Datasets:

---

kejian

/

SciRIFF-4096-0214-v2

like 0

[ { "content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: Pembrolizumab in Patients With Advanced Triple-Negative Breast Cancer: Phase Ib KEYNOTE-012 Study.\nSummary: PURPOSE Immune checkpoint inhibition has been demonstrated to be an effective anticancer strategy . Several lines of evidence support the study of immunotherapy in triple-negative breast cancer ( TNBC ) . We assessed the safety and antitumor activity of the programmed cell death protein 1 ( PD-1 ) inhibitor pembrolizumab in patients with advanced TNBC . METHODS KEYNOTE-012 ( Clinical Trials.gov identifier : NCT01848834 ) was a multicenter , nonr and omized phase Ib trial of single-agent pembrolizumab given intravenously at 10 mg/kg every 2 weeks to patients with advanced PD-L1-positive ( expression in stroma or ≥ 1 % of tumor cells by immunohistochemistry ) TNBC , gastric cancer , urothelial cancer , and head and neck cancer . This report focuses on the TNBC cohort . RESULTS Among 111 patients with TNBC whose tumor sample s were screened for PD-L1 expression , 58.6 % had PD-L1-positive tumors . Thirty-two women ( median age , 50.5 years ; range , 29 to 72 years ) were enrolled and assessed for safety and antitumor activity . The median number of doses administered was five ( range , 1 to 36 doses ) . Common toxicities were mild and similar to those observed in other tumor cohorts ( eg , arthralgia , fatigue , myalgia , and nausea ) , and included five ( 15.6 % ) patients with grade ≥ 3 toxicity and one treatment-related death . Among the 27 patients who were evaluable for antitumor activity , the overall response rate was 18.5 % , the median time to response was 17.9 weeks ( range , 7.3 to 32.4 weeks ) , and the median duration of response was not yet reached ( range , 15.0 to ≥ 47.3 weeks ) . CONCLUSION This phase Ib study describes preliminary evidence of clinical activity and a potentially acceptable safety profile of pembrolizumab given every 2 weeks to patients with heavily pretreated , advanced TNBC . A single-agent phase II study examining a 200-mg dose given once every 3 weeks ( Clinical Trials.gov identifier : NCT02447003 ) is ongoing\n\n\nReport 2:\nTitle: Tumor-associated lymphocytes as an independent predictor of response to neoadjuvant chemotherapy in breast cancer.\nSummary: PURPOSE Pre clinical data suggest a contribution of the immune system to chemotherapy response . In this study , we investigated the prespecified hypothesis that the presence of a lymphocytic infiltrate in cancer tissue predicts the response to neoadjuvant chemotherapy . METHODS We investigated intratumoral and stromal lymphocytes in a total of 1,058 pretherapeutic breast cancer core biopsies from two neoadjuvant anthracycline/taxane-based studies ( GeparDuo , n = 218 , training cohort ; and GeparTrio , n = 840 , validation cohort ) . Molecular parameters of lymphocyte recruitment and activation were evaluated by kinetic polymerase chain reaction in 134 formalin-fixed , paraffin-embedded tumor sample s. Results In a multivariate regression analysis including all known predictive clinicopathologic factors , the percentage of intratumoral lymphocytes was a significant independent parameter for pathologic complete response ( pCR ) in both cohorts ( training cohort : P = .012 ; validation cohort : P = .001 ) . Lymphocyte-predominant breast cancer responded , with pCR rates of 42 % ( training cohort ) and 40 % ( validation cohort ) . In contrast , those tumors without any infiltrating lymphocytes had pCR rates of 3 % ( training cohort ) and 7 % ( validation cohort ) . The expression of inflammatory marker genes and proteins was linked to the histopathologic infiltrate , and logistic regression showed a significant association of the T-cell-related markers CD3D and CXCL9 with pCR . CONCLUSION The presence of tumor-associated lymphocytes in breast cancer is a new independent predictor of response to anthracycline/taxane neoadjuvant chemotherapy and provides useful information for oncologists to identify a subgroup of patients with a high benefit from this type of chemotherapy\n\n\nReport 3:\nTitle: Tumor-infiltrating CD8+ lymphocytes predict clinical outcome in breast cancer.\nSummary: Breast carcinomas are often infiltrated by inflammatory cells , particularly macrophages and T lymphocytes , but the significance of these cells remains unclear . One possible role of these inflammatory cells is that they represent a cell-mediated immune response against the carcinoma . CD8(+ ) lymphocytes are a known crucial component of cell-mediated immunity . The purpose of this study was to explore the prognostic value of tumor-infiltrating CD8(+ ) cytotoxic lymphocytes in breast cancer . Tumor-infiltrating CD8(+ ) lymphocytes were assessed by immunohistochemical staining of tissue microarray cores from 1,334 unselected breast tumors from patients with long-term follow-up . The number of CD8(+ ) T cells was counted in tumor nests ( intratumoral ) , in stroma adjacent to tumor cells , and in stroma distant to tumor cells , and their relationship with clinical outcome was determined . The total number of CD8(+ ) cells was positively correlated with tumor grade ( r(s ) = 0.20 ; P < .001 ) and inversely correlated with patient 's age at diagnosis , estrogen receptor-alpha ( ER-α ) , and progesterone receptor ( PgR ) expression ( Mann-Whitney U test , P < .001 ) . The total patient cohort was r and omly divided into two separate training and validation sets before performing univariate survival analysis . Total number and distant stromal CD8(+ ) lymphocytes were associated with better patient survival ( P = .041 and P < .001 , respectively ) in the training set . In multivariate analysis , total CD8(+ ) T-cell count was an independent prognostic factor in both training and validation sets . These results suggest that tumor-infiltrating CD8(+ ) T lymphocytes have antitumor activity as judged by their favorable effect on patients ' survival and could potentially be exploited in the treatment of breast cancer\n\n\nReport 4:\nTitle: Tumor infiltrating lymphocytes are prognostic in triple negative breast cancer and predictive for trastuzumab benefit in early breast cancer: results from the FinHER trial.\nSummary: BACKGROUND We have previously shown the prognostic importance of tumor-infiltrating lymphocytes ( TILs ) in newly diagnosed triple-negative breast cancer ( TNBC ) using tumor sample s from a large clinical trial cohort . In this study , we aim ed to vali date these findings and also investigate associations with trastuzumab benefit in HER2-overexpressing disease ( HER2 + ) . PATIENTS AND METHODS A prospect ive-retrospective study was conducted using sample s from the FinHER adjuvant , phase III trial that enrolled 1010 early-stage BC patients , 778 of whom were HER2-nonamplified . Those with HER2 + disease ( n = 232 ) were r and omized to 9 weeks of trastuzumab or no trastuzumab in addition to chemotherapy . Two pathologists independently quantified stromal TILs in 935 ( 92.6 % ) available slides . The primary end point of distant disease-free survival ( DDFS ) and interactions with trastuzumab were studied in Cox regression models . RESULTS Confirming our previous findings , in TNBC ( n = 134 ) each 10 % increase in TILs was significantly associated with decreased distant recurrence in TNBC ; for DDFS the hazard ratio adjusted for clinicopathological factors : 0.77 ; 95 % confidence interval ( CI ) 0.61 - 0.98 , P = 0.02 . In HER2 + BC ( n = 209 ) , each 10 % increase in lymphocytic infiltration was significantly associated with decreased distant recurrence in patients r and omized to the trastuzumab arm ( DDFS P interaction = 0.025 ) . CONCLUSIONS Higher levels of TILs present at diagnosis were significantly associated with decreased distant recurrence rates in primary TNBC . These results confirm our previous data and further support that TILs should be considered as a robust prognostic factor in this BC subtype . We also report for the first time an association between higher levels of TILs and increased trastuzumab benefit in HER2 + disease . Further research into why some TN and HER2 + BCs can or can not generate a host antitumor immune response and how trastuzumab can favorably alter the immune microenvironment is warranted\n\n\nReport 5:\nTitle: Prognostic and predictive value of tumor-infiltrating lymphocytes in a phase III randomized adjuvant breast cancer trial in node-positive breast cancer comparing the addition of docetaxel to doxorubicin with doxorubicin-based chemotherapy: BIG 02-98.\nSummary: PURPOSE Previous pre clinical and clinical data suggest that the immune system influences prognosis and response to chemotherapy ( CT ) ; however , clinical relevance has yet to be established in breast cancer ( BC ) . We hypothesized that increased lymphocytic infiltration would be associated with good prognosis and benefit from immunogenic CT-in this case , anthracycline-only CT-in selected BC subtypes . PATIENTS AND METHODS We investigated the relationship between quantity and location of lymphocytic infiltrate at diagnosis with clinical outcome in 2009 node-positive BC sample s from the BIG 02 - 98 adjuvant phase III trial comparing anthracycline-only CT ( doxorubicin followed by cyclophosphamide , methotrexate , and fluorouracil [ CMF ] or doxorubicin plus cyclophosphamide followed by CMF ) versus CT combining doxorubicin and docetaxel ( doxorubicin plus docetaxel followed by CMF or doxorubicin followed by docetaxel followed by CMF ) . Readings were independently performed by two pathologists . Disease-free survival ( DFS ) , overall survival ( OS ) , and interaction with type of CT associations were studied . Median follow-up was 8 years . RESULTS There was no significant prognostic association in the global nor estrogen receptor ( ER ) -positive/human epidermal growth factor receptor 2 ( HER2 ) -negative population . However , each 10 % increase in intratumoral and stromal lymphocytic infiltrations was associated with 17 % and 15 % reduced risk of relapse ( adjusted P = .1 and P = .025 ) , respectively , and 27 % and 17 % reduced risk of death in ER-negative/HER2-negative BC regardless of CT type ( adjusted P = .035 and P = .023 ) , respectively . In HER2-positive BC , there was a significant interaction between increasing stromal lymphocytic infiltration ( 10 % increments ) and benefit with anthracycline-only CT ( DFS , interaction P = .042 ; OS , P = .018 ) . CONCLUSION In node-positive , ER-negative/HER2-negative BC , increasing lymphocytic infiltration was associated with excellent prognosis . Further validation of the clinical utility of tumor-infiltrating lymphocytes in this context is warranted . Our data also support the evaluation of immunotherapeutic approaches in selected BC subtypes\n\n\nReport 6:\nTitle: Tumor-infiltrating lymphocytes and response to neoadjuvant chemotherapy with or without carboplatin in human epidermal growth factor receptor 2-positive and triple-negative primary breast cancers.\nSummary: PURPOSE Modulation of immunologic interactions in cancer tissue is a promising therapeutic strategy . To investigate the immunogenicity of human epidermal growth factor receptor 2 ( HER2 ) -positive and triple-negative ( TN ) breast cancers ( BCs ) , we evaluated tumor-infiltrating lymphocytes ( TILs ) and immunologically relevant genes in the neoadjuvant GeparSixto trial . PATIENTS AND METHODS GeparSixto investigated the effect of adding carboplatin ( Cb ) to an anthracycline-plus-taxane combination ( PM ) on pathologic complete response ( pCR ) . A total of 580 tumors were evaluated before r and om assignment for stromal TILs and lymphocyte-predominant BC ( LPBC ) . mRNA expression of immune-activating ( CXCL9 , CCL5 , CD8A , CD80 , CXCL13 , IGKC , CD21 ) as well as immunosuppressive factors ( IDO1 , PD-1 , PD-L1 , CTLA4 , FOXP3 ) was measured in 481 tumors . RESULTS Increased levels of stromal TILs predicted pCR in univariable ( P < .001 ) and multivariable analyses ( P < .001 ) . pCR rate was 59.9 % in LPBC and 33.8 % for non-LPBC ( P < .001 ) . pCR rates ≥ 75 % were observed in patients with LPBC tumors treated with PMCb , with a significant test for interaction with therapy in the complete ( P = .002 ) and HER2-positive ( P = .006 ) , but not the TNBC , cohorts . Hierarchic clustering of mRNA markers revealed three immune subtypes with different pCR rates ( P < .001 ) . All 12 immune mRNA markers were predictive for increased pCR . The highest odds ratios ( ORs ) were observed for PD-L1 ( OR , 1.57 ; 95 % CI , 1.34 to 1.86 ; P < .001 ) and CCL5 ( OR , 1.41 ; 95 % CI , 1.23 to 1.62 ; P < .001 ) . CONCLUSION Immunologic factors were highly significant predictors of therapy response in the GeparSixto trial , particularly in patients treated with Cb . After further st and ardization , they could be included in histopathologic assessment of BC", "role": "user" }, { "content": "RESULTS We find that whilst factors such as TILs and certain subgroups of TILs ( e.g. , CD8 + and regulator T-cells ) have been extensively research ed , none of these markers are currently applicable to routine clinical practice .\nAlso , TNBC differs from other types of breast cancer with regards to cellular composition of the immune infiltrate and PD-L1 expression , and the prognostic significance of these .\nImmune-related factors have the potential as both prognostic and predictive biomarkers for new treatments targeting the immune system in breast cancer .", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nSuperbright Bioorthogonal Turn-on Probes**\n\nContent Extracts:\n\n<p>Visualizing biomolecular processes has been enhanced by combining fluorophores with bioorthogonal chemistry, resulting in new tools to study the complex biochemical milieu of living cells and organisms.[1] The resulting probes have been applied to image glycosylation and phospholipid uptake[2,3], cellular proteins[4–6], and intracellular drug distribution[7]. In some of these applications, the capacity of in situ chemical conjugation has been paired with fluorogenic turn-on, whereby fluorophore emission increases upon reaction with its bioorthogonal counterpart (\"turn-on\" probes).[8] This has the very attractive feature of reducing background fluorescence when doing in vivo imaging, potentially allowing real time imaging, without washing or clearance steps. For optimal performance, such a fluorogenic real-time reporter should be i) catalyst-free (to minimize toxicity and need for multiple reaction partners), ii) fast (to allow efficient imaging and temporal resolution) and iii) highly fluorescent after turn-on (to maximize signal and minimize background). Existing methods that exploit azide-phosphine, azide-alkyne, or inverse electron demand Diels-Alder tetrazine cycloadditions have only partially satisfied these criteria, resulting in subsets of probes with good fluorescence turn-on ratios but slow reaction kinetics and another subset with agreeably fast kinetics but only modest turn-on. What has been missing however, are exceptionally bright, fast, and biocompatible (water soluble, cell membrane permeable, non-toxic) probes with turn-on ratios exceeding 10x.</p><p>Previously described tetrazine-based probes achieve their fluorogenic turn-on by a unique mechanism, in which the tetrazine (Tz) chromophore is both quencher and bioorthogonal reactant.[8] In published studies, flexibly-linked Tz-fluorophore pairs—chosen for their ready synthetic accessibility—are quenched with moderate efficiency, yielding turn-on ratios on the order of 10–20 fold after reaction with dienophile targets.[3–5,8] Although intriguing applications have been demonstrated, the limited turn-on ratios almost always result in native background during imaging applications. In our estimation, a turn-on ratio of 102 would be preferable for robust utility in cellular imaging applications, and a ratio of 103 may be necessary for low abundance targets and super-resolution imaging.[9] Mechanistic observations have suggested that quenching in bichromophoric fluorophore-tetrazines occurs via Förster resonance energy transfer (FRET), offering a starting point for efforts to optimize turn-on.[8,10] Although its relatively weak visible light absorbance inherently limits the range of tetrazine as a FRET acceptor, Förster theory dictates that energy transfer efficiency will be crucially dependent upon inter-chromophore distance (varying as r6) and upon transition dipole alignment, which are both optimizable parameters.[11] As an alternative way of designing more efficient turn-on probes, one might consider adapting through-bond energy transfer (TBET) for fluorescence quenching. With these goals in mind, we synthesized a series of new bioorthogonal boron dipyrromethene (BODIPY)-tetrazine derivatives (Figure 1). These structures enhance spatial donor-acceptor proximity, provide predictable donor-acceptor transition dipole orientation, and afford the possibility of accessing alternate modes of fluorescence quenching.</p><p>In the course of selecting a design for these cassettes, we noted that a crystal structure of p-cyanophenyl-BODIPY 1 exhibited a 90 degree rotation between the BODIPY and phenyl ring, a conformation which prevents pi-system conjugation.[12] We speculated that a tetrazine attached to this phenyl ring would thus be spectrally decoupled from the fluorophore and capable of efficient FRET-based quenching. We therefore utilized recently-reported conditions for transition metal catalyzed tetrazine formation to directly install tetrazines on nitrile-derivatized BODIPY scaffolds (Figure 1).[13] On treatment of 1 with hydrazine, formamidine acetate, and 50 mol% nickel triflate, with DMF as a cosolvent, the major product observed was the dipyrromethene core of 1. When zinc triflate was used, however, we observed formation of the desired H-tetrazine 2a. The fluorescence enhancement observed on reaction of 2a with trans-cyclooctenol (TCO) in water (schematized in Figure 1) was characteristically fast and of significantly greater magnitude than previously reported Tz-fluorophore derivatives, with a turn-on ratio of several hundred fold (Figure 2c). However, it proved somewhat challenging to completely eliminate trace bright impurities from the reaction products. We therefore turned to the synthesis of methyltetrazine 2b, speculating that enhanced Tz stability would facilitate purification and precise quantification.[14] With 50 mol% zinc triflate, hydrazine, and acetonitrile at 60C, we observed formation of both 2a and 2b in approximately equal quantities (Figure 1a). H-tetrazine formation was unexpected, as it has not been previously reported under these reaction conditions, but is likely derived from the DMF cosolvent. In sharp contrast to the parent compound 1, both 2a and 2b are modestly soluble in aqueous solution and almost completely non-fluorescent. The methyltetrazine derivative 2b could be isolated with a clean fluorescence baseline for accurate quantification (supporting information). Reaction of 2b with TCO in acetonitrile and in water allowed us to measure turn-on ratios of 340 and 900-fold, respectively (Table 1).</p><p>To explore configurational effects on turn-on efficiency, we moved the position of the tetrazine from para- to meta- on the phenyl ring. Structural modeling estimated that this one-bond shift reduces the inter-chromophore distance (center to center) from 8.4Å to 7Å. Condensation of dimethylpyrrole with 3-formylbenzonitrile, followed by routine oxidation with DDQ, deprotonation with Hünig's base, and boron complexation afforded the m-cyanophenyl-BODIPY 3 (supporting information). From this precursor, meta-Tz derivatives 4a and 4b were synthesized via the same reaction conditions as for 2. Impressively, these compounds exhibit even greater fluorogenic turn on, reaching 1100-fold in acetonitrile and 1600-fold in water for 4b (Table 1). Figure 2a plots the normalized fluorescence emission spectrum of 4b in acetonitrile before and after reaction with TCO; a logarithmic scale is necessary to visualize both spectra simultaneously. The fluorescence time-courses for representative compounds in acetonitrile appear in Figure 2b.</p><p>The exceptional fluorogenic turn-on of 2 and 4—as much as 100-fold greater than flexibly linked fluorophore-Tz conjugates—suggested that FRET may not be the sole quenching mechanism for these compounds. Burgess, Topp, and co-workers observed efficient through-bond energy transfer in cassettes that linked anthracene to BODIPY in a similar scaffold.[15] Coumarin-BODIPY and quinoline-BODIPY derivatives that exploit TBET have also been reported.[16] In each of these cases, excitation energy transfers from the attached donor chromophore into the BODIPY acceptor, whereas TBET in the reverse direction is the potential mechanism here. Redox-based quenching, such as via photoinduced-electron transfer (PET) from the excited BODIPY to the relatively electron-poor tetrazine ring, was judged unlikely, as the fluorescence emission intensity of 4b was found to be independent of solvent polarity (supporting information). [17]</p><p>The architectural hallmark of TBET is a conjugated, but not coplanar, pi-system, in which steric factors enforce a twist in the inter-chromophore linkage.[18] A three-dimensional structure of compound 4a (Figure 2b) illustrates these characteristic traits. Also depicted in the figure are the known orientation of the BODIPY transition dipole, and the likely orientation of the tetrazine S0->S1 (n->π*) absorption dipole, which is perpendicular to the plane of the Tz ring, as inferred from the known S0->S1 dipole of s-tetrazine.[19,20] Limited experimental data on the conformational behavior of aryl-tetrazines indicate a preference for coplanarity, as depicted, which brings the transition dipoles into parallel alignment.[19] Several practical features distinguish TBET from FRET, including insensitivity to spectral overlap (allowing donor chromophores to excite significantly red-shifted acceptors), decreased dependence on donor acceptor dipole alignment, and energy transfer kinetics (TBET is substantially faster, due to the lack of a strict orientational requirement).[18] In lieu of ultrafast spectroscopy studies, we elected to perturb the donor-acceptor geometry of the BODIPY-Tz derivatives and test the effect on fluorescence quenching.</p><p>Compounds 5a and 5b were synthesized starting from 2-iodo-pentamethyl BODIPY[21] (supporting information). An ortho-methyl group was added to enhance twist (i.e. minimize conjugation) of the phenyl linker. In these derivatives, the tetrazine and BODIPY transition dipoles are perpendicular irrespective of intramolecular bond rotation, a configuration in which Förster theory predicts FRET efficiency to be near zero.[11] Elegant confirmation of this prediction has been made with non-conjugated anthracene-porphyrin cassettes.[22] Upon reaction of 5b with TCO in acetonitrile, we observed a 120-fold turn-on, corresponding to >99% baseline quenching. This result stands in sharp contrast to both the Förster theory prediction and the exceptionally efficient transfer observed for 2 and 4. It is, however, consistent with the results observed for BODIPY-anthracene TBET cassettes, in which efficient energy transfer was observed in the perpendicular dipole configuration, but with slower kinetics than when the transition dipoles were aligned head to tail.[15] We anticipate that the tetrazine-TBET quenching mechanism can be extended to other fluorophores and other tetrazines, and that consideration of transition dipole orientation will be critical to the design of optimized turn-on probes.</p><p>Having advanced our understanding of the quenching mechanism, we sought to validate the utility of fluorogenic BODIPY-tetrazines for biological imaging (Figure 3). Both extracellular and intracellular TCO-labeled targets were readily visualized, with excellent signal intensity, very low background, and with no washing steps required after addition of the dye solution.</p><p>In summary, we report the synthesis and characterization of extraordinarily efficient bioorthogonal turn-on probes. We expect that these materials will find applications for live cell imaging, in pre-targeting, and perhaps in vivo imaging, i.e. applications where washing steps are difficult to achieve. Another unique application of the described materials may be for super-resolution microscopy,[24] to achieve new applications, faster reconstruction, or to address existing problems where fluorochrome crowding limits reconstructions.[25] Finally we anticipate that the described principles will find applications in the design of blue- and yellow/orange fluorochromes to widen the palette of available colors for in vivo imaging. Irrespective of the specific design, the described turn-on probes already have activation ratios that are up to two orders of magnitude higher than those previously reported.</p><p>Part of this work was supported by NHI RO1EB010011 and 2P50CA086355. JC was supported by a DFCI-MGH Hematology Oncology Fellowship. We thank Prof. Ralph Mazitschek for many insightful discussions, Dr. Katy Yang for cell culture assistance, Dr. Sarit Agasti for the gift of reagents, Alex Zaltsman for microscopy assistance, and Dr. Eszter Boros for her assistance with NMR spectroscopy.</p><p>Supporting information for this article is available on the WWW under http://www.angewandte.org or from the author.</p><p>a) Initial synthesis of BODIPY-p-Tz derivatives (2a,2b), schematic of fluorogenic reaction with trans-cyclooctenol (TCO), and observed turn-on in water. Reaction conditions: i = Zn(OTf)2, NH2NH2, acetonitrile, 60°C, 18hrs; ii = NaNO2; iii = HCl (1M). b) Synthesis of BODIPY-m-Tz derivatives (4a,4b) and fluorogenic turn-on in water; reaction conditions as in part a). c) Equatorial BODIPY-Tz derivatives (5a,5b) and observed turn-on upon reaction with TCO in acetonitrile.</p><p>a) Fluorescence emission spectra for compound 4b in acetonitrile at baseline (black) and after addition of TCO (green); excitation at 490nm. b) Normalized fluorescence turn-on after addition of TCO (240uM) to a solution of the indicated fluorophore (1uM) in acetonitrile. c) Equimolar solutions of compound 2a (at left) and 2a plus TCO (at right) under excitation by a handheld UV lamp. d) 3D model of compound 4a, illustrating a twisted phenyl linker between the BODIPY and tetrazine chromophores and the orientation of the donor and acceptor transition dipoles (gray arrows).</p><p>Biological application of activatable BODIPY. a) Fluorogenic imaging of EGFR expression on both fixed and live A-431 cells. Cells were incubated with TCO-conjugated monoclonal antibodies[23], washed, and then imaged immediately after the addition of 100nM BODIPY-Tz in PBS [see supporting information]. b) Fluorogenic live-cell imaging of nanoparticles internalized by RAW 264.7 cells. The nanoparticles are labeled with both TCO and with the near-infrared dye VT680[23], and were imaged in two channels after addition of 100nM BODIPY-Tz, demonstrating co-localization.</p><p>Quantum Yield and Fluorogenic Activation</p><p>Quantum yield for dihydropyridazine product; fluorescein in 0.1M NaOH (pH 13, Φ=0.925) was used as the standard.</p><p>Increase in peak fluorescence intensity at reaction completion; for experiments in water, 400nM BODIPY-Tz, and 1µM TCO were used.</p><p>Compound 5b is insufficiently soluble in water for this determination.</p>", "role": "user" }, { "content": "The fastest and the brightest: A new design that intimately connects tetrazine to a BODIPY fluorophore enables exceptionally efficient energy transfer and quenching. Upon reaction of the tetrazine, the brightness of the fluorophore increases more than a thousand-fold, a fluorogenic activation up to two orders of magnitude greater than previously described.", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nHomozygousCln3Deltaex7/8knock-inmiceexpressmultipleCln3mRNAsplicevariantsandmutantbatteninproteinthatisdetectablebybatp1antibodyrecognizingC-terminalepitopes[12].", "role": "user" }, { "content": "[\"mRNA\", \"protein\", \"C\"]", "role": "assistant" } ]

[ { "content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Mucosal effects of tenofovir 1% gel\nContent Overview:\nAbstract:\nTenofovir gel is being evaluated for vaginal and rectal pre-exposure prophylaxis against HIV transmission. Because this is a new prevention strategy, we broadly assessed its effects on the mucosa. In MTN-007, a phase-1, randomized, double-blinded rectal microbicide trial, we used systems genomics/proteomics to determine the effect of tenofovir 1% gel, nonoxynol-9 2% gel, placebo gel or no treatment on rectal biopsies( 15 subjects/arm). We also treated primary vaginal epithelial cells from four healthy women with tenofovir in vitro. After seven days of administration, tenofovir 1% gel had broad-ranging effects on the rectal mucosa, which were more pronounced than, but different from, those of the detergent nonoxynol-9. Tenofovir suppressed anti-inflammatory mediators, increased T cell densities, caused mitochondrial dysfunction, altered regulatory pathways of cell differentiation and survival, and stimulated epithelial cell proliferation. The breadth of mucosal changes induced by tenofovir indicates that its safety over longer-term topical use should be carefully monitored. Clinical trial registration: NCT01232803.\nIntroduction:\nThe HIV prevention field has invested considerable resources in testing the phosphonated nucleoside reverse transcriptase inhibitor( NRTI) tenofovir as a mucosally applied topical microbicide to prevent sexual HIV transmission. In a phase 2B trial, CAPRISA 004, pericoital tenofovir 1% gel was 39% efficacious in preventing vaginal HIV acquisition( Abdool Karim et al., 2010). However, in another phase 2B trial, the VOICE study( MTN-003), the daily vaginal tenofovir 1% gel arm was discontinued for futility( Marrazzo et al., 2015). Adherence to product use was low in VOICE, likely explaining the differences in findings between the two studies. Currently, the CAPRISA 004 study is being repeated in a phase 3 trial( FACTS 001 study). A reduced glycerin formulation of the vaginal tenofovir 1% gel for use as a rectal microbicide appears safe when evaluated by epithelial sloughing, fecal calprotectin, inflammatory cytokine mRNA/protein levels, and cellular immune activation markers( McGowan et al., 2013). However, because topical application of an antiretroviral drug to the mucosa is a novel prevention strategy without clinical precedent, we conducted a comprehensive systems biology assessment of tenofovir gel's effects on the mucosa.\nDiscussion:\nOur findings indicate that reduced glycerin rectal tenofovir 1% gel affects expression of a different and much broader range of genes than N-9 2% gel, potentially affecting mucosal immune homeostasis, mitochondrial function, and regulation of epithelial cell differentiation and survival. These results make biological sense given that tenofovir is a DNA chain terminator, with possible off-target effects in human cells( Lewis et al., 2003), and that topical application achieves at least 100-fold higher active drug concentrations in the mucosa than oral administration of 300 mg tenofovir disoproxil fumarate( Anton et al., 2012; Hendrix et al., 2013). Moreover, tenofovir caused similar changes in primary vaginal epithelial cells cultured from several healthy women. We did not find evidence that tenofovir directly causes inflammation, which is in keeping with our prior report that rectal tenofovir gel did not cause overt histological inflammation or increased mRNA/protein levels of a select panel of pro-inflammatory cytokines( McGowan et al., 2013). Rather, tenofovir dampened anti-inflammatory factors. Most prominently, it strongly inhibited IL-10 gene and protein expression, likely via blocking of CREB1 and its coactivator CREBBP( Martin et al., 2005; Woodgett and Ohashi, 2005; Gee et al., 2006; Alvarez et al., 2009). In addition, it suppressed signaling pathways downstream of TGF-β, a central anti-inflammatory mediator in the gut( Konkel and Chen, 2011; Surh and Sprent, 2012). Consequently, a number of chemokines were induced, such as the B lymphocyte chemoattractant CXCL13( Ansel et al., 2002), and CCL19 and CCL21, both ligands of CCR7 on T lymphocytes and dendritic cells( Forster et al., 2008). Correspondingly, CCR7, the B cell marker CD19, and the T cell markers CD2, CD3D and CD7 increased. In keeping with this, we observed higher densities of CD3+ and CD7+ T lymphocytes in the rectal mucosa following 7 days of tenofovir 1% gel use. In concert, these changes suggest that tenofovir creates a state of potential hyper-responsiveness to external inflammatory stimuli but does not itself cause inflammation. In populations who, unlike our MTN-007 study cohort, have a high incidence of mucosal infections and associated immune activation, this could potentially diminish the anti-viral protective effect of topical tenofovir prophylaxis( Naranbhai et al., 2012). Mitochondrial toxicity of nucleotide/nucleoside reverse transcriptase inhibitors such as tenofovir is well described but the mechanism remains unclear( Lewis et al., 2003). We found that tenofovir consistently inhibited expression of PNPT1, which encodes polynucleotide phosphorylase( PNPASE). PNPASE regulates nucleus-encoded RNA import into mitochondria( Wang et al., 2010). In PNPT1 knock-out mice, mitochondrial morphology and respiratory capacity are disrupted in a manner quite similar to the disruption in renal proximal tubular cells in patients with tenofovir-induced nephrotoxicity( Perazella, 2010; Wang et al., 2010). In our study, just 1 week of daily tenofovir 1% gel application lowered transcription of mitochondrial ATP6 by sixfold and caused visible ultrastructural mitochondrial changes. These findings suggest that tenofovir's suppression of PNPT1 expression may underlie its reported, but heretofore unexplained, mitochondrial toxicity. A number of changes in rectal biopsies and primary vaginal epithelial cells also suggested that tenofovir can cause increased epithelial proliferation. Furthermore, tenofovir's negative effect on mitochondrial function could lead to impairment of tumor progenitor cell apoptosis( Modica-Napolitano et al., 2007; Ni Chonghaile et al., 2011), as has been specifically reported for loss-of-function mutations of mtATP6, a mitochondrial gene strongly suppressed by tenofovir in our study( Shidara et al., 2005). Neoplastic pressure could also arise from the strong induction of KIAA0101 and UBD( ubiquitin D). KIAA0101 is important for regulation of DNA repair( Simpson et al., 2006), is increased in tumor tissues( Yu et al., 2001), and enhances cancer cell growth( Jain et al., 2011; Hosokawa et al., 2007). UBD appears to increase mitotic non-disjunction and chromosome instability( Ren et al., 2006, 2011) and is highly up-regulated in gastrointestinal cancers( Lee et al., 2003; Ren et al., 2006, 2011). Notably, though, these findings remain circumstantial, as there is no actual clinical evidence for carcinogenicity. Nevertheless, they raise the question of whether the relatively high concentrations of tenofovir achieved in the mucosa during topical use could potentially lead to neoplastic lesions with continuous and long-term use. According to Viread's Product Monograph, gastrointestinal tumorigenicity has been observed in mice after high oral dosing of tenofovir disoproxil fumarate. Vaginal tumorigenicity has been documented for azido-thymidine, an NRTI and DNA chain terminator like tenofovir, which induced vaginal hyperplasia and carcinomas when delivered to mice intravaginally as a 2% solution( ∼25% carcinoma rate)( Ayers et al., 1996). This is the first time that a systems biology approach has been applied to a clinical trial of mucosal pre-exposure prophylaxis, and our study shows the value of using these technologies for comprehensive mucosal safety assessment. Our findings raise concerns regarding the safety of topical tenofovir 1% gel in the rectum with long-term use. Tenofovir's effects on vaginal epithelial cells suggest similar activities in the vagina, which we are currently verifying in MTN-014, a phase I clinical trial comparing vaginal and rectal tenofovir 1% gel in a cross-over format. Further studies are required to gauge whether tenofovir, which has become a valuable cornerstone drug in treating HIV infection, can also be safely and effectively used as a vaginal or rectal microbicide.", "role": "user" }, { "content": "Tenofovir is a drug that can stop some viruses—including HIV—from multiplying . It is commonly used in multidrug therapies to control HIV infection . Clinical trials are underway to find out whether using the drug in the form of a gel applied to the vagina or rectum could be an effective way to prevent HIV transmission during sex . Some of the clinical trials carried out so far have produced promising results . However , since the use of gels containing anti-viral drugs is a new strategy for HIV prevention , there are limited data available about the safety of these products . Previous studies have shown that the concentration of tenofovir in the vagina is much higher in individuals using the gel than in those taking the tablet form of the drug . These high concentrations could lead to unexpected effects on the health of the cells exposed to the gel . Here , Hladik , Burgener , Ballweber et al . used a systems biology approach to look at the broad effects of tenofovir gel on tissue from the rectum . Tissue samples taken from the rectums of 15 patients who used tenofovir gel for seven days were compared with tissue samples taken from individuals who used a control gel that did not contain the drug or who did not use any gel . Genes that regulate inflammation were suppressed in the rectal tissue from patients who used tenofovir , as were genes that help these tissues regenerate and produce energy . The tissue from these patients also contained more immune cells , suggesting that their local immune systems were more active . Additionally , Hladik , Burgener , Ballweber et al . observed changes that could potentially lead to the increased growth of cells . Similar differences were also observed in vaginal cells that had been treated with tenofovir in the laboratory . These findings suggest that tenofovir delivered directly to the vagina or rectum may have unintentional local side effects . However , it is important to acknowledge that tenofovir gel has been evaluated in multiple studies that have not observed overt clinical adverse effects . Therefore , the implication of these findings is currently unclear and warrants further study .", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nPeptideslinkedtoKLH(keyholelimpethemacyanin)fromAcdp1N-andC-terminalsandtheconserveddomain(ACD)wereusedforgenerationofantibodiesspecificallyforAcdp1andallAcdpmembersasreported,respectively[5].", "role": "user" }, { "content": "[\"N\", \"C\"]", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Universal Reinforcement Learning Algorithms: Survey and Experiments \nChapter Title: Literature Survey \n1. Abstract of Cited Paper (BIB001): We introduce a new count-based optimistic exploration algorithm for Reinforcement Learning (RL) that is feasible in environments with high-dimensional state-action spaces. The success of RL algorithms in these domains depends crucially on generalisation from limited training experience. Function approximation techniques enable RL agents to generalise in order to estimate the value of unvisited states, but at present few methods enable generalisation regarding uncertainty. This has prevented the combination of scalable RL algorithms with efficient exploration strategies that drive the agent to reduce its uncertainty. We present a new method for computing a generalised state visit-count, which allows the agent to estimate the uncertainty associated with any state. Our \\phi-pseudocount achieves generalisation by exploiting same feature representation of the state space that is used for value function approximation. States that have less frequently observed features are deemed more uncertain. The \\phi-Exploration-Bonus algorithm rewards the agent for exploring in feature space rather than in the untransformed state space. The method is simpler and less computationally expensive than some previous proposals, and achieves near state-of-the-art results on high-dimensional RL benchmarks.\n\nReview Chapter:", "role": "user" }, { "content": "This survey covers history-based Bayesian algorithms; we choose history-based algorithms, as these are maximally general, and we restrict ourselves to Bayesian algorithms, as 1 The framework is named AIXIJS; the source code can be found at http://github.com/aslanides/aixijs. 2 A more comprehensive introduction and discussion including more experimental results can be found in the associated thesis at https://arxiv.org/abs/1705.07615. they are generally both principled and theoretically tractable. The universal Bayesian agent AIXI is a model of a maximally intelligent agent, and plays a central role in the sub-field of universal reinforcement learning (URL). Recently, AIXI has been shown to be flawed in important ways; in general it doesn't explore enough to be asymptotically optimal BIB002 , and it can perform poorly, even asymptotically, if given a bad prior BIB001 . Several variants of AIXI have been proposed to attempt to address these shortfalls: among them are entropyseeking BIB002 , information-seeking , Bayes with bursts of exploration , MDL agents , Thompson sampling , and optimism [Sunehag and Hutter, 2015] . It is worth emphasizing that these algorithms are models of rational behavior in general environments, and are not intended to be efficient or practical reinforcement learning algorithms. In this section, we provide a survey of the above algorithms, and of relevant theoretical results in the universal reinforcement learning literature.", "role": "assistant" } ]

[ { "content": "Analyze the given research paper excerpts and address the question provided. Extract the necessary information directly from the text. Your answer should be formatted as a JSON object with the following structure:\n\n\"answer\": A list of text segments from the paper that directly respond to the question.\n\"evidence\": A list of text segments from the paper where the answer can be found.\n\nIf the question cannot be answered with the given text, return \"null\".\n\nDocument: Careful Selection of Knowledge to solve Open Book Question Answering\n\nOpen book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA tasks that focus on linguistic understanding, OpenBookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.\n\nIntroduction\nNatural language based question answering (NLQA) not only involves linguistic understanding, but often involves reasoning with various kinds of knowledge. In recent years, many NLQA datasets and challenges have been proposed, for example, SQuAD BIBREF0 , TriviaQA BIBREF1 and MultiRC BIBREF2 , and each of them have their own focus, sometimes by design and other times by virtue of their development methodology. Many of these datasets and challenges try to mimic human question answering settings. One such setting is open book question answering where humans are asked to answer questions in a setup where they can refer to books and other materials related to their questions. In such a setting, the focus is not on memorization but, as mentioned in BIBREF3 , on “deeper understanding of the materials and its application to new situations BIBREF4 , BIBREF5 .” In BIBREF3 , they propose the OpenBookQA dataset mimicking this setting.\nThe OpenBookQA dataset has a collection of questions and four answer choices for each question. The dataset comes with 1326 facts representing an open book. It is expected that answering each question requires at least one of these facts. In addition it requires common knowledge. To obtain relevant common knowledge we use an IR system BIBREF6 front end to a set of knowledge rich sentences. Compared to reading comprehension based QA (RCQA) setup where the answers to a question is usually found in the given small paragraph, in the OpenBookQA setup the open book part is much larger (than a small paragraph) and is not complete as additional common knowledge may be required. This leads to multiple challenges. First, finding the relevant facts in an open book (which is much bigger than the small paragraphs in the RCQA setting) is a challenge. Then, finding the relevant common knowledge using the IR front end is an even bigger challenge, especially since standard IR approaches can be misled by distractions. For example, Table 1 shows a sample question from the OpenBookQA dataset. We can see the retrieved missing knowledge contains words which overlap with both answer options A and B. Introduction of such knowledge sentences increases confusion for the question answering model. Finally, reasoning involving both facts from open book, and common knowledge leads to multi-hop reasoning with respect to natural language text, which is also a challenge.\nWe address the first two challenges and make the following contributions in this paper: (a) We improve on knowledge extraction from the OpenBook present in the dataset. We use semantic textual similarity models that are trained with different datasets for this task; (b) We propose natural language abduction to generate queries for retrieving missing knowledge; (c) We show how to use Information Gain based Re-ranking to reduce distractions and remove redundant information; (d) We provide an analysis of the dataset and the limitations of BERT Large model for such a question answering task.\nThe current best model on the leaderboard of OpenBookQA is the BERT Large model BIBREF7 . It has an accuracy of 60.4% and does not use external knowledge. Our knowledge selection and retrieval techniques achieves an accuracy of 72%, with a margin of 11.6% on the current state of the art. We study how the accuracy of the BERT Large model varies with varying number of knowledge facts extracted from the OpenBook and through IR.\n\nRelated Work\nIn recent years, several datasets have been proposed for natural language question answering BIBREF0 , BIBREF1 , BIBREF2 , BIBREF8 , BIBREF9 , BIBREF10 , BIBREF11 , BIBREF12 , BIBREF13 and many attempts have been made to solve these challenges BIBREF7 , BIBREF14 , BIBREF15 .\nAmong these, the closest to our work is the work in BIBREF7 which perform QA using fine tuned language model and the works of BIBREF16 , BIBREF17 which performs QA using external knowledge.\nRelated to our work for extracting missing knowledge are the works of BIBREF18 , BIBREF19 , BIBREF20 which respectively generate a query either by extracting key terms from a question and an answer option or by classifying key terms or by Seq2Seq models to generate key terms. In comparison, we generate queries using the question, an answer option and an extracted fact using natural language abduction.\nThe task of natural language abduction for natural language understanding has been studied for a long time BIBREF21 , BIBREF22 , BIBREF23 , BIBREF24 , BIBREF25 , BIBREF26 , BIBREF27 , BIBREF28 . However, such works transform the natural language text to a logical form and then use formal reasoning to perform the abduction. On the contrary, our system performs abduction over natural language text without translating the texts to a logical form.\n\nOpenBook Knowledge Extraction\nTo retrieve a small set of relevant knowledge facts from the knowledge corpus $\\mathbf {F}$ , a textual similarity model is trained in a supervised fashion on two different datasets and the results are compared. We use the large-cased BERT BIBREF7 (BERT Large) as the textual similarity model.\nWe train it on the semantic textual similarity (STS-B) data from the GLUE dataset BIBREF31 . The trained model is then used to retrieve the top ten knowledge facts from corpus $\\mathbf {F}$ based on the STS-B scores. The STS-B scores range from 0 to 5.0, with 0 being least similar.\nWe generate the dataset using the gold OpenBookQA facts from $\\mathbf {F}$ for the train and validation set provided. To prepare the train set, we first find the similarity of the OpenBook $\\mathbf {F}$ facts with respect to each other using the BERT model trained on STS-B dataset. We assign a score 5.0 for the gold $\\mathbf {\\hat{F_i}}$ fact for a hypothesis. We then sample different facts from the OpenBook and assign the STS-B similarity scores between the sampled fact and the gold fact $\\mathbf {\\mathbf {\\hat{F}_{i}}}$ as the target score for that fact $\\mathbf {F_{ij}}$ and $\\mathbf {H_{ij}}$ . For example:\nHypothesis : Frilled sharks and angler fish live far beneath the surface of the ocean, which is why they are known as Deep sea animals. Gold Fact : deep sea animals live deep in the ocean : Score : 5.0 Sampled Facts : coral lives in the ocean : Score : 3.4 a fish lives in water : Score : 2.8 \nWe do this to ensure a balanced target score is present for each hypothesis and fact. We use this trained model to retrieve top ten relevant facts for each $\\mathbf {H_{ij}}$ from the knowledge corpus $\\mathbf {F}$ .\nQuestion: .. they decide the best way to save money is ? (A) to quit eating lunch out (B) to make more phone calls (C) to buy less with monopoly money (D) to have lunch with friends Knowledge extraction trained with STS-B: using less resources usually causes money to be saved a disperser disperses each season occurs once per year Knowledge extraction trained with OpenBookQA: using less resources usually causes money to be saved decreasing something negative has a positive impact on a thing conserving resources has a positive impact on the environment \nTable 3 shows a comparative study of our three approaches for OpenBook knowledge extraction. We show, the number of correct OpenBook knowledge extracted for all of the four answer options using the three approaches TF-IDF, BERT model trained on STS-B data and BERT model Trained on OpenBook data. Apart from that, we also show the count of the number of facts present precisely across the correct answer options. It can be seen that the Precision@N for the BERT model trained on OpenBook data is better than the other models as N increases.\nThe above example presents the facts retrieved from BERT model trained on OpenBook which are more relevant than the facts retrieved from BERT model trained on STS-B. Both the models were able to find the most relevant fact, but the other facts for STS-B model introduce more distractors and have lesser relevance. The impact of this is visible from the accuracy scores for the QA task in Table 3 . The best performance of the BERT QA model can be seen to be 66.2% using only OpenBook facts.\n\nQuestion Answering\nOnce the OpenBook knowledge facts $\\mathbf {F}$ and missing knowledge $\\mathbf {K}$ have been extracted, we move onto the task of answering the questions.\nWe use BERT Large model for the question answering task. For each question, we create a passage using the extracted facts and missing knowledge and fine-tune the BERT Large model for the QA task with one additional feed-forward layer for classification. The passages for the train dataset were prepared using the knowledge corpus facts, $\\mathbf {F}$ . We create a passage using the top N facts, similar to the actual gold fact $\\mathbf {\\hat{F}_i}$ , for the train set. The similarities were scored using the STS-B trained model (section \"Conclusion\" ). The passages for the training dataset do not use the gold missing knowledge $\\mathbf {\\hat{K}_i}$ provided in the dataset. For each of our experiments, we use the same trained model, with passages from different IR models.\nThe BERT Large model limits passage length to be lesser than equal to 512. This restricts the size of the passage. To be within the restrictions we create a passage for each of the answer options, and score for all answer options against each passage. We refer to this scoring as sum score, defined as follows:\nFor each answer options, $A_j$ , we create a passage $P_j$ and score against each of the answer options $A_i$ . To compute the final score for the answer, we sum up each individual scores. If $Q$ is the question, the score for the answer is defined as $\nPr(Q,A_i) = \\sum _{j=1}^{4}score(P_j,Q,A_i)\n$ \nwhere $score$ is the classification score given by the BERT Large model. The final answer is chosen based on, $\nA = \\operatornamewithlimits{arg\\,max}_A Pr(Q,A_i)\n$ \nIn the first round, we score each of the answer options using a passage created from the selected knowledge facts from corpus $\\mathbf {F}$ . For each question, we ignore the passages of the answer options which are in the bottom two. We refer to this as Passage Selection. In the second round, we score for only those passages which are selected after adding the missing knowledge $\\mathbf {K}$ .\nWe assume that the correct answer has the highest score in each round. Therefore we multiply the scores obtained after both rounds. We refer to this as Weighted Scoring. We define the combined passage selected scores and weighted scores as follows : $\nPr(\\mathbf {F},Q,A_i) = \\sum _{j=1}^{4}{score(P_j,Q,A_i)}\n$ \nwhere $P_j$ is the passage created from extracted OpenBook knowledge, F. The top two passages were selected based on the scores of $Pr(\\mathbf {F},Q,A_i)$ . $\nPr(\\mathbf {F}\\cup \\mathbf {K},Q,A_i) = \\sum _{k=1}^{4}{\\delta * score(P_k,Q,A_i)}\n$ \nwhere $\\delta =1$ for the top two scores and $\\delta =0$ for the rest. $P_k$ is the passage created using both the facts and missing knowledge. The final weighted score is : $\nwPr(Q,A_i) = Pr(\\mathbf {F},Q,A_i) * Pr(\\mathbf {F} \\cup \\mathbf {K},Q,A_i)\n$ \nThe answer is chosen based on the top weighted scores as below: $\nA = \\operatornamewithlimits{arg\\,max}_A wPr(Q,A_i)\n$ \nTable 4 shows the incremental improvement on the baselines after inclusion of carefully selected knowledge.\nPassage Selection and Weighted Scoring are used to overcome the challenge of boosted prediction scores due to cascading effect of errors in each stage.\nQuestion: What eat plants? (A) leopards (B) eagles (C) owls (D) robin Appropriate extracted Fact from $\\mathbf {F}$ : some birds eat plants Wrong Extracted Fact from $\\mathbf {F}$ : a salamander eats insects Wrong Retrieved Missing Knowledge: Leopard geckos eat mostly insects \nFor the example shown above, the wrong answer leopards had very low score with only the facts extracted from knowledge corpus $\\mathbf {F}$ . But introduction of missing knowledge from the wrong fact from $\\mathbf {F}$ boosts its scores, leading to wrong prediction. Passage selection helps in removal of such options and Weighted Scoring gives preference to those answer options whose scores are relatively high before and after inclusion of missing knowledge.\nNo Passage Selection and Weighted Scoring.\n\nDataset and Experimental Setup\nThe dataset of OpenBookQA contains 4957 questions in the train set and 500 multiple choice questions in validation and test respectively. We train a BERT Large based QA model using the top ten knowledge facts from the corpus $\\mathbf {F}$ , as a passage for both training and validation set. We select the model which gives the best score for the validation set. The same model is used to score the validation and test set with different passages derived from different methods of Abductive IR. The best Abductive IR model, the number of facts from $\\mathbf {F}$ and $\\mathbf {K}$ are selected from the best validation scores for the QA task.\n\nAcknowledgement\nWe thank NSF for the grant 1816039 and DARPA for partially supporting this research.\n\nFigure 1: Our approach\n\nTable 3: Compares (a) The number of correct facts that appears across any four passages (b) The number of correct facts that appears in the passage of the correct hypothesis (c) The accuracy for TF-IDF, BERT model trained on STS-B dataset and BERT model trained on OpenBook dataset. N is the number of facts considered.\n\nTable 4: Test Set Comparison of Different Components. Current state of the art (SOTA) is the Only Question model. K is retrieved from Symmetric Difference Model. KE refers to Knowledge Extraction.\n\nInquiry: How is OpenBookQA different from other natural language QA?", "role": "user" }, { "content": "{\"answer\": [\"in the OpenBookQA setup the open book part is much larger\", \"the open book part is much larger (than a small paragraph) and is not complete as additional common knowledge may be required\"], \"evidence\": [\"The OpenBookQA dataset has a collection of questions and four answer choices for each question. The dataset comes with 1326 facts representing an open book. It is expected that answering each question requires at least one of these facts. In addition it requires common knowledge. To obtain relevant common knowledge we use an IR system BIBREF6 front end to a set of knowledge rich sentences. Compared to reading comprehension based QA (RCQA) setup where the answers to a question is usually found in the given small paragraph, in the OpenBookQA setup the open book part is much larger (than a small paragraph) and is not complete as additional common knowledge may be required. This leads to multiple challenges. First, finding the relevant facts in an open book (which is much bigger than the small paragraphs in the RCQA setting) is a challenge. Then, finding the relevant common knowledge using the IR front end is an even bigger challenge, especially since standard IR approaches can be misled by distractions. For example, Table 1 shows a sample question from the OpenBookQA dataset. We can see the retrieved missing knowledge contains words which overlap with both answer options A and B. Introduction of such knowledge sentences increases confusion for the question answering model. Finally, reasoning involving both facts from open book, and common knowledge leads to multi-hop reasoning with respect to natural language text, which is also a challenge.\"]}", "role": "assistant" } ]

[ { "content": "Review the following segment from a research document in AI. Answer the subsequent query based solely on the provided information. Limit your response to the answer itself.\n\nResearch Segment: All networks were trained using SGD with momentum. An exponentially decaying learning rate was used in Section 3.1. For the rest of the experiments, a simpler commonly used strategy was employed where the learning rate starts at a value \\lambda and decays according to a fixed schedule by a factor \\gamma. \\lambda, \\gamma and the schedule were selected once based on validation set performance on the CIFAR-10 dataset, and kept fixed for all experiments.All convolutional highway networks utilize the rectified linear activation function [16] to compute the block state H. To provide a better estimate of the variability of classification results due to random initialization, we report our results in the format Best (mean \\pm std.dev.) based on 5 runs wherever available. Experiments were conducted using Caffe [33] and Brainstorm (https://github.com/IDSIA/brainstorm) frameworks. Source code, hyperparameter search results and related scripts are publicly available at http://people.idsia.ch/~rupesh/very_deep_learning/. We trained both plain and highway networks of varying varying depths on the MNIST digit classification dataset.All networks are thin: each layer has 50 blocks for highway networks and 71 units for plain networks, yielding roughly identical numbers of parameters (\\approx5000) per layer.In all networks, the first layer is a fully connected plain layer followed by 9, 19, 49, or 99 fully connected plain or highway layers. Finally, the network output is produced by a softmax layer.We performed a random search of 100 runs for both plain and highway networks to find good settings for the following hyperparameters: initial learning rate, momentum, learning rate exponential decay factor & activation function (either rectified linear or tanh). For highway networks, an additional hyperparameter was the initial value for the transform gate bias (between -1 and -10). Other weights were initialized using the same normalized initialization as plain networks.\n\nInquiry: What hyperparameters values were used to train both the plain and highway networks ?", "role": "user" }, { "content": "Both the plain network and the highway network set the best hyperparameters after 100 experiments.", "role": "assistant" } ]

[ { "content": "Examine the provided biomedical abstract. Identify and list entities based on the specified categories: [\"Brand\", \"Drug\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nFormat your findings as a JSON object: {\"Brand\": [\"Aspirin\", ...], \"DrugGroup\": [\"Salicylate\", ...], \"Drug\": [\"Phenobarbital\", ...], \"UnapprovedDrug\": [\"Heroin\", ...]}. Each key represents an entity type, and the corresponding value is a list of entities. If no entities are found for a type, use an empty list [].\n\nFocus solely on producing the JSON object.\n\nSource Text:\n\nThe use of codeine may result in additive CNS depressant effects when coadministered with alcohol, antihistamines, psychotropics or other drugs that produce CNS depression. Serious toxicity may result if dextromethorphan is coadministered with monoamine oxidase inhibitors (MAOIs). The use of dextromethorphan hydrobromide may result in additive CNS depressant effects when coadministered with alcohol, antihistamines, psychotropics or other drugs that produce CNS depression.", "role": "user" }, { "content": "{\"Brand\": [], \"Drug\": [\"dextromethorphan hydrobromide\", \"alcohol\", \"dextromethorphan\", \"codeine\"], \"DrugGroup\": [\"psychotropics\", \"monoamine oxidase inhibitors\", \"MAOIs\", \"antihistamines\"], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Nuclear genetic regulation of the human mitochondrial transcriptome\nContent Overview:\nAbstract:\nMitochondria play important roles in cellular processes and disease, yet little is known about how the transcriptional regime of the mitochondrial genome varies across individuals and tissues. By analyzing >11, 000 RNA-sequencing libraries across 36 tissue/cell types, we find considerable variation in mitochondrial-encoded gene expression along the mitochondrial transcriptome, across tissues and between individuals, highlighting the importance of cell-type specific and post-transcriptional processes in shaping mitochondrial-encoded RNA levels. Using whole-genome genetic data we identify 64 nuclear loci associated with expression levels of 14 genes encoded in the mitochondrial genome, including missense variants within genes involved in mitochondrial function( TBRG4, MTPAP and LONP1), implicating genetic mechanisms that act in trans across the two genomes. We replicate ~21% of associations with independent tissue-matched datasets and find genetic variants linked to these nuclear loci that are associated with cardio-metabolic phenotypes and Vitiligo, supporting a potential role for variable mitochondrial-encoded gene expression in complex disease.\nIntroduction:\nMitochondria are involved in a wide range of fundamental cellular processes, including cellular energy production, thermogenesis, lipid biosynthesis and cell death, and mutations in both nuclear and mitochondrial DNA( mtDNA) encoded genes have been linked to an array of different diseases( Taylor and Turnbull, 2005; He et al., 2010; Nunnari and Suomalainen, 2012; Hudson et al., 2014; Idaghdour and Hodgkinson, 2017). Most of the genes encoded in the mitochondrial genome are transcribed as one strand of RNA, and post-transcriptional processes are therefore particularly important for gene regulation. After transcription, poly-cistronic mitochondrial RNA is processed under the ‘punctuation model’ whereby transfer RNAs( tRNAs) that intersperse protein-coding regions are recognized for cleavage and the release of gene products( Ojala et al., 1981; Sanchez et al., 2011). Various processes including RNA modifications( Helm et al., 1998; Helm et al., 1999; Agris et al., 2007), further cleavage events( Mercer et al., 2011; Rackham et al., 2012), RNA degradation( Sasarman et al., 2010; Rackham et al., 2011) and translation rates then ultimately determine the levels of mitochondrial proteins available for utilization in the electron transport chain. Across tissues, different cell types have specific physiological requirements and thus variable energy demands. In mammals it has been shown that mitochondrial DNA replication( Herbers et al., 2019) and segregation( Jokinen et al., 2010), mitochondrial DNA copy number( Wachsmuth et al., 2016) and the abundance of nuclear-encoded mitochondrial proteins( Mootha et al., 2003) vary across cell types, perhaps as a way to match local energy requirements, however it is unclear whether regulation of the mitochondrial transcriptome varies across tissues. Understanding these processes is important, since many mitochondrial disorders are thought to be tissue specific( Koppen et al., 2007; Hämäläinen et al., 2013). Although the mitochondrial genome is transcribed, processed and translated within the mitochondria, almost all of the proteins required for these processes are coded for in the nuclear genome. Previous work has shown that the expression of a large number nuclear genes correlates with mitochondrial encoded gene expression( Mercer et al., 2011; Barshad et al., 2018), pointing to strong links between the two genomes, yet there is still not a complete understanding of which nuclear genes are directly involved in regulating the mitochondrial genome and how this might vary in different tissues, as well as whether nuclear genetic variation drives variation in these processes across individuals. Despite the wide-ranging impact of mitochondrial dysfunction on health and disease, to our knowledge only a single mitochondria-focussed study has been carried out comparing nuclear genome-wide genetic variation with mitochondrial encoded gene expression, which analysed two sets of ~70 samples and was underpowered to detect genetic variation acting across two genomes( Wang et al., 2014). More recently, studies have shown links between mitochondrial genome mutations and nuclear gene expression, identifying 11 significant associations( Kassam et al., 2016), as well as associations between single nucleotide polymorphisms( SNPs) in mitochondrial RNA-binding proteins and haplogroup-specific mtDNA encoded gene expression patterns in LCLs( Cohen et al., 2016), providing good evidence for regulatory links between the two genomes. In general, genetic variation associated with the expression of distal genes( trans expression quantitative trait loci( eQTLs)) has been more difficult to find due to the large statistical burden when comparing large numbers of variants and genes, and very few significant associations have been replicated in independent datasets( Innocenti et al., 2011; Kirsten et al., 2015; GTEx Consortium et al., 2017). Here we aim to characterize variation in mitochondrial encoded gene expression across >11, 000 RNA sequencing libraries for 36 different tissue/cell types. We also aim to identify genetic links between the mitochondrial and nuclear genomes through the detection of trans-genome eQTLs, not only to evidence occasions where genetic mechanisms act at long range across different genetic regions, but also to identify novel genes and genetic variation in the nuclear genome that are associated with fundamental processes taking place in human mitochondria.\nDiscussion:\nDespite key roles for mitochondria in a range of fundamental biological processes, as well as a wide array of human diseases, knowledge of how the mitochondrial transcriptome is processed across different individuals and tissues on a population scale is incomplete. Using RNA sequencing data for a large number of individuals and across a wide range of tissues, we find considerable variation in mitochondrial gene expression along the mitochondrial genome, across tissues and between individuals. Variation in mitochondrial encoded gene expression profiles is likely important for the cells ability to respond to changing energy demands in specific cell types and environments, and may also play a role in tissue specific disease processes across individuals. Through integrated analysis of genetic and RNA data, we identify a large number of common nuclear genetic variants associated with mitochondrial encoded gene expression and replicate a substantial fraction of these( ~21% after correcting for multiple testing, ~41% at nominal 5% with the same direction of effect) in independent tissue-matched datasets. Through mediation analysis and functional genetic variants we identify the potential causal nuclear gene influencing mitochondrial encoded gene expression in 36 cases. A large number of these genes are already known to play a role in mitochondrial processes, and thus validate our findings in a biological context, but also implicate functional mechanisms by which common nuclear genetic variation can act between chromosomes( and indeed, genomes) to influence gene expression. Such trans-eQTLs have been notoriously difficult to replicate in humans, and thus the 13 replicated associations identified in this study provide candidates to test the mechanisms associated with genetic variation that acts over large genetic distances. For some of the potential causal nuclear genes that we identify as being linked to variation in the expression mitochondrial-encoded genes, it is not difficult to speculate on potential mechanisms through which they might act. For example, MTPAP( within which we identify a missense mutation associated with the expression of MTND3 in LCLs) synthesizes the poly( A) tail of mitochondrial transcripts. Since polyadenylation of mitochondrial transcripts is required in many cases to complete the termination codon and is thought to influence RNA stability( Rackham et al., 2012), a functional mutation in this enzyme may lead to variable accumulation of unprocessed mitochondrial transcripts and ultimately influence mitochondrial encoded gene expression levels. Similarly, TBGR4( within which we identify a missense mutation associated with the expression of multiple mitochondrial genes in multiple tissues) is known to process mitochondrial precursor transcripts and stabilize some mature mitochondrial messenger RNAs( Boehm et al., 2017), thus having obvious links to changes in mitochondrial gene expression. These findings lay the foundation for future work to functionally validate the causal role of these genetic variants. Beyond this, we also identify nuclear genes through mediation analysis that have not previously been linked with mitochondrial gene expression. These results potentially point to novel roles for these proteins and thus may be important new targets in the context of mitochondrial disease in cases where it has thus far been difficult to identify causal mutations in patients. Examples that may be interesting for further study include ZFP90, a zinc finger protein that modulates nuclear gene expression. ZFP90 transgenic mice show altered expression of genes involved in oxidative phosphorylation and fatty acid elongation in mitochondria compared to wild type littermates( Yang et al., 2009), pointing to a potential role in mitochondrial processes. Similarly, CCM2 is involved in the stress-activated p38 mitogen-activated protein kinase( MAPK) signalling cascade and is thought to localize to the mitochondria. CCM proteins are implicated in Cerebral Cavernous Malformation and accumulating evidence points to a role for these proteins in processes related to mitochondrial function, including cellular responses to oxidative stress and autophagy( Retta and Glading, 2016). Finally, the common genetic variants we identify here as associated with mitochondrial encoded gene expression profiles across individuals potentially have downstream functional consequences that influence disease processes and risk. We find some evidence for this, as nuclear genetic variation associated with variable mitochondrial encoded gene expression is linked to mutations that have been implicated in blood pressure and Vitiligo, yet further study of these genes is required to identify the causal mechanisms that influence how mitochondrial RNA is processed in the cell and how dysregulation of these mechanisms may cause disease. Combined, these data now serve as a frame of reference for mitochondrial disease researchers who wish to consider how patient samples may vary in mitochondrial gene expression versus a healthy cohort in the relevant tissue type, and for the community as whole interested in the genes and genetics of fundamental processes taking place in mitochondria and the genetic architecture of gene expression.", "role": "user" }, { "content": "Mitochondria are like the batteries of our cells; they perform the essential task of turning nutrients into chemical energy . A cell relies on its mitochondria for its survival , but they are not completely under the cell’s control . Mitochondria have their own DNA , separate from the cell’s DNA which is stored in the nucleus . It contains a handful of genes , which carry the code for some of the important proteins needed for energy production . These proteins are made in the mitochondria themselves , and their levels are tweaked to meet the cell's current energy needs . To do this , mitochondria make copies of their genes and feed these copies into their own protein-production machinery . By controlling the number of gene copies they make , mitochondria can control the amount of protein they produce . But the process has several steps . The copies come in the form of a DNA-like molecule called RNA and , at first , they contain several genes connected one after the other . To access each gene , the mitochondria need to cut them up . They then process the fragments , fine-tuning the number of copies of each gene . This process – called gene expression – happens in the mitochondria , but they cannot do it on their own; they need proteins that are coded within the DNA in the cell nucleus . Genes in the cell nucleus can affect gene expression in the mitochondria , changing the cell's energy supply . Scientists do not yet know all of the genes involved , or how this might differ between different tissues or among different individuals . To find out , Ali et al . examined more than 11 , 000 records of RNA sequences from 36 different human cells and tissues , including blood , fat and skin . This revealed a large amount of variation in the expression of mitochondrial genes . The way the mitochondria processed their genes changed in different cells and in different people . To find out which genes in the nucleus were responsible for the differences in the mitochondria , the next step was to compare RNA levels from the mitochondria to the DNA sequences in the nucleus . This is because changes in the DNA sequence between different people – called genetic variants – can also affect how genes work , and how genes are expressed . This comparison revealed 64 genetic variants from DNA in the cell nucleus that are associated with the expression of genes in the mitochondria . Some of these had a known link to genetic variants involved in diseases like the skin condition vitiligo or high blood pressure . So , although mitochondria contain their own DNA , they rely on genes from the cell nucleus to function . Changes to the genes in the nucleus can alter the way that the mitochondria process their own genetic code . Understanding how these two sets of genes interact could reveal how and why mitochondria go wrong . This could aid in future research into illnesses like heart disease and cancer .", "role": "assistant" } ]

[ { "content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nRegulation of amino acid metabolism as a defensive strategy in the brain of three freshwater teleosts in response to high environmental ammonia exposure. Many teleosts have evolved mechanisms to cope with ammonia toxicity in the brain when confronted with high environmental ammonia (HEA). In the present study, the possible role of conversion of accumulated ammonia to glutamine and other free amino acids in the brain of three freshwater teleosts differing in their sensitivities to ammonia was investigated. The detoxification mode of ammonia in brain is suggested to be through amination of glutamate to glutamine by the coupled activities of glutamate dehydrogenase (GDH), transaminase (aspartate aminotransaminase 'AST' and alanine aminotransaminase 'ALT') and glutamine synthetase (GSase). We investigated the metabolic response of amino acids in the brain of highly sensitive salmonid Oncorhynchus mykiss (rainbow trout), the less sensitive cyprinid Cyprinus carpio (common carp) and the highly resistant cyprinid Carassius auratus (goldfish) when exposed to 1mM ammonia (as NH4HCO3; pH 7.9) for 0 h (control), 3 h, 12 h, 24 h, 48 h, 84 h and 180 h. Results show that HEA exposure increased ammonia accumulation significantly in the brain of all the three species from 12h onwards. Unlike in trout, ammonia accumulation in carp and goldfish was restored to control levels (48-84h); which was accompanied with a significant increase in glutamine content as well as GSase activity. In trout, glutamine levels also increased (84-180 h) but GSase was not activated. The elevated glutamine level in trout was accompanied by a significant depletion of the glutamate pool in contrast to the stable glutamate levels seen in carp and goldfish. This suggests a simultaneous increase in the rate of glutamate formation to match with the demand of glutamine formation in cyprinids. The activity of GDH was elevated significantly in carp and goldfish but remained unaltered in trout. Also, the transaminase enzymes (AST and ALT) were elevated significantly in exposed carp and goldfish while only ALT was up-regulated in trout. Consequently, in carp and goldfish both aspartate and alanine were utilized under HEA, whereas only alanine was consumed in trout. With ammonia treatment, significant changes in concentrations of other amino acids also occurred. None of the species could detoxify brain ammonia into urea. This study suggests that protective strategies to combat ammonia toxicity in brain are more pronounced in carp and goldfish than in trout.", "role": "user" }, { "content": "{\"Chemical\": [\"glutamine\", \"NH4HCO3\", \"aspartate\", \"amino acids\", \"glutamate\", \"amino acid\", \"ammonia\", \"alanine\"]}", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nAlowincidenceofcornealscarringwasnotedinsomestrainsandlikelyresultedfromascratchedcornea.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nEsterification Delivers a Functional Enzyme into a Human Cell\n\nContent Extracts:\n\n<p>Biologics are driving the growth of the modern pharmacopeia.1 Still, nearly all of these biologics are antibodies and hormones that act on the cell surface.2,3 Virtually none are proteins that intervene beneficially in the cytosol or nucleus, despite incalculable opportunities there.4</p><p>The translocation of a putative therapeutic agent across the plasma membrane is made difficult by the high anionicity of the glycocalyx and hydrophobicity of the lipid bilayer.5 Any strategy for protein delivery must overcome these two obstacles. Medicinal chemists have done so by the bioreversible masking of anionic functional groups. The ensuing \"prodrugs\",6–8 which are usually esters of carboxylic acids, constitute 20% of small-molecule drugs.9 Recently, we demonstrated that the esterification of the carboxyl groups of the green fluorescent protein (GFP) with 2-diazo-2-(p-methylphenyl)-N,N-dimethylacetamide enables its passage across the plasma membrane, akin to a small-molecule prodrug (Scheme 1).10 Importantly, the nascent esters are substrates for endogenous intracellular esterases.11,12 Thus, esterification can be a \"traceless\" delivery method that leaves no residual atoms attached to the cargo.</p><p>Upon cytosolic entry, esterified GFP retains its fluorescence,10 consistent with the retention of its three-dimensional structure.13 The catalytic activity of an enzyme is, however, the most sensitive indicator of proper conformation.14 We sought to investigate the utility of esterification as a means to promote the delivery of a functional enzyme.</p><p>As a model enzyme, we chose human ribonuclease 1 (RNase 1; EC 3.1.27.5; UniProtKB P07998).15 RNase 1 is an efficient catalyst of RNA cleavage, and its ribonucleolytic activity can be cytotoxic.16–18 To be cytotoxic, RNase 1 must not only enter the cytosol, but also evade the ribonuclease inhibitor protein (RI) that resides there.19,20 Wild-type RNase 1 forms a complex with RI that has a Kd value of (at most21) 0.29 fM22 and is not appreciably cytotoxic because of its sequestration by RI.23</p><p>RI is a highly anionic protein, and its evasion is best achieved by installing anionic groups into RNase 1. Indeed, the most evasive known variant is R39D/N67D/N88A/G89D/R91D RNase 1, which has 1010-fold lower affinity for RI than does the wild-type enzyme.22 The DDADD variant is, however, not a potent cytotoxin because its anionicity deters cellular uptake.24 Hence, the DDADD variant along with wild-type RNase 1 were ideal enzymes for the assessment of our approach, using cytotoxicity as a readout.</p><p>The mechanism of esterification with a diazo compound relies on a carboxyl group being in a protonated state.25,26 To encourage protonation, we performed esterification reactions at pH 5.5 in aqueous acetonitrile (Scheme 1). These conditions were well-tolerated by RNase 1 and its variants, and enabled esterification of 1/3–1/2 of enzymic carboxyl groups (Table 1). Esterification did reduce ribonucleolytic activity slightly (Table 1), but to a lesser extent than did the amidation of enzymic carboxyl groups.27</p><p>As observed previously,23 wild-type RNase 1 had no detectable effect on the viability of HeLa cells, even at a concentration of 100 μM (Figure 2A). In contrast, esterification of wild-type RNase 1 engendered toxicity towards HeLa cells with an IC50 value of (10 ± 1) μM (Figure 2A). These data are consistent with esterified RNase 1 overwhelming cytosolic RI, which is present at ~4 μM.29 Notably, only ~7% of unmodified RNase A (which is a bovine homolog of RNase 1) translocates to the cytosol from endosomes.30 Accordingly, the lack of toxicity of unmodified RNase 1 along with the near-equivalence of the IC50 value of esterified RNase 1 and the cytosolic concentration of RI suggests that esterification of RNase 1 makes its cytosolic delivery efficient.</p><p>Wild-type RNase 1 has a net charge of Z = 5.28 The unmodified enzyme enters endosomes rapidly.24 In contrast, DDADD RNase 1 has a net charge of Z = 0 and enters endosomes slowly.24 As expected, DDADD RNase 1 did not have an impact on the viability of HeLa cells (Figure 2B). In contrast, esterification made the DDADD variant cytotoxic with an IC50 value of (6 ± 1) μM (Figure 2B), despite its low kcat/KM value (Table 1). This cytotoxicity is consistent with the esterified enzyme entering the cytosol and cleaving cellular RNA there.</p><p>We were aware that the observed cytotoxicity of the esterified enzymes could be due to a property other than their catalytic activity. For example, some proteins and peptides are cytotoxic because of their ability to disrupt lipid bilayers.31,32 To test this alternative mechanism, we employed H12A/K41A/H119A RNase 1, which has an eviscerated active site and no detectable ribonucleolytic activity (Table 1). We found that this variant is not cytotoxic, even upon esterification (Figure 2C). Accordingly, we conclude that the cytotoxicity of both esterified wild-type RNase 1 and esterified DDADD RNase 1 relies on the manifestation of their catalytic activity within cells. We note, too, that the toxicity of these esterified enzymes for HeLa cells exceeds that of QBI-139 (IC50 = 18 ± 2 μM),23 which is an RI-evasive variant of RNase 1 that is undergoing clinical trials as a cancer chemotherapeutic agent.33,34</p><p>HeLa cells, which were derived from a cervical tumor, have numerous abnormalities.35 Accordingly, we sought to reproduce our results in another cell line. We chose H460 cells, which were derived from a non-small-cell lung tumor. We also used this cell line to assess the effect of esterification level on cytotoxicity. Wild-type RNase 1 and its DDADD variant were treated with either 100 or 200 equiv of diazo compound 1. We found that increasing the esters in wild-type RNase 1 from ~4 to ~6 reduced the IC50 value from (7 ± 1) μM to (5.1 ± 0.5) μM (Figure 3A). Wild-type RNase 1 has 13 carboxyl groups (Figure 1), whereas the DDADD variant has 17 carboxyl groups. The larger number of carboxyl groups amplified the effects. Specifically, we found that increasing the esters in DDADD RNase 1 from ~7 to ~11 reduced the IC50 value from (8.4 ± 0.5) μM to (1.0 ± 0.2) μM (Figure 3B).</p><p>Finally, we investigated the reversibility of enzymic esterification in living cells. To do so, we appended an 8-residue FLAG tag to the N terminus of wild-type RNase 1 and esterified the resulting FLAG–RNase 1 by using diazo compound 1. We treated HeLa cells with untreated or esterified FLAG–RNase 1 for 24 h, washed and lysed the cells, and recovered the FLAG–RNase 1 by using anti-FLAG magnetic beads. Mass spectrometry revealed the removal of labels by intracellular esterases (Figure S6).36 These data indicate that the esters installed by diazo compound 1 are hydrolyzed by esterases in human cells.</p><p>In summary, we have used a diazo compound to esterify enzymic carboxyl groups and shown that the ensuing enzyme enters the cytosol of human cells and is functional there. Because the catalytic activity of an enzyme is fragile, its maintenance indicates that the delivery process is gentle. Notably, esterification can be performed without the need for mutagenesis,37 and the modification is traceless, being removed by cellular esterases. This facile, versatile strategy provides new opportunities for delivering native, functional proteins to intracellular targets.</p>", "role": "user" }, { "content": "A major hurdle in chemical biology is the delivery of native proteins into the cytosol of mammalian cells. Herein, we report that esterification of the carboxyl groups of an enzyme with a diazo compound enables not only its passage into the cytosol, but also the retention of its catalytic activity there. This scenario is demonstrated with human ribonuclease 1, which manifests ribonucleolytic activity that can be cytotoxic. After internalization, the nascent esters are hydrolyzed in situ by endogenous esterases, making the process traceless. This strategy provides unprecedented opportunities for the delivery of functional enzymes into human cells.", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\n\n nonalcoholic fatty liver disease ( nafl ) is a term applied to the accumulation of fat in the liver in the absence of alcohol consumption .\nnafl refers to a wide spectrum of liver damage ranging from simple steatosis to non - alcoholic steatohepatitis ( nash ) to advanced fibrosis and finally , cirrhosis . \n \n\nthe clinical significance of nafl is derived mostly from its high prevalence in the general population and in its possible progression to liver failure . \n \n\nobesity , type 2 diabetes mellitus and hyperlipidemia are the major risk factors associated with nafl .\na bulk of evidence suggests that insulin resistance plays a major role in the pathogenesis of nafl and nash . \n \n\nhowever with meticulous questioning , more than half would mention fatigue , right upper quadrant pain and occasional discomfort , although the significance of these symptoms is uncertainmost cases initially come to medical attention by the incidental finding of increased liver echogenicity during ultrasonography performed for other reasons\n. \n \n ultrasonography could be used as a non - invasive predictor of liver histology in both moderate and severe steatosis , and advanced fibrosis with acceptable sensitivity and specificity . \n \n\nnevertheless , gradual and sustained weight reduction and exercise are most frequently recommended for overweight nafl patients . \n \n\nweight reduction can not only improve symptoms , but also the risk of progression of nafl to cirrhosis . \n \n in the present study\nwe compare the effect of a weight reduction diet on liver ultrasonographic findings in overweight nafl patients .\nto our knowledge , only one study has thus far researched weight reduction in nafl adults . \n\n\n from july 2003 to december 2005 all patients incidentally found to have fatty liver by ultrasonography who referred to radiology and gastroenterology clinics were included . \n \n\nfasting blood sugar ( fbs ) , and liver transaminase were checked for all patients .\nwaist circumference was measured using a measuring tap placed in a horizontal plane around the abdomen at the level of the iliac creast . \n \n\npatients with body mass index ( bmi ) above 25 and of the ages 16 to 60 were included in the study .\npatients not consenting to the study or not able to refer for regular follow - up were also excluded . \n \n\nthe degree of steatosis was graded by ultrasonography from 0 to 3 according to table 2 .\nthe diet contained 50 percent carbohydrates , 30 percent fat and 20 percent protein given in three meals with a deficit of 500 calories planned to ideally reduce weight by 2 kg per month .\npatients were followed monthly by a nutritionist . \n \n at the end of month three ,\nanthropometric and ultrasonographic measures before and after dieting were compared using student s paired t - test by spss version 14 . \n \n\nthe study protocol was approved by the institutional review board and ethics committee of the digestive disease research center ( ddrc ) of tehran university of medical sciences ( tums ) . \n\n\n in this study , 23 patients ( 13 females , 10 males ) were enrolled .\nthe decrease in weight , bmi , waist circumference and hip circumference were statistically significant .\nthe ultrasonographic grade decreased in all patients ; eight had a two grade reduction and 15 patients reduced one grade ( table 4 ) . \n \n\nthe decrease in ultrasonographic grade had a significant correlation with decrease in weight and bmi , but not with changes in waist and hip circumferences ( table 5 ) . \n \n\nthe amount of decrease in weight and bmi was significantly greater in patients whose ultrasonographic grades improved by two scores when compared to patients who only had a one score improvement . \n \n\nmen had a significantly greater weight loss ( p<0.01 ) , but changes in ultrasonographic grade , bmi , waist circumference and hip circumference were not significantly different among the two sexes . \n\n\n the treatment of nafl is controversial and even the necessity of treatment is doubted when there is no indication of liver damage . even in nash , where liver damage is well documented ,\nthere is no universally accepted treatment . when treatment is instituted , evaluation of treatment response is usually through transaminase levels or liver histology . \n \n\nin nafl patients , where the transaminase levels are normal to begin with , histology is the only guide to treatment .\nbut liver biopsy is a fairly invasive procedure and is difficult to justify in subjects with normal liver transaminase levels where the prognosis is generally considered to be very good . in such cases\nanother non - invasive method , such as ultrasonography , could be a good substitute . \n \n\nin this study we observed a significant improvement in ultrasonographic features of nafl by a low calorie diet .\nunfortunately , we did not have histologic confirmation but we believe it is safe to assume that improvement in histology parallels improvement in ultrasonography . \n \n\nultrasonography has an acceptable sensitivity and specificity in evaluating liver steatosis and provides a non - invasive predictor of liver histology and degree of steatosis in nafl patients . \n \n\nbased on the current study , we suggest ultrasonography as a guide to weight loss . \n \n we also observed that patients with a higher initial ultrasonographic grade had greater improvement .\nit can be concluded that more severe cases will respond better to weight loss . \n \n in our study ,\nthe diet was designed with a modest calorie deficit aiming at a maximum weight loss of 2 kg per month .\nthe gradual weight loss is important as rapid and severe weight loss , starvation , or even total parenteral nutrition , could result in or perpetuate fatty liver disease 3 - 5 .\nalthough slightly more rapid weight loss might also be safe , a modest diet would result in better patient compliance . \n \n as mentioned above , the necessity of treatment for non - complicated nafl with no indication of liver injury is in doubt . but considering the safety and other obvious benefits of gradual weight loss , we believe it should be offered to all overweight cases of nafl .\nwe conclude that weight loss is effective in improving the ultrasonographinc grade of steatosis and ultrasonography may be used as a non - invasive indicator of improvement of liver steatosis in patients with nafl during weight reduction .", "role": "user" }, { "content": "background \n non - alcoholic fatty liver ( nafl ) includes a spectrum of diseases ranging from simple hepatic steatosis to nonalcoholic steatohepatitis ( nash ) and cirrhosis . \n nafl is typically seen in association with obesity , diabetes and hypertriglyceridaemia . in order to seek the role of diet therapy in treatment of nafl \n , we compared the ultrasonographic findings of patients with fatty liver disease before and after standard diet therapy . \n \n methods \n\n twenty - three overweight or obese subjects with incidental fatty liver discovered during ultrasonography were included . \n subjects underwent 3 months of diet therapy , and anthropometric data including weight , height , bmi , waist circumference , and hip circumference were measured . \n ultrasonographic findings were graded from 0 to 3 . \n changes in ultrasonographic findings and anthropometric data were studied . \n\n \n results \n\n after three months of dieting , the ultrasonographic grade of all patients decreased by one or two grades . \n fifteen patients decreased one grade while 8 others decreased by 2 grades . \n we observed a significant correlation between the decrease in ultrasonographic grade and the decrease in weight and bmi . \n\n \n conclusion \n\n our study indicates that standard diet therapy could be used as an effective treatment for nafl patients .", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: I want to train a deep energy model to generate realistic images.\n\nKeywords: image synthesis\n\nDataset Information:\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.\nConvAI2: The ConvAI2 NeurIPS competition aimed at finding approaches to creating high-quality dialogue agents capable of meaningful open domain conversation. The ConvAI2 dataset for training models is based on the PERSONA-CHAT dataset.\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.\nUAVA: The UAVA,<i>UAV-Assistant</i>, dataset is specifically designed for fostering applications which consider UAVs and humans as cooperative agents. We employ a real-world 3D scanned dataset (<a href=\"https://niessner.github.io/Matterport/\">Matterport3D</a>), physically-based rendering, a gamified simulator for realistic drone navigation trajectory collection, to generate realistic multimodal data both from the user’s exocentric view of the drone, as well as the drone’s egocentric view.\n\nAvailable Datasets: A: CelebA B: ConvAI2 C: SNIPS D: UAVA", "role": "user" }, { "content": "CelebA", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: alcohol does not protect against infection or illness relating to COVID-19.\n\nResearch Abstract:\nAmidst the coronavirus pandemic, universities across the country abruptly closed campuses and transitioned to remote learning.\nThe effects of these unprecedented closures are unknown.\nThe current study examined reported alcohol consumption during the week prior to and after campus closure at a public university in Northeast Ohio.\nAnalysis of data from 1,958 students, who endorsed using alcohol in the past 30 days, demonstrates that alcohol consumption (amount and frequency) increased as time progressed.\nThose with more symptoms of depression and anxiety reported greater increases in alcohol consumption (assessed via retrospective timeline follow-back) compared to students with fewer symptoms.\nFurthermore, students with greater perceived social support reported less alcohol consumption.\nTogether, these findings highlight the need for universities to offer services and programs to students that will minimize risk factors and maximize protective factors in order to reduce or prevent alcohol abuse during the coronavirus pandemic.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nEffect of postural supports on neuromotor function in very preterm infants to term equivalent age . OBJECTIVE To determine the effect of a postural support nappy and/or a postural support roll on neuromotor function in very preterm infants when nursed prone to term equivalent age . METHODS A randomized observer blind controlled trial of 123 very preterm infants was conducted in the neonatal intensive care unit of the sole tertiary referral centre in Western Australia . Infants were stratified by gestational age ( < 29 weeks or 29-30 weeks ) , then randomized into one of three intervention groups : postural support nappy , postural support nappy and postural support roll , or disposable nappy and postural support roll . Interventions started when infants were stable and ceased when routine side-lying commenced . Measurements of shoulder and hip posture were performed pre-intervention , 5 weeks post-intervention and term postmenstrual age . RESULTS Infants nursed with a postural support roll and a postural support nappy demonstrated improved hip posture to term equivalent age compared with infants nursed with either a postural support roll only , or a postural support nappy only . Infants nursed with a postural support roll either with or without a postural support nappy demonstrated improved shoulder posture to term equivalent age . CONCLUSIONS Combined use of a postural support roll and a postural support nappy while very preterm infants are nursed prone improves hip posture up to term postmenstrual age . Use of a postural support roll improves shoulder posture up to term equivalent age .", "role": "user" }, { "content": "{\"Intervention\": [\"postural supports\", \"postural support roll\", \"postural support nappy and postural support roll\", \"postural support nappy\", \"postural support roll and a postural support nappy\", \"disposable nappy and postural support roll\"], \"Outcome\": [\"shoulder posture\", \"neuromotor function\", \"hip posture\", \"shoulder and hip posture\"], \"Participant\": [\"neuromotor function\", \"very preterm\", \"infants\", \"29 weeks or 29-30 weeks\", \"Infants\", \"123\"]}", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nImpact of a fixed combination of clindamycin phosphate 1.2 % -benzoyl peroxide 2.5 % aqueous gel on health-related quality of life in moderate to severe acne vulgaris . The acne-specific quality of life ( Acne-QoL ) questionnaire was developed to measure the impact of facial acne across 4 domains ( acne symptoms , role-emotional , self-perception , role-social ) of health-related quality of life ( HRQL ) . This analysis assessed the impact of clindamycin phosphate 1.2 % -benzoyl peroxide 2.5 % ( clindamycin-BPO 2.5 % ) gel on HRQL in a combined study population ( N = 2813 ) of participants with moderate to severe acne vulgaris . Although the results presented within do not include factors of study and study-by-treatment interaction , analyses were performed to confirm that the results were consistent across the 2 identical , double-blind , randomized studies and within each treatment group across studies to justify pooling the data from both studies . The Acne-QoL questionnaire was administered at baseline and at the end of treatment ( week 12 ) . Treatment with clindamycin-BPO 2.5 % gel significantly improved participant-reported HRQL across all 4 domains compared with individual active ingredients and vehicle ( P < .001 ) . The percentage improvement in mean Acne-QoL domain scores with clindamycin-BPO 2.5 % gel ranged from 37 % to 59 % . Because the negative impact of facial acne on HRQL is one of the primary motivators for patients to seek treatment , this analysis underscores the importance of physicians incorporating assessments of HRQL into their clinical decision making .", "role": "user" }, { "content": "{\"Intervention\": [\"clindamycin phosphate 1.2 % -benzoyl peroxide 2.5 % ( clindamycin-BPO 2.5 % ) gel\", \"clindamycin phosphate 1.2 % -benzoyl peroxide 2.5 % aqueous gel\", \"clindamycin-BPO\"], \"Outcome\": [\"HRQL\", \"health-related quality of life ( HRQL ) .\", \"Acne-QoL questionnaire\", \"measure the impact of facial acne\", \"Impact\", \"mean Acne-QoL domain scores\"], \"Participant\": [\"2813\", \"moderate to severe acne vulgaris\"]}", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nThese results are in agreement with a study by Wikström et al. (2007) in which loss of AMH expression was also observed to occur at a later age in 14 KS patients.", "role": "user" }, { "content": "Result", "role": "assistant" } ]

[ { "content": "Analyze the provided paragraph from a scientific document. Your goal is to identify and extract relevant entities.\n\nFormat your findings as a JSON object, where each key represents a category of entities, and the corresponding value is a list of entities identified in that category. If no entities are found for a category, return an empty list.\n\nFocus on precision and ensure that the output is strictly in JSON format.\n\nDocument:\n\nThe CD9, CD81, and CD151 EC2 domains bind to the classical RGD-binding site of integrin αvβ3 Tetraspanins play important roles in normal (e.g., cell adhesion, motility, activation, and proliferation), and pathological conditions (e.g., metastasis and viral infection). Tetraspanins interact with integrins and regulate integrin functions, but the specifics of tetraspanin - integrin interaction are unclear. Using co-immunoprecipitation with integrins as a sole method to detect interaction between integrins and full-length tetraspanins, it has been proposed that the variable region (helices D and E) of the extracellular-2 (EC2) of tetraspanins laterally associate with non-ligand-binding site of integrins. We describe that, using adhesion assays, the EC2 domain of CD81, CD9, and CD151 bound to integrin αvβ3 and this binding was suppressed by cRGDfV, a specific inhibitor of αvβ3, and antibody 7E3 that is mapped to the ligand-binding site of β3. We also present evidence that the specificity loop of β3 directly bound to the EC2 domains. This suggests that the EC2 domains specifically binds to the classical ligand-binding site of αvβ3. αvβ3 was a more effective receptor for the EC2 domains than previously known tetraspanin receptors α3β1, α4β1, and α6β1. Docking simulation predicted that the helices A and B of CD81 EC2 binds to the RGD-binding site of αvβ3. Substituting Lys residues at position 116, 144/148 of CD81 EC2 in the predicted integrin - binding interface reduced the binding of CD81 EC2 to αvβ3, consistent with the docking model. These findings suggest that, in contrast to previous models, the ligand-binding site of integrin αvβ3, a new tetraspanin receptor, binds to the constant region (helices A and B) of the EC2 domain.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [\"interaction\", \"binds\", \"cell adhesion\", \"metastasis\", \"bind\", \"viral infection\", \"interact\", \"motility\", \"activation\", \"bound\", \"proliferation\", \"binding\", \"adhesion\", \"functions\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"CD9\", \"\\u03b13\\u03b21\", \"receptor\", \"\\u03b1v\\u03b23\", \"\\u03b14\\u03b21\", \"antibody 7E3\", \"receptors\", \"Tetraspanins\", \"non-ligand-binding site\", \"\\u03b16\\u03b21\", \"CD81\", \"integrins\", \"integrin\", \"inhibitor\", \"integrin \\u03b1v\\u03b23\", \"tetraspanin\", \"\\u03b23\", \"CD151\", \"Lys residues\", \"cRGDfV\", \"tetraspanins\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"in contrast\", \"findings\"], \"Food\": [], \"HealthCareActivity\": [\"co-immunoprecipitation\", \"assays\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"models\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"Docking simulation\", \"docking model\"], \"SpatialConcept\": [\"loop\", \"ligand-binding site\", \"extracellular-2\", \"position\", \"EC2 domain\", \"EC2 domains\", \"EC2\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nAs in other studies, major depression among the gay men we surveyed was strongly associated with weaker social support, less community involvement, the experience of more stress and a reliance on passive coping strategies (Dew et al. 1997; Mao et al. 2009b; Mills et al. 2004; Prachakul et al. 2007).", "role": "user" }, { "content": "Result", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: An Ultra Wideband Survey: Global Regulations and Impulse Radio Research Based on Standards \nChapter Title: C. Medical and Healthcare \n1. Abstract of Cited Paper (BIB001): Abstract : The utilization of wireless technology in traditional medical services provides patients with enhanced mobility. This has a positive effect in the recovery speed of a person after major surgical procedures or prolonged illness. Ultra wideband (UWB) radio signals have inherent characteristics that make them highly suitable for less invasive medical applications. This paper surveys our recent research on UWB technology for medical sensing, imaging, and localization. The interconnection of multiple wireless sensors that constitute a medical body area network (WBAN) is also described. Research perspectives in the aforementioned topics are suggested too. \n2. Abstract of Cited Paper (BIB002): Ultra-wideband (UWB) technology has received great attention in recent short-range communication systems and been considered one of the potential candidates for upcoming IEEE 802.15.6 body area network (BAN) standard. High penetration capability and high precision ranging with a wide bandwidth of up to 7.5GHz (from 3.1GHz to 10.6GHz) make it easy to image the organs of human body for biomedical applications. In addition, low electromagnetic radiation less than −41.3dBm/MHz is safe for human tissue exposure and makes it suitable for hospital and home applications. This paper reviews the state-of-the-art UWB systems and addresses IC design challenges for WBAN and biomedical applications. \n3. Abstract of Cited Paper (BIB003): In wireless applications, power consumption has been, and will be, one of the important characteristics when designing any wireless device. This is the case especially in sensor networks where a single sensor may be functioning, hopefully for very long time, without external power source. Generally, the architecture complexity reduces the battery life, but the performance increases with complexity. The best performance is achieved with the most complex devices which, however, consume a lot of power. Rake receivers can offer a good tradeoff between complexity and performance. In the near future, due to the aging of population, personal medical applications are most likely increasing in number and gaining more attention in industry. This paper presents simulation results for IEEE 802.15.4a ultra wideband (UWB) rake receivers in measured hospital channel. Oulu University Hospital in Oulu, Finland, was the location of the wireless body area network (WBAN) channel model measurements. \n4. Abstract of Cited Paper (BIB004): Ultra wideband (UWB) has lots of potential in short range wireless communications. One suitable target area is applications for medical and healthcare sector. In this paper, the performances of different UWB receivers are investigated by simulations. The transceiver system was built following the IEEE 802.15.4a UWB physical layer definitions. The standard, launched in 2007, is targeted for low-complexity and low-cost devices operating in wireless personal area networks (WPANs) being therefore an option for wireless body area networks (WBANs). Another UWB standard, IEEE 802.15.6 targeted directly for WBANs, is currently in finalising phase and is assumed to be published by 2012. In this study, a WBAN channel model based on measurements in a real hospital environment is used. This study is contributing to a process in healthcare sector where the costs and the number of elderly people, in developed countries especially, are constantly increasing. \n5. Abstract of Cited Paper (BIB005): In this paper, we proposed optimized wireless ECG monitoring system with consideration of various factors from ECG in medical practice and wireless sensor network. For same, we introduced ECG data recording scheme and Wireless sensor network model that is efficient in terms of energy and space requirements without affecting the various parameter of ECG. ECG data recoding scheme deal with recording of ECG at different sampling rate, bit resolution and number of leads; that reduce the amount of data for transmission and storage. Wireless sensor network model includes combination of ultra wide band transmit only transmitter and IEEE 802.15.4 transceiver node that supports the high bandwidth requirement and contention free multiple access at hospital environment. \n6. Abstract of Cited Paper (BIB006): Wearable wireless medical sensors beneficially impact the healthcare sector, and this market is experiencing rapid growth. In the United States alone, the telecommunications services market for the healthcare sector is forecast to increase from $7.5 billion in 2008 to $11.3 billion in 2013. Medical body area networks improve the mobility of patients and medical personnel during surgery, accelerate the patients? recovery, and facilitate the remote monitoring of patients suffering from chronic diseases. Currently, MBANs are being introduced in unlicensed frequency bands, where the risk of mutual interference with other electronic devices can be high. Techniques developed during the evolution of cognitive radio can potentially alleviate these problems in medical communication environments. In addition, these techniques can help increase the efficiency of spectrum usage to accommodate the rapidly growing demand for wireless MBAN solutions and enhance coexistence with other collocated wireless systems. This article proposes a viable architecture of an MBAN with practical CR features based on ultra wideband radio technology. UWB signals offer many advantages to MBANs, and some features of this technology can be exploited for effective implementation of CR. We discuss the physical and MAC layer aspects of the proposal in addition to the implementation challenges. \n7. Abstract of Cited Paper (BIB007): In 2002, Federal Communications Commission (FCC) was the first in defining regulations for ultra wideband (UWB) communications followed by Europe and Japan some years later. Focusing on impulse radio (IR) UWB, in 2007 was the time for the first published standard targeting in personal area networks, released by the IEEE. The second IEEE released standard including UWB definitions is targeted for wireless body area networks (WBAN) and was published in 2012. As the wireless communications has been and will be passing through almost any levels in society, the natural step with WBAN is using it in different medical, healthcare and wellbeing applications. The arguments for these are related to the modern lifestyle, in which people have increasingly more free time and are more interested in taking care of their health and wellbeing. Another challenge is the population composition, i.e., aging in developed countries which call for new solutions and procedures, particularly from cost wise. In this paper, we are evaluating UWB receivers based on the IEEE 802.15.6 physical layer definitions and capable of detecting differentially encoded modulation. The evaluation is performed using two different WBAN channel models. \n8. Abstract of Cited Paper (BIB008): Advantages of remote health monitoring are incontestable: prolonging the patient's possibility to stay at home by monitoring the health condition remotely, the quality of patient's life is improved as well as healthcare costs are significantly reduced. Parkinson's disease is one example, for which some wireless monitoring systems have been presented recently. However, concrete performance evaluations for the IEEE 802.15.6 standard based communication in the realistic use scenarios have not been presented yet in the literature. The aim of this paper is to evaluate performance of ultra wideband energy detector receivers on the physical layer of the IEEE 802.15.6 standard. The monitoring system and node locations are designed for monitoring Parkinson's disease symptoms. Measurement based radio channel models were used in the evaluations. Two modulation methods, on-off keying and pulse position modulation, are evaluated and compared using two different antennas suitable for body area network communication. Pulse position modulation based system is found to outperform on-off keying based system, which on the other hand, is simpler to implement. Furthermore, it is shown how antenna placement, position, and properties are impacting on the channel characteristics of the radio link, and hence, on the bit error rate performance.\n\nReview Chapter:", "role": "user" }, { "content": "Both BIB004 and BIB005 present simulation results of different receiver structures including different rake and ED receivers that are capable of detecting the WPAN standard defined signal model. Additionally, channel models based on hospital measurements, are used in the simulations. A review and a presentation of both IR-UWB and FM-UWB techniques related to the WBAN standard is presented in BIB003 providing different perspectives of biomedical applications and design challenges. A system for electrocardiograph measurement based on the WPAN standard is proposed in BIB006 . Interestingly, transmit only type IR-UWB radio is used and it is studied more thoroughly in BIB001 . Chávez-Santiago et al. BIB002 propose ideas of an architecture for medical BAN which connects both in-body and on-body sensors and is utilized by both IR-UWB and MB-UWB techniques. In BIB007 , partially by the same authors, their medical BAN architecture is extended by adding cognitive radio features on it. Evaluations of energy detector receivers based on the WBAN standard is presented in BIB009 for symptom detection of Parkinson's disease. Another WBAN standard based article is BIB008 , where a WBAN PHY compatible transceiver system with hospital environment channel models is used for comparing receivers with differential detection.", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nparaganglioma is a rare neuroendocrine neoplasm that may develop at various body sites like abdomen , thorax , head and neck .\nmajority of paragangliomas develop in abdomen while mediastinal paraganglioma is a rare mediastinal tumor.12 posterior mediastinum is the commonest site for mediastinal paraganglioma while anterior mediastinal localization is unusual.13 most paraganglioma are asymptomatic and present as painless mass .\nendoscopic ultrasound ( eus ) features of retroperitoneal paraganglioma have been described4 while that of mediastinal paraganglioma have not been described . in this report\nwe describe the eus features of mediastinal paraganglioma in a patient who presented with cough and chest pain without any neuroendocrinal symptoms .\na fifty - six year old female presented with one month history of chest pain and cough .\nthe patient was not hypertensive and did not give any history related to neuroendocrinal hormone over secretion .\nthe mass was inverted triangular shape with bulging peripheries , situated between aorta and left pulmonary artery .\nthe mass was hypervascular in the center and the interface between the mass and vessels described was intact and there was no lymphadenopathy ( fig . 1 - 3 ) .\neus - guided fine needle aspiration ( eus - fna ) was done using a 22-g needle ( echotip , cook corporation ) .\nslides were prepared and the material was air dried as well as alcohol fixed before sending for cytopathological evaluation ( fig . 4 , 5 ) .\ngood material was obtained on eus - fna , but three experienced cytopathologists gave three different reports ; final diagnosis of paraganglioma was only made on thoracoscopic biopsy and immunohistochemistry .\nmediastinal paraganglioma is a rare mediastinal tumor.12 it constituted 0.3% of all mediastinal tumors in the series described by cesar et al.1 while no case of mediastinal paraganglioma was found out of 57 eus - fna done for mediastinal masses by zeppa et al.2 majority of thoracic paragangliomas occur in posterior mediastinum . out of 16 cases of thoracic paragangliomas reported by cesar\nparagangliomas arise from parasympathetic or sympathetic ganglia located in ap window or posterior mediastinum.34 diagnosis of asymptomatic paraganglioma on any imaging modality is difficult . on fna cytology , it is difficult to give final diagnosis.4 in our patient also the tumor could be finally diagnosed only upon thoracoscopic biopsy and immunohistochemistry and the tumor was positive for chromogranin , synaptophysin and neuron specific enolase .\neus features of mediastinal paraganglioma are not described while only in one case eus features of retroperitoneal paraganglioma are reported.2 the situations in retroperitoneum and mediastinum are different .\nretroperitoneum is a potential big space where tumor can grow freely to any size and can assume any shape while there is little space in mediastinum for tumor to grow and tumor may assume a particular shape . in the present case , there were certain features which were highly suggestive of paraganglioma .\nit is inverted triangular shape with base of the triangle lying superiorly , because there is sufficient space in ap window where tumor can grow , and apex lying inferiorly , because the tumor has to grow in between the vessels .\nbesides , there were other features such as rich vascularity of the tumor , bulging peripheries , no invasion of vessels and absence of lymphadenopathy .\nwe analyzed our 50 cases of various mass lesions involving ap window and subcarinal space , and in none of the cases such typical eus features were seen .\ngrowth in between the vessels without invasion of vessels was a typical feature of benign paraganglioma .\nwhen such appearance is seen on eus imaging , diagnosis of paraganglioma is quite likely and eus - fna may be risky and may not provide final diagnosis .", "role": "user" }, { "content": "endoscopic ultrasound ( eus ) features of mediastinal paraganglioma have not been described . in this paper , we report a female patient presented with cough and chest pain without any neuroendocrinal symptoms . \n final diagnosis of mediastinal paraganglioma was made on thoracoscopic biopsy and immunohistochemistry after eus - guided fine needle aspiration . \n eus features of mediastinal paraganglioma are described .", "role": "assistant" } ]

[ { "content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nexperiments\n\nText Before Citation:\nFor example, consider a relational description (cfXXX, Dale and Haddock 1991) involving a gradable adjective, as in the dog in the large shed. Some generalizations of our method are fairly straightforward. Extensions of the Approach 9.1 Relational Descriptions\n\nCitation Text:\nFor example , consider a relational description ( cfXXX , Dale and Haddock 1991 ) involving a gradable adjective , as in the dog in the large shed .\n\nText After Citation:\nCD for this type of descriptions along the lines of Section 4 is not difficult once relational descriptions are integrated with a standard GRE algorithm (Krahmer and Theune 2002, Section 8.6.2): Suppose an initial description is generated describing the set of all those dogs that are in sheds over a given size (say, size 5); if this description happens to distinguish an individual dog then this legitimizes the use of the noun phrase the dog in the large shed. Note that this is felicitous even if the shed is not the largest one in the domain, as is true for d2 in the following situation (contains-a=b means that a is contained by b): In other words, the dog in the large shed denotes ‘the dog such that there is no other shed that is equally large or larger and that contains a dog’. Note that it would be odd, in the above-sketched situation, to say the dog in the largest shed. \u0000\u0000\u0000\u0000", "role": "user" }, { "content": "Background", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nTrichuris infections in pigs : a treatment trial in the field .", "role": "user" }, { "content": "{\"Intervention\": [\"treatment trial\"], \"Outcome\": [], \"Participant\": []}", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: A new approach to video event recognition using covariance matrices is introduced. The video descriptor is\n\nKeywords: low-level event recognition video\n\nDataset Information:\nFineGym: FineGym is an action recognition dataset build on top of gymnasium videos. Compared to existing action recognition datasets, FineGym is distinguished in richness, quality, and diversity.\nUCLA Aerial Event Dataset: The UCLA Aerial Event Dataest has been captured by a low-cost hex-rotor with a GoPro camera, which is able to eliminate the high frequency vibration of the camera and hold in air autonomously through a GPS and a barometer. It can also fly 20 ∼ 90m above the ground and stays 5 minutes in air.\nHMDB51: The HMDB51 dataset is a large collection of realistic videos from various sources, including movies and web videos. The dataset is composed of 6,766 video clips from 51 action categories (such as “jump”, “kiss” and “laugh”), with each category containing at least 101 clips.\nMTL-AQA: A new multitask action quality assessment (AQA) dataset, the largest to date, comprising of more than 1600 diving samples; contains detailed annotations for fine-grained action recognition, commentary generation, and estimating the AQA score. Videos from multiple angles provided wherever available.\n\nAvailable Datasets: A: FineGym B: UCLA Aerial Event Dataset C: HMDB51 D: MTL-AQA", "role": "user" }, { "content": "HMDB51", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: A Review on Facial Micro-Expressions Analysis: Datasets, Features and Metrics \nChapter Title: 2.2.3 \n1. Abstract of Cited Paper (BIB001): A robust automatic micro-expression recognition system would have broad applications in national safety, police interrogation, and clinical diagnosis. Developing such a system requires high quality databases with sufficient training samples which are currently not available. We reviewed the previously developed micro-expression databases and built an improved one (CASME II), with higher temporal resolution (200 fps) and spatial resolution (about 280x340 pixels on facial area). We elicited participants' facial expressions in a well-controlled laboratory environment and proper illumination (such as removing light flickering). Among nearly 3000 facial movements, 247 micro-expressions were selected for the database with action units (AUs) and emotions labeled. For baseline evaluation, LBP-TOP and SVM were employed respectively for feature extraction and classifier with the leave-one-subject-out cross-validation method. The best performance is 63.41% for 5-class classification.\n\nReview Chapter:", "role": "user" }, { "content": "Chinese Academy of Sciences Micro-Expression II (CASME II) CASME II has been developed by Yan et al. BIB002 , which succeeds the CASME dataset BIB001 with major improvements. All samples in CASME II are spontaneous and dynamic micro-expressions with high frame rate (200 fps). There is always a few frames kept before and after each microexpressions, to make it suitable for detection experiments, however the amount of these frames can vary across clips. The resolution of samples is 640×480 pixels for recording, which were saved as MJPEG with a resolution of around 280×340 pixels for the cropped facial area. Fig. 2 shows a sample from the CASME II with a happiness-class expression. The micro-expressions were elicited in a wellcontrolled laboratory environment. The dataset contains 247 micro-expressions (gathered from 35 participants) that were selected from nearly 3000 facial movements and have been labeled with action units (AUs) based on the Facial Action Coding System (FACS) . Lighting flickers were avoided in the recordings and highlights to the regions of the face have been reduced.", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nAnti-subunitcantibody(0.7mug/ml)waskindlyprovidedbyDr.Kominami(JuntendoUniversity,Tokyo,Japan).", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Analyze the provided clinical trial criteria. Identify and extract distinct entities from the text.\n\nReturn the results as a JSON structure. Ensure the output is strictly in JSON format without any additional commentary.\n\nCriteria Text:\n\nPatient is currently enrolled in a Novartis OGD or GMA-sponsored or Incyte-sponsored clinical study (where Incyte can delegate the sponsorship to a preferred CRO, if applicable) that is approved to enroll into this rollover study, is receiving ruxolitinib and has fulfilled all of the requirements of the parent protocol.\nPatient is currently benefiting from the treatment with ruxolitinib, as determined by the investigator\nPatient has demonstrated compliance, as assessed by the investigator, with the parent study protocol requirements Willingness and ability to comply with scheduled visits, treatment plans and any other study procedures\nPatient currently has no evidence of progressive disease, as determined by the investigator, following previous treatment with ruxolitinib\nWritten informed consent obtained prior to enrolling in roll-over study and receiving study medication. If consent cannot be expressed in writing, it must be formally documented and witnessed, ideally via an independent trusted witness.", "role": "user" }, { "content": "{\"Condition\": [\"progressive disease\"], \"Device\": [], \"Drug\": [\"ruxolitinib\"], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [], \"Visit\": []}", "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:\ngluon fusion and weak - boson fusion ( wbf ) are expected to be the most copious sources of higgs bosons in @xmath0 collisions at the large hadron collider ( lhc ) and a future very large hadron collider ( vlhc ) . beyond representing the most promising discovery processes\n@xcite , these two production modes are also expected to provide a wealth of information on higgs couplings to gauge bosons and fermions @xcite .\nthe extraction of higgs boson couplings , in particular , requires precise predictions of production cross sections .\na key component of the program to measure higgs boson couplings at a @xmath0 collider is the wbf process , @xmath3 via @xmath4-channel @xmath5 or @xmath6 exchange , characterized by two forward quark jets @xcite .\nqcd radiative corrections to wbf are known to be small @xcite and , hence , this process promises small systematic errors .\njet production via gluon fusion , while part of the inclusive higgs signal , constitutes a background when trying to isolate the @xmath8 and @xmath9 couplings responsible for the wbf process . in two recent papers\n@xcite we presented the details of the calculation and some results for the real - emission corrections to gluon fusion which lead to @xmath7 parton final states , at order @xmath10 , at lhc energies .\nthe contributing subprocesses include quark - quark scattering which involves top - quark triangles , quark - gluon scattering processes which are mediated by top - quark triangles and boxes , and @xmath11 which requires pentagon diagrams in addition . in these papers we investigated the validity of the large top - mass limit ( @xmath12 ) by comparing a few distributions computed using the heavy - top effective lagrangian @xcite with the corresponding ones computed keeping @xmath13 finite .\nin addition , we studied the renormalization and factorization scale - dependence of the resulting @xmath7 jet cross section , and discussed some phenomenologically important distributions at the lhc . in this contribution , we extend the analysis to the higher energy @xmath0 collisions of a vlhc , at center of mass energies @xmath14 and 200 tev .\nin particular , we investigate the cuts that need to be applied in order to enhance wbf signals with respect to gluon fusion contributions .\nthe gluon - fusion processes at @xmath16 , together with weak - boson fusion , are expected to be the dominant sources of @xmath7 jet events at the lhc and vlhc .\nthe relative size of the two contributions decides the impact which gluon - fusion will have on the study of wbf processes .\nthe gluon - fusion cross sections diverge as the final - state partons become collinear with one another or with the incident beam directions , or as final - state gluons become soft . a minimal set of cuts on the final - state partons\nis required to define a finite @xmath7 jet cross section , and these cuts should at the same time anticipate detector capabilities and jet finding algorithms .\nwe consider two broadly defined sets of cuts : a selection for generic @xmath7 jet events ( called `` inclusive cuts '' ) and a more stringent selection which is typical for wbf studies ( `` wbf cuts '' ) . in going from lhc to the higher vlhc energies\n, harder jet cuts will have to be imposed , in particular on the jet transverse momentum , @xmath17 .\nwe distinguish between lhc and vlhc specific cuts : * inclusive cuts [ e4_oleari_0927_sec_eq : incl_lhc ] lhc : & & p_tj>20 gev , [ e4_oleari_0927_sec_eq : incl_vlhc ] vlhc : & & p_tj>30 gev , |_j|<6 , r_jj>0.6 , * wbf cuts : previous inclusive cuts plus @xcite [ e4_oleari_0927_sec_eq : wbf_lhc ] lhc : & & |_j_1-_j_2|>4.2 , _\nj_1_j_2<0 , m_jj>600 gev , + [ e4_oleari_0927_sec_eq : wbf_vlhc ] vlhc : & & |_j_1-_j_2|>5 , _\nj_1_j_2<0 , m_jj>3 tev . in general , the gluon fusion differential cross section tends to peak for central jets and and at a relatively small invariant mass , @xmath18 , of the dijet system .\nthis is because final - state gluons tend to be soft and the energy of initial gluons is restricted due to the rapid fall - off of the gluon distribution , @xmath19 , with increasing @xmath20 .\nthe wbf cuts then enhance the wbf contribution with respect to gluon fusion .\nfor the inclusive cuts , which allow soft events , the gluon fusion cross section dominates over wbf by a factor 310 .\nthe wbf cuts force the two tagging jets to be well separated in pseudorapidity , @xmath21 , they must reside in opposite detector hemispheres and they must possess a large dijet invariant mass .\nthe combination of these requirements forces the gluon fusion cross section below the wbf rate for all machine energies .\n.total cross section , in picobarn , for @xmath7 jet production , in @xmath0 collisions at lhc ( @xmath1 tev ) and vlhc ( @xmath2 tev ) for three different values of the higgs mass @xmath22 .\nresults are shown for gluon fusion ( gf ) and wbf , using the inclusive cuts of eq .\n( [ e4_oleari_0927_sec_eq : incl_lhc ] ) and the wbf cuts of eqs .\n( [ e4_oleari_0927_sec_eq : incl_lhc ] ) and ( [ e4_oleari_0927_sec_eq : wbf_lhc ] ) for lhc , and the inclusive cuts of eq .\n( [ e4_oleari_0927_sec_eq : incl_vlhc ] ) and the wbf cuts of eqs .\n( [ e4_oleari_0927_sec_eq : incl_vlhc ] ) and ( [ e4_oleari_0927_sec_eq : wbf_vlhc ] ) for vlhc . [ cols=\"^,^,^,^,^,^,^,^,^,^,^,^,^,^,^,^,^ \" , ] this is demonstrated in table [ e4_oleari_0927_tab : sigma ] , where the expected @xmath7 jet cross sections are shown for higgs masses of 115 , 160 , and 200 gev , and for the two sets of cuts introduced previously .\nthe gluon fusion cross sections depend only weakly on the higgs mass .\ncross sections correspond to the sum over all higgs decay modes : finite higgs width effects are included .\nwe use cteq4l parton - distribution functions @xcite .\nthe factorization scale was set to @xmath23 and we fix @xmath24 .\ndifferent choices for the renormalization and factorization scales have been discussed in ref .\n@xcite , where a strong dependence on the renormalization scale was found for the gluon fusion cross section .\ntev , and vlhc , with center - of - mass energies of 50 , 100 and 200 tev .\nthe mass of the higgs was fixed at @xmath25 gev .\ncross sections are for wbf cuts as discussed in the text , without the @xmath18 constraint.,title=\"fig:\",scaledwidth=45.0% ] tev , and vlhc , with center - of - mass energies of 50 , 100 and 200 tev .\nthe mass of the higgs was fixed at @xmath25 gev .\ncross sections are for wbf cuts as discussed in the text , without the @xmath18 constraint.,title=\"fig:\",scaledwidth=45.0% ] tev , and vlhc , with center - of - mass energies of 50 , 100 and 200 tev .\nthe mass of the higgs was fixed at @xmath25 gev .\ncross sections are for wbf cuts as discussed in the text , without the @xmath18 constraint.,title=\"fig:\",scaledwidth=45.0% ] tev , and vlhc , with center - of - mass energies of 50 , 100 and 200 tev .\nthe mass of the higgs was fixed at @xmath25 gev .\ncross sections are for wbf cuts as discussed in the text , without the @xmath18 constraint.,title=\"fig:\",scaledwidth=45.0% ] it is instructive to consider the dijet invariant mass distributions for our two sources of @xmath7 jet events . within the wbf cuts\n( but without the @xmath18 constraint ) they are shown in fig . [\nfig : mjj_wbf_cuts ] . at machine energies below 100 tev\n, wbf soon dominates the @xmath18 distribution : a relatively modest @xmath18 requirement ( 500 gev at the lhc , 1 tev at a 50 tev machine ) will suffice , while retaining most of the wbf signal . at higher collision energies wbf only dominates at very large dijet invariant masses , and cuts at 2 or 4\ntev will come at a huge cost of wbf cross section .\nin addition , since the jet transverse momenta in wbf events are tied to the weak boson masses , such cuts leave us with dijet systems with very large rapidity separation .\ncontaining such events will require superior rapidity coverage of vlhc detectors , up to @xmath26 .\nas the center - of - mass energy is increased at very high energy hadron colliders , the mix of @xmath7 jet events shifts more and more to gluon fusion induced events , even with cuts geared towards the enhancement of weak boson fusion .\na separation of the two sources is partially possible with the rapidity and invariant mass cuts discussed above .\nhowever , other distinguishing characteristics will have to be exploited .\nchief among these will be the different color structure of the events : @xmath4-channel color singlet exchange for wbf , @xmath4-channel color octet exchange for gluon fusion .\nthe resulting suppression of soft jets in the central region for wbf events @xcite will need to be studied in detail to prepare tools for the isolation of wbf events at a vlhc .\nthis summary is based on work done with v. del duca , w. kilgore and c. schmidt , whom we thank for enjoyable collaborations and discussions .\nc.o . acknowledges the support of a dpf snowmass fellowship .\nthis research was supported in part by the university of wisconsin research committee with funds granted by the wisconsin alumni research foundation and in part by the u. s. department of energy under contract no .\nde - fg02 - 95er40896 .\n10 [ 2]#2 [ 1]#1 [ 1]#1 and , cms note 1997/057 ; and , cms tn/97 - 106 ; and , ; ( ) , cms technical proposal , cern / lhcc/94 - 38x .\n( ) , atlas tdr , cern / lhcc/99 - 15 .\nd. rainwater and d. zeppenfeld , jhep * 9712 * , 005 ( 1997 ) [ hep - ph/9712271 ] ; d. rainwater , d. zeppenfeld and k. hagiwara , phys .\nd * 59 * , 014037 ( 1999 ) [ hep - ph/9808468 ] ; d. rainwater and d. zeppenfeld , phys .\nd * 60 * , 113004 ( 1999 ) [ erratum - ibid .\nd * 61 * , 099901 ( 1999 ) ] [ hep - ph/9906218 ] ; t. plehn , d. rainwater and d. zeppenfeld , phys .\nd * 61 * , 093005 ( 2000 ) [ hep - ph/9911385 ] ; n. kauer , t. plehn , d. rainwater and d. zeppenfeld , phys .\nb * 503 * , 113 ( 2001 ) [ hep - ph/0012351 ] ; , , , and , , ( ) . and , , ( ) .\n, , , , and , , ( ) , ; , , , , and , . and , , ( ) ; , , and , , ( ) , erratum - ibid . phys . rev . * d58 * , 119901 ( 1998 ) , . h.l .\nlai et al . , phys .\nrev . * d55 * , 1280 , ( 1997 ) [ hep - ph/9606399 ] .\ny. l. dokshitzer , v. a. khoze , and s. troyan , in _ proc . of the 6th int .\nconf . on physics in collisions _ , ( 1986 ) ed .\nm. derrick ( world scientific , 1987 ) p.365 ; j. d. bjorken , int .\nj. mod .\nphys . * a7 * , 4189 ( 1992 ) ; phys .\n* d47 * , 101 ( 1993 ) .", "role": "user" }, { "content": "we consider gluon - fusion and weak - boson fusion production of higgs plus two jets in @xmath0 collisions at @xmath1 tev ( lhc ) and @xmath2 tev ( vlhc ) . \n we give cross sections for higgs masses between 115 gev and 200 gev , and discuss the experimental cuts that should be applied in order to enhance the weak - boson fusion contribution with respect to the gluon - fusion background .", "role": "assistant" } ]

[ { "content": "Analyze the provided clinical trial criteria. Identify and extract distinct entities from the text.\n\nReturn the results as a JSON structure. Ensure the output is strictly in JSON format without any additional commentary.\n\nCriteria Text:\n\nAny previous treatments for active CSC;\nPrevious prescription of mineralocorticoid receptor antagonists, for cCSC or for other diseases;\nCurrent treatment with corticosteroids (topical or systemic), corticosteroid use within 3 months before possible start of trial treatment, or anticipated start of corticosteroid treatment within the first 2 years from the start of the trial period;\nEvidence of another diagnosis that can explain serous SRF or visual loss;\nBest-corrected visual acuity < 20/200 (Snellen equivalent);\nProfound chorioretinal atrophy in central macular area on ophthalmoscopy and OCT;\nMyopia > 6D;\nVisual loss and/or serous detachment on OCT < 6 weeks;\nContinuous and/or progressive visual loss > 18 months or serous detachment on OCT > 18 months;\nNo hyperfluorescence on ICGA;\nIntraretinal edema on OCT;\n(relative) Contraindications for FA or ICGA;\n(relative) Contraindications for photodynamic treatment (pregnancy, porphyria, severely disturbed liver function). Pregnancy will not be routinely tested in female patients, but the possibility of pregnancy will be discussed during screening\n(relative) Known contraindications for initiation of eplerenone treatment (hyperkalemia, abnormal renal clearance, severe hepatic insufficiency (Child-Pugh C), type 2 diabetes mellitus with microalbuminuria, concomitant use of potassium supplements, potassium-sparing diuretics, strong CYP3A4 inhibitors, or the combination of an ACE-inhibitor and an angiotensin receptor blocking agent). Pregnancy will not be routinely tested in female patients, but the possibility of pregnancy will be discussed during screening;\nSoft drusen in treated eye or fellow eye, signs of choroidal neovascularization on ophthalmoscopy and/or FA/ICGA of the study eye.", "role": "user" }, { "content": "{\"Condition\": [\"severe hepatic insufficiency\", \"Visual loss\", \"pregnancy\", \"choroidal neovascularization\", \"contraindications\", \"microalbuminuria\", \"Contraindications\", \"type 2 diabetes mellitus\", \"serous detachment\", \"visual loss\", \"other diseases\", \"porphyria\", \"chorioretinal atrophy\", \"abnormal renal clearance\", \"Soft drusen\", \"Intraretinal edema\", \"disturbed liver function\", \"CSC\", \"hyperkalemia\", \"cCSC\"], \"Device\": [], \"Drug\": [\"strong CYP3A4 inhibitors\", \"mineralocorticoid receptor antagonists\", \"angiotensin receptor blocking agent\", \"ACE-inhibitor\", \"corticosteroids\", \"potassium-sparing diuretics\", \"eplerenone\", \"potassium supplements\"], \"Measurement\": [\"renal clearance\", \"ICGA\", \"Myopia\", \"Child-Pugh\", \"Best-corrected visual acuity\"], \"Mood\": [\"anticipated\"], \"Multiplier\": [], \"Negation\": [\"No\"], \"Observation\": [], \"Person\": [], \"Procedure\": [\"FA\", \"treatments\", \"photodynamic treatment\", \"ICGA\", \"corticosteroid use\", \"OCT\", \"corticosteroid treatment\", \"ophthalmoscopy\"], \"Qualifier\": [\"treated eye\", \"Continuous\", \"progressive\", \"topical\", \"central macular area\", \"study eye\", \"Profound\", \"severely\", \"active\", \"systemic\", \"fellow eye\"], \"ReferencePoint\": [\"the first 2 years from the start of the trial period\", \"possible start of trial treatment\"], \"Scope\": [\"cCSC or for other diseases\", \"ACE-inhibitor and an angiotensin receptor blocking agent\", \"ophthalmoscopy and/or FA/ICGA\", \"potassium supplements, potassium-sparing diuretics, strong CYP3A4 inhibitors, or the combination of an ACE-inhibitor and an angiotensin receptor blocking agent\", \"topical or systemic\", \"Continuous and/or progressive\", \"Visual loss and/or serous detachment\", \"ophthalmoscopy and OCT\", \"FA or ICGA\", \"pregnancy, porphyria, severely disturbed liver function\", \"type 2 diabetes mellitus with microalbuminuria\", \"treated eye or fellow eye\", \"Contraindications for photodynamic treatment\"], \"Temporal\": [\"concomitant\", \"Current\", \"within 3 months before possible start of trial treatment\", \"Previous\", \"\\u003e 18 months\", \"within the first 2 years from the start of the trial period\", \"previous\", \"\\u003c 6 weeks\"], \"Value\": [\"\\u003e 6D\", \"\\u003c 20/200\", \"hyperfluorescence\", \"C\", \"abnormal\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: Scanned optogenetic control of mammalian somatosensory input to map input-specific behavioral outputs\nContent Overview:\nAbstract:\nSomatosensory stimuli guide and shape behavior, from immediate protective reflexes to longer-term learning and higher-order processes related to pain and touch. However, somatosensory inputs are challenging to control in awake mammals due to the diversity and nature of contact stimuli. Application of cutaneous stimuli is currently limited to relatively imprecise methods as well as subjective behavioral measures. The strategy we present here overcomes these difficulties, achieving ‘remote touch’ with spatiotemporally precise and dynamic optogenetic stimulation by projecting light to a small defined area of skin. We mapped behavioral responses in freely behaving mice with specific nociceptor and low-threshold mechanoreceptor inputs. In nociceptors, sparse recruitment of single-action potentials shapes rapid protective pain-related behaviors, including coordinated head orientation and body repositioning that depend on the initial body pose. In contrast, activation of low-threshold mechanoreceptors elicited slow-onset behaviors and more subtle whole-body behaviors. The strategy can be used to define specific behavioral repertoires, examine the timing and nature of reflexes, and dissect sensory, motor, cognitive, and motivational processes guiding behavior.\nIntroduction:\nThe survival of an organism depends on its ability to detect and respond appropriately to its environment. Afferent neurons innervating the skin provide sensory information to guide and refine behavior( Seymour, 2019; Zimmerman et al., 2014). Cutaneous stimuli are used to study a wide range of neurobiological mechanisms since neurons densely innervating skin function to provide diverse information as the body interfaces with its immediate environment. These afferents maintain the integrity of the body by recruiting rapid sensorimotor responses, optimize movement through feedback loops, provide teaching signals that drive learning, and update internal models of the environment through higher-order perceptual and cognitive processes( Barik et al., 2018; Brecht, 2017; Corder et al., 2019; de Haan and Dijkerman, 2020; Haggard et al., 2013; Huang et al., 2019; Petersen, 2019; Seymour, 2019). Damaging stimuli, for example, evoke rapid motor responses to minimize immediate harm and generate pain that motivates longer-term behavioral changes. Compared to visual, olfactory, and auditory stimuli, somatosensory inputs are challenging to deliver in awake unrestrained mammals. This is due to the nature of stimuli that require contact and the diversity of stimulus features encoded by afferents that innervate skin. Cutaneous afferent neurons are functionally and genetically heterogeneous, displaying differential tuning, spike thresholds, adaptation rates, and conduction velocities( Abraira and Ginty, 2013; Dubin and Patapoutian, 2010; Gatto et al., 2019; Häring et al., 2018). The arborization of their peripheral terminals can delineate spatial and temporal dimensions of the stimulus( Pruszynski and Johansson, 2014), particularly once many inputs are integrated by the central nervous system( Prescott et al., 2014). Cutaneous stimulation in freely moving mice often requires the experimenter to manually touch or approach the skin. This results in inaccurate timing, duration, and localization of stimuli. The close proximity of the experimenter can cause observer-induced changes in animal behavior( Sorge et al., 2014). Stimuli also activate a mixture of sensory neuron populations. For example, intense stimuli can co-activate fast-conducting low-threshold afferents that encode innocuous stimuli simultaneously with more slowly conducting high-threshold afferents( Wang et al., 2018). The latter are nociceptors that trigger fast protective behaviors and pain. Consequently, mixed cutaneous inputs recruit cells, circuits, and behaviors that are not specific to the neural mechanism under study. A way to control genetically defined afferent populations is to introduce opsins into these afferents and optogenetically stimulate them through the skin( Abdo et al., 2019; Arcourt et al., 2017; Barik et al., 2018; Beaudry et al., 2017; Browne et al., 2017; Daou et al., 2013; Iyer et al., 2014). However, these methods in their current form do not fully exploit the properties of light. The behaviors that are evoked by cutaneous stimuli are also typically measured with limited and often subjective means. Manual scoring introduces unnecessary experimenter bias and omits key features of behavior. Behavioral assays have traditionally focused on a snapshot of the stimulated body part rather than dynamics of behavior involving the body as a whole( Gatto et al., 2019). Recent advances in machine vision and markerless pose estimation have enabled the dissection of animal behavioral sequences( Mathis et al., 2018; Pereira et al., 2019; Wiltschko et al., 2015). However, these have not been adapted to study behavioral outputs relating to specific cutaneous inputs. Here we developed an approach to project precise optogenetic stimuli onto the skin of freely behaving mice( Figure 1A). The strategy elicits time-locked individual action potentials in genetically targeted afferents innervating a small stimulation field targeted to the skin. Stimuli can be delivered remotely as predefined microscale patterns, lines, or moving points. The utility of the system was demonstrated by precisely stimulating nociceptors, or Aβ low threshold mechanoreceptors( LTMRs), in freely behaving mice to map behavioral outputs at high speed. We provide an analysis toolkit that quantifies the millisecond-timescale dynamics of behavioral responses using machine vision methods. We dissect discrete behavioral components of local paw responses, head orienting and body repositioning behaviors, and determine how these specific behavioral components relate to precise somatosensory inputs.\nDiscussion:\nWe describe a strategy for remote, precise, dynamic somatosensory input and behavioral mapping in awake unrestrained mice. The approach can remotely deliver spatiotemporally accurate optogenetic stimuli to the skin with predefined size, geometry, duration, timing, and location, while simultaneously monitoring behavior in the millisecond timescale. Microscale optogenetic stimulation can be used to simulate patterns, edges, and moving points on the skin. Responses to these precisely defined points and patterns can be mapped using machine vision approaches. The design is modular, for example, additional lasers for multicolor optogenetic control or naturalistic infrared stimuli can be added and complementary machine vision analysis approaches readily implemented. As an example, we combine this with DeepLabCut( Mathis et al., 2018), for markerless tracking of individual body parts to further dissect specific components of whole-body responses. We validated the system in two transgenic mouse lines, providing optical control of broad-class Aδ and C-nociceptors, and Aβ-LTMRs. Advances in transcriptional profiling have identified a vast array of genetically defined primary afferent neuron populations involved in specific aspects of temperature, mechanical, and itch sensation( Usoskin et al., 2015). Selective activation of these populations is expected to recruit a specific combination of downstream cells and circuits depending on their function. For example, nociceptive input generates immediate sensorimotor responses and also pain that acts as a teaching signal. This strategy can be thus combined with techniques to modify genes, manipulate cells and neural circuits, and record neural activity in freely behaving mice to probe these mechanisms( Boyden et al., 2005; Kim et al., 2017). We provide approaches to map behavioral responses to defined afferent inputs across the spectrum of somatosensory modalities( Browne et al., 2017; Huang et al., 2019). We find that the probabilistic recruitment of nociceptors determines the behavioral response probability, latency, and magnitude. We propose that the aggregate number of first action potentials arriving from nociceptors to the spinal cord can be utilized to optimize the timing and extent of rapid protective responses. These first action potentials could be summated by spinal neurons so that appropriate behaviors are selected based on thresholds. Resultant fast behaviors are diverse but include coordinated head orientation and body repositioning that depends on the initial pose. In contrast, responses to optogenetic activation of Aβ-LTMRs occurred with slower onset, lower probability, and resulted in more subtle whole-body movements. Using a fixed number of pulses, we find that responses from multiple Aβ-LTMR inputs can be explained by the sum rule of probabilities rather than frequency-dependence( Chamessian et al., 2019). This does not, however, rule out the tuning of responses to more spatially or temporally complex stimuli. We used broad-class Cre driver lines to selectively stimulate either nociceptors or Aβ-LTMRs, and it is possible that their respective subpopulations exploit a diversity of coding strategies. This optical approach can reveal how such subpopulation and their specific downstream circuits guide behavior. In summary, we have developed a strategy to precisely control afferents in the skin without touching or approaching them by projecting light to optogenetically generate somatosensory input in patterns, lines, or points. This is carried out non-invasively in awake freely behaving mice in a way that is remote yet precise. Remote control of temporally and spatially precise input addresses the many limitations of manually applied contact stimuli. The timing, extent, directionality, and coordination of resultant millisecond-timescale behavioral responses can be investigated computationally with specific sensory inputs. This provides a way to map behavioral responses, circuits, and cells recruited by defined afferent inputs and dissect the neural basis of processes associated with pain and touch. This strategy thus enables the investigation of sensorimotor, perceptual, cognitive, and motivational processes that guide and shape behavior in health and disease.", "role": "user" }, { "content": "To safely navigate their world , animals need to be able to tell apart a gentle touch from an eye-watering pinch , detect cold water or sense the throbbing pain stemming from an infected cut . These ‘somatic’ sensations are relayed through thousands of nerve endings embedded in the skin and other tissues . Yet the neurological mechanisms that underpin these abilities are complex and still poorly understood . Indeed , these nerve endings can be stimulated by extreme temperatures , harmful chemicals , friction or even internal signals such as inflammation . One event can also recruit many different types of endings: a cut for example , will involve responses to mechanical pressure , tissue damage and local immune response . To disentangle these different actors and how they affect behavior , scientists need to develop approaches that allow them to deliver specific stimuli with increased precision , and to monitor the impact on an animal . To achieve this goal , Schorscher-Petcu et al . used mice in which blue light could trigger specific types of nerve endings . For instance , depending on the genetic background of the animals , a laser could either activate nerve endings involved in pain or gentle touch . Crucially , this could be done from a distance by beaming light with exquisite precision onto the paws of the mice without physically touching or disturbing the animals . How the mice responded could then be observed without any interference . Their behavior was analyzed using a combination of high-speed videos , computer-driven recording systems , and machine learning . This revealed subtle changes in behavior that had not been detected before , spotting microscopic movements of the stimulated paw and mapping simultaneous whole-body movements such as changes in posture or head orientation . The approach therefore allows scientists to assess the impact of touch , pain or temperature sensation in freely behaving mice . It could also be harnessed to develop much needed treatments against chronic pain .", "role": "assistant" } ]

[ { "content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nA cross-linked polymeric micellar delivery system for cisplatin(IV) complex. A polymeric cisplatin(IV) prodrug in the form of cross-linked micelles (M(Pt(IV)) was prepared by first constructing MPEG-b-PCL-b-PLL micelles and then attaching a cisplatin(IV) complex with two axial succinic moieties to the lysine residues of the carrier polymer in aqueous medium. The micelles obtained were characterized by TEM, DLS, and zeta potential measurement. Their in vitro release experiments were carried out at pH 7.4 and 5.0 or in the presence of 5mM sodium ascorbate (NaAsc). Results showed that the micelles were sensitive to both acidic hydrolysis and mild reducing agents; in the presence of 5mM NaAsc, cisplatin(II) was directly released and the released cisplatin(II) could chelate with nucleobases; the micelles displayed comparable cytotoxicities to cisplatin; and the micelles were much more efficiently internalized by the cells than cisplatin(II) and cisplatin(IV) counterparts. Moreover, in vivo study showed accumulation of more Pt species in the tumor site and lower systematic toxicity compared to free cisplatin(II) and cisplatin(IV). This polymeric prodrug of cisplatin is expected to be used more for future study and applications.", "role": "user" }, { "content": "{\"Chemical\": [\"nucleobases\", \"cisplatin\", \"NaAsc\", \"cisplatin(IV)\", \"sodium ascorbate\", \"cisplatin(II)\", \"Pt(IV)\"]}", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: We study the Bayes-Optimal classifier for realistic image classification tasks. We show that in certain cases, the\n\nKeywords: adversarial attack images\n\nDataset Information:\nBDD100K: Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities.\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.\nADAM: ADAM is organized as a half day Challenge, a Satellite Event of the ISBI 2020 conference in Iowa City, Iowa, USA. The ADAM challenge focuses on the investigation and development of algorithms associated with the diagnosis of Age-related Macular degeneration (AMD) and segmentation of lesions in fundus photos from AMD patients.\nMIMIC-CXR: MIMIC-CXR from Massachusetts Institute of Technology presents 371,920 chest X-rays associated with 227,943 imaging studies from 65,079 patients. The studies were performed at Beth Israel Deaconess Medical Center in Boston, MA.\n\nAvailable Datasets: A: BDD100K B: CelebA C: ADAM D: MIMIC-CXR", "role": "user" }, { "content": "CelebA", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nRecently, the cholera outbreak in Haiti demonstrated just how unprepared the country is to rapidly isolate an outbreak of this magnitude, and its vulnerability to the COVID-19 pandemic. This communication briefly examines the health system in Haiti and its vulnerability toward the COVID-19 outbreak.", "role": "user" }, { "content": "[\"Prevention\"]", "role": "assistant" } ]

[ { "content": "Analyze the provided clinical trial criteria. Identify and extract distinct entities from the text.\n\nReturn the results as a JSON structure. Ensure the output is strictly in JSON format without any additional commentary.\n\nCriteria Text:\n\nWomen with a singleton pregnancy undergoing cesarean section after 37 weeks of gestation.", "role": "user" }, { "content": "{\"Condition\": [\"singleton pregnancy\"], \"Device\": [], \"Drug\": [], \"Measurement\": [\"gestation\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [\"Women\"], \"Procedure\": [\"cesarean section\"], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [\"after 37 weeks\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Analyze the given research paper excerpts and address the question provided. Extract the necessary information directly from the text. Your answer should be formatted as a JSON object with the following structure:\n\n\"answer\": A list of text segments from the paper that directly respond to the question.\n\"evidence\": A list of text segments from the paper where the answer can be found.\n\nIf the question cannot be answered with the given text, return \"null\".\n\nDocument: Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines\n\nIn this paper, we describe a methodology to infer Bullish or Bearish sentiment towards companies/brands. More specifically, our approach leverages affective lexica and word embeddings in combination with convolutional neural networks to infer the sentiment of financial news headlines towards a target company. Such architecture was used and evaluated in the context of the SemEval 2017 challenge (task 5, subtask 2), in which it obtained the best performance.\n\nIntroduction\nReal time information is key for decision making in highly technical domains such as finance. The explosive growth of financial technology industry (Fintech) continued in 2016, partially due to the current interest in the market for Artificial Intelligence-based technologies.\nOpinion-rich texts such as micro-blogging and news can have an important impact in the financial sector (e.g. raise or fall in stock value) or in the overall economy (e.g. the Greek public debt crisis). In such a context, having granular access to the opinions of an important part of the population is of key importance to any public and private actor in the field. In order to take advantage of this raw data, it is thus needed to develop machine learning methods allowing to convert unstructured text into information that can be managed and exploited.\nIn this paper, we address the sentiment analysis problem applied to financial headlines, where the goal is, for a given news headline and target company, to infer its polarity score i.e. how positive (or negative) the sentence is with respect to the target company. Previous research BIBREF0 has highlighted the association between news items and market fluctiations; hence, in the financial domain, sentiment analysis can be used as a proxy for bullish (i.e. positive, upwards trend) or bearish (i.e. negative, downwards trend) attitude towards a specific financial actor, allowing to identify and monitor in real-time the sentiment associated with e.g. stocks or brands.\nOur contribution leverages pre-trained word embeddings (GloVe, trained on wikipedia+gigaword corpus), the DepecheMood affective lexicon, and convolutional neural networks.\n\nRelated Works\nWhile image and sound come with a natural high dimensional embedding, the issue of which is the best representation is still an open research problem in the context of natural language and text. It is beyond the scope of this paper to do a thorough overview of word representations, for this we refer the interest reader to the excellent review provided by BIBREF1 . Here, we will just introduce the main representations that are related to the proposed method.\n\nData\nThe data consists of a set of financial news headlines, crawled from several online outlets such as Yahoo Finance, where each sentence contains one or more company names/brands.\nEach tuple (headline, company) is annotated with a sentiment score ranging from -1 (very negative, bearish) to 1 (very positive, bullish). The training/test sets provided contain 1142 and 491 annotated sentences, respectively.\nA sample instance is reported below:\nHeadline: “Morrisons book second consecutive quarter of sales growth”\nCompany name: “Morrisons”\nSentiment score: 0.43\n\nMethod\nIn Figure FIGREF5 , we can see the overall architecture of our model.\n\nSentence representation and preprocessing\nMinimal preprocessing was adopted in our approach: we replaced the target company's name with a fixed word <company> and numbers with <number>. The sentences were then tokenized using spaces as separator and keeping punctuation symbols as separate tokens.\nThe words are represented as fixed length vectors INLINEFORM0 resulting from the concatenation of GloVe pre-trained embeddings and DepecheMood BIBREF19 lexicon representation. Since we cannot directly concatenate token-based embeddings (provided in GloVe) with the lemma#PoS-based representation available in DepecheMood, we proceeded to re-build the latter in token-based form, applying the exact same methodology albeit with two differences: we started from a larger dataset (51.9K news articles instead of 25.3K) and used a frequency cut-off, i.e. keeping only those tokens that appear at least 5 times in the corpus.\nThese word-level representation are used as the first layer of our network. During training we allow the weights of the representation to be updated. We further add the VADER score for the sentence under analysis. The complete sentence representation is presented in Algorithm UID8 .\nInputInput OutputOutput The sentence embedding INLINEFORM0 INLINEFORM1 \n INLINEFORM0 in INLINEFORM1 INLINEFORM2 = [GloVe( INLINEFORM3 , INLINEFORM4 ), DepecheMood( INLINEFORM5 )] INLINEFORM6 Sentence representation\n\nArchitectural Details\nA 1D convolutional layer with filters of multiple sizes {2, 3, 4} is applied to the sequence of word embeddings. The filters are used to learn useful translation-invariant representations of the sequential input data. A global max-pooling is then applied across the sequence for each filter output.\nWe apply the concatenation layer to the output of the global max-pooling and the output of VADER.\nThe activation function used between layers is ReLU BIBREF24 except for the out layer where tanh is used to map the output into [-1, 1] range.\nDropout BIBREF25 was used to avoid over-fitting to the training data: it prevents the co-adaptation of the neurones and it also provides an inexpensive way to average an exponential number of networks. In addition, we averaged the output of multiple networks with the same architecture but trained independently with different random seeds in order to reduce noise.\nThe loss function used is the cosine distance between the predicted scores and the gold standard for each batch. Even though stochastic optimization methods like Adam BIBREF26 are usually applied to loss functions that are written as a sum of per-sample loss, which is not the case for the cosine, it converges to an acceptable solution. The loss can be written as : DISPLAYFORM0 \nwhere INLINEFORM0 and INLINEFORM1 are the predicted and true sentiment scores for batch INLINEFORM2 , respectively.\nThe algorithm for training/testing our model is reported in Algorithm UID15 .\nInputInput OutputOutput ParameterParameters A set of trained models INLINEFORM0 , and the predictions INLINEFORM1 for the test set INLINEFORM2 The number INLINEFORM3 of models to train INLINEFORM4 see sec 3.1 INLINEFORM5 in INLINEFORM6 INLINEFORM7 ) see Alg. UID8 INLINEFORM8 INLINEFORM9 see Eq. EQREF16 INLINEFORM10 INLINEFORM11 INLINEFORM12 Training/Testing algorithm. To build our model, we set N=10.\n\nResults\nIn this section, we report the results obtained by our model according to challenge official evaluation metric, which is based cosine-similarity and described in BIBREF27 . Results are reported for three diverse configurations: (i) the full system; (ii) the system without using word embeddings (i.e. Glove and DepecheMood); and (iii) the system without using pre-processing. In Table TABREF17 we show model's performances on the challenge training data, in a 5-fold cross-validation setting.\nFurther, the final performances obtained with our approach on the challenge test set are reported in Table TABREF18 . Consistently with the cross-validation performances shown earlier, we observe the beneficial impact of word-representations and basic pre-processing.\n\nConclusions\nIn this paper, we presented the network architecture used for the Fortia-FBK submission to the Semeval-2017 Task 5, Subtask 2 challenge, with the goal of predicting positive (bullish) or negative (bearish) attitude towards a target brand from financial news headlines. The proposed system ranked 1st in such challenge.\nOur approach is based on 1d convolutions and uses fine-tuning of unsupervised word representations and a rule based sentiment model in its inputs. We showed that the use of pre-computed word representations allows to reduce over-fitting and to achieve significantly better generalization, while some basic pre-processing was needed to further improve the performance.\n\nFigure 1: Network architecture\n\nTable 2: Final results\n\nTable 1: Cross-validation results\n\nInquiry: What is the source of their lexicon?", "role": "user" }, { "content": "{\"answer\": [\"DepecheMood\"], \"evidence\": [\"Our contribution leverages pre-trained word embeddings (GloVe, trained on wikipedia+gigaword corpus), the DepecheMood affective lexicon, and convolutional neural networks.\"]}", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nthe centers for disease control and prevention ( cdc ; atlanta , ga , usa ) has been performing passive surveillance for c. gattii in the united states since 2009 .\nisolates were collected as part of routine surveillance for c. gattii or submitted to the fungal reference laboratory at the cdc for identification .\nwe identified all isolates to the species level as described ( 8) and used the consensus protocol for multilocus sequence typing ( mlst ) ( 9 ) .\nin the course of this surveillance , several isolates were received from states in the southeast ; genotypic analysis revealed that these isolates consisted of 2 molecular types , vgi and vgiii ( 8) .\nof > 400 isolates received from throughout the united states , 42 were molecular type vgi .\nmlst analysis of vgi isolates showed a cluster of isolates with a single mlst sequence type originating in the southeastern states ( figure 1 ) .\nfive isolates from georgia and 1 each from florida , tennessee , and michigan were indistinguishable by mlst ( sequence type 162 ) .\na second isolate from georgia differed from this group by 1 single - nucleotide polymorphism ( snp ) in the intergenic spacer gene locus .\nmaximum - parsimony tree of multilocus sequence typing analysis of vgi isolates of cryptococcus gattii from the southeastern united states . in the predominant clade ,\n1 isolate was from michigan ; all remaining isolates were from the southeastern united states .\nnearest neighbor isolates were included for comparison , and an environmental vgi isolate from australia was used as an outgroup .\nscale bar indicates 1 single - nucleotide polymorphism . because the population of vgi isolates from the southeastern states ( vgi - se )\nwas only recently identified , it might be a newly emerging population similar to the independent emergences of vgiia and vgiic in the pnw ( 68 ) . to further characterize this cluster , we used whole - genome sequence typing ( wgst ) of isolates from this cluster , other closely related isolates , and unrelated control isolates ( table 1 ; figure 2 ) .\n, san diego , ca , usa ) , used gatk unified genotyper version 2.4 ( broad institute , cambridge , ma , usa ) for snp detection , and constructed maximum - parsimony snp trees using paup * ( sinauer associates , inc . , sunderland , ma , usa ) , as previously described ( 6 ) .\nmaximum - parsimony tree of whole - genome sequence data of isolates of cryptococcus gattii from the southeastern united states .\nnearest neighbor isolates were included for comparison , and an environmental vgi isolate from australia was used as an outgroup .\nalthough the overall topology of the tree we generated remained almost identical to that seen by mlst , we were able to separate each of the isolates within the cluster using wgst ( figure 2 ) .\na total of 41,024 snps were within the vgi - se cluster , which had an average branch length of 4,558 snp differences between any 2 isolates .\nthe isolate from georgia that differed in mlst by 1 snp was placed well within the cluster by wgst . outside the cluster , the nearest neighbor , an isolate collected from a resident of oregon with a history of living near the southeastern united states in texas ( table 1 ) , differed by > 29,000 snps .\nthe other cluster of vgi isolates was separated from vgi - se by 49,992 snps .\npreviously , whole - genome sequencing was performed on isolates of c. gattii molecular type vgii exclusively from the pnw .\nresults showed that the vgii isolates consisted of 3 different highly clonal and recently emerged populations with only 107 , 132 , and 137 snps identified within the vgiia , vgiib , and vgiic populations , respectively ( 10 ) ( table 2 ) .\nthe average branch length between any 2 isolates was < 18 snps for the vgiia and vgiic populations and only slightly higher for the vgiib population . on the basis of snp diversity ,\nthe vgi - se subtype is substantially older than the clonal vgii populations in the pnw and has likely been in the united states for a much longer time . *\nthese isolates , accessed from the same national reference laboratory , were submitted without clinical history ; therefore , we can not discern whether they represent the diversity of 2 isolates from 1 patient over time or whether they are part of a local clonal population .\nall of the patients for whom disease manifestation was known had meningitis ( table 1 ) .\nthis finding differs notably from c. gattii vgii patients in the pnw , among whom a substantial proportion ( 59% ) had a primary pulmonary infection ( 8) . the average age of the patients with isolates in the vgi - se cluster was 46 ( range 1870 ) years . for most patients ,\nthe source of infection was unknown , although 2 of the patients had been exposed to rotting wooden structures ( 1 demolished a wooden structure , 1 power - washed old houses ) .\nour data indicate that the clonal diversity of the c. gattii vgi - se clade in the southeastern united states is an order of magnitude greater than that seen in isolates from the pnw .\nhypothesized that the emergence in the pnw began in the mid-1990s in british columbia , canada , and spread to the united states in the early 2000s ( 12 ) .\ncomparison of the average number of snps detected among the 3 vgii clonal groups in the pnw with the average number of snps detected between the vgi - se isolates indicates that the vgi - se isolates have been in place substantially longer .\nthe limitation to this conclusion is that we do not know the rate of mutation for the vgi or vgii molecular types ; however , there is no reason to believe that they would be substantially different .\nthere may also be higher rate of recombination within the vgi - se clade related to opposite - sex or same - gender sexual recombination .\nthe isolates from this clade for which the mating type is known are all , but that does not preclude the possibility that some mating type a isolates exist in the environment in the southeastern united states .\nthe first identified isolate of c. gattii in the united states was reported from west virginia in 1924 ( 11 ) , although the isolate was not recognized as c. gattii vgi until decades later ( 12 ) .\ntwo other historical reports of c. gattii isolates from the southeastern united states exist : the first , from 1968 , describes clinical and environmental isolates from savannah , georgia ; the other , from 1982 , describes isolates from alabama , tennessee , and louisiana from patients with no travel history to a c. gattii endemic region ( 13,14 ) .\nalthough both of these reports use the previous name for c. gattii , c. neoformans serotypes b and c , their results clearly indicate that c. gattii has existed in the southeastern united states for > 40 years , as opposed to the recent emergence in the pnw during the past 2 decades .\na more recent report describes a c. gattii vgi isolate from an hiv - positive patient in north carolina ( 15 ) ; those authors surmised that the isolate was related to travel to san francisco , but that assumption may have to be revised . no current molecular clock for c. gattii indicates the time required to generate the level of diversity seen in the vgi isolates\nhowever , our findings lend credence to the hypothesis that c. gattii has circulated in the southeastern united states long enough to be considered endemic .", "role": "user" }, { "content": "cryptococcus gattii is a recognized pathogenic fungus along the pacific coast of the united states from california to washington . here \n we report that c. gattii may also be endemic to the southeastern united states and has probably been present there longer than in the pacific northwest .", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nHowever,occasionallytheN=1parametercausedtheprogramtoassignverysmallsequences(1-4bp)todistantupstreamexons,whentheyprobablymatchnearertothecorrespondingcodingsequence.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: camostat mesylate is a drug that may work to combat COVID-19, the disease caused by the SARS-CoV-2 coronavirus.\n\nResearch Abstract:\nDifferent treatments are currently used for clinical management of SARS-CoV-2 infection, but little is known about their efficacy yet.\nHere we present ongoing results to compare currently available drugs for a variety of diseases to find out if they counteract SARS-CoV-2-induced cytopathic effect in vitro.\nOur goal is to prioritize antiviral activity to provide a solid evidence-driven rationale for forthcoming clinical trials.\nSince the most effective antiviral approaches are usually based on combined therapies that tackle the viral life cycle at different stages, we are also testing combinations of drugs that may be critical to reduce the emergence of resistant viruses.\nWe will provide results as soon as they become available, so data should be interpreted with caution, clearly understanding the limitations of the in vitro model, that may not always reflect what could happen in vivo.\nThus, our goal is to test the most active antivirals identified in adequate animal models infected with SARS-CoV-2, to add more information about possible in vivo efficacy.\nIn turn, successful antivirals could be tested in clinical trials as treatments for infected patients, but also as pre-exposure prophylaxis to avoid novel infections until an effective and safe vaccine is developed.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nfigure 6 outlines the fabrication process of our \n devices . we start with a commercial silicon on insulator ( soi , from \n soitec ) substrate with a 340 nm p - type ( 7 10 cm ) si layer on top of a 2 m buried oxide ( box ) . \n\nfirst , a 100 nm sin mask is deposited by plasma enhanced chemical \n vapor deposition ( pecvd , oxford plasmalab100 ) onto the soi substrate \n at 300 c ( figure 6b ) .\nnext , a si photonic waveguide and the pd area are defined by \n electron beam lithography ( ebl , raith eline 150 ) using positive e - beam \n resist ( zep 520a ) .\nthe ebl pattern is subsequently transferred to \n sin by reactive ion etching ( rie ) ( oxford plasmalab 100 ) with a chf3/o2 gas mixture .\nthen the soi substrate is locally \n oxidized ( wet , 1000 c ) to grow a sio2 layer only \n in localized patterns defined by ebl where si is exposed to o2 , while at the same time a sin mask prevents o2 diffusion into the si in protected areas ( figure 6c ) .\nafter oxidation , the sacrificial sin \n mask layer is etched in hot phosphoric acid ( h3po4 , 180 ) followed by sio2 removal in a buffered oxide \n etch ( boe ) solution .\nthe ohmic contact to si is realized by al evaporation \n followed by metal lift - off and thermal alloying at 460 c in \n a forming gas ( h2/n2 , 5%/95% ) environment .\nthis \n fabrication process is based on the technique of local - oxidation of \n si ( locos ) in which a si waveguide is defined by oxide spacers rather than rie .\nthe locos process enables the \n realization of low - loss ( 0.3 db / cm ) si photonic waveguides coupled to a schottky pd using the same fabrication \n step . fabrication process of si slg schottky pds integrated with \n photonic waveguides .\n( a ) planar soi substrate ; ( b ) pecvd deposition \n and patterning of sin mask ; ( c ) local oxidation ; ( d ) etching of sin \n and sio2 al ohmic contact to si ; ( e ) slg transfer ; ( f ) \n formation of schottky contact and consequent slg etching .\nslg is grown on a 35 m cu foil following \n the process described in ref ( 98 ) .\nthe substrate is annealed in hydrogen atmosphere ( h2 , 20 sccm ) up to 1000 c for 30 min .\nthe substrate \n is subsequently cooled in vacuum ( 1 mtorr ) to room temperature and \n removed from the chamber .\nafter growth , the quality and uniformity \n of slg are monitored by raman spectroscopy using a renishaw invia \n equipped with a 100 objective ( numerical aperture na = 0.85 ) . \n\nthe raman spectrum of slg on cu at 514 nm is shown in figure 7b ( green curve ) .\nthe 2d peak is a single sharp lorentzian with full width at half - maximum , \n fwhm(2d ) 29 cm , a signature of slg .\ndifferent ( 20 ) point measurements show \n similar spectra , which indicate uniform quality .\nthe position of the \n g peak , pos(g ) , is 1589 cm , with fwhm(g ) \n 13 cm .\nthe 2d peak position , pos(2d ) \n is 2698 cm , while the 2d to g peak intensity \n and area ratios , i(2d)/i(g ) and a(2d)/a(g ) , are 2.6 and 5.8 , respectively , \n indicating a p - doping 300 mev , which corresponds to a carrier concentration 5 10 cm .\n( a ) raman spectra of ( red curve ) si substrate \n and ( black curve ) slg transferred on si .\n( b ) raman spectra of ( green \n curve ) slg on cu , and ( blue curve ) after normalized , point - to - point \n subtraction of the si substrate spectrum ( shown in ( a ) , red curve ) \n from the spectrum of slg transferred on si ( shown in ( a ) , black curve ) .\na 500 nm thick layer of poly(methyl \n methacrylate ) ( pmma ) is spin coated on the slg / cu sample and then \n placed in a solution of ammonium persulfate ( aps ) in di water until \n cu is completely etched . after cu etching , \n the pmma membrane with attached slg is transferred to di water for \n cleaning aps residuals . to obtain a schottky interface between \n the si waveguide and slg without the native oxide layer ,\nwe perform \n the transfer in diluted hydrofluoric acid ( hf ) and di water ( 1:100 ) . \n after cleaning from aps residuals ,\na slg / pmma membrane is placed on \n a plastic beaker containing 5 ml/500 ml hf and di water .\nnext , the \n target soi chips are first dipped in boe for 5 s to etch the si native \n oxide and then used to lift the floating slg / pmma membrane from diluted \n hf . as a result ,\nduring drying , the presence of hf at the slg / si interface \n prevents si oxidation and allows formation of oxide free \n slg / si schottky contacts . after drying ,\npmma is removed in acetone , \n which leaves slg to entirely cover the soi .\nwe also transfer slg from \n the same cu foil with the same transfer procedure onto si .\nthe raman spectrum of slg transferred on si is shown in figure 7a ( black line ) .\nthis \n is measured at 514.5 nm and with laser power below 300 w to \n avoid possible heating effects or damage .\nthe d peak region overlaps \n the bands at 12001500 cm , attributed \n to third order raman scattering from to phonons in the si substrate .\nthe peaks at 1550 and 2330 \n cm in the raman spectrum of si substrate ( red \n line ) arise from molecular vibrations of ambient oxygen ( o2 ) and nitrogen ( n2 ) .\nthe raman spectra of the transferred slg film \n ( black line ) and reference si substrate ( red line ) are acquired using \n identical exposure time and laser power .\nafter the intensity of the \n third order si peak at 1450 cm in the \n si reference spectrum ( red line ) is normalized to the same peak in \n the spectrum of the transferred slg film ( black line ) , a point - to - point \n subtraction is implemented ( figure 7b , blue line ) .\nthe 2d peak retains its single - lorentzian line - shape with fwhm(2d ) \n 33 cm , validating that slg has been successfully \n transferred .\npos(g ) 1584 cm , fwhm(g ) 17 cm , and pos(2d ) 2687 cm , while i(2d)/i(g ) and a(2d)/a(g ) are 3.2 and 5.9 , respectively , suggesting a p - doping \n 4 10 cm ( 200 \n mev ) .\nafter slg transfer , we use an additional \n ebl step followed by o2 plasma etching to selectively remove \n slg from the substrate area containing five waveguides and dedicated \n to the reference m si devices .\nthen a schottky contact is prepared \n by evaporation and liftoff of an 3 nm/100 nm cr / au metal strip intersecting \n the si waveguide with slg on top ( figure 6f ) ( or without slg for reference devices ) \n and forming a schottky interface for photodetection .\nfinally , the \n samples are placed in a reactive o2 plasma to remove superfluous \n slg .\nthe tfe current is given \n by1where a * * is the \n effective richardson constant , k is the boltzmann \n constant , t is the temperature , and q is the electron charge .\nthe contribution of tfe to charge injection \n across the m si interface can be evaluated by comparing the \n thermal energy kt to e00 , defined as2where is the reduced \n planck constant , n is the si doping , m * is the effective mass of the charge carriers in si , and s is the dielectric permittivity of si . when kt e00 , the tfe process mainly \n contributes to charge carriers injection across the schottky interface . the parameters e0 and are analytically defined as34 in our case , for si doping 7 10 cm using eq 2\n, we get e00 45 mev , comparable to the thermal \n energy at room temperature of 26 mev , reflecting a significant tfe \n contribution to carriers injection at the schottky interface .", "role": "user" }, { "content": "we report an on - chip integrated metal \n graphene silicon plasmonic schottky photodetector with 85 ma / w \n responsivity at 1.55 m and 7% internal quantum efficiency . \n \n this is one order of magnitude higher than metal \n silicon schottky \n photodetectors operated in the same conditions . at a reverse bias \n of 3 v , we achieve avalanche multiplication , with 0.37a / w responsivity \n and avalanche photogain 2 . this paves the way to graphene \n integrated silicon photonics .", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nWethankMTakeichi,PCoulombe,GLongmore,andLGoldforsharingtheirantibodies,andAGdeHerrerosfortheSnailconstruct.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nsebaceous carcinoma , first described by allaire in 1891 accounts for less than 1% of all cutaneous malignancies .\nit is a rare but aggressive malignant neoplasm that arises from sebaceous glands with a tendency for both local recurrence and distant metastases .\nwe report a case of an extraocular type of sebaceous carcinoma of the scalp with no distant metastases .\na 65-year elderly man presented with a large asymptomatic swelling over the vertex of the scalp , which gradually progressed over a period of twelve months .\nexamination showed a large swelling of 15 12 5 cm size situated over the vertex of the scalp extending to the occipital and tempero - parietal regions.the tumor showed focal ulceration with yellowish malodorous seropurulent discharge [ figure 1 ] .\nclinically , a differential diagnosis of cylindroma , angiosarcoma , deep fungal infections , nocardiosis , mycobacterial or atypical mycobacterial infections were considered .\na large multi- lobulated swelling with ill - defined margins and irregular surface showing focal ulceration and yellow sero - purulent discharge the culture of the seropurulent discharge revealed staphylococcus aureus and acinetobacter baumanni suggestive of secondary bacterial infection .\nafb stain and culture for both mycobacteria and atypical mycobacteria and fungal culture were negative .\nct scan of the brain showed only age related cerebral atrophy , and there was no evidence of extension of the tumour or metastatic deposits .\nhistopathology revealed an infiltrating neoplasm in the dermis composed of cells arranged in lobules separated by fibrovascular stroma .\n[ figure 2 ] neoplastic cells were round having moderate amount of eosinophilic to vacuolated cytoplasm and large nuclei with prominent eosinophilic nucleoli .\ndermis showing a neoplasm composed of cells arranged in lobules separated by fibrovascular stroma ( h and e , 4 ) neoplastic cells having moderate amount of eosinophilic to vacuolated cytoplasm and large nuclei with prominent eosinophilic nucleoli and increased mitoses ( h and e , 40 ) immunohistochemical marker study showed diffuse strong positivity for cytokeratin and focal positivity for epithelial membrane antigen ( ema ) [ figure 4 ] .\nsebaceous carcinoma is a rare malignant neoplasm , often occurs in adults with a slight male preponderance this malignancy can occur as peri - ocular and extraocular types and the former variant contributes to 75% of sebaceous neoplasms .\nthe upper eyelid is affected two to three times more often than the lower eyelid due to greater number of meibomian glands extraocular sebaceous carcinoma which constitutes 25% of the sebaceous neoplasms has been reported more commonly on the head and neck areas followed by trunk , salivary glands , genitalia , breast , ear canal , and the intra - oral cavity . the most frequent clinical presentation is a painless subcutaneous nodule but it can also present as pedunculated lesions , irregular mass or diffuse thickening of the skin .\nthis protean appearance frequently masquerades as other benign tumors or inflammatory conditions thereby leading to delay in diagnosis , inappropriate treatment , increased morbidity , and mortality .\nthe morphological hall mark of sebaceous differentiation is the detection of sebaceous cells and demonstration of fat in vacuolated tumor cells .\nspecial stains such as oil red o may be helpful in confirming the presence of fat , but requires frozen section .\nother differential diagnosis includes basal cell carcinoma with sebaceous differentiation for poorly differentiated sebaceous cell carcinoma .\nour case did not show poorly differentiated basaloid cells and other features of basal cell carcinoma .\nsebaceous carcinoma cells express immunohistochemical markers such as cytokeratin , epithelial membrane antigen ( ema ) , cam5.2 and anti - breast carcinoma associated antigen-225 antibody .\nthe current case showed diffuse strong cytokeratin expression and ema was focally positive in cells with sebaceous differentiation .\nconsidering the morphological , histopathological and immunohistochemical marker study findings we favoured a diagnosis of sebaceous carcinoma .\nthe common associations of sebaceous carcinoma are muir - torre syndrome , an autosomal dominant condition comprising of sebaceous neoplasm with one or more low - grade visceral malignancies and nevus sebaceous of jadassohn .\ndistant metastases and recurrence rates are more common in the ocular type of sebaceous carcinoma when compared to extraocular sebaceous carcinoma as seen in our case .\nrecurrence rates of ocular sebaceous carcinoma ranges from 11% to 30% with distant metastases occurring in 3% to 25% though extraocular sebaceous carcinoma is less aggressive , a study with 91 cases of extraocular sebaceous carcinoma showed a recurrence rate of 29% with 21% developing metastases .\nwide excision and selective use of radiotherapy is the ideal treatment of choice . in summary ,\nthis tumor should suggest the possibility of muir - torre syndrome and alert the clinician to search for occult malignancies .", "role": "user" }, { "content": "extra ocular sebaceous carcinoma is a rare malignancy when compared to peri ocular variant and these are derived from sebaceous gland epithelium . \n the aggressive types of extra ocular sebaceous neoplasm are reported with lymph node and visceral metastasis associated with poor prognosis . here \n we report a case of extensive cutaneous extra ocular sebaceous cell carcinoma confined to large area of scalp proven by immunohistochemistry without intra cranial involvement , distant metastases or evidence of muir - torre syndrome .", "role": "assistant" } ]

[ { "content": "Examine the text below and extract disease-related entities. Present your findings in a structured JSON format.\n\nYour response should be a JSON object with keys as entity types and values as lists of entities. If no entities are found, return an empty list for that type.\n\nContent:\n\nLinkage of DNA markers at Xq28 to adrenoleukodystrophy and adrenomyeloneuropathy present within the same family. We present a large kindred that contained patients with either adrenoleukodystrophy (ALD) or adrenomyeloneuropathy (AMN). The pedigree clearly supported the X-linked mode of inheritance of the nonneonatal form of ALD/AMN. Analysis with DNA markers at Xq28 suggested segregation of both ALD and AMN with an identical haplotype. This indicated that nonneonatal ALD and AMN are caused by a mutation in the same gene at Xq28. It showed, furthermore, that phenotypic differences between ALD and AMN are not necessarily the consequence of allelic heterogeneity due to different mutations within the same gene. The maximal lod score for linkage of the ALD/AMN gene and the multiallelic anonymous DNA marker at DXS52 was 3. 0 at a recombination fraction of 0. 00. This made a prenatal or presymptomatic diagnosis and heterozygote detection by DNA analysis with this marker reliable.", "role": "user" }, { "content": "{\"Disease\": [\"AMN\", \"ALD\", \"adrenomyeloneuropathy\", \"adrenoleukodystrophy\"]}", "role": "assistant" } ]

[ { "content": "Craft a concise summary for a chemistry research paper using the provided title and selected text segments.\n\nHeading:\nIntramolecular Disulfide Bond between Catalytic Cysteines in an Intein Precursor\n\nContent Extracts:\n\n<p>Protein splicing is a self-catalyzed post-translational process in which an intervening protein, called an intein, is excised from a precursor protein, together with the ligation of the two flanking sequences immediately N- and C-terminal to the intein, termed N- and C-exteins, respectively1–3 (supporting information Fig. S1). Protein splicing is strictly intramolecular4, requiring no external co-factor or energy input4–5. Inteins have been found in all domains of life6, but exist only in unicellular organisms7. Hedgehog (Hh) proteins, crucial for the embryonic patterning of higher eukaryotes, undergo similar auto-processing in the cholesterolylation of the Hh signaling domain by the Hh processing domain8–10. The Hh processing domain and inteins share many conserved sequence motifs and a common Hh-intein (HINT) fold11.</p><p>There is usually a residue with a side chain nucleophile (e.g. Cys, Ser, and Thr) at the junction between the N-extein and intein (N-terminal splice junction) and between C-extein and intein (C-terminal splice junction). These two conserved residues, Cys1 (the first residue of intein) and Cys+1 (the first residue of C-extein) for many inteins, serve as the nucleophiles for first two steps of splicing, N-X acyl shift and trans-esterification, respectively (supporting information Fig. S1). Therefore, differential reactivity of Cys residues can control the steps of protein splicing12–13. Recently, an intramolecular disulfide bond has been engineered in Ssp DnaE intein precursor with a CPGC motif14, resulting in a stable intein precursor that can be reduced to induce splicing. Likewise, intein-mediated protein ligation was used to create a non-native disulfide bond to trap an intein precursor of the M. jannaschii KlbA intein15. Salic et al. have shown that there is an intramolecular disulfide bond in the Hh processing domain16, which needs to be reduced before cholesterolylation can proceed. However, within native intein precursor sequences, intramolecular disulfide bonds have not been observed between the two catalytic cysteines. For Cys1 and Cys+1 to catalyze protein splicing efficiently, the N- and C- terminal splice junctions need to be close in space. However, crystal structures of inteins show variable distances between the two junctions, from 3~4 Å up to 8~9 Å17–20.</p><p>Recently, we solved the NMR structure of a hyperthermophilic intein interrupting the Pyrococcus abyssi DNA polymerase II (Pab PolII)21–22. The Pab PolII intein only splices at high temperature, offering the opportunity to study a stable precursor containing native intein and extein sequences at room temperature. We overexpressed in E. coli BL21(DE3) a 25 kDa precursor composed of the Pab PolII intein, a short N-extein and a short His-tagged C-extein, which contains Cys1 and Cys+1, the only two cysteines in the sequence (see supporting information). The Pab PolII intein precursor was purified by nickel-NTA affinity chromatography. In the SDS PAGE in Fig. 1A, instead of the expected 25 kDa band, a strong 20 kDa band was observed along with a very weak 25 kDa band. We then treated the Pab PolII precursor protein with increasing amounts of reducing agent (tris (2-carboxyethyl) phosphine (TCEP) or β-mercaptoethanol) at room temperature, below the optimal temperature for protein splicing of this intein. The 25 kDa band became progressively stronger with the concomitant decrease of the 20 kDa band. We suspect that an intramolecular disulfide bond was formed between the two catalytic cysteine residues, resulting in a circle-like protein and increasing the rate of migration in non-reducing SDS PAGE23. Therefore, the 20 kDa protein band is likely the disulfide-linked form of the intein precursor (oxidized precursor), which is then converted to the expected 25 kDa band (reduced precursor) upon reduction at a temperature that does not permit splicing. Additional bands observed by SDS-PAGE between 40–50 kDa are likely intein dimers, as they disappear with the addition of reducing agent. There are two cysteines in each intein monomer, and therefore several different types of intermolecular disulfide bonds can form, giving rise to multiple bands.</p><p>The identification of the 20 kDa band as an intein with an intramolecular disulfide bond is further supported by the comparison with a Cys1Gly mutant, which cannot form an intramolecular disulfide bond. As expected, the 20 kDa band was absent for this mutant (Fig. 1B). The WT precursor protein migrating at 20 kDa was then excised from the SDS-PAGE, digested by trypsin and analyzed by LC-MS/MS. All predicted tryptic peptides were identified except for the ones containing a single cysteine (supporting information Fig. S2). Instead, a tryptic peptide containing covalently linked Cys1 and Cys+1 was detected and identified by accurate MS and MS/MS, conclusively demonstrating the presence of the intramolecular disulfide bond between the two active site cysteines (Fig. 1C). This disulfide in Pab PolII intein precursor is particularly strong, as it forms on over-expression in E. coli BL21 (DE3) rather than requiring a trxB- and gor-strain.</p><p>Next, we tested if the presence of the intramolecular disulfide affects the splicing activity. Very little ligated extein was detected after overnight incubation at 60°C in the absence of reducing agent, indicating the intramolecular disulfide bond inhibits splicing. TCEP was then introduced to break the disulfide bond to initiate splicing. Ligated exteins, detected by LC/MS and confirmed by MS/MS, were generated in the presence of 0.25 mM TCEP (supporting information Fig. S3 and S4). Spliced exteins accumulated with TCEP concentration up to 2 mM (Fig. 2A and 2B).</p><p>Next, we explored the influence of extein residues on the formation of the disulfide bond. In this precursor, three of the four C-terminal residues of the N-extein are positively charged and three of the four N-terminal residues of the C-extein are negatively charged (see supporting information). This might provide attractive forces that favor disulfide bond formation. Mutation of Lys(-4), Arg(-3) and Arg(-2) in the N-extein to Glu, Asp, and Asp, respectively, results in a significant decrease of oxidized species with the concurrent increase of the reduced species in SDS-PAGE (Fig. 2C). This suggests that electrostatic interactions between the N- and C-exteins play an important role in the formation of the intramolecular disulfide bond and in coordinating the N- and C-terminal splice junction. Electrostatic interactions were also observed to assist in the reassociation of the fragments of the split Npu DnaE intein24.</p><p>We tested if temperature can change the equilibrium between reduced and oxidized precursor. Purified Pab PolII intein precursor protein was incubated at 35°C, 45°C, 55°C, 65°C, and 75°C overnight at pH 6.5 (Fig. 2D). The protein aggregates when the temperature is above 80°C (data not shown). With increased temperature, there is an increased amount of reduced precursor and a decreased amount of oxidized precursor, indicating that the disulfide bond is weakened by high temperature, which may help account for the temperature dependence of the splicing activity.</p><p>This is the first time that an intramolecular disulfide bond between the two active site cysteines, Cys1 and Cys+1, has been discovered in a native intein precursor protein. The two cysteines are separated by 185 residues of primary sequence, in contrast to engineered intein disulfide bonds separated by just two residues, such as that formed by the CPGC motif.14 In the Hh processing domain, the Cys1 forms a disulfide bridge with another cysteine that is not homologous to Cys+1, which must be reduced by a protein disulfide isomerase before cholesterolylation16. Salic et al. proposed that the disulfide may be important for the folding of the Hh processing domain, but this is not the case for the Pab PolII intein, which has a well folded structure without the intramolecular disulfide bond22.</p><p>The Pab PolII intein interrupts a crucial extein, the DNA polymerase II DP2 subunit, which is essential for DNA replication in Pab25–26. Pab is anaerobic, and the presence of oxygen may impose oxidative stress and result in a more oxidizing cellular environment. Under these conditions, disulfide formation between C1 and C+1 may be promoted, inhibiting splicing and the formation of the fused active exteins, the DNA PolII DP2 subunit. This may arrest DNA replication to preserve the integrity of the genome during oxidative stress. Callahan et al. have proposed a similar redox-switch for the intein that interrupts the Pab MoaA14. The molybdopterin cofactor produced by active MoaA is used in a variety of redox-dependent enzymes. Although disulfide bonds are unusual in intracellular proteins, genomic studies suggest that they are more common in hyperthermophilic archaebacteria, including Pab, suggesting that the intramolecular disulfide bond might be relevant in vivo27–28.</p><p>The temperature-dependence of the Pab PolII intein may also be a function of the redox switch, and possibly play a role in regulation of extein activity. Below its optimal growth temperature of ~100°C, Pab needs to shut down DNA replication. As shown in Fig. 2D, more intramolecular disulfide bond is present at lower temperatures for the Pab PolII precursor, inhibiting splicing. With native exteins, this would prevent the formation of active DNA polymerase DP2. The redox sensitivity of this intramolecular disulfide bond may contribute to the mechanism how Pab stops replication, even at relatively moderate temperature, such as 37°C.</p><p>Interestingly, the intein interrupting another essential DNA replication protein in Pab, replication factor 229, also has the conserved residues C1 and C+1. Although the intein has yet to be studied, it may further contribute to redox regulation in the physiological response to hyperoxia and low temperature in Pab using redox chemistry of the intramolecular disulfide bond. It is intriguing that inteins may not just be a parasitic element in protein or DNA sequence7; instead, inteins may act as switches and regulate the function of crucial exteins and cellular physiology through redox sensitivity conferred by intramolecular disulfide bonds.</p><p>In summary, for the first time, we have conclusively established the existence of an intramolecular disulfide bond between two active site residues, Cys1 and Cys+1, in an intein precursor composed of native Pab PolII intein and exteins. Our findings suggest that redox chemistry of intramolecular disulfide bond may regulate protein splicing and extein function.</p>", "role": "user" }, { "content": "Protein splicing is a self-catalyzed and spontaneous post-translational process in which inteins excise themselves out of precursor proteins while the exteins are ligated together. We report the first discovery of an intramolecular disulfide bond between the two active site cysteines, Cys1 and Cys+1, in an intein precursor composed of the hyperthermophilic P. abyssi PolII intein and extein. The existence of this intramolecular disulfide bond is demonstrated by the effect of reducing agent on the precursor, mutagenesis, and liquid chromatography\\xe2\\x80\\x93mass spectrometry (LC-MS) with tandem MS (MS/MS) of the tryptic peptide containing the intramolecular disulfide bond. The disulfide bond inhibits protein splicing, and splicing can be induced by reducing agents such as tris (2-carboxyethyl) phosphine (TCEP). The stability of the intramolecular disulfide bond is enhanced by electrostatic interactions between the N- and C-exteins but is reduced by elevated temperature. The presence of this intramolecular disulfide bond may contribute to the redox control of splicing activity in hypoxia and at low temperature and point to the intriguing possibility that inteins may act as switches to control extein function.", "role": "assistant" } ]

[ { "content": "Examine the citation provided below. Determine the primary purpose of this citation within the context of the research paper. \n\nCitation:\n\nPropionylations were found at 129 sites on the mid-stationary phase proteins in this study, in comparison to the 121 and 323 sites identified on midexponential and late stationary phase proteins, respectively, in our previous study (Okanishi et al. 2014).", "role": "user" }, { "content": "Result", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: In this paper, we propose an iterative optimization framework to optimize the memory consumption of deep learning\n\nKeywords: actor-action semantic segmentation video\n\nDataset Information:\nMNIST-1D: A minimalist, low-memory, and low-compute alternative to classic deep learning benchmarks. The training examples are 20 times smaller than MNIST examples yet they differentiate more clearly between linear, nonlinear, and convolutional models which attain 32, 68, and 94% accuracy respectively (these models obtain 94, 99+, and 99+% on MNIST).\nKuzushiji-49: Kuzushiji-49 is an MNIST-like dataset that has 49 classes (28x28 grayscale, 270,912 images) from 48 Hiragana characters and one Hiragana iteration mark.\nSet11: Set11 is a dataset of 11 grayscale images. It is a dataset used for image reconstruction and image compression.\nCIFAR-10: The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck).\n\nAvailable Datasets: A: MNIST-1D B: Kuzushiji-49 C: Set11 D: CIFAR-10", "role": "user" }, { "content": "CIFAR-10", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nPromoting health in schools through a board game . Primary prevention and health promotion have become salient topics in Canadian society and in nursing during the past two decades . The noncommunicable chronic diseases , such as heart disease and cancer , have been linked to specific lifestyle behaviors or habits , which often develop early in life . The success of public health efforts to improve the health status of all Canadians depends substantially on the success of educational programs directed toward children . Effective teaching strategies that seek to promote health and wellness in children need to be developed and empirically evaluated . Educational games may provide an efficient vehicle for carrying out developmentally specific nursing interventions in school settings . This article begins with a brief overview of the historical origins of games , along with their advantages and disadvantages as educational strategies . The results of a pretest-posttest control group design study that evaluated the effectiveness of a board game as a primary prevention teaching strategy with 23 sixth grade children in Winnipeg , Manitoba are presented . The experimental group had significant gains in knowledge related to anatomy and physiology , diet , and lifestyle risk factors associated with the development of heart disease and cancer .", "role": "user" }, { "content": "{\"Intervention\": [\"board game\", \"effectiveness of a board game as a primary prevention teaching strategy\"], \"Outcome\": [\"lifestyle behaviors\", \"knowledge related to anatomy and physiology , diet , and lifestyle risk factors associated with the development of heart disease and cancer .\"], \"Participant\": [\"children .\", \"in children\"]}", "role": "assistant" } ]

[ { "content": "Analyze the provided text excerpt from a scientific document. Identify and extract distinct entities based on predefined categories.\n\nDeliver the results as a JSON structure where each key represents an entity category, and the associated value is a list of identified entities. If no entities are found for a category, return an empty list.\n\nText Excerpt:\n\nSynergy between signal transduction pathways is obligatory for expression of c-fos in B and T cell lines: implication for c-fos control via surface immunoglobulin and T cell antigen receptors. Expression of the protooncogene c-fos is controlled by three main regulatory pathways involving kinase C, cAMP, and calcium. Kinase C mediates its effects via phosphorylation of serum response factor (SRF) which interacts with the serum response element (SRE); cAMP and calcium mediate their effects via phosphorylation of CREB (cAMP regulatory element binding protein) presumably by activation of a protein kinase A or calmodulin-regulated kinase. We have examined the function of these elements in Burkitt 's lymphoma cells (Ramos and Daudi) as well as a T lymphocytic cell line (Jurkat). We have found that stimulation of any one of these pathways alone has little or no effect on c-fos induction. However, kinase C activation (PMA stimulation) combined with either cAMP (forskolin plus MIX) or calcium stimulation (ionophore) leads to greatly enhanced c-fos induction. By contrast, cAMP in the presence of calcium shows no synergy in c-fos induction. Okadaic acid augments PMA-as well as calcium-mediated activation of c-fos, and has little or no effect when combined with cAMP. The main difference between Ramos (B cells) and Jurkat (T cells) in the regulation of c-fos is that cAMP plus calcium is strongly synergistic in Jurkat and is without effect in Ramos. Analysis of AP-1 activity using gel mobility shift assays confirms that the requirements for synergy in c-fos mRNA induction are paralleled by requirements for synergy in induction of AP-1 activity. Signaling in B cells due to anti-Ig stimulation involves both kinase C activation and release of intracellular calcium, and results in c-fos mRNA induction. Our results indicate that synergy between the kinase C activation and calcium is needed for efficient c-fos induction since neither of these two alone induces c-fos well. That synergy of signaling pathways is relevant for the anti-Ig induction of c-fos is supported by the fact that cAMP-inducing agents and okadaic acid further enhance anti-Ig induction of c-fos. These results suggest that cell-specific patterns of synergy are an essential feature for c-fos induction and may be relevant for c-fos control through B and T cell antigen receptors.", "role": "user" }, { "content": "{\"CellLine\": [\"Ramos\", \"Jurkat\", \"B and T cell lines\", \"Burkitt \\u0027s lymphoma cells\", \"Daudi\", \"T lymphocytic cell line\"], \"CellType\": [\"T cells\", \"B cells\"], \"DNA\": [\"SRE\", \"serum response element\", \"c - fos\", \"protooncogene c - fos\"], \"Protein\": [\"anti - Ig\", \"cAMP\", \"cAMP regulatory element binding protein\", \"protein kinase A\", \"AP - 1\", \"SRF\", \"kinase C\", \"serum response factor\", \"calmodulin - regulated kinase\", \"T cell antigen receptors\", \"surface immunoglobulin\", \"CREB\", \"B and T cell antigen receptors\", \"Kinase C\"], \"RNA\": [\"the protooncogene c - fos\", \"c - fos\", \"c - fos mRNA\"]}", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: I want to apply an unsupervised learning method for image restoration.\n\nKeywords: image restoration images paragraph-level\n\nDataset Information:\nCOVERAGE: COVERAGE contains copymove forged (CMFD) images and their originals with similar but genuine objects (SGOs). COVERAGE is designed to highlight and address tamper detection ambiguity of popular methods, caused by self-similarity within natural images.\nMiddlebury: The Middlebury Stereo dataset consists of high-resolution stereo sequences with complex geometry and pixel-accurate ground-truth disparity data. The ground-truth disparities are acquired using a novel technique that employs structured lighting and does not require the calibration of the light projectors.\nSTARE: The STARE (Structured Analysis of the Retina) dataset is a dataset for retinal vessel segmentation. It contains 20 equal-sized (700×605) color fundus images.\nSTL-10: The STL-10 is an image dataset derived from ImageNet and popularly used to evaluate algorithms of unsupervised feature learning or self-taught learning. Besides 100,000 unlabeled images, it contains 13,000 labeled images from 10 object classes (such as birds, cats, trucks), among which 5,000 images are partitioned for training while the remaining 8,000 images for testing.\n\nAvailable Datasets: A: COVERAGE B: Middlebury C: STARE D: STL-10", "role": "user" }, { "content": "Middlebury", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nINTRODUCTION: Clustered regularly interspaced short palindromic repeats (CRISPR) are segments of nucleic acid that play a role in prokaryotic defense and form the basis of a genome editing technology that allows permanent alteration of genetic material. This methodology, known as CRISPR-Cas9, is poised to revolutionize molecular biology, but no literature yet exists on how these advances will affect hospitalists. AREAS COVERED: These specialists in inpatient medicine care for a wide variety of hospitalized patients, including those with infectious disease, cancer, cardiovascular disease, autoimmune disease, hematologic disease, and a variety of other conditions that may soon be impacted by advances in gene-modifying technology provided by CRISPR-Cas9. A Literature search was performed using PubMed [1 December 2019-17 April 2020]. EXPERT OPINION: This paper reviews the remarkable diagnostic and therapeutic potential of the CRISPR-Cas9 platform and concludes with a look at ethical issues and technical hurdles pertaining to the implementation of permanent gene modification in the practice of Hospital Medicine.", "role": "user" }, { "content": "[\"Diagnosis\", \"Treatment\"]", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nNeuronalcellsofallareasintheadultbrainpresentAnnexinA7inthenucleus,whereasglialfibrillaryacidicprotein(GFAP)-positiveastrocytesexhibitboth,acytoplasmicandnuclearstaining.", "role": "user" }, { "content": "[\"acidic\", \"protein\"]", "role": "assistant" } ]

[ { "content": "Analyze the provided paragraph from a scientific document. Your goal is to identify and extract relevant entities.\n\nFormat your findings as a JSON object, where each key represents a category of entities, and the corresponding value is a list of entities identified in that category. If no entities are found for a category, return an empty list.\n\nFocus on precision and ensure that the output is strictly in JSON format.\n\nDocument:\n\nTumor-infiltrating Tim-3(+) T cells proliferate avidly except when PD-1 is co-expressed: Evidence for intracellular cross talk Programmed Death 1 (PD-1) and T cell Ig and mucin domain-3 protein (Tim-3) are immune checkpoint receptors highly expressed on tumor infiltrating T lymphocytes (TIL). PD-1 inhibits T cell activation and type-1 T cell responses, while Tim-3 is proposed to mark more extensively exhausted cells, although the mechanisms underlying Tim-3 function are not clear. Trials of anti-PD-1 therapy have identified a large subset of non-responder patients, likely due to expression of alternative checkpoint molecules like Tim-3. We investigated the phenotypic and functional characteristics of T cells with differential expression of PD-1 (high/low) and Tim-3 (positive / negative), using TIL directly isolated from head and neck squamous cell carcinomas (HNSCC). Unexpectedly, we found that expression of Tim-3 alone does not necessarily mark TIL as dysfunctional / exhausted. In Tim-3-TIL, PD-1 levels correlate with T cell dysfunction, with a PD-1(low/intermed) phenotype identifying recently activated and still functional cells, whereas PD-1(hi)Tim-3(-) T cells are actually exhausted. Nonetheless, PD-1(intermed) cells are still potently suppressed by PD-L1. PD-1 expression was associated with reduced phosphorylation of ribosomal protein S6 (pS6), whereas Tim-3 expression was associated with increased pS6. Using a novel mouse model for inducible Tim-3 expression, we confirmed that expression of Tim-3 does not necessarily render T cells refractory to further activation. These results suggest the existence of PD-1 and Tim-3 crosstalk in regulating antitumor T cell responses, with important implications for anti-PD-1 immunotherapy.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"tumor infiltrating T lymphocytes\", \"Tim-3-TIL\", \"T cell\", \"TIL\", \"T cells\", \"cells\", \"PD-1(hi)Tim-3(-) T cells\", \"PD-1(intermed) cells\", \"Tumor-infiltrating Tim-3(+) T cells\"], \"Bacterium\": [], \"BiologicFunction\": [\"proliferate\", \"type-1 T cell responses\", \"phosphorylation\", \"mouse model\", \"antitumor\", \"expression\", \"crosstalk\", \"HNSCC\", \"mechanisms\", \"functional\", \"T cell responses\", \"T cell activation\", \"activation\", \"cross talk\", \"head and neck squamous cell carcinomas\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"Programmed Death 1\", \"pS6\", \"T cell Ig and mucin domain-3 protein\", \"ribosomal protein S6\", \"PD-1\", \"PD-L1\", \"Tim-3\", \"immune checkpoint receptors\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"exhausted\", \"negative\", \"positive\"], \"Food\": [], \"HealthCareActivity\": [\"anti-PD-1 therapy\", \"anti-PD-1 immunotherapy\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"intracellular\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Analyze the following text to identify specific entities. Focus on the categories provided: [\"Chemical\", \"Protein\"].\n\nDeliver your findings as a JSON structure: {\"Chemical\": [\"ExampleChemical\", ...], \"Protein\": [\"ExampleProtein\", ...]}. Each key represents an entity type, and the associated list contains the entities found. \n\nEnsure the response is strictly the JSON format without any extra text.\n\nSource:\n\nAcromegaly: molecular expression of somatostatin receptor subtypes and treatment outcome.\nAbout a third of acromegalic patients are resistant to the currently commercially available somatostatin analogs (SA) octreotide and lanreotide. Such resistance is related to an overall reduction of somatostatin receptor (SSTR) density or to a differentiated expression of SSTR subtypes. There are five known SSTR subtypes. SSTR2 and SSTR5 are usually expressed in GH-secreting pituitary tumors, and both octreotide and lanreotide bind preferentially to SSTR2 and, to a lesser extent, to SSTR5. SA inhibitory effects on GH secretion and tumor cell proliferation can occur together or be dissociated events, depending on the tumor expression of SSTR subtypes involved in each mechanism. The development of specific somatostatin subtypes analogs, mainly for SSTR5, of a SSTR2-SSTR5 bispecific compound, and of a \"universal\" analog with high affinity to SSTR1, 2, 3, and 5 showed preliminary, albeit promising results for the treatment of resistant somatotropic adenomas.", "role": "user" }, { "content": "{\"Chemical\": [\"octreotide\", \"somatostatin\", \"lanreotide\"], \"Protein\": [\"SSTR5\", \"SSTR1, 2, 3, and 5\", \"SSTR\", \"GH\", \"SSTR2\", \"somatostatin receptor\"]}", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nit must be reasons significant enough for me to argue for such a fundamental renovation ( table 1 ) .\nlet me first very briefly review the minimal functionality of the dna code . for simplicity ,\ni use a , u , g , and c for adenosine , uridine , guanine , and cytosine , respectively .\nthe code of a dna sequence for producing proteins has only four basic variables : length , order , gc and ag ( purine ) contents ( which are equivalent to what measured for au and uc contents ) , if we put aside the variability of nucleotide sequences over time for the moment .\nonly the last two variables are relevant to the codon table of the canonical genetic code ( hereby referred to as the table ) .\nunfortunately , the popular table is assembled merely for a concise and neat manifestation of the codon - to - aa context , and scrabbles clear messages that implicate physicochemical diversity of the amino acids and mutation sustainability of the dna - borne code .\nconsequently , there is no reason to turn away new synthesis when the table is not really in its legitimate form and does not give correct illustrations even when similar displays may have been proposed for different reasoning ( 5 ) .\nsecond , the new arrangement attempts to demonstrate the relationship between the informational and functional contents , concerning variability of gc and ag contents , thus more comprehensive and meaningful as we will see .\nthird , though a minor point , it is also simpler to be understood and memorized since it makes no effort to distinguish the two purines and the two pyrimidines for the third codon position ( cp3 ) .\ni hope everyone who reads this article is able to memorize the renovated table precisely for his or her life time .\nfirst , i considered only two basic variables , gc and ag contents , although there have been many other hypotheses proposed over the past half century , such as resistance to frameshift errors in translation [ 6 .\nit has been too much expectation for the codon - to - aa relationship analyses that have led to numerous hypotheses and debates ( 2 .\n, 9 . , 10 . ; the relevant publications are so vast in number that i feel guilty to quote only a few .\nhowever , this article is not written as a comprehensive overview of the field but merely as an illustration of the alternative codon table ) .\ni do not have a slight doubt that the relatedness in the metabolism of amino acids and codon assignment does exist , but it is the genetic code that unites them in a unique way and brings them together to compose functional contents ( encoding proteins ) .\nsecond , i can not agree more with early discoveries in nucleoside chemistry that a and t may be more ancient than g and c because c is too unstable to play a role in the origin of life 11 .\n, especially when c may not be essential for the constitution of early functional macromolecules ( 13 ) . perhaps a transient role in the rna world for c is more than enough for it to deserve a place in the basic structure of dna ; or in a positive notion , its pairing with g makes dna more stable than the alternatives .\nnevertheless , this particular display divides the table into four parts ; each has its informational and biological sanities : the au - rich , the gc - rich , and the two intermediate - gc quarters ( table 2a ) that are actually not the same regarding to their first and second codon positions ( cp1 and cp2 ) . for the sake of convenience , let me call them the gcp1 and gcp2 quarters , referring to the difference of their gc contents at the codon position ; codons in the former have g or c at cp1 whereas those in the latter have g or c at cp2 .\nthe content - sensitivity of the au - rich and gc - rich quarters is very obvious if we ignore the third codon position 14 . , 15 .. for instance , when the genomic gc content ( ggc content ) of an organism ( say a bacterium ) goes up , the former becomes underrepresented and the latter goes overrepresented because every a or t is subjected to be flipped over into g or c. nature then selects the individual who has made the right choice or eliminates the ones that made the wrong nucleotide flipping before the moment of truth under a given circumstance .\nthe gcp1 and gcp2 quarters remain , by and large , neutral when ggc content varies in a statistic sense overall .\nalthough it remains in the same column as other two aromatic amino acids , tyrosine and phenylalanine , it is difficult to know how much it compensates the pressure on uay and uuy codon pairs when ggc increases , since a or u at cp2 and y at cp3 have to change simultaneously to turn uay and uuy into ugg .\ncertainly , the conversion of uay to cay encoding another aromatic amino acid histidine in the gcp1 quarter is possible under pro - gc pressure .\nin addition , it is also predictable that gc2 ( the gc content of cp2 ) is greater than gc1 ( the gc content of cp1 ) since one of the codons in the gcp2 quarter is a stop codon , despite the fact that general codon usage biases may complicate the real statistics .\nthe au - rich quarter possesses the most diversified set of amino acids in terms of their physicochemical properties , containing sixteen codons that encode for seven amino acids as well as two stop and one start signals . in comparison ,\nthe gcp1 and gcp2 quarters both encode six amino acids , whereas the gc - rich quarter encodes only four amino acids .\nthe au - rich quarter is the only quarter that possesses codons for both start and stop signals , leaving us wondering if this quarter might represent the core diversity of the amino acids in building primordial proteins for the early life forms on earth .\nin addition to the legitimate concern about gc content variations , we can also see a division of the table into two halves ( table 2b ) according to the codon - aa variability between purine and pyrimidine ( nucleotide transversions between r and y ) at cp3 ; it also exhibits a clear separation of the amino acids with fourfold - degenerate codes from those with twofold - degenerate ones albeit the existence of two exceptions , aur and ugr .\nthis separation further divides the two gc - insensitive quarters ( the gcp1 and gcp2 quarters ) into two portions .\ni would like to call these two halves as pro - diversity and pro - robustness ( hereby referred to as the pd half and the pr half ) based on their functional indications .\nfirst , three amino acids ( serine , arginine , and leucine ) that have six codons are partitioned precisely into each of the two halves although they are distributed among all quarters in a seemingly disordered way .\nthis explicit distribution is obvious for the purpose of balancing the three amino acids , which are among the top abundance class by simple statistics such as the average or relative codon usage .\nan alternative way of explaining this distribution is to assume that these three amino acids were actually selected for the balance due to their roles in maintaining special physicochemical properties ( such as catalytic residues ) and unique functional domains ( such as leucine zippers for transcription factors and the serine - arginine - rich domain for rna - binding proteins ) of proteins .\nthe balancing route involves all four quarters : ( 1 ) between the au - rich and gcp1 quarters ( leucine ) ; ( 2 ) between the gc - rich and gcp2 quarters ( arginine ) ; and ( 3 ) within the gcp2 quarter ( serine ) but across the sub - divided pd and pr halves ( serine ) . as a result of this arrangement\n, the effect of gc - content increase is reduced through codon conversion rather than amino acid changes .\nthis distribution suggests that the three stop codons ( uaa , uag , and uga ) are readily converted to the corresponding amino acids when gc content goes high , a potential to extend the length of encoded proteins at the 3-end .\nthird , the two basic amino acids , arginine and lysine , appear robust against gc - content changes ; not only these two amino acids are partitioned sturdily into the pr and pd halves , but also the six arginine codons are divided into the gc - rich quarter and the gcp2 quarter between the two halves . as a contrast , the two acidic amino acids , glutamic acid and aspartic acid , appear taking a different approach they stay in the gcp1 quarter that is not sensitive to gc - content changes .\nit is also predictable that these two amino acids must be abundant in the proteins possessing them due to their neutrality against gc - content increase as well as their similarity in chemistry ( acidic or negatively charged ) and their positions in the table they are the most obvious pair resembling a fourfold - degenerate code when charges arose as the only concern in a polypeptide with complex structural constraints ( i intend to classify this quadruplet and isoleucine as pseudo - quadruplet ) .\nanother likely candidate for achieving high abundance is valine ; it has many neighboring amino acids ( positioned in the table with perceptible rationales ) that are either similar in hydrophobicity or equivalent in structural characteristics ( such as physical dimensions ) . finally , staring at the table ,\none can easily understand why proline and its codons are sitting at the corner of the gc - rich quarter , and it may only be seriously called upon when gc content goes extremely high .\nthe renovated table reveals that the codon arrangement is prioritized to reduce the impact of gc - content variations that fluctuate from 20% to 80% in eubacterial genomes where over 80% of the sequences are protein - coding . in other words , it seizes gc - content variations as the primary parameter .\nfirst , it divides the code into two portions , either sensitive ( the au - rich and gc - rich quarters ) or insensitive ( the gcp1 and gcp2 quarters ) to gc - content variations .\nsecond , it confines the high - gc codons as fourfold degenerate to further release the pressure from gc content increases at cp3 .\nthird , it keeps the physicochemically diversified amino acids in the au - rich quarter ( pro - diversity ) but leaves the amino acids of the gc - rich quarter to endure mutation pressure ( pro - robustness ) since they are less likely to be involved in catalytic activities as well as initiation and termination signals ( with the exception of the amino acids with sixfold - degenerate codons , especially arginine and serine ) .\nfourth , the function of the gc - insensitive quarters is to protect ( or generate in a sense for the origin of the genetic code ) the majority of the abundant amino acids in addition to isoleucine in the au - rich and alanine in the gc - rich quarters .\nthe ag content is the second to be concerned by the table since it fluctuates only 10% above or below the 50% mark among eubacterial genomes according to the chargaff s rule 16 .\n, 17 .. it further divides the gcp1 and gcp2 quarters into purine - variation sensitive and insensitive divisions or the entire table into two halves .\nthis division draws a clear line that separates the fourfold - degenerate code with the rest . in the low - diversity (\nreferring to physicochemical properties of amino acids ) or the high - robustness ( referring to mutation tolerance ) half , there are only five amino acids unique to it ; each has its subtleties in physicochemical characteristics unique to itself or shared with others .\nfor instance , threonine shares the property of hydroxyl group with serine yet has a slightly extended hydrocarbonic chain .\nanother example is valine ( gun ) ; it should be one of the most abundant amino acids since it is almost the most flexible amino acid of the quadruplet group , which is capable of replacing leucine ( uur ) , methionine ( aug ) , isoleucine ( auy ) , and even phenylalanine ( uuy ) when gc content increases and if the mutation - altered protein backbone is embraced by hydrophobicity only .\nthe third most striking feature in the table is the clustering of small amino acids aside from the relevance of gc and ag contents .\nthere are several simple measures for the size or volume of the amino acids , such as residue volume ( rv , ) ( 18 ) and accessible surface area ( asa , ) that was calculated for the residue x in the tripeptide g - x - g ( 19 ) .\nif we rank four smallest amino acids according to their size parameters , they are glycine ( rv 60.1 and asa 75 ) , alanine ( rv 88.6 and asa 115 ) , serine ( rv 89.0 and asa 115 ) , and cysteine ( rv 108.5 and asa 135 ) .\nthe next in line is disputable , either aspartic acid ( rv 111.1 and asa 150 ) or threonine ( rv 116.1 and asa 140 ) , depending on which measurement is preferred .\nclearly the most exchangeable pair in size is serine to alanine or vice versa when gc content varies .\none essential feature of the table or the organization of the genetic code is its balancing power .\nalthough the table divides gc / ag sensitivity vs. insensitivity , amino acid diversity vs. simplicity , and mutation sensitivity vs. tolerance , it seems not favoring one over another .\nit is predictable that the balance may be severely distorted at least under certain conditions , such as when gc content goes to extremities .\nthe purine content of eubacterial genomes can also go beyond the chargaff s rule ( 14 ) , which puts pressure on protein sequence alterations .\nhowever , as the table indicates in its ag - sensitive half , some of the members in this half are there to play relief roles , too .\naspartic acid and glutamic acid are in the same quadruplet , and when a negative charge is essential but not what the size or volume is , a purine to pyrimidine shift in cp3 becomes harmless . to a lesser extent , there are several similar cases in the pd half , including q / h ( size ) , m / i ( hydrophobicity ) , l / f ( hydrophobicity ) , r / s ( polar ) , w / c ( polar ) , and k / n ( polar ) .\nthis is not farfetched since there has not been a case found possessing a mixed - up feature of hydrophobic vs. hydrophilic or polar vs. non - polar amino acids in the same quadruplet . sometimes , the obvious seems easier to be overlooked than the obscure . to sum up ,\nin my thirty years or so scientific career , i have yet to find another topic that is so fundamental but so misunderstood as the genetic code ( even ignoring discussion on the origin of the genetic code ) .\nit is critical for biology students to appreciate this rearrangement , to be able to memorize the distribution of the codons ( amino acids ) in the table , and to understand the functional indications of the codon positions and their relatedness deeply in order to avoid wasting time to read meaningless publications that have been trying to mystify the genetic code albeit mostly deemed unintentional .", "role": "user" }, { "content": "the codon table for the canonical genetic code can be rearranged in such a way that the code is divided into four quarters and two halves according to the variability of their gc and purine contents , respectively . for prokaryotic genomes , when the genomic gc content increases , their amino acid contents tend to be restricted to the gc - rich quarter and the purine - content insensitive half , where all codons are fourfold degenerate and relatively mutation - tolerant . \n conversely , when the genomic gc content decreases , most of the codons retract to the au - rich quarter and the purine - content sensitive half ; most of the codons not only remain encoding physicochemically diversified amino acids but also vary when transversion ( between purine and pyrimidine ) happens . \n amino acids with sixfold - degenerate codons are distributed into all four quarters and across the two halves ; their fourfold - degenerate codons are all partitioned into the purine - insensitive half in favorite of robustness against mutations . \n the features manifested in the rearranged codon table explain most of the intrinsic relationship between protein coding sequences ( the informational content ) and amino acid compositions ( the functional content ) . \n the renovated codon table is useful in predicting abundant amino acids and positioning the amino acids with related or distinct physicochemical properties .", "role": "assistant" } ]

[ { "content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nWe present a new family of objective functions, which we term the Conditional Entropy Bottleneck (CEB).\nThese objectives are motivated by the Minimum Necessary Information (MNI) criterion.\nWe demonstrate the application of CEB to classification tasks.\nWe show that CEB gives: well-calibrated predictions; strong detection of challenging out-of-distribution examples and powerful whitebox adversarial examples; and substantial robustness to those adversaries.\nFinally, we report that CEB fails to learn from information-free datasets, providing a possible resolution to the problem of generalization observed in Zhang et al. (2016).\nThe field of Machine Learning has suffered from the following well-known problems in recent years 1 :• Vulnerability to adversarial examples.\nEssentially all machine-learned systems are currently believed by default to be highly vulnerable to adversarial examples.\nMany defenses have been proposed, but very few have demonstrated robustness against a powerful, general-purpose adversary.\nLacking a clear theoretical framework for adversarial attacks, most proposed defenses are ad-hoc and fail in the presence of a concerted attacker BID8 BID5 ).•\nPoor out-of-distribution detection. Classifiers\ndo a poor job of signaling that they have received data that is substantially different from the data they were trained on. Ideally, a\ntrained classifier would give less confident predictions for data that was far from the training distribution (as well as for adversarial examples). Barring that\n, there would be a clear, principled statistic that could be extracted from the model to tell whether the model should have made a low-confidence prediction. Many different\napproaches to providing such a statistic have been proposed BID18 BID28 BID19 BID32 BID30 BID13 , but most seem to do poorly on what humans intuitively view as obviously different data.• Miscalibrated\npredictions. Related to the\nissues above, classifiers tend to be very overconfident in their predictions BID18 . This may be a\nsymptom, rather than a cause, but miscalibration does not give practitioners confidence in their models.• Overfitting\nto the training data. BID48 demonstrated\nthat classifiers can memorize fixed random labelings of training data, which means that it is possible to learn a classifier with perfect inability to generalize. This critical observation\nmakes it clear that a fundamental test of generalization is that the model should fail to learn when given what we call information-free datasets.\nWe have presented the basic form of the Conditional Entropy Bottleneck (CEB), motivated by the Minimum Necessary Information (MNI) criterion for optimal representations.\nWe have shown through careful experimentation that simply by switching to CEB, you can expect substantial improvements in OoD detection, adversarial example detection and robustness, calibration, and generalization.\nAdditionally, we have shown that it is possible to get all of these advantages without using any additional form of regularization, and without any new hyperparameters.\nWe have argued empirically that objective hyperparameters can lead to hard-to-predict suboptimal behavior, such as memorizing random labels, or reducing robustness to adversarial examples.\nIn Appendix E and in future work, we will show how to generalize CEB beyond the simple case of two observed variables.It is our perspective that all of the issues explored here -miscalibration, failure at OoD tasks, vulnerability to adversarial examples, and dataset memorization -stem from the same underlying issue, which is retaining too much information about the training data in the learned representation.\nWe believe that the MNI criterion and CEB show a path forward for many tasks in machine learning, permitting fast, amortized inference while ameliorating major problems.\na b Figure 4 : Geometry of the optimal surfaces for both CEB (purple) and IB (green) for models that can only come within of the optimal surface (a: = 0.1I(X; Y); b: = 0.01I(X; Y)).\nThe tangent lines have the slope of the corresponding β -the tangent point on the ball corresponds to the point on the pareto-optimal frontier for the corresponding model.\nNote that β determines the \"exchange rate\" between bits of I(X; Z) and I(Y; Z), which is how we determine the coordinate of the center of the ball.\nFor IB to achieve the MNI point, 2 bits of I(Y; Z) are needed for every bit of I(X; Z).\nConsequently, even for an infitely powerful model (corresponding to = 0), the only value of β that hits the MNI point is β = 2.\nThus, knowing the function (β) for a given model and dataset completely determines the model's pareto-optimal frontier.Here we collect a number of results that are not critical to the core of the paper, but may be of interest to particular audiences.A Analysis of CEB and IB From Equation FORMULA5 and the definition of CEB in Equation (6), the following equivalence between CEB and IB is obvious: DISPLAYFORM0 where we are parameterizing IB with β on the I(Y; Z) term for convenience.\nThis equivalence generalizes as follows: DISPLAYFORM1 DISPLAYFORM2 In Figure 4 , we show the combined information planes for CEB and IB given the above parameterization.\nThe figures show the simple geometry that determines a point on the pareto-optimal frontier for both objectives.\nEvery such point is fully determined by the function (β) for a given model and dataset, where is the closest the model can approach the true optimal surface.\n(β) = 0 corresponds to the \"infinite\" model family that exactly traces out the boundaries of the feasible region.\nThe full feasible regions can be seen in Figure 2 .From\nthis geometry we can immediately conclude that if an IB model and a CEB model have the same value of > 0 at equivalent β, the CEB model will always yield a value of I(Y; Z) closer to I(X; Y). This\nis because the slope of the tangent lines for CEB are always lower, putting the tangent points higher on the ball. This\ngives part of a theoretical justification for the empirical observations above that V IB 0.5 (equivalent to IB 2 in the parameterization we are describing here) fails to capture as much of the necessary information as the CEB model. Even\nat the pareto-optimal frontier, V IB 0.5 cannot get I(Y; Z) as close to I(X; Y) as CEB can. Of course\n, we do not want to claim that this effect accounts for the fairly substantial difference in performance -that is likely to be due to a combination of other factors, including the fact that it is often easier to train continuous conditional distributions (like b(z|y)) than it is to train continuous marginal distributions (like m(z)).We also think\nthat this analysis of the geometry of IB and CEB supports our preference for targeting the MNI point and treating CEB as an objective without hyperparameters. First, there\nare only a maximum of 4 points of interest in both the IB and CEB information planes (all 4 are visibile in Figure 2 ): the origin, where there is no information in the representation; the MNI point; the point at (I(Y; Z) = I(X; Y), I(X; Z) = H(X)) (which is an MDL-compatible representation BID17 ); and the point at (I(Y; Z) = 0, I(X; Z) = H(X|Y)) (which would be the optimal decoder for an MNI representation). These are the\nonly points naturally identified by the dataset -selecting a point on one of the edges between those four points seems to need additional justification. Second, if you\ndo agree with the MNI criterion, for a given model it is impossible to get any closer to the MNI point than by setting CEB's β = 1, due to the convexity of the pareto-optimal frontier. Much more useful\nis making changes to the model, architecture, dataset, etc in order to make smaller. One possibility\nin that direction that IB and CEB models offer is inspecting training examples with high rate or residual information to check for label noise, leading to a natural human-in-the-loop model improvement algorithm. Another is using\nCEB's residual information as a measure of the quality of the trained model, as mentioned in Appendix C.", "role": "user" }, { "content": "The Conditional Entropy Bottleneck is an information-theoretic objective function for learning optimal representations.", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: Developmental Programming Mediated by Complementary Roles of Imprinted Grb10 in Mother and Pup\nContent:\nAbstract:\nDevelopmental programming links growth in early life with health status in adulthood. Although environmental factors such as maternal diet can influence the growth and adult health status of offspring, the genetic influences on this process are poorly understood. Using the mouse as a model, we identify the imprinted gene Grb10 as a mediator of nutrient supply and demand in the postnatal period. The combined actions of Grb10 expressed in the mother, controlling supply, and Grb10 expressed in the offspring, controlling demand, jointly regulate offspring growth. Furthermore, Grb10 determines the proportions of lean and fat tissue during development, thereby influencing energy homeostasis in the adult. Most strikingly, we show that the development of normal lean/fat proportions depends on the combined effects of Grb10 expressed in the mother, which has the greater effect on offspring adiposity, and Grb10 expressed in the offspring, which influences lean mass. These distinct functions of Grb10 in mother and pup act complementarily, which is consistent with a coadaptation model of imprinting evolution, a model predicted but for which there is limited experimental evidence. In addition, our findings identify Grb10 as a key genetic component of developmental programming, and highlight the need for a better understanding of mother-offspring interactions at the genetic level in predicting adult disease risk.\nIntroduction:\nGrowth during prenatal and postnatal development influences adult health status. In humans, low birth weight is associated with an increased risk of metabolic diseases, including obesity and diabetes[1]. In addition to overall size, disproportionate growth during development is also a risk factor for common adult diseases, including coronary heart disease and high blood pressure[2]. It is well-established that environmental stresses, such as poor maternal diet[3], can influence offspring growth, but the genetic control of developmental programming is not fully understood. Additionally, most studies have focused on prenatal development, but development in the postnatal period is also critical in influencing adult health status( reviewed in[4]). The genetic control of growth and nutrient acquisition in utero is mediated in part by imprinted genes, defined by their expression from a single parental allele[5]. In the placenta, paternally expressed genes generally promote growth and maternally expressed genes suppress growth. For many genes, this pattern is thought to reflect conflict between the parental genomes, played out within the offspring, over maternal resource allocation[6]. Females maximise lifetime reproductive success by evenly distributing their resources to offspring( since a mother is equally related to all of her offspring). However, when there is multiple paternity within or among litters, males are only related to some offspring produced by a female, and so it is in his genetic interest for his offspring to extract as much of his mate's resources as possible. The functions of a number of imprinted genes are consistent with the predictions of this “parental conflict hypothesis. ” For example, deletion of the paternally expressed Igf2 P0 transcript in the mouse placenta causes a failure in the supply of nutrients to the developing fetus, resulting in growth restriction[7]. Conversely, deficiency of the maternally expressed gene Grb10 causes placental overgrowth and increases placental efficiency[8]. Conflict between the parental genomes appears to be conserved in humans[9]. Postnatally, the majority of imprinted genes influence aspects of metabolism or behaviour. Grb10 is an intriguing example of an imprinted gene with diverse postnatal functions. We have previously generated and characterised Grb10 knockout mice to show that Grb10 is expressed from the maternally inherited allele in most peripheral tissues but expression in the central nervous system( CNS) is from the paternally inherited allele[10]. Consistent with these sites of parent-of-origin specific expression, we have demonstrated that maternally expressed Grb10 controls placental and fetal growth[8],[11], as well as adiposity and energy homeostasis in adulthood[12],[13], while paternally expressed Grb10 tempers social dominance[10]. This reciprocal imprint, with the parental alleles of Grb10 influencing distinct physiological and behavioural processes, raises questions about the evolution of imprinting at this and other loci. The presence of imprinted gene expression beyond weaning, i. e., after the cessation of parental provisioning, is not consistent with the original predictions of the parental conflict hypothesis[14]. However, theoretical analyses have demonstrated that there are conditions that can favour imprinted expression later in life, but the expectations for patterns of imprinting in adults are not as clear as those associated with imprinting during the phase of parental care[15],[16]. It is also possible that selection for imprinting at a locus occurs only during development and the imprint simply persists into adulthood. Postnatal nutrient provisioning by mothers occurs through the mammary gland, but unlike the placenta, the genome of the offspring's father is not represented in this tissue, precluding it as a site of direct parental conflict over allocation of resources to offspring. Despite this, we find that Grb10 is expressed and imprinted in the mammary epithelium during lactation. We show that Grb10 controls postnatal nutrient supply through expression of the maternally inherited allele in the lactating mammary gland, but at the same time, expression of the maternally inherited allele in the offspring controls nutrient demand. Proportionate growth as in wild-type( WT) animals requires a combination of Grb10 expression in the mother, which influences offspring adiposity, and Grb10 expression in the offspring, which influences lean mass. Together, these findings have two key implications. Firstly, our data suggest that Grb10 mediates both sides of the mother-offspring interaction. The coordinated pleiotropic effects of the gene suggest a possible role for Grb10 in mother-offspring coadaptation[17]. Coadaptation has been shown theoretically to potentially favour the evolution of imprinting[18], but there is limited empirical evidence to support this. Secondly, when coupled with our previous observations that Grb10-associated control of lean/fat proportions influences adult energy homeostasis, our data identify Grb10 as a key genetic mediator of developmental programming. Moreover, the need for expression of Grb10 in both mother and offspring to achieve WT lean/fat proportions suggests that a better understanding of mother-offspring interactions at the genetic level will be required for more accurate prediction of adult disease risk.\nDiscussion:\nIn mice, most imprinted genes are expressed in the placenta and many have been shown experimentally to influence placental development and function. The parental conflict hypothesis, which, at a gross level, predicts that paternally expressed genes promote growth while maternally expressed genes suppress growth, is consistent with the functions of several genes imprinted in the placenta, including Grb10[8],[11]. While the conflict hypothesis can potentially explain the occurrence of imprinting at many loci, the functions of a considerable number of imprinted genes cannot be easily reconciled with the predictions of the model, such as those involved in maternal care behaviours. Recent extensions to the model have considered cases in which asymmetries between genes inherited from mothers and fathers can arise from various patterns of interactions with kin, but they do not provide strong predictions about the nature of imprinting in adult tissues[15],[31]. There are also alternative models that do not consider conflict, such as the maternal-offspring coadaptation model, which describes how the combination of alleles expressed in mothers and their offspring jointly determines offspring fitness[18]. Whether each of these models could potentially account for the complex patterns of Grb10 expression and imprinting is unclear, but we present here some of the strongest empirical evidence that coadaptation could play a role, without necessarily ruling out alternative hypotheses. Earlier studies involving reciprocal crosses, and cross-fostering, between two distinct mouse strains established that parent-of-origin effects such as genomic imprinting could contribute to coadaptation between genotypes( e. g.,[26],[29]). These studies provide evidence that maternal provisioning is influenced by maternal and offspring genotypes[27] and that provisioning is optimal when mother and offspring are of the same genotype[29]. A study mapping quantitative trait loci on adult mouse body weight and organ weights indicated that a number of imprinted loci had small but detectable effects on these traits[28]. This genome-wide mapping is complementary to our approach, the manipulation of a single imprinted gene, which shows that Grb10 can contribute functionally to body weight and proportions through actions in both mother and offspring. Grb10 is an intriguing model with which to study imprinted gene function and evolution, because its two parental alleles are expressed in different tissues where they influence distinct physiological and behavioural processes[10]. Our earlier work characterising the same knockout mice used in this study established that maternally expressed Grb10 regulates fetal and placental growth[8],[11], consistent with the conflict hypothesis, as well as glucose homeostasis in adulthood[12]. In the present study, we demonstrate that Grb10 also controls postnatal growth through imprinted expression in mammary epithelium. The two archetypal mammalian tissues differ fundamentally in that the placenta contains both maternal and paternal genetic contributions, as in the offspring, but the mammary gland shares only maternal genes with offspring. Thus, while they are functionally analogous in supporting offspring growth, the placenta can be a site of direct conflict between the maternal and paternal genomes, whereas the mammary gland is not[14]. Consequently, our findings do not appear to fit with the simple predictions of the conflict hypothesis. The finding that WT body size and proportions require the combined and complementary actions of Grb10 in mother and pup( Figure 5), provides support for the coadaptation model of imprinting evolution, although further work would be needed to confirm that the effects of Grb10 lead to increased fitness. However, even if coadaptation explains the imprinting of Grb10 in pups, the coadaptation process would not favour imprinted expression in the mammary gland. Either a different hypothesis is needed to explain why the gene is imprinted in this tissue, or the pattern of expression in the mammary gland could simply reflect the selection that led to imprinting earlier in life. It should also be noted that our study compares WT Grb10 with a single knockout allele. Strong support for the coadaptation theory would come from an analysis of different allelic variants. Pups from combinations where mothers and offspring are expressing the same allelic variant would be expected to have higher fitness than those from combinations expressing different alleles. Conflict between the parental genomes, coadaptation of processes regulating postnatal nutrient acquisition, or indeed some other driving force, could have provided the initial selective pressure for the evolution of imprinting. However, a mechanism for imprinted gene regulation, once evolved, could facilitate development of novel gene functions, and thus the two models for the evolution of imprinting at the Grb10 locus, conflict and coadaptation, need not be mutually exclusive[32]. Indeed, expression of both the maternally and paternally inherited alleles of Grb10 in different tissues, influencing different phenotypes, strongly supports this notion, since the same selective forces presumably could not have led to both patterns of expression. Evidence for the later evolutionary acquisition of novel functions or imprinted expression of a gene in adult tissues could be viewed as consistent with this idea. In this context it is interesting that in at least one marsupial species, the tammar wallaby, Grb10 is expressed in a range of fetal and adult tissues, including lactating mammary gland, but its expression appears not to be imprinted[33]. Future work on the expression and functions of Grb10 in non-mammalian species will help to unravel the likely evolutionary course of this pleiotropic gene. The mechanism through which Grb10 regulates postnatal nutrient supply is not clear, but its pregnancy-dependent expression in the mammary epithelium is consistent with Grb10 controlling supply through this tissue. Our data suggest that Grb10 might mediate the response of the epithelium to pituitary prolactin, but further work will be needed to define its mode of action. We could not detect any phenotype associated with Grb10KO in analyses of mammary glands at the cellular level or in analyses of milk fat and protein content. One intriguing possibility is that Grb10 in mammary epithelium could regulate the release of signalling molecules that influence growth or metabolism of suckling offspring. Evidence exists for such lactocrine signalling playing a role in offspring development[34]. Environmental influences on the programming of adult health status during development have been widely investigated. In humans, maternal and child undernutrition are risk factors for high glucose concentration and blood pressure in adulthood[3]. Chemical insults can also adversely affect development with implications for adult health. Bisphenol A( BPA), which mimics oestrogen, has garnered much attention recently because of its widespread use in the manufacture of baby bottles, coatings for food cans and other commonly used items. Effects of exposure during development to environmentally relevant levels of BPA, using rodent models, include increased body weight, advanced puberty, and altered reproductive function, as well as a possible predisposition to mammary and prostate cancers[35]. This is effected, at least in part, through alterations to the fetal epigenome, including reduced levels of DNA methylation, which is associated with changes in gene transcription[36],[37]. The genetic control of developmental programming of adult health status is relatively poorly understood. We have previously shown that Grb10 determines the proportions of lean and fat tissue during development, and that altering the lean/fat ratio by ablating Grb10 affects glucose homeostasis in adulthood[12]. In the present study, we find that this programming of adult metabolic state during postnatal development is not the result of Grb10 acting in the pup alone, but is achieved through the combined actions of Grb10 in mother and offspring. Interestingly, two recent mouse studies of nutrient restriction during gestation have demonstrated up-regulation of Grb10 expression in offspring, consistent with our findings that Grb10 plays a key role in responding to nutrient supply[38],[39]. Our work highlights the need for a much better understanding of genetic interactions between mother and offspring in predicting adult health status.", "role": "user" }, { "content": "Experiences during early life can impact on health status in adulthood; low birth weight , for example , is linked to an increased risk of diabetes and obesity in later life . Such developmental programming can be influenced by environmental factors such as diet , but the importance of genetics in this process is not well understood . Using the mouse as a model , we investigate the gene Grb10 , which is imprinted , meaning that it is expressed from only one of its two copies . We show that Grb10 is a key mediator of developmental programming , controlling supply and demand of nutrients in the postnatal period and influencing growth and body composition . Specifically , we find that Grb10 determines the proportions of lean and fat tissue during development , and that this is dependent on the combined actions of Grb10 in the mother and offspring . Our findings have two main implications . First , they suggest that the functions of Grb10 in mother and offspring are coadapted , providing support for a coadaptation model for the evolution of imprinted genes . Second , they highlight the need for a better grasp of how maternal and offspring genetics interact during development if we are to understand more fully the causes of complex adult disorders such as obesity .", "role": "assistant" } ]

[ { "content": "Transform the provided sections of a biomedical research paper into a digestible summary for a general audience. Focus on simplifying complex ideas while retaining key scientific insights.\n\nResearch Title: The LIM protein complex establishes a retinal circuitry of visual adaptation by regulating Pax6 α-enhancer activity\nContent Overview:\nAbstract:\nThe visual responses of vertebrates are sensitive to the overall composition of retinal interneurons including amacrine cells, which tune the activity of the retinal circuitry. The expression of Paired-homeobox 6( PAX6) is regulated by multiple cis-DNA elements including the intronic α-enhancer, which is active in GABAergic amacrine cell subsets. Here, we report that the transforming growth factor ß1-induced transcript 1 protein( Tgfb1i1) interacts with the LIM domain transcription factors Lhx3 and Isl1 to inhibit the α-enhancer in the post-natal mouse retina. Tgfb1i1-/- mice show elevated α-enhancer activity leading to overproduction of Pax6ΔPD isoform that supports the GABAergic amacrine cell fate maintenance. Consequently, the Tgfb1i1-/- mouse retinas show a sustained light response, which becomes more transient in mice with the auto-stimulation-defective Pax6ΔPBS/ΔPBS mutation. Together, we show the antagonistic regulation of the α-enhancer activity by Pax6 and the LIM protein complex is necessary for the establishment of an inner retinal circuitry, which controls visual adaptation.\nIntroduction:\nThe retina is a primary sensory tissue that receives light stimulus and converts it into electrical signals, which are then sent to the brain for further processing. After light detection by rod and cone photoreceptors, the first step in visual processing occurs in bipolar cells that are either stimulated or inhibited by light-absorbed photoreceptors( Masland, 2012). The activities of bipolar cells are then tuned by horizontal cells while they receive visual input from the photoreceptors and by amacrine cells while they deliver the signals to retinal ganglion cells( RGCs)( Hoon et al., 2014; Masland, 2012). The amacrine cells do not simply convey the signals from bipolar cells, but they also invert the signals by releasing inhibitory neurotransmitters such as γ-aminobutyric acid( GABA) and glycine. Therefore, even subtle changes in the composition and connectivity of amacrine cell subsets might alter the output of the retina, modifying the visual information sent to the brain. The neurons of the vertebrate retina develop in an ordered fashion from multipotent retinal progenitor cells( RPCs)( Cepko, 2014). A number of transcription factors with precise temporal and spatial expression patterns control the composition of retinal neurons via the hierarchical and reciprocal regulation of other transcription factor expression( Zagozewski et al., 2014). Thus, the alterations of transcription factors that specify retinal neuron subtypes should modify visual output of mature retina. Those transcription factors include Pax6 in amacrine cells( Marquardt et al., 2001), Vsx2 in bipolar cells( Liu et al., 1994), Otx2 in bipolar cells and photoreceptors( Koike et al., 2007; Nishida et al., 2003), and Lhx2 and Sox2 in Müller glia and certain amacrine subtypes( de Melo et al., 2012; Gordon et al., 2013; Lin et al., 2009). These transcription factors are not only expressed in the earlier optic structures to play critical roles in the eye and brain development( Danno et al., 2008; Glaser et al., 1994; Yun et al., 2009), but also in the mature retinal neurons to support the survival and functions of the neurons( de Melo et al., 2012; Kim et al., 2015). However, the mechanisms underlying the recurrent expression of transcription factors in the retinal lineage are still largely unknown. Pax6 is one of the earliest transcription factors expressed in the eye field, and as such, it is considered as a master regulator of eye development( Ashery-Padan and Gruss, 2001; Hanson and Van Heyningen, 1995). Pax6 contains two DNA-binding domains—a paired domain( PD) and a homeodomain( HD)—linked via a glycine-rich domain, and activates target gene transcription through its C-terminal proline-, serine-, and threonine-rich( PST) domain( Epstein et al., 1994; Xu et al., 1999a). Multiple cis-regulatory elements govern Pax6 expression in various mouse tissues( Kammandel et al., 1999; Xu et al., 1999b). The ‘α-enhancer’, located within intron 4 of the Pax6 gene, is active in the retina from embryo to adult( Kammandel et al., 1999; Marquardt et al., 2001; Plaza et al., 1995). This retina-specific enhancer activity sustains in RPCs in the peripheral retina of the embryos and regulates neuronal differentiation in a context-dependent manner( Marquardt et al., 2001). In the mature eye, the α-enhancer is active in cells of the ciliary body and amacrine cells of the retina( Marquardt et al., 2001). The α-enhancer contains multiple binding sites for transcription factors, including the auto-stimulatory Pax6( Kammandel et al., 1999), the stimulatory Msx1( Kammandel et al., 1999) and Pou4f2( Plaza et al., 1999), and the inhibitory Pax2( Kammandel et al., 1999; Schwarz et al., 2000) and Vax1( Mui et al., 2005). Although the inhibition of α-enhancer activity by Vax1 has been shown to be crucial for the development of the retina-optic stalk border( Mui et al., 2005), the roles the other transcription factors that bind the α-enhancer in the retina remain unclear. In this study, we show that regulation of Pax6 expression through the α-enhancer fine tunes amacrine cell subtype composition, and consequently, the visual output of the retina.\nDiscussion:\nTranscription factors frequently act in combination, allowing relatively few to generate the tremendous cellular diversity of the nervous system( Jessell, 2000). Especially, the ‘LIM code’ mixes and matches LIM domain-containing transcription factors to direct tissue- and cell-specific gene expression( Gill, 2003; Shirasaki and Pfaff, 2002). Lhx3, for example, specifies motor neuron cell fate in the spinal cord by forming a hetero-hexameric complex with Isl1 and nuclear LIM interactor( NLI) for the binding to the promoter of the Mnx1/Hb9 gene, whereas it specifies V2 interneuron cell fate by forming a hetero-tetrameric complex with NLI at the promoter of the Vsx2/Chx10 gene( Thaler et al., 2002). Given that the various LIM homeodomain transcription factors, including Lhx2, Lhx3, Lhx4, and Lhx9, share a consensus target sequence( Gehring et al., 1994), we speculate Isl1 partners with different LIM homeodomain transcription factors in a cell-context-dependent manner. In contrast to its relationship with Lhx3, Isl1 cooperates with Lhx2 to activate the α-enhancer in cultured cell lines( data not shown). However, this is unlikely to occur in vivo, because Lhx2 and Isl1 are expressed mutually exclusively in RPCs( Lhx2) and post-mitotic RGCs( Isl1) of the embryonic mouse retina, in GABAergic( Lhx2) and cholinergic amacrine cells( Isl1) in the mature retina, as well as in Müller glia( Lhx2) and ON bipolar cells( Isl1)( Balasubramanian et al., 2014; Elshatory et al., 2007; Gordon et al., 2013; Pan et al., 2008). Moreover, Lhx2flox/flox;P6α-Cre retinas, which lack Lhx2 expression in the Cre-active lineages( Gordon et al., 2013), show no change in the number of Pax6 α-enhancer-active cells( data not shown). This suggests Lhx2 may be dispensable for the activation of the Pax6 α-enhancer in the mouse retina. We propose that a Tgfb1i1 dimer links Isl1 and Lhx3 to form a hetero-tetrameric complex that represses the Pax6 α-enhancer( Figures 2 and 3). The effects of Tgfb1i1 on the α-enhancer could be achieved by blocking Pax6’s access the PBS sequence( Figure 3G, H). Alternatively, Tgfb1i1 may also recruit transcriptional co-repressors, such as NCoR( nuclear receptor co-repressor)( Heitzer and DeFranco, 2006), to the Pax6 α-enhancer. These negative effects of Tgfb1i1 on the Pax6 α-enhancer can be antagonized by Lmo4, which is persistently co-expressed with Pax6 in the retina and interferes with the interactions between Tgfb1i1 and Lhx3 and/or Isl1( Duquette et al., 2010)( Figures 2D and 3D). Retinas lacking Lmo4 have fewer GABAergic amacrine cells than controls( Duquette et al., 2010), which suggests Lmo4 may positively affect Pax6 α-enhancer-dependent GABAergic amacrine cell fate determination by inhibiting the formation of the LIM complex. However, the antagonistic regulation of the LIM complex by Tgfb1i1 and Lmo4 could not be applied to OFF bipolar cell fate determination, since OFF bipolar cell numbers are decreased commonly in Tgfb1i1−/− and Lmo4-cko mouse retinas. Our results suggest that Tgfb1i1 and Lmo4 might involve in the development of different OFF bipolar cell subsets. The numbers of Bhlhb5-positive OFF bipolar cell subsets were not altered significantly in Tgfb1i1−/− mouse retinas( Figure 4E, F), in contrast to a significant decrease in Lmo4-cko mouse retinas. In addition to its canonical form, two alternative forms of Pax6, Pax6( 5a) and Pax6ΔPD, are produced by alternative splicing and internal transcription initiation, respectively( Epstein et al., 1994; Mishra et al., 2002). Pax6ΔPD does not affect Pax6 target gene expression via the conserved PBS( data not shown). Instead, as previously reported( Mikkola et al., 2001), Pax6ΔPD may potentiate the expression of Pax6 target genes by interacting with full-length Pax6. This facilitation of Pax6-induced gene transcription by Pax6ΔPD may also occur with the Pax6 α-enhancer, resulting in a feed-forward activation of the α-enhancer. Alternatively, it may bind another promoter element containing the Pax6 homeodomain target DNA sequence( TAATT( /C) NA( /C) ATTA). Therefore, future studies will be needed to identify the targets of Pax6ΔPD in RPCs and post-mitotic retinal neurons. This will provide a full understanding of the distinctive roles Pax6 and Pax6ΔPD play in the retina. Although the mechanisms of light adaptation and re-sensitization in the photoreceptors are fairly well-understood, how the inner retina contributes to these mechanisms is less clear. Acting downstream of rod bipolar cells that deliver visual signals from rod photoreceptors, A17 GABAergic amacrine cells provide a direct feedback inhibition to the rod bipolar cells( Chávez et al., 2010). In parallel, an unidentified subset of GABAergic amacrine cells is also proposed to inhibit rod bipolar cells at the downstream of ON-cone bipolar cells, which can be activated by AII amacrine cells in the rod pathway as well as by daylight( Demb and Singer, 2012; Eggers et al., 2013). GABAergic inhibition to the rod bipolar cells could be reduced in Tgfb1i1−/− mouse retinas, leading to sustained ON responses( Figure 7A). Conversely, the ON pathway in Pax6ΔPBS/ΔPBS mouse retinas is activated more transiently and is also more readily re-activated by subsequent visual stimuli( Figure 7D). Therefore, the P6α amacrine cells might attenuate those GABAergic inhibitions to rod bipolar cells and prevent premature inactivation of rod pathway. However, future studies should identify molecular and electrophysiological identities of the P6α amacrine cells and their pre- and post-synaptic partners to fully understand this visual adaptive circuits in the inner retina.", "role": "user" }, { "content": "The retina is a light-sensitive layer of tissue that lines the inside of the eye . This tissue is highly organized and comprises a variety of different nerve cells , including amacrine cells . Together , these cells process incoming light and then trigger electrical signals that travel to the brain , where they are translated into an image . Changes in the nerve cell composition of the retina , or in how the cells connect to each other , can alter the visual information that travels to the brain . The nerve cells of the retina are formed before a young animal opens its eyes for the first time . Proteins called transcription factors – which regulate the expression of genes – tightly control how the retina develops . For example , a transcription factor called Pax6 drives the development of amacrine cells . Several other transcription factors control the production of Pax6 by binding to a section of DNA known as the “α-enhancer” . However , it is not clear how regulating Pax6 production influences the development of specific sets of amacrine cells . Kim et al . reveal that a protein known as Tgfb1i1 interacts with two transcription factors to form a “complex” that binds to the α-enhancer and blocks the production of a particular form of Pax6 . In experiments performed in mice , the loss of Tgfb1i1 led to increased production of this form of Pax6 , which resulted in the retina containing more of a certain type of amacrine cell that produce a molecule called GABA . Mice lacking Tgfb1i1 show a stronger response to light and are therefore comparable to people who are too sensitive to light . On the other hand , mice with a missing a section of the α-enhancer DNA have fewer amacrine cells releasing GABA and become less sensitive to light and are comparable to people who have difficulty detecting weaker light signals . The findings of Kim et al . suggest that an individual’s sensitivity to light is related , at least in part , to the mixture of amacrine cells found in their retina , which is determined by certain transcription factors that target the α-enhancer .", "role": "assistant" } ]

[ { "content": "Review the provided collection of medical RCT summaries. Your objective is to distill the essential insights into a brief conclusion. Focus solely on the synthesis of findings without additional commentary. The RCT summaries are as follows:\n\n\n\nReport Title 1:\nTreatment of detrusor hyperreflexia in multiple sclerosis: a double-blind, crossover clinical trial comparing methantheline bromide (Banthine), flavoxate chloride (Urispas) and meladrazine tartrate (Lisidonil).\nReport Abstract 1:\n34 patients suffering from detrusor hyperreflexia due to multiple sclerosis entered the trial and 32 patients accomplished. The patients received each drug for a period of 14 days. The patients made records of relevant symptoms, urgency and urge incontinence and compared the treatment periods according to these symptoms. Registration of the number of micturitions was also made. Furthermore, the patients underwent cystometric studies. The following parameters were recorded and compared: residual urine, volume at the first bladder contraction, effective volume and amplitude of the first bladder contraction. The study showed that the patients preferred methantheline bromide. The entire cystometric pattern changed statistically significant with methantheline bromide, but only with concordance to the patients preferences in 60%. Decrease in number of micturitions and volume at the first bladder contraction were the only parameters showing accordance with the preferences. The drugs caused many various side effects. 12 treatment periods were discontinued due to side effects of meladrazine tartrate. The cystometric recordings seem to be of little use in evaluation of a drugs therapeutic effect, and it is difficult to find parameters which reflect the patients preference of the drugs.\n\n\nReport Title 2:\nIntravesical atropine compared to oral oxybutynin for neurogenic detrusor overactivity: a double-blind, randomized crossover trial.\nReport Abstract 2:\nWe tested the efficacy and side effect profiles of intravesical atropine compared to oxybutynin immediate release when used by individuals with multiple sclerosis.\n We performed a study to determine the most effective dose of atropine. Eight participants used increasing doses of intravesical atropine during a 12-day period. Bladder diary data showed that the instillation of 6 mg atropine 4 times daily was most effective for increasing bladder capacity (voided/catheter volumes). We then did a randomized, double-blind crossover trial. Participants received 14 days of treatment with oral oxybutynin or with intravesical atropine, followed by 14 days of alternative treatment. Participants recorded a bladder diary and rated side effects and quality of life. The primary outcome variable was bladder capacity.\n A total of 57 participants with multiple sclerosis completed the study. Average change in bladder capacity was higher in the atropine arm. The mean +/- SD oxybutynin change was 55.5 +/- 67.2 ml, the mean atropine change was 79.6 +/- 89.6 ml and the mean difference between arms was 24.1 ml (95% CI -0.4, 49.7; p = 0.053). Changes in incontinence events and voiding frequency were not statistically different between the arms. Changes in total side effect and dry mouth scores were significantly better in the atropine treatment arm.\n Intravesical atropine was as effective as oxybutynin immediate release for increasing bladder capacity and it was probably better with less antimuscarinic side effects. We recommend that intravesical atropine should be made available to patients with neurogenic detrusor overactivity and voiding problems requiring intermittent catheterization as an alternative to oral therapy, which often has troublesome side effects.\n\n\nReport Title 3:\nOxybutynin versus propantheline in patients with multiple sclerosis and detrusor hyperreflexia.\nReport Abstract 3:\nHyperreflexia is the most common urological finding in patients with multiple sclerosis. A prospective randomized study was done to compare the effectiveness of 2 commonly used drugs, oxybutynin and propantheline. Of the 34 patients entered into the trial 19 were treated with oxybutynin and 15 with propantheline. The urological symptoms (frequency, nocturia, hesitancy, urgency and urge incontinence) were graded according to severity from 0 to 3. Patients with urinary infection were excluded. Urodynamic examination, consisting of cystometrography and electromyography, was performed in all patients before treatment. Both groups of patients had comparable neurological, urological and urodynamic status before treatment. In 4 patients (21 per cent) treated with oxybutynin and in 4 (27 per cent) treated with propantheline side effects were so severe that the treatment had to be discontinued. Symptomatic response to oxybutynin was good in 10 patients (67 per cent), fair in 2 (13 per cent) and poor in 3 (20 per cent). Propantheline produced good symptomatic results in 4 patients (36 per cent), fair in 1 (9 per cent) and poor in 6 (55 per cent). The mean increase in maximum cystometric capacity on cystometrography was significantly larger in the oxybutynin group than in the propantheline group (144 +/- 115 versus 35 +/- 101). Our results indicate that oxybutynin is more effective than propantheline in the treatment of detrusor hyperreflexia in patients with multiple sclerosis.", "role": "user" }, { "content": "From the available evidence we cannot advocate the use of anticholinergics in MS.", "role": "assistant" } ]

[ { "content": "Analyze the given research paper excerpts and address the question provided. Extract the necessary information directly from the text. Your answer should be formatted as a JSON object with the following structure:\n\n\"answer\": A list of text segments from the paper that directly respond to the question.\n\"evidence\": A list of text segments from the paper where the answer can be found.\n\nIf the question cannot be answered with the given text, return \"null\".\n\nDocument: Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks\n\nLearners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architecture. We investigate which architectural factors affect the generalization behavior of neural sequence-to-sequence models trained on two syntactic tasks, English question formation and English tense reinflection. For both tasks, the training set is consistent with a generalization based on hierarchical structure and a generalization based on linear order. All architectural factors that we investigated qualitatively affected how models generalized, including factors with no clear connection to hierarchical structure. For example, LSTMs and GRUs displayed qualitatively different inductive biases. However, the only factor that consistently contributed a hierarchical bias across tasks was the use of a tree-structured model rather than a model with sequential recurrence, suggesting that human-like syntactic generalization requires architectural syntactic structure.\n\nIntroduction\nAny finite training set is consistent with multiple generalizations. Therefore, the way that a learner generalizes to unseen examples depends not only on the training data but also on properties of the learner. Suppose a learner is told that a blue triangle is an example of a blick. A learner preferring shape-based generalizations would conclude that blick means “triangle,” while a learner preferring color-based generalizations would conclude that blick means “blue object” BIBREF0. Factors that guide a learner to choose one generalization over another are called inductive biases.\nWhat properties of a learner cause it to have a particular inductive bias? We investigate this question with respect to sequence-to-sequence neural networks BIBREF1, BIBREF2. As a test case for studying differences in how models generalize, we use the syntactic task of English question formation, such as transforming SECREF1 into SECREF1:\n. Ṫhe zebra ForestGreendoes chuckle. ForestGreenDoes the zebra chuckle?\nFollowing BIBREF3's (BIBREF3) empirical claims about children's linguistic input, we constrain our training set to be consistent with two possible rules illustrated in Figure FIGREF1: move-main (a rule based on hierarchical syntactic structure) and move-first (a rule based on linear order). We then evaluate each trained model on examples where the rules make different predictions, such as SECREF1: given SECREF1, move-main would generate SECREF1 while move-first would generate SECREF1:\n. Ẏour zebras that bluedon't dance ForestGreendo chuckle. ForestGreenDo your zebras that bluedon't dance chuckle? blueDon't your zebras that dance ForestGreendo chuckle?\nSince no such examples appear in the training set, a model's behavior on them reveals which rule the model is biased toward. This task allows us to study a particular bias, namely a bias for hierarchical generalization, which is important for models of language because it has been argued to underlie human language acquisition BIBREF4.\nTo test which models have a hierarchical bias, we use the question formation task and a second task: tense reinflection. For both tasks, our training set is ambiguous between a hierarchical generalization and a linear generalization. If a model chooses the hierarchical generalization for only one task, this preference is likely due to task-specific factors rather than a general hierarchical bias. On the other hand, a consistent preference for hierarchical generalizations across tasks would provide converging evidence that a model has a hierarchical bias.\nWe find that all the factors we tested can qualitatively affect how a model generalizes on the question formation task. These factors are the type of recurrent unit, the type of attention, and the choice of sequential vs. tree-based model structure. Even though all these factors affected the model's decision between move-main and move-first, only the use of a tree-based model can be said to impart a hierarchical bias, since this was the only model type that chose a hierarchical generalization across both of our tasks. Specific findings that support these general conclusions include:\nGeneralization behavior is profoundly affected by the type of recurrent unit and the type of attention, and also by the interactions between these factors.\nLSTMs and GRUs have qualitatively different inductive biases. The difference appears at least partly due to the fact that the values in GRU hidden states are bounded within a particular interval BIBREF5.\nOnly a model built around the correct tree structure displayed a robust hierarchical bias across tasks. Sequentially-structured models failed to generalize hierarchically even when the input contained explicit marking of each sentence's hierarchical structure.\nOverall, we conclude that many factors can qualitatively affect a model's inductive biases, but human-like syntactic generalization may require specific types of high-level structure, at least when learning from text alone.\n\nThe question formation task ::: Framing of the task\nFollowing frank2007 and mccoy2018revisiting, we train models to take a declarative sentence as input and to either output the same sentence unchanged, or transform that sentence into a question. The sentences were generated from a context-free grammar containing only the sentence types shown in Figure FIGREF5 and using a 75-word vocabulary; the full grammar is at the project website.fn:website The different types of sentences vary in the linear position of the main auxiliary, such that a model cannot identify the main auxiliary with a simple positional heuristic. The task to be performed is indicated by the final input token, as in SECREF7 and SECREF7:\n. Input:your zebra does read . declXX Output: your zebra does read . declXX\n. Input:your zebra does read . questX Output:does your zebra read ? questX\nDuring training, all question formation examples are consistent with both move-first and move-main, such that there is no direct evidence favoring one rule over the other (see Figure FIGREF5).\nTo assess how models generalize, we evaluate them on a generalization set consisting of examples where move-main and move-first make different predictions due to the presence of a relative clause on the subject (see sentence SECREF1).\n\nRecurrent unit and attention ::: Recurrent unit\nThe recurrent unit is the component that updates the hidden state after each word for the encoder and decoder. We used three types of recurrent units: simple recurrent networks (SRNs; BIBREF17), gated recurrent units (GRUs; BIBREF18), and long short-term memory (LSTM) units BIBREF19. In SRNs and GRUs, the hidden state is represented by a single vector, while LSTMs use two vectors (the hidden state and the cell state). In addition, GRUs and LSTMs both use gates, which control what information is retained across time steps, while SRNs do not; GRUs and LSTMs differ from each other in the number and types of gates they use.\n\nRecurrent unit and attention ::: Differences between LSTMs and GRUs\nOne striking result in Figure FIGREF13 is that LSTMs and GRUs display qualitative differences, even though the two architectures are often viewed as interchangeable and achieve similar performance in applied tasks BIBREF24. One difference between LSTMs and GRUs is that a squashing function is applied to the hidden state of a GRU to keep its values within the range $(-1,1)$, while the cell state of an LSTM is not bounded. weiss2018 demonstrate that such squashing leads to a qualitative difference in how well these models generalize counting behavior. Such squashing may also explain the qualitative differences that we observe: counting the input elements is equivalent to keeping track of their linear positions, so we might expect that a tendency to count would make the linear generalization more accessible.\nTo test whether squashing increases a model's preference for move-main, we created a modified LSTM that included squashing in the calculation of its cell state, and a modified GRU that did not have the squashing usually present in GRUs. See Appendix SECREF11 for more details. Using the same training setup as before, we trained models with these modified recurrent units and with location-based attention. LSTMs and GRUs with squashing chose move-main more often than the corresponding models without squashing (Figure FIGREF20), suggesting that such squashing is one factor that causes GRUs to behave differently than LSTMs.\n\nTense reinflection\nWe have shown that several models reliably preferred move-main over move-first. However, this behavior alone does not necessarily mean that these models have a hierarchical bias, because a preference for move-main might arise not from a hierarchical bias but rather from some task-specific factors such as the prevalence of certain n-grams BIBREF28, BIBREF29. A true hierarchical bias would lead a model to adopt hierarchical generalizations across training tasks; by contrast, we hypothesize that other factors (such as a bias for focusing on n-gram statistics) will be more sensitive to details of the task and will thus be unlikely to consistently produce hierarchical preferences. To test the robustness of the hierarchical preferences of our models, then, we introduce a second task, tense reinflection.\n\nTree structure vs. tree information\nOur sequential and tree-based models differ not only in structure but also in the information they have been provided: the tree-based models have been given correct parse trees for their input and output sentences, while the sequential models have not been given parse information. Therefore, it is unclear whether the hierarchical generalization displayed by the tree-based models arose from the tree-based model structure, from the parse information provided to the models, or both.\nTo disentangle these factors, we ran two further experiments. First, we retrained the Tree/Tree GRU but using uniformly right-branching trees (as in (11b)) instead of correct parses (as in (11a)). Thus, these models make use of tree structure but not the kind of parse structure that captures linguistic information. Second, we retrained the sequential GRU without attention but modified the input and output by adding brackets that indicate each sentence's parse; for example, SECREF7 would be changed to SECREF7. Thus, these models are provided with parse information in the input but such structure does not guide the neural network computation as it does with tree RNNs.\n. a. [ [ [ my yak ] [ does giggle ] ] $.$ ] b. [ my [ yak [ does [ giggle $.$ ] ] ] ]\n. ṁy yak does giggle . quest\n$\\rightarrow $ does my yak giggle ? [ [ [ my yak ] [ does giggle ] . ] quest ] $\\rightarrow $ [ [ does [ [ my yak ] giggle ] ] ? ]\nWe ran 100 instances of each experiment using different random seeds. For the experiment with bracketed input, the brackets significantly increased the lengths of the sentences, making the learning task harder; we therefore found it necessary to use a patience of 6 instead of the patience of 3 we used elsewhere, but all other hyperparameters remained as described in Appendix SECREF10.\nFor both tasks, neither the sequential GRU that was given brackets in its input nor the Tree/Tree model that was given right-branching trees displayed a hierarchical bias (Figure FIGREF36). The lack of hierarchical bias in the sequential GRU with bracketed input indicates that simply providing parse information in the input and target output is insufficient to induce a model to favor hierarchical generalization; it appears that such parse information must be integrated into the model's structure to be effective. On the other hand, the lack of a hierarchical bias in the Tree/Tree model using right-branching trees shows that simply having tree structure is also insufficient; it is necessary to have the correct tree structure.\n\nDiscussion ::: Relation to Rethinking Innateness\nOur experiments were motivated in part by the book Rethinking Innateness BIBREF33 which argued that humans' inductive biases must arise from constraints on the wiring patterns of the brain. Our results support two conclusions from this book. First, those authors argued that “Dramatic effects can be produced by small changes” (p. 359). This claim is supported by our observation that low-level factors, such as the size of the hidden state, qualitatively affect how models generalize (Section SECREF26). Second, they argued that “[w]hat appear to be single events or behaviors may have a multiplicity of underlying causes” (p. 359); in our case, we found that a model's generalization behavior results from some combination of factors that interact in hard-to-interpret ways; e.g., changing the type of attention had different effects in SRNs than in GRUs.\nThe dramatic effects of these low-level factors offer some support for the claim that humans' inductive biases can arise from fine-grained architectural constraints in the brain. However, this support is only partial. Our only model that robustly displayed the kind of preference for hierarchical generalization that is necessary for language learning did not derive such a preference from low-level architectural properties but rather from the explicit encoding of linguistic structure.\n\nEquations for squashing experiments\nThe equations governing a standard LSTM are:\nTo create a new LSTM whose cell state exhibits squashing, like the hidden state of the GRU, we modified the LSTM cell state update in (DISPLAY_FORM45) to (DISPLAY_FORM47), where the new coefficients now add to 1:\nThe equations governing a standard GRU are:\nThe GRU's hidden state is squashed because its update gate $z$ merges the functions of the input and forget gates ($i$ and $f$) of the LSTM (cf. equations DISPLAY_FORM45 and DISPLAY_FORM48). As a result, the input and forget weights are tied in the GRU but not the LSTM. To create a non-squashed GRU, we added an input gate $i$ and changed the hidden state update (Equation DISPLAY_FORM48) to Equation DISPLAY_FORM49 to make $z$ act solely as a forget gate:\n\nInquiry: What architectural factors were investigated?", "role": "user" }, { "content": "{\"answer\": [\"type of recurrent unit\", \"type of attention\", \"choice of sequential vs. tree-based model structure\"], \"evidence\": [\"We find that all the factors we tested can qualitatively affect how a model generalizes on the question formation task. These factors are the type of recurrent unit, the type of attention, and the choice of sequential vs. tree-based model structure. Even though all these factors affected the model\\u0027s decision between move-main and move-first, only the use of a tree-based model can be said to impart a hierarchical bias, since this was the only model type that chose a hierarchical generalization across both of our tasks. Specific findings that support these general conclusions include:\"]}", "role": "assistant" } ]

[ { "content": "Analyze the provided clinical trial criteria. Identify and extract distinct entities from the text.\n\nReturn the results as a JSON structure. Ensure the output is strictly in JSON format without any additional commentary.\n\nCriteria Text:\n\nAge 18-65\nDiagnosis of MDD (Major Depressive Disorder), made or affirmed by a senior psychiatrist in Shalvata\nMADRS score > 20\nTreated with conventional anti-depressant, administered within a formal psychiatric clinic or by a certified psychiatrist.", "role": "user" }, { "content": "{\"Condition\": [\"Major Depressive Disorder\", \"MDD\"], \"Device\": [], \"Drug\": [\"conventional anti-depressant\"], \"Measurement\": [\"MADRS score\"], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [\"Age\"], \"Procedure\": [\"Treated\"], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [\"\\u003e 20\", \"18-65\"], \"Visit\": []}", "role": "assistant" } ]

[ { "content": "Examine the given text from a research paper in the field of NLP. Your task is to identify the role of the citation within the context provided. Focus on understanding the intent behind the citation and classify it accordingly.\n\nSection Title:\nintroduction\n\nText Before Citation:\nA few others incorporate various measures of inter-document similarity between the texts to be labeled (Agarwal and Bhattacharyya, 2005; Pang and Lee, 2005; Goldberg and Zhu, 2006). Most sentiment-polarity classifiers proposed in the recent literature categorize each document independently. In particular, since we treat each individual speech within a debate as a single “document”, we are considering a version of document-level sentiment-polarity classification, namely, automatically distinguishing between positive and negative documents (Das and Chen, 2001; Pang et al., 2002; Turney, 2002; Dave et al., 2003).\n\nCitation Text:\nA few others incorporate various measures of inter-document similarity between the texts to be labeled ( Agarwal and Bhattacharyya , 2005 ; Pang and Lee , 2005 ; Goldberg and Zhu , 2006 ) .\n\nText After Citation:\nMany interesting opinion-oriented documents, however, can be linked through certain relationships that occur in the context of evaluative discussions. For example, we may find textual4 evidence of a high likelihood of agreement be4Because we are most interested in techniques applicable across domains, we restrict consideration to NLP aspects of the problem, ignoring external problem-specific information. For example, although most votes in our corpus were almost completely along party lines (and despite the fact that sameparty information is easily incorporated via the methods we propose), we did not use party-affiliation data. Indeed, in other settings (e.g., a movie-discussion listserv) one may not be able to determine the participants’ political leanings, and such information may not lead to significantly improved results even if it were available.", "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:\nwaves play an important role in the dynamics of the solar atmosphere .\nthey are believed as carriers of photospheric energy into the corona leading to plasma heating .\nwaves are intensively observed in the solar chromosphere and corona by soho ( solar and heliospheric observatory ) and trace ( transition region and coronal explorer ) ( nakariakov & verwichte 2005 ) .\ndominant intensity oscillations in a chromospheric network have a period of @xmath13-min .\nthe 3-min oscillations are believed to be either standing waves in a chromospheric cavity ( leibacher & stein 1981 ) or propagating waves , which arise as the response of the atmosphere to a general disturbance set at its base ( fleck & schmitz 1991 ) .\ncoupling of these oscillations to the alfvn waves is a crucial process in both cases , as the alfvn waves may easily pass through the transition region taking the energy into the corona . on the other hand , recent numerical ( rosenthal et al . , 2002 ) , analytical ( zaqarashvili & roberts , 2006 ) and observational ( muglach et al . , 2005 ) studies point out the importance of @xmath2 region of the solar atmosphere in the wave coupling phenomena .\nhere we consider the 3-min oscillations as the standing acoustic waves oscillating along an uniform vertical magnetic field and study their weakly nonlinear coupling to alfvn waves near the chromospheric @xmath2 regions .\nwe use cartesian coordinate system @xmath3 , where spatially inhomogeneous ( along the @xmath4 axis ) magnetic field is directed along the @xmath5 axis , i.e. @xmath6 .\nunperturbed plasma pressure @xmath7 and density @xmath8 are also assumed to vary along @xmath4 . in the equilibrium ,\nmagnetic and hydrodynamic pressures satisfy the transverse balance , i.e. @xmath9 .\nplasma @xmath10 is defined as @xmath11 , where @xmath12 and @xmath13 are the sound and alfvn speeds respectively and @xmath14 is the ratio of specific heats . for simplicity , temperature is suggested to be homogeneous so that the sound speed does not depend on the @xmath4 coordinate .\nwe consider wave propagation along the @xmath5 axis ( thus along the magnetic field ) and wave polarisation in @xmath15 plane .\nthen in this case only sound and linearly polarised alfvn waves arise .\nthe velocity component of sound wave is polarised along the @xmath5 axis and the velocity component of alfvn wave is polarised along the y axis .\nthen the ideal mhd equations can be written as @xmath16 @xmath17 @xmath18 @xmath19 @xmath20 where @xmath21 and @xmath22 denote the total ( unperturbed plus perturbed ) hydrodynamic pressure and density , @xmath23 and @xmath24 are velocity perturbations ( of the alfvn and sound waves , respectively ) , @xmath25 is the perturbation in the magnetic field .\nnote , that the @xmath4 coordinate stands as a parameter in these equations .\n( 1)-(5 ) describe the fully nonlinear behavior of sound and linearly polarized alfvn waves propagating along the magnetic field\n. however the sound waves may be trapped in a chromospheric cavity between the photosphere and transition region leading to standing patterns .\ntherefore here we consider the sound waves oscillating along the @xmath5 axis and bounded at @xmath26 and @xmath27 points .\nthus there are the standing patterns @xmath28 where @xmath29 is the wavenumber of sound wave such that @xmath30 , so @xmath31 , where @xmath32 denotes the order of corresponding harmonics .\nit is natural that almost whole oscillation energy in bounded systems is stored in a fundamental harmonic .\ntherefore here we consider the first ( @xmath33 ) harmonic of acoustic oscillations , however the same can be applied to harmonics with arbitrary @xmath34 .\nrecently , zaqarashvili and roberts ( 2006 ) found that the harmonics of acoustic and alfvn waves are coupled when the wave length of acoustic wave is half of alfvn wave one .\ntherefore let express the alfvn wave components as @xmath35 where @xmath36 is the wavenumber of the alfvn waves and the condition @xmath37 is satisfied .\nthen the substitution of expressions ( 6)-(7 ) into eqs .\n( 1)-(5 ) and averaging with @xmath5 over the distance @xmath38 leads to @xmath39 @xmath40 @xmath41 @xmath42 here eqs .\n( 10)-(11 ) describe the time evolution of acoustic oscillation forced by ponderomotive force of alfvn waves , while eqs .\n( 8)-(9 ) governs the dynamics of alfvn waves forced by acoustic waves in a parametric way .\nit must be noted that the coupling between sound and alfvn waves at @xmath43 has been recently studied by zaqarashvili & roberts ( 2006 ) .\nthey consider the general case of propagating waves and show an alternate energy exchange between the waves during the propagation . here\nwe consider the coupling between standing patterns of the waves , which is the particular case of their results .\nsubstitution of @xmath44 from eq .\n( 8) into eq .\n( 9 ) and neglecting of all third order terms leads to the second order differential equation for alfvn waves @xmath45 b= 0.\\ ] ] this equation reflects the parametric influence of standing acoustic wave due to the density variation\n. then the particular time dependence of density perturbation determines the type of equation and consequently its solutions .\nif we consider the initial amplitude of alfvn waves smaller than the amplitude of acoustic waves , then the term with @xmath46 in eq .\n( 10 ) can be neglected .\nphysically it means that the back reaction of alfvn waves due to the ponderomotive force is small .\nthen the solution of eqs .\n( 10)-(11 ) is just harmonic function of time @xmath47 , where @xmath48 is the frequency of the first harmonic of standing acoustic wave and @xmath49 is the relative amplitude .\nhere we consider the small amplitude acoustic waves @xmath50 , so the nonlinear steepening due to the generation of higher harmonics is negligible .\nthen the substitution of this expression into eq .\n( 12 ) leads to mathieu equation @xmath51\nb= 0.\\ ] ] the solution of this equation with the frequency of @xmath52 has an exponentially growing character , thus the main resonant solution occurs when @xmath53 where @xmath54 is the frequency of alfvn waves . since @xmath55 , the resonance takes place when @xmath56 .\nsince the alfvn speed @xmath57 is a function of the @xmath4 coordinate , then this relation will be satisfied at particular locations along the @xmath4 axis .\ntherefore the acoustic oscillations will be resonantly transformed into alfvn waves near this layer .\nwe call this region _ swing layer _ ( see similar consideration in shergelashvili et al . 2005 ) . under the resonant condition ( 14 ) the solution of eq .\n( 13 ) is @xmath58,\\ ] ] where @xmath59 .\nthe solution ( 15 ) has a resonant character within the frequency interval latexmath:[${\\left |{\\omega_a } - { { \\omega_1}/ 2 } \\right |}<{\\left latexmath:[${\\left |{{v_a}/ c_s } - 1 \\right |}<{\\left |{{\\alpha } } \\right wave amplitude .\ntherefore the acoustic oscillations are converted into alfvn waves not only at the surface @xmath56 but in the region where @xmath61 .\nthus the resonant layer can be significantly wider for stronger amplitude acoustic oscillations .\nnote , that the resonant alfvn waves expressed by eqs .\n( 7 ) and ( 15 ) are standing patterns with the velocity node at the bottom boundary ( @xmath26 ) and antinode at the top boundary ( @xmath27 ) ; the wave length of alfvn waves is twice than that of the acoustic oscillations due to the condition @xmath55 .\ntherefore the oscillation of magnetic field lines at the upper boundary may excite the waves in an external plasma , which carry energy away .\nupper panels show the density and velocity components of standing acoustic oscillations , while lower panels show the magnetic field and velocity component of alfvn waves .\nrelative amplitude of acoustic oscillations is 0.1 .\nalfvn waves with twice the period of acoustic oscillations show rapid exponential increase in time.,width=377 ] [ figvibstab ] it must be noted that the alfvn waves may undergo a phase mixing due to the @xmath4 dependence of the alfvn speed ( tsiklauri & nakariakov 2002 ) .\nhowever the aim of this paper is to show the energy conversion from 3-min oscillations into alfvn waves only , therefore we do not consider the effect of phase mixing here . region . amplitude of alfvn waves ( lower panels ) shows no increase in time , so there is no wave coupling in this region.,width=377 ] [ figvibstab ] numerical solutions of eqs .\n( 8)-(11 ) ( here the back reaction of alfvn waves , i. e. the second term of right hand side in eq .\n( 10 ) , is again neglected ) are presented on fig.1 - 2 .\nfigure 1 shows the wave dynamics in @xmath62 region and we see the rapid growth of alfvn waves with twice the period of acoustic oscillations .\nhowever fig.2 shows the wave dynamics away from the resonant layer ( in @xmath63 region ) and we see no energy exchange between the waves . thus there is a good agreement between numerical results and analytical solutions .\nit must be mentioned that the equilibrium used in this paper is simplified as gravitational stratification , which is important in the solar chromosphere , is ignored .\nthe stratification leads to klein - gordon equation for propagating waves with a cut - off for wave frequencies ( roberts , 2004 ) .\nthe 3-min oscillations and alfvn waves are above the cut - off , so they may propagate in the chromosphere .\nunfortunately , the stratification greatly complicates mathematical description of the non - linear coupling . on the other hand ,\nplasma @xmath10 can be constant along a vertical magnetic tube even in the case of stratification ( roberts , 2004 ) ; this is the case when sound and alfvn speeds vary with height but their ratio remains constant .\ntherefore if the waves are coupled at @xmath64 region in an unstratified atmosphere , then the same can be expected in a stratified medium .\nhowever the wave coupling in the stratified atmosphere needs further detailed study , but is not the scope of present paper .\nour goal is just to show that the 3-min oscillations may transfer energy into incompressible alfvn waves in @xmath43 region , which was recently observed by muglach et al .\nhere we show that acoustic oscillations trapped in transversally inhomogeneous medium can be resonantly absorbed by alfvn waves near the layer of @xmath65 .\nthe spatial width of the layer depends on amplitude of acoustic oscillations and can be significantly wider for strong amplitude oscillations .\nwe consider the observed 3-min oscillations as the standing fundamental harmonic of acoustic waves trapped in the solar chromospheric cavity with vertical magnetic field and show that their nonlinear coupling to alfvn waves may take place near @xmath43 layer .\nthe coupling may explain the recent observational evidence of compressible wave absorption near @xmath2 region of solar lower atmosphere ( muglach et al . , 2005 ) .\nthe amplified alfvn waves with the period of @xmath1 6 min may carry energy into the corona .\nthere they may deposit the energy back to density perturbations leading to observed intensity variations in coronal spectral lines .\nthus the layer of @xmath43 may play a role of _ energy channel _ for otherwise trapped acoustic oscillations guiding the photospheric energy into the solar corona .\ntherefore the process of wave coupling can be of importance for coronal heating problem , but requires further study especially for a stratified atmosphere .\nthe work was supported by the grant of georgian national science foundation gnsf / st06/4 - 098 and the nato reintegration grant fel.rig 980755 .\na part of the work is supported by the issi international programme `` waves in the solar corona '' .\nrosenthal , c. s. , bogdan , t.j . , carlsson ,\nm . , dorch , s.b.f . ,\nhansteen , v. , mcinstosh , s.v . ,\nmcmurry , a . , nordlund , a. & stein , r.f .\n, waves in the magnetized solar atmosphere . i.\nbasic processes and internetwork oscillations , 2002 , apj , 564 , 508 roberts , b. , mhd waves in the solar atmosphere , 2004 , soho 13 - waves , oscillations and small - scale transient events in the solar atmosphere : a joint view from soho and trace .\npalma de mallorca , balearic islands , spain , ( esa sp-547 ) , 1", "role": "user" }, { "content": "nonlinear coupling between 3-minute oscillations and alfvn waves in the solar lower atmosphere is studied . \n 3-minute oscillations are considered as acoustic waves trapped in a chromospheric cavity and oscillating along transversally inhomogeneous vertical magnetic field . \n it is shown that under the action of the oscillations the temporal dynamics of alfvn waves is governed by mathieu equation . \n consequently , the harmonics of alfvn waves with twice period and wavelength of 3-minute oscillations grow exponentially in time near the layer where the sound and alfvn speeds equal i.e. @xmath0 . thus the 3-minute oscillations are resonantly absorbed by pure alfvn waves near this resonant layer . \n the resonant alfvn waves may penetrate into the solar corona taking energy from the chromosphere . \n therefore the layer @xmath0 may play a role of _ energy channel _ for otherwise trapped acoustic oscillations . solar atmosphere ; magnetohydrodynamic waves", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: Non-monotonic Response to Monotonic Stimulus: Regulation of Glyoxylate Shunt Gene-Expression Dynamics in Mycobacterium tuberculosis\nContent:\nAbstract:\nUnderstanding how dynamical responses of biological networks are constrained by underlying network topology is one of the fundamental goals of systems biology. Here we employ monotone systems theory to formulate a theorem stating necessary conditions for non-monotonic time-response of a biochemical network to a monotonic stimulus. We apply this theorem to analyze the non-monotonic dynamics of the σB-regulated glyoxylate shunt gene expression in Mycobacterium tuberculosis cells exposed to hypoxia. We first demonstrate that the known network structure is inconsistent with observed dynamics. To resolve this inconsistency we employ the formulated theorem, modeling simulations and optimization along with follow-up dynamic experimental measurements. We show a requirement for post-translational modulation of σB activity in order to reconcile the network dynamics with its topology. The results of this analysis make testable experimental predictions and demonstrate wider applicability of the developed methodology to a wide class of biological systems.\nIntroduction:\nUncovering how regulatory networks shape the dynamical properties of cellular responses to external stimuli is one of the ultimate goals of system biology. Despite our successes in mapping and modeling gene regulatory networks for a wide variety of model systems, only a handful of generalizable rules relating network architecture to its dynamic performance have been formulated. These rules are often called evolutionary design principles of biochemical networks[1]. Developing new approaches to find these design principles should allow us to extend our understanding of biological network dynamics from a few case studies to a wide variety of model systems. Here we formulate one such approach and apply it to a network controlling the response of Mycobacterium tuberculosis, the causative agent of tuberculosis( TB), to hypoxic stress. With almost one-third of the world population infected, TB remains a major public health threat[2]. M. tuberculosis survives stress conditions induced by host immunity by undergoing major metabolic and physiological remodeling that leads to mycobacterial dormancy[3–6]. Understanding this adaptive response of the tubercle bacillus is central to our long-term ability to control the pathogen. Transcriptional networks downstream of the alternative sigma factor σE, are critical for this adaptive response. They are activated when bacteria infect host macrophages, and induce the production of virulence factors and host inflammatory responses[7, 8]. Deletion of sigE leads to the strongest attenuation of M. tuberculosis murine infection among all accessory sigma factor mutant strains[7]. Induction of σE can be studied in vitro by exposing M. tuberculosis cells to a wide range of stressors such as hypoxia and surface or oxidative stress[7, 8]. Due to its importance for cellular survival, σE is subjected to rather complex regulatory mechanisms at both the transcriptional and post-translational levels. Transcription of sigE is controlled by three different promoters( P1-3). P1 is responsible for basal expression of sigE under normal physiological conditions. P2 is activated in the presence of MprA, part of the MprAB two component system that can sense surface stress[9, 10]. Interestingly, σE also activates the transcription of MprAB, forming a positive feedback loop. The last promoter( P3) is transcribed by the σH-RNAP holoenzyme in response to oxidative stress. σE post-translational regulation is primarily controlled by its anti-sigma factor, RseA. RseA binds to and sequesters σE, preventing the formation of the active σE-RNAP holoenzyme. However, under stressful conditions, PknB( a eukaryotic-like Ser/Thr protein kinase) will phosphorylate RseA, tagging it for degradation by the ClpC1P2 proteases[10, 11]. Recently, the transcriptional dynamics of σE and several of its regulon members following hypoxic stress have been quantified, and the networks controlling production of two critical central metabolism genes, icl1( Rv0467, glyoxylate shunt) and gltA1( Rv1131, methylcitrate cycle), have been characterized[12]. These genes are implicated in the growth-phase-dependent metabolic adaptation of M. tuberculosis[13] and are essential for growth and persistence of tubercle bacilli in infection models[14–16]. The glyoxylate shunt is especially important because it allows M. tuberculosis to efficiently metabolize fatty acids; indeed, it has been suggested that fatty acids may be the major source of carbon and energy for tubercle bacilli in chronically infected lung tissue[16]. For icl1( Fig 1A), transcription requires both σB, an alternative sigma factor transcribed under σE control, and a σB-regulated transcription factor, named lrpI( Rv0465c, local regulatory protein of icl1)[12]. This network motif–coherent feedforward loop–is a common motif of bacterial regulatory networks that is known to produce delays in responses to step-up inputs, to filter transient stimuli, and to increase network sensitivity[1, 17]. Notably, in the case of icl1, the resulting activation dynamics is different from that is seen for other coherent feedforward loops. Following gradual depletion of oxygen over the course of 3 days, which leads to σE activation, icl1 is transiently induced on day 4, and then decreases to pre-induction levels by day 5( Fig 1B). A similar transient surge in icl1 has also been observed in vivo[12]. In this paper, we develop a methodology to uncover the mechanism of non-monotonic response following the monotonic dynamics of a stimulus, and apply it to the transient surge in icl1 dynamics. We first formulate a general theorem based on monotone systems theory that gives a necessary condition for this observation. Then we employ a combination of modeling, parameter optimization, and experimental tests to uncover missing interactions in the icl1 regulatory network and to make new experimentally testable predictions.\nDiscussion:\nThe combination of traditional molecular genetics and novel high-throughput assays has generated a vast amount of information on the interactions that comprise biochemical networks inside living cells. For example, transcriptional regulatory networks can be obtained from gene-expression analyses such as qPCR, gene expression microarray technology, and RNA-seq, while DNA-protein interactions can be studied by chromatin immunoprecipitation-based( ChIP) measurements. However, regulatory networks are incomplete in even the best studied model systems[28, 29]. At the same time, as more dynamical information about the responses of these networks to external perturbations is accumulated, mathematical models can use this data to pinpoint the inconsistencies between observed gene expression dynamics and presumed network topology, and to predict missing interactions[30]. In this context, dynamical systems theories that formulate necessary or sufficient conditions for a given network topology to lead to certain dynamical behaviors are especially useful as these conditions are often independent from detailed reaction mechanisms and kinetic parameters. Much research exists on the characterization of dynamics of bio-molecular networks by means of their topology. Among many such directions of work, one may mention:( 1) the deep theory worked out by Feinberg in the early 1970s based on the idea of deficiency[31], which has been applied to many fields, including T-cell kinetic proofreading models[32] or receptor-ligand pharmaceutical models[33], and is still the subject of a major research effort[34, 35];( 2) the use of graph-theoretic ideas based on Petri nets[36];( 3) the theories of cooperative and competitive systems[37]; and( 4) methods of commutative algebra and algebraic geometry[38, 39]. In this work, we formulated the necessary conditions for an output variable of a dynamical system to non-monotonically vary in time with changing inputs. In simplified terms, a non-monotonic response to monotonic stimulus requires the presence of an indirect negative feedback or an incoherent feedforward loop in the network graph. Even when the exact stimulus dynamics is not known, the comparison of the dynamics of internal components with the topology of the network graph can point to inconsistencies or missing loops. We applied these results in combination with mathematical modeling and subsequent experimental tests to a network controlling transient upregulation of icl1, the gene encoding a glyoxylate shunt enzyme( isocitrate lyase 1), in response to hypoxia in M. tuberculosis. We found at least one inconsistency in the previously postulated network structure. Our results predict that there should be biochemical interactions that post-transcriptionally downregulate sigma factors σB, and possibly σE. Focusing on the former, we show that this downregulation can be explained by proteolytic degradation of σB protein by Clp protease system. Our model demonstrates that this interaction is consistent with all measurements for wild-type and genetically modified strains( Fig 6). As ClpP is essential for M. tuberculosis growth in vitro[40], a ClpP knockout mutant could not be created. Thus, this is a major prediction of the model that will be tested in future studies. The predicted proteolytic degradation of σB is not unprecedented. In multiple bacterial species, stress-induced alternative sigma factors are proteolytically degraded by clp homologs. For example, RpoS( σS) is an enterobacterial sigma factor that is implicated in stationary-phase survival as well as virulence in pathogenic species[8, 41–45]. The protease ClpXP has been implicated in the regulation of RpoS in several pathogens, including S. typhimurium[43, 44], and has been directly shown to degrade RpoS in E. coli[45]. It is known that the mycobacterial σB and RpoS share an evolutionary relationship[8], which might suggest that proteolytic degradation by ClpP is conserved among some sigma factors. Additionally, ClpP has been shown to degrade σB of B. subtilis[46]. Despite sharing a common name, the σB of B. subtilis is actually more closely related to the mycobacterial σF[27]; however, mycobacterial σF and σB share a common evolutionary origin[27], again possibly pointing to a potential conserved mechanism for the regulation of stress-induced sigma factors. What is the significance of the transient activation of icl1 in hypoxia and the predicted feedforward loops? The hypoxic response can be considered a component of the metabolic adaptation of M. tuberculosis during infection, both because oxygen may become limiting inside the infected macrophage and because the lung tissue microenvironment becomes hypoxic as a granuloma develops[47–49]. Such adaptation ultimately leads to tubercle bacilli transitioning to a non-replicating/persistent state that is associated with latent infection. It may be argued that the stress-induced activation of adaptive metabolic pathways, such as those involving the activity of the icl1 product, is transient because the response to stress is followed by slow-down of the mycobacterial metabolic activity. Consequently, no sustained expression of metabolic enzymes such as Icl1 is required. Presumably, the transient surge in icl1 transcription at day 4 of hypoxia produces sufficient amounts of Icl1 protein until persistence is fully attained. Indeed, the observation that icl1 is induced transiently also during mouse lung infection supports a physiological role of this dynamics in pathogenesis[12]. If these hypotheses are correct, drugs blocking negative interactions responsible for non-monotonic dynamics could in principle destabilize transitions to latency or trigger reactivation. The theorem described in this work can be applied to a wide variety of biological systems to help understand the relationship between network topology and dynamics. For example, biochemical adaptation is a topic of wide interest, largely because of its ubiquity in biological systems—adaptation occurs when a step-up input into a biochemical network causes one or more downstream components to transiently increase but then return to the previously maintained steady state. Chemotaxis—the process where a cell moves in response to a chemical signal—is a well-known behavior that exhibits adaptive responses. This behavior is seen in a wide variety of organisms, including bacteria, neutrophils[50] and amoeba[50–52]. The mechanisms whereby these organisms achieve adaptation vary widely, but a well-studied case is chemotaxis in E. coli—given a step input of a chemoattractant, the rate of ‘tumbling’ will initially sharply decrease, but then return to nearly its original level[53]. Therefore, biochemical adaptation is a specific case where a monotonic input gives rise to a non-monotonic output. We may apply the described theorem to conclude that there must be either an incoherent feedforward loop or a negative feedback loop. Indeed, this observation is recapitulated by previous work by Ma et al. that used simulations and parameter sampling to show that there are only two types of networks that can produce robust biochemical adaptation–incoherent feedforward loops and negative feedback loops[54]. Thus, the theorem may help clarify structure-function relationships in well-characterized biochemical networks, as well as predict previously unforeseen inconsistencies in others.", "role": "user" }, { "content": "Over the last several years mathematical modeling has become widely used to understand how biochemical systems respond to perturbations . In particular , dynamics of the response , i . e . the precise nature of how the responses changes with time , has become the focus of multiple studies . However , to this date only a few general rules that relate the dynamical responses with the structure of the underlying networks have been formulated . To this end , we ask which properties of the network allow systems to have a non-monotonic time-response ( first increasing and then decreasing ) to a monotonically increasing signal . We show that the networks displaying such responses must include indirect negative feedback or incoherent feedforward loop . Applying this result to the measured non-monotonic expression for glyoxylate shunt genes in Mycobacterium tuberculosis , a network known to be important to mycobacterial virulence , we show that the currently postulated network structure does not match the predictions of the theorem . Using a combination of mathematical modeling and follow-up experimental test we predict a novel incoherent loop in the network . This methodology has wide applications outside the specific network studied in this work—the theorem may potentially simplify the analysis of many biological systems .", "role": "assistant" } ]

[ { "content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: Hypertension Intervention Pooling Project.\nSummary: Data from 12 independently design ed and conducted r and omized trials of behavioral interventions for hypertension , consisting principally of variants of relaxation and biofeedback therapies , were aggregated to assess current progress of research in this area . Meta-analytical methods revealed a statistically significant decrease in diastolic blood pressure for nonmedicated patients at the end of intervention . No significant improvement was detected in medicated patients , but potential differential effectiveness of prescribed medications and differences in compliance among patients prohibits separation of changes due to behavioral treatments alone . The need to devise criteria for selection of patients , and to establish the most appropriate patient-treatment match is emphasized\n\n\nReport 2:\nTitle: STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT\nSummary: In clinical measurement comparison of a new measurement technique with an established one is often needed to see whether they agree sufficiently for the new to replace the old . Such investigations are often analysed inappropriately , notably by using correlation coefficients . The use of correlation is misleading . An alternative approach , based on graphical techniques and simple calculations , is described , together with the relation between this analysis and the assessment of repeatability\n\n\nReport 3:\nTitle: Quality of controlled clinical trials. The case of imaging ultrasound in obstetrics: a review\nSummary: Summary . R and omized controlled trials are increasingly used t o assess clinical practice s in obstetrics and gynaecology . The strength of these studies is that they usually address the issue of selection bias satisfactorily . Yet , as with any form of scientific investigation , the r and omized controlled trial has inherent limitations and is subject to flaws in its conduct . Using basic method ological criteria , this report assesses the quality of the four published controlled trials in which a policy of routine imaging ultrasonography in pregnancy was compared with a more restrictive policy . In addition , a pooled analysis using data from all four trials was conducted to illustrate how increasing the sample size may reveal differences between the two policies which remain undetected in trials using small sample s. The research ers in these studies reached different conclusions as to the effectiveness of routine ultrasound screening . Taken together , these four trials provide valuable information about routine ultrasound screening but fail to demonstrate adequately the usefulness of imaging ultrasound as a screening procedure for all pregnant women . The assessment criteria presented here could be used by investigators , editors , referees and other readers as a guideline for assessing the quality of therapeutic studies upon which clinical practice should be based\n\n\nReport 4:\nTitle: Relative efficacy of vasodilator therapy in chronic congestive heart failure. Implications of randomized trials.\nSummary: We examined existing evidence concerning the relative efficacy of various vasodilator agents in chronic congestive heart failure . Only r and omized placebo-controlled trials with clinical end points and treatment duration s of four weeks or more were selected from an exhaustive search of the English- language medical literature . Twenty-eight trials involving 1976 patients were found . Treatment duration s of the trials varied from one month to two years . Patients with symptomatic heart failure despite digitalis and diuretic therapy were studied ; most were middle-aged men and approximately half had coronary artery disease . Results of the trials were appraised by three independent observers , and mortality and functional status outcomes were pooled in a meta- analysis . All vasodilator agents except hydralazine hydrochloride were associated with improvements in functional status . Angiotensin converting-enzyme inhibitors were the only agents associated with both decreased mortality ( odds ratio , 0.51 ; 95 % confidence interval , 0.34 to 0.75 ) and improved functional status ( odds ratio , 4.53 ; 95 % confidence interval , 3.46 to 5.92 ) . The optimal timing for initiation of these agents was not established\n\n\nReport 5:\nTitle: Assessing the quality of randomized controlled trials: an annotated bibliography of scales and checklists.\nSummary: Assessing the quality of r and omized controlled trials ( RCTs ) is important and relatively new . Quality gives us an estimate of the likelihood that the results are a valid estimate of the truth . We present an annotated bibliography of scales and checklists developed to assess quality . Twenty-five scales and nine checklists have been developed to assess quality . The checklists are most useful in providing investigators with guidelines as to what information should be included in reporting RCTs . The scales give readers a quantitative index of the likelihood that the reported methodology and results are free of bias . There are several shortcomings with these scales . Future scale development is likely to be most beneficial if questions common to all trials are assessed , if the scale is easy to use , and if it is developed with sufficient rigor", "role": "user" }, { "content": "AMSTAR has good agreement , reliability , construct validity , and feasibility .", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\n[ Observation on therapeutic effect of picking therapy on Graves ' disease ] . OBJECTIVE To observe therapeutic effect of picking therapy on Graves ' disease ( GD ) and its effects on thyroid function . METHODS Sixty cases of GD were randomly divided into a treatment group ( pricking therapy group ) and a control group ( medication group ) . They were treated respectively with pricking thyroid gland high point or oral administration of tapazole . And changes of total triiodothyronine ( TT3 ) , total thyroxine ( TT4 ) , free T3 ( FT3 ) , free T4 ( FT4 ) , thyroxine receptor antibody ( TRAb ) , supersensitive thyrotropin ( S-TSH ) after treatment were investigated . RESULTS The total effective rate was 93.33 % in the treatment group and 76.67 % in the control group with a significant difference between the two groups ( P < 0.05 ) . After treatment , serum TT3 , TT4 , FT3 , FT4 and S-TSH contents had very significant change in the two groups ( P < 0.01 ) , TRAb had very significant change in the treatment group ( P < 0.01 ) and no significant change in the control group ( P > 0.05 ) there were significant differences in decrease of TT3 , FT3 , TRAb ( P < 0.05 ) and no significant difference in decrease of TT4 , FT4 and increase of S-TSH between the two groups ( P > 0.05 ) . CONCLUSION Pricking therapy has a definite therapeutic effect on Graves ' disease , which is carried out through regulating thyroid function .", "role": "user" }, { "content": "{\"Intervention\": [\"or\", \"oral administration of tapazole\", \".\", \"medication\", \"pricking thyroid gland high point\", \"pricking therapy\"], \"Outcome\": [\"serum TT3 , TT4 , FT3 , FT4 and S-TSH contents\", \"TT3 , FT3 , TRAb\", \"TT4 , FT4 and increase of S-TSH\", \"total triiodothyronine ( TT3 ) , total thyroxine ( TT4 ) , free T3 ( FT3 ) , free T4 ( FT4 ) , thyroxine receptor antibody ( TRAb ) , supersensitive thyrotropin ( S-TSH )\"], \"Participant\": [\"GD\", \"Graves \\u0027 disease\", \"Sixty\"]}", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Joint Source-Channel Decoding of Variable-Length Codes with Soft Information : A Survey \nChapter Title: ESTIMATION OF SOURCE STATISTICS FROM NOISY OBSERVATIONS \n1. Abstract of Cited Paper (BIB001): The performance and complexity of channel-optimized vector quantizers are studied for the Gauss-Markov source. Observations on the geometric structure of these quantizers are made, which have an important implication on the encoding complexity. For the squared-error distortion measure, it is shown that an operation equivalent to a Euclidean distance measurement with respect to an appropriately defined set of points (used to identify the encoding regions) can be used to perform the encoding. This implies that the encoding complexity is proportional to the number of encoding regions. It is then demonstrated that for very noisy channels and a heavily correlated source, when the codebook size is large, the number of encoding regions is considerably smaller than the codebook size-implying a reduction in encoding complexity. > \n2. Abstract of Cited Paper (BIB002): In this paper we propose an optimized transmission system for still images. This system comprises a VQ source encoder with a compression rate of 9. The source data is encoded using a BCH product code and mapped on a 16-QAM constellation. The codebook and channel encoder have been optimized to minimize distortion in presence of transmission errors. We use a new joint source-channel turbo decoding algorithm of the product code. As compared to classical channel decoding algorithms (soft decoding), we obtain an improvement of 0.7 dB in terms of coding gain for a BER of 10/sup -5/. The PSNR of the received image exhibits an improvement of 11 dB as compared to conventional turbo decoding at low SNRs. \n3. Abstract of Cited Paper (BIB003): We present a method for utilizing soft information in decoding of variable length codes (VLCs). When compared with traditional VLC decoding, which is performed using \"hard\" input bits and a state machine, soft-input VLC decoding offers improved performance in terms of packet and symbol error rates. Soft-input VLC decoding is free from the risk, encountered in hard decision VLC decoders in noisy environments, of terminating the decoding in an unsynchronized state, and it offers the possibility to exploit a priori knowledge, if available, of the number of symbols contained in the packet. \n4. Abstract of Cited Paper (BIB004): A process for the preparation by sintering of molybdenum based alloys containing at least one reinforcing element, characterized in that at least one addition compound is introduced in the liquid state into molybdenum used in the form of at least one of the members belonging to the group consisting of the salts of molybdenum, the oxides of molybdenum and metallic molybdenum, and in that carbon is then added in sufficient quantity and the intimate member, after reduction of the matrix to the metallic state of molybdenum was used in the form of at least one molybdenum salt or at least one molybdenum oxide, is sintered at a temperature at which the said carbon at least partially reduces the addition compound. \n5. Abstract of Cited Paper (BIB005): We describe a joint source-channel scheme for modifying a turbo decoder in order to exploit the statistical characteristics of hidden Markov sources. The basic idea is to treat the trellis describing the hidden Markov source as another constituent decoder which exchanges information with the other constituent decoder blocks. The source block uses as extrinsic information the probability of the input bits that is provided by the constituent decoder blocks. On the other hand, it produces a new estimation of such a probability which will be used as extrinsic information by the constituent turbo decoders. The proposed joint source-channel decoding technique leads to significantly improved performance relative to systems in which source statistics are not exploited and avoids the need to perform any explicit source coding prior to transmission. Lack of a priori knowledge of the source parameters does not degrade the performance of the system, since these parameters can be jointly estimated with turbo decoding.\n\nReview Chapter:", "role": "user" }, { "content": "In a practical set-up, in order to run the above algorithms, the source statistics need to be estimated from the received noisy bitstream Y N 1 . If we consider a quantized first-order Markov source, both the stationary and conditional distributions (P(S k ) and P(S k |S k−1 )) need to be estimated. Two cases can be considered: if the source can be represented using a reasonable number of parameters, a parametric estimation can be carried out, otherwise, a direct estimation has to be performed. In BIB003 where the VQ indexes are coded with FLC, a direct estimation using simple histograms of stationary and transition probabilities is shown to be sufficient. However, this assumes the source to be stationary. Alternatively, a parametric estimation method, making use of a modified turbo decoding procedure, is described in . The estimation procedure has been tested with a quantized first-order GaussMarkov (GM) source having a correlation factor denoted by ρ S . It is shown that for a stationary source, an appropriate solution is to proceed, before iterating, to a hard decoding at the source decoder output. Then the correlation, say ρ, can be estimated using a Yule-Walker algorithm. From this correlation, we can easily get an estimate of the transition probabilities that are used at the next iteration to help the BCJR decoding of the source. Setting the initial value of ρ to zero, it is shown that, for sufficiently high channel signal-tonoise ratio (E b /N 0 ), after a few iterations, the performances obtained are close to those resulting from a perfect knowledge of ρ. Figure 9 shows a set of results obtained using a GM source, with a correlation factor ρ S = 0.9, uniformly quantized on 16 levels and encoded with a Huffman code adapted to the stationary probabilities. The encoded source bitstream is protected by an RSC code (see ) with feed-forward and feedback polynomials given by F(z) = 1 + z 2 + z 3 + z BIB002 and G(z) = 1 + z + z 4 , respectively. Furthermore a puncturing matrix with first and second rows given by [111], [100], respectively, is introduced that leads us to a code rate R c = 3/4. After a binary phase shift keying modulation, the resulting bitstream is transmitted over an AWGN channel. In Figure 9 , it can be seen that the online estimation provides acceptable results. It also appears that an overestimation setting a JSCD with ρ = 0.9, instead of ρ S = 0.5 for the actual source, may have a dramatic impact on the overall performance. When dealing with real nonstationary signals, a good fit with a parametrical model cannot always be found. An example is given in for a model that is supposed to fit the motion vectors of a video sequence, where the authors acknowledge the relative inaccuracy of their model. Then a direct approach has to be preferred, the underlying problem being to estimate the parameters of an HMM. Techniques, such as the Baum-Welch algorithm BIB001 , are well suited for this problem. They have been used in BIB006 for joint turbo decoding and estimation of Hidden Markov sources, and also in BIB004 where the authors have proposed a method based on a forward-backward recursion to estimate the HMM parameters of a VLC compressed source. In , an iterative source-channel decoder is slightly modified in order to integrate in its source decoding module an estimation of the source statistics. The principle is illustrated in Figure 10 where the block named SISO-VLC realizes a BCJR decoding of the VLCs using the decoding trellis presented in . The SISO-VLC makes use of an augmented HMM, as explained in Section 3, in order to handle the bitstream segmentation problem. The HMM thus incorporates in the state variables a counter N k of the number of bits encoded at the symbol instant k. Indeed, any symbol S k may be represented by a binary word whose length L(S k ) is not a priori known. Consequently, at each symbol time k (k = 1, 2, . . . , K), not only the symbol S k , but also the segmentation value has to be estimated. Using the notation presented in Section 3.6, the codeword associated to S k may be written as We assume again that the symbols S k take their values in the alphabet A = {a 1 , . . . , a i (20) Then, as in the original BCJR algorithm BIB005 , α k (a i , n k ) and β k (a i , n k ) are obtained by recursion equations corresponding to the forward and backward steps, respectively. But in many practical problems, the source conditional probability P(a i |a j ) is not a priori known and has to be estimated. The solution proposed in makes use of the Baum-Welch method (cf. BIB001 for a tutorial presentation). As the Baum-Welch source HMM parameter estimation can be carried out together with the estimation performed by the BCJR algorithm, this approach does not imply a significant increase in complexity. For a first-order Markov source and a source alphabet of size |Q|, the estimates of the |Q| 2 source conditional probabilities P(a i |a j ) are estimated as The performance of this online statistics estimation algorithm is illustrated in Section 8 in the context of JSCD of H.263++ video motion vectors.", "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:\nan _ oriented graph _ is a digraph @xmath2 without loops and multiple arcs\nacyclic set _ in @xmath2 is a set of vertices which induces a subgraph without directed cycles .\nthe complement of an acyclic set of @xmath2 is a _ feedback vertex set _ of @xmath2 .\na question of albertson , which was the problem of the month on mohar s page @xcite , asks whether every planar oriented graph on @xmath0 vertices has an acyclic set of size at least @xmath3 .\nthere are three independent strengthenings of this question in the literature . in the following ,\nwe discuss them briefly .\n[ conj : harutyunyan ] every planar oriented graph of order @xmath0 has an acyclic set of size at least @xmath4 .\nthe _ digirth _ of a directed graph is the length of a smallest directed cycle .\ngolowich and rolnick @xcite showed that a planar oriented graph of digirth @xmath5 has an acyclic set of size at least @xmath6 in particular proving conjecture [ conj : harutyunyan ] for planar oriented graphs of digirth @xmath7 .\na lower bound of @xmath3 for the size of an acyclic set in an oriented planar graph would immediately follow from any of the following two conjectures .\n[ conj : neumann - lara ] every planar oriented graph can be vertex - partitioned into two acyclic sets .\nharutyunyan and mohar @xcite proved conjecture [ conj : neumann - lara ] for planar oriented graphs of digirth @xmath8 .\nthe undirected analogue of conjecture [ conj : neumann - lara ] is false , because it is equivalent to _\ntait s conjecture _\n( which is false )\n. however , the following remains open : [ conj : albertson - berman ] every simple undirected planar graph of order @xmath0 has an induced forest of order at least @xmath3 .\nthere are many graphs showing that conjecture [ conj : albertson - berman ] , if true , is best - possible , e.g. , @xmath9 and the octahedron .\nthe best - known lower bound for the order of a largest induced forest in a planar graph is @xmath10 and follows from borodin s result on acyclic vertex - coloring of undirected planar graphs @xcite .\nwe summarize the discussion in table [ table ] : .lower bounds for acyclic sets in planar oriented graphs . [\ncols=\"<,^,^,^,^\",options=\"header \" , ]\nhere , we give an upper bound for the maximum acyclic set in an oriented planar graph of given order and digirth .\nthe most important case of this result is the one when the digirth is 3 . for this case\nour result implies that , if true , the lower bound of @xmath3 in albertson s question is best possible .\nin particular it disproves conjecture [ conj : harutyunyan ] .\nwe show the corresponding statement for feedback vertex sets . indeed , a little stronger , we show that for any @xmath5 and @xmath12 there is an oriented planar graph @xmath13 such that : @xmath13 has digirth @xmath5 , order @xmath14 , and a minimum vertex feedback set of size @xmath12 .\nmoreover , @xmath13 has two vertices @xmath15 and @xmath16 on a common face @xmath17 , which do not simultaneously appear in any minimum feedback vertex set .\nwe induct on @xmath12 . for @xmath18\nwe take a directed cycle of order @xmath5 .\nthis clearly satisfies all conditions .\nif @xmath19 , take the plane digraph @xmath20 , add a directed path @xmath21 into its face @xmath17 and add arcs @xmath22 , @xmath23 , @xmath24 , and @xmath25 .\nsee figure [ fig : dessin ] . since in @xmath20\nno minimum feedback vertex set uses both @xmath15 and @xmath16 , in order to hit the two newly created directed cycles , an additional vertex @xmath26 is needed .\nthus , @xmath13 has a minimum feedback vertex set of size at least @xmath12 .\nnow , choosing @xmath27 , indeed gives a feedback vertex set of size @xmath12 .\nthus , in @xmath13 there is no minimum feedback vertex containing two vertices from @xmath28 .\nsince each such pair of vertices lies on a newly created common face , it only remains to check the order of @xmath13 . since we added a total of @xmath29 new vertices\n, @xmath13 has @xmath30 vertices , i.e. , @xmath31 .\nthus , the largest acyclic set in @xmath13 is of size @xmath32 . by theorem [ thm : ub ] , for even @xmath0 , an acyclic set in a planar oriented graph of digirth @xmath33\nis of size at most @xmath34 .\na computer check , using tools from sage @xcite , shows that there are 9 planar triangulations with @xmath0 vertices ( @xmath0 is even and @xmath35 ) that are tight examples for conjecture [ conj : albertson - berman ] .\nfurthermore , for all orientations of these examples , the largest directed acyclic set is of size at least @xmath34 .\nwe wonder if the following is true : if a largest induced forest in a simple undirected planar graph @xmath36 on @xmath0 vertices is of size @xmath37 , then for every orientation @xmath2 of @xmath36 there is an acyclic set of size at least @xmath38 .", "role": "user" }, { "content": "given a directed graph , an acyclic set is a set of vertices inducing a subgraph with no directed cycle . in this note \n we show that there exist oriented planar graphs of order @xmath0 for which the size of the maximum acyclic set is at most @xmath1 , for any @xmath0 . \n this disproves a conjecture of harutyunyan and shows that a question of albertson is best possible .", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nA search for serologic correlates of immunity to Bordetella pertussis cough illnesses . In a pertussis vaccine efficacy trial in Germany we collected sera from vaccinees ( DTaP or DTP ) after the third and fourth doses of vaccine or at comparable time periods in DT vaccine recipients . In addition , sera were collected from a randomized sample of subjects in each vaccine group at approximately 3-month intervals from which antibody kinetic curves were constructed , which allowed us to estimate specific antibody values to pertussis toxin ( PT ) , filamentous hemagglutinin ( FHA ) , pertactin and fimbriae-2 at the time of exposure in the household setting . The imputed geometric mean antibody values to PT , pertactin and fimbriae-2 at the time of household exposure to Bordetella pertussis infection were higher ( p < 0.07 or lower ) in non-cases compared with cases . A multivariate ( classification tree ) analysis found that only pertactin and PT were significant in protection . Subjects with an imputed pertactin value of < 7 EU ml-1 had a 67 % ( 18/27 ) chance of infection regardless of the PT value . If the pertactin value was > or = 7 EU ml-1 and the PT value > or = 66 EU ml-1 all subjects were non-cases . If the pertactin value was > or = 7 and the PT value was < 66 EU ml-1 the predicted probability of being a case was 31 % ( 15/49 ) . Logistic regression analysis also found that high versus low pertactin values were associated with illness prevention following household exposure . In the presence of antibody to pertactin , PT and fimbriae-2 , the additional presence of antibody to FHA did not contribute to protection . Our data support historical data indicating that agglutinating antibodies are associated with protection and also recent serologic correlates data and clinical efficacy data which indicate that multicomponent vaccines containing pertactin and fimbriae have better efficacy than PT or PT/FHA vaccines .", "role": "user" }, { "content": "{\"Intervention\": [\"pertussis\", \"vaccinees ( DTaP or DTP )\", \"multicomponent vaccines containing pertactin and fimbriae\"], \"Outcome\": [\"Logistic regression analysis\"], \"Participant\": [\"pertussis vaccine efficacy trial in Germany\"]}", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nSafety and immunogenicity of IMVAMUNE , a promising candidate as a third generation smallpox vaccine . A Phase I trial was performed to investigate the safety and immunogenicity of the third generation smallpox vaccine MVA-BN ( IMVAMUNE ) , a highly attenuated clone derived from the Modified Vaccinia Virus Ankara strain 571 , in naive and pre-immunized subjects . A total of 86 healthy subjects received the vaccine in five groups using different doses and routes of administration . All 38 subjects seroconverted in the groups receiving the highest dose ( 10 ( 8 ) TCID50 ) . All vaccinations were well tolerated with mainly mild or moderate pain at the injection site being the most frequent symptom . The results indicate that MVA-BN has the potential to be developed as an efficient and safe alternative to the conventional smallpox vaccines such as Lister-Elstree or Dryvax . Unique attributes render it a promising candidate for prophylactic mass immunization , even in subjects for whom conventional smallpox vaccines are contraindicated .", "role": "user" }, { "content": "{\"Intervention\": [\"third generation smallpox vaccine MVA-BN ( IMVAMUNE )\", \"IMVAMUNE\", \"vaccine\", \"Lister-Elstree or Dryvax .\"], \"Outcome\": [\"Safety\", \"safety\", \"moderate pain\", \"efficient and safe\", \"mild or\", \"well tolerated\", \"at the injection site\", \"immunogenicity\"], \"Participant\": [\"86\", \"healthy\", \"naive and pre-immunized subjects\"]}", "role": "assistant" } ]

[ { "content": "Analyze the provided text excerpt from a scientific document. Identify and extract distinct entities based on predefined categories.\n\nDeliver the results as a JSON structure where each key represents an entity category, and the associated value is a list of identified entities. If no entities are found for a category, return an empty list.\n\nText Excerpt:\n\nHuman T-cell leukemia virus type 1 tax protein abrogates interleukin-2 dependence in a mouse T-cell line. Human T-cell leukemia virus type 1 (HTLV-1) is the etiologic agent of adult T-cell leukemia. Tax, the viral protein, is thought to be crucial in the development of the disease, since it transforms healthy T cells in vitro and induces tumors in transgenic animals. We examined the effect of Tax activity on the growth of the interleukin-2 (IL-2) -dependent T-cell line CTLL-2. Stable expression of Tax in CTLL-2 transformed cell growth from being IL-2 dependent to IL-2 independent. Tax stimulated transcription through NF-kappaB and the cyclic AMP-responsive element-like sequence in the HTLV-1 promoter. The finding of Tax mutants segregating these two pathways suggested that the NF-kappaB pathway was essential for IL-2-independent growth of CTLL-2 cells while the CRE pathway was unnecessary. However, both pathways were necessary for another transformation-related activity (colony formation in soft agar) of CTLL-2 / Tax. Our results show that Tax has at least two distinct activities on T cells, and suggest that Tax plays a crucial role in IL-2-independent T-cell transformation induced by HTLV-1, in addition to its well-known IL-2-dependent cell transformation.", "role": "user" }, { "content": "{\"CellLine\": [\"mouse T - cell line\", \"CTLL - 2\", \"interleukin - 2 (IL - 2) - dependent T - cell line\"], \"CellType\": [\"CTLL - 2 cells\", \"T cells\", \"healthy T cells\"], \"DNA\": [\"cyclic AMP - responsive element - like sequence\", \"CRE\"], \"Protein\": [\"Human T - cell leukemia virus type 1 tax protein\", \"CTLL - 2 / Tax\", \"viral protein\", \"IL - 2\", \"interleukin - 2\", \"NF - kappaB\", \"Tax\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: Peer-to-Peer Information Retrieval: An Overview \nChapter Title: Optimization Techniques \n1. Abstract of Cited Paper (BIB001): The recent file storage applications built on top of peer-to-peer distributed hash tables lack search capabilities. We believe that search is an important part of any document publication system. To that end, we have designed and analyzed a distributed search engine based on a distributed hash table. Our simulation results predict that our search engine can answer an average query in under one second, using under one kilobyte of bandwidth. \n2. Abstract of Cited Paper (BIB002): We consider the problem of building a P2P-based search engine for massive document collections. We describe a prototype system called ODISSEA (Open DIStributed Search Engine Architecture) that is currently under development in our group. ODISSEA provides a highly distributed global indexing and query execution service that can be used for content residing inside or outside of a P2P network. ODISSEA is different from many other approaches to P2P search in that it assumes a two-tier search engine architecture and a global index structure distributed over the nodes of the system. We give an overview of the proposed system and discuss the basic design choices. Our main focus is on efficient query execution, and we discuss how recent work on topqueries in the database community can be applied in a highly distributed environment. We also give some preliminary simulation results on a real search engine log and a terabytesize web page collection that indicate good scalability for our approach. Project homepage: http://cis.poly.edu/westlab/odissea/. A preliminary version of this paper appeared at the International Workshop on the Web and Databases, June 2003. Contact author. Email: [email protected] \n3. Abstract of Cited Paper (BIB003): This paper addresses the efficient processing of top-k queries in wide-area distributed data repositories where the index lists for the attribute values (or text terms) of a query are distributed across a number of data peers and the computational costs include network latency, bandwidth consumption, and local peer work. We present KLEE, a novel algorithmic framework for distributed top-k queries, designed for high performance and flexibility. KLEE makes a strong case for approximate top-k algorithms over widely distributed data sources. It shows how great gains in efficiency can be enjoyed at low result-quality penalties. Further, KLEE affords the query-initiating peer the flexibility to trade-off result quality and expected performance and to trade-off the number of communication phases engaged during query execution versus network bandwidth performance. We have implemented KLEE and related algorithms and conducted a comprehensive performance evaluation. Our evaluation employed real-world and synthetic large, web-data collections, and query benchmarks. Our experimental results show that KLEE can achieve major performance gains in terms of network bandwidth, query response times, and much lighter peer loads, all with small errors in result precision and other result-quality measures. \n4. Abstract of Cited Paper (BIB004): The authors studied the problem of evaluating ranked (top-k) queries on textual collections ranging from multiple gigabytes to terabytes in size. The authors focused on the case of a global index organization in a highly distributed environment, and consider a class of ranking functions that includes common variants of the Cosine and Okapi measures. The main bottleneck in such a scenario is the amount of communication required during query evaluation. Several efficient query evaluation schemes were proposed and their performances were evaluated. The results on real search engine query traces and over 120 million Web pages show that after careful optimization such queries can be evaluated at a reasonable cost, while challenges remain for even larger collections and more general classes of ranking functions. \n5. Abstract of Cited Paper (BIB005): We consider a collaboration of peers autonomously crawling the Web. A pivotal issue when designing a peer-to-peer (P2P) Web search engine in this environment is query routing: selecting a small subset of (a potentially very large number of relevant) peers to contact to satisfy a keyword query. Existing approaches for query routing work well on disjoint data sets. However, naturally, the peers’ data collections often highly overlap, as popular documents are highly crawled. Techniques for estimating the cardinality of the overlap between sets, designed for and incorporated into information retrieval engines are very much lacking. In this paper we present a comprehensive evaluation of appropriate overlap estimators, showing how they can be incorporated into an efficient, iterative approach to query routing, coined Integrated Quality Novelty (IQN). We propose to further enhance our approach using histograms, combining overlap estimation with the available score/ranking information. Finally, we conduct a performance evaluation in MINERVA, our prototype P2P Web search engine.\n\nReview Chapter:", "role": "user" }, { "content": "In this section we discuss several optimization approaches. There are two reasons to use these techniques. One is to reduce bandwidth usage and latency, the other is to improve the quality and quantity of the search results returned. Most techniques discussed influence both of these aspects and offer trade-offs, for example, one could compromise on quantity to save bandwidth and on quality to reduce latency. BIB001 BIB004 BIB006 BIB002 BIB003 BIB005 .", "role": "assistant" } ]

[ { "content": "Analyze the provided text excerpt from a scientific document. Identify and extract distinct entities based on predefined categories.\n\nDeliver the results as a JSON structure where each key represents an entity category, and the associated value is a list of identified entities. If no entities are found for a category, return an empty list.\n\nText Excerpt:\n\nInhibition of NF-kappa B activation in vitro and in vivo: role of 26S proteasome. It is becoming increasingly apparent that NF-kappa B plays a critical role in regulating the inflammatory response. Data obtained from studies in our laboratories demonstrate that the proteasome plays an important role in the inflammatory cascade by regulating the activation of NF-kappa B. Indeed, the availability of selective and orally active proteasome inhibitors should prove useful in delineating the roles of the proteasome and NF-kappa B in other pathophysiological conditions such as cancer and heart disease.", "role": "user" }, { "content": "{\"CellLine\": [], \"CellType\": [], \"DNA\": [], \"Protein\": [\"NF - kappa B\", \"26S proteasome\"], \"RNA\": []}", "role": "assistant" } ]

[ { "content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nWe propose Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks.\nA Bayesian hypernetwork, h, is a neural network which learns to transform a simple noise distribution, p(e) = N(0,I), to a distribution q(t) := q(h(e)) over the parameters t of another neural network (the ``primary network).\nWe train q with variational inference, using an invertible h to enable efficient estimation of the variational lower bound on the posterior p(t | D) via sampling.\nIn contrast to most methods for Bayesian deep learning, Bayesian hypernets can represent a complex multimodal approximate posterior with correlations between parameters, while enabling cheap iid sampling of q(t). \nIn practice, Bayesian hypernets provide a better defense against adversarial examples than dropout, and also exhibit competitive performance on a suite of tasks which evaluate model uncertainty, including regularization, active learning, and anomaly detection.\n\nSimple and powerful techniques for Bayesian inference of deep neural networks' (DNNs) parameters have the potential to dramatically increase the scope of applications for deep learning techniques.\nIn real-world applications, unanticipated mistakes may be costly and dangerous, whereas anticipating mistakes allows an agent to seek human guidance (as in active learning), engage safe default behavior (such as shutting down), or use a \"reject option\" in a classification context.\nDNNs are typically trained to find the single most likely value of the parameters (the \"MAP estimate\"), but this approach neglects uncertainty about which parameters are the best (\"parameter uncertainty\"), which may translate into higher predictive uncertainty when likely parameter values yield highly confident but contradictory predictions.\nConversely, Bayesian DNNs model the full posterior distribution of a model's parameters given the data, and thus provides better calibrated confidence estimates, with corresponding safety benefits BID9 BID0 .\n1 Maintaining a distribution over parameters is also one of the most effective defenses against adversarial attacks BID4 .Techniques\nfor Bayesian DNNs are an active research topic. The most popular\napproach is variational inference BID2 BID8 , which typically restricts the variational posterior to a simple family of distributions, for instance a factorial Gaussian BID2 BID16 . Unfortunately, from\na safety perspective, variational approximations tend to underestimate uncertainty, by heavily penalizing approximate distributions which place mass in regions where the true posterior has low density. This problem can be\nexacerbated by using a restricted family of posterior distribution; for instance a unimodal approximate posterior will generally only capture a single mode of the true posterior. With this in mind,\nwe propose learning an extremely flexible and powerful posterior, parametrized by a DNN h, which we refer to as a Bayesian hypernetwork in reference to BID17 .A Bayesian hypernetwork\n(BHN) takes random noise ∼ N (0, I) as input and outputs a sample from the approximate posterior q(θ) for another DNN of interest (the \"primary network\"). The key insight for building\nsuch a model is the use of an invertible hypernet, which enables Monte Carlo estimation of the entropy term − logq(θ) in the variational inference training objective.We begin the paper by reviewing previous work on Bayesian DNNs, and explaining the necessary components of our approach (Section 2). Then we explain how to compose\nthese techniques to yield Bayesian hypernets, as well as design choices which make training BHNs efficient, stable and robust (Section 3). Finally, we present experiments\nwhich validate the expressivity of BHNs, and demonstrate their competitive performance across several tasks (Section 4).\nWe introduce Bayesian hypernets (BHNs), a new method for variational Bayesian deep learning which uses an invertible hypernetwork as a generative model of parameters.\nBHNs feature efficient we found the BALD values our implementation computes provide a better-than-random acquisition function (compare the blue line in the top and bottom plots).\n10 Li & Gal (2017) and BID28 used 10 and 1 model samples, respectively, to estimate gradient.\nWe report the result with 1 sample; results with more samples are given in the appendix.\nwhen more perturbation is added to the data (left), uncertainty measures also increase (first row).\nIn particular, the BALD and Mean STD scores, which measure epistemic uncertainty, are strongly increasing for BHNs, but not for dropout.\nThe second row and third row plots show results for adversary detection and error detection (respectively) in terms of the AUC of ROC (y-axis) with increasing perturbation along the x-axis.\nGradient direction is estimated with one Monte Carlo sample of the weights/dropout mask.training and sampling, and can express complicated multimodal distributions, thereby addressing issues of overconfidence present in simpler variational approximations.\nWe present a method of parametrizing BHNs which allows them to scale successfully to real world tasks, and show that BHNs can offer significant benefits over simpler methods for Bayesian deep learning.\nFuture work could explore other methods of parametrizing BHNs, for instance using the same hypernet to output different subsets of the primary net parameters.A", "role": "user" }, { "content": "We propose Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks.", "role": "assistant" } ]

[ { "content": "Consider the following research inquiry and associated key terms. Review the dataset summaries provided and determine which datasets are suitable for addressing the research question. Base your decision on your understanding of machine learning datasets.\nProvide your answer as a JSON list. For example, for the inquiry \"Semi supervised image classification\", a possible response could be: [\"CIFAR-10\", \"CIFAR-100\"]. Ensure the response contains only the dataset names in JSON format.\n\nResearch Inquiry: Glaucoma is a leading cause of irreversible blindness worldwide. Optic disc analysis can be used\n\nKey Terms: optic disc detection fundus images\n\nDataset Summaries:\nDRIVE: The Digital Retinal Images for Vessel Extraction (DRIVE) dataset is a dataset for retinal vessel segmentation. It consists of a total of JPEG 40 color fundus images; including 7 abnormal pathology cases.\nG1020: A large publicly available retinal fundus image dataset for glaucoma classification called G1020. The dataset is curated by conforming to standard practices in routine ophthalmology and it is expected to serve as standard benchmark dataset for glaucoma detection.\nLAG: Includes 5,824 fundus images labeled with either positive glaucoma (2,392) or negative glaucoma (3,432).\nHRF: The HRF dataset is a dataset for retinal vessel segmentation which comprises 45 images and is organized as 15 subsets. Each subset contains one healthy fundus image, one image of patient with diabetic retinopathy and one glaucoma image.\nFUNSD: Form Understanding in Noisy Scanned Documents (FUNSD) comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task.\nADAM: ADAM is organized as a half day Challenge, a Satellite Event of the ISBI 2020 conference in Iowa City, Iowa, USA. The ADAM challenge focuses on the investigation and development of algorithms associated with the diagnosis of Age-related Macular degeneration (AMD) and segmentation of lesions in fundus photos from AMD patients.\n\nDataset Options: A: DRIVE B: G1020 C: LAG D: HRF E: FUNSD F: ADAM", "role": "user" }, { "content": "[\"DRIVE\", \"HRF\"]", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nGenderdoesnottypicallyaffectIOPandagingresultsinanIOPdecreaseinsomestrains.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Consider the following research inquiry and associated key terms. Review the dataset summaries provided and determine which datasets are suitable for addressing the research question. Base your decision on your understanding of machine learning datasets.\nProvide your answer as a JSON list. For example, for the inquiry \"Semi supervised image classification\", a possible response could be: [\"CIFAR-10\", \"CIFAR-100\"]. Ensure the response contains only the dataset names in JSON format.\n\nResearch Inquiry: We propose a novel implicit 3D representation for 3D reconstruction.\n\nKey Terms: 3d reconstruction point clouds\n\nDataset Summaries:\nScanNet: ScanNet is an instance-level indoor RGB-D dataset that includes both 2D and 3D data. It is a collection of labeled voxels rather than points or objects.\nDeep Fashion3D: A novel benchmark and dataset for the evaluation of image-based garment reconstruction systems. Deep Fashion3D contains 2078 models reconstructed from real garments, which covers 10 different categories and 563 garment instances.\nWHU: Created for MVS tasks and is a large-scale multi-view aerial dataset generated from a highly accurate 3D digital surface model produced from thousands of real aerial images with precise camera parameters.\nPeople Snapshot Dataset: Enables detailed human body model reconstruction in clothing from a single monocular RGB video without requiring a pre scanned template or manually clicked points.\nMatterport3D: The Matterport3D dataset is a large RGB-D dataset for scene understanding in indoor environments. It contains 10,800 panoramic views inside 90 real building-scale scenes, constructed from 194,400 RGB-D images.\nShapeNet: ShapeNet is a large scale repository for 3D CAD models developed by researchers from Stanford University, Princeton University and the Toyota Technological Institute at Chicago, USA. The repository contains over 300M models with 220,000 classified into 3,135 classes arranged using WordNet hypernym-hyponym relationships.\n\nDataset Options: A: ScanNet B: Deep Fashion3D C: WHU D: People Snapshot Dataset E: Matterport3D F: ShapeNet", "role": "user" }, { "content": "[\"ScanNet\", \"Matterport3D\", \"ShapeNet\"]", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nWe introduce a new task named Story Ending Generation (SEG), which aims at generating a coherent story ending from a sequence of story plot. We propose a framework consisting of a Generator and a Reward Manager for this task. The Generator follows the pointer-generator network with coverage mechanism to deal with out-of-vocabulary (OOV) and repetitive words. Moreover, a mixed loss method is introduced to enable the Generator to produce story endings of high semantic relevance with story plots. In the Reward Manager, the reward is computed to fine-tune the Generator with policy-gradient reinforcement learning (PGRL). We conduct experiments on the recently-introduced ROCStories Corpus. We evaluate our model in both automatic evaluation and human evaluation. Experimental results show that our model exceeds the sequence-to-sequence baseline model by 15.75 and 13.57 in terms of CIDEr and consistency score respectively.\n\nCited Works Summary:\n[1]: Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.\n\n[2]: In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.\n\n[3]: In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder-Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.\n\n[4]: \n\n[5]: \n\n[6]: Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.\n\n[7]: \n\n[8]: Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT-14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous state of the art. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.", "role": "user" }, { "content": "Encoder-decoder framework, which uses neural networks as encoder and decoder, was first proposed in machine translation [3] [4]2 and has been widely used in NLG tasks. The encoder reads and encodes a source sentence into a fixed-length vector, then the decoder outputs a new sequence from the encoded vector. Attention mechanism [6] extends the basic encoder-decoder framework by assigning different weights to input words when generating each target word. [5] , [2] and [1] apply attention-based encoder-decoder model to text summarization. [7] and [4] develop new and effective attentive models for machine reading comprehension.", "role": "assistant" } ]

[ { "content": "Analyze the given research paper excerpts and address the question provided. Extract the necessary information directly from the text. Your answer should be formatted as a JSON object with the following structure:\n\n\"answer\": A list of text segments from the paper that directly respond to the question.\n\"evidence\": A list of text segments from the paper where the answer can be found.\n\nIf the question cannot be answered with the given text, return \"null\".\n\nDocument: Make Lead Bias in Your Favor: A Simple and Effective Method for News Summarization\n\nLead bias is a common phenomenon in news summarization, where early parts of an article often contain the most salient information. While many algorithms exploit this fact in summary generation, it has a detrimental effect on teaching the model to discriminate and extract important information. We propose that the lead bias can be leveraged in a simple and effective way in our favor to pretrain abstractive news summarization models on large-scale unlabeled corpus: predicting the leading sentences using the rest of an article. Via careful data cleaning and filtering, our transformer-based pretrained model without any finetuning achieves remarkable results over various news summarization tasks. With further finetuning, our model outperforms many competitive baseline models. Human evaluations further show the effectiveness of our method.\n\nIntroduction\nThe goal of text summarization is to condense a piece of text into a shorter version that contains the salient information. Due to the prevalence of news articles and the need to provide succinct summaries for readers, a majority of existing datasets for summarization come from the news domain BIBREF0, BIBREF1, BIBREF2. However, according to journalistic conventions, the most important information in a news report usually appears near the beginning of the article BIBREF3. While it facilitates faster and easier understanding of the news for readers, this lead bias causes undesirable consequences for summarization models. The output of these models is inevitably affected by the positional information of sentences. Furthermore, the simple baseline of using the top few sentences as summary can achieve a stronger performance than many sophisticated models BIBREF4. It can take a lot of effort for models to overcome the lead bias BIBREF3.\nAdditionally, most existing summarization models are fully supervised and require time and labor-intensive annotations to feed their insatiable appetite for labeled data. For example, the New York Times Annotated Corpus BIBREF1 contains 1.8 million news articles, with 650,000 summaries written by library scientists. Therefore, some recent work BIBREF5 explores the effect of domain transfer to utilize datasets other than the target one. But this method may be affected by the domain drift problem and still suffers from the lack of labelled data.\nThe recent promising trend of pretraining models BIBREF6, BIBREF7 proves that a large quantity of data can be used to boost NLP models' performance. Therefore, we put forward a novel method to leverage the lead bias of news articles in our favor to conduct large-scale pretraining of summarization models. The idea is to leverage the top few sentences of a news article as the target summary and use the rest as the content. The goal of our pretrained model is to generate an abstractive summary given the content. Coupled with careful data filtering and cleaning, the lead bias can provide a delegate summary of sufficiently good quality, and it immediately renders the large quantity of unlabeled news articles corpus available for training news summarization models.\nWe employ this pretraining idea on a three-year collection of online news articles. We conduct thorough data cleaning and filtering. For example, to maintain a quality assurance bar for using leading sentences as the summary, we compute the ratio of overlapping non-stopping words between the top 3 sentences and the rest of the article. As a higher ratio implies a closer semantic connection, we only keep articles for which this ratio is higher than a threshold.\nWe end up with 21.4M articles based on which we pretrain a transformer-based encoder-decoder summarization model. We conduct thorough evaluation of our models on five benchmark news summarization datasets. Our pretrained model achieves a remarkable performance on various target datasets without any finetuning. This shows the effectiveness of leveraging the lead bias to pretrain on large-scale news data. We further finetune the model on target datasets and achieve better results than a number of strong baseline models. For example, the pretrained model without finetuning obtains state-of-the-art results on DUC-2003 and DUC-2004. The finetuned model obtains 3.2% higher ROUGE-1, 1.6% higher ROUGE-2 and 2.1% higher ROUGE-L scores than the best baseline model on XSum dataset BIBREF2. Human evaluation results also show that our models outperform existing baselines like pointer-generator network.\nThe rest of paper is organized as follows. We introduce related work in news summarization and pretraining in Sec:rw. We describe the details of pretraining using lead bias in Sec:pre. We introduce the transformer-based summarization model in Sec:model. We show the experimental results in Sec:exp and conclude the paper in Sec:conclusion.\n\nRelated work ::: Document Summarization\nEnd-to-end abstractive text summarization has been intensively studied in recent literature. To generate summary tokens, most architectures take the encoder-decoder approach BIBREF8. BIBREF9 first introduces an attention-based seq2seq model to the abstractive sentence summarization task. However, its output summary degenerates as document length increases, and out-of-vocabulary (OOV) words cannot be efficiently handled. To tackle these challenges, BIBREF4 proposes a pointer-generator network that can both produce words from the vocabulary via a generator and copy words from the source article via a pointer. BIBREF10 utilizes reinforcement learning to improve the result. BIBREF11 uses a content selector to over-determine phrases in source documents that helps constrain the model to likely phrases. BIBREF12 adds Gaussian focal bias and a salience-selection network to the transformer encoder-decoder structure BIBREF13 for abstractive summarization. BIBREF14 randomly reshuffles the sentences in news articles to reduce the effect of lead bias in extractive summarization.\n\nRelated work ::: Pretraining\nIn recent years, pretraining language models have proved to be quite helpful in NLP tasks. The state-of-the-art pretrained models include ELMo BIBREF15, GPT BIBREF7, BERT BIBREF6 and UniLM BIBREF16. Built upon large-scale corpora, these pretrained models learn effective representations for various semantic structures and linguistic relationships. As a result, pretrained models have been widely used with considerable success in applications such as question answering BIBREF17, sentiment analysis BIBREF15 and passage reranking BIBREF18. Furthermore, UniLM BIBREF16 leverages its sequence-to-sequence capability for abstractive summarization; the BERT model has been employed as an encoder in BERTSUM BIBREF19 for extractive/abstractive summarization.\nCompared to our work, UniLM BIBREF16 is a general language model framework and does not take advantage of the special semantic structure of news articles. Similarly, BERTSUM BIBREF19 directly copies the pretrained BERT structure into its encoder and finetunes on labelled data instead of pretraining with the large quantity of unlabeled news corpus available. Recently, PEGASUS BIBREF20 leverages a similar idea of summarization pretraining, but they require finetuning with data from target domains, whereas our model has a remarkable performance without any finetuning.\n\nModel\nIn this section, we introduce our abstractive summarization model, which has a transformer-based encoder-decoder structure. We first formulate the supervised summarization problem and then present the network architecture.\n\nModel ::: Problem formulation\nWe formalize the problem of supervised abstractive summarization as follows. The input consists of $a$ pairs of articles and summaries: $\\lbrace (X_1, Y_1), (X_2, Y_2), ..., (X_a, Y_a)\\rbrace $. Each article and summary are tokenized: $X_i=(x_1,...,x_{L_i})$ and $Y_i=(y_1,...,y_{N_i})$. In abstractive summarization, the summary tokens need not be from the article. For simplicity, we will drop the data index subscript. The goal of the system is to generate summary $Y=(y_1,...,y_m)$ given the transcript $X=\\lbrace x_1, ..., x_n\\rbrace $.\n\nModel ::: Network Structure ::: Encoder\nThe encoder maps each token into a fixed-length vector using a trainable dictionary $\\mathcal {D}$ randomly initialized using a normal distribution with zero mean and a standard deviation of 0.02. Each transformer block conducts multi-head self-attention. And we use sinusoidal positional embedding in order to process arbitrarily long input. In the end, the output of the encoder is a set of contextualized vectors:\n\nExperiments ::: Implementation Details\nWe use SentencePiece BIBREF24 for tokenization, which segments any sentence into subwords. We train the SentencePiece model on pretrained data to generate a vocabulary of size 32K and of dimension 720. The vocabulary stays fixed during pretraining and finetuning.\nPretraining. We collect three years of online news articles from June 2016 to June 2019. We filter out articles overlapping with the evaluation data on media domain and time range. We then conduct several data cleaning strategies.\nFirst, many news articles begin with reporter names, media agencies, dates or other contents irrelevant to the content, e.g. “New York (CNN) –”, “Jones Smith, May 10th, 2018:”. We therefore apply simple regular expressions to remove these prefixes.\nSecond, to ensure that the summary is concise and the article contains enough salient information, we only keep articles with 10-150 words in the top three sentences and 150-1200 words in the rest, and that contain at least 6 sentences in total. In this way, we filter out i) articles with excessively long content to reduce memory consumption; ii) very short leading sentences with little information which are unlikely to be a good summary. To encourage the model to generate abstrative summaries, we also remove articles where any of the top three sentences is exactly repeated in the rest of the article.\nThird, we try to remove articles whose top three sentences may not form a relevant summary. For this purpose, we utilize a simple metric: overlapping words. We compute the portion of non-stopping words in the top three sentences that are also in the rest of an article. A higher portion implies that the summary is representative and has a higher chance of being inferred by the model using the rest of the article. To verify, we compute the overlapping ratio of non-stopping words between human-edited summary and the article in CNN/DailyMail dataset, which has a median value of 0.87. Therefore, in pretraining, we keep articles with an overlapping word ratio higher than 0.65.\nThese filters rule out around 95% of the raw data and we end up with 21.4M news articles, 12,000 of which are randomly sampled for validation.\nWe pretrain the model for 10 epochs and evaluate its performance on the validation set at the end of each epoch. The model with the highest ROUGE-L score is selected.\nDuring pretraining, we use a dropout rate of 0.3 for all inputs to transformer layers. The batch size is 1,920. We use RAdam BIBREF25 as the optimizer, with a learning rate of $10^{-4}$. Also, due to the different numerical scales of the positional embedding and initialized sentence piece embeddings, we divide the positional embedding by 100 before feeding it into the transformer. The beam width is set to 5 during inference.\nFinetuning. During finetuning, we keep the optimizer, learning rate and dropout rate unchanged as in pretraining. The batch size is 32 for all datasets. We pick the model with the highest ROUGE-L score on the validation set and report its performance on the test set. Our strategy of Pretraining with unlabeled Lead-3 summaries is called PL. We denote the pretrained model with finetuning on target datasets as PL-FT. The model with only pretraining and no finetuning is denoted as PL-NoFT, which is the same model for all datasets.\n\nExperiments ::: Baseline\nTo compare with our model, we select a number of strong summarization models as baseline systems. $\\textsc {Lead-X}$ uses the top $X$ sentences as a summary BIBREF19. The value of $X$ is 3 for NYT and CNN/DailyMail and 1 for XSum to accommodate the nature of summary length. $\\textsc {PTGen}$ BIBREF4 is the pointer-generator network. $\\textsc {DRM}$ BIBREF10 leverages deep reinforcement learning for summarization. $\\textsc {TConvS2S}$ BIBREF2 is based on convolutional neural networks. $\\textsc {BottomUp}$ BIBREF11 uses a bottom-up approach to generate summarization. ABS BIBREF26 uses neural attention for summary generation. DRGD BIBREF27 is based on a deep recurrent generative decoder. To compare with our pretrain-only model, we include several unsupervised abstractive baselines: SEQ$^3$ BIBREF28 employs the reconstruction loss and topic loss for summarization. BottleSum BIBREF23 leverages unsupervised extractive and self-supervised abstractive methods. GPT-2 BIBREF7 is a large-scaled pretrained language model which can be directly used to generate summaries.\n\nExperiments ::: Abstractiveness Analysis\nWe measure the abstractiveness of our model via the ratio of novel n-grams in summaries, i.e. the percentage of n-grams in the summary that are not present in the article. fig:novel shows this ratio in summaries from reference and generated by PL-NoFT and PL-FT in NYT dataset. Both PL-NoFT and PL-FT yield more novel 1-grams in summary than the reference. And PL-NoFT has similar novelty ratio with the reference in other n-gram categories. Also, we observe that the novelty ratio drops after finetuning. We attribute this to the strong lead bias in the NYT dataset which affects models trained on it.\n\nConclusions\nIn this paper, we propose a simple and effective pretraining method for news summarization. By employing the leading sentences from a news article as its target summary, we turn the problematic lead bias for news summarization in our favor. Based on this strategy, we conduct pretraining for abstractive summarization in a large-scale news corpus. We conduct thorough empirical tests on five benchmark news summarization datasets, including both automatic and human evaluations. Results show that the same pretrained model without any finetuning can achieve state-of-the-art results among unsupervised methods over various news summarization datasets. And finetuning on target domains can further improve the model's performance. We argue that this pretraining method can be applied in more scenarios where structural bias exists.\n\nFigure 1: Using Lead-3 summary as target in pretraining.\n\nFigure 2: Ratio of novel n-grams in summaries from reference, PL-NoFT and PL-FT models in NYT test set.\n\nTable 2: ROUGE F1 results on XSum test set.\n\nTable 3: ROUGE F1 results on CNN/DailyMail test set.\n\nTable 4: Scoring criteria for human evaluation of summaries.\n\nTable 5: Average and standard deviations of human evaluation scores for summaries on CNN/DailyMail test set. Scores range from 1 to 5 with 5 being perfect. Each summary is judged by 3 human evaluators. PL-FT’s result is statistically significant compared with pointer-generator network with coverage with a p-value less than 10−7.\n\nInquiry: What did they pretrain the model on?", "role": "user" }, { "content": "{\"answer\": [\"hree years of online news articles from June 2016 to June 2019\"], \"evidence\": [\"Pretraining. We collect three years of online news articles from June 2016 to June 2019. We filter out articles overlapping with the evaluation data on media domain and time range. We then conduct several data cleaning strategies.\"]}", "role": "assistant" } ]

[ { "content": "Read the provided biomedical research paper and create a concise abstract. Ensure the abstract captures the main points of the paper.\n\nFull Paper:\nalthough cataract surgery is highly effective and relatively safe , owing to the enormous numbers , even uncommon surgical complications could be potentially harmful for many patients .\nendophthalmitis is one of the most serious complications of cataract surgery , affecting around 0.1% of the cases , and often resulting in severe visual impairment .\nthis complication often occurs sporadically , and in such situations , the common source of infection may be due to the conjunctival flora of the patient .\nthe major pathogens are coagulase - negative staphylococci ( 70% ) , staphylococcus aureus ( 10% ) , streptococci ( 9% ) , other gram - positive cocci , including enterococci and mixed bacteria ( 5% ) , and gram - negative bacilli ( 6% ) . the fact that gram - positive bacteria cause > 95% of the cases reflect the usual pathogenesis , i.e. contamination of the aqueous humor with skin bacteria flora during surgery . however , unusual germs causing the infection are sometimes isolated and should be suspected in cases with a non - typical evolution .\na 65 year - old female patient was urgently admitted to a hospital emergency room 48 hours after a cataract surgery , referring to red eye and vision decrease in the operated eye . visual acuity on\nthe initial exam was hands movement in the right eye and 20/40 in the left eye .\nophthalmological examinations showed conjunctival injection in the right eye , hypopyon , 3 + cells in anterior chamber and severe vitreitis with no fundus view .\nshe was hospitalized and 23 g pars plana vitrectomy was immediately performed and a vitreous biopsy was taken for culture .\nadditionally , she was treated with topical ocular applications of fortified tobramycin ( 15 mg / ml ) and ceftazidime ( 50 mg / ml ) every hour and with intravitreal injections of vancomycin ( 1 mg/0.1 ml ) and ceftazidime ( 2 mg/0.1 ml ) after the vitrectomy and 2 and 4 days after operation . intravenous antibiotics ( 1 g of vancomycin ) were also administered twice a day , 500 mg ceftazidime/12 hours , as well as the administration of systemic corticosteroid after 24 hours ( oral prednisone 1 mg / kg / day ) .\nbecause of the bad evolution after 36 hours , systemic treatment was then empirically changed to linezolid 600 mg and moxifloxacin 400 mg , twice a day .\nvitreous was cultured in blood agar , chocolate agar ( incubated 48h in microaerophilic conditions ) and thioglycollate broth ; and was isolated in an all media pure culture of gram - positive cocci , forming white colonies and catalase positive , which was identified by the microbiology laboratory as rothia mucilaginosa through matrix - assisted laser desorption / ionization - time of flight ( maldi - tof , bruker daltonics , bruker corporation , billerica , ma , usa ) .\nantimicrobial sensitivity test was done by the kirby - bauer method , being susceptible to all antibiotics tested ( penicillins , cephalosporins , fluoroquinolones , erythromycin , clindamycin , and tetracycline ) .\nalthough this organism was susceptible to the empirical antibiotics used , a bad clinical response was observed with increasing hypopyon . during the next days ,\npain , conjunctival injection , hypopyon and anterior chamber reaction worsened and a large vitreous abscess was observed .\nr. mucilaginosa , formerly called stomatococcus mucilaginosus , is part of the normal flora of the upper respiratory tract and oral cavity .\nit was reclassified into a new genus belonging to the family micrococcaceae in 2000 , based on 16s rrna sequencing .\ngram staining reveals non - spore - forming , encapsulated gram - positive cocci that can appear in pairs , tetrads , or irregular clusters .\nit is a facultative anaerobic bacterium , which grows well on most nonselective media and in standard blood culture systems . on sheep blood and chocolate agar , the bacterium forms clear to gray / white , non - hemolytic , mucoid or sticky colonies , which adhere to the agar surface\n. it can be difficult to distinguish it from coagulase - negative staphylococci , micrococci , and streptococci based on the catalase test result .\nits inability to grow in 6.5% sodium chloride and its ability to hydrolyze gelatin and esculin distinguish it from species of staphylococcus , micrococcus , and enterococcus genera .\nidentification from automatic methods should correlate with phenotypic identification ; otherwise , genetic sequencing may be required to identify this organism .\nrecently , infections in immunocompetent hosts have been described in various organ systems , including patients with pneumonia , bacteremia , and septic arthritis .\nit has been reported in two cases of eye infection , a postoperative endophthalmitis in a 91-year - old male and a keratitis in vitamin a deficiency .\nthe known risk factors for this infection are immunosuppression , parenteral drugs , alcoholism , diabetes , neoplastic and valvular disease , but our patient did not present any of these .\nnone of the reported patients with ocular infections caused by r mucilaginosa had these risk factors , so it is possible that in - ocular infections could be irrelevant . in this sense , the source of the infection in our case remains unknown . as mentioned , r. mucilaginosa is part of the normal flora of the upper respiratory tract and oral cavity but has not been isolated in normal conjunctival flora . in our opinion self - contamination of\nthe patient could be the origin of the infection , but contamination of eye drops used in the perioperative period with r. mucilaginosa is also a possibility .\nunfortunately , a search of r. mucilaginosa in the eye drops was not performed when the patient was admitted in the hospital .\nit would have been of interest to demonstrate the origin of the contamination . however , it was reported that r. mucilaginosa is able to colonize a foreign body as a vascular catheter .\nthe organism s ability to produce a biofilm , similar to other gram - positive bacteria , is believed to be a key pathogenic mechanism .\nthe physical protective layer provided by the biofilm presumably facilitates adhesion of the organisms to devices and renders them relatively refractory to medical therapy .\nto our knowledge , this is the second case report of r. mucilaginosa endophthalmitis after a cataract surgery and the first after phacoemulsification .\nit is increasingly recognized as an emerging opportunistic pathogen associated with eye infections and it may be difficult to identify .\nphysicians should be aware of this organism when treating nonresponding patients infected with gram - positive bacteria in ocular infections .", "role": "user" }, { "content": "we aimed at reporting the first case of rapidly progressive acute postoperative endophthalmitis after phacoemulsification cataract surgery in an immunocompetent patient caused by rothia mucilaginosa . \n an immunocompetent patient manifested endophthalmitis signs 48 hours after an uncomplicated cataract surgery by phacoemulsification . \n a bacteria of the family micrococcaceae was cultured in the vitreous biopsy , namely r. mucilaginosa . \n the patient did not show a favorable clinical response after vitrectomy and systemic , intravitreal , and topical fortified antibiotics . \n the patient s eye was very painful , and consequently , it deemed necessary to perform an evisceration . \n r. mucilaginosa may be an aggressive etiologic agent for postoperative endophthalmitis . although the isolated r. mucilaginosa was susceptible to empirical treatment , it was impossible to control the infection with standard treatment , probably due to its ability to create a biofilm around the intraocular lens .", "role": "assistant" } ]

[ { "content": "Analyze the provided paragraph from a scientific document. Your goal is to identify and extract relevant entities.\n\nFormat your findings as a JSON object, where each key represents a category of entities, and the corresponding value is a list of entities identified in that category. If no entities are found for a category, return an empty list.\n\nFocus on precision and ensure that the output is strictly in JSON format.\n\nDocument:\n\nSmart Thin Hydrogel Coatings Harnessing Hydrophobicity and Topography to Capture and Release Cancer Cells Smart thin hydrogel coatings are fabricated to capture and release targeted cancer cells by simultaneously tuning surface hydrophobicity and topography. At physiological temperature, the targeted cancer cells are capture d on the hydrophobic and wrinkled coating surface. At room temperature, the captured cells are released from the hydrophilic and smooth coating surface.", "role": "user" }, { "content": "{\"AnatomicalStructure\": [\"cancer cells\", \"Cancer Cells\", \"cells\"], \"Bacterium\": [], \"BiologicFunction\": [], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"Smart thin hydrogel coatings\", \"Smart Thin Hydrogel Coatings\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [], \"Food\": [], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"wrinkled coating surface\", \"hydrophilic\", \"coating surface\", \"surface\"], \"Virus\": []}", "role": "assistant" } ]

[ { "content": "Craft a cohesive chapter for a literature review using the abstracts provided. Focus on the chapter's theme, weaving together insights and findings from the abstracts. Highlight key points and note any research gaps.\nLiterature Review Title: A review of parameters and heuristics for guiding metabolic pathfinding \nChapter Title: Topology \n1. Abstract of Cited Paper (BIB001): Abstract This article presents a new graph-based algorithm for identifying branched metabolic pathways in multi-genome scale metabolic data. The term branched is used to refer to metabolic pathways between compounds that consist of multiple pathways that interact biochemically. A branched pathway may produce a target compound through a combination of linear pathways that split compounds into smaller ones, work in parallel with many compounds, and join compounds into larger ones. While branched metabolic pathways predominate in metabolic networks, most previous work has focused on identifying linear metabolic pathways. The ability to automatically identify branched pathways is important in applications that require a deeper understanding of metabolism, such as metabolic engineering and drug target identification. The algorithm presented in this article utilizes explicit atom tracking to identify linear metabolic pathways and then merges them together into branched metabolic pathways. We provide results on ...\n\nReview Chapter:", "role": "user" }, { "content": "Almost all pathfinding algorithms are limited to producing linear pathways with a few exceptions BIB001 BIB002 . Branched pathways and cycles represent different topologies of metabolic networks that are of interest to metabolic engineering because the resulting condensation or recycling of constituent material can potentially improve the theoretical yield for a pathway. Though linear pathways are sufficient in most cases, the capability of identifying more complex and efficient pathways would be desirable.", "role": "assistant" } ]

[ { "content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nA central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks.\nTwo distinct research paradigms have studied this question.\nMeta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the set of tasks are available together as a batch.\nIn contrast, online (regret based) learning considers a sequential setting in which problems are revealed one after the other, but conventionally train only a single model without any task-specific adaptation.\nThis work introduces an online meta-learning setting, which merges ideas from both the aforementioned paradigms to better capture the spirit and practice of continual lifelong learning.\nWe propose the follow the meta leader (FTML) algorithm which extends the MAML algorithm to this setting.\nTheoretically, this work provides an O(logT) regret guarantee for the FTML algorithm.\nOur experimental evaluation on three different large-scale tasks suggest that the proposed algorithm significantly outperforms alternatives based on traditional online learning approaches.\nTwo distinct research paradigms have studied how prior tasks or experiences can be used by an agent to inform future learning.\nMeta-learning (Schmidhuber, 1987) casts this as the problem of learning to learn, where past experience is used to acquire a prior over model parameters or a learning procedure.\nSuch an approach, where we draw upon related past tasks and form associated priors, is particularly crucial to effectively learn when data is scarce or expensive for each task.\nHowever, meta-learning typically studies a setting where a set of meta-training tasks are made available together upfront as a batch.\nIn contrast, online learning (Hannan, 1957 ) considers a sequential setting where tasks are revealed one after another, but aims to attain zero-shot generalization without any task-specific adaptation.\nWe argue that neither setting is ideal for studying continual lifelong learning.\nMetalearning deals with learning to learn, but neglects the sequential and non-stationary nature of the world.\nOnline learning offers an appealing theoretical framework, but does not generally consider how past experience can accelerate adaptation to a new task.\nIn this work, we motivate and present the online meta-learning problem setting, where the agent simultaneously uses past experiences in a sequential setting to learn good priors, and also adapt quickly to the current task at hand.Our contributions: In this work, we first formulate the online meta-learning problem setting.\nSubsequently, we present the follow the meta-leader (FTML) algorithm which extends MAML (Finn et al., 2017) to this setting.\nFTML is analogous to follow the leader in online learning.\nWe analyze FTML and show that it enjoys a O(log T ) regret guarantee when competing with the best metalearner in hindsight.\nIn this endeavor, we also provide the first set of results (under any assumptions) where MAML-like objective functions can be provably and efficiently optimized.\nWe also develop a practical form of FTML that can be used effectively with deep neural networks on large scale tasks, and show that it significantly outperforms prior methods in terms of learning efficiency on vision-based sequential learning problems with the MNIST, CIFAR, and PASCAL 3D+ datasets.\nIn this paper, we introduced the online meta-learning problem statement, with the aim of connecting the fields of meta-learning and online learning.\nOnline meta-learning provides, in some sense, a more natural perspective on the ideal real-world learning procedure.\nAn intelligent agent interacting with a constantly changing environment should utilize streaming experience to both master the task at hand, and become more proficient at learning new tasks in the future.\nWe summarize prior work related to our setting in Appendix D. For the online meta-learning setting, we proposed the FTML algorithm and showed that it enjoys logarithmic regret.\nWe then illustrated how FTML can be adapted to a practical algorithm.\nOur experimental evaluations demonstrated that the proposed practical variant outperforms prior methods.", "role": "user" }, { "content": "We introduce the online meta learning problem setting to better capture the spirit and practice of continual lifelong learning.", "role": "assistant" } ]

[ { "content": "Explore the following research question and associated terms. Identify the most suitable dataset from the list provided. Use the dataset descriptions to guide your choice.\n\nInquiry: Hierarchical representations for object recognition.\n\nKeywords: object recognition\n\nDataset Information:\nDrive&Act: The Drive&Act dataset is a state of the art multi modal benchmark for driver behavior recognition. The dataset includes 3D skeletons in addition to frame-wise hierarchical labels of 9.6 Million frames captured by 6 different views and 3 modalities (RGB, IR and depth).\nHow2QA: To collect How2QA for video QA task, the same set of selected video clips are presented to another group of AMT workers for multichoice QA annotation. Each worker is assigned with one video segment and asked to write one question with four answer candidates (one correctand three distractors).\nCaltech-101: The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories.\nPartNet: PartNet is a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. The dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories.\n\nAvailable Datasets: A: Drive&Act B: How2QA C: Caltech-101 D: PartNet", "role": "user" }, { "content": "Caltech-101", "role": "assistant" } ]

[ { "content": "Analyze the following collection of medical RCT summaries. Your goal is to craft a concise synthesis of the findings. Focus on the core insights and present them succinctly. Only include the synthesis in your response. Below are the RCT summaries:\n\n\n\nReport 1:\nTitle: Perceptions of terminally ill patients and family members regarding home and hospice as places of care at the end of life.\nSummary: To enable dem and -based palliative care , it is important to know the perceptions of terminally ill patients and their family members regarding home and hospice as places of care at the end of life . Eight women and five men suffering from cancer and with a life expectancy of 3 months or less were interviewed . In each case one of the family members was also interviewed . Four patients spent their last phase of life at home , nine in a hospice . This paper provides further insight in the patient perspective in palliative care . The results reveal that a cohabiting partner seems an important prerequisite for terminally ill patients to stay at home . For spouses it is an obvious choice to facilitate the patients ' stay at home , even when it becomes too dem and ing , something not discussed between spouse and patient . When sufficient care at home seems impossible and the negotiation between patients and family members results in the opinion that living at home is no longer an option , it is decided that the patient moves to a hospice . The choice for the specific setting of the patients ' new residence seems to be r and om ; one possibility is pointed out to them and seems appropriate\n\n\nReport 2:\nTitle: Dignity Through Integrated Symptom Management: Lessons From the Breathlessness Support Service.\nSummary: CONTEXT Dignity is poorly conceptualized and little empirically explored in end-of-life care . A qualitative evaluation of a service offering integrated palliative and respiratory care for patients with advanced disease and refractory breathlessness uncovered an unexpected outcome , it enhanced patients ' dignity . OBJECTIVES To analyze what constitutes dignity for people suffering from refractory breathlessness with advanced disease , and its implication s for the concept of dignity . METHODS Qualitative study of cross-sectional interviews with 20 patients as part of a Phase III evaluation of a r and omized controlled fast-track trial . The interviews were transcribed verbatim , imported into NVivo , and analyzed through constant comparison . The findings were compared with Chochinov et al. 's dignity model . The model was adapted with the themes and subthemes specific to patients suffering from breathlessness . RESULTS The findings of this study underscore the applicability of the conceptual model of dignity for patients with breathlessness . There were many similarities in themes and subthemes . Differences specifically relevant for patients suffering from severe breathlessness were as follows : 1 ) physical distress and psychological mechanisms are interlinked with the disability and dependence breathlessness causes , in the illness-related concerns , 2 ) stigma is an important component of the social dignity inventory , 3 ) conditions and perspectives need to be present to practice self-care in the dignity-conserving repertoire . CONCLUSION Dignity is an integrated concept and can be affected by influences from other areas such as illness-related concerns . The intervention shows that targeting the symptom holistically and equipping patients with the means for self-care realized the outcome of dignity", "role": "user" }, { "content": "Conclusions : The Dynamic Reciprocity of Dignity model highlights the importance of adopting a systemic lens to address dignity-related needs and concerns at the end of life , while providing insights on how compassionate care and self-compassion can serve as the foundation of dignified care , which in turn serve as a buffer against patients ’ existential suffering as well as caregivers ’ burnout and fatigue .", "role": "assistant" } ]

[ { "content": "Examine the provided biomedical abstract. Identify and list entities based on the specified categories: [\"Brand\", \"Drug\", \"DrugGroup\", \"UnapprovedDrug\"].\n\nFormat your findings as a JSON object: {\"Brand\": [\"Aspirin\", ...], \"DrugGroup\": [\"Salicylate\", ...], \"Drug\": [\"Phenobarbital\", ...], \"UnapprovedDrug\": [\"Heroin\", ...]}. Each key represents an entity type, and the corresponding value is a list of entities. If no entities are found for a type, use an empty list [].\n\nFocus solely on producing the JSON object.\n\nSource Text:\n\nCYP450 Metabolized Drugs Results from in vitro and in vivo studies suggest that enfuvirtide is unlikely to have significant drug interactions with concomitantly administered drugs metabolized by CYP450 enzymes. Antiretroviral Agents: No drug interactions with other antiretroviral medications have been identified that would warrant alteration of either the enfuvirtide dose or the dose of the other antiretroviral medication.", "role": "user" }, { "content": "{\"Brand\": [], \"Drug\": [\"enfuvirtide\"], \"DrugGroup\": [\"Antiretroviral Agents\", \"antiretroviral medications\", \"antiretroviral medication\"], \"UnapprovedDrug\": []}", "role": "assistant" } ]

[ { "content": "Given the following biomedical passages, answer the question succinctly. Ensure your response is precise and limited to the answer only.\n\nQuestion: Which retinal dystrophy related gene is targeted by the AAV2-hRPE65v2 drug?\n\nPassages: Voretigene neparvovec gene replacement improved functional vision in RPE65-mediated inherited retinal dystrophy previously medically untreatable.\nIn this open-label, randomised, controlled phase 3 trial done at two sites in the USA, individuals aged 3 years or older with, in each eye, best corrected visual acuity of 20/60 or worse, or visual field less than 20 degrees in any meridian, or both, with confirmed genetic diagnosis of biallelic RPE65 mutations, sufficient viable retina, and ability to perform standardised multi-luminance mobility testing (MLMT) within the luminance range evaluated, were eligible.\nEfficacy and safety of voretigene neparvovec (AAV2-hRPE65v2) in patients with RPE65-mediated inherited retinal dystrophy: a randomised, controlled, open-label, phase 3 trial.", "role": "user" }, { "content": "RPE65", "role": "assistant" } ]

[ { "content": "Analyze the given text to identify specific entities. Focus on extracting relevant data.\n\nProvide your findings in JSON format. Each category should list the entities found.\n\nText:\n\nCyclic denaturation and renaturation of double-stranded DNA by redox-state switching of DNA intercalators. Hybridization of complementary nucleic acid strands is fundamental to nearly all molecular bioanalytical methods ranging from polymerase chain reaction and DNA biosensors to next generation sequencing. For nucleic acid amplification methods, controlled DNA denaturation and renaturation is particularly essential and achieved by cycling elevated temperatures. Although this is by far the most used technique, the management of rapid temperature changes requires bulky instrumentation and intense power supply. These factors so far precluded the development of true point-of-care tests for molecular diagnostics. To overcome this limitation we explored the possibility of using electrochemical means to control reversible DNA hybridization by using the electroactive intercalator daunomycin (DM). We show that redox-state switching of DM altered its properties from DNA binding to nonbinding, under otherwise constant conditions, and thus altered the thermodynamic stability of duplex DNA. The operational principle was demonstrated using complementary synthetic 20mer and 40mer DNA oligonucleotides. Absorbance-based melting curve analysis revealed significantly higher melting temperatures for DNA in the presence of oxidized compared to chemically reduced DM. This difference was exploited to drive cyclic electrochemically controlled denaturation and renaturation. Analysis with in situ UV-vis and circular dichroism spectroelectrochemistry, as two independent techniques, indicated that up to 80% of the DNA was reversibly hybridized. This remarkable demonstration of electrochemical control of five cycles of DNA denaturation and renaturation, under otherwise constant conditions, could have wide-ranging implications for the future development of miniaturized analytical systems for molecular diagnostics and beyond.", "role": "user" }, { "content": "{\"Chemical\": [\"daunomycin\"]}", "role": "assistant" } ]

[ { "content": "Review the provided sections from a computer science paper and distill the primary contribution into a single sentence. Provide only the summary sentence.\n\nSections:\n\nGenerative networks are promising models for specifying visual transformations.\nUnfortunately, certification of generative models is challenging as one needs to capture sufficient non-convexity so to produce precise bounds on the output.\nExisting verification methods either fail to scale to generative networks or do not capture enough non-convexity.\nIn this work, we present a new verifier, called ApproxLine, that can certify non-trivial properties of generative networks.\nApproxLine performs both deterministic and probabilistic abstract interpretation and captures infinite sets of outputs of generative networks.\nWe show that ApproxLine can verify interesting interpolations in the network's latent space.\nNeural networks are becoming increasingly used across a wide range of applications, including facial recognition and autonomous driving.\nSo far, certification of their behavior has remained predominantly focused on uniform classification of norm-bounded balls Katz et al., 2017; Wong et al., 2018; Gowal et al., 2018; Singh et al., 2018; Raghunathan et al., 2018; Tjeng et al., 2017; Dvijotham et al., 2018b; Salman et al., 2019; Dvijotham et al., 2018c; , which aim to capture invisible perturbations.\nHowever, a system's safety can also depend on its behavior on visible transformations.\nFor these reasons, investigation of techniques to certify more complex specifications has started to take place (Liu et al., 2019; Dvijotham et al., 2018a; Singh et al., 2019) .\nOf particular interest is the work of Sotoudeh & Thakur (2019) which shows that if the inputs of a network are restricted to a line segment, the verification problem can sometimes be efficiently solved exactly.\nThe resulting method has been used to certify non-norm-bounded properties of ACAS Xu networks (Julian et al., 2018) and improve Integrated Gradients (Sundararajan et al., 2017) .\nThis work We extend this technique in two key ways:\n(i) we demonstrate how to soundly approximate EXACTLINE, handling significantly larger networks faster than even methods based on sampling can (a form of deterministic abstract interpretation), and\n(ii) we use this approximation to provide guaranteed bounds on the probabilities of outputs given a distribution over the inputs (a form of probabilistic abstract interpretation).\nWe believe this is the first time probabilistic abstract interpretation has been applied in the context of neural networks.\nBased on these techniques, we also provide the first system capable of certifying interesting properties of generative networks.\nIn this paper we presented a highly scalable non-convex relaxation to verify neural network properties where inputs are restricted to a line segment.\nOur results show that our method is faster and more precise than previous methods for the same networks, including sampling.\nThis speed and precision permitted us to verify properties based on interesting visual transformations induced by generative networks for the first time, including probabilistic properties.", "role": "user" }, { "content": "We verify deterministic and probabilistic properties of neural networks using non-convex relaxations over visible transformations specified by generative models", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: The effects of COVID-19 on the lungs are well-known. As the COVID-19 pandemic continues, more information is becoming available about the role the virus, called SARS-CoV-2, has on the heart.\n\nResearch Abstract:\nThe presence of cardiovascular co-morbidities and the known effects of coronaviruses on the cardiovascular system have called attention to the potential implications for patients with cardiovascular risk factors.\nThis evidence-based viewpoint will address two questions: (a) are individuals with underlying cardiovascular risk factors (e.g. high blood pressure or diabetes) or overt disease (e.g. coronary heart disease, heart failure, kidney disease) more likely to develop severe Covid-19 and to die than those without underlying conditions?\n(b) does the regular use of angiotensin-converting enzyme inhibitors (ACE-i) or angiotensin-receptor blockers (ARB) make patients more likely to get infected and to die of Covid-19?\nWith a necessary cautionary note that the evidence around the links between Covid-19 and cardiovascular disease is accruing at a fast pace, to date we can conclude that: (a) the greater susceptibility of individuals with underlying cardiovascular conditions to develop more severe Covid-19 with higher mortality rate is likely to be confounded, in part, by age and the type of co-morbidities.\nPatients with heart failure or chronic kidney disease might show an excess risk; (b) neither ACE-i nor ARB are associated with greater risk of SARS-Cov2 infection, or severity or risk of death in patients with Covid-19.\nPatients on these drugs should not stop them, unless under strict medical supervision and with the addition of a suitable replacement medicine.", "role": "user" }, { "content": "{\"verdict\": \"NEI\", \"evidence\": []}", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\n[ Cooperative study of surgical adjuvant chemotherapy of colorectal carcinoma ( second study ) : 3-year survival after surgery of non-curatively resected patients . Cooperative Study Group of Surgical Adjuvant Chemotherapy of Colorectal Cancer in Japan ] . A prospective randomized study was carried out to evaluate the efficacy of surgical adjuvant chemotherapy for non-curatively resected colorectal carcinoma patients as a collaborative study at 428 institutes in Japan from Jan. , 1984 to Dec. , 1985 . A total of 1,138 patients were entered in this study . All patients were divided according to disease location ( colon or rectum ) and received one of two chemotherapeutic regimens after surgery ( Regimen C : MMC 12 mg/m2 i.v . at operation day and 6 mg/m2 in every 2 months +UFT 600 mg/day p.o. , D : the same dose of MMC + UFT 400 mg/day p.o . ) randomly . 556 cases ( colon carcinoma regimen C : 148 , D : 185 cases , rectal carcinoma regimen C : 94 , D : 129 cases ) were evaluable at this presentation . Three-year-survival rate of histologically confirmed non-curatively resected colon carcinoma patients was higher in the group receiving regimen C than in regimen D. But no significant difference was found among the other groups .", "role": "user" }, { "content": "{\"Intervention\": [\"regimen C\", \"( Regimen C : MMC\", \"surgical adjuvant chemotherapy\", \"+UFT\", \"chemotherapeutic regimens\", \"regimen D.\", \"D : the same dose of MMC + UFT 400 mg/day p.o . ) randomly .\"], \"Outcome\": [\"Three-year-survival rate\"], \"Participant\": [\"non-curatively resected colorectal carcinoma patients\", \"556\", \"collaborative study\", \"1,138\", \"129\", \"colorectal carcinoma\", \"non-curatively resected\", \"185\", \"148\", \"94\"]}", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: ProxECAT: Proxy External Controls Association Test. A new case-control gene region association test using allele frequencies from public controls\nContent:\nAbstract:\nA primary goal of the recent investment in sequencing is to detect novel genetic associations in health and disease improving the development of treatments and playing a critical role in precision medicine. While this investment has resulted in an enormous total number of sequenced genomes, individual studies of complex traits and diseases are often smaller and underpowered to detect rare variant genetic associations. Existing genetic resources such as the Exome Aggregation Consortium( >60, 000 exomes) and the Genome Aggregation Database( ~140, 000 sequenced samples) have the potential to be used as controls in these studies. Fully utilizing these and other existing sequencing resources may increase power and could be especially useful in studies where resources to sequence additional samples are limited. However, to date, these large, publicly available genetic resources remain underutilized, or even misused, in large part due to the lack of statistical methods that can appropriately use this summary level data. Here, we present a new method to incorporate external controls in case-control analysis called ProxECAT( Proxy External Controls Association Test). ProxECAT estimates enrichment of rare variants within a gene region using internally sequenced cases and external controls. We evaluated ProxECAT in simulations and empirical analyses of obesity cases using both low-depth of coverage( 7x) whole-genome sequenced controls and ExAC as controls. We find that ProxECAT maintains the expected type I error rate with increased power as the number of external controls increases. With an accompanying R package, ProxECAT enables the use of publicly available allele frequencies as external controls in case-control analysis.\nIntroduction:\nRecent investments have produced sequence data on millions of people with the number of sequenced individuals continuing to grow. Although large sequencing studies, such as the Trans-Omics for Precision Medicine( TopMed) through the National Heart, Lung, and Blood Institute, exist, most sequencing data is gathered and processed in much smaller units of hundreds to thousands of samples. This is especially true in the study of diseases that are not very common but still likely to have a complex or oligogenic genetic architecture. These silos of data mean that most rare-variant association studies of uncommon, complex diseases are underpowered. Zuk et al. suggest that sample sizes in the tens, and perhaps hundreds of thousands are required for adequate power[1]. In addition to increasing the sample size of future studies, fully leveraging existing sequencing resources could increase power considerably and could be vital in scenarios where resources to sequence more samples are limited. Existing genetic resources such as the Exome Aggregation Consortium( ExAC; >60, 000 exomes)[2] and more recently, the Genome Aggregation Database( gnomAD; ~140, 000 sequenced samples) have the potential to be used as controls in studies of complex diseases. However, to date, these large, publicly available genetic resources remain underutilized, or even misused[3], in large part due to the lack of statistical methods that can appropriately use this summary level data in complex disease studies. In particular, there is a large potential for bias caused by differences in sequencing technology, processing, and read depth[3]. Recently, Lee et al[4] developed iECAT, a method to incorporate publicly available allele frequencies from controls into an existing, unbiased, but underpowered case-control analysis. They found that iECAT controls for bias while increasing power to detect association to a genetic region and can be applied to both single variant analysis and gene region analysis using a SKAT-O framework[5]. iECAT cannot be applied to very rare variants such as singletons or doubletons and requires a set of controls that were sequenced and variant-called in parallel to the cases( i. e. internal controls). Additionally, the type I error rate for iECAT increases as the size of the internal control sample set decreases relative to the internal cases. Thus, there is still the need for methods that can incorporate very rare variants and external controls without the explicit need for large internal control samples. Here we present Proxy External Controls Association Test( ProxECAT), a method to estimate enrichment of rare variants within a gene region using internal cases and external controls. Our method addresses existing gaps such as using singleton and doubleton variants and requiring only external controls. Rare-variant tests in a gene are often limited to variants predicted to have a functional effect on the protein, hence discarding non-functional variants. This can result in greater power[6, 7]. The development of ProxECAT was motivated by the observation that these discarded variants can be used as a proxy for how well variants within a genetic region are sequenced and called within a sample. ProxECAT is both simple and fast, requiring only allele frequency information, and is thus well suited to use publicly available resources such as ExAC and gnomAD. We evaluate ProxECAT in simulations, and empirical analysis of high depth of coverage( 80x) whole-exome sequenced childhood obesity cases( N = 927) using both low-depth of coverage( 7x) whole-genome sequenced controls( N = 3, 621), and ExAC( N = 33, 370). Our method controls the type I error rate in simulations and yields the expected distribution of test statistics in real data settings. Given an accompanying R package, ProxECAT provides a robust and previously unavailable method to use publicly available allele frequencies as external controls in case-control analysis. This increases the utility of existing sequenced datasets to generate hypotheses and further research into the genetic basis of disease.\nDiscussion:\nWe propose a new method, ProxECAT, to test for enrichment of an accumulation of very rare variant alleles in a gene-region using publicly available external allele frequencies. ProxECAT only requires allele frequencies and uses exclusively external controls enabling the use of large, publicly available datasets such as ExAC and gnomAD. Analyses in simulations and using UK10K Cohort and ExAC as control sets for childhood obesity cases show that ProxECAT keeps the type I error rate and expected distribution of test statistics under control despite differences in sequencing technology and processing. Because ProxECAT uses external controls, additional resources can be devoted to sequencing cases. This results in greater power for ProxECAT compared to the case-control LRT test for the same number of internally sequenced individuals. There are several limitations to the method proposed here. First, ProxECAT has a minor, but consistent inflation in the type I error rate. This limitation is easily addressed by using a more conservative significance threshold. Second, ProxECAT cannot currently include covariates such as sex, and ancestry. Thus, internal cases and external controls should be closely matched by ancestry and, as with any association study, findings will need independent replication preferably using a study where cases and controls are sequenced and processed in parallel. Third, the current approach does not enable internal controls to be analyzed along with external controls. While two analyses can be done in parallel and compared, it would be ideal to incorporate internal and external controls into the same statistical test. We are actively working on extensions to address these limitations. It is important to highlight that research utilizing solely external controls is more susceptible to confounding due to known or unknown factors. Thus, any genes identified using ProxECAT or any method that uses only external controls should be carefully followed up in further validation, replication, and functional studies. ProxECAT provides a robust approach to using allele frequencies from existing, publicly available sequencing data enabling case-control analysis when no or limited internal controls exist. ProxECAT uses the insight that readily available genomic information often discarded from analyses( here synonymous variation) can adjust for sizeable confounding due to differences in data generation. In the era of big data, we hope that both this insight and the ProxECAT method will enable additional genetic discoveries and will also motivate future methodological advancements in analyzing data across technologies and platforms.", "role": "user" }, { "content": "Recent investments have produced sequence data on millions of people with the number of sequenced individuals continuing to grow . Although large sequencing studies exist , most sequencing data is gathered and processed in much smaller units of hundreds to thousands of samples . These silos of data result in underpowered studies for rare-variant association of complex diseases . Existing genetic resources such as the Exome Aggregation Consortium ( >60 , 000 exomes ) and the Genome Aggregation Database ( ~140 , 000 sequenced samples ) have the potential to be used as controls in rare variant studies of complex diseases and traits . However , to date , these large , publicly available genetic resources remain underutilized , or even misused , in part due to the high potential for bias caused by differences in sequencing technology and processing . Here we present a new method , Proxy External Controls Association Test ( ProxECAT ) , to integrate sequencing data from different , previously incompatible sources . ProxECAT provides a robust approach to using publicly available sequencing data enabling case-control analysis when no or limited internal controls exist . Further , ProxECAT’s motivating insight , that readily available but often discarded information can be used as a proxy to adjust for differences in data generation , may motivate further method development in other big data technologies and platforms .", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: AKAP200 promotes Notch stability by protecting it from Cbl/lysosome-mediated degradation in Drosophila melanogaster\nContent:\nAbstract:\nAKAP200 is a Drosophila melanogaster member of the “A Kinase Associated Protein” family of scaffolding proteins, known for their role in the spatial and temporal regulation of Protein Kinase A( PKA) in multiple signaling contexts. Here, we demonstrate an unexpected function of AKAP200 in promoting Notch protein stability. In Drosophila, AKAP200 loss-of-function( LOF) mutants show phenotypes that resemble Notch LOF defects, including eye patterning and sensory organ specification defects. Through genetic interactions, we demonstrate that AKAP200 interacts positively with Notch in both the eye and the thorax. We further show that AKAP200 is part of a physical complex with Notch. Biochemical studies reveal that AKAP200 stabilizes endogenous Notch protein, and that it limits ubiquitination of Notch. Specifically, our genetic and biochemical evidence indicates that AKAP200 protects Notch from the E3-ubiquitin ligase Cbl, which targets Notch to the lysosomal pathway. Indeed, we demonstrate that the effect of AKAP200 on Notch levels depends on the lysosome. Interestingly, this function of AKAP200 is fully independent of its role in PKA signaling and independent of its ability to bind PKA. Taken together, our data indicate that AKAP200 is a novel tissue specific posttranslational regulator of Notch, maintaining high Notch protein levels and thus promoting Notch signaling.\nIntroduction:\nSignaling pathways are critically involved throughout embryonic development, as well as adult tissue function and homeostasis. Many of these pathways are highly conserved from invertebrates to humans, and were first discovered in Drosophila melanogaster, making it an ideal model system for identification and analysis of new pathway components. Notch signaling, is one such pathway, and is required for fundamental developmental processes including polarity, cell fate specification, tissue growth, stem cell maintenance, and organ patterning[1–5]. Moreover, misregulation of Notch signaling underlies several human diseases including various cancers highlighting the importance of Notch pathway regulation[1, 3, 6–8]. In Drosophila, Notch signaling is activated by the interaction of the ligands Delta and Serrate with the extracellular domains of the Notch receptor[9]. Ligand binding activates extracellular cleavage of Notch by ADAM/TACE metalloproteases[10], followed by γ-secretase mediated cleavage[11], which releases the Notch intracellular domain( NICD)[12]. The NICD, which is the signal transducing end of the protein, enters the nucleus, forms a complex with the transcription factor Suppressor of Hairless[Su( H)]/CSL and activates target genes[5, 13–15]. The same fundamental elements/mechanisms of the pathway are conserved in mammals[16, 17]. Notch signaling is tempered by endocytosis of the receptor and degradation of NICD and these processes are essential to avoid hyperactivity[18, 19]. Several studies have demonstrated proteasomal degradation of Notch. For example, dominant negative mutations of proteasomal subunits enhance Notch signaling in Drosophila[20]. Initial evidence for lysosomal degradation of Notch came from a study in skeletal myoblasts, the C2C12 cell line, where a role was demonstrated for c-Cbl( Casitas B-lineage lymphoma, a proto-oncogene and E3 ubiquitin ligase) in mono-ubiquitinating the endogenous transmembrane Notch1 and targeting it for lysosomal degradation[21]. Suppressor of Deltex[Su( dx)]/Itch( Drosophila/mouse) and Sel10 have been shown to decrease Notch signaling in this context[22–25]. Mutations in Notch affect many developmental decisions in various Drosophila tissues[26, 27]. For example, Notch signaling instructs specification of the eye field and initiation of eye development, as well as controlling growth and cell fate[28–31]. The interplay between Notch and Frizzled( Fz) /Planar Cell Polarity( PCP) signaling is critical for induction of specific photoreceptor( PR) subtypes[29, 30, 32–34]. In the developing eye disc, there is a Frizzled/PCP activity gradient that is highest at the dorso-ventral midline, termed the equator, and lowest at each pole[30, 35, 36]. Within each developing PR cluster, there are pairs of cells that are initially equivalent that then develop into photoreceptor 3 and 4( R3 and R4). Within each pair, the cell that is closest to the midline adopts the R3 fate and upregulates the Notch ligand Delta, and neuralized and signals via Notch to its polar neighbor to adopt the R4 fate[30, 36–38]. In a screen for novel regulators of PCP signaling in the Drosophila eye, we identified a scaffolding protein, A Kinase Anchoring Protein 200( AKAP200)[39]. AKAPs are a family of proteins responsible for the subcellular compartmentalization of Protein Kinase A( PKA), which facilitate the spatial and temporal regulation of signaling[40–42]. Despite being structurally and sequentially diverse, the AKAP family of proteins show functional conservation amongst species[43]. AKAP200 is one member of the AKAP family of proteins and is expressed throughout all stages of Drosophila development. Alternative splicing produces two isoforms of AKAP200—the full length AKAP200-Long( AKAP200-L), and the short isoform, AKAP200-Short( AKAP200-S). AKAP200-S lacks the PKA-interaction domain and may therefore be limited to PKA- independent functions[44, 45]. Here we provide evidence that AKAP200 is required for the regulation of Notch protein levels, via the lysosomal degradation pathway. AKAP200’s loss and gain-of-function( LOF/GOF) phenotypes are characteristic of misregulation of the Notch signaling pathway. AKAP200 LOF mutants display defects in cell fate specification manifested as loss of PRs in the eye and extra sensory bristles in the thorax, while AKAP200 overexpression causes wing vein defects and tissue overgrowth in the wing. Genetic interaction studies revealed that AKAP200 acts as a positive regulator of Notch signaling, as loss of AKAP200 suppresses Notch overexpression phenotypes in the eye and thorax. Consistent with this, we observe a decrease in overall Notch protein levels and increased ubiquitination in the AKAP200 mutant relative to wild type( WT). Importantly, AKAP200’s effects on Notch are independent of PKA. However, we find that the suppression of Notch hyperactivity in AKAP200 mutant tissues is instead dependent on the E3 ubiquitin ligase Cbl and the lysosomal degradation pathway. Based on these data, we postulate a novel mechanism for the regulation of Notch levels, with AKAP200 preventing Cbl-mediated lysosomal degradation of Notch.\nDiscussion:\nAKAP200 was identified in a PCP-signaling mediated screen performed in the Drosophila eye[39]. However, AKAP200 LOF phenotypes resemble Notch LOF. As PCP is instructive to Notch signaling in the R3/R4 specification context in the Drosophila eye, the identification of novel Notch pathway regulators was expected and in line with previous experiments; for example, the Notch ligand Dl was identified in the screen as well[39]. Furthermore, AKAP200’s strong and specific interaction with sev-NΔECD, which is a membrane tethered, ligand-independent activated Notch, indicates that it acts on Notch itself. Due to AKAP200’s ‘canonical’ role in PKA regulation, we tested how AKAP200 acts in Notch signaling. Analyses of the two isoforms of AKAP200, which differ in their ability to bind PKA, revealed that AKAP200’s Notch associated function is PKA independent, which was corroborated by functional rescue assays with both isoforms rescuing the AKAP200 eye phenotypes indistinguishably. The AKAP200 LOF mutants display other defects, which in some tissues are PKA associated phenotypes: for example AKAP200 mutant wings have a penetrant wing blistering phenotype, which has been observed upon disruption of the PKA pathway[59, 60] and, similarly, AKAP200 mutant ovaries have developmental defects, which have been linked to PKA signaling[75]. Our work identifies AKAP200 as a regulator of Notch protein levels( also below). However, it does not affect Notch in all tissues, and even in tissues where it is required, it is specific to a subset of Notch signaling contexts. In the eye for example, it affects Notch signaling during photoreceptor specification but not during lateral inhibition in the furrow. Strikingly, there are no effects of AKAP200 on Notch signaling mediated wing margin development, which is even a haplo-insufficient Notch phenotype[76, 77]. Likely, the Notch signaling feedback loops at the wing margin, which also includes Wingless( Wg) expression[78–80], are not sensitive to AKAP200 mediated input. However, overexpression of AKAP200 in the wing led to expansion of wing veins, a phenotype linked to Notch GOF[81, 82], and thus consistent with the Notch GOF effects in photoreceptor specification in the eye. Taken together, our data suggest that AKAP200 affects Notch levels in a tissue and context specific manner, rather than being a general Notch protein level regulator. How do the AKAP200 Notch signaling requirements relate to each other? In the eye, AKAP200 LOF defects correlate with photoreceptor specification, particularly with R7 and R4 induction, and associated steps. Specification of R7 and R4 both require Notch signaling activation from neighboring R-cells, R1/6 and R8 induce R7 and R3 activates the pathway in R4, and interestingly in both contexts Egfr/RTK signaling is also required for the specific R-cell fate[30, 33, 36–38, 83]. We did not detect an interaction between AKAP200 and the GOF EgfrEllipse alleles, however, suggesting that AKAP200 does not act via Egfr. Can this correlation be related to other AKAP200 requirement contexts? In the wing, although there is no AKAP200 effect on the margin, both overexpression and LOFs of AKAP200 affect wing vein development. Establishment of wing veins is a multi-step, multi-pathway process, involving coordination of Notch signaling and other pathways, which also include Egfr/RTK signaling[84–88]. Notch signaling causes restriction of cell fate and width of the vein[4, 66, 89–92]. Consistent with the defects in the eye, LOF or GOF of AKAP200 correlates with vein development or vein widening, respectively. In the thorax, Notch is required at different stages of SOP specification and AKAP200 LOF phenotypes resemble several of these. Can this be linked to Egfr signaling as well? Previous reports have shown an involvement of Egfr/RTK signaling in promoting bristle development, where Egfr hypomorphs developed fewer bristles[93, 94]. The Egfr requirement has been attributed to SOPs requiring Egfr-signaling to maintain wild-type levels of ac-sc expression[95]. In summary, it appears that AKAP200 affects Notch activity/levels in specific contexts and that these involve Egfr signaling in some capacity. The role of AKAP200 appears to be in stabilization of the Notch protein: there is a decrease of endogenous Notch in the AKAP200 LOF vs. an increase of Notch in AKAP200 GOF backgrounds. We also observed increased ubiquitination of Notch in AKAP200 null mutant backgrounds. Ubiquitination and subsequent degradation of cellular proteins serves as a key mechanism to regulate their activity and disruption in this process often lead to overactivation of signaling. Both AKAP200 and Notch have previously been associated with the E3 ubiquitin ligase, Cbl[21, 96], and strikingly Cbl has also been linked to the regulation of Egfr[97, 98]. Thus, we explored a role for Cbl in AKAP200’s regulation of Notch. Strikingly, suppression of Notch hyperactivation by AKAP200 depends on the presence of wild-type levels of Cbl. Our studies thus suggest that AKAP200’s function is to antagonize Cbl effects on Notch ubiquitination and protein levels. Of note, it is also possible that AKAP200 modulates Notch or other components of the signaling pathway via other mechanisms. One hypothesis that leads from our work is that AKAP200 could maintain the balance between Cbl’s effects on Notch and Egfr. Since AKAP200 is a scaffolding protein, it may affect both pathways, and only processes that require balanced effects of Notch and Egfr signaling may be impacted. AKAP200 was previously identified as a positive regulator of Ras signaling[99]. However, we did not pursue AKAP200’s role in this context as we did not detect interactions with the EgfrElp allele. In conclusion, we postulate a novel mechanism of regulation of Notch signaling by AKAP200 antagonizing Cbl-mediated lysosomal degradation of Notch. This study advances our understanding of the tight regulation of Notch protein levels, which is fundamental to numerous key developmental processes and diseases.", "role": "user" }, { "content": "AKAP200 belongs to a family of scaffolding proteins best known for their regulation of PKA localization . In this study , we have identified a novel role of AKAP200 in Notch protein stability and signaling . In Drosophila melanogaster , AKAP200’s loss and gain-of-function ( LOF/GOF ) phenotypes are characteristic of Notch signaling defects . Furthermore , we demonstrated genetic interactions between AKAP200 and Notch . Consistent with this , AKAP200 stabilizes the endogenous Notch protein and limits its ubiquitination . AKAP200 exerts its effects on Notch by antagonizing Cbl-mediated ubiquitination and thus lysosome targeting of Notch . Based on these data , we postulate a novel PKA independent mechanism of AKAP200 to achieve optimal Notch protein levels , with AKAP200 preventing Cbl-mediated lysosomal degradation of Notch .", "role": "assistant" } ]

[ { "content": "Transform the following sections from a biomedical study into a simple summary for the general public. Focus on making the information accessible and easy to understand.\n\nResearch Heading: Combined Analysis of Variation in Core, Accessory and Regulatory Genome Regions Provides a Super-Resolution View into the Evolution of Bacterial Populations\nContent:\nAbstract:\nThe use of whole-genome phylogenetic analysis has revolutionized our understanding of the evolution and spread of many important bacterial pathogens due to the high resolution view it provides. However, the majority of such analyses do not consider the potential role of accessory genes when inferring evolutionary trajectories. Moreover, the recently discovered importance of the switching of gene regulatory elements suggests that an exhaustive analysis, combining information from core and accessory genes with regulatory elements could provide unparalleled detail of the evolution of a bacterial population. Here we demonstrate this principle by applying it to a worldwide multi-host sample of the important pathogenic E. coli lineage ST131. Our approach reveals the existence of multiple circulating subtypes of the major drug–resistant clade of ST131 and provides the first ever population level evidence of core genome substitutions in gene regulatory regions associated with the acquisition and maintenance of different accessory genome elements.\nIntroduction:\nThe ability to sequence hundreds or thousands of bacteria genomes in a timely and cost effective manner has allowed microbiologists to study microbial evolution at an unprecedented scale and level of resolution[1]. The focus of microbial population genomics research has often involved the creation of core genome phylogenetic trees to reconstruct the evolutionary trajectory of a pathogenic species or subspecies. Core genomes can be obtained by mapping genome data against a common reference sequence or by extracting the coding sequences( CDS) which are common across all members of a given data set. This approach has led to significant discoveries of the emergence of pathogenic bacteria[2–5], and allows fine scale analysis to inform interpretation of transmission events[6, 7]. Whilst the use of core genome phylogenetics has improved understanding of the evolution of bacterial pathogens, discarding information from genes which are differentially present in a bacterial population( the accessory genome) results in the loss of a large amount of potentially useful genetic information. Pan genome analyses of bacteria from the Enterobacteriaceae show that the core genome accounts for only a small proportion of the entire gene pool of a species[8, 9]. Integrating accessory gene pool analysis can improve the resolution of core genome phylogenetic studies. For example, investigation of the accessory genome of Yersinia enterocolitica revealed ecological patterns of separation within the population[9] and a study of a global collection of enterotoxigenic Escherichia coli( ETEC) used plasmid profiling to identify multiple clones of ETEC circulating globally[10]. Furthermore a study of the accessory genome of Klebsiella pneumoniae identified virulence loci significantly associated with isolates from invasive disease[11]. The acquisition of lineage specific gene-regulatory regions in the core genome has also been recently shown to play a key role in the formation of phylogenetically distinct phenotypes in E. coli[12]. Therefore, systematic analysis of sequence variation in regulatory regions should complement the information provided by the core and accessory CDSs. In this study we analyse the core and accessory genome jointly with core regulatory elements to provide unprecedented insight into the population structure and ecological inference of the globally important human pathogen E. coli ST131. This lineage of extra-intestinal pathogenic E. coli( ExPEC) has been rapidly globally disseminated to become the dominant multi-drug resistant( MDR) isolate of E. coli from urinary tract and bloodstream infections across the world[13]. Three distinct clades have been identified within the ST131 lineage[14, 15], of which clade C, also known as H30Rx, is associated with the rapid expansion and global dissemination of MDR isolates carrying the CTX-M-15 extended spectrum beta lactamase( ESBL). However, ambiguities remain regarding the importance of some undersampled reservoirs of resistant strains[16, 17, 18, 19]. First, while frequent plasmid movement between poultry and human ST-131 isolates and clustering of marine animal isolates with those of human[15], suggests ecological overlap of human and animal niches, human and agricultural animal strains are rarely isolated from the same environment[20]. Second, diverse sets of human clinical isolates show distinct plasmids associated with each CTX-M type, highlighting the importance of sampling isolates from people in multiple countries. Here we study the emergence of this important human pathogen by analysing the genomes of diverse isolates from avian species, domesticated animals, and humans encompassing a full spectrum of geographical and ESBL gene diversity. Our combined analysis allows the highest resolution view to date of the population structure of the ST131 lineage and shows how emergence of distinct MDR clusters are underpinned by associated changes in the core gene regulatory regions.\nDiscussion:\nThe data and analytical techniques presented here represent a comprehensive approach to merge fragmented views of bacterial evolution. Combining analysis of the core genome phylogeny, accessory genome profiles and core gene regulatory elements we provide a robust mechanism for understanding the population dynamics of an important MDR lineage of E. coli and identify significant evolutionary events that have underpinned its emergence as a dominant and successful MDR pathogen. Furthermore, by using strains isolated from non-human reservoirs and under-sampled geographical regions we provide enhanced insight into the complex ecology of an MDR E. coli lineage beyond the often human-centric approach taken to genomic epidemiological studies of these pathogens. Our data enables several key conclusions on the ecology of the MDR E. coli lineage ST131. By including the genomes of companion animal and wild bird isolates into our analysis we were able to show that human, dog, cat, and wild bird isolates can freely move across niches without obvious genomic signals of ecological adaptation and niche segregation. As such our data provides a high-resolution confirmation that the MDR E. coli lineage ST131 is a host generalist and could be argued to be a zoonotic pathogen. Of particular interest is the inference from our AdaptML analysis concerning a significant ecological jump from a small cluster of predominantly European companion animal isolates in clade A to the rest of the phylogeny, with the only other isolate in the cluster being a human clinical isolate from China which was isolated over 10 years before the European strains. Recent data have shown the importance of fluoroquinolone resistance and virulence gene acquisition to the evolution and emergence of clade C ST131[23, 28]. However, given the fact that ST131 move freely between animal hosts there is an argument that more non-human isolates from all three clades, and more isolates from the understudied clades A and B, would give an even greater level of resolution for understanding the evolutionary events that lead to the creation of the dominant MDR clade C of E. coli ST131. The power of such an approach is exemplified by the study of human and animal Salmonella Typhimurium DT104 isolates at a genome level which showed that human and animal outbreaks were distinct events and not zoonotic infections as previously accepted[29]. The phylogenetic structure of the E. coli ST131 lineage is well defined[14, 15] with all analyses suggesting a single global dissemination of clade C as the driver for the emergence of MDR ST131 as a dominant human clinical isolate[14, 15, 23, 28]. Our study utilises the wealth of information within the accessory gene pool to enhance the resolution of this well-defined population structure. By focusing on the entire accessory gene pool and not just plasmid sequences[23] we show the existence of multiple subtypes of ST131 clade C based on highly congruent accessory gene profiles which often intermingle within the core genome phylogeny. If the levels of admixture observed for the rarest accessory genes throughout the ST131 population held true for all of the accessory gene pool, then over time these clusters would merge and become non-existent, which is inconsistent with our observations. Recent Bayesian dating analysis suggests that clade C diverged around 30–40 years ago and clade B and C from A 60–90 years ago[23, 28]. Therefore it seems more likely that the accessory genome clusters of ST131 represent distinct ST131 subtypes which have expanded and disseminated while generally maintaining a defined accessory gene repertoire. The rapid expansion of novel subtypes of E. coli STs due to gene acquisition has been shown in intestinal pathogenic E. coli[10, 30] but our analysis provides the first indication of this occurring in such a lineage of extra-intestinal pathogenic E. coli. Finally, our finding that the alleles of gene regulatory regions of core CDS are concordant with the accessory genome profiles of isolates provides even greater evidence of expansion of multiple subtypes of E. coli ST131. The importance of the mobility of gene regulatory regions was previously demonstrated in E. coli[12] and our data set provides the first population level evidence of this phenomenon in E. coli lineages. Furthermore, our data lend population genomic support to the experimental evolutionary studies suggesting that acquisition and maintenance of MDR plasmids in the absence of antibiotic selection occurs as a result of compensatory mutations that influence gene expression and minimise the fitness costs of the plasmid[25, 26]. This is indicated by the fact that clades A and B are closer to each other in terms of gene regulatory profile than to clade C, yet clade B is closer to clade C from a core genome phylogenetic and accessory genome composition perspective. Given that we know the main differences between clade B and clade C to be in the virulence gene profiles and the prevalence of MDR plasmids[14, 15, 28], this suggests that compensatory mutations in gene regulatory regions as a response to acquisition of MDR plasmids, acts to facilitate the successful emergence of ST131 clade C alongside fluoroquinolone resistance and particular virulence gene alleles[28]. Our work highlights that by combining core, accessory, and gene regulatory region genome analysis it is possible to provide a completely different perspective of the evolution of an extremely well studied and defined bacterial lineage. The enhanced resolution afforded by our approach enabled the generation of an updated hypothesis for the emergence of a globally important MDR E. coli lineage. According to this hypothesis, a potentially host-restricted group of E. coli has adapted to become more generalist, resulting in exposure to a more expansive accessory gene pool[31]. The development of fluoroquinolone resistance and selection for important allele variants in virulence genes then occurred to create a lineage adapted to successful human colonization[23, 28]. This lineage was subsequently exposed to a number of circulating plasmids, including MDR plasmids, and phages which are acquired and maintained, resulting in compensatory mutations in gene regulatory regions to offset the cost of maintenance. It is also possible that these gene regulatory alleles have been acquired by recombination allowing a more rapid adaptation to the fitness cost, and this is a testable hypothesis that should be focused upon in the immediate future. The above hypothesised evolutionary process has, in summary resulted in successful MDR clones which rapidly disseminate globally and have led to a global healthcare burden. Similar integrated analyses will be of interest in the future to add further resolution to our knowledge of the evolution and emergence of other globally important bacterial pathogens.", "role": "user" }, { "content": "We present an approach to evolutionary analysis of bacterial pathogens combining core genome , accessory genome , and gene regulatory region analyses . This enables unparalleled resolution of the evolution of a multi-drug resistant pandemic pathogen that would remain invisible to a core genome phylogenetic analysis alone . In particular , our combined analysis approach identifies population-level evidence for compensatory mutations offsetting the costs of resistance plasmid maintenance as a key event in the emergence of dominant MDR lineages of E . coli .", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nThicknessofstriavascularis(SV)wasobtainedasaverageofthreedistancemeasurementsperpendiculartothesurfaceofmarginalcells.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Analyze the following sentence to identify chemical entities of interest. List these entities in a JSON array format. If no entities are found, return an empty array.\n\nText to Analyze:\nTemporalboneswereremovedandtwopreparationsofinnereartissueswereobtainedbymicrodissection:(1)striavasculariswithoutspiralligament,and(2)spiralgangliaincludingthesurroundingboneandtheorganofCorti.", "role": "user" }, { "content": "[]", "role": "assistant" } ]

[ { "content": "Examine the following abstract and identify distinct entities. Focus on extracting entities related to participants, interventions, and outcomes.\n\nPresent your findings in a JSON format like: {\"Participant\": [\"example entity\", ...], \"Intervention\": [\"example entity\", ...], \"Outcome\": [\"example entity\", ...]}. If no entities are found for a category, use an empty list.\n\nAbstract Content:\n\nRandomized comparative study of group versus individual cognitive behavioural therapy for obsessive compulsive disorder . OBJECTIVE The primary aim of the study was to compare the effectiveness of group and individual cognitive behaviour therapy ( CBT ) for obsessive compulsive disorder ( OCD ) . METHOD One hundred and ten out-patients with OCD were randomly assigned to 15 sessions of either group CBT or individual CBT . Outcome measures were administered before and after treatment , as well as at 6- and 12-month follow-ups . The study was supplemented by a meta-analysis of accomplished comparative studies of group vs. individual CBT for OCD . RESULTS Large and stable pre-post effect sizes were found for both treatment conditions in the study ( d = 1.06-1.24 on the Yale-Brown Obsessive Compulsive Scale ) . There were no significant between-group differences in outcome at any data point ( ds= -0.13 to 0.15 ) . The meta-analysis of four accomplished comparative studies ( including the present one ) found a between-group mean effect size of ( d= 0.15 favouring individual over group CBT at posttreatment ( 95 % confidence interval , -0.12 , 0.42 ) . CONCLUSION The results of this study suggest that OCD can be treated effectively with a group format of CBT , thus sparing some therapist resources , although the four accomplished comparative studies do not rule out the possibility of a small superiority of individually conducted CBT .", "role": "user" }, { "content": "{\"Intervention\": [\"group versus individual cognitive behavioural therapy\", \"CBT\", \"group and individual cognitive behaviour therapy ( CBT )\", \"group CBT or individual CBT .\", \"group format of CBT\", \"group vs. individual CBT\"], \"Outcome\": [\"effectively\", \"effect sizes\", \"Yale-Brown Obsessive Compulsive Scale\"], \"Participant\": []}", "role": "assistant" } ]

[ { "content": "Evaluate the given public health statement using the provided research abstract. Your goal is to determine the relationship between the claim and the abstract content.\n\n- \"decision\": Indicate whether the abstract \"SUPPORTS\", \"CONTRADICTS\", or provides \"INSUFFICIENT\" information regarding the claim.\n- \"justification\": List sentences from the abstract that back your decision. If the decision is \"INSUFFICIENT\", leave this list empty.\n\nStatement: UV light kill the new coronavirus\n\nResearch Abstract:\nAs the world economies get out of the lockdown imposed by the COVID-19 pandemic, there is an urgent need to assess the suitability of known technologies to mitigate COVID-19 transmission in confined spaces such as buildings.\nThis feasibility study looks at the method of upper-room ultraviolet (UV) air disinfection that has already proven its efficacy in preventing the transmission of airborne diseases such as measles and tuberculosis.\nUsing published data from various sources it is shown that the SARS-CoV-2 virus, which causes COVID-19, is highly likely to be susceptible to UV damage while suspended in air irradiated by UV-C at levels that are acceptable and safe for upper-room applications.\nThis is while humans are present in the room.\nBoth the expected and worst-case scenarios are investigated to show the efficacy of the upper-room UV-C approach to reduce COVID-19 air transmission in a confined space with moderate but sufficient height.\nDiscussion is given on the methods of analysis and the differences between virus susceptibility to UV-C when aerosolised or in liquid or on a surface.", "role": "user" }, { "content": "{\"verdict\": \"SUPPORT\", \"evidence\": [\"Using published data from various sources it is shown that the SARS-CoV-2 virus, which causes COVID-19, is highly likely to be susceptible to UV damage while suspended in air irradiated by UV-C at levels that are acceptable and safe for upper-room applications.\"]}", "role": "assistant" } ]

[ { "content": "Examine the abstracts provided from a main scientific article and its cited works. Craft a narrative that synthesizes the key insights and contributions, emphasizing their interconnections. Employ numerical citations such as [1], [2], etc., to reference the cited works.\n\nMain Article Summary:\nThe arboricity of a graph is the minimum number of forests it can be partitioned into. Previous approximation schemes were nonconstructive, i.e., they only approximated the arboricity as a value without computing a corresponding forest partition, as they operate on the related pseudoforest partitions or the dual problem. We propose an algorithm for converting a partition of @math pseudoforests into a partition of @math forests in @math time, where @math is the inverse Ackermann function, when @math expected time is allowed for pre-computation of a perfect hash function. Without perfect hashing, we obtain @math with a data structure by Brodal and Fagerberg that stores graphs of arboricity @math . For every fixed @math , the latter result implies a constructive @math -approximation algorithm with runtime @math by using Kowalik's approximation scheme for pseudoforest partitions. Our algorithm might help in designing a faster exact arboricity algorithm. We also make several remarks on approximation algorithms for the pseudoarboricity and the equivalent graph orientations with smallest maximum indegree, and correct some mistakes made in the literature.\n\nCited Works Summary:\n[1]: \n\n[2]: A data structure for representing a set of n items from a umverse of m items, which uses space n + o(n) and accommodates membership queries m constant time is described. Both the data structure and the query algorithm are easy to mplement.\n\n[3]: Given an undirected graph G = (V ,E ), the density of a subgraph on vertex set S is defined as @math , where E (S ) is the set of edges in the subgraph induced by nodes in S . Finding subgraphs of maximum density is a very well studied problem. One can also generalize this notion to directed graphs. For a directed graph one notion of density given by Kannan and Vinay [12] is as follows: given subsets S and T of vertices, the density of the subgraph is @math , where E (S ,T ) is the set of edges going from S to T . Without any size constraints, a subgraph of maximum density can be found in polynomial time. When we require the subgraph to have a specified size, the problem of finding a maximum density subgraph becomes NP -hard. In this paper we focus on developing fast polynomial time algorithms for several variations of dense subgraph problems for both directed and undirected graphs. When there is no size bound, we extend the flow based technique for obtaining a densest subgraph in directed graphs and also give a linear time 2-approximation algorithm for it. When a size lower bound is specified for both directed and undirected cases, we show that the problem is NP-complete and give fast algorithms to find subgraphs within a factor 2 of the optimum density. We also show that solving the densest subgraph problem with an upper bound on size is as hard as solving the problem with an exact size constraint, within a constant factor.\n\n[4]: A succint representation of a graph is a widely studied problem. A number of criteria can be used to determine the succinctness of the representation. We examined the representation of a graph in these two aspects: 1. The space complexity of the representation.\n\n[5]: In graphs of bounded arboricity, the total complexity of all maximal complete bipartite subgraphs is O(n). We described a linear time algorithm to list such subgraphs. The arboricity bound is necessary: for any constant k and any n there exists an n-vertex graph with O(n) edges and (nlog n)k maximal complete bipartite subgraphs Kk,l.\n\n[6]: We study the problem of finding highly connected subgraphs of undirected and directed graphs. For undirected graphs, the notion of density of a subgraph we use is the average degree of the subgraph. For directed graphs, a corresponding notion of density was introduced recently by Kannan and Vinay. This is designed to quantify highly connectedness of substructures in a sparse directed graph such as the web graph. We study the optimization problems of finding subgraphs maximizing these notions of density for undirected and directed graphs. This paper gives simple greedy approximation algorithms for these optimization problems. We also answer an open question about the complexity of the optimization problem for directed graphs.\n\n[7]:", "role": "user" }, { "content": "Kowalik's approximation scheme [7] works by terminating Dinitz's algorithm early. It computes an @math -orientation in time @math . The aforementioned greedy algorithm computes an acyclic @math -orientation [5] [4] and a subgraph of density at least @math [2] [3] [6] [1] in linear time. It repeatedly removes the vertex of minimum degree and orients its unassigned edges towards it. Georgakopoulos and Politopoulos [1] give a generalization to hypergraphs. Charikar [6] and Khuller and Saha [3] address directed graphs. The fractional orientation problem is dual to the densest subgraph problem [6] .", "role": "assistant" } ]

[ { "content": "Analyze the given paragraph from COVID-19 research. Determine the relevant topics discussed in the text. Your response should be a JSON array containing the identified topics. Ensure the output is a valid JSON array with no additional commentary.\n\nText:\n\nThis study investigates the association between the treatment with heparin and mortality in patients admitted with Covid-19. Routinely recorded, clinical data, up to the 24th of April 2020, from the 2075 patients with Covid-19, admitted in 17 hospitals in Spain between the 1st of March and the 20th of April 2020 were used. The following variables were extracted for this study: age, gender, temperature, and saturation of oxygen on admission, treatment with heparin, hydroxychloroquine, azithromycin, steroids, tocilizumab, a combination of lopinavir with ritonavir, and oseltamivir, together with data on mortality. Multivariable logistic regression models were used to investigate the associations. At the time of collecting the data, 301 patients had died, 1447 had been discharged home from the hospitals, 201 were still admitted, and 126 had been transferred to hospitals not included in the study. Median follow up time was 8 (IQR 5-12) days. Heparin had been used in 1734 patients. Heparin was associated with lower mortality when the model was adjusted for age and gender, with OR (95% CI) 0.55 (0.37-0.82) p = 0.003. This association remained significant when saturation of oxygen < 90%, and temperature > 37 degrees C were added to de model with OR 0.54 (0.36-0.82) p = 0.003, and also when all the other drugs were included as covariates OR 0.42 (0.26-0.66) p < 0.001. The association between heparin and lower mortality observed in this study can be acknowledged by clinicians in hospitals and in the community. Randomized controlled trials to assess the causal effects of heparin in different therapeutic regimes are required.", "role": "user" }, { "content": "[\"Treatment\"]", "role": "assistant" } ]