene expression of gata6 , tspan8 , s100a8 , and lmo2 may act via novel pathways that play functionally important roles in men1-associated tumor progression .\ninsulinomas are rare tumors with an estimated incidence of one per 250,000 person - years .\nmost insulinomas are benign with less than 10 percent demonstrating malignant behavior , the vast majority of which occur in adults .\na systemic review of the literature revealed only nine cases of malignant insulinomas occurring in children .\nherein , it was presented a case of metastatic malignant insulinoma in a 12-year - old child .\nthe occurrence of this diagnosis in a child , its unusual pattern of metastases and the challenging management of severe hypoglycemia make this case worth reporting .\ntreatment of hypoglycemia in such patients is difficult and frequently fails to respond to numerous therapeutic agents , requiring continuous dextrose infusion .\nthe authors present the experience with yttirum-90 radioembolization in a patient with metastatic malignant insulinoma who failed to respond to distal pancreatectomy , systemic chemotherapy with capecitabine and everolimus and medical treatment with somatostatin analogues , diazoxide and corticosteroids .\ntreatment with repeated y-90 radioembolization resulted in rapid resolution of hypoglycemic events , allowing discontinuation of dextrose infusion and hospital discharge .\nhowever , the effect of y-90 administration seems to be transient and without evidence of tumor shrinkage in imaging studies .\noctreotide long acting repeatable ( lar ) is commonly used to control the symptoms of patients with functional neuroendocrine tumors .\nunfortunately , most patients escape control over time and require higher lar doses or more frequent rescue therapy to remain asymptomatic .\nprevious work has shown that body weight and monthly lar dose will significantly affect circulating plasma octreotide levels in patients undergoing therapy . to determine\nif other parameters change circulating plasma octreotide levels , it was prospectively studied 82 patients undergoing long - term lar therapy .\nmultivariate analysis demonstrated that the plasma octreotide levels decrease by approximately 3.4 percent for each unit of body mass index ( bmi ) increase , adjusting for sex and monthly lar dose .\nplasma octreotide levels for females were approximately 48 percent higher than those for males , adjusting for bmi and monthly lar dose .\nmales are estimated to require 14 mg higher monthly lar doses than females with the same bmi .", "role": "user" }, { "content": "pancreatic endocrine tumours are rare tumours , and arise from the types of pancreatic cells that produce hormones . \n these tumours may or may not secrete hormones themselves and may or may not be cancerous ( malignant ) . \n functioning tumours secrete a particular hormones which may cause various syndromes . \n the present article reviews the latest reports on the pancreatic endocrine tumours", "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 whole-to-part network and a part-to-whole network for the\n\nKeywords: image classification\n\nDataset descriptions:\nLocalized Narratives: We propose Localized Narratives, a new form of multimodal image annotations connecting vision and language. We ask annotators to describe an image with their voice while simultaneously hovering their mouse over the region they are describing.\nUMDFaces: UMDFaces is a face dataset divided into two parts: Still Images - 367,888 face annotations for 8,277 subjects. Video Frames - Over 3.7 million annotated video frames from over 22,000 videos of 3100 subjects.\nUNITOPATHO: Histopathological characterization of colorectal polyps allows to tailor patients' management and follow up with the ultimate aim of avoiding or promptly detecting an invasive carcinoma. Colorectal polyps characterization relies on the histological analysis of tissue samples to determine the polyps malignancy and dysplasia grade.\nMuPoTS-3D: MuPoTs-3D (Multi-person Pose estimation Test Set in 3D) is a dataset for pose estimation composed of more than 8,000 frames from 20 real-world scenes with up to three subjects. The poses are annotated with a 14-point skeleton model.\nBusiness Scene Dialogue: The Japanese-English business conversation corpus, namely Business Scene Dialogue corpus, was constructed in 3 steps: selecting business scenes, writing monolingual conversation scenarios according to the selected scenes, and translating the scenarios into the other language. Half of the monolingual scenarios were written in Japanese and the other half were written in English.\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.\n\nOptions: A: Localized Narratives B: UMDFaces C: UNITOPATHO D: MuPoTS-3D E: Business Scene Dialogue F: CIFAR-10 G: ImageNet", "role": "user" }, { "content": "[\"CIFAR-10\", \"ImageNet\"]", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: There are antiviral medicines that can be used to fight some viruses, such as those that cause flu. However, scientists haven't yet developed antiviral medicines that can kill the coronavirus that causes COVID-19.\n\nAbstract:\nIn December 2019, a new coronavirus, named SARS-CoV-2, has emerged from China causing pneumonia outbreaks first in the Wuhan region and have now spread worldwide because of its probable high transmission efficiency.\nDue to the lack of efficient and specific treatments and the need to contain the epidemic, drug repurposing appears to be the best tool to find therapeutic solution.\nChloroquine, remdesivir, lopinavir, ribavirin or ritonavir have shown efficacy to inhibit coronavirus in vitro.\nTeicoplanin, an antibiotic used to treat staphylococci infection, previously showed efficacy to inhibit the first stage of MERS-coronarivus viral cycle in human cells.\nThis activity is conserved on the SARS-Cov-2, thus placing teicoplanin as a potential treatment for patients with this virus.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Teicoplanin, an antibiotic used to treat staphylococci infection, previously showed efficacy to inhibit the first stage of MERS-coronarivus viral cycle in human cells.\", \"This activity is conserved on the SARS-Cov-2, thus placing teicoplanin as a potential treatment for patients with this virus.\"]}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Heme Uptake by Leishmania amazonensis Is Mediated by the Transmembrane Protein LHR1\nArticle:\nAbstract:\nTrypanosomatid protozoan parasites lack a functional heme biosynthetic pathway, so must acquire heme from the environment to survive. However, the molecular pathway responsible for heme acquisition by these organisms is unknown. Here we show that L. amazonensis LHR1, a homolog of the C. elegans plasma membrane heme transporter HRG-4, functions in heme transport. Tagged LHR1 localized to the plasma membrane and to endocytic compartments, in both L. amazonensis and mammalian cells. Heme deprivation in L. amazonensis increased LHR1 transcript levels, promoted uptake of the fluorescent heme analog ZnMP, and increased the total intracellular heme content of promastigotes. Conversely, deletion of one LHR1 allele reduced ZnMP uptake and the intracellular heme pool by approximately 50%, indicating that LHR1 is a major heme importer in L. amazonensis. Viable parasites with correct replacement of both LHR1 alleles could not be obtained despite extensive attempts, suggesting that this gene is essential for the survival of promastigotes. Notably, LHR1 expression allowed Saccharomyces cerevisiae to import heme from the environment, and rescued growth of a strain deficient in heme biosynthesis. Syntenic genes with high sequence identity to LHR1 are present in the genomes of several species of Leishmania and also Trypanosoma cruzi and Trypanosoma brucei, indicating that therapeutic agents targeting this transporter could be effective against a broad group of trypanosomatid parasites that cause serious human disease.\nIntroduction:\nLeishmania spp. are protozoan parasites from the Trypanosomatidae family. In mammalian hosts Leishmania is an obligate intracellular parasite, replicating as amastigotes inside acidic phagolysosomes of macrophages. Disease caused by infection with Leishmania spp. has a severe impact on human populations throughout much of the tropics. The clinical manifestations range from self-healing cutaneous lesions to lethal visceralizing disease. In many regions of the world treatment of leishmaniasis still relies on toxic drugs such as pentavalent antimony, which requires high doses and a lengthy course of treatment[1],[2]. Treatment failure is commonly observed with pentavalent antimony[3], and alternative drugs are costly and not widely available in endemic areas. This situation, combined with the recent increase in Leishmania infections in urban areas[4],[5],[6], highlights the urgent need for identification of essential parasite molecular pathways that can be targeted by new drugs of lower cost and toxicity. Leishmania species are uniquely dependent on the acquisition of heme from the environment. Heme is a metalloporphyrin that serves as a prosthetic group for proteins that perform critical cellular functions such as oxidative metabolism, oxygen storage and transport, and signal transduction[7]. Unlike mammalian hosts which can synthesize heme[8], Leishmania and other trypanosomatid protozoa lack several enzymes in the heme biosynthetic pathway[9],[10] and thus depend on an exogenous supply for survival. Leishmania amazonensis acquire exogenous he3me as extracellular promastigotes and also as intracellular amastigotes replicating within macrophages[11]. The existence of a specific transporter or receptor for heme on the Leishmania plasma membrane has been speculated, based on reports showing high affinity heme binding to the cell surface of L. amazonensis promastigotes[12] and L. infantum axenic amastigotes[13], and specific uptake of the porphyrin heme analog MgPPIX in L. donovani[14]. However, the nature of the membrane-associated molecule( s) responsible for heme uptake by Leishmania has remained unknown. In this study, we identify Leishmania Heme Response-1( LHR1), a L. amazonensis gene that shares homology with HRG-4, a C. elegans gene that encodes a plasma membrane heme importer[15]. We show that LHR1 transcript levels increase during heme deprivation, and that the LHR1 protein localizes to the plasma membrane and endocytic compartments, promotes heme uptake, and regulates the intracellular pool of heme in the parasites. Our results identify LHR1 as a strong candidate for the elusive transmembrane transporter responsible for heme acquisition from the environment by Leishmania.\nDiscussion:\nThe existence of an essential pathway for acquisition of exogenous heme in Leishmania and other trypanosomatid protozoa was proposed decades ago[9], when it became clear that these organisms lack several enzymes of the heme biosynthetic pathway[10]. However, the molecule( s) responsible for this critical activity remained unknown. In this work we identify LHR1, a Leishmania gene upregulated under heme-deficient conditions that encodes a membrane protein able to promote heme uptake from the environment. Transfection of Leishmania with LHR1 promotes uptake of a heme analog and increases the total intracellular heme concentration in the parasites. A L. amazonensis single-allele LHR1 knockout strain shows reduced uptake of a heme analog and has a significantly smaller intracellular heme pool. Viable parasites lacking both chromosomal copies of LHR1 could not be isolated even when carrying episomal LHR1, suggesting that LHR1 performs a critical function that depends on levels of expression not achieved with the tagged LHR1-3xFLAG. Importantly, LHR1 functionally complemented a yeast strain deficient in heme biosynthesis, in both growth and heme-dependent gene expression assays. These results strongly support a role of LHR1 as a transporter and not a receptor for heme, because yeast cells lack a efficient heme import machinery[22][16]. The efficiency of heme uptake from the environment may vary among Leishmania species, since Campos-Salinas et al. reported faster incorporation of Mg-PPIX by L. donovani promastigotes[14] than what we observed with L. amazonensis. Future studies may provide evidence for the intriguing possibility that LHR1 is differentially expressed in visceral strains of Leishmania, a property that might be associated with their increased virulence and capacity to proliferate in internal organs. LHR1 was identified based on its partial sequence identity and similarity to HRG-4, a gene encoding a plasma membrane heme transporter in the nematode C. elegans. HRG-4 was identified in a genetic screen designed to take advantage of the heme auxotrophy of C. elegans to identify heme-responsive genes[15]. LHR1 and CeHRG-4[15][16] have a similar molecular mass( ∼20 kDa), and four predicted transmembrane domains. One intriguing difference observed between CeHRG-4 and LHR1 is their subcellular localization. While HRG-4 is localized primarily on the plasma membrane, GFP-tagged LHR1 was detected on the plasma membrane and on endocytic compartments of L. amazonensis. In mammalian cells, GFP-LHR1 was also targeted to the plasma membrane and lysosomes, strongly suggesting that the large intracellular compartments containing LHR1 in L. amazonensis correspond to parasite lysosomal compartments. A morphometric and cytochemical study in L. amazonensis showed that during differentiation of promastigotes into amastigotes, the lysosomal vacuoles of promastigotes become a megasome, a very large compartments that can comprise up to ∼5% of the total cell volume[21]. This stage-specific lysosomal pattern is very consistent with the intracellular localization of GFP-LHR1 in our study. In addition to the plasma membrane, GFP-LHR1 was observed in several intracellular vesicles in promastigotes and in one very large compartment in intracellular amastigotes. The dual localization of LHR1 on the plasma membrane and on lysosomes raises interesting questions about the cellular site where heme is translocated into the cytosol. In yeast, LHR1 was targeted to the plasma membrane and promoted functional complementation of a strain incapable of synthesizing heme. However, earlier studies in Leishmania donovani showed that hemoglobin is internalized and degraded within parasite lysosomes[25], releasing heme that can then be transported into the cytosol to promote parasite growth. Interestingly, exogenously added hemin rescued the growth of a L. donovani strain defective in endocytic transport into lysosomes, indicating that heme translocation across the membrane can occur at both locations – the plasma membrane and the parasite lysosome[26]. The ATP-binding cassette protein LABCG5 was also recently proposed to mediate the salvage of heme released after lysosomal degradation of internalized hemoglobin in L. donovani. This intracellular process for heme salvage from degraded hemoglobin was proposed to be distinct from the pathway directly promoting porphyrin transport into the parasites[14]. Additional studies should determine if LHR1 can also mediate the uptake of heme released from hemoglobin inside parasite lysosomes, or if it's primary role is to transport heme from the environment directly across the plasma membrane. LHR1 null strains could not be generated despite extensive attempts, suggesting that this transporter is essential for the survival of promastigote forms of L. amazonensis. Episomal expression of LHR1 increased the intracellular heme concentration of wild type and single knockout L. amazonensis promastigotes, but was not sufficient to allow recovery of viable parasites lacking both copies of the gene. This finding is likely related to the fact that episomal LHR1 expression failed to restore the intracellular heme concentration to the same levels observed in wild type parasites. Dysregulated expression and incomplete functional complementation is a frequent observation after episomal or integrated gene expression in Leishmania[27],[28],[29],[30]. Incomplete restoration of heme acquisition in LHR1 double knockout parasites may result in the impairment of critical, essential roles played by hemoproteins in the parasites. For example, LFR1, the recently identified NADPH-dependent ferric iron reductase from L. amazonensis, contains a bis-heme motif that is essential for activity and required to allow iron acquisition through the ferrous iron transporter LIT1[30]. Thus, deleting both copies of LHR1 may severely affect not only heme uptake, but also the ferrous iron acquisition process. Searches of the TriTryp database indicate that highly syntenic, close homologs of L. amazonensis LHR1( LmxM. 24. 2230) are present in the additional Leishmania species L. major( LmjF24. 2230), L. braziliensis( LbrM. 24. 2310) and L. infantum( LinJ. 24. 2320), and in the Trypanosoma species T. brucei( Tb427. 08. 6010, Tb927. 8. 6010), T. brucei gambiense( Tbg972. 8. 6030), T. congolense( TclL3000. 8. 5780), and T. cruzi( Tc00. 1047053511071. 190). These trypanosomatid species are the causative agents of serious infectious diseases in humans( L. infantum, visceral leishmaniasis; T. brucei gambiense, sleeping sickness; T. cruzi, Chagas' disease) or in livestock( T. congolense and T. brucei brucei, cattle Nagana). Given that the human genome does not include putative orthologs of CeHRG-4 and LHR1[15], our study suggests that LHR1 may represent a promising target for the development of new therapeutic drugs with a potentially broad impact in human health and quality of life.", "role": "user" }, { "content": "The biological activity of many proteins and enzymes requires heme , a large organic ring containing one iron atom at the center . It has been known for several decades that trypanosomatid protozoa lack several enzymes in the heme biosynthetic pathway . Therefore , unlike mammalian cells that can synthesize heme , these unicellular organisms must acquire heme from the environment . However , the mechanism by which this critical co-factor is transported into trypanosomatid parasites was unknown . In this study we identified LHR1 , a trans-membrane protein from Leishmania amazonensis that mediates transport of extracellular heme into the parasites . Parasites partially deficient in LHR1 are impaired in heme import , and strains completely deficient do not survive . Genes highly similar to LHR1 are present in several species of trypanosomatid parasites that cause human disease , identifying this transporter as an important target for the development of anti-parasitic drugs .", "role": "assistant" } ]

[ { "content": "Read this passage from a research paper and answer the question.\n\nContext: On top of the CNN responses in each layer of the network we built a style representation\n\nQuestion: What does a \"Gram\" matrix mean?", "role": "user" }, { "content": "The stylistic representation of the image in a single layer is calculated as the Gram matrix of vectorized feature maps of that layer. The gram matrix is a matrix of the inner products of each vector. In other words, G_i_j = \\sum(V_i_k * V_j_k).", "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:\nHuman platelet response to three salicylate dosage forms . Acetylsalicylic acid ( ASA ) inhibition of platelet aggregation as evaluated by collagen-induced 14C-serotonin release , has been measured in 12 healthy male subjects . Each subject received a single oral dose ( 650 mg ) of enteric-coated ASA ( ecASA ) and compressed ASA tablets ( cASA ) , or ecASA and sodium salicylate ( 578 mg ) separated by a minimum of 5 weeks . The platelet response was related to plasma ASA and salicyclic acid determined by high-pressure liquid chromatography . Both ecASA and cASA inhibited 14C-serotonin release ; no significant difference was observed in the maximum effect between these two products ( p less than 0.05 ) . No relationship was found between the maximum observed plasma ASA level and the maximum effect . Further , no correlation was found between the maximum inhibition of 14C-serotonin release in vivo and the release predicted from in vitro experiments wherein the effect was measured after incubating plasma containing specified ASA concentrations .", "role": "user" }, { "content": "{\"Intervention\": [\"enteric-coated ASA\", \"Acetylsalicylic acid\", \"salicylate\", \"cASA\", \"ecASA\", \"compressed ASA tablets ( cASA )\", \"ASA\", \"sodium salicylate\"], \"Outcome\": [\"maximum effect\", \"plasma ASA level and the maximum effect\"], \"Participant\": [\"male\", \"12\"]}", "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:\nSafety , pharmacokinetics and pharmocodynamics of recombinant human porphobilinogen deaminase in healthy subjects and asymptomatic carriers of the acute intermittent porphyria gene who have increased porphyrin precursor excretion . BACKGROUND AND OBJECTIVE Acute intermittent porphyria is an autosomal dominant disorder caused by deficient activity of the third enzyme in the haem biosynthetic pathway , porphobilinogen deaminase . It is characterised by acute , potentially life-threatening neurological attacks that are precipitated by various drugs , reproductive hormones and other factors . During acute attacks , the porphyrin precursors 5-aminolevulinic acid and porphobilinogen accumulate and are excreted at high concentrations in the urine . Current treatment is based on glucose loading and parenteral haem replenishment , which reduce the accumulation of 5-aminolevulinic acid and porphobilinogen . Recently , a new form of treatment based on porphobilinogen deaminase enzyme replacement therapy has been shown to be effective in an acute intermittent porphyria mouse model which , during phenobarbital ( phenobarbitone ) induction of haem biosynthesis , mimics the biochemical pattern of acute porphyric attacks . The objective of the present study was to investigate the safety , pharmacokinetics and pharmacodynamics of recombinant human porphobilinogen deaminase ( P 9808 ) , administered to healthy subjects and asymptomatic porphobilinogen deaminase-deficient subjects with high concentrations of porphobilinogen , the substrate of porphobilinogen deaminase . STUDY DESIGN Forty individuals participated in this two-part study : 20 asymptomatic porphobilinogen deaminase-deficient subjects ( both male and female ) with > or =4 times the upper reference urinary porphobilinogen level , and 20 healthy male subjects . Four different doses of recombinant human porphobilinogen deaminase were studied ( 0.5 , 1 , 2 and 4 mg/kg bodyweight ) . Part A included 12 asymptomatic porphobilinogen deaminase-deficient subjects , and the enzyme was administered in an open-label , single-dose design . Part B included 20 asymptomatic porphobilinogen deaminase-deficient subjects and 20 healthy subjects . The same enzyme dosages were administered as divided doses every 12 hours for 4 consecutive days in a randomised , double-blinded , placebo-controlled design . The washout period between Parts A and B was 2 weeks . METHODS The concentrations of recombinant human porphobilinogen deaminase and titres of antibodies against recombinant human porphobilinogen deaminase were analysed by ELISA . Plasma porphobilinogen and 5-aminolevulinic acid concentrations were analysed using a novel liquid chromatography-tandem mass spectrometry method . Urinary porphobilinogen , 5-aminolevulinic acid and porphyrin concentrations , as well as plasma porphyrin concentrations , were analysed using standard methods . The pharmacodynamic effect of the enzyme was studied through changes in plasma porphobilinogen concentrations . RESULTS No serious adverse events were observed . Seven subjects ( four healthy men and three asymptomatic porphobilinogen deaminase-deficient subjects ) developed antibodies against recombinant human porphobilinogen deaminase but did not experience allergic manifestations . The mean elimination half-lives of the highest doses of recombinant human porphobilinogen deaminase ranged between 1.7 and 2.5 hours for both healthy men and asymptomatic porphobilinogen deaminase-deficient subjects . The area under the plasma concentration-time curve was proportional to the respective dose . In asymptomatic porphobilinogen deaminase-deficient subjects , plasma porphobilinogen concentrations decreased below measurable levels almost instantaneously after administration of any dose of the enzyme . The effect lasted for approximately 2 hours , after which the plasma porphobilinogen concentration slowly increased , reaching about 70 % of the initial values 12 hours after administration . There was no effect on plasma 5-aminolevulinic acid concentrations , and there was a transitory increment in porphyrin concentrations . The corresponding concentrations of metabolites in the urine reflected the pattern observed in the plasma . CONCLUSIONS The recombinant human porphobilinogen deaminase enzyme preparation was found to be safe to administer and effective for removal of the accumulated metabolite porphobilinogen from plasma and urine . The pharmacokinetic profile of recombinant human porphobilinogen deaminase showed dose proportionality , and the elimination half-life was about 2.0 hours for the two highest doses . Thus , clinical grounds were established for investigation of the therapeutic efficacy of the enzyme during periods of overt disease in patients with acute intermittent porphyria .", "role": "user" }, { "content": "{\"Intervention\": [\"porphobilinogen deaminase enzyme replacement therapy\", \"porphobilinogen deaminase\", \"recombinant human porphobilinogen deaminase enzyme preparation\", \"recombinant human porphobilinogen deaminase\", \"human porphobilinogen deaminase\"], \"Outcome\": [\"antibodies against recombinant human porphobilinogen deaminase\", \"mean elimination half-lives of the highest doses of recombinant human porphobilinogen deaminase\", \"area under the plasma concentration-time curve\", \"plasma porphobilinogen concentrations\", \"therapeutic efficacy\", \"concentrations of recombinant human porphobilinogen deaminase and titres of antibodies against recombinant human porphobilinogen deaminase\", \"allergic manifestations .\", \"Urinary porphobilinogen , 5-aminolevulinic acid and porphyrin concentrations\", \"plasma porphyrin concentrations\", \"Plasma porphobilinogen and 5-aminolevulinic acid concentrations\", \"porphyrin concentrations .\", \"plasma 5-aminolevulinic acid concentrations\", \"serious adverse events\", \"corresponding concentrations of metabolites in the urine\", \"5-aminolevulinic acid and porphobilinogen .\", \"plasma porphobilinogen concentration\", \"Safety , pharmacokinetics and pharmocodynamics\"], \"Participant\": [\"porphyrin\", \"with high concentrations of porphobilinogen\", \"Forty individuals participated in this two-part study : 20 asymptomatic porphobilinogen deaminase-deficient subjects ( both male and female ) with \\u003e or =4 times the upper reference urinary porphobilinogen level , and 20 healthy male subjects .\", \"porphobilinogen deaminase-deficient subjects\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nFluorophore-Quencher Pair For Monitoring Protein Motion\n\nPaper sections:\nIntroduction\n<p>Fluorescent DNA base analogs provide a useful means to study the interactions of nucleic acids with proteins. A recent perspective of fluorescent DNA bases concludes that these analogs are better able than tethered fluorophores to provide a direct response to physical changes because of their defined location and orientation within a DNA duplex [1]. Previous experiments with a tricyclic cytosine analog, 1,3-diaza-2-oxophenothiazine (tC, Figure 1a) [2], have shown that it does not disturb base stacking, does not distort the DNA backbone [3], forms hydrogen bonds with G in the complementary strand [4] and its fluorescence is relatively insensitive to interaction with neighboring bases [5]. Hence, tC is a non-perturbing fluorescent probe that becomes an integral part of the surrounding DNA structure. Here we explore the possibility of using tC as a reporter of large scale conformational changes of DNA or a DNA-protein complex, wherein the fluorescence of tC is modulated in a distance-dependent fashion by a remote quenching moiety, such as the stable nitroxide radical TEMPO. TEMPO has been used in combination with dyes to measure the distance dependence of fluorescence quenching. As an example, TAMRA and TEMPO were attached to a series of oligonucleotide duplexes with varying distances between them. Deniz et. al. showed that TEMPO could be used to measure dye-quencher distances in the 10-30Å range [6].</p><p>In this study, we use tC and TEMPO to establish a fluorophore-quencher system to detect conformational changes of a protein-DNA complex. We illustrate the method using the Klenow fragment (KF) of E. coli DNA polymerase I, a DNA-dependent DNA polymerase. In common with many other DNA polymerases, KF undergoes a significant conformational change during its nucleotide incorporation cycle. Thus, when a binary polymerase-DNA complex binds a cognate nucleotide substrate, it converts from an open inactive form to a closed active form. Crystal structures of the open and closed forms of ternary complexes of Klentaq, which is structurally similar to KF, show that the fingers domain is reoriented in the two forms, which significantly changes the positioning of the O-helix. In the closed form, the O-helix is significantly closer to the DNA than in the open complex [7].</p><p>To monitor this conformational change in solution, we incorporated tC within a duplex DNA substrate and attached TEMPO to an engineered cysteine residue at the end of the O-helix of KF. We measured the fluorescence intensity and quenching efficiency of tC in a binary DNA-KF complex and in ternary complexes containing either cognate or non-cognate dNTP substrates. The results establish the tC-TEMPO pair as a sensitive reporter of enzyme conformational changes specifically induced by a correct incoming nucleotide substrate.</p>\n\nMaterials and Methods\n<p>The fluorescent tC and an oligonucleotide containing tC were synthesized according to literature procedure [5]. The 11-mer primer tC strand, which was dideoxy terminated to prevent incorporation of nucleosides, was annealed with a 17-mer oligonucleotide to form a primer/template duplex (Figure 1b). A plasmid encoding the D424A/C907S/S751C KF mutant, a mutant lacking the 3'-5' exonuclease activity, with its single cysteine removed and another cysteine introduced at position 751 within the O-helix, was provided by Dr. Catherine Joyce (Yale University). DNA sequencing of the complete KF gene confirmed the presence of the desired mutations. Expression and purification of the KF mutant was carried out as described [8].</p><p>TEMPO-labeled KF was prepared by coupling TEMPO maleimide to the cysteine at position 751. After reduction with DTT, KF was reacted with a 15-fold molar excess of TEMPO maleimide in 50 mM phosphate buffer, pH 7.0 containing approximately 5% DMSO. The excess TEMPO maleimide was removed on a Sephadex-G25 gel filtration column and the KF-751 TEMPO was purified by FPLC. The unlabeled and labeled KF-751 were well resolved by FPLC allowing for the collection of pure TEMPO labeled material. The results of a primer extension assay using an extendable primer/template duplex assure that the KF selectivity for the incoming cognate nucleotide is not compromised by the presence of TEMPO at position 751 or tC adjacent to the primer 3' terminus (Figure 2).</p><p>Steady-state fluorescence spectra of tC complexes were measured by exciting the tC at 393 nm and scanning the emission spectrum under magic angle conditions. Primer:template (PT) duplexes were formed in aqueous buffer (50 mM Tris/HCl pH 7.5, 5 mM MgCl2, 1 mM DTT, 5% (v/v) glycerol) with a 20% excess of the template strand. Binary complexes contained 500 nM PT and 1 μM TEMPO-labeled KF. Ternary complexes contained, in addition, 250 μM of cognate (dATP) or non-cognate (dTTP) nucleotide.</p>\n\nResults and Discussion\n<p>The emission spectrum of a binary complex of PT (500 nM) with KF-751-TEMPO (1 μM), shown in Figure 3 (green), is the same as the PT duplex alone (red). This result indicates that in the binary complex, there is no significant quenching of the tC fluorescence by TEMPO. As predicted from the crystal structure of a binary complex of the homologous Klentaq polymerase with DNA, the O-helix is likely rotated away from the tC base, keeping TEMPO too far away to exhibit any significant quenching. This result is also important because it shows that the intrinsic fluorescence of tC is insensitive to the presence and/or interaction with DNA polymerase. This lack of environmental sensitivity is in marked contrast to the fluorescent nucleotide analog 2-aminopurine (2-AP), which has been used extensively as a fluorescent probe of nucleic acid structural changes [9]. Unlike 2-AP, any changes in tC fluorescence observed in the present system can be attributed to a change in the fluorophore-quencher distance rather than a change in local environment.</p><p>When a KF binary complex binds a cognate nucleotide, the O-helix in the fingers domain is expected to move from an \"open\" (green, Figure 4) to a \"closed\" (blue) conformation. Position 751 of KF is at the outside hinge of the O-helix. Based on crystal structures of Klentaq [9, 10], TEMPO will be brought significantly closer to the fluorescent tC in the closed complex as compared to the open complex and within the distance reporting range of TEMPO. Consistent with this expectation, we observe significant quenching of the tC emission when the cognate nucleotide (250 μM dATP) is added to the binary complex complex of PT with TEMPO-labeled KF (Fig. 3, purple). By comparison with the spectrum of PT alone, tC is quenched by approximately 30 % in the presence of the cognate nucleotide. Note that the primer terminus is blocked with a 2',3'-dideoxy modification to prevent actual incorporation of the nucleotide.</p><p>In contrast, when a non-cognate nucleotide (250 μM dTTP) is added to a binary complex of PT and TEMPO-751-KF, shown in Figure 3 (black), no significant tC quenching is observed. This result indicates that the O-helix does not rotate close enough to the tC to quench the fluorescence to any measurable extent under these conditions. Clearly, the structural rearrangement to form the closed ternary complex only occurs in the presence of the cognate nucleotide. Moreover, this conformational change is readily detected with the tC-TEMPO pair. While the distance dependence of fluorescence quenching has been established for the TAMRA-TEMPO pair [6], these results are not directly applicable to the tC fluorophore. Studies are now underway in our laboratories to correlate the degree of quenching of tC by TEMPO with the physical proximity of the fluorophore and quencher. The completion of those studies will establish a ruler to correlate tC quenching with distance changes of position 751 on KF.</p><p>In summary, we have described the use of tC and TEMPO as a fluorophore-quencher pair which can report on structural changes associated with binding of a cognate dNTP substrate by a DNA-polymerase complex. Steady-state fluorescence measurements have shown that the fluorescence of tC is unaffected by the formation of a binary DNA-KF complex or addition of a non-cognate dNTP. However, when cognate nucleotide is added to the binary complex, the tC fluorescence is reduced by approximately 30%. The change in fluorescence indicates the formation of a closed ternary complex in which the O-helix is closer to the tC than in the binary complex. The kinetics and dynamics of nucleotide selection and incorporation are areas of significant current interest [11-13]. The tC-TEMPO pair provides a sensitive spectroscopic system to investigate the structural changes of the polymerase that occur during nucleotide selection and binding. More generally, the tC-TEMPO pair should be applicable to other DNA processing enzymes.</p>\n\n\n<p>(a) 1 tC nucleoside. (b) Primer/template sequence (X = tC).</p><p>Selective extension of primer/template complex with cognate dNTP. The assay was initiated by adding KF-751-TEMPO to a solution of primer/template duplex and dNTP so that the final concentration of KF was 45 nM, primer/template was 9 mM and 900 mM dNTP. The reaction buffer contained 50 mM Tris-HCl, pH 7.5, 5 mM MgCl2, 1 mM DTT, and 10% (v/v) glycerol. The reaction was stopped after 30 minutes by quenching with 80% formamide containing 50 mM EDTA. The top band is the template strand and the bottom band is the primer strand. The difference in brightness is due to differential staining with SYBR gold (Invitrogen, Carlsbad, CA), based on strand length. The single base extension product is only observed in the presence of the cognate nucleotide dATP.</p><p>Fluorescence emission spectra (uncorrected) of primer/template (PT), binary complex (PT + KF-751-TEMPO) and ternary complexes containing cognate (PT + KF-751-TEMPO + dATP) and non-cognate (PT + KF-751-TEMPO + dTTP) dNTPs.</p><p>Overlay of crystal structures of primer/template bound to Klentaq in open binary (PDB accession code 2KTQ) and closed ternary complexes (3KTQ), emphasizing the movement of the 751 residue (numbered according to the KF sequence) in red (binary/green; ternary/blue; tC position/yellow)[7].</p>", "role": "user" }, { "content": "A fluorophore/quencher pair capable of detecting conformational changes of DNA-protein complexes is described. The system employs a fluorescent nucleoside analog 1,3-diaza-2-oxophenothiazine (tC) within duplex DNA and a non-fluorescent quencher (TEMPO) attached to an engineered cysteine residue of the protein. The straightforward labeling methodology allows for the placement of the fluorophore and quencher moieties at specific positions suited to studying the conformational change of interest. To illustrate the utility of the tC-TEMPO pair, we have monitored nucleotide-induced conformational changes of the Klenow fragment (KF) polymerase bound to duplex DNA. In this system, tC was incorporated in the primer strand of the duplex, adjacent to the 3\\xe2\\x80\\x99 end, while TEMPO was positioned at the end of the O-helix within the fingers domain of KF. Using steady-state fluorescence spectroscopy, we measured the quenching efficiency in a binary complex of tC-modified DNA and TEMPO-labeled KF and in ternary complexes containing cognate or non-cognate dNTP substrates. The quenching efficiency is significantly enhanced in the presence of a cognate dNTP, indicating that the O-helix has moved closer towards the DNA. In contrast, no significant tC quenching is observed in the presence of a non-cognate dNTP, indicating that the O-helix remains in a position that is beyond the distance reporting range of the tC-TEMPO pair. These results demonstrate that a cognate dNTP substrate induces a large conformational change of the O-helix, which can be sensitively detected using the tC-TEMPO pair. This fluorophore/quencher pair may be useful to study conformational changes associated with other DNA-enzyme complexes.", "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\nSignificant illness, trauma or surgical procedures. \nClinically significant laboratory abnormalities. \nClinically significant medical history", "role": "user" }, { "content": "{\"Condition\": [\"laboratory abnormalities\", \"trauma\", \"illness\"], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [\"medical history\"], \"Person\": [], \"Procedure\": [\"laboratory\", \"surgical procedures\"], \"Qualifier\": [\"Clinically significant\", \"Significant\"], \"ReferencePoint\": [], \"Scope\": [\"illness, trauma or surgical procedures\"], \"Temporal\": [], \"Value\": [], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Extract all unique entities of these types from the biomedical abstract: [\"CellLine\", \"DNA\", \"Protein\", \"CellType\", \"RNA\"].\n\nOutput a JSON object with entity types as keys and lists of extracted entities as values. If no entities found for a type, use [].\n\nAbstract:\n\nRegulation of IL-6 synthesis in human peripheral blood mononuclear cells by C3a and C3a (desArg). The anaphylatoxin C3a has been reported to have immunomodulatory effects on a number of different cell types. In this study we investigated the effects of C3a and C3a (desArg) on gene expression and protein secretion of IL-6 in human PBMCs, either alone or in combination with LPS or IL-1beta. C3a or C3a (desArg) alone exhibited no effect on the expression or secretion of IL-6. However, when PBMC were stimulated with LPS or IL-1beta, both C3a and C3a (desArg) were found to enhance IL-6 release by PBMC in a dose-dependent manner. Since C3a has been shown to induce PGE2 production by monocytes, and PGE2 has been shown to influence cytokine production, we investigated the potential role of PGE2 in C3a-mediated enhancement of LPS-and IL-1beta-induced IL-6 production. Indomethacin blocked PGE2 release, but had no influence on the observed effects of C3a, suggesting that the effects of C3a on IL-6 production are independent of PGE2 formation by monocytes. Northern blot analysis showed that C3a as well as C3a (desArg) enhanced LPS-induced mRNA levels for IL-6. Pretreatment of PBMCs with pertussis toxin blocked the functions of C3a and C3a (desArg), indicating that the actions of these two molecules are mediated by a G protein-coupled pathway. Furthermore, we investigated the effects of C3a and C3a (desArg) on induction of NF-kappaB and activating protein-1 binding. Both molecules enhanced LPS-induced NF-kappaB and activating protein-1 binding activity. These results demonstrate the capacity of intact C3a and its circulating des-Arg form to exert immunmodulatory effects in vitro.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"monocytes\", \"PBMCs\", \"human peripheral blood mononuclear cells\", \"PBMC\"], \"DNA\": [], \"Protein\": [\"pertussis toxin\", \"des - Arg form\", \"IL - 6\", \"its circulating des - Arg form\", \"The anaphylatoxin C3a\", \"anaphylatoxin\", \"NF - kappaB\", \"activating protein - 1\", \"IL - 1beta\", \"G protein\", \"C3a\", \"C3a (desArg)\"], \"RNA\": [\"- induced mRNA\"]}", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nVirtual and in vitro bioassay screening of phytochemical inhibitors from flavonoids and isoflavones against xanthine oxidase and cyclooxygenase-2 for gout treatment. Synthetic drugs such as allopurinol and benzbromarone are commonly used to treat the complex pathogenesis of gout, a metabolic disease that results from an inflammation of the joints caused by precipitation of uric acid. We seek to discover novel phytochemicals that could treat gout, by targeting the xanthine oxidase and cyclooxygenase-2 enzymes. In this study, we report the screening of nine compounds of flavonoids from the ZINC and PubChem databases (containing 2092 flavonoids) using the IGEMDOCK software tool against the xanthine oxidase and cyclooxygenase-2 3D protein structures. Each compound was also evaluated by an in vitro bioassay testing the inhibition of xanthine oxidase and cyclooxygenase-2. Myricetin and luteolin were found to be the potential dual inhibitors of xanthine oxidase and cyclooxygenase-2 as demonstrated by IC(50): 62.7 and 3.29 μg/mL (xanthine oxidase)/70.8 and 16.38 μg/mL (cyclooxygenase-2), respectively. In addition, structure-activity relationships and other important factors of the flavonoids binding to the active site of xanthine oxidase and cyclooxygenase-2 were discussed, which is expected for further rational drug design.", "role": "user" }, { "content": "{\"Chemical\": [\"isoflavones\", \"luteolin\", \"allopurinol\", \"uric acid\", \"Myricetin\", \"benzbromarone\", \"flavonoids\", \"xanthine\"]}", "role": "assistant" } ]

[ { "content": "Summarize the paper:\n\nPaper text:\n\nSupervised learning with irregularly sampled time series have been a challenge to Machine Learning methods due to the obstacle of dealing with irregular time intervals.\nSome papers introduced recently recurrent neural network models that deals with irregularity, but most of them rely on complex mechanisms to achieve a better performance.\nThis work propose a novel method to represent timestamps (hours or dates) as dense vectors using sinusoidal functions, called Time Embeddings.\nAs a data input method it and can be applied to most machine learning models.\nThe method was evaluated with two predictive tasks from MIMIC III, a dataset of irregularly sampled time series of electronic health records.\nOur tests showed an improvement to LSTM-based and classical machine learning models, specially with very irregular data.\nAn irregularly (or unevenly) sampled time series is a sequence of samples with irregular time intervals between observations.\nThis class of data add a time sparsity factor when the intervals between observations are large.\nMost machine learning methods do not have time comprehension, this means they only consider observation order.\nThis makes it harder to learn time dependencies found in time series problems.\nTo solve this problem recent work propose models that are able to deal with such irregularity (Lipton et al., 2016; Bahadori & Lipton, 2019; Che et al., 2018; Shukla & Marlin, 2018) , but they often rely on complex mechanisms to represent irregularity or to impute missing data.\nIn this paper, we introduce a novel way to represent time as a dense vector representation, which is able to improve the expressiveness of irregularly sampled data, we call it Time Embeddings (TEs).\nThe proposed method is based on sinusoidal functions discretized to create a continuous representation of time.\nTEs can make a model capable of estimating time intervals between observations, and they do so without the addition of any trainable parameters.\nWe evaluate the method with a publicly available real-world dataset of irregularly sampled electronic health records called MIMIC-III (Johnson et al., 2016) .\nThe tests were made with two tasks: a classification task (in-hospital mortality prediction) and a regression (length of stay).\nTo evaluate the impact of time representation in the data expressiveness we used LSTM and SelfAttentive LSTM models.\nBoth are common RNN models that have been reported to achieve great performance in several time series classification problems, and specifically with the MIMIC-III dataset (Lipton et al., 2016; Shukla & Marlin, 2018; Bahadori & Lipton, 2019; Zhang et al., 2018) .\nWe also evaluated simpler models such as linear and logistic regression and a shallow Multi Layer Perceptron.\nAll models were evaluated with and without TEs to asses possible improvements.\nThis paper propose a novel method to represent hour time or dates as dense vectors to improve irregularly sampled time series.\nIt was evaluated with two different approaches and evaluated in two tasks from the MIMIC III dataset.\nOur method showed some improvement with most models tested, including recurrent neural networks and classic machine learning methods.\nDespite being outperformed by binary masking in some tests we believe TEs can still be an viable option.\nSpecially to very irregular time series and high dimensional data, were TEs can be applied by addition without increasing the input dimensionality.", "role": "user" }, { "content": "A novel method to create dense descriptors of time (Time Embeddings) to make simple models understand temporal structures", "role": "assistant" } ]

[ { "content": "Extract all chemical entities (ChEBI) from this biomedical text. Output as JSON array.\n\nText: Together,thesedataunderscoretheimportanceoftheTGF-beta2isoformdespiteexpressionofbothTGF-beta1andTGF-beta2indevelopinghairbudsatthisstage.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: Nonlinear q-Generalizations of Quantum Equations: Homogeneous and Nonhomogeneous Cases: An Overview \nChapter Title: Generalized Nonlinear Klein-Gordon Equation \n1. Abstract of Cited Paper (BIB001): Generalizations of the three main equations of quantum physics, namely, the Schrödinger, Klein-Gordon, and Dirac equations, are proposed. Nonlinear terms, characterized by exponents depending on an index q, are considered in such a way that the standard linear equations are recovered in the limit q→1. Interestingly, these equations present a common, solitonlike, traveling solution, which is written in terms of the q-exponential function that naturally emerges within nonextensive statistical mechanics. In all cases, the well-known Einstein energy-momentum relation is preserved for arbitrary values of q. \n2. Abstract of Cited Paper (BIB002): A translation operator is introduced to describe the quantum dynamics of a position-dependent mass particle in a null or constant potential. From this operator, we obtain a generalized form of the momentum operator as well as a unique commutation relation for $\\hat x$ and $\\hat p_\\gamma$. Such a formalism naturally leads to a Schr\\\"odinger-like equation that is reminiscent of wave equations typically used to model electrons with position-dependent (effective) masses propagating through abrupt interfaces in semiconductor heterostructures. The distinctive features of our approach is demonstrated through analytical solutions calculated for particles under null and constant potentials like infinite wells in one and two dimensions and potential barriers. \n3. Abstract of Cited Paper (BIB003): An exact classical field theory, for a recently proposed nonlinear generalization of the Schr?dinger equation, is presented. In this generalization, a nonlinearity depending on an index q appears in the kinetic term, such that the free-particle linear Schr?dinger equation is recovered in the limit q?1. It is shown that besides the usual , a new field must be introduced, which becomes only when q?1. In analogy to the linear case, is interpreted as the probability density for finding the particle at time t, in a given position inside an arbitrary finite volume V, for any q. The possible physical consequences are discussed, and, in particular, the important property that the fields and do not interact with light. \n4. Abstract of Cited Paper (BIB004): An exact classical field theory for nonlinear quantum equations is presented herein. It has been applied recently to a nonlinear Schrodinger equation, and it is shown herein to hold also for a nonlinear generalization of the Klein-Gordon equation. These generalizations were carried by introducing nonlinear terms, characterized by exponents depending on an index q, in such a way that the standard, linear equations, are recovered in the limit q → 1. The main characteristic of this field theory consists on the fact that besides the usual Ψ(x,t), a new field Φ(x,t) needs to be introduced in the Lagrangian, as well. The field Φ(x,t), which is defined by means of an additional equation, becomes Ψ*(x,t) only when q → 1. The solutions for the fields Ψ(x,t) and Φ(x,t) are found herein, being expressed in terms of a q-plane wave; moreover, both field equations lead to the relation E2 = p2c2 + m2c4, for all values of q. The fact that such a classical field theory works well for two very distinct nonlinear quan... \n5. Abstract of Cited Paper (BIB005): We show that the Schrodinger and Klein–Gordon equations can both be derived from a hypergeometric differential equation. The same applies to non linear generalizations of these equations.\n\nLiterature Review:", "role": "user" }, { "content": "In BIB002 , besides the NLSE of Section 3, other nonlinear generalized quantum equations were introduced, like proposals for the Klein-Gordon and Dirac equations. In this section, we will discuss briefly the nonlinear Klein-Gordon equation (NLKGE) introduced in BIB002 , which for a particle of mass m in d dimensions is given by: recovering the standard linear Klein-Gordon equation in the case q = 1 . One may verify that the q-plane wave of Equation (6) satisfies the NLKGE above, preserving the corresponding energy-momentum relation for all q, Although Equation BIB003 and its solution in Equation (6) are valid for a general d-dimensional position vectorx, herein, for simplicity, we will restrict ourselves to a three-dimensional vectorx; let us then introduce the four-dimensional space-time operators [79] , so that Equation (104) may be rewritten as: Similarly to the NLSE BIB004 , a classical field theory was introduced for the NLKGE in BIB005 . This approach was also developed in terms of two classical fields, Y(x, t) and F(x, t), by writing the following Lagrangian density, with the multiplicative factor,Ã ⌘h 2 c 2 /[2(1 3q)EW], depending on the total energy E, and as usual, the fields Y(x, t) and F(x, t) are confined to a finite volume W . The Lagrangian above is equivalent to: where the total derivative terms are relevant for q 6 = 1 (contrary to what happens in the linear case) BIB005 . One should notice that the above Lagrangian density presents higher-order derivatives, as compared to the one of Equation (41), i.e., it depends on the fields Y(x, t) and F(x, t), as well as on their first and second derivatives, In this case, the Euler-Lagrange equations should take into account higher-order terms, in such a way that for the field F, one has BIB001 , Substituting the Lagrangian density of Equation (109) in the above Euler-Lagrange equation, one obtains the NLKGE of Equation (107); carrying out the same procedure in the Euler-Lagrange equation for the field Y, one obtains an additional equation for the field F, . The equation above becomes the complex conjugate of Equation (104) for q ! 1 through the identification F(x, t) = Y ⇤ (x, t); substituting the q-exponential of Equation . One important aspect of Equation (113) may be seen by substituting the above solutions for Y(x, t) and F(x, t) in order to reproduce the same energy-momentum relation of Equation (105), for all q. The NLKGE of Equation (104) has attracted some interest recently, and it was shown to be directly related to the hypergeometric differential equation, being derived from the latter, through mathematical manipulations BIB006 . Moreover, by introducing a dissipative term in Equation (104), a nonlinear generalization of the celebrated telegraph equation was proposed .", "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: These experiments are described in detail elsewhere (Oum et al., 1998; Knipping et al., 2000; Hunt et al., 2004).", "role": "user" }, { "content": "Method", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: I want to use the proposed framework to train a transfer network for multiple styles and further show\n\nKeyphrases: image style transfer images\n\nDataset descriptions:\nFreebaseQA: FreebaseQA is a data set for open-domain QA over the Freebase knowledge graph. The question-answer pairs in this data set are collected from various sources, including the TriviaQA data set and other trivia websites (QuizBalls, QuizZone, KnowQuiz), and are matched against Freebase to generate relevant subject-predicate-object triples that were further verified by human annotators.\nCOCO: The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.\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.\nUASOL: The UASOL an RGB-D stereo dataset, that contains 160902 frames, filmed at 33 different scenes, each with between 2 k and 10 k frames. The frames show different paths from the perspective of a pedestrian, including sidewalks, trails, roads, etc.\n\nOptions: A: FreebaseQA B: COCO C: SNIPS D: UASOL", "role": "user" }, { "content": "COCO", "role": "assistant" } ]

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

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Hydroxychloroquine Is Ineffective In Treatment Of Patients Hospitalized With Covid-19\n\nAbstract:\nBackground: There is no effective therapy for COVID-19.\nHydroxychloroquine (HCQ) and chloroquine (CQ) have been used for its treatment but their safety and efficacy remain uncertain.\nObjective: We performed a systematic review to synthesize the available data on the efficacy and safety of CQ and HCQ for the treatment of COVID-19.\nMethods: Two reviewers searched for published and pre-published relevant articles between December 2019 to 8th June 2020.\nThe data from the selected studies were abstracted and analyzed for efficacy and safety outcomes.\nCritical appraisal of the evidence was done by Cochrane risk of bias tool and Newcastle Ottawa scale.\nThe quality of evidence was graded as per the GRADE approach.\nResults: We reviewed 12 observational and 3 randomized trials which included 10659 patients of whom 5713 received CQ/HCQ and 4966 received only standard of care.\nThe efficacy of CQ/HCQ for COVID-19 was inconsistent across the studies.\nMeta-analysis of included studies revealed no significant reduction in mortality with HCQ use [RR 0.98 95% CI 0.66-1.46] , time to fever resolution [mean difference -0.54 days (-1.19-011)] or clinical deterioration/development of ARDS with HCQ [RR 0.90 95% CI 0.47-1.71].\nThere was a higher risk of ECG abnormalities/arrhythmia with HCQ/CQ [RR 1.46 95% CI 1.04 to 2.06].\nThe quality of evidence was graded as very low for these outcomes.\nConclusions: The available evidence suggests that CQ or HCQ does not improve clinical outcomes in COVID-19.\nWell-designed randomized trials are required for assessing the efficacy and safety of HCQ and CQ for COVID-19.", "role": "user" }, { "content": "{\"verdict\": \"CONTRADICT\", \"evidence\": [\"Conclusions: The available evidence suggests that CQ or HCQ does not improve clinical outcomes in COVID-19.\"]}", "role": "assistant" } ]

[ { "content": "Find entities of these types in the text: [\"Participant\", \"Outcome\", \"Intervention\"].\n\nOutput a JSON object with entity types as keys and lists of found entities as values.\n\nText:\n[ Prophylactic intraaortic balloon pumping in high-risk cardiac surgery patients ] . BACKGROUND We examined the impact of prophylactic IABP insertion in EuroSCORE-stratified high-risk cardiac surgery patients with a score ≥8 . MATERIAL AND METHODS A randomized trial with 104 patients either without prophylactic IABP insertion ( group A , n=52 ) or with IABP ( group B , n=52 ) was conducted . The primary endpoint was 30-day mortality . RESULTS The median age of the patients was 74 years and 43 % of participants were females . The 30-day mortality did not differ between group A ( 17.3 % ) and group B ( 13.4 % ; p=0.78 ) . The median hospital stay was 14 days in both groups . Intra- and postoperative IABP support was required by 13 patients ( 21 % ) in group A . The median ventilation time ( 14 hours versus 13 hours ) , median catecholamine dose , frequency of dialysis-dependent acute renal failure ( 28 % versus 18 % ) , cardiac indices , and frequency of a low cardiac output syndrome ( 26 % versus 25 % ) did not significantly differ between groups . CONCLUSION Prophylactic preoperative IABP insertion in EuroSCORE-stratified high-risk patients is not associated with decreased 30-day mortality .", "role": "user" }, { "content": "{\"Intervention\": [\"Prophylactic intraaortic balloon pumping\", \"prophylactic IABP insertion\"], \"Outcome\": [\"30-day mortality\", \"median ventilation\", \"median catecholamine dose\", \"frequency of dialysis-dependent acute renal\", \"median hospital\", \"cardiac indices , and frequency of a low cardiac output\"], \"Participant\": [\"high-risk cardiac surgery patients\", \"74\"]}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: The virus that causes coronavirus disease 2019 (COVID-19) is stable for several hours to days in aerosols and on surfaces\n\nAbstract:\nPURPOSE OF REVIEW This article reviews 'no touch' methods for disinfection of the contaminated surface environment of hospitalized patients' rooms.\nThe focus is on studies that assessed the effectiveness of ultraviolet (UV) light devices, hydrogen peroxide systems, and self-disinfecting surfaces to reduce healthcare-associated infections (HAIs).\nRECENT FINDINGS The contaminated surface environment in hospitals plays an important role in the transmission of several key nosocomial pathogens including methicillin-resistant Staphylococcus aureus, vancomycin-resistant Enterococcus spp.\n, Clostridium difficile, Acinetobacter spp., and norovirus.\nMultiple clinical trials have now demonstrated the effectiveness of UV light devices and hydrogen peroxide systems to reduce HAIs.\nA limited number of studies have suggested that 'self-disinfecting' surfaces may also decrease HAIs.\nSUMMARY Many studies have demonstrated that terminal cleaning and disinfection with germicides is often inadequate and leaves environmental surfaces contaminated with important nosocomial pathogens. 'No touch' methods of room decontamination (i.e., UV devices and hydrogen peroxide systems) have been demonstrated to reduce key nosocomial pathogens on inoculated test surfaces and on environmental surfaces in actual patient rooms.\nFurther UV devices and hydrogen peroxide systems have been demonstrated to reduce HAI.\nA validated 'no touch' device or system should be used for terminal room disinfection following discharge of patients on contact precautions.\nThe use of a 'self-disinfecting' surface to reduce HAI has not been convincingly demonstrated.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Coronavirus quarantines like the ones in China are likely not feasible in the U.S., according to a top health official.\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\": \"NEI\", \"evidence\": []}", "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: have shown that the distended region of the intestine demonstrates inflammatory reactions, which could cause the disruption of the ICC network [8,16,17].", "role": "user" }, { "content": "Background", "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: DENS: A Dataset for Multi-class Emotion Analysis\n\nWe introduce a new dataset for multi-class emotion analysis from long-form narratives in English. The Dataset for Emotions of Narrative Sequences (DENS) was collected from both classic literature available on Project Gutenberg and modern online narratives available on Wattpad, annotated using Amazon Mechanical Turk. A number of statistics and baseline benchmarks are provided for the dataset. Of the tested techniques, we find that the fine-tuning of a pre-trained BERT model achieves the best results, with an average micro-F1 score of 60.4%. Our results show that the dataset provides a novel opportunity in emotion analysis that requires moving beyond existing sentence-level techniques.\n\nIntroduction\nHumans experience a variety of complex emotions in daily life. These emotions are heavily reflected in our language, in both spoken and written forms.\nMany recent advances in natural language processing on emotions have focused on product reviews BIBREF0 and tweets BIBREF1, BIBREF2. These datasets are often limited in length (e.g. by the number of words in tweets), purpose (e.g. product reviews), or emotional spectrum (e.g. binary classification).\nCharacter dialogues and narratives in storytelling usually carry strong emotions. A memorable story is often one in which the emotional journey of the characters resonates with the reader. Indeed, emotion is one of the most important aspects of narratives. In order to characterize narrative emotions properly, we must move beyond binary constraints (e.g. good or bad, happy or sad).\nIn this paper, we introduce the Dataset for Emotions of Narrative Sequences (DENS) for emotion analysis, consisting of passages from long-form fictional narratives from both classic literature and modern stories in English. The data samples consist of self-contained passages that span several sentences and a variety of subjects. Each sample is annotated by using one of 9 classes and an indicator for annotator agreement.\n\nBackground\nUsing the categorical basic emotion model BIBREF3, BIBREF4, BIBREF5 studied creating lexicons from tweets for use in emotion analysis. Recently, BIBREF1, BIBREF6 and BIBREF2 proposed shared-tasks for multi-class emotion analysis based on tweets.\nFewer works have been reported on understanding emotions in narratives. Emotional Arc BIBREF7 is one recent advance in this direction. The work used lexicons and unsupervised learning methods based on unlabelled passages from titles in Project Gutenberg.\nFor labelled datasets on narratives, BIBREF8 provided a sentence-level annotated corpus of childrens' stories and BIBREF9 provided phrase-level annotations on selected Project Gutenberg titles.\nTo the best of our knowledge, the dataset in this work is the first to provide multi-class emotion labels on passages, selected from both Project Gutenberg and modern narratives. The dataset is available upon request for non-commercial, research only purposes.\n\nDataset\nIn this section, we describe the process used to collect and annotate the dataset.\n\nDataset ::: Plutchik’s Wheel of Emotions\nThe dataset is annotated based on a modified Plutchik’s wheel of emotions.\nThe original Plutchik’s wheel consists of 8 primary emotions: Joy, Sadness, Anger, Fear, Anticipation, Surprise, Trust, Disgust. In addition, more complex emotions can be formed by combing two basic emotions. For example, Love is defined as a combination of Joy and Trust (Fig. 1).\nThe intensity of an emotion is also captured in Plutchik's wheel. For example, the primary emotion of Anger can vary between Annoyance (mild) and Rage (intense).\nWe conducted an initial survey based on 100 stories with a significant fraction sampled from the romance genre. We asked readers to identify the major emotion exhibited in each story from a choice of the original 8 primary emotions.\nWe found that readers have significant difficulty in identifying Trust as an emotion associated with romantic stories. Hence, we modified our annotation scheme by removing Trust and adding Love. We also added the Neutral category to denote passages that do not exhibit any emotional content.\nThe final annotation categories for the dataset are: Joy, Sadness, Anger, Fear, Anticipation, Surprise, Love, Disgust, Neutral.\n\nDataset ::: Passage Selection\nWe selected both classic and modern narratives in English for this dataset. The modern narratives were sampled based on popularity from Wattpad. We parsed selected narratives into passages, where a passage is considered to be eligible for annotation if it contained between 40 and 200 tokens.\nIn long-form narratives, many non-conversational passages are intended for transition or scene introduction, and may not carry any emotion. We divided the eligible passages into two parts, and one part was pruned using selected emotion-rich but ambiguous lexicons such as cry, punch, kiss, etc.. Then we mixed this pruned part with the unpruned part for annotation in order to reduce the number of neutral passages. See Appendix SECREF25 for the lexicons used.\n\nDataset ::: Mechanical Turk (MTurk)\nMTurk was set up using the standard sentiment template and instructed the crowd annotators to `pick the best/major emotion embodied in the passage'.\nWe further provided instructions to clarify the intensity of an emotion, such as: “Rage/Annoyance is a form of Anger”, “Serenity/Ecstasy is a form of Joy”, and “Love includes Romantic/Family/Friendship”, along with sample passages.\nWe required all annotators have a `master' MTurk qualification. Each passage was labelled by 3 unique annotators. Only passages with a majority agreement between annotators were accepted as valid. This is equivalent to a Fleiss's $\\kappa $ score of greater than $0.4$.\nFor passages without majority agreement between annotators, we consolidated their labels using in-house data annotators who are experts in narrative content. A passage is accepted as valid if the in-house annotator's label matched any one of the MTurk annotators' labels. The remaining passages are discarded. We provide the fraction of annotator agreement for each label in the dataset.\nThough passages may lose some emotional context when read independently of the complete narrative, we believe annotator agreement on our dataset supports the assertion that small excerpts can still convey coherent emotions.\nDuring the annotation process, several annotators had suggested for us to include additional emotions such as confused, pain, and jealousy, which are common to narratives. As they were not part of the original Plutchik’s wheel, we decided to not include them. An interesting future direction is to study the relationship between emotions such as ‘pain versus sadness’ or ‘confused versus surprise’ and improve the emotion model for narratives.\n\nDataset ::: Dataset Statistics\nThe dataset contains a total of 9710 passages, with an average of 6.24 sentences per passage, 16.16 words per sentence, and an average length of 86 words.\nThe vocabulary size is 28K (when lowercased). It contains over 1600 unique titles across multiple categories, including 88 titles (1520 passages) from Project Gutenberg. All of the modern narratives were written after the year 2000, with notable amount of themes in coming-of-age, strong-female-lead, and LGBTQ+. The genre distribution is listed in Table TABREF8.\nIn the final dataset, 21.0% of the data has consensus between all annotators, 73.5% has majority agreement, and 5.48% has labels assigned after consultation with in-house annotators.\nThe distribution of data points over labels with top lexicons (lower-cased, normalized) is shown in Table TABREF9. Note that the Disgust category is very small and should be discarded. Furthermore, we suspect that the data labelled as Surprise may be noisier than other categories and should be discarded as well.\nTable TABREF10 shows a few examples labelled data from classic titles. More examples can be found in Table TABREF26 in the Appendix SECREF27.\n\nBenchmarks\nWe performed benchmark experiments on the dataset using several different algorithms. In all experiments, we have discarded the data labelled with Surprise and Disgust.\nWe pre-processed the data by using the SpaCy pipeline. We masked out named entities with entity-type specific placeholders to reduce the chance of benchmark models utilizing named entities as a basis for classification.\nBenchmark results are shown in Table TABREF17. The dataset is approximately balanced after discarding the Surprise and Disgust classes. We report the average micro-F1 scores, with 5-fold cross validation for each technique.\nWe provide a brief overview of each benchmark experiment below. Among all of the benchmarks, Bidirectional Encoder Representations from Transformers (BERT) BIBREF11 achieved the best performance with a 0.604 micro-F1 score.\nOverall, we observed that deep-learning based techniques performed better than lexical based methods. This suggests that a method which attends to context and themes could do well on the dataset.\n\nBenchmarks ::: Bag-of-Words-based Benchmarks\nWe computed bag-of-words-based benchmarks using the following methods:\nClassification with TF-IDF + Linear SVM (TF-IDF + SVM)\nClassification with Depeche++ Emotion lexicons BIBREF12 + Linear SVM (Depeche + SVM)\nClassification with NRC Emotion lexicons BIBREF13, BIBREF14 + Linear SVM (NRC + SVM)\nCombination of TF-IDF and NRC Emotion lexicons (TF-NRC + SVM)\n\nBenchmarks ::: Doc2Vec + SVM\nWe also used simple classification models with learned embeddings. We trained a Doc2Vec model BIBREF15 using the dataset and used the embedding document vectors as features for a linear SVM classifier.\n\nBenchmarks ::: Hierarchical RNN\nFor this benchmark, we considered a Hierarchical RNN, following BIBREF16. We used two BiLSTMs BIBREF17 with 256 units each to model sentences and documents. The tokens of a sentence were processed independently of other sentence tokens. For each direction in the token-level BiLSTM, the last outputs were concatenated and fed into the sentence-level BiLSTM as inputs.\nThe outputs of the BiLSTM were connected to 2 dense layers with 256 ReLU units and a Softmax layer. We initialized tokens with publicly available embeddings trained with GloVe BIBREF18. Sentence boundaries were provided by SpaCy. Dropout was applied to the dense hidden layers during training.\n\nBenchmarks ::: Bi-directional RNN and Self-Attention (BiRNN + Self-Attention)\nOne challenge with RNN-based solutions for text classification is finding the best way to combine word-level representations into higher-level representations.\nSelf-attention BIBREF19, BIBREF20, BIBREF21 has been adapted to text classification, providing improved interpretability and performance. We used BIBREF20 as the basis of this benchmark.\nThe benchmark used a layered Bi-directional RNN (60 units) with GRU cells and a dense layer. Both self-attention layers were 60 units in size and cross-entropy was used as the cost function.\nNote that we have omitted the orthogonal regularizer term, since this dataset is relatively small compared to the traditional datasets used for training such a model. We did not observe any significant performance gain while using the regularizer term in our experiments.\n\nBenchmarks ::: ELMo embedding and Bi-directional RNN (ELMo + BiRNN)\nDeep Contextualized Word Representations (ELMo) BIBREF22 have shown recent success in a number of NLP tasks. The unsupervised nature of the language model allows it to utilize a large amount of available unlabelled data in order to learn better representations of words.\nWe used the pre-trained ELMo model (v2) available on Tensorhub for this benchmark. We fed the word embeddings of ELMo as input into a one layer Bi-directional RNN (16 units) with GRU cells (with dropout) and a dense layer. Cross-entropy was used as the cost function.\n\nBenchmarks ::: Fine-tuned BERT\nBidirectional Encoder Representations from Transformers (BERT) BIBREF11 has achieved state-of-the-art results on several NLP tasks, including sentence classification.\nWe used the fine-tuning procedure outlined in the original work to adapt the pre-trained uncased BERT$_\\textrm {{\\scriptsize LARGE}}$ to a multi-class passage classification task. This technique achieved the best result among our benchmarks, with an average micro-F1 score of 60.4%.\n\nConclusion\nWe introduce DENS, a dataset for multi-class emotion analysis from long-form narratives in English. We provide a number of benchmark results based on models ranging from bag-of-word models to methods based on pre-trained language models (ELMo and BERT).\nOur benchmark results demonstrate that this dataset provides a novel challenge in emotion analysis. The results also demonstrate that attention-based models could significantly improve performance on classification tasks such as emotion analysis.\nInteresting future directions for this work include: 1. incorporating common-sense knowledge into emotion analysis to capture semantic context and 2. using few-shot learning to bootstrap and improve performance of underrepresented emotions.\nFinally, as narrative passages often involve interactions between multiple emotions, one avenue for future datasets could be to focus on the multi-emotion complexities of human language and their contextual interactions.\n\nAppendices ::: Sample Data\nTable TABREF26 shows sample passages from classic titles with corresponding labels.\n\nFigure 1: Plutchik’s wheel of emotions (Wikimedia, 2011)\n\nTable 1: Genre distribution of the modern narratives\n\nTable 4: Benchmark results (averaged 5-fold cross validation)\n\nTable 2: Dataset label distribution\n\nQuestion: What is the size of this dataset?", "role": "user" }, { "content": "{\"answer\": [\"9710 passages, with an average of 6.24 sentences per passage, 16.16 words per sentence, and an average length of 86 words\"], \"evidence\": [\"The dataset contains a total of 9710 passages, with an average of 6.24 sentences per passage, 16.16 words per sentence, and an average length of 86 words.\"]}", "role": "assistant" } ]

[ { "content": "Extract drug combinations from this sentence and classify each combination into one of these categories:\n- POS: Positive interaction between drugs\n- NEG: Negative interaction between drugs\n- COMB: Drugs used together with unknown interaction type\n\nOutput only a JSON array where each entry is [drug_1, drug_2, ..., drug_n, category].\n\nparagraph: How do azoles inhibit cytochrome P450 enzymes? A density functional study. To examine how azole inhibitors interact with the heme active site of the cytochrome P450 enzymes, we have performed a series of density functional theory studies on azole binding. These are the first density functional studies on azole interactions with a heme center and give fundamental insight into how azoles inhibit the catalytic function of P450 enzymes. Since azoles come in many varieties, we tested three typical azole motifs representing a broad range of azole and azole-type inhibitors: methylimidazolate, methyltriazolate, and pyridine. These structural motifs represent typical azoles , such as econazole , fluconazole , and metyrapone . The calculations show that azole binding is a stepwise mechanism whereby first the water molecule from the resting state of P450 is released from the sixth binding site of the heme to create a pentacoordinated active site followed by coordination of the azole nitrogen to the heme iron. This process leads to the breaking of a hydrogen bond between the resting state water molecule and the approaching inhibitor molecule. Although, formally, the water molecule is released in the first step of the reaction mechanism and a pentacoordinated heme is created, this does not lead to an observed spin state crossing. Thus, we show that release of a water molecule from the resting state of P450 enzymes to create a pentacoordinated heme will lead to a doublet to quartet spin state crossing at an Fe-OH(2) distance of approximately 3.0 A, while the azole substitution process takes place at shorter distances. Azoles bind heme with significantly stronger binding energies than a water molecule, so that these inhibitors block the catalytic cycle of the enzyme and prevent oxygen binding and the catalysis of substrate oxidation. Perturbations within the active site (e.g., a polarized environment) have little effect on the relative energies of azole binding. Studies with an extra hydrogen-bonded ethanol molecule in the model, mimicking the active site of the CYP121 P450, show that the resting state and azole binding structures are close in energy, which may lead to chemical equilibrium between the two structures, as indeed observed with recent protein structural studies that have demonstrated two distinct azole binding mechanisms to P450 heme.\n\nsentence: These structural motifs represent typical azoles , such as econazole , fluconazole , and metyrapone .", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Alcohol does not disinfect the mouth or provide protection.\n\nAbstract:\nWhile it remains much too early to determine precisely how alcohol use might affect risk for or progression of COVID‐19, any efforts to connect the dots from past alcohol research would suggest it wise for nondrinkers and low‐risk drinkers to maintain that status during this public health crisis.\nIt's already known that disaster can result in increased alcohol consumption based on the work of Deborah Hasin, Ph.D., after 9/11 (see “Alcohol and isolation: Experts comment on drinking behavior during COVID‐19,” ADAW March 30; https://onlinelibrary.wiley.com/doi/10.1002/adaw.32670).", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"It's already known that disaster can result in increased alcohol consumption based on the work of Deborah Hasin, Ph.D., after 9/11 (see \\u201cAlcohol and isolation: Experts comment on drinking behavior during COVID\\u201019,\\u201d ADAW March 30; https://onlinelibrary.wiley.com/doi/10.1002/adaw.32670).\"]}", "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:\nNone\n\nContext before:\nA number of proposals in the 1990s deliberately limited the extent to which they relied on domain and/or linguistic knowledge and reported promising results in knowledge-poor operational environments (Dagan and Itai 1990, 1991; Lappin and Leass 1994; Nasukawa 1994; Kennedy and Boguraev 1996; Williams, Harvey, and Preston 1996; Baldwin 1997; Mitkov 1996, 1998b). However, the pressing need for the development of robust and inexpensive solutions to meet the demands of practical NLP systems encouraged many researchers to move away from extensive domain and linguistic knowledge and to embark instead upon knowledge-poor anaphora resolution strategies. Much of the earlier work in anaphora resolution heavily exploited domain and linguistic knowledge (Sidner 1979; Carter 1987; Rich and LuperFoy 1988; Carbonell and Brown 1988), which was difficult both to represent and to process, and which required considerable human input.\n\nCitation:\nA number of proposals in the 1990s deliberately limited the extent to which they relied on domain and/or linguistic knowledge and reported promising results in knowledge-poor operational environments ( Dagan and Itai 1990 , 1991 ; Lappin and Leass 1994 ; Nasukawa 1994 ; Kennedy and Boguraev 1996 ; Williams , Harvey , and Preston 1996 ; Baldwin 1997 ; Mitkov 1996 , 1998b ) .\n\nContext after:\nThe drive toward knowledge-poor and robust approaches was further motivated by the emergence of cheaper and more reliable corpus-based NLP tools such as partof-speech taggers and shallow parsers, alongside the increasing availability of corpora and other NLP resources (e.g., ontologies). In fact, the availability of corpora, both raw and annotated with coreferential links, provided a strong impetus to anaphora resolu- tion with regard to both training and evaluation. Corpora (especially when annotated) are an invaluable source not only for empirical research but also for automated learning (e.g., machine learning) methods aiming to develop new rules and approaches; they also provide an important resource for evaluation of the implemented approaches.", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Given the full text of a scientific research paper, write an abstract section for the paper. Your response should contain only the abstract without any other text.\n\nArticle text:\nthe aim of this note is to establish a new link between discrete geometry and classical concepts in topology . configurations of vectors can be understood with the help of grassmannian manifolds equipped with a stratification controlled by matroids @xcite .\nsimilarly , affine configurations yield stratified grassmannians whose structure is determined by affine oriented matroids .\nthe decomposition provided by schubert cells of a grassmannian has striking equivalent formulations in terms of convex polyhedra and of matroids @xcite .\naffine analogues of these results have been pursued in @xcite , where the focus there lies in understanding the combinatorics of these polyhedral structures .\nwe will show that the topology of based loops of certain affine configurations can be explained using braids .\na braid should be thought of as a system of @xmath0 strings which do not intersect and have fixed start and end points .\nlet @xmath1 and @xmath2 be the sets @xmath3 and @xmath4 in @xmath5 , respectively . consider a smooth embedding @xmath6 of an interval @xmath7 into @xmath5 such that @xmath8 lies in @xmath1 and @xmath9 in @xmath2 .\ndenote by @xmath10 a collection of @xmath0 such embeddings @xmath6 , each one starting from a distict point in @xmath1 and ending in a distinct point in @xmath2 , such that the projection to the @xmath11 coordinate is decreasing as @xmath12 runs from @xmath13 to @xmath14 in @xmath7 .\nwe also require that @xmath15 for every @xmath16 in @xmath7 and @xmath17 , which means we obtain disjoint images and the strings do not intersect .\n* definition * _ a braid @xmath18 is an isotopy class of a @xmath10 as described above .\n_ braids form a group @xmath19 @xcite and each braid @xmath18 permutes the order of @xmath1 to a new order in @xmath2 .\nwhen this order remains unchanged , i.e. the permutation is trivial , we say @xmath18 is a _ pure _ braid .\nit is easy to see that pure braids form a subgroup @xmath20 .\nthe fundamental group of the space of @xmath0-tuples of distinct points in the plane is isomorphic to the pure braid group @xmath21 @xcite .\nthe centre of @xmath21 is the infinite cyclic group @xmath22 , generated by the element @xmath23 .\nthe spaces of affine configurations of flats in affine and projective spaces were defined in @xcite .\nfollowing the same notation we consider @xmath24 , the space of distinct @xmath25 , oriented @xmath26 affine classes of sets of @xmath0 points in the real affine plane . for simplicity we will refer to this space as @xmath27 .\n* theorem 1 . * _ for @xmath28 , @xmath29 .\n_ this can be seen as a variation of the classical result about the configurations of distinct points in the plane and the pure braid group mentioned above .\nit allows results from braid groups to be translated into results about affine configurations .\nfor example , the conjugacy problem for braids is solvable @xcite , therefore the isomorphism above implies that the conjugacy problem for homotopy classes of based loops of oriented affine configurations in the plane is also solvable . in principle\nthere exists an algorithm to decide whether or not two such loops are conjugate .\nsuppose @xmath30 is a topological space and let @xmath31 denote the group of self - homemorphisms of @xmath30 .\nlet @xmath32 and @xmath33 be the subgroups which consist of homeomorphisms which are isotopic to the identity and those which preserve orientation , respectively .\ndefine the _ pure mapping class group _ of @xmath30 as @xmath34 .\nthe group @xmath21 is isomorphic to the pure mapping class group of the disk @xmath35 minus @xmath0 points @xcite , we can now establish another isomorphism . from theorem 4.5 in @xcite\nit follows that the pure mapping class group of the sphere @xmath36 with @xmath37 punctures is @xmath38 .\ntherefore we obtain for @xmath39 , * corollary 2 . * _ the fundamental group of @xmath27 is isomorphic to the pure mapping class group of the sphere @xmath36 punctured @xmath37 times .\n_ we will show that the group @xmath40 is isomorphic to a free group with eleven generators .\nthis can be seen by using the combinatorial decomposition of the affine configuration spaces , as outlined in @xcite and @xcite .\nnotice that the configuration space @xmath41 consists of a single point .\n* acknowledgements : * the author thanks luis montejano peimbert for his guidance and encouragement , and is also grateful to francisco gonzalez acua , mario eudave muoz and raymond lickorish for useful conversations and for pointing out subtle details in previous versions .\nlet @xmath42 be the affine span of the set @xmath43 , where @xmath44 .\ndefine @xmath45 in other words , we are considering the sets of @xmath0 points in @xmath46 which are not all co - linear and hence span the real plane affinely .\nthe group @xmath47 of orientation preserving affine transformations of @xmath48 acts freely on @xmath49 .\nwe denote the quotient of @xmath50 under this action by @xmath51 , in @xcite it is denoted by @xmath52 .\nwe call @xmath27 the space of oriented affine configurations of @xmath53 distinct points in the real plane .\nit was shown in @xcite that @xmath54 is a principal fibre bundle .\ntake @xmath64 , for @xmath65 $ ] to be a representative of @xmath61 .\nthen the path @xmath66 rotates the plane by one whole turn , and hence also rotates the points @xmath67 by one whole turn .\ntherefore @xmath66 is identified with @xmath68 under the classical identification of @xmath69 with @xmath21 , where @xmath68 is the generator of the centre @xmath22 of the pure braid group @xmath21 .\nthis implies , @xmath70 we now claim that for @xmath28 the fundamental group of @xmath50 is isomorphic to the pure braid group @xmath21 .\nconsider the smooth inclusion @xmath71 , and note that both @xmath50 and @xmath72 are smooth submanifolds of @xmath73 , because they are the complements of a collection of closed subspaces of codimension @xmath74 .\nfurthermore , @xmath50 is a smooth submanifold of @xmath72 .\nsimilarly @xmath75 is a smooth inclusion .\nwe will show that the complement of @xmath50 in @xmath72 has dimension @xmath76 .\nthe claim @xmath77 will follow from the general fact that when a smooth submanifold @xmath78 of dimension @xmath53 in a smooth manifold @xmath79 of dimension @xmath80 , with @xmath81 then the inclusion @xmath82 induces an isomorphism on the fundamental groups @xmath83 so that @xmath84 .\nnotice @xmath72 is an open subset of @xmath73 , which means @xmath85 .\nan element of @xmath86 is a @xmath0-tuple of points @xmath87 , all of which lie on the same line in @xmath48 .\nfirst we will use the real projective plane @xmath88 minus a point to parametrise free lines in @xmath48 .\nlet @xmath89 be the plane @xmath90 , for @xmath91\\in { \\bf r}p^2 $ ] consider the plane through the origin which is normal to @xmath92 and call it @xmath93 .\ndenote the intersection @xmath94 by @xmath95 , then @xmath91\\mapsto l'$ ] is the homeomorphism that parametrises free lines in @xmath48 by elements of @xmath88 minus the element corresponding to the @xmath11 axis ( and @xmath96 ) .\nsince the @xmath0-tuple @xmath97 is allowed to move freely within the line @xmath92 , it can be described as an open subset of @xmath98 .\nhence @xmath99 , and we are left with @xmath100 . which implies that @xmath101 when @xmath28 . in @xcite\nit was shown that @xmath105 is homeomorphic to @xmath88 .\ntaking the double orientation covering we can see @xmath106 is homeomorphic to @xmath36 and it has the polyhedral structure of the truncated cube .\nthen @xmath107 , which in the notation of @xcite is @xmath108 , is homeomorphic to @xmath36 minus the vertices of the truncated cube . because these vertices correspond to configurations where two points @xmath109 and @xmath110 coincide , i.e. @xmath111 for @xmath112 .\nhence @xmath107 is homeomorphic to @xmath36 minus 12 points , which correspond to the vertices of the truncated cube .\ntherefore the fundamental group of @xmath107 is isomorphic to the free group generated by 11 elements .\na. bjrner , m. las vergnas , b. sturmfels , n. white , g.m .\nziegler , oriented matroids .\nsecond edition .\nencyclopedia of mathematics and its applications , 46 .\ncambridge university press , cambridge , 1999 .\nxii+548 pp .", "role": "user" }, { "content": "we show that the fundamental group of the space of ordered affine equivalent configurations of at least five points in the real plane is isomorphic to the pure braid group modulo its centre . in the case of four points \n this fundamental group is free with eleven generators .", "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: Subluxation and semantics: a corpus linguistics study The purpose of this study was to analyze the curriculum of one chiropractic college in order to discover if there were any implicit consensus definitions of the term subluxation. Using the software WordSmith Tools, the corpus of an undergraduate chiropractic curriculum was analyzed by reviewing collocated terms and through discourse analysis of text blocks containing words based on the root ' sublux .' It was possible to identify 3 distinct concepts which were each referred to as ' subluxation :' i) an acute or instantaneous injurious event; ii) a clinical syndrome which manifested post - injury; iii) a physical lesion, i.e. an anatomical or physiological derangement which in most instances acted as a pain generator. In fact, coherent implicit definitions of subluxation exist and may enjoy broad but subconscious acceptance. However, confusion likely arises from failure to distinguish which concept an author or speaker is referring to when they employ the term subluxation.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"subconscious\", \"identify\", \"confusion\", \"distinguish\"], \"BiomedicalOccupationOrDiscipline\": [\"chiropractic\"], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"pain\", \"derangement\", \"possible\", \"acceptance\", \"lesion\"], \"Food\": [], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [\"injury\", \"injurious\", \"Subluxation\", \"subluxation\"], \"IntellectualProduct\": [\"software WordSmith Tools\", \"words\", \"definitions\", \"text\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [\"speaker\"], \"ProfessionalOrOccupationalGroup\": [\"author\"], \"ResearchActivity\": [\"study\", \"analyzed\", \"corpus\", \"analyze\"], \"SpatialConcept\": [\"broad\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Read the text and answer the question. Only include the exact text from the passage that answers the question.\n\nText: A.; Ewees, Ahmed A.; Fan, Hong; Abd El Aziz, Mohamed\nDate: 2020\nDOI: 10.3390/jcm9030674\nLicense: cc-by\n\nAbstract: In December 2019, a novel coronavirus, called COVID-19, was discovered in Wuhan, China , and has spread to different cities in China as well as to 24 other countries. The number of confirmed cases is increasing daily and reached 34,598 on 8 February 2020. In the current study, we present a new forecasting model to estimate and forecast the number of confirmed cases of COVID-19 in the upcoming ten days based on the previously confirmed cases recorded in China. The proposed model is an improved adaptive neuro-fuzzy inference system (ANFIS) using an enhanced flower pollination algorithm (FPA) by using the salp swarm algorithm (SSA). In general, SSA is employed to improve FPA to avoid its drawbacks (i.e., getting trapped at the local optima). The main idea of the proposed model, called FPASSA-ANFIS, is to improve the performance of ANFIS by determining the parameters of ANFIS using FPASSA. The FPASSA-ANFIS model is evaluated using the World Health Organization (WHO) official data of the outbreak of the COVID-19 to forecast the confirmed cases of the upcoming ten days. More so, the FPASSA-ANFIS model is compared to several existing models, and it showed better performance in terms of Mean Absolute Percentage Error (MAPE), Root Mean Squared Relative Error (RMSRE), Root Mean Squared Relative Error (RMSRE), coefficient of determination ( R 2 ), and computing time. Furthermore, we tested the proposed model using two different datasets of weekly influenza confirmed cases in two countries, namely the USA and China. The outcomes also showed good performances. Text: A large family of viruses, called coronaviruses, are severe pathogens for human beings, which infect respiratory, hepatic, gastrointestinal, and neurologic diseases. They are distributed among humans, birds, livestock, mice, bats, and other wild animals [1] [2] [3] . The outbreaks of two previous coronaviruses, SARS-CoV and MERS-CoV in 2003 and 2012, respectively, have approved the transmission from animal to animal, and human to human [4] . In December 2019, the World Health Organization (WHO) received notifications from China for many cases of respiratory illness that were linked to some people who had visited a seafood market in Wuhan [5] . Currently, Wuhan city suffers from the spreading of a novel coronavirus, called COVID-19 (previously, it was called 2019-nCoV). In [6] , the authors concluded that COVID-19 likely originated in bats, because it is more similar to two bat-derived coronavirus strains. However, the source of the COVID-19 is not confirmed yet, and it communities, Hong Kong and Toronto, were 1.2 and 1.32, respectively. Ong et al. [20] proposed a monitoring and forecasting model for influenza A (H1N1-2009). Furthermore, Nah et al. [21] proposed a probability-based model to predict the spread of the MERS. The Adaptive Neuro-Fuzzy Inference System (ANFIS) [22] is widely applied in time series prediction and forecasting problems, and it showed good performance in many existing applications. It offers flexibility in determining nonlinearity in the time series data, as well as combining the properties of both artificial neural networks (ANN) and fuzzy logic systems. It has been applied in various forecasting applications, for example, in [23] , a stock price forecasting model was proposed using ANFIS and empirical mode decomposition. Chen et al. [24] proposed a TAIEX time series forecasting model based on a hybrid of ANFIS and ordered weighted averaging (OWA). In [25] , another time series forecasting method was presented for electricity prices based on ANFIS. Svalina et al. [26] proposed an ANFIS based forecasting model for close price indices for a stock market for five days. Ekici and Aksoy [27] presented an ANFIS based building energy consumption forecasting model. More so, ANFIS is also applied to forecast electricity loads [28] . Kumar et al. [29] proposed an ANFIS based model to forecast return products. Ho and Tsai [30] applied ANFIS to forecast product development performance. However, estimating ANFIS parameters is a challenge that needs to be improved. Therefore, in previous studies, some individual swarm intelligence (SI) methods have been applied to the ANFIS parameters to enhance time series forecasting because these parameters have a significant effect on the performance of ANFIS. The SI methods include the particle swarm optimization (PSO) [31, 32] , social-spider optimization [33] , sine-cosine algorithm (SCA) [34] , and multi-verse optimizer (MVO) [35] . For example, in [34] SCA algorithm was applied to improve the ANFIS model to forecast oil consumption in three countries, namely, Canada, Germany, and Japan. In the same context, in [35] , The MVO algorithm was used to enhance the ANFIS model to forecast oil consumption in two countries. In addition, in [36] the PSO was used with ANFIS to predict biochar yield. However, individual SI algorithms may stock at local optima. Therefore, one solution is to apply hybrid SI algorithms to avoid this problem. In [37] , a hybrid of two SI algorithms, namely GA and SSA, was presented to improve the ANFIS model. The proposed new model called GA-SSA-ANFIS was applied to forecast crude oil prices for long-term time series data. However, the previously mentioned methods suffer from some limitations that can affect the performance of the forecasting output such as slow convergence and the ability to balance between exploration and exploitation phases can influence the quality of the final output. This motivated us to propose an alternative forecasting method dependent on the hybridization concept. This concept avoids the limitations of traditional SI techniques by combining the strengths of different techniques, and this produces new SI techniques that are better than traditional ones. In the current study, we propose an improved ANFIS model based on a modified flower pollination algorithm (FPA) using the salp swarm algorithm (SSA). The FPA is an optimization algorithm proposed by Yang [38] , which was inspired by the flow pollination process of the flowering plants. The FPA was employed in various optimization applications, for example to estimate solar PV parameter [39, 40] , solving sudoku puzzles [41] , feature selection [42] , antenna design [43] , and other applications [44] [45] [46] [47] . Moreover, SSA is also an optimization algorithm proposed by Mirjalili et al. [48] inspired by the behavior of salp chains. In recent years, the SSA was utilized to solve different optimization problems, such as feature selection [49, 50] , data classification [51] , image segmentation [52] , and others [53, 54] . The proposed method called FPASSA is a hybrid of FPA and SSA, in which the SSA is applied as a local search method for FPA. The proposed FPASSA starts by receiving the historical COVID-19 dataset. Then a set of solutions is generated where each of them represents the value for the parameters of the ANFIS model. Then the quality of each solution is calculated using the fitness value, and the solution that has the best fitness value is chosen to represent the best solution. Then the probability of each solution is computed. Then the current solution will be updated, either using global or local strategy in FPA. However, in the case of local strategy, the operators of SSA or FPA will be used according to the probability of the fitness value for each solution. The process of updating the solutions is repeated until reaching the stop condition, and the best parameter configurations are used to forecast the number of confirmed cases of COVID-19. The main contribution points of the current study are as follows:\n\n1. We propose an efficient forecasting model to forecast the confirmed cases of the COVID-19 in China for the upcoming ten days based on previously confirmed cases. An improved ANFIS model is proposed using a modified FPA algorithm, using SSA. We compare the proposed model with the original ANFIS and existing modified ANFIS models, such as PSO, GA, ABC, and FPA. The rest of this study is organized as follows. The preliminaries of ANFIS, FPA, and SSA are described in Section 2. Section 3 presents the proposed FPASSA, and Section 4 presents the experimental setup and results. We conclude this study in Section 5. The principles of the ANFIS are given in this section. The ANFIS model links the fuzzy logic and neural networks [22] . It generates a mapping between the input and output by applying IF-THEN rules (it is also called Takagi-Sugeno inference model). Figure 1 illustrates the ANFIS model where, y and x define the inputs to Layer 1 whereas, O 1i is its output of node i that is computed as follows:\n\nwhere µ denotes the generalized Gaussian membership functions. A i and B i define the membership values of µ. α i and ρ i denote the premise parameters set. The output of Layer 2 (it is also known as the firing strength of a rule) is calculated as follows:\n\nMeanwhile, the output of Layer 3 (it is also known as the normalized firing strength) is calculated as follows:\n\nThe output of Layer 4 (it is also known as an adaptive node) is calculated as follows:\n\nwhere r i , q i , and p i define the consequent parameters of the node i. Layer 5 contains only one node; its output is computed as: \n\nFlower Pollination Algorithm is an optimization method proposed by Yang [38] . It simulates the transfer of flowers' pollen by pollinators in nature. This algorithm utilizes the two types of pollination (i.e., self-pollination and cross-pollination). In self-pollination, the pollination occurs with no pollinators, whereas, in cross-pollination, the pollens are moved between different plants. In more detail, the self-pollination can be represented as a local pollination while the cross-pollination can be called global pollination. The global pollination or cross-pollination can be mathematically formed as follows:\n\nwhere x t i defines the pollen i at iteration t. L denotes the pollination's strength or the step size. F * is the target position or best solution. In some cases, insects can fly with different distance steps for a long space; therefore, Levy fly distribution is applied to simulate this movement. where λ = 1.5. Γ(λ) denotes the gamma function. This distribution is available for large steps s > 0. The self-pollination or local pollination can be mathematically formed as follows:\n\nwhere x t i and x k i represent pollens from different flower in the same plant. in the range [0,1] The process of pollination can be done using cross-pollination or self-pollination. Therefore, the random variable p, in the range [0, 1], is used to determine this process. SSA is an optimization technique introduced by [48] . It simulates the Salps' behavior in nature. This behavior is called salp chain. The mathematical model of SSA begins by splinting its population into a leader group and followers group. The leader is the front salp, whereas, the followers are the other salps. The search space is determined in n-dimensions with n variables. Equation (10) works to update the salps' positions. where x 1 j denotes the leader's position in j-th dimension. F j is the target position. ub j and lb j represent the max and min bounds, respectively. c 2 and c 3 denote random numbers in [0, 1]. c 1 is an important parameter; it balances between the exploration and exploitation phases. It is computed as follows:\n\nwhere the current loop number is t and the max loop' number is t max . Then, the followers' position is updated as follows:\n\nwhere x i j defines the i-th position of the follower in j-th dimension. i > 1. This section explains the proposed FPASSA-ANFIS method. It is a time series method for forecasting the confirmed cases of the COVID-19, as given in Figure 2 . The FPASSA-ANFIS utilizes the improved FPA to train the ANFIS model by optimizing its parameters. The FPASSA-ANFIS contains five layers as the classic ANFIS model. Layer 1 contains the input variables (the historical COVID-19 confirmed cases). Whereas Layer 5 produces the forecasted values. In the learning phase, the FPASSA is used to select the best weights between Layer 4 and Layer 5. The FPASSA-ANFIS starts by formatting the input data in a time series form. In our case, the autocorrelation function (ACF) was considered. ACF is one of the methods applied to find patterns in the data; it presents information about the correlation between points separated by various time lags. Therefore, in this paper, the variables with ACF greater than 0.2 are considered i.e., 5-lags. Besides, the training data contains 75% of the dataset, whereas the testing data contains 25% of them. The number of clusters is defined by the fuzzy c-mean (FCM) method to construct the ANFIS model. The parameters of the ANFIS model are prepared by the FPASSA algorithm. In the training phase, the calculation error (as in Equation (13)) between the real data and the predicted data is used to evaluate the parameters' quality. where T is the real data, and P is the predicted data. N s is the sample length. The smaller values of the objective function indicate good ANFIS's parameter. On the other hand, the updating phase of the followers' positions in the SSA algorithm is applied to improve the global pollination phase in the FPA algorithm. In this improvement, there is a random variable (r) used to switch between both phases. If r > 0.5, then the operators of the SSA is used; otherwise, the operators of the FPA are used. In general, The FPASSA starts by constructing the population (X); afterward, the objective function is calculated for each solution. The solution with the lowest error value is saved to the next iteration. This sequence is repeated until meeting the stop condition, which in this paper, is the maximum number of iterations. Then the best solution is passed to train the parameters of the ANFIS model. After finishing the training phase, the testing phase is started with the best solution to compute the final output. The performance of the proposed method is evaluated by comparing the real data with the predicted data using the performance measures. Finally, the FPASSA produces a foretasted value for confirmed cases of COVID-19 in China in the next day. The steps of the proposed FPASSA are presented in Algorithm 1. Input: Historical COVID-19 dataset, size of population N, total number of iterations t max . Divide the data into training and testing sets. Using Fuzzy c-mean method to determine the number of membership functions. Constructing the ANFIS network. Set the initial value for N solutions (X). Return the best solution that represents the best configuration for ANFIS. Apply the testing set to the best ANFIS model. Forecasting the COVID-19 for the next ten days. This section presents the description of the used dataset, the performance measures, the parameter setting for all methods, the experiment results, and discussions. The main dataset of this study is COVID-19 dataset. It was collected from the WHO website (https: //www.who.int/emergencies/diseases/novel-coronavirus-2019/situation-reports/). It contains the daily confirmed cases in China from 21 January 2020 to 18 February 2020, as shown in Table 1 . We used 75% from the dataset to train the model while the rest is used to test it. Moreover, we evaluated the performance of the proposed method using two datasets of weekly influenza confirmed cases.\nQuestion: Where was the coronavirus discovered?", "role": "user" }, { "content": "Wuhan, China", "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 hydrochlorothiazide therapy on cardiac arrhythmias in African-American men with systemic hypertension and moderate to severe left ventricular hypertrophy . The effect of hydrochlorothiazide therapy on ventricular arrhythmias was studied in 45 hypertensive African-American men with moderate to severe left ventricular ( LV ) hypertrophy . After medication washout , patients were treated with placebo followed by hydrochlorothiazide . Clinical , biochemical , and 48-hour ambulatory electrocardiographic data was collected after each treatment phase . Signal-averaged electrocardiograms were recorded in a subgroup of 24 patients . Average LV posterior wall thickness was 15 +/- 1.1 mm , septum 16 +/- 2 mm , LV mass 420 +/- 90 g , and LV mass index 212 = 51 g/m2 . Systolic blood pressure ( BP ) was 168 +/- 18 mm Hg after the placebo phase and 146 +/- 15 mm Hg after hydrochlorothiazide ; diastolic BP was 103 +/- 6 mm Hg and 89 +/- 9 mm Hg , respectively . Serum potassium decreased significantly from 4.2 +/- 0.4 mmol/L to 3.7 +/- 0.6 mmol/L after hydrochlorothiazide therapy . The average hourly incidence of ventricular premature contractions was 22 with placebo and 25 with hydrochlorothiazide . There were 3 and 1 couplets and 0.2 and 0.2 runs of ventricular tachycardia per patient per hour , respectively . Variables of signal-averaged electrocardiography did not differ between the 2 treatments . Thus , in hypertensive African-American men with moderate to severe LV hypertrophy , hydrochlorothiazide does not worsen ventricular arrhythmias or signal-averaged electrocardiographic variables .", "role": "user" }, { "content": "{\"Intervention\": [\"placebo\", \"hydrochlorothiazide\", \"hydrochlorothiazide therapy\"], \"Outcome\": [\"signal-averaged electrocardiographic variables\", \"cardiac arrhythmias\", \"signal-averaged electrocardiography\", \"Average LV posterior wall thickness\", \"ventricular premature contractions\", \"Signal-averaged electrocardiograms\", \"Clinical , biochemical , and 48-hour ambulatory electrocardiographic data\", \"Systolic blood pressure ( BP )\", \"ventricular tachycardia\", \"Effect\", \"Serum potassium\", \"ventricular arrhythmias\"], \"Participant\": [\"with moderate to severe left ventricular ( LV ) hypertrophy\", \"men\", \"cardiac arrhythmias in African-American men with systemic hypertension and moderate to severe left ventricular hypertrophy\", \"45 hypertensive African-American\", \"subgroup of 24 patients\", \"hypertensive African-American men with moderate to severe LV hypertrophy\"]}", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Changes in parasite traits, rather than intensity, affect the dynamics of infection under external perturbation\nArticle:\nAbstract:\nUnderstanding the mechanisms that generate complex host-parasite interactions, and how they contribute to variation between and within hosts, is important for predicting risk of infection and transmission, and for developing more effective interventions based on parasite properties. We used the T. retortaeformis( TR)-rabbit system and developed a state-space mathematical framework to capture the variation in intensity of infection and egg shedding in hosts infected weekly, then treated with an anthelminthic and subsequently re-challenged following the same infection regime. Experimental infections indicate that parasite intensity accumulates more slowly in the post-anthelminthic phase but reaches similar maximum numbers. By contrast, parasite EPG( eggs per gram of feces) shed from rabbits in the post-treatment phase is lower and less variable through time. Inference based on EPG alone suggests a decline in parasite intensity over time. Using a state-space model and incorporating all sources of cross-sectional and longitudinal data, we show that while parasite intensity remains relatively constant in both experimental phases, shedding of eggs into the environment is increasingly limited through changes in parasite growth. We suggest that host immunity directly modulates both the accumulation and the growth of the parasite, and indirectly affects transmission by limiting parasite length and thus fecundity. This study provides a better understanding of how within-host trophic interactions influence different components of a helminth population. It also suggests that heterogeneity in parasite traits should be addressed more carefully when examining and managing helminth infections in the absence of some critical data on parasite dynamics.\nIntroduction:\nThe large variation in disease severity and transmission often observed among individuals infected with helminths is strongly determined by the local conditions that incoming and established parasites encounter within the host, in addition to variation in the exposure of hosts to infective stages[1–3]. These conditions are mainly determined by the current and previous immuno-physiological attributes of the host, such as the local immune profile or the level of chemical homeostasis, and ecological parasite processes mostly driven by intensity-dependent competition for resources[1, 4–15], where intensity represents the number of parasites in infected hosts. Host and parasite constraints have been shown to affect both the intensity and the life history of parasites with interactions that frequently lead to non-linear dynamics of infection and complex trade-offs between parasite life-history traits. The within-host regulation of gastrointestinal helminths, and the consequences for the dynamics and life history of the parasite, remains a subject of ongoing research[4, 16–19]. The fundamental challenge is to provide convincing evidence for the mechanisms that affect the intensity of infection and the way parasite traits( i. e. development, fecundity and shedding) adjust to these changes. Ultimately, the understanding of these processes under ecological and immunological forces, and their relative contribution to the observed phenotype of infection, is important for explaining the often large variation in the host’s ability to control the infection. A useful approach to disentangling the contribution of these two forces is by examining how parasites adjust to external perturbations, such as anthelminthic treatments. Anthelminthics are commonly delivered over one to several days( depending on the type of treatment) and parasites are removed within hours or multiple days; however, in endemic areas reinfection is inevitably the norm. Because of this, by altering the number of parasites competing for host resources and/or the strength of intensity-dependent immune responses[20, 21] treatments lead to patterns of infection and re-infection that can be fundamentally different[2, 4, 22] than treatment-free settings. Indeed, the transient disruption caused by the drug treatment resets the background environment by placing the initial parasite population to 0, thus upon re-infection the new incoming parasites face a primed environment where competition for resources is minimal and/or the immunity still holds some memory from the previous history of infection. Any change in the dynamics of parasite establishment from the pre-treatment to the post-treatment phase should be due to the additional effects of memory in the immune response. In contrast, no changes in parasite dynamics between treatments should be indicative of a regulation by ecological forces driven by intensity-dependent processes in the parasite population. Irrespective of the anthelminthic treatment, following the constant exposure to infective stages and the accumulation of parasites within the host, the intensity of infection will exhibit a logistic growth with host age if regulated by intensity-dependent ecological forces, such as processes of competition for space and food[4]. A hump-shaped age-intensity profile, where older hosts carry fewer parasites, is indicative of an immune response that regulates the parasite population with a strength that increases proportionately with the force of infection[1, 20]. Other processes can generate this convex profile[2, 22] but here we address this shape as an immunity-generated process. Our previous observations in the Trichostrongylus retortaeformis—rabbit system have conformed to the latter pattern, indicating immune regulation[12, 23–26]. The interpretation of the relative contribution of these two forces—ecological limitation through parasite competition for resources and host immune regulation—have conventionally relied on either cross-sectional measures of parasite intensity or longitudinal measures of egg shedding. However, both of these approaches have limitations. For instance, the common method of using age-related, cross-sectional measures of parasite intensity, from dead or drug-treated hosts, assumes that sequential cross-sectional observations in different animals approximate the temporal progression of parasite intensity in a single or average animal and is indicative for a time series of infection[1, 10, 21, 22, 27–31]. This necessarily averages out the within-host heterogeneity in parasite dynamics and traits, as it assumes that the unobservable or hidden dynamics of infection in individuals measured at later times behave similarly to those measured at earlier times. This problem can be circumvented by using time series of parasite shedding, which allows observations of individual host variation during the course of the infection. However, this method requires the assumption that the amount of eggs or larvae shed by a host into the environment is directly proportional to the actual parasite burden[32, 33] and remains constant over time. Yet, an increasing number of studies have shown that this assumption is rarely confirmed or correct[34–43] and the view that the infection-shedding relationship remains constant over time can lead to wrong conclusions. Indeed, any feedback between parasite intensity and fecundity/shedding, or between-host immunity and parasite fecundity, would violate this assumption. The apparent limitations in the conventional measures of within-host parasite dynamics reflect two challenges in the inference for dynamical systems: the states of interest are often not directly measurable( e. g. parasite burden prior to sacrifice) and/or they are only indirectly measurable( e. g. egg shedding as an indicator of adult parasite burden). State-space or hidden Markov models provide a statistical framework that links a dynamical model of the progression of unobservable states through time to observable measures[44–47]. This class of statistical models has increasingly been used to study the dynamics of infectious diseases at the host population level, where the true incidence of infection is only partially observable through a subset of cases reported through surveillance[48–50]. To understand the relative contribution of immunity and parasite ecological constraints to patterns of helminth intensity, fecundity and shedding, we developed a within-host state-space model of parasite dynamics using a laboratory experiment and the Trichostrongylus retortaeformis( TR)-rabbit system. By linking a dynamic model to an observation model and by combining cross-sectional data on TR intensity, body length and fecundity with longitudinal data on egg shedding we are able to reconstruct the unobservable dynamics of infection within each individual and make inference on the underlying dynamic processes. Specifically, to evaluate changes in TR dynamics and traits following external perturbations and provide a mechanism of regulation we compare the model performance before and after anthelminthic treatment and under constant exposure to infective stages.\nDiscussion:\nOur modeling framework provides a novel approach to the study of helminth infections at the host level. Indeed, while offering a parsimonious explanation of the forces driving the dynamics of the parasite it also identifies the traits that are primarily constrained and the processes that generate such patterns. Moreover, the impact of external perturbations, namely anthelminthic drug treatment, is well captured in the simulated dynamics of infection. Ultimately, although this modeling approach needs information both on longitudinal and cross-sectional data it can provide quantitative predictions on changes in helminth intensity and traits under testable external disturbance.", "role": "user" }, { "content": "Host-parasite interactions frequently lead to complex dynamics of infection that can be difficult to explain when parasite data are not accurate or complete , which is often the case in natural systems . We used the helminth-rabbit study case and developed a state-space mathematical model to capture the variation in intensity of infection and egg shedding in an experimental trial where hosts were infected weekly , then treated with an anthelminthic and subsequently re-challenged following the same infection regime . Simulations indicate that hosts control the parasite proportionally to the accumulated force of infection and intensities decrease both in the pre- and post-treatment phase . The peak and mean intensity of infection is similar before and after treatment; however , the degree of egg shedding declines proportionately with parasite body length and both traits are lower in the post- than the pre-treatment phase . The intensity of infection fails to adequately explain the variation in the degree of shedding within and between hosts . Instead , this pattern is captured by changes in parasite body length . More attention should be given to the host-parasite interactions within hosts and the impact of external perturbation on the dynamics of infection and transmission .", "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\nCiprofloxacin induces an immunomodulatory stress response in human T lymphocytes. Exposure of cells to adverse environmental conditions invokes a genetically programmed series of events resulting in the induction of specific genes. The fluoroquinolone antibiotic ciprofloxacin has recently been reported to upregulate interleukin-2 (IL-2) gene induction. In the present investigation, the effect of ciprofloxacin at supratherapeutic concentrations on immediate-early (< 2 h) gene expression in primary human peripheral blood lymphocytes was studied with Northern blots. In addition, transcriptional activity of IL-2 and metallothionein enhancer and promoter regions and transcription factors AP-1, NF-kappaB, and NF-AT were analyzed by chloramphenicol acetyltransferase (CAT) and electrophoretic mobility shift assays, respectively. The concentration of c-fos, c-jun, c-myc, junB, and fra-1 mRNAs was increased in activated peripheral blood lymphocytes incubated with ciprofloxacin compared to that in untreated controls. Ciprofloxacin increased CAT activity in stimulated lymphocytes transfected with plasmids containing either the IL-2 or metallothionein enhancer. Furthermore, among the transcription factors tested, AP-1 activity was increased in stimulated purified T helper lymphocytes incubated with ciprofloxacin compared to drug-free controls. Taken together, ciprofloxacin increased the levels of immediate-early transcripts, enhanced IL-2 and metallothionein promoter induction, and upregulated AP-1 concentrations in primary lymphocytes, reflecting a program commonly observed in mammalian stress responses.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [\"human T lymphocytes\", \"primary lymphocytes\", \"plasmids\", \"primary human peripheral blood lymphocytes\", \"drug - free controls\", \"stimulated purified T helper lymphocytes\", \"peripheral blood lymphocytes\"], \"DNA\": [\"metallothionein enhancer and promoter regions\", \"metallothionein enhancer\", \"specific genes\"], \"Protein\": [\"IL - 2\", \"CAT\", \"interleukin - 2\", \"AP - 1\", \"NF - AT\", \"NF - kappaB\", \"chloramphenicol acetyltransferase\", \"transcription factors\", \"metallothionein\"], \"RNA\": [\"c - fos , c - jun , c - myc , junB , and fra - 1 mRNAs\", \"immediate - early transcripts\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nendometriosis , the presence of endometrial glands and stroma at extra - uterine sites , is common among reproductive age women , prevalence ranging 315% ( kim et al . , 2014 ) .\nthe etiology of endometriosis is unknown but proposed mechanisms include retrograde menstruation , hematogenous or lymphatic dissemination , and coelomic metaplasia .\nendometriosis is most frequently identified on the ovaries , rectovaginal septum , and broad and uterosacral ligaments ( loizzi et al . , 2015 ) .\nendometriosis may also involve extra - pelvic organs including the small and large intestine , abdominal scars , the urinary system , and the lung / diaphragm .\nthe bladder is the most common site of occurrence within the urinary system , though it is involved in less than 1% of extra - ovarian cases ( dadhania et al . , 2015 ,\nstudies report an elevated risk of ovarian cancer in women with endometriosis , rates ranging 0.31.6% .\nspecifically , malignant transformation of endometriosis is associated with clear cell ovarian cancer ( kim et al . , 2014 ) . the majority ( 80% ) of malignant transformations\nhowever , clear cell adenocarcinoma ( cca ) arising from endometriosis has also been reported in non - gynecologic organs including the bladder , abdominal wall , diaphragm , and rectum ( loizzi et al . , 2015 , mann et al . , 2012 ,\nwhen it occurs , 70% and 4.5% of malignancies are of endometrioid and cell clear histology , respectively ( okazaws et al . , 2014 ) .\nonly 8 cases of cca arising from vesical endometriosis have been reported in the english literature .\nwe present a case of cca arising within vesical endometriosis in the absence of ovarian endometriosis .\na 44-year - old para 0 , with a history of urge urinary incontinence and recurrent urinary tract infections , presented with urinary frequency , incontinence , and hematuria . in 2008 ,\nthe patient was lost to follow up until 2015 , when she re - presented with recurrent symptoms .\npatient underwent work - up for cancer including cystoscopy with biopsies and urine cytology which identified a tumor at the bladder neck and atypical cells , respectively .\nrenal ultrasonography showed normal kidneys and a 3 2 3 cm\nfollowing , she underwent a transurethral resection of bladder tumor ( turbt ) , the pathology of which revealed invasive clear cell adenocarcinoma involving the muscularis propria .\nmicroscopic examination of the tissue specimen showed a tumor composed of high grade adenocarcinoma with abundant clear cytoplasm , pleomorphic nuclei , and frequent hobnail cells .\nthe tumor cells were arranged in tubulocystic , papillary , and solid patterns and abundant mitotic figures were identified .\nseveral foci of bland cuboidal / columnar cells lined microcysts were seen , consistent with endocervicosis / mullerian rests .\nfocally , the clear cell adenocarcinoma involved the endocervicosis , raising the possibility of tumor arising from the mullerian rests in the bladder .\nimmunohistochemically , the tumor cells were positive for ae1/ae3 , ck7 , ca-125(focal ) , napsin - a , pax-8 , p-504s , and p16 , and negative for cd20 , er , pr , ttf-1 , wt-1 , cea - r , p63 , mammaglobin , cdx-2 , p53 , cd10 and vimentin ( fig . 1a \nd ) . the immunoprofile itself could not distinguish primary bladder clear cell adenocarcinoma from metastatic clear cell adenocarcinoma from the gynecologic tract .\ntransvaginal ultrasonography revealed a 9 5 6 cm uterus with a 3 3 4 cm exophytic fundal myoma .\na staging ct scan demonstrated diffuse bladder wall thickening and a mural soft tissue mass along the posterior bladder but no evidence of metastatic disease .\nfollowing multi - disciplinary tumor board discussion including urology , medical oncology , and gynecologic oncology , the decision was made to proceed with anterior exenteration , ileal conduit , bilateral salpingo - oophorectomy , and pelvic lymph node dissection .\nfinal pathology revealed rare mullerian rests in the bladder wall , ureters , and the surrounding soft tissue in the form of endometriosis , endocervicosis , or endosalpingiosis ( mullerianosis ) . no residual bladder tumor was identified ( fig . 1e \nthe lack of primary gynecologic tumor and close association with vesical mullerian rests suggest this t2b , n0 , m0 ( stage ii ) clear cell adenocarcinoma of the bladder is of mullerian origin .\nthe patient 's postoperative course was complicated by clostridium difficile colitis and right femoral nerve neuropraxia requiring acute rehabilitation at discharge .\nct imaging identified a urinoma , which was managed with intravenous antibiotics and percutaneous drainage .\nafter interdisciplinary meeting , the recommendation for treatment included adjuvant carboplatin and paclitaxel though the patient declined further treatment .\nshe is currently being followed by urology and gynecologic oncology with urine cytology , serum comprehensive metabolic panel , and ct imaging of the chest , abdomen , and pelvis every 36 months .\nsecondary malignancies presenting with metastases from other sites must be ruled out as secondary adenocarcinomas are more prevalent than primary bladder adenocarcinomas .\nprimary bladder adenocarcinomas demonstrate pure glandular differentiation ( enteric , mucinous , signet ring , clear cell , other ) , yet derive directly from bladder urothelium ( dadhania et al . , 2015 ) .\nwhether clear cell adenocarcinomas ( ccas ) of the bladder are of mullerian origin ( like ccas of the female genital tract ) , of mesonephric origin , or derived from glandular differentiation of the urothelium is of current debate ( oliva et al . , 2002 ) .\nthey usually arise in the urethra but when found in the bladder , most commonly occur at the trigone or posterior wall . grossly\n, the tumor may have a papillary , exophytic , or polypoid appearance ( roy & parwani , 2011 ) .\nmany bladder ccas are histologically and immunohistochemically similar to ccas of the female genital tract ( dadhania et al . , 2015 ) .\nhistologically , these tumors demonstrate solid , papillary , or tubulocystic growth patterns , which may be lined by flat , cuboidal or columnar cells with clear or eosinophilic glycogen - containing cytoplasm .\nhobnail cells , severe atypia , and frequent mitoses are common ( dadhania et al . , 2015 , roy and parwani , 2011 ) .\nimmunohistochemistry often demonstrates positivity for ca-125 , pax8 , pancytokeratin , and ck7 ( roy & parwani , 2011 ) .\ndefinitive treatment included radical surgery , chemotherapy , and radiotherapy in 18% , 18% , and 21% of cases , respectively ( lu et al . , 2012 ) .\nthe role of surgery , chemotherapy , and radiotherapy remains to be delineated for this rare entity .\ncurrent literature suggests an association between cca and endometriosis ; the majority of this data comes from the gynecologic literature as malignant transformation of extra - gonadal endometriosis is rare and only 4.5% of these transformations lead to cca ( okazaws et al . ,\novarian cancer reportedly occurs in 0.31.6% of women with endometriosis . a 2014 meta - analysis reported a relative risk of ovarian cancer of 1.265 ( 95% ci 1.2141.318 ) in women with and without endometriosis .\nas expected , ccas were more common ( rr 2.606 , 95% ci 2.2253.053 ) in endometriosis - associated cancers ( kim et al . , 2014 ) .\nthese recommendations are largely extrapolated from studies in serous ovarian cancer . because it is relatively rare ,\nlarge prospective trials evaluating this , and other , treatment paradigms have not been performed in ovarian cca .\nretrospective studies suggest that ovarian ccas demonstrate chemoresistance and may be associated with poorer survival than their serous counterparts ( del carmen et al . , 2012 ) .\nfurther investigation is required to delineate the role of multi - modality treatment in ovarian cca .\nurologic literature does not support adjuvant chemotherapy in patients with node - negative transitional cell carcinomas following radical surgery .\nhowever , the histology and immunohistochemical profile of this tumor support a mullerian , as opposed to urothelial , origin . in this case , the high grade cca , arising in background of endometriosis , was indistinguishable from ccas of the female genital tract . only eight cases of vesical cca arising from endometriosis have been previously reported in the english literature .\ngiven the mullerian origin , this case was reviewed by the gynecologic oncology tumor board . extrapolating from the gynecologic literature ,\nthe recommendation was made for adjuvant carboplatin and paclitaxel though the patient declined further treatment .\nfurthermore , the approach to the adnexa in patients with no adnexal abnormalities needs to be carefully evaluated with each individual patient . performing bilateral salpingo - oophorectomy ( bso ) in patients with endometriosis\nis considered part of definitive management and is usually standard of care in order to maximally decrease symptoms .\nbso may be considered in patients with cca of the genito - urinary tract , regardless of ovarian involvement .\nindividual patient factors must be balanced with acog recommendations for ovarian preservation during patient counseling .\nfurther studies are needed to clarify the optimal treatment paradigm for bladder clear cell adenocarcinomas .\nour case highlights the need for multi - disciplinary approach among urology , medical oncology , and gynecologic oncology in patients with ccas of the genito - urinary tract .\nwritten informed consent was obtained from the patient for publication of this case report and accompanying images .\na copy of the written consent is available for review by the editor - in - chief of this journal , upon request .", "role": "user" }, { "content": "endometriosis is associated with increased rates of ovarian , particularly clear cell , adenocarcinomas . \n malignant transformation of ovarian endometriosis is most common but rare cases have been reported in the bladder , abdominal wall , diaphragm , and rectum . \n we present the case of a 44-year - old female with vesical clear cell adenocarcinoma arising in a background of endometriosis in the absence of other pelvic endometriosis . \n the malignancy was diagnosed on transurethral resection of bladder tumor and managed with radical surgery . \n histology and immunohistochemical findings were consistent mullerian origin and indistinguishable from similar tumors arising in the female genital tract . \n extrapolating from the gynecologic literature , the recommendation was made for adjuvant chemotherapy . \n further studies are needed to clarify the optimal treatment paradigm for ovarian and bladder clear cell adenocarcinomas .", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: Reprogramming to Pluripotency Can Conceal Somatic Cell Chromosomal Instability\nArticle:\nAbstract:\nThe discovery that somatic cells are reprogrammable to pluripotency by ectopic expression of a small subset of transcription factors has created great potential for the development of broadly applicable stem-cell-based therapies. One of the concerns regarding the safe use of induced pluripotent stem cells( iPSCs) in therapeutic applications is loss of genomic integrity, a hallmark of various human conditions and diseases, including cancer. Structural chromosome defects such as short telomeres and double-strand breaks are known to limit reprogramming of somatic cells into iPSCs, but whether defects that cause whole-chromosome instability( W-CIN) preclude reprogramming is unknown. Here we demonstrate, using aneuploidy-prone mouse embryonic fibroblasts( MEFs) in which chromosome missegregation is driven by BubR1 or RanBP2 insufficiency, that W-CIN is not a barrier to reprogramming. Unexpectedly, the two W-CIN defects had contrasting effects on iPSC genomic integrity, with BubR1 hypomorphic MEFs almost exclusively yielding aneuploid iPSC clones and RanBP2 hypomorphic MEFs karyotypically normal iPSC clones. Moreover, BubR1-insufficient iPSC clones were karyotypically unstable, whereas RanBP2-insufficient iPSC clones were rather stable. These findings suggest that aneuploid cells can be selected for or against during reprogramming depending on the W-CIN gene defect and present the novel concept that somatic cell W-CIN can be concealed in the pluripotent state. Thus, karyotypic analysis of somatic cells of origin in addition to iPSC lines is necessary for safe application of reprogramming technology.\nIntroduction:\nThe potential to restore pluripotency to mature somatic cells has generated new prospects in the establishment of patient-specific regenerative therapies and has also offered new options for more advanced and specific modeling of human disease[1],[2]. However, several obstacles remain prior to the therapeutic application of iPSCs, including the risk of introducing loss of genomic integrity[3],[4]. Recent studies revealed that somatic cell reprogramming introduces changes at the nucleotide level. Both cell culture length and conditions were identified as key determinants of this type of genetic variation[5],[6]. In contrast to changes at the nucleotide level, reprogramming seems to be less permissive to certain types of structural chromosome damage, such as short telomeres and double strand DNA breaks[7]. Cells with these kinds of aberrations are thought to be eliminated during the early stages of reprogramming by induction of p53-dependent apoptosis[7]. Reprogrammed cells have successfully been generated from somatic cells that undergo stable inheritance of an abnormal number of chromosomes, such as Down syndrome. This implies that aneuploidy( an abnormal number of chromosomes) is not a barrier to reprogramming[8]. However, the extent to which defects that promote the continuous reshuffling of whole chromosomes during mitosis, a condition referred to as whole chromosome instability( W-CIN)[9], interfere with efficient reprogramming of somatic cells is unknown. The molecular mechanisms that underlie chromosome segregation and that safeguard the process are highly complex and remain incompletely understood[10],[11]. In budding yeast, over one hundred genes are known to cause chromosomal instability when defective, including genes implicated in chromosome condensation, sister chromatid cohesion and decatenation, kinetochore assembly and function, spindle formation, mitotic checkpoint control and attachment error correction[12],[13]. Many more genes are expected to contribute to chromosomal stability in mammals, although only a limited number have been identified to date[9],[14]. To begin to address the impact of numerical chromosome instability, we examined the impact of two distinct W-CIN gene defects on somatic cell reprogramming. The first defect involves the BubR1 gene, which encodes a core component of the mitotic checkpoint, an intricate surveillance mechanism that acts to delay anaphase onset until all duplicated chromosomes are properly attached to spindle microtubules and aligned in the metaphase plate[15]–[18]. The role of BubR1 in the mitotic checkpoint is to bind to and inhibit Cdc20, a key activator of the anaphase-promoting complex/cyclosome( APC/C) that drives cells into anaphase by targeting cyclin B1 and securin for degradation by the proteasome[19],[20]. In addition, BubR1 functions at kinetochores to stabilize microtubule-chromosome attachments[20],[21]. While complete loss of BubR1 results in cell death by mitotic catastrophe, cells with low amounts of BubR1 are viable despite frequent chromosome missegregation and development of near-diploid aneuploidies[22]. The second defect involves the RanBP2 gene, which encodes a giant nuclear pore complex( NPC) protein with SUMO E3 ligase activity[23]. At the onset of mitosis, when the nuclear envelope disintegrates and NPCs disassemble, RanBP2 becomes an important regulator of topoisomerase II alpha( hereafter referred to as Top2a), an enzyme that decatenates the centromeric DNA regions of duplicated chromosomes[24]. Accumulation of Top2a at mitotic centromeres is dependent on sumoylation by RanBP2. Complete inactivation of RanBP2 gene expression results in cell death, but cells with low levels of RanBP2 survive and proliferate normally despite incomplete DNA decatenation, frequent chromosome missegregation and aneuploidization[24]. Here, we show that both W-CIN gene defects are compatible with reprogramming. Unexpectedly, however, the two genetic defects had contrasting effects on the genomic integrity of the reprogrammed cells, with RanBP2-insufficient MEFs generating karyotypically normal and chromosomally stable iPSCs and BubR1-insufficient MEFs almost exclusively yielding aneuploid and chromosomally unstable iPSC clones. These data indicate that aneuploid cells can be selected for or against during reprogramming depending on the genetic defect driving the chromosome number instability. Furthermore, our data reveal that W-CIN that exists at the somatic cell level can become dormant upon reprogramming, indicating that testing of both iPSCs and the iPSC-founding cells for chromosome number instability will be necessary for the safe application of iPSC technology in regenerative medicine.\nDiscussion:\nAlthough the importance of iPSC technology for regenerative therapies is broadly recognized, several hurdles to their clinical use exist, including the potential of genomic instability. Here we have examined the relationship between somatic cell reprogramming and W-CIN, a type of genomic instability associated with cancer and other human disorders. Our studies provide several important new insights that should improve the efficacy of iPSC use in future clinical applications. First, we demonstrate that W-CIN does not pose a barrier to reprogramming. Second, we show that W-CIN iPSCs are capable of differentiating into all three distinct germ layer cell types. Third, we show that although MEFs with two distinct W-CIN defects efficiently reprogram into iPSCs, they do so with highly contrasting outcomes on chromosome number integrity and stability( Figure 6): our data suggest that BubR1 hypomorphic iPSC clones preferentially originate from aneuploid MEFs, while RanBP2 hypomorphic iPSC clones preferentially stem from MEFs with normal diploid chromosome numbers. Fourth, our data uncovered the fascinating concept that a W-CIN gene defect responsible for severe aneuploidization in somatic cells can become dormant upon reprogramming. The particular W-CIN defect that revealed this concept is RanBP2 hypomorphism. We ruled out that a failure to maintain the RanBP2 hypomorphic status after reprogramming is responsible for restoring high-fidelity chromosome segregation. One possibility is that SUMO E3 ligases other than RanBP2, such as PIAS proteins, redundantly targeting Top2a to inner centromeric regions of duplicated chromosomes[40]–[42]. An alternative explanation might be that Top2a accumulates to inner centromeres in a SUMO independent fashion in pluripotent cells. Regardless of the precise mechanism by which W-CIN can be concealed in iPSCs, the phenomenon itself highlights that it will not only be important to check iPSCs for aneuploidization but also the somatic cells from which they originated. The observation that aneuploid cells within BubR1 hypomorphic MEF cultures undergo preferential reprogramming is puzzling given that BubR1 insufficiency engages the p16Ink4a-Rb and p53-p19Arf pathways[43], both of which have been shown to inhibit reprogramming[7],[28]. Perhaps activation of these tumor suppressor pathways is necessary but not sufficient for the elimination of aneuploid MEFs during the early stages of reprogramming. The observation that BubR1H/H aneuploid MEFs preferentially dedifferentiate raises the possibility that BubR1 might be a key component of a surveillance pathway that prevents aneuploid cells from reprogramming. Interestingly, in earlier studies we have shown that BubR1 levels decrease with aging in various mouse tissues[22],[44],[45]. This, together with the observation that aneuploid MEFs with low amounts of BubR1 readily reprogram into chromosomally unstable iPSCs implies that reprogramming of somatic cells from elderly individuals into karyotypically normal and stable iPSCs may be particularly challenging. It will be interesting to further explore this possibility by testing whether restoration of high BubR1 levels in somatic cells of older individuals would improve iPSC quality. Mitosis is more prone to errors when cells divide in culture as evidenced by the low rates of chromosome missegregation observed in early passage MEFs from wildtype mice[26],[46]. Although the actual cause of such aneuploidies is unknown, it is generally believed that they are induced by cell culture stress[47]. Karyotypically normal mouse ESC lines used in gene targeting experiments are known to acquire severe aneuploidy upon extensive in vitro passaging, indicating that pluripotent cells are also susceptible to cell culture-induced chromosome segregation errors[48]. Our finding that aneuploid cells emerge in iPSC cultures originating from karyotypically normal wildtype MEFs( Table 1) confirms earlier indications that reprogrammed cell lines, like ESC lines, are subject to cell culture induced aneuploidization[49]. Since aneuploidy poses a risk for negative side effects in therapeutic applications, it will be important to devise strategies to avoid it. We find that aneuploidization rates of iPSC clones derived from wildtype MEF cultures can be markedly reduced through subcloning, implying that iPSC cultures contain subsets of cells that are quite resistant to cell culture induced mitotic stress. Thus subcloning might be a pragmatic method to produce iPSC lines with high chromosome integrity.", "role": "user" }, { "content": "iPSC technology has the potential to revolutionize stem-cell based regenerative medicine and would also allow for the production of patient-specific cells for disease modeling and drug discovery . One of the primary safety concerns of iPSCs is genetic instability , which is associated with cancer and various other diseases and includes abnormalities in both chromosomal structure and number . Whereas certain structural chromosome changes have been shown to preclude somatic cell reprogramming , the effect of whole-chromosome reshuffling on this process is completely unknown . Here we show that BubR1 and RanBP2 hypomorphic MEF lines , which are highly prone to erroneous chromosome segregation due to mitotic checkpoint and DNA decatenation failure , respectively , reprogram to pluripotency with normal efficiency . However , while RanBP2 hypomorphic MEFs yielded karyotypically normal iPSC clones with generally low chromosomal instability rates , BubR1 hypomorphic MEFs almost exclusively yielded aneuploid iPSC clones with high instability rates . These data provide important new insights into the genomic integrity requirements during somatic cell reprogramming , and they establish that the safe application of iPSC technology requires screening of both iPSCs and the iPSC-founder cells for chromosome number instability .", "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: We conducted several experiments to compare the proposed detection methods with one of the scene text detection methods (STD) [8], SBD [5] and TLD [6].", "role": "user" }, { "content": "Method", "role": "assistant" } ]

[ { "content": "Based on the abstract below, determine if the claim is supported or contradicted. Output a JSON object with the verdict (\"SUPPORT\" or \"CONTRADICT\") and evidence sentences from the abstract.\n\nClaim: The sars-cov-2-like virus found in captive pangolins from guangdong should be better sequenced .\n\nText:\nViruses closely related to SARS-CoV-2, which is the virus responsible of the Covid-19 pandemic, were sequenced in several Sunda pangolins (Manis javanica) seized in the Guangdong and Guangxi provinces of China between 2017 and 20191-3.\nThese viruses belong to two lineages: one from Guangdong (GD/P) and the other from Guangxi (GX/P).\nThe GD/P viruses are particularly intriguing as the amino-acid sequence of the receptor binding domain of the spike protein is very similar to that of the human SARS-CoV-2 virus (97.4%)2.\nThis characteristic suggests that GD/P viruses are capable of binding human ACE2 receptor and may therefore be able to mediate infection of human cells.\nWhereas all six GX/P genomes were deposited as annotated sequences in GenBank, none of the two GD/P genomes assembled in previous studies2,3 are currently available.\nTo overcome this absence, I assembled these genomes from the Sequence Read Archive (SRA) data available for SARS-CoV-2-like viruses detected in five captive pangolins from Guangdong.\nI found the genome assemblies of GD/P virus of poor quality, having high levels of missing data.\nAdditionally, unexpected reads in the Illumina sequencing data were identified.\nThe GD/P2S dataset2 contains reads that are identical to SARS-CoV-2, suggesting either the coexistence of two SARS-CoV-2-like viruses in the same pangolin or contamination by the human virus.\nIn the four other GD/P datasets1 many mitochondrial reads from pangolin were identified, as well as from three other species, namely, human, mouse and tiger.\nImportantly, I only identified three polymorphic nucleotide sites between the five GD/P sequences.\nSuch low levels of polymorphism may reasonably be accounted for by sequencing errors alone, thus raising the possibility that the five pangolins seized in Guangdong in March 2019 were infected by the same virus strain, most probably during their captivity.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"To overcome this absence, I assembled these genomes from the Sequence Read Archive (SRA) data available for SARS-CoV-2-like viruses detected in five captive pangolins from Guangdong.\", \"The GD/P2S dataset2 contains reads that are identical to SARS-CoV-2, suggesting either the coexistence of two SARS-CoV-2-like viruses in the same pangolin or contamination by the human virus.\"]}", "role": "assistant" } ]

[ { "content": "Write an abstract for this chemistry paper.\n\nTitle:\nRare-Cell Enrichment by a Rapid, Label-Free, Ultrasonic Isopycnic Technique for Medical Diagnostics**\n\nPaper sections:\n\n<p>Parasitic infections continue to exert a disproportionate burden on the world's poorest people. Hundreds of millions of people are infected with parasites that cause diseases like malaria and trypanosomiasis (HAT). In many cases of HAT there are fewer than 100 parasites mL−1 of blood, and serological and molecular tests are not considered of sufficient efficacy to offer positive diagnosis.1 Thus enriching these parasites from the blood of individuals with very low parasitemias will be important, if the declared intention of the World Health Organization to eliminate such diseases by 2030 is to be reached.2</p><p>In general, existing techniques available for enrichment of samples—whether for the identification of infectious diseases or for other acute or chronic pathologies—either exploit differences in mechanical properties, in immunologic targets, or in other affinity-based receptor–ligand interactions. Some of these methods, such as centrifugation, rely on the innate physical properties of the cell (such as density) to provide the mechanism of separation. Others, however, such as magnetic-activated cell sorting or fluorescent-activated cell sorting, require a labeling strategy.3 Separation techniques for diagnosis in resource-poor environments are difficult to implement particularly when complex chemical reactions are required for labeling, or where the cost of the instrumentation or the infrastructure required is high.4 As such, the development of a low-cost, low-power, label-free technology, which can be used with fingerprick blood sample, is paramount.</p><p>To achieve this, we have established an innovative technique based on an acoustically actuated microchip (Figure 1 a). The technique has been implemented in hand-held instrumentation which can be battery powered. In a first example, we study the performance of the microchip by enriching the circulating ring stage of Plasmodium falciparum in malaria-infected red blood cells (iRBCs). It is noteworthy that it is only the ring stage of this Plasmodium species that circulates in the peripheral blood, and is thus available within a fingerprick of blood; It is therefore important that any diagnostic or enrichment technique can demonstrate the separation of this specific parasite stage. Our method is based on developing unique flow patterns generated by the interaction of surface acoustic waves (SAWs) with blood, which, when coupled with a density gradient akin to that used in isopycnic techniques, results in the separation of parasites and parasite-infected cells from non-infected cells (Figure 1 b,c and Video 1 in the Supporting Information). Only a few microliters of blood are required, without the need for tubes, pumps, or centrifuges. Current standard methods are discussed in Note 1 in the Supporting Information</p><p>a) Photograph of the device comprising a slanted-finger interdigitated electrode (SFIDT) on LiNbO3. The surface acoustic wave (SAW) is generated at a defined position asymmetrically with respect to the drop of blood, thereby inducing a rotational motion within the drop. Scale bar: 3 mm. b) Photographs of a droplet of blood before (left) and after (right) actuation with SAW (3 s). In the actuated droplet, the red blood cells (RBCs) are concentrated in the middle, while infected RBCs (iRBCs) are enriched at the periphery. Scale bars: 1.5 mm. c) Fluorescent micrographs of the enriched iRBCs at the periphery (left) and concentrated RBCs in the center of the drop (right). Acridine orange (1.5 μg mL−1) was added to the solution to stain the parasites. Scale bars: 100 μm.</p><p>More challenging is the diagnosis of sleeping sickness or HAT, which is a deadly parasitic disease endemic in sub-Saharan Africa, and where the detection of parasite levels of 100 to 10 000 trypanosomes mL−1 of blood is necessary (the limit of detection using a thick blood smear only reaches 5000 trypanosomes mL−1\n5). Immunodiagnostics or traditional stains are not effective for the large number of patients with low parasitemia, who are consequently neither diagnosed nor treated.6 Identifying and treating those patients with subclinical parasite burdens is key to achieving the elimination of HAT.2 Realizing the potential to bring such diagnostic assays away from centralized laboratories to point-of-care settings and implementing tests to resource-limited settings will underpin future disease control strategies.7</p><p>Here, we describe a method that involves actuating fluid on a low-cost, disposable chip by means of a SAW.8 When a drop of blood is placed in the path of this SAW, the mechanical waves refract, generating fluid streaming.8, 9 Important applications have already emerged from such acoustic technologies in the field of diagnostics such as SAW-based immunoassays10 and nucleic acid amplification.11 We now demonstrate a step change in diagnostic sample processing, providing a new suitable format for the ultrasensitive analysis of blood from a fingerprick sample.</p><p>The technique relies upon controlling the shape of the acoustic field to generate a unique pattern of fluid streaming within the blood. Asymmetric actuation of the drop on the surface of the piezoelectric substrate with the SAW (Figure 1 a) causes a circular rotational motion, inducing secondary flows (Figure 2 a) in a manner similar to Batchelor flows12–15 (see Note 2 in the Supporting Information). Here we have used a slanted finger interdigitated electrode (SFIDT; Figure 1 a) to create a narrow path of propagation, providing the asymmetry in the propagation of the waves.16</p><p>Characterization of the separation mechanism using 5 μm fluorescent beads: silica (red, ρ=2 g cm−3) and polystyrene (green, ρ=1.05 g cm−3). a) Flows induced by the SAW within the drop at the beginning of the process, when the beads are distributed in the liquid. b) After actuation, for ρf=1 g cm−3, both types of beads were concentrated in the center of the drop as shown in the micrograph (c). d) For ρf=1.160 g cm−3, the lighter polystyrene beads were distributed at the periphery (e). Scale bars: 300 μm.</p><p>A model system consisting of fluorescent microbeads of two different densities was first used to characterize the method. This showed clear separation between the dense beads, which accumulated in the middle of the drop and the less-dense beads, which were carried to the periphery (Figure 2 c,e). In detail, when the density of the sample matrix was lower than that of both types of beads, all the beads collected in the center of the drop (Figure 2 b,c). However, when the density of the sample matrix was lower than that of the red beads but higher than that of the green beads, the buoyancy (FB) and the drag force (FD) of the green beads was were sufficiently strong to overcome gravity (Fg), lifting only the green beads into the flow field (Figure 2 d,e and Note 3 in the Supporting Information). As a consequence, the more dense red beads (Figure 3) were accumulated in the center of the droplet whilst the lighter green beads were enriched at the periphery. The enriched material was then easily isolated and analyzed.</p><p>Diagram of the flow pattern within the droplet. The SAW induces streaming in the drop and a secondary flow brings the particles to the center of the drop. The two lower diagrams show the forces acting on the RBCs and iRBCs for different values of ρf. When ρiRBC≤ρf<ρRBC, the buoyancy (FB) and drag force (FD) overcome gravity (Fg) and lift the iRBCs but not the RBCs.</p><p>It is already established that infection of RBCs by P. falciparum causes changes in the physical properties of RBCs, altering their surface biochemistry, elasticity, volume, and density.17 The densities of RBCs infected with P. falciparum (1.077–1.080 g cm−3) are lower than those of uninfected RBCs (1.080–1.110 g cm−3).18, 19 The enrichment system was operated using parasite-infected RBCs (iRBCs), initially containing a mixture of the different asexual stages of the parasite. While the enrichment of the infected blood cells was not dependent on the frequency of the SAW (Figure S1 in the Supporting Information), we showed that there was an optimum input power (between 65 to 250 mW) for densities of the sample above 1.083 g cm−3 (Figure 4 a,b). Under these conditions, a critical fluid flow velocity was achieved which generated sufficient drag force to lift the iRBCs into the flow patterns shown in Figure 3. Stronger streams generated at powers above 250 mW also lifted uninfected RBCs, negating the enrichment process (see Figure 4 b).</p><p>a) The acoustic enrichment of P. falciparum ring-stage parasites as a function of the density of the solution (at 10 MHz, 100 mW, 3 s). Controls indicate the parasitemia in the sample used prior to microseparation. Parasitemias were determined by Giemsa staining. The data are means of nine replicates and the error bars are standard errors of the mean. Statistically significant enrichments are marked with * (95 % confidence) and ** (99 %). b) The effect of the input power on the enrichment of P. falciparum for a frequency of 10 MHz and solution density of 1.083 g cm−3. c) Enrichment (ratio of parasitemia after processing, over initial parasitemia) of ring-stage malaria parasites at parasitemias from 2.39 % to 0.0005 % in Histodenz at 15 % (at 10 MHz, 100 mW, 3 s). The control for 0.0005 % parasitemia was determined by serial dilutions.</p><p>As only the ring stage of the parasite is detectable in the circulating blood, we further demonstrated its enrichment at a frequency of 10 MHz, a power of 100 mW, and an optimal density of the solution above 1.083 g cm−3 (Figure 4 a). The limit of the effectiveness of the system was investigated for low parasitemias and it was found that as the parasitemia decreased to 0.0005 % (25 parasites μL−1), the enrichment increased to 100-fold (Figure 4 c). The enriched material could be detected microscopically on a thin smear, which would not have been possible using the blood before enrichment.</p><p>This method of enrichment relies on the contrasting mechanical properties of the different cell types present in the sample. As such, it has the potential to be used for a wider range of diseases. To illustrate the broader applicability, we showed that members of the Trypanosoma genus of protozoa can also be enriched from infected blood at an optimum density of 1.083 g cm−3 (Figure 5 a). Trypanosoma cyclops was enriched from blood on a low-cost platform comprising a disposable chip interfaced with the SAW actuation.10, 11 The sample was positioned on a microchip, onto which phononic structures had been manufactured.13 The phononic lattices provided the capability to filter the acoustic waves, creating the asymmetric flow required for the enrichment process. In this case, we used a conventional \"straight\" interdigitated electrode (IDT) to generate the acoustic actuation (see Methods and Figure S2 in the Supporting Information). The disposable chip, which can be fabricated using low-cost materials (e.g. glass), is coupled onto the reusable piezoelectric actuator. Figure 5 b shows an enrichment factor over 100-fold with a parasitemia of 4.3×10−5 % (or ca. 6 trypanosomes mL−1), again allowing detection of parasites at a level not possible using current techniques in isolation. The results (Figure 5 b) show enrichment comparable to that obtained on the piezoelectric substrate (\"slanted IDT\").</p><p>a) The concentration effect of SAW microseparation on Trypanosoma cyclops suspended in Histodenz as a function of the density of the solution for a frequency of 10.9 MHz. b) Enrichment achieved following SAW microseparation on a slanted IDT and a disposable superstrate (8.8 MHz, 1 W, 5 s) of samples containing trypanosomes in 15 % Histodenz. Parasitemias were determined by hemocytometry in samples taken from the periphery of the droplet following SAW microseparation. The data are means of three replicates; the error bars are standard errors of the mean.</p><p>In conclusion, the use of SAW as described here provides a low-power, low-cost, label-free technique appropriate for resource-limited settings, which could find broad application in both point-of-care and field settings. The power required for enrichment indicates that over 30 000 sample manipulations could be run from the charge of a mobile phone when the test is performed directly on the piezoelectric actuator, and 2000 assays when a disposable device is used. Most simply, in a field setting, the enriched samples could be stained (Giemsa or acridine orange) and examined microscopically, decreasing the limit of detection of the current gold standard for malaria and sleeping sickness by more than two orders of magnitude. Our methods could also work alongside an LED-based field fluorescence microscope20 or a lensfree system, providing both enrichment and detection within the same device. We could also use this method in the diagnosis of other infectious diseases, as well as in the study of circulating tumor cells, which have also been reported to have different mechanical properties.21</p>\n\nSupporting Information\n<p>Supporting information for this article is available on the WWW under http://dx.doi.org/10.1002/anie.201310401.</p>", "role": "user" }, { "content": "One significant challenge in medical diagnostics lies in the development of label-free methods to separate different cells within complex biological samples. Here we demonstrate a generic, low-power ultrasonic separation technique, able to enrich different cell types based upon their physical properties. For malaria, we differentiate between infected and non-infected red blood cells in a fingerprick-sized drop of blood. We are able to achieve an enrichment of circulating cells infected by the ring stage of the parasite over nonparasitized red blood cells by between two and three orders of magnitude in less than 3 seconds (enabling detection at parasitemia levels as low as 0.0005 %). In a second example, we also show that our methods can be used to enrich different cell types, concentrating Trypanosoma in blood at very low levels of infection, on disposable, low-cost chips.", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nSynthesis and biological evaluation of novel pyrrolidine-2,5-dione derivatives as potential antidepressant agents. Part 1. A series of 3-(1H-indol-3-yl)pyrrolidine-2,5-dione derivatives was synthesized and their biological activity was evaluated. The chemical structures of the newly prepared compounds were confirmed by (1)H NMR, (13)C NMR and ESI-HRMS spectra data. All tested compounds proved to be potent 5-HT1A receptor and serotonin transporter protein (SERT) ligands. Among them, compounds 15, 18, 19 and 30 showed significant affinity for 5-HT1A and SERT. Computer docking simulations carried out for compounds 15, 31 and 32 to models of 5-HT1A receptor and SERT confirm the results of biological tests. Due to high affinity for the 5-HT1A receptor and moderate affinity for SERT, compounds 31, 32, 35, and 37 were evaluated for their affinity for D2L, 5-HT6, 5-HT7 and 5-HT2A receptors. In vivo tests, in turn, resulted in determining the functional activity of compounds 15, 18, 19 and 30 to the 5-HT1A receptor. The results of these tests indicate that all of the ligands possess properties characteristic of 5-HT1A receptor agonists.", "role": "user" }, { "content": "{\"Chemical\": [\"pyrrolidine-2,5-dione\", \"serotonin\", \"(1)H\", \"(13)C\", \"3-(1H-indol-3-yl)pyrrolidine-2,5-dione\"]}", "role": "assistant" } ]

[ { "content": "Extract drug combinations from this sentence and classify each combination into one of these categories:\n- POS: Positive interaction between drugs\n- NEG: Negative interaction between drugs\n- COMB: Drugs used together with unknown interaction type\n\nOutput only a JSON array where each entry is [drug_1, drug_2, ..., drug_n, category].\n\nparagraph: Lenalidomide triggers T-cell effector functions in vivo in patients with follicular lymphoma. The immunomodulatory drug lenalidomide is used in patients with follicular lymphoma (FL) with the aim of stimulating T-cell antitumor immune response. However, little is known about the effects of lenalidomide on T-cell biology in vivo in patients with FL. We thus undertook an extensive longitudinal immunologic study , including phenotypic , transcriptomic , and functional analyses , on 44 first-line and 27 relapsed/refractory patients enrolled in the GALEN trial ( Obinutuzumab Combined With Lenalidomide for Relapsed or Refractory Follicular B-Cell Lymphoma ) to test the efficacy of lenalidomide and obinutuzumab combination in patients with FL . lenalidomide rapidly and transiently induced an activated T-cell phenotype, including HLA-DR, Tim-3, CD137, and programmed cell death protein 1 (PD-1) upregulation. Furthermore, sequential RNA-sequencing of sorted PD-1+ and PD-1- T-cell subsets revealed that lenalidomide triggered a strong enrichment for several gene signatures related to effector memory T-cell features, including proliferation, antigen receptor signaling, and immune synapse restoration; all were validated at the phenotypic level and with ex vivo functional assays. Correlative analyses pinpointed a negative clinical impact of high effector T-cell and regulatory T-cell percentages before and during treatment. Our findings bring new insight in lenalidomide mechanisms of action at work in vivo and will fuel a new rationale for the design of combination therapies.\n\nsentence: We thus undertook an extensive longitudinal immunologic study , including phenotypic , transcriptomic , and functional analyses , on 44 first-line and 27 relapsed/refractory patients enrolled in the GALEN trial ( Obinutuzumab Combined With Lenalidomide for Relapsed or Refractory Follicular B-Cell Lymphoma ) to test the efficacy of lenalidomide and obinutuzumab combination in patients with FL .", "role": "user" }, { "content": "[[\"Obinutuzumab\", \"Lenalidomide\", \"COMB\"]]", "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: Safe Practices for Copy and Paste in the EHR. Systematic Review, Recommendations, and Novel Model for Health IT Collaboration Copy and paste functionality can support efficiency during clinical documentation, but may promote inaccurate documentation with risks for patient safety. The Partnership for Health IT Patient Safety was formed to gather data, conduct analysis, educate, and disseminate safe practices for safer care using health information technology (IT). To characterize copy and paste events in clinical care, identify safety risks, describe existing evidence, and develop implementable practice recommendations for safe reuse of information via copy and paste. The Partnership 1) reviewed 12 reported safety events, 2) solicited expert input, and 3) performed a systematic literature review (2010 to January 2015) to identify publications addressing frequency, perceptions / attitudes, patient safety risks, existing guidance, and potential interventions and mitigation practices. The literature review identified 51 publications that were included. Overall, 66% to 90% of clinicians routinely use copy and paste. One study of diagnostic errors found that copy and paste led to 2.6% of errors in which a missed diagnosis required patients to seek additional unplanned care. Copy and paste can promote note bloat, internal inconsistencies, error propagation, and documentation in the wrong patient chart. Existing guidance identified specific responsibilities for authors, organizations, and electronic health record (EHR) developers. Analysis of 12 reported copy and paste safety events was congruent with problems identified from the literature review. Despite regular copy and paste use, evidence regarding direct risk to patient safety remains sparse, with significant study limitations. Drawing on existing evidence, the Partnership developed four safe practice recommendations: 1) Provide a mechanism to make copy and paste material easily identifiable; 2) Ensure the provenance of copy and paste material is readily available; 3) Ensure adequate staff training and education; 4) Ensure copy and paste practices are regularly monitored, measured, and assessed.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"practice\", \"perceptions\", \"Practices\", \"practices\", \"attitudes\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"diagnosis\"], \"Food\": [], \"HealthCareActivity\": [\"monitored\", \"safety\", \"guidance\", \"Patient Safety\", \"reported\", \"patient safety\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"documentation\", \"electronic health record\", \"chart\", \"Model\", \"literature review\", \"EHR\", \"Systematic Review\", \"publications\", \"systematic literature review\"], \"MedicalDevice\": [], \"Organization\": [\"Partnership\", \"organizations\"], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [\"clinicians\", \"authors\"], \"ResearchActivity\": [\"study\", \"Analysis\"], \"SpatialConcept\": [\"safe\", \"internal\", \"disseminate\", \"Safe\", \"safer\"], \"Virus\": []}", "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: Upstream Pathways Controlling Mitochondrial Function in Major Psychosis: A Focus on Bipolar Disorder Mitochondrial dysfunction is commonly observed in bipolar disorder (BD) and schizophrenia (SCZ) and may be a central feature of psychosis. These illnesses are complex and heterogeneous, which is reflected by the complexity of the processes regulating mitochondrial function. Mitochondria are typically associated with energy production; however, dysfunction of mitochondria affects not only energy production but also vital cellular processes, including the formation of reactive oxygen species, cell cycle and survival, intracellular Ca(2+) homeostasis, and neurotransmission. In this review, we characterize the upstream components controlling mitochondrial function, including 1) mutations in nuclear and mitochondrial DNA, 2) mitochondrial dynamics, and 3) intracellular Ca(2+) homeostasis. Characterizing and understanding the upstream factors that regulate mitochondrial function is essential to understand progression of these illnesses and develop biomarkers and therapeutics.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"Mitochondria\", \"mitochondria\"], \"Bacterium\": [], \"BiologicFunction\": [\"bipolar disorder\", \"Psychosis\", \"energy production\", \"neurotransmission\", \"BD\", \"survival\", \"formation\", \"progression\", \"mutations\", \"Bipolar Disorder\", \"Upstream Pathways\", \"illnesses\", \"schizophrenia\", \"intracellular Ca(2+) homeostasis\", \"psychosis\", \"SCZ\", \"cellular processes\", \"processes\", \"mitochondrial dynamics\", \"cell cycle\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"upstream factors\", \"mitochondrial DNA\", \"nuclear\", \"upstream components\", \"reactive oxygen species\"], \"ClinicalAttribute\": [\"biomarkers\"], \"Eukaryote\": [], \"Finding\": [\"Mitochondrial dysfunction\", \"heterogeneous\"], \"Food\": [], \"HealthCareActivity\": [\"therapeutics\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Output a JSON object with \"verdict\" and \"evidence\" fields based on the claim and abstract below.\n\nClaim: Can you boost your immune system to fight COVID-19? This is the question on everyone's mind as we face a worldwide crisis.\n\nAbstract:\nThe outbreak of the 2019 Novel Coronavirus (SARS-CoV-2) rapidly spread from Wuhan, China to more than 150 countries, areas or territories, causing staggering number of infections and deaths.\nA systematic profiling of the immune vulnerability landscape of SARS-CoV-2, which can bring critical insights into the immune clearance mechanism, peptide vaccine development, and antiviral antibody development, is lacking.\nIn this study, we investigated the potential of the SARS-CoV-2 viral proteins to induce class I and II MHC presentation and to form linear antibody epitopes.\nWe created an online database to broadly share the predictions as a resource for the research community.\nUsing this resource, we showed that genetic variations in SARS- CoV-2, though still few for the moment, already follow the pattern of mutations in related coronaviruses, and could alter the immune vulnerability landscape of this virus.\nImportantly, we discovered evidence that SARS-CoV-2, along with related coronaviruses, used mutations to evade attack from the human immune system.\nOverall, we present an immunological resource for SARS-CoV-2 that could promote both therapeutic development and mechanistic research.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Write an abstract for the research paper below.\n\nPaper text:\nlaparoscopic inguinal hernia repair is now used as an alternative to conventional open herniotomy in children .\nalthough there is ongoing debate regarding the preferred method of inguinal hernia repair , the laparoscopic approach is gaining popularity because of the potential advantages of faster recovery , attenuated pain , improved cosmetics , and low recurrence rates ( 1,2 ) . among various laparoscopic techniques ,\nlaparoscopic percutaneous extraperitoneal closure ( lpec ) of the hernia is a recently well - developed technique ( 3 ) .\na previous study evaluated the safety , efficacy , and reliability of lpec in children ( 4 ) .\nhowever , because this technique involves percutaneous closure of inguinal hernias , the inclusion of tissues between the skin and hernial sac , including nerves and muscles , may cause injury and increase the postoperative morbidity in the long - term ( 5 ) .\nthe present study described a novel and effective technique to close inguinal hernias with transumbilical endoscopic surgery in girls .\nthe surgical technique was modified according to our previous study ( 5 ) . under general anesthesia , patients were laid supine in the trendelenburg position at a 15 tilt .\nthe surgeon performed the operation standing on the patient 's left side , and the camera assistant stood on the right side .\na veress needle was inserted into the abdomen , and pneumoperitoneum was established at 8 to 12 mmhg .\none 3-mm trocar and one 5-mm trocar were inserted through the umbilicus , and a 4.5-mm 0 laparoscope ( karl storz gmbh & co. , tuttlingen , germany ) and a 3-mm needle holder were placed through the umbilical incision ( fig .\nthe needle holder was placed on the identical side for the convenience of suturing . under laparoscopic monitoring , a round needle with 20\nnon - absorbable suture material was introduced into the peritoneal cavity through the anterior abdominal wall near the internal inguinal ring .\nthe suture inside the peritoneal cavity was 5 to 8 cm long , and the end of the suture was left outside the peritoneal cavity in favor of ligation .\nthe needle was passed through the peritoneum to place an extraperitoneal purse - string suture around the internal inguinal ring ( fig .\nthe needle was then passed back into the peritoneal cavity and out through the abdominal wall , and the needle ends of the stitch were cut .\nthe operating assistant maintained tension on the end of the suture outside the abdominal cavity , and a 3- or 5-mm needle holder was used to manipulate the end of the suture inside the peritoneal cavity ( fig .\n3 ) . before the knot of the purse - string stitch was tied , the hernia sac was compressed to expel the gas and liquid within the sac .\nairtightness was confirmed by the absence of hernial sac enlargement when the intraperitoneal pressure was increased .\nthe same procedure was performed on the contralateral side if the processus vaginalis was patent .\na total of 96 female pediatric patients ( age range , 8 months to 8 years ; median , 3.4 years ) with inguinal hernias ( 25 left - sided , 53 right - sided and 18 bilateral ) were included in this study .\nfrom december , 2009 to august , 2015 , 114 procedures were performed in 96 female pediatric patients using the transumbilical laparoscopic intraperitoneal closure technique .\nthe mean operating time was 15 min ( range , 1020 min ) for the unilateral and 24 min ( range , 1828 min ) for the bilateral lesions .\nthe findings showed less operative bleeding , no major complications , and no secondary injury for all the groups .\nthe postoperative course was uneventful for all the patients , and no severe perioperative complications were observed .\nthe mean follow - up period was 28 months ( range , 674 months ) . there were no cases of recurrence or postoperative hydrocele .\nlaparoscopic inguinal hernia repair in children has recently become an alternative to conventional open herniotomy .\nvarious single - incision laparoscopic surgeries have been reported ( 57 ) . however , given the fact that laparoscopic inguinal hernia repair technique involves percutaneous closure of inguinal hernias , tissues between the skin and hernial sac , including nerves and muscles , may be injured by their inclusion in the suture line , which potentially increases postoperative morbidity in the long - term . to preserve the advantages and overcome the limitations of the single - port technique , we designed a novel technique with which to close inguinal hernias with transumbilical laparoscopic intraperitoneal closure in female pediatric patients .\nthis technique involves transumbilical laparoscopic closure of inguinal hernias without the use of special instruments .\nit requires one 3-mm trocar and one 5-mm trocar with a 4.5-mm 0 laparoscope and a 3-mm needle holder .\nthe direction of the purse - string suture is circular , counterclockwise on the left and clockwise on the right to avoid injury to the inferior epigastric artery .\npurse - string suturing is easier to perform in female patients because there is no vas deferens or spermatic cord ; thus , the operator is less concerned about causing injury . after purse - string suturing ,\nthe needle is passed out through the abdominal wall and knots are tied intraperitoneally with a one - hand tie to avoid injury .\ntransumbilical laparoscopic intraperitoneal closure in female patients provides a true high ligation analogous to that performed in the open technique .\nwe observed no recurrence in the patients of the present study during our limited follow - up period .\nscarless endoscopic abdominal surgery has become an important concern in recent years with the development of minimally invasive surgery . a new concept known as natural orifice transluminal endoscopic surgery appeared with the publication of the first experimental study by kalloo et al ( 8) ; however , few clinical studies explaining this method exist in the literature .\nthe major limiting barriers for its clinical application include access , closure , infection , suturing technology , and orientation ( 9 ) . compared to natural orifice transluminal endoscopic surgery , transumbilical endoscopic surgery is a less complicated and safer method .\ntransumbilical endoscopic surgery produce scarless outcome and theoretically has the same advantage of rapid recovery .\ncompared to the current single - incision laparoscopic extraperitoneal closure techniques , our method is easy to perform and the instruments are readily available .\nour preliminary experience showed satisfactory outcomes with the transumbilical laparoscopic intraperitoneal closure technique for complete endoscopic closure of inguinal hernias in female pediatric patients .\ncosmetic result and the ability to simultaneously detect and repair contralateral patent processus vaginalis are the two main advantages of laparoscopic surgery over open surgery .\nour results suggest that transumbilical endoscopic surgery for inguinal hernias in female pediatric patients is safe , effective , and reliable .\ntwo - port transumbilical laparoscopic intraperitoneal closure of inguinal hernias is an effective technique in minimal - access surgery for pediatric patients .\nthe cosmetic results of transumbilical laparoscopic intraperitoneal closure in the present study were excellent because of the presence of only two umbilical wounds for the unilateral and bilateral hernias . the wound scar associated with the laparoscopic port was hidden in the umbilicus , and the puncture wounds made by the devices were minimal .\n4 ) . in the present study , because the hernia sac was closed intracorporeally , the risk of intra - abdominal complications was not totally eliminated .\nalthough serious complications such as unintentional puncturing of the iliac vein and intra - abdominal viscus did not occur , future studies with greater numbers of patients and long - term follow - ups should be conducted .", "role": "user" }, { "content": "laparoscopic percutaneous extraperitoneal closure of inguinal hernia with variable devices as an effective technique in minimal - access surgery for pediatric inguinal hernias in children was investigated in the present study . \n a veress needle was inserted into the abdomen . \n trocars , laparoscope and needle holder were placed through the umbilical incision . under laparoscopic monitoring , \n a round needle was introduced into the peritoneal cavity through the anterior abdominal wall . \n the end of the suture inside the peritoneal cavity was left outside the peritoneal cavity in favor of ligation . \n the needle was passed through the peritoneum to place an extraperitoneal purse - string suture around the internal inguinal ring , counterclockwise on the left and clockwise on the right . \n the needle was then passed back into the peritoneal cavity and out through the abdominal wall , and the needle ends of the stitch were cut . \n the ends of the suture were tied . \n we described a technique used for transumbilical endoscopic closure of pediatric inguinal hernias in girls . \n this technique is simple and can be performed quickly . \n the cosmetic result is excellent because the two umbilical incisions are only 5-mm long , which make it possible to perform surgery without a visible scar . \n we performed this procedure in over 96 patients and have had no recurrences . \n thus , this method may become the laparoscopic repair of choice for females with inguinal hernias .", "role": "assistant" } ]

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: We propose a method for loop detection and correction from lidar point clouds, and we show that the\n\nKeyphrases: loop detection correction lidar\n\nDataset descriptions:\nKITTI: KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) is one of the most popular datasets for use in mobile robotics and autonomous driving. It consists of hours of traffic scenarios recorded with a variety of sensor modalities, including high-resolution RGB, grayscale stereo cameras, and a 3D laser scanner.\nCompletion3D: The Completion3D benchmark is a dataset for evaluating state-of-the-art 3D Object Point Cloud Completion methods. Ggiven a partial 3D object point cloud the goal is to infer a complete 3D point cloud for the object.\nUASOL: The UASOL an RGB-D stereo dataset, that contains 160902 frames, filmed at 33 different scenes, each with between 2 k and 10 k frames. The frames show different paths from the perspective of a pedestrian, including sidewalks, trails, roads, etc.\nFord Campus Vision and Lidar Data Set: Ford Campus Vision and Lidar Data Set is a dataset collected by an autonomous ground vehicle testbed, based upon a modified Ford F-250 pickup truck. The vehicle is outfitted with a professional (Applanix POS LV) and consumer (Xsens MTI-G) Inertial Measuring Unit (IMU), a Velodyne 3D-lidar scanner, two push-broom forward looking Riegl lidars, and a Point Grey Ladybug3 omnidirectional camera system.\n\nOptions: A: KITTI B: Completion3D C: UASOL D: Ford Campus Vision and Lidar Data Set", "role": "user" }, { "content": "KITTI", "role": "assistant" } ]

[ { "content": "Summarize the article in an uncomplicated manner.\n\nTitle: The Role of Coupled Positive Feedback in the Expression of the SPI1 Type Three Secretion System in Salmonella\nArticle:\nAbstract:\nSalmonella enterica serovar Typhimurium is a common food-borne pathogen that induces inflammatory diarrhea and invades intestinal epithelial cells using a type three secretion system( T3SS) encoded within Salmonella pathogenicity island 1( SPI1). The genes encoding the SPI1 T3SS are tightly regulated by a network of interacting transcriptional regulators involving three coupled positive feedback loops. While the core architecture of the SPI1 gene circuit has been determined, the relative roles of these interacting regulators and associated feedback loops are still unknown. To determine the function of this circuit, we measured gene expression dynamics at both population and single-cell resolution in a number of SPI1 regulatory mutants. Using these data, we constructed a mathematical model of the SPI1 gene circuit. Analysis of the model predicted that the circuit serves two functions. The first is to place a threshold on SPI1 activation, ensuring that the genes encoding the T3SS are expressed only in response to the appropriate combination of environmental and cellular cues. The second is to amplify SPI1 gene expression. To experimentally test these predictions, we rewired the SPI1 genetic circuit by changing its regulatory architecture. This enabled us to directly test our predictions regarding the function of the circuit by varying the strength and dynamics of the activating signal. Collectively, our experimental and computational results enable us to deconstruct this complex circuit and determine the role of its individual components in regulating SPI1 gene expression dynamics.\nIntroduction:\nSalmonella enterica is a common food-borne pathogen that causes an array of diseases in humans, ranging from self-limiting gastroenteritis to life-threatening systemic infections[1],[2]. The bacterium initiates infection by invading intestinal epithelial cells using a type three secretion system( T3SS) encoded within a forty kilobase region of the chromosome called Salmonella Pathogenicity Island 1( SPI1)[3],[4],[5],[6],[7],[8]. The bacterium uses this T3SS to inject proteins into the cytoplasm of host cells[9],[10],[11]. The injected proteins commandeer the host cell actin-cytoskeleton machinery and promote the uptake of the bacterium into these otherwise non-phagocytic cells[12],[13],[14],[15]. The genes encoding the SPI1 T3SS are tightly regulated by a network of interacting transcriptional regulators that are responsive to a combination of environmental and intracellular signals[16],[17],[18]. These signals are presumably used by Salmonella as anatomical cues for initiating invasion and also for coordinating SPI1 gene expression with other cellular processes, most notably adhesion and motility[19],[20],[21],[22],[23],[24]. The master regulator for the SPI1 gene circuit is HilA, a transcription factor that contains a DNA-binding motif belonging to the OmpR/ToxR family[4] and a large C-terminal domain of unknown function[25]. HilA activates the expression of the genes encoding the structural components of the SPI1 T3SS[4],[26],[27],[28]. HilA also activates the expression of an AraC-like transcription factor, InvF, involved in regulating the expression of the SPI1 secreted effector proteins and their cognate chaperones[29],[30]. HilA expression, in turn, is regulated by three AraC-like transcription factors- HilC, HilD, and RtsA – with homologous DNA binding domains[22],[31],[32]. Both hilC and hilD are encoded within SPI1 whereas rtsA is encoded elsewhere on the chromosome. These three transcription factors can independently activate HilA expression. They can also activate each others' and their own expression[16]. Specifically, HilC, HilD, and RtsA are all capable of individually activating the PhilA PhilC, PhilD, and PrtsA promoters. These auto-regulatory interactions result in three coupled positive feedback loops comprising HilC, HilD, and RtsA, the output of each capable of activating HilA expression( Figure 1A). Of the three, HilD is dominant, as there is no HilA expression in its absence[33]. This reflects the fact that many activating signals, both environmental and intracellular, affect SPI1 gene expression by modifying the activity of HilD protein[16],[18],[19],[23],[34],[35]. In addition to positive regulation, SPI1 gene expression is also subject to negative regulation. HilE, a protein of unknown structure encoded outside SPI1, binds HilD[34] and prevents it from activating its target promoters. While the core architecture of the SPI1 gene circuit has been determined( Figure 1A), the functions of these interacting regulators and associated feedback loops are still unknown. Therefore, to deconstruct this circuit, we measured gene expression dynamics at both population and single-cell resolution in a number of SPI1 regulatory mutants. Based on these experimental results, we constructed a simple mathematical model of the SPI1 gene circuit. Using the model, we demonstrate that the circuit serves two functions. The first is to place a threshold on SPI1 activation, ensuring that the genes encoding the T3SS are expressed only in response to the appropriate combination of environmental and cellular cues. The second is to amplify SPI1 gene expression. To experimentally test these two predictions, we rewired the SPI1 network by changing its regulatory architecture. The resulting experimental and computational analyses underpin an integrated model for the regulation of SPI1 gene expression.\nDiscussion:\nUsing a combination of experimental and computational approaches, we found that the SPI1 gene circuit functions as a signal amplifier with an activation threshold. This virulence switch likely ensures that the SPI1 T3SS is assembled only when the bacterium has reached its target site for invasion, the distal small intestine[45]. Salmonella is thought to be able to determine its location within the host by sensing a number of environmental factors, key among them oxygen and osmolarity[28]. In addition to these environmental signals, SPI1 gene expression is also coordinated with other cellular processes such as motility and adhesion[19],[20],[21],[22],[23],[24]. The accumulated evidence to date, including the results from this study, indicates that HilD is the primary site for signal integration. According to our model, these activating signals, both intracellular cellular and environmental, initiate SPI1 gene expression by inducing the expression and activation of HilD through still unknown mechanisms. HilE, however, binds to HilD and inhibits its activity. Only when the activating signals are sufficiently strong is HilD expressed at a high enough level to overcome sequestration by HilE and activate the expression of the other SPI1 regulators – HilC, RtsA, and HilA- and also further induce its own expression. Once induced, HilC and RtsA serve to further amplify and also accelerate SPI1 gene expression. The result is a two-state switch with a defined activation threshold, defined in the sense that the threshold is set by the level of HilE expression and possibly other systems that function through HilD protein[44]. A notable feature of the SPI1 gene circuit is the presence of three, coupled positive feedback loops. At the most fundamental level, positive feedback amplifies the response to an external signal[46],[47]. It is also capable of effectively transforming a continuous input into a digital output when the feedback is sufficiently strong. In the context of bacterial gene circuits, positive feedback has most often been associated with multi-stable switches and cell population heterogeneity[43],[48]. What makes the SPI1 gene circuit particularly intriguing is that most bacterial systems utilizing positive feedback, at least those documented so far in the literature, possess only a single loop. We first note that these additional feedback loops, namely the ones regulating the expression of HilC and RtsA, do not add redundancy to the circuit, as the loss of HilD effectively shuts off SPI1 gene expression. Rather, they serve to further amplify and accelerate SPI1 gene expression. In vivo, loss of either HilC or RtsA does not significantly attenuate intestinal invasion. Yet, loss of both does[16], indicating that the amplification or acceleration provided by these loops plays an important physiological role. Whether this role is simply to ensure that the SPI1 structural genes are expressed at sufficiently high levels or to provide a sharp activation threshold is still unknown. Only a few studies to date, mostly focused on eukaryotic systems where this regulation is more common, have explored systems employing coupled positive feedback[49],[50],[51],[52]. In one notable theoretical study, the coupling of a slow and fast positive feedback loop was shown to yield a “dual-time” switch that is capable of being rapidly induced yet still is robust to fluctuations in the activating signal[49]. However, these properties are not obtained when two loops of the same type are coupled. While rapid induction is observed in SPI1 gene expression, there is no evidence to suggest that some loops are fast whereas others are slow. Furthermore, these loops do not operate synergistically in the sense that coupling in the SPI1 gene circuit does not engender new functions unattainable with just a single loop. As the loops involving HilC and RtsA only additively contribute to the response, we imagine that the coupling in SPI1 may result instead from the piecewise evolution of the circuit. According to this model, HilC and RtsA were acquired to compensate for the inability of HilD alone to mediate a robust response. The motivation for this model comes from a recent study where a synthetic gene circuit coupling two weak positive feedback loops was engineered[53]. The authors found that their coupled circuit yielded a bistable response that, in the case of a single loop circuit, could be obtained only with an ultrasensitive activator even though the individual regulators in the coupled circuit lacked this behavior. Based on these results, the authors speculated that natural circuits could evolve using a similar approach- rather than evolve a circuit with a single regulator requiring precise biochemical properties, a more robust and facile solution may be obtained by simply linking together multiple regulators that alone lack the requisite properties. Similarly, others have shown that by changing the regulatory architecture of a circuit one can affect is behavior without commensurate changes in the underlying proteins[54],[55],[56]. We hypothesize that a similar process may have occurred with the SPI1 gene circuit. As such, this model provides one possible explanation as to why the circuit involves multiple feedback loops when one alone would suffice. In a related study, we found that the gene circuit controlling the expression of type I fimbriae in Salmonella utilizes two coupled positive feedback loops[24]. In this system, the expression of the genes encoding the type I fimbriae is controlled by two regulators, FimY and FimZ. These two proteins form two coupled positive feedback loops and encode a logical AND gate or, alternatively, a coincidence circuit. A similar logic may also be also encoded within the SPI1 gene circuit. In particular, HilC is expressed in the absence of HilD. Moreover, the signals activating the PhilC promoter appear to be different than the ones activating the PhilD promoter, given their dissimilar dynamics. We are tempted therefore to speculate that, in addition to being an amplifier, the SPI1 gene circuit may also function as some sort of coincidence circuit, optimally expressing SPI1 genes only when the activating signals for both the PhilC and PhilD promoter are present. Coupled feedback in this case would reinforce the effect of these signals and further link the two. While such a model alone would not explain why multiple feedbacks loops are present in the SPI1 gene circuit, it may nonetheless provide one possible advantage for such a design. In conclusion, we have been able to propose an integrated model for the regulation of SPI1 gene expression. While this system has been studied extensively, an integrated model of its regulation was previously lacking. Using a combination of experimental and computational analyses, we have been able to deconstruct this complex circuit and determine how the individual components contribute towards its integrated function. A key element in our analysis involved rewiring the SPI1 genetic circuit. As the kinetic parameters are unavailable and difficult to perturb, direct validation of our model remains an elusive challenge. However, by rewiring the circuit, we were nonetheless able to test a number of predictions from our mathematical model. Such an approach provides a powerful framework for integrating models with experimental data, particularly when parameters values are lacking or difficult to perturb. Finally, our results provide a detailed examination of a natural system employing coupled positive feedback, a mechanism of control that to date has primarily been investigated in eukaryotes.", "role": "user" }, { "content": "Salmonella is a causative agent for a wide range of diseases in humans , including gastroenteritis and enteric fever . A key step in the infection process occurs when Salmonella invades intestinal epithelial cells using a molecular hypodermic needle . Salmonella uses these needles to inject proteins into host cells that enable the bacterium to enter and replicate within them . The production of these needles , and the corollary decision to invade the host , is tightly controlled by a complex network of interacting regulatory proteins that , when studied individually , seemingly have either redundant or antagonizing effects . To understand how this ensemble of regulators dynamically controls the expression of these invasion genes , we systematically deconstructed the network and then used this information to analyze their composite behavior by computer simulation . Our analysis demonstrates that this regulatory network ensures that the invasion genes are expressed only when the invasion signals , a combination of environmental and cellular cues , exceed a defined threshold . Once induced , this network further amplifies and accelerates the expression of the invasion genes . These results further our understanding of this important pathogen by unraveling a key mechanism during infection , namely the decision to invade .", "role": "assistant" } ]

[ { "content": "Write a literature review chapter based on these paper abstracts.\nLiterature Review Title: A Survey of Monte Carlo Tree Search Methods \nChapter Title: 1) MCTS-Solver: \n1. Abstract of Cited Paper (BIB001): We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics of this problem are quite complex, it is often possible to provide or learn a coarse simulation-based model of a tactical domain, which makes Monte-Carlo planning an attractive approach. In this paper, we investigate the use of UCT, a recent Monte-Carlo planning algorithm for this problem. UCT has recently shown impressive successes in the area of games, particularly Go, but has not yet been considered in the context of multiagent tactical planning. We discuss the challenges of adapting UCT to our domain and an implementation which allows for the optimization of user specified objective functions. We present an evaluation of our approach on a range of tactical assault problems with different objectives in the RTS game Wargus. The results indicate that our planner is able to generate superior plans compared to several baselines and a human player. \n2. Abstract of Cited Paper (BIB002): The success of Monte Carlo tree search (MCTS) in many games, where αβ-based search has failed, naturally raises the question whether Monte Carlo simulations will eventually also outperform traditional game-tree search in game domains where αβ -based search is now successful. The forte of αβ-based search are highly tactical deterministic game domains with a small to moderate branching factor, where efficient yet knowledge-rich evaluation functions can be applied effectively. In this paper, we describe an MCTS-based program for playing the game Lines of Action (LOA), which is a highly tactical slow-progression game exhibiting many of the properties difficult for MCTS. The program uses an improved MCTS variant that allows it to both prove the game-theoretical value of nodes in a search tree and to focus its simulations better using domain knowledge. This results in simulations superior in both handling tactics and ensuring game progression. Using the improved MCTS variant, our program is able to outperform even the world's strongest αβ-based LOA program. This is an important milestone for MCTS because the traditional game-tree search approach has been considered to be the better suited for playing LOA.\n\nLiterature Review:", "role": "user" }, { "content": "Proof-number search (PNS) is a standard AI technique for proving game-theoretic values, typically used for endgame solvers, in which terminal states are considered to be proven wins or losses and deductions chained backwards from these . A nonterminal state is a proven win if at least one of its children is a proven win, or a proven loss if all of its children are proven losses. When exploring the game tree, proof-number search prioritizes those nodes whose values can be proven by evaluating the fewest children. Winands et al. BIB003 , BIB001 propose a modification to MCTS based on PNS in which game-theoretic values BIB002 are proven and backpropagated up the tree. If the parent node has been visited more than some threshold times, normal UCB selection applies and a forced loss node is never selected; otherwise, a child is selected according to the simulation policy and a forced loss node may be selected. Nijssen and Winands also describe a multiplayer version of their MCTS-solver (Section IV-E).", "role": "assistant" } ]

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

[ { "content": "Which dataset would be most relevant for this research query?\n\nQuery: The code for Few-shot Semantic Segmentation\n\nKeyphrases: few-shot semantic segmentation images\n\nDataset descriptions:\nNDD20: Northumberland Dolphin Dataset 2020 (NDD20) is a challenging image dataset annotated for both coarse and fine-grained instance segmentation and categorisation. This dataset, the first release of the NDD, was created in response to the rapid expansion of computer vision into conservation research and the production of field-deployable systems suited to extreme environmental conditions -- an area with few open source datasets.\nFSS-1000: FSS-1000 is a 1000 class dataset for few-shot segmentation. The dataset contains significant number of objects that have never been seen or annotated in previous datasets, such as tiny daily objects, merchandise, cartoon characters, logos, etc.\nFSOD: Few-Shot Object Detection Dataset (FSOD) is a high-diverse dataset specifically designed for few-shot object detection and intrinsically designed to evaluate thegenerality of a model on novel categories.\nSBD: The Semantic Boundaries Dataset (SBD) is a dataset for predicting pixels on the boundary of the object (as opposed to the inside of the object with semantic segmentation). The dataset consists of 11318 images from the trainval set of the PASCAL VOC2011 challenge, divided into 8498 training and 2820 test images.\n\nOptions: A: NDD20 B: FSS-1000 C: FSOD D: SBD", "role": "user" }, { "content": "FSS-1000", "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\nApnea-hypopnea index of less than 5 h-1 or greater than 30 h-1.\nPredominance of central apneas and hypopneas, defined as more than 25% of all respiratory events.\nProfessional drivers, risk profession or respiratory failure (according to criteria of the clinical pathway for diagnosis and treatment of sleep-disordered breathing).\nVery excessive daytime sleepiness (Epworth Sleepiness Scale> 18).\nMorbid obesity (BMI> 40 kg / m2).\nPrior treatment with CPAP.", "role": "user" }, { "content": "{\"Condition\": [\"central apneas and hypopneas\", \"Predominance\", \"respiratory failure\", \"Morbid obesity\", \"daytime sleepiness\"], \"Device\": [], \"Drug\": [], \"Measurement\": [\"all respiratory events\", \"Epworth Sleepiness Scale\", \"Apnea-hypopnea index\", \"BMI\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [\"Professional drivers\", \"risk profession\"], \"Procedure\": [\"CPAP\", \"criteria of the clinical pathway for diagnosis and treatment of sleep-disordered breathing\"], \"Qualifier\": [\"Very excessive\"], \"ReferencePoint\": [], \"Scope\": [\"Epworth Sleepiness Scale\\u003e 18\", \"Very excessive daytime sleepiness\", \"Predominance of central apneas and hypopneas\"], \"Temporal\": [\"Prior\"], \"Value\": [\"\\u003e 40 kg / m2\", \"more than 25%\", \"less than 5 h-1 or greater than 30 h-1\", \"\\u003e 18\"], \"Visit\": []}", "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: For our experimental evaluation, we used the binary test-datasets of Weber et al. [35] and Batenburg and Sijbers [4].", "role": "user" }, { "content": "Method", "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: Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention\n\nMost Chinese pre-trained encoders take a character as a basic unit and learn representations according to character's external contexts, ignoring the semantics expressed in the word, which is the smallest meaningful unit in Chinese. Hence, we propose a novel word aligned attention to incorporate word segmentation information, which is complementary to various Chinese pre-trained language models. Specifically, we devise a mixed-pooling strategy to align the character level attention to the word level, and propose an effective fusion method to solve the potential issue of segmentation error propagation. As a result, word and character information are explicitly integrated at the fine-tuning procedure. Experimental results on various Chinese NLP benchmarks demonstrate that our model could bring another significant gain over several pre-trained models.\n\nIntroduction\nPre-trained language Models (PLM) such as ELMo BIBREF0, BERT BIBREF1, ERNIE BIBREF2 and XLNet BIBREF3 have been proven to capture rich language information from text and then benefit many NLP applications by simple fine-tuning, including sentiment classification, natural language inference, named entity recognition and so on.\nGenerally, most of PLMs focus on using attention mechanism BIBREF4 to represent the natural language, such as word-level attention for English and character-level attention for Chinese. Unlike English, in Chinese, words are not separated by explicit delimiters, which means that character is the smallest linguistic unit. However, in most cases, the semantic of single Chinese character is ambiguous. UTF8gbsn For example, in Table 1, using the attention over word 西山 is more intuitive than over the two individual characters 西 and 山. Moreover, previous work has shown that considering the word segmentation information can lead to better language understanding and accordingly benefits various Chines NLP tasks BIBREF5, BIBREF6, BIBREF7.\nAll these factors motivate us to expand the character-level attention mechanism in Chinese PLM to represent attention over words . To this end, there are two main challenges. (1) How to seamlessly integrate word segmentation information into character-level attention module of PLM is an important problem. (2) Gold-standard segmentation is rarely available in the downstream tasks, and how to effectively reduce the cascading noise caused by automatic segmentation tools BIBREF8 is another challenge.\nIn this paper, we propose a new architecture, named Multi-source Word Alignd Attention (MWA), to solve the above issues. (1) Psycholinguistic experiments BIBREF9, BIBREF10 have shown that readers are likely to pay approximate attention to each character in one Chinese word. Drawing inspiration from such finding, we introduce a novel word-aligned attention, which could aggregate attention weight of characters in one word into a unified value with the mixed pooling strategy BIBREF11. (2) For reducing segmentation error, we further extend our word-aligned attention with multi-source segmentation produced by various segmenters, and deploy a fusion function to pull together their disparate output. In this way, we can implicitly reduce the error caused by automatic annotation.\nExtensive experiments are conducted on various Chinese NLP datasets including named entity recognition, sentiment classification, sentence pair matching, natural language inference, etc. The results show that the proposed model brings another gain over BERT BIBREF1, ERNIE BIBREF2 and BERT-wwm BIBREF12, BIBREF13 in all the tasks.\n\nMethodology ::: Character-level Pre-trained Encoder\nThe primary goal of this work is to inject the word segmentation knowledge into character-level Chinese PLM and enhance original models. Given the strong performance of recent deep transformers trained on language modeling, we adopt BERT and its updated variants (ERNIE, BERT-wwm) as the basic encoder for our work, and the outputs $\\mathbf {H}$ from the last layer of encoder are treated as the enriched contextual representations.\n\nMethodology ::: Word-aligned Attention\nAlthough the character-level PLM can well capture language knowledge from text, it neglects the semantic information expressed in the word level. Therefore we apply a word-aligned layer on top of the encoder to integrate the word boundary information into representation of character with the attention aggregation mechanism.\nFor an input sequence with with $n$ characters $S=[c_1, c_2, ... , c_n]$, where $c_j$ denotes the $j$-th character, Chinese words segmentation tool $\\pi $ is used to partition $S$ into non-overlapping word blocks:\nwhere $w_i = \\lbrace c_s, c_{s+1}, ..., c_{s+l-1}\\rbrace $ is the $i$-th segmented word of length $l$ and $s$ is the index of $w_i$'s first character in $S$. We apply the self-attention with the representations of all input characters to get the character-level attention score matrix $\\textbf {A}_c \\in \\mathbb {R}^{n \\times n}$. It can be formulated as:\nwhere $\\textbf {Q}$ and $\\textbf {K}$ are both equal to the collective representation $\\textbf {H}$ at the last layer of the Chinese PLM, $\\textbf {W}_k \\in \\mathbb {R}^{d\\times d}$ and $\\textbf {W}_q \\in \\mathbb {R}^{d\\times d}$ are trainable parameters for projection. While $\\textbf {A}_c$ models the relationship between two arbitrarily characters without regard to the word boundary, we argue that incorporating word as atoms in the attention can better represent the semantics, as the literal meaning of each individual characters can be quite different from the implied meaning of the whole word, and the simple weighted sum in character-level cannot capture the semantic interaction between words.\nTo this end, we propose to align $\\textbf {A}_c$ in the word level and integrate the inner-word attention. For the sake of simplicity, we rewrite $\\textbf {A}_c$ as $[\\textbf {a}_c^1, \\textbf {a}_c^2, ... ,\\textbf {a}_c^n]$, where $\\textbf {a}_c^i \\in \\mathbb {R}^n $ denotes the $i$-th row vector of $\\textbf {A}_c$ and the attention score vector of the $i$-th character. Then we deploy $\\pi $ to segment $\\textbf {A}_c$ according to $\\pi (S)$. For example, if $\\pi (S) = [\\lbrace c_1, c_2\\rbrace , \\lbrace c_3\\rbrace , ...,\\lbrace c_{n-1}, c_{n}\\rbrace ]$, then\nIn this way, an attention vector sequence is segmented into several subsequences and each subsequence represents the attention of one word. Then, motivated by the psycholinguistic finding that readers are likely to pay approximate attention to each character in one Chinese word, we devise an appropriate aggregation module to fuse the inner-word character attention. Concretely, we first transform $\\lbrace \\textbf {a}_c^s,..., \\textbf {a}_c^{s+l-1}\\rbrace $ into one attention vector $\\textbf {a}_w^i$ for $w_i$ with the mixed pooling strategy BIBREF11. Then we execute the piecewise up- mpling operation over each $\\textbf {a}_w^i$ to keep input and output dimensions unchanged for the sake of plug and play. The detailed process can be summarized as follows:\nwhere $\\lambda \\in R^1 $ is a weighting trainable variable to balance the mean and max pooling, $\\textbf {e}_l=[1,...,1]^T$ represents a $l$-dimensional all-ones vector, $l$ is the length of word $w_i$, $\\textbf {e}_l \\otimes \\textbf {a}_w^i=[\\textbf {a}_w^i,...,\\textbf {a}_w^i]$ denotes the kronecker product operation between $\\textbf {e}_l$ and $\\textbf {a}_w^i$, $\\hat{\\textbf {A}}_c \\in \\mathbb {R}^{n \\times n}$ is the aligned attention matrix. The Eq. (DISPLAY_FORM9-) can help incorporate word segmentation information into character-level attention calculation process, and determine the attention vector of one character from the perspective of the whole word, which is beneficial for eliminating the attention bias caused by character ambiguity. Finally, we get the enhanced character representation produced by word-aligned attention:\nwhere $\\textbf {V} = \\textbf {H}$, $\\textbf {W}_v \\in \\mathbb {R}^{d\\times d}$ is a trainable projection matrix. Besides, we also use multi-head attention BIBREF4 to capture information from different representation subspaces jointly, thus we have $K$ different aligned attention matrices $\\hat{\\textbf {A}}_c^k (1\\le k\\le K)$ and corresponding output $\\hat{\\textbf {H}}^k$. With multi-head attention architecture, the output can be expressed as follows:\n\nMethodology ::: Multi-source Word-aligned Attention\nAs mentioned in Section SECREF1, our proposed word-aligned attention relies on the segmentation results of CWS tool $\\pi $. Unfortunately, a segmenter is usually unreliable due to the risk of ambiguous and non-formal input, especially on out-of-domain data, which may lead to error propagation and an unsatisfactory model performance. In practice, The ambiguous distinction between morphemes and compound words leads to the cognitive divergence of words concepts, thus different $\\pi $ may provide diverse $\\pi (S)$ with various granularities. To reduce the impact of segmentation error and effectively mine the common knowledge of different segmenters, it’s natural to enhance the word-aligned attention layer with multi-source segmentation input. Formally, assume that there are $M$ popular CWS tools employed, we can obtain $M$ different representations $\\overline{\\textbf {H}}^1, ..., \\overline{\\textbf {H}}^M $ by Eq. DISPLAY_FORM11. Then we propose to fuse these semantically different representations as follows:\nwhere $\\textbf {W}_g$ is the parameter matrix and $\\tilde{\\textbf {H}}$ is the final output of the MWA attention layer.\n\nExperiments ::: Experiments Setup\nTo test the applicability of the proposed MWA attention, we choose three publicly available Chinese pre-trained models as the basic encoder: BERT, ERNIE, and BERT-wwm. In order to make a fair comparison, we keep the same hyper-parameters (such maximum length, warm-up steps, initial learning rate, etc) as suggested in BERT-wwm BIBREF13 for both baselines and our method on each dataset. We run the same experiment for five times and report the average score to ensure the reliability of results. For detailed hyper-parameter settings, please see Appendix. Besides, three popular CWS tools thulac BIBREF14, ictclas BIBREF15 and hanlp BIBREF16 are employed to segment the Chinese sentences into words.\nWe carried out experiments on four Chinese NLP tasks, including Emotion Classification (EC), Named Entity Recognition (NER), Sentence Pair Matching (SPM) and Natural Language Inference (NLI). The detail of those tasks and the corresponding datasets are introduced in Appendix.\n\nExperiments ::: Experiment Results\nTable TABREF14 shows the experiment measuring improvements from the MWA attention on test sets of four datasets. Generally, our method consistently outperforms all baselines on all of four tasks, which clearly indicates the advantage of introducing word segmentation information into the encoding of character sequences. Moreover, the Wilcoxon’s test shows that significant difference ($p< 0.01$) exits between our model with baseline models.\nIn detail, On the EC task, we observe 1.46% absolute improvement in F1 score over ERINE. SPM and NLI tasks can also gain benefits from our enhanced representation, achieving an absolute F1 increase of 0.68% and 0.55% over original models averagely. For the NER task, our method improves the performance of BERT by 1.54%, and obtains 1.23% improvement averagely over all baselines. We attribute such significant gain in NER to the particularity of this task. Intuitively, Chinese NER is correlated with word segmentation, and named entity boundaries are also word boundaries. Thus the potential boundary information presented by the additional segmentation input can provide a better guidance to label each character, which is consistent with the conclusion in BIBREF6, BIBREF7.\n\nExperiments ::: Ablation Study\nTo demonstrate the effectiveness of our multi-source fusion method in reducing the segmentation error introduced by CWS tools, We further carry out experiments on the EC task with different segmentation inputs. Table TABREF16 presents the comprehensive results on the three segmentation inputs produced by three CWS tools aforementioned. Experimental results show that our model gives quite stable improvement no matter the segmentation input quality. This again suggests the effectiveness of incorporating word segmentation information into character-level PLMs. And by employing multiple segmenters and fusing them together could introduce richer segmentation information and reduce the impact of general existent segmentation error.\n\nConclusion\nIn this paper, we propose an effective architecture Word-aligned Attention to incorporate word segmentation information into character-based pre-trained language models, which is adopted to a variety of downstream NLP tasks as an extend layer in fine-tuned process. And we also employ more segmenters into via proposed Multi-source Word-aligned Attention for reducing segmentation error. The experimental results show the effectiveness of our method. Comparing to BERT, ERNIE and BERT-wwm, our model obtains substantial improvements on various NLP benchmarks. Although we mainly focused on Chinese PLM in this paper, our model would take advantage the capabilities of Word-aligned Attention for word-piece in English NLP task. We are also considering applying this model into pre-training language model for various Language Model task in different grain to capture multi-level language features.\n\nTable 1: Results from different tokenizers over北京西 山森林公园(Beijing west mount forest park).\n\nFigure 1: Architecture of Word-aligned Attention\n\nTable 2: Results of word-aligned attention models on multi NLP task. All of results are f1-score evaluated on test set and each experiment are enacted five times, the average is taken as result. Part of results are similar to results from BERT-wwm technical report (Cui et al., 2019).\n\nTable 3: Results of word-aligned attention produced by difference segmenters, and results of aggregated model over multi tokenizers on weibo sentiment-100k dataset.\n\nQuestion: How does the fusion method work?", "role": "user" }, { "content": "{\"answer\": [\"ttention vector sequence is segmented into several subsequences and each subsequence represents the attention of one word\", \"we devise an appropriate aggregation module to fuse the inner-word character attention\"], \"evidence\": [\"In this way, an attention vector sequence is segmented into several subsequences and each subsequence represents the attention of one word. Then, motivated by the psycholinguistic finding that readers are likely to pay approximate attention to each character in one Chinese word, we devise an appropriate aggregation module to fuse the inner-word character attention. Concretely, we first transform $\\\\lbrace \\\\textbf {a}_c^s,..., \\\\textbf {a}_c^{s+l-1}\\\\rbrace $ into one attention vector $\\\\textbf {a}_w^i$ for $w_i$ with the mixed pooling strategy BIBREF11. Then we execute the piecewise up- mpling operation over each $\\\\textbf {a}_w^i$ to keep input and output dimensions unchanged for the sake of plug and play. The detailed process can be summarized as follows:\"]}", "role": "assistant" } ]

[ { "content": "Classify the topics of this COVID-19 literature paragraph by selecting from these categories:\n\n- Epidemic Forecasting: Predictions about COVID-19 spread\n- Treatment: Therapeutic methods or medication\n- Prevention: Measures to prevent spread\n- Mechanism: Biological mechanisms of the virus\n- Case Report: Report of a COVID-19 case\n- Transmission: How COVID-19 is transmitted\n- Diagnosis: Diagnosing COVID-19 in individuals\n\nYour output should be a valid JSON array with topics in double quotes and separated by commas. No additional text should be included.\n\nArticle:\n\nThe COVID-19 epidemic originating in China has spread rapidly worldwide and converted to pandemic proportions in March 2020. In India and densely populated countries like Brazil and USA the numbers are still rising. Clinicians all over the world are trying to contain it by minimizing the cross-transmission of disease among hospital staff members. In the field of Otorhinolaryngology (ENT) the doctors are exposed to high viral load while examining the patients. Therefore contingency plans are required for dealing with patients in outpatient clinics, and while performing diagnostic endoscopies, minor procedures in OPD and surgeries in operating rooms. Infected patients may shed severe acute respiratory syndrome coronavirus-2 particles into their environment via body secretions. Therefore, Otolaryngologists should be vigilant. In this submission, we share our experience of an innovative practice plan in redesigning the ENT OPD setup, endoscopy set up and OT so as to reduce the risk of transmission of virus not only to doctors but other healthcare workers. We hope that our modifications will serve as a guide for every Otolaryngologist throughout India towards performing their clinical duties confidently without any apprehension and ensuring adequate safety during this testing times in their small set-up/ clinical establishments.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Find all [\"Chemical\"] entities in this text. Output a JSON object.\n\nText:\nTransformation of paralytic shellfish poisoning toxins in UK surf clams (Spisula solida) for targeted production of reference materials. The periodic occurrence of Paralytic Shellfish Poisoning (PSP) toxins in UK surf clams and the recent move away from biological assays for PSP testing resulted in the need to determine method performance characteristics for the replacement analytical method in this species. With the requirement for laboratory reference materials to aid this validation together with known issues relating to toxin transformation in live clams and homogenised tissue, there was the need to assess the toxin transformation characteristics of PSP toxins in surf clam tissue. Initial work examined the rates of toxin transformation in UK surf clam tissue incubated with toxin standards, showing rapid transformation of N-sulfocarbamoyl toxins with slower transformation of carbamate toxins. Full transformational pathways were determined using a combination of three different analytical methods and confirmed the major expected transformations involving decarbamoylation, with some evidence for additional reaction pathways. Results obtained from the analysis of surf clam and oyster tissues incubated with varying concentrations of toxic Alexandrium algae highlighted expected transformation reactions, although significant differences were observed in the extent of the transformations amongst the range of toxins studied, with less efficient transformation of N-hydroxylated toxins as compared with other carbamate and N-sulfocarbamoyl toxins. Analysis of PSP-toxic incurred oyster, scallop and mussel tissues incubated with variable proportions of surf clam tissue showed large differences in the extent of the transformations. Total conversion of N-sulfocarbamoyl toxins was confirmed at low relative proportions of surf clam tissue in all three species, whereas transformation of carbamate toxins was found to occur only in the presence of higher proportions of surf clam tissue in oysters and mussels in comparison with scallops. Results enabled the production of three laboratory reference materials prepared following incubation of incurred homogenates with optimum proportions of surf clam tissue, resulting in materials containing a large number of PSP toxins. Stability experiments provided good preliminary evidence for the stability of these targeted materials under storage conditions. The work therefore provides both additional information relating to the transformational activity in UK surf clams and highlights a good potential method for the targeted production of reference materials which include a wider range of toxins than normally present in naturally incurred shellfish.", "role": "user" }, { "content": "{\"Chemical\": [\"N-sulfocarbamoyl\", \"carbamate and N-sulfocarbamoyl\", \"N\", \"carbamate\"]}", "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: Procedural Reasoning Networks for Understanding Multimodal Procedures\n\nThis paper addresses the problem of comprehending procedural commonsense knowledge. This is a challenging task as it requires identifying key entities, keeping track of their state changes, and understanding temporal and causal relations. Contrary to most of the previous work, in this study, we do not rely on strong inductive bias and explore the question of how multimodality can be exploited to provide a complementary semantic signal. Towards this end, we introduce a new entity-aware neural comprehension model augmented with external relational memory units. Our model learns to dynamically update entity states in relation to each other while reading the text instructions. Our experimental analysis on the visual reasoning tasks in the recently proposed RecipeQA dataset reveals that our approach improves the accuracy of the previously reported models by a large margin. Moreover, we find that our model learns effective dynamic representations of entities even though we do not use any supervision at the level of entity states.\n\nIntroduction\nA great deal of commonsense knowledge about the world we live is procedural in nature and involves steps that show ways to achieve specific goals. Understanding and reasoning about procedural texts (e.g. cooking recipes, how-to guides, scientific processes) are very hard for machines as it demands modeling the intrinsic dynamics of the procedures BIBREF0, BIBREF1, BIBREF2. That is, one must be aware of the entities present in the text, infer relations among them and even anticipate changes in the states of the entities after each action. For example, consider the cheeseburger recipe presented in Fig. FIGREF2. The instruction “salt and pepper each patty and cook for 2 to 3 minutes on the first side” in Step 5 entails mixing three basic ingredients, the ground beef, salt and pepper, together and then applying heat to the mix, which in turn causes chemical changes that alter both the appearance and the taste. From a natural language understanding perspective, the main difficulty arises when a model sees the word patty again at a later stage of the recipe. It still corresponds to the same entity, but its form is totally different.\nOver the past few years, many new datasets and approaches have been proposed that address this inherently hard problem BIBREF0, BIBREF1, BIBREF3, BIBREF4. To mitigate the aforementioned challenges, the existing works rely mostly on heavy supervision and focus on predicting the individual state changes of entities at each step. Although these models can accurately learn to make local predictions, they may lack global consistency BIBREF3, BIBREF4, not to mention that building such annotated corpora is very labor-intensive. In this work, we take a different direction and explore the problem from a multimodal standpoint. Our basic motivation, as illustrated in Fig. FIGREF2, is that accompanying images provide complementary cues about causal effects and state changes. For instance, it is quite easy to distinguish raw meat from cooked one in visual domain.\nIn particular, we take advantage of recently proposed RecipeQA dataset BIBREF2, a dataset for multimodal comprehension of cooking recipes, and ask whether it is possible to have a model which employs dynamic representations of entities in answering questions that require multimodal understanding of procedures. To this end, inspired from BIBREF5, we propose Procedural Reasoning Networks (PRN) that incorporates entities into the comprehension process and allows to keep track of entities, understand their interactions and accordingly update their states across time. We report that our proposed approach significantly improves upon previously published results on visual reasoning tasks in RecipeQA, which test understanding causal and temporal relations from images and text. We further show that the dynamic entity representations can capture semantics of the state information in the corresponding steps.\n\nProcedural Reasoning Networks ::: Attention Module\nAttention module is in charge of linking the question with the recipe text and the entities present in the recipe. It takes the matrices $\\mathbf {Q^{\\prime }}$ and $\\mathbf {R}^{\\prime }$ from the input module, and $\\mathbf {E}$ from the reasoning module and constructs the question-aware recipe representation $\\mathbf {G}$ and the question-aware entity representation $\\mathbf {Y}$. Following the attention flow mechanism described in BIBREF14, we specifically calculate attentions in four different directions: (1) from question to recipe, (2) from recipe to question, (3) from question to entities, and (4) from entities to question.\nThe first two of these attentions require computing a shared affinity matrix $\\mathbf {S}^R \\in \\mathbb {R}^{N \\times M}$ with $\\mathbf {S}^R_{i,j}$ indicating the similarity between $i$-th recipe word and $j$-th image in the question estimated by\nwhere $\\mathbf {w}^{\\top }_{R}$ is a trainable weight vector, $\\circ $ and $[;]$ denote elementwise multiplication and concatenation operations, respectively.\nRecipe-to-question attention determines the images within the question that is most relevant to each word of the recipe. Let $\\mathbf {\\tilde{Q}} \\in \\mathbb {R}^{2d \\times N}$ represent the recipe-to-question attention matrix with its $i$-th column being given by $ \\mathbf {\\tilde{Q}}_i=\\sum _j \\mathbf {a}_{ij}\\mathbf {Q}^{\\prime }_j$ where the attention weight is computed by $\\mathbf {a}_i=\\operatorname{softmax}(\\mathbf {S}^R_{i}) \\in \\mathbb {R}^M$.\nQuestion-to-recipe attention signifies the words within the recipe that have the closest similarity to each image in the question, and construct an attended recipe vector given by $ \\tilde{\\mathbf {r}}=\\sum _{i}\\mathbf {b}_i\\mathbf {R}^{\\prime }_i$ with the attention weight is calculated by $\\mathbf {b}=\\operatorname{softmax}(\\operatorname{max}_{\\mathit {col}}(\\mathbf {S}^R)) \\in \\mathbb {R}^{N}$ where $\\operatorname{max}_{\\mathit {col}}$ denotes the maximum function across the column. The question-to-recipe matrix is then obtained by replicating $\\tilde{\\mathbf {r}}$ $N$ times across the column, giving $\\tilde{\\mathbf {R}} \\in \\mathbb {R}^{2d \\times N}$.\nThen, we construct the question aware representation of the input recipe, $\\mathbf {G}$, with its $i$-th column $\\mathbf {G}_i \\in \\mathbb {R}^{8d \\times N}$ denoting the final embedding of $i$-th word given by\nAttentions from question to entities, and from entities to question are computed in a way similar to the ones described above. The only difference is that it uses a different shared affinity matrix to be computed between the memory encoding entities $\\mathbf {E}$ and the question $\\mathbf {Q}^{\\prime }$. These attentions are then used to construct the question aware representation of entities, denoted by $\\mathbf {Y}$, that links and integrates the images in the question and the entities in the input recipe.\n\nProcedural Reasoning Networks ::: Modeling Module\nModeling module takes the question-aware representations of the recipe $\\mathbf {G}$ and the entities $\\mathbf {Y}$, and forms their combined vector representation. For this purpose, we first use a two-layer BiLSTM to read the question-aware recipe $\\mathbf {G}$ and to encode the interactions among the words conditioned on the question. For each direction of BiLSTM , we use its hidden state after reading the last token as its output. In the end, we obtain a vector embedding $\\mathbf {c} \\in \\mathbb {R}^{2d \\times 1}$. Similarly, we employ a second BiLSTM, this time, over the entities $\\mathbf {Y}$, which results in another vector embedding $\\mathbf {f} \\in \\mathbb {R}^{2d_E \\times 1}$. Finally, these vector representations are concatenated and then projected to a fixed size representation using $\\mathbf {o}=\\varphi _o(\\left[\\mathbf {c}; \\mathbf {f}\\right]) \\in \\mathbb {R}^{2d \\times 1}$ where $\\varphi _o$ is a multilayer perceptron with $\\operatorname{tanh}$ activation function.\n\nProcedural Reasoning Networks ::: Output Module\nThe output module takes the output of the modeling module, encoding vector embeddings of the question-aware recipe and the entities $\\mathbf {Y}$, and the embedding of the answer $\\mathbf {A}$, and returns a similarity score which is used while determining the correct answer. Among all the candidate answer, the one having the highest similarity score is chosen as the correct answer. To train our proposed procedural reasoning network, we employ a hinge ranking loss BIBREF15, similar to the one used in BIBREF2, given below.\nwhere $\\gamma $ is the margin parameter, $\\mathbf {a}_+$ and $\\mathbf {a}_{-}$ are the correct and the incorrect answers, respectively.\n\nExperiments\nIn this section, we describe our experimental setup and then analyze the results of the proposed Procedural Reasoning Networks (PRN) model.\n\nExperiments ::: Entity Extraction\nGiven a recipe, we automatically extract the entities from the initial step of a recipe by using a dictionary of ingredients. While determining the ingredients, we exploit Recipe1M BIBREF16 and Kaggle What’s Cooking Recipes BIBREF17 datasets, and form our dictionary using the most commonly used ingredients in the training set of RecipeQA. For the cases when no entity can be extracted from the recipe automatically (20 recipes in total), we manually annotate those recipes with the related entities.\n\nExperiments ::: Training Details\nIn our experiments, we separately trained models on each task, as well as we investigated multi-task learning where a single model is trained to solve all these tasks at once. In total, the PRN architecture consists of $\\sim $12M trainable parameters. We implemented our models in PyTorch BIBREF18 using AllenNLP library BIBREF6. We used Adam optimizer with a learning rate of 1e-4 with an early stopping criteria with the patience set to 10 indicating that the training procedure ends after 10 iterations if the performance would not improve. We considered a batch size of 32 due to our hardware constraints. In the multi-task setting, batches are sampled round-robin from all tasks, where each batch is solely composed of examples from one task. We performed our experiments on a system containing four NVIDIA GTX-1080Ti GPUs, and training a single model took around 2 hours. We employed the same hyperparameters for all the baseline systems. We plan to share our code and model implementation after the review process.\n\nExperiments ::: Baselines\nWe compare our model with several baseline models as described below. We note that the results of the first two are previously reported in BIBREF2.\nHasty Student BIBREF2 is a heuristics-based simple model which ignores the recipe and gives an answer by examining only the question and the answer set using distances in the visual feature space.\nImpatient Reader BIBREF19 is a simple neural model that takes its name from the fact that it repeatedly computes attention over the recipe after observing each image in the query.\nBiDAF BIBREF14 is a strong reading comprehension model that employs a bi-directional attention flow mechanism to obtain a question-aware representation and bases its predictions on this representation. Originally, it is a span-selection model from the input context. Here, we adapt it to work in a multimodal setting and answer multiple choice questions instead.\nBiDAF w/ static memory is an extended version of the BiDAF model which resembles our proposed PRN model in that it includes a memory unit for the entities. However, it does not make any updates on the memory cells. That is, it uses the static entity embeeddings initialized with GloVe word vectors. We propose this baseline to test the significance of the use of relational memory updates.\n\nExperiments ::: Results\nTable TABREF29 presents the quantitative results for the visual reasoning tasks in RecipeQA. In single-task training setting, PRN gives state-of-the-art results compared to other neural models. Moreover, it achieves the best performance on average. These results demonstrate the importance of having a dynamic memory and keeping track of entities extracted from the recipe. In multi-task training setting where a single model is trained to solve all the tasks at once, PRN and BIDAF w/ static memory perform comparably and give much better results than BIDAF. Note that the model performances in the multi-task training setting are worse than single-task performances. We believe that this is due to the nature of the tasks that some are more difficult than the others. We think that the performance could be improved by employing a carefully selected curriculum strategy BIBREF20.\nIn Fig. FIGREF28, we illustrate the entity embeddings space by projecting the learned embeddings from the step-by-step memory snapshots through time with t-SNE to 3-d space from 200-d vector space. Color codes denote the categories of the cooking recipes. As can be seen, these step-aware embeddings show clear clustering of these categories. Moreover, within each cluster, the entities are grouped together in terms of their state characteristics. For instance, in the zoomed parts of the figure, chopped and sliced, or stirred and whisked entities are placed close to each other.\nFig. FIGREF30 demonstrates the entity arithmetics using the learned embeddings from each entity step. Here, we show that the learned embedding from the memory snapshots can effectively capture the contextual information about the entities at each time point in the corresponding step while taking into account of the recipe data. This basic arithmetic operation suggests that the proposed model can successfully capture the semantics of each entity's state in the corresponding step.\n\nAcknowledgements\nWe thank the anonymous reviewers and area chairs for their invaluable feedback. This work was supported by TUBA GEBIP fellowship awarded to E. Erdem; and by the MMVC project via an Institutional Links grant (Project No. 217E054) under the Newton-Katip Çelebi Fund partnership funded by the Scientific and Technological Research Council of Turkey (TUBITAK) and the British Council. We also thank NVIDIA Corporation for the donation of GPUs used in this research.\n\nFigure 2: An illustration of our Procedural Reasoning Networks (PRN). For a sample question from visual coherence task in RecipeQA, while reading the cooking recipe, the model constantly performs updates on the representations of the entities (ingredients) after each step and makes use of their representations along with the whole recipe when it scores a candidate answer. Please refer to the main text for more details.\n\nFigure 3: Sample visualizations of the self-attention weights demonstrating both the interactions among the ingredients and between the ingredients and the textual instructions throughout the steps of a sample cooking recipe from RecipeQA (darker colors imply higher attention weights). The attention maps do not change much after the third step as the steps after that mostly provide some redundant information about the completed recipe.\n\nFigure 4: t-SNE visualizations of learned embeddings from each memory snapshot mapping to each entity and their corresponding states from each step for visual cloze task.\n\nFigure 5: Step-aware entity representations can be used to discover the changes occurred in the states of the ingredients between two different recipe steps. The difference vector between two entities can then be added to other entities to find their next states. For instance, in the first example, the difference vector encodes the chopping action done on onions. In the second example, it encodes the pouring action done on the water. When these vectors are added to the representations of raw tomatoes and milk, the three most likely next states capture the semantics of state changes in an accurate manner.\n\nQuestion: What are previously reported models?", "role": "user" }, { "content": "{\"answer\": [\"Hasty Student\", \"Impatient Reader\", \"BiDAF\", \"BiDAF w/ static memory\"], \"evidence\": [\"We compare our model with several baseline models as described below. We note that the results of the first two are previously reported in BIBREF2.\", \"Hasty Student BIBREF2 is a heuristics-based simple model which ignores the recipe and gives an answer by examining only the question and the answer set using distances in the visual feature space.\", \"Impatient Reader BIBREF19 is a simple neural model that takes its name from the fact that it repeatedly computes attention over the recipe after observing each image in the query.\", \"BiDAF BIBREF14 is a strong reading comprehension model that employs a bi-directional attention flow mechanism to obtain a question-aware representation and bases its predictions on this representation. Originally, it is a span-selection model from the input context. Here, we adapt it to work in a multimodal setting and answer multiple choice questions instead.\", \"BiDAF w/ static memory is an extended version of the BiDAF model which resembles our proposed PRN model in that it includes a memory unit for the entities. However, it does not make any updates on the memory cells. That is, it uses the static entity embeeddings initialized with GloVe word vectors. We propose this baseline to test the significance of the use of relational memory updates.\"]}", "role": "assistant" } ]