{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2238,"total_is_capped":false,"direct_labels_cover":4,"predictions_cover":2238,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"82ec2e9177e9","filters":{"topic":"Computational Drug Discovery Methods"}},"results":[{"id":"W2767891136","doi":"10.1093/nar/gkx1037","title":"DrugBank 5.0: a major update to the DrugBank database for 2018","year":2017,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8798,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; Health Canada","keywords":"DrugBank; Drug repositioning; Drug; Database; Biology; Pharmacology; World Wide Web; Computer science; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.1189811418117239,"gpt":0.4389949253302896,"spread":0.3200137835185657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007572696,0.0002038108,0.0002284632,0.0002827423,0.00261523,0.002011882,0.007736574,0.0000721991,0.00008017587],"category_scores_gemma":[0.002516321,0.000152331,0.0001320156,0.0005144892,0.0003472128,0.001229892,0.004495993,0.0004975903,0.001419047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001524748,"about_ca_system_score_gemma":0.0004133594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001931183,"about_ca_topic_score_gemma":0.00008698402,"domain_scores_codex":[0.9957634,0.0005935574,0.0003063385,0.0009030461,0.001470049,0.0009635986],"domain_scores_gemma":[0.9937636,0.001406914,0.0001045597,0.00384284,0.0005663355,0.0003158032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001679178,0.0001749309,0.0003146901,0.00006812931,0.00007755846,0.00003623305,0.001627662,0.0006774066,0.00173178,0.318519,0.4347412,0.2418635],"study_design_scores_gemma":[0.001036806,0.0002138135,0.01127432,0.00007177611,0.00001019278,0.00001847496,0.0001220727,0.2130109,0.003140247,0.05265748,0.7180088,0.0004351301],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0467966,0.0001477235,0.8420765,0.09895329,0.00120341,0.002002047,0.000192654,0.0001548095,0.008472957],"genre_scores_gemma":[0.5843341,0.00003953049,0.4053745,0.002265265,0.001283572,0.0006945299,0.00003920255,0.00008138053,0.005887864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5375375,"threshold_uncertainty_score":0.9993585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170146596","doi":"10.1093/nar/gkj067","title":"DrugBank: a comprehensive resource for in silico drug discovery and exploration","year":2005,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4028,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"DrugBank; PubChem; Cheminformatics; In silico; chEMBL; Protein Data Bank; Drug discovery; Bioinformatics; Drug; Computational biology; Biology; Computer science; Database; Pharmacology; Protein structure; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.08993724777240726,"gpt":0.3895307683833659,"spread":0.2995935206109586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002059113,0.0001528288,0.0002155878,0.0005130479,0.0002531406,0.0005302806,0.000774267,0.00006595487,0.000005662822],"category_scores_gemma":[0.0003513552,0.0001520275,0.00005718934,0.000913386,0.0001882879,0.002363747,0.0007308214,0.0003798112,0.00003176193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002020514,"about_ca_system_score_gemma":0.0001706133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004473735,"about_ca_topic_score_gemma":0.00006343763,"domain_scores_codex":[0.9970072,0.0006890803,0.0003188624,0.0006652018,0.0007767593,0.0005429071],"domain_scores_gemma":[0.9968676,0.002205698,0.00005021582,0.0005079094,0.0002469001,0.0001216686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003830794,0.0005438266,0.001760458,0.0001993734,0.00004336977,0.00002817023,0.02182297,0.0415241,0.007755165,0.3031542,0.02069266,0.6020926],"study_design_scores_gemma":[0.001839321,0.00019257,0.01529418,0.00009711721,0.000003233261,0.00001492824,0.001632921,0.7974018,0.003672405,0.06215491,0.1172809,0.0004157219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7551656,0.0004719299,0.2278318,0.0135893,0.00008502526,0.000948265,0.0000115055,0.00008974703,0.001806754],"genre_scores_gemma":[0.9164518,0.00004709509,0.08180603,0.0003677908,0.0002173976,0.0001740167,0.00001273844,0.00002520342,0.000897899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7558777,"threshold_uncertainty_score":0.6199499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007826806","doi":"10.1207/s15327752jpa8001_18","title":"Starting at the Beginning: An Introduction to Coefficient Alpha and Internal Consistency","year":2003,"lang":"en","type":"article","venue":"Journal of Personality Assessment","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3721,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Baycrest Hospital","funders":"","keywords":"Cronbach's alpha; Internal consistency; Psychology; Reliability (semiconductor); Scale (ratio); Consistency (knowledge bases); Interpretation (philosophy); Statistics; Psychometrics; Social psychology; Mathematics; Clinical psychology; Computer science; Geography; Cartography; Discrete mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03245160760684651,"gpt":0.3592277944351563,"spread":0.3267761868283098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004411121,0.0001180709,0.0001893097,0.0001003302,0.0002573751,0.0002556773,0.0003592621,0.00002224445,0.00004600852],"category_scores_gemma":[0.000296702,0.00008479318,0.00008358294,0.000237126,0.00007816665,0.0004636973,0.0001753794,0.0002397438,0.000001696146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003617532,"about_ca_system_score_gemma":0.0002912223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001927573,"about_ca_topic_score_gemma":0.0000144288,"domain_scores_codex":[0.9976432,0.0007434895,0.0004568417,0.0002610342,0.0007066742,0.0001888078],"domain_scores_gemma":[0.9986256,0.0002622625,0.0003659151,0.0002473351,0.0003193635,0.0001794722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000179104,0.001571237,0.02818562,0.0001035416,0.0004903668,0.0001604856,0.02909992,0.2235446,0.01619357,0.5740514,0.02023887,0.1061813],"study_design_scores_gemma":[0.003292317,0.003710366,0.4454945,0.0002132172,0.0001989985,0.003173534,0.01090903,0.3648046,0.007048445,0.05400956,0.1058894,0.001256015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5261233,0.00008122617,0.4502781,0.02261482,0.0005761663,0.00007448917,0.000001073053,0.000006884185,0.0002439006],"genre_scores_gemma":[0.8610522,0.00000381357,0.137445,0.00108919,0.0003006537,0.000002533039,5.472007e-7,0.000005697143,0.0001004358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5200419,"threshold_uncertainty_score":0.3457766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009313526","doi":"10.1093/nar/gkm958","title":"DrugBank: a knowledgebase for drugs, drug actions and drug targets","year":2007,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2917,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Genome Alberta; Genome Canada","keywords":"DrugBank; Drug; Drug discovery; Drug action; ADME; Pharmacogenomics; In silico; Pharmacology; PubChem; Computational biology; Bioinformatics; Computer science; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.07127227794910762,"gpt":0.416100006730903,"spread":0.3448277287817954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009337699,0.0002234707,0.0002589534,0.0007327645,0.0008826177,0.0004077326,0.001214101,0.0000849458,0.00004374135],"category_scores_gemma":[0.0008666419,0.0002210202,0.0001256849,0.00138197,0.0003254536,0.0008516611,0.0009745646,0.0006064348,0.0001395217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002561639,"about_ca_system_score_gemma":0.0003890956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007711758,"about_ca_topic_score_gemma":0.00006634591,"domain_scores_codex":[0.9961167,0.000519297,0.0003971203,0.0008640071,0.001063215,0.001039686],"domain_scores_gemma":[0.9935902,0.00440449,0.00006984485,0.0007603685,0.0007496652,0.0004254804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002108781,0.0005838923,0.0007510961,0.0002077518,0.00009514643,0.00004597839,0.01692435,0.000451095,0.002480762,0.3438248,0.09106204,0.5433622],"study_design_scores_gemma":[0.002660563,0.0002306273,0.01253571,0.0001201852,0.00001971294,0.00005321695,0.002723372,0.3089137,0.01396708,0.1610328,0.4967554,0.0009876685],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1971778,0.001061517,0.7721059,0.006809016,0.0008118327,0.001284966,0.000029505,0.0003288566,0.02039052],"genre_scores_gemma":[0.7534181,0.00004907309,0.2400974,0.0002121637,0.0004353017,0.0001175342,0.00001290095,0.00004920934,0.005608354],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5562403,"threshold_uncertainty_score":0.9012943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134471382","doi":"10.1016/j.cell.2012.06.024","title":"A Landscape of Driver Mutations in Melanoma","year":2012,"lang":"en","type":"article","venue":"Cell","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2621,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Biology; Neuroblastoma RAS viral oncogene homolog; Genetics; Melanoma; Mutation; Gene; Cancer research; Exome; Exome sequencing; Computational biology; KRAS","retraction":null,"screen_n_in":null,"score":{"opus":0.0189702807580103,"gpt":0.2779444651890635,"spread":0.2589741844310531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002076777,0.00004103298,0.00006643905,0.00009347765,0.00001203428,0.00001028835,0.0002126426,0.00001728933,0.00002674001],"category_scores_gemma":[0.00001910729,0.00003993744,0.00002514563,0.0002731941,0.00001360361,0.000287137,0.00008486645,0.00004039231,0.00004818401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000114915,"about_ca_system_score_gemma":0.00003426583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008869843,"about_ca_topic_score_gemma":0.000002247568,"domain_scores_codex":[0.9995171,0.00006721313,0.0001101778,0.00008450258,0.0001038101,0.0001172252],"domain_scores_gemma":[0.9995604,0.0001948871,0.00003818845,0.0001485234,0.00002191796,0.00003604375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002144047,0.001995638,0.4816916,0.0001760916,0.00003617067,0.00002914486,0.03606667,0.1015713,0.02009112,0.306271,0.003728171,0.04832166],"study_design_scores_gemma":[0.0006848007,0.00004198156,0.770479,0.00001652315,0.000006153088,0.000008846861,0.0001271632,0.1844262,0.02785787,0.0134906,0.002643484,0.000217353],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7663053,0.0001761415,0.2177477,0.00007986154,0.0001883033,0.00005329666,0.000001398341,0.00001726693,0.01543081],"genre_scores_gemma":[0.935321,0.000001230638,0.06450133,0.00003363286,0.00002160525,0.00000345252,0.000001937392,0.000002411615,0.0001133642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2927805,"threshold_uncertainty_score":0.1628602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3007309629","doi":"10.1016/j.cell.2020.01.021","title":"A Deep Learning Approach to Antibiotic Discovery","year":2020,"lang":"en","type":"article","venue":"Cell","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2198,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research; Defense Threat Reduction Agency; Defense Advanced Research Projects Agency; Canada Research Chairs; Canada Foundation for Innovation; Broad Institute; Pershing Square Foundation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Institutes of Health; National Science Foundation","keywords":"Biology; Drug discovery; Computational biology; Antibiotics; Bioinformatics; Microbiology","retraction":null,"screen_n_in":null,"score":{"opus":0.02774392521283146,"gpt":0.2620180445409746,"spread":0.2342741193281432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001626451,0.0001049649,0.0001253316,0.00004819101,0.00006984895,0.0002603232,0.0006499815,0.00002475731,0.000003042985],"category_scores_gemma":[0.00009107475,0.0001029699,0.00005868664,0.0005421203,0.00001414861,0.0004517869,0.0004483741,0.0001487086,0.000246636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000022439,"about_ca_system_score_gemma":0.00004398188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003553885,"about_ca_topic_score_gemma":1.325448e-7,"domain_scores_codex":[0.9988909,0.0001322778,0.0001291973,0.0004213844,0.000223334,0.0002028588],"domain_scores_gemma":[0.9994514,0.0001208145,0.00003877471,0.0002026008,0.00002644555,0.0001599703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007611417,0.00008908525,0.000230701,0.00005811275,0.00000715453,0.000007656109,0.003165388,0.9647527,0.003587658,0.01320667,0.001143937,0.01374335],"study_design_scores_gemma":[0.0001407589,0.00006836881,0.001338365,0.00000479407,0.000003170875,0.000002803529,0.00006337562,0.9887624,0.003754107,0.000510655,0.005175238,0.0001759884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02311841,0.00007450489,0.9493171,0.0006901463,0.000238608,0.0001143222,3.592399e-7,0.0001285597,0.02631801],"genre_scores_gemma":[0.7533035,0.000002015782,0.245007,0.001232115,0.0001672534,0.000001999454,0.00000271111,0.000009268392,0.0002741663],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7301851,"threshold_uncertainty_score":0.4198989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2033757486","doi":"10.1021/jm4004285","title":"QSAR Modeling: Where Have You Been? Where Are You Going To?","year":2013,"lang":"en","type":"article","venue":"Journal of Medicinal Chemistry","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2073,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences","keywords":"Quantitative structure–activity relationship; Management science; Reliability (semiconductor); Computer science; Chemistry; Biochemical engineering; Data science; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02295736012740132,"gpt":0.2928844189549778,"spread":0.2699270588275765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001035988,0.0002402456,0.0004322705,0.00009894238,0.00009607112,0.0001825628,0.001322371,0.0001168159,0.0001741229],"category_scores_gemma":[0.0004123061,0.0002036668,0.0001875037,0.0002692145,0.00004388947,0.0007031394,0.0002797902,0.0006643038,0.00005586208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001948518,"about_ca_system_score_gemma":0.0003311462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002473931,"about_ca_topic_score_gemma":0.000002931801,"domain_scores_codex":[0.9972757,0.00008770854,0.000759722,0.0003292025,0.001184206,0.000363498],"domain_scores_gemma":[0.9976195,0.0002297042,0.0005203107,0.000411482,0.0007063441,0.0005126988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002443334,0.0007709592,0.01066442,0.001542995,0.0005760461,0.001528346,0.006613675,0.5682574,0.1042125,0.0005624732,0.145907,0.1591199],"study_design_scores_gemma":[0.001588931,0.0002540145,0.001413069,0.001989088,0.00007522183,0.001965607,0.002112434,0.958951,0.01067486,0.009110904,0.01120925,0.0006556149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3965853,0.002460732,0.5788322,0.01816337,0.0005469251,0.0001274963,0.000002664358,0.0000428756,0.003238439],"genre_scores_gemma":[0.8900892,0.0001165981,0.1058198,0.0008277732,0.001749085,0.000007682334,0.000001348904,0.00003187733,0.001356738],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4935038,"threshold_uncertainty_score":0.8305292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018518196","doi":"10.1093/nar/gkt1068","title":"DrugBank 4.0: shedding new light on drug metabolism","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2064,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Genome Alberta; Canadian Institutes of Health Research; Alberta Innovates; Alberta Innovates - Health Solutions; Genome Canada","keywords":"DrugBank; In silico; Drug; Drug metabolism; Drug discovery; Pharmacology; Biology; Computational biology; Bioinformatics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.04963956558686514,"gpt":0.3670297575201365,"spread":0.3173901919332713,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002491067,0.0002366215,0.000284712,0.0006882566,0.0004243026,0.001041249,0.002655694,0.00009297117,0.0007103861],"category_scores_gemma":[0.0006205558,0.0002075815,0.0001356911,0.001778124,0.0001078593,0.001420391,0.001300874,0.000863891,0.006090996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001861138,"about_ca_system_score_gemma":0.0004275214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004092144,"about_ca_topic_score_gemma":0.000004618201,"domain_scores_codex":[0.9948055,0.0009494855,0.0003520685,0.0008544245,0.00208454,0.0009540081],"domain_scores_gemma":[0.9964868,0.001334839,0.00006111401,0.00120059,0.000426899,0.0004896935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001808681,0.0001643062,0.0001447479,0.00002106536,0.00004904696,0.0000266406,0.003315755,0.001818411,0.004953421,0.4227686,0.2344173,0.3323026],"study_design_scores_gemma":[0.001307741,0.0001795752,0.03046276,0.0001258824,0.000008397034,0.00002687347,0.0003437063,0.2667993,0.02138304,0.372957,0.30552,0.0008857769],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5049998,0.0008977556,0.220674,0.07704137,0.002117837,0.001934232,0.000005540151,0.0009517784,0.1913777],"genre_scores_gemma":[0.8292516,0.00003862078,0.1538656,0.001039012,0.0009390185,0.0001021399,0.000004060877,0.00006586796,0.0146941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3314168,"threshold_uncertainty_score":0.9999958,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3098269892","doi":"10.17863/cam.34134","title":"Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules.","year":2018,"lang":"en","type":"article","venue":"Cambridge University Engineering Department Publications Database","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1978,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto; University of New Brunswick","funders":"Division of Information and Intelligent Systems; Division of Graduate Education; Samsung Advanced Institute of Technology; Basic Energy Sciences; Alfred P. Sloan Foundation","keywords":"Representation (politics); Chemical space; Computer science; Encoder; Set (abstract data type); Continuous optimization; Simple (philosophy); Algorithm; Biological system; Theoretical computer science; Artificial intelligence; Optimization problem; Chemistry; Drug discovery","retraction":null,"screen_n_in":null,"score":{"opus":0.05573509527027944,"gpt":0.2891603192911648,"spread":0.2334252240208853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003082164,0.000133744,0.0001766297,0.0003490892,0.00009078849,0.0000782032,0.0014087,0.00003464424,0.000007588536],"category_scores_gemma":[0.0003817138,0.0001667256,0.00004339906,0.001188089,0.00008427292,0.0016556,0.0009898607,0.00007831735,0.00001329433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001721587,"about_ca_system_score_gemma":0.0002292998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000277875,"about_ca_topic_score_gemma":5.175818e-7,"domain_scores_codex":[0.9986795,0.0001155175,0.0002295821,0.000489943,0.0002792652,0.0002062451],"domain_scores_gemma":[0.997647,0.0002798538,0.0001465768,0.001524672,0.0002781003,0.0001237598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005442169,0.001175681,0.0007161023,0.0002050682,0.0006469525,0.00009376977,0.0004012643,0.3364404,0.09342467,0.5116628,0.04330327,0.01187559],"study_design_scores_gemma":[0.0002779459,0.00001927995,0.0006023896,0.00002238525,0.00003966702,0.00002153556,0.00001344351,0.9892248,0.007501237,0.000006344565,0.002119284,0.0001517176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08513712,0.00001652983,0.9136126,0.00015523,0.0001098074,0.0002813919,0.000332872,0.0002323439,0.0001221256],"genre_scores_gemma":[0.2210856,0.000004071847,0.7778878,0.0000210608,0.00004205715,0.000002528057,0.0009080911,0.00001037844,0.0000383598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6527843,"threshold_uncertainty_score":0.6798874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137052779","doi":"10.1093/nar/gkq1126","title":"DrugBank 3.0: a comprehensive resource for 'Omics' research on drugs","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1857,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"DrugBank; Pharmacogenomics; Drug action; Drug discovery; Drug; Pharmacology; Data science; Computer science; Bioinformatics; Computational biology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1404948455682654,"gpt":0.4544141880977378,"spread":0.3139193425294725,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01142909,0.0002667077,0.0003466263,0.001383833,0.001318111,0.0008377528,0.003993032,0.0002609984,0.00007076691],"category_scores_gemma":[0.00196726,0.0002569635,0.0001923967,0.002563616,0.0008478771,0.00049782,0.00199254,0.003063596,0.000739375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002580947,"about_ca_system_score_gemma":0.0007029544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007082077,"about_ca_topic_score_gemma":0.00001098843,"domain_scores_codex":[0.9913576,0.0019732,0.0004429174,0.001356023,0.003259433,0.001610827],"domain_scores_gemma":[0.9821863,0.01312356,0.00007044656,0.002014751,0.002160377,0.0004445793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003549855,0.0004003365,0.00009668099,0.00008745254,0.00004969122,0.00003105799,0.003698731,0.001428301,0.02139456,0.7694921,0.06707494,0.1358911],"study_design_scores_gemma":[0.001566667,0.0008378749,0.003430096,0.00006424674,0.000003317441,0.00002454579,0.001066453,0.2053265,0.01189261,0.1736672,0.6016163,0.0005042036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8596157,0.00009917487,0.05757096,0.01776522,0.001079874,0.002734071,0.00005896677,0.0004125464,0.06066347],"genre_scores_gemma":[0.8680046,0.0000138428,0.1268076,0.0006718063,0.0009261536,0.0004095996,0.00002630058,0.00009636027,0.003043718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.595825,"threshold_uncertainty_score":0.9999883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2548357532","doi":"10.1186/s13321-016-0174-y","title":"ClassyFire: automated chemical classification with a comprehensive, computable taxonomy","year":2016,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1587,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"The Metabolomics Innovation Centre; Alberta Innovates; Athabasca University; Ottawa Hospital; University of Ottawa; University of Alberta","funders":"Alberta Innovates; National Institutes of Health; Genome Alberta; U.S. National Library of Medicine; University of Alberta; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Taxonomy (biology); Class (philosophy); Druggability; Information retrieval; Chemical database; Artificial intelligence; Data science; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.04246514513245019,"gpt":0.2767156684727564,"spread":0.2342505233403062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003628768,0.0001713569,0.0003261828,0.0001528054,0.0000477237,0.0001358101,0.0008087388,0.00006953075,0.000007867893],"category_scores_gemma":[0.0001031573,0.0001026329,0.00009628348,0.0003979507,0.00009459633,0.001797332,0.0001464151,0.000165863,0.00002477599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001855454,"about_ca_system_score_gemma":0.0003585092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.726375e-7,"about_ca_topic_score_gemma":5.447978e-8,"domain_scores_codex":[0.9981908,0.00002886727,0.0008103041,0.0001130386,0.0006198549,0.0002371324],"domain_scores_gemma":[0.9972426,0.0006378684,0.0009530674,0.0003194467,0.0006832212,0.0001637882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00052871,0.001038957,0.002121184,0.0006397567,0.0009052214,0.0001325223,0.003017465,0.02299565,0.1091127,0.05639686,0.1323903,0.6707206],"study_design_scores_gemma":[0.002633015,0.0002243667,0.002104221,0.0003943216,0.0000370605,0.001299566,0.0001232268,0.8974704,0.05642163,0.001807921,0.03707732,0.0004069787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1048676,0.00003420639,0.890677,0.001218393,0.0001854312,0.0001441132,0.000002705005,0.0001419021,0.002728712],"genre_scores_gemma":[0.5290284,0.00001244816,0.4705911,0.0002300384,0.00008122114,0.000005524155,0.000001571981,0.000009204754,0.00004050544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8744747,"threshold_uncertainty_score":0.418525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388615774","doi":"10.1093/nar/gkad976","title":"DrugBank 6.0: the DrugBank Knowledgebase for 2024","year":2023,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1530,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Alberta; Canadian Institutes of Health Research; Alberta Innovates; Genome Canada","keywords":"DrugBank; Biology; Bioinformatics; Computational biology; Pharmacology; Drug","retraction":null,"screen_n_in":null,"score":{"opus":0.1251609761501077,"gpt":0.4387112823119583,"spread":0.3135503061618506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00828475,0.0001791082,0.0001966604,0.0005421134,0.000892166,0.000573579,0.002941363,0.00008961466,0.0001192554],"category_scores_gemma":[0.00163923,0.0001324256,0.0001782828,0.003910111,0.0003044391,0.0004546862,0.001710005,0.0005942082,0.002699746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001558151,"about_ca_system_score_gemma":0.0005023874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000233248,"about_ca_topic_score_gemma":0.000009911807,"domain_scores_codex":[0.9957198,0.000923792,0.0003092381,0.000720566,0.001348041,0.0009785991],"domain_scores_gemma":[0.9920754,0.005851129,0.00004474133,0.001208416,0.0006369171,0.0001833948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003744244,0.00009141476,0.0001756711,0.0000739695,0.00004718829,0.00002625086,0.002283676,0.002315661,0.0006304826,0.271899,0.4916084,0.2308109],"study_design_scores_gemma":[0.0004257725,0.0001127231,0.003557549,0.00002832376,0.000004134679,0.000007504428,0.0002883133,0.5772354,0.0008422869,0.1120639,0.3052282,0.0002059149],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1704428,0.001029489,0.6560507,0.07799796,0.005303043,0.004330222,0.0001088537,0.00178184,0.08295512],"genre_scores_gemma":[0.8200316,0.0002123587,0.09092728,0.001088212,0.002397862,0.001750964,0.00006133183,0.0001877436,0.0833426],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6495889,"threshold_uncertainty_score":0.9980768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2578119541","doi":"10.1007/s12551-016-0247-1","title":"Software for molecular docking: a review","year":2017,"lang":"en","type":"review","venue":"Biophysical Reviews","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1464,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Docking (animal); Protein–ligand docking; Searching the conformational space for docking; Chemistry; Druggability; van der Waals force; Electrostatics; Computational chemistry; Drug discovery; Molecule; Molecular dynamics; Protein structure; Biochemistry; Virtual screening","retraction":null,"screen_n_in":null,"score":{"opus":0.2535480854321492,"gpt":0.4895213996216476,"spread":0.2359733141894985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001659956,0.0007911612,0.004797585,0.0001127019,0.0002038,0.0003484789,0.004285162,0.0001915068,0.00001158182],"category_scores_gemma":[0.004615746,0.000573172,0.003039186,0.0006065432,0.00007836724,0.0003777211,0.0009579451,0.0003900987,0.0006258754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322203,"about_ca_system_score_gemma":0.0006993061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001601023,"about_ca_topic_score_gemma":1.369211e-7,"domain_scores_codex":[0.9954434,0.000907712,0.00137455,0.001306284,0.0004647587,0.0005033146],"domain_scores_gemma":[0.9939596,0.001041408,0.001603626,0.002956828,0.0002096153,0.0002289428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[2.559651e-7,0.00003746887,3.201736e-9,0.1122931,0.00003943926,0.000008526144,0.000001834662,9.659759e-7,1.265828e-7,0.01508972,0.00725355,0.865275],"study_design_scores_gemma":[0.00005562033,0.00003847201,7.62208e-8,0.1157723,0.0004303717,0.00001853673,1.73848e-8,0.0002286555,5.377659e-7,0.002489114,0.8804217,0.0005446282],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.155948e-9,0.685427,0.3104369,0.00013148,0.0004076927,0.00330912,0.00003581734,0.00008620533,0.0001658085],"genre_scores_gemma":[4.903102e-9,0.8768992,0.1200081,0.0006203532,0.000340354,0.001774887,0.00009217321,0.00005600574,0.0002088417],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8731682,"threshold_uncertainty_score":0.999672,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999798000","doi":"10.1021/ci500747n","title":"Deep Neural Nets as a Method for Quantitative Structure–Activity Relationships","year":2015,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Machine learning; Artificial neural network; Set (abstract data type); Random forest; Deep neural networks; Support vector machine; Data set; Training set; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1295232065273913,"gpt":0.3918566737895487,"spread":0.2623334672621574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089224,0.00007946582,0.0001529242,0.0001303848,0.0000526044,0.000154435,0.0001773628,0.00005358304,6.89224e-7],"category_scores_gemma":[0.001286198,0.00006707803,0.00006159898,0.000134215,0.00001275132,0.003232347,0.00006339692,0.0002255071,7.995916e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005370467,"about_ca_system_score_gemma":0.0001333062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000050056,"about_ca_topic_score_gemma":4.001645e-7,"domain_scores_codex":[0.999037,0.0001026796,0.000414418,0.0000657772,0.0002799148,0.000100189],"domain_scores_gemma":[0.998347,0.0005022955,0.0003209574,0.00007219847,0.0006103168,0.00014717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001089279,0.00001014457,0.000007028161,0.00001238442,0.00001610514,3.537447e-7,0.002843714,0.9131353,0.0009167215,0.03684094,0.00006073098,0.04604767],"study_design_scores_gemma":[0.0005048635,0.00005847625,0.00001068869,0.000008840814,0.000008085349,0.00009468956,0.0001579847,0.9078919,0.001650648,0.0894134,0.000130376,0.00007003998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2033224,0.00004987009,0.7953919,0.0009381095,0.0001360447,0.00006760535,0.00000139291,0.00001016403,0.00008246824],"genre_scores_gemma":[0.5142378,0.000001039209,0.4855394,0.0001945177,0.00002235278,9.317458e-7,0.00000176774,0.000001600281,5.624622e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3109154,"threshold_uncertainty_score":0.2735363,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165253681","doi":"10.1093/nar/gkr1088","title":"The IntAct molecular interaction database in 2012","year":2011,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"FP7 Health; European Commission; European Bioinformatics Institute","keywords":"Annotation; Biology; Database; Download; Data curation; Information retrieval; World Wide Web; Bioinformatics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1361185997653013,"gpt":0.4182936330271091,"spread":0.2821750332618078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003921804,0.00009379609,0.00009014582,0.0003037694,0.0002133366,0.0002139468,0.001616088,0.00004307883,0.00008524388],"category_scores_gemma":[0.00053756,0.00007187282,0.0000435222,0.001039151,0.0001350479,0.001222467,0.00112693,0.0006487012,0.0003555584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001551728,"about_ca_system_score_gemma":0.000156614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002458869,"about_ca_topic_score_gemma":0.000059192,"domain_scores_codex":[0.9970751,0.001092945,0.0002229934,0.0003745992,0.000772587,0.0004617995],"domain_scores_gemma":[0.9979688,0.0008880558,0.00003681287,0.000827293,0.0001803351,0.00009869947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001530383,0.0003408075,0.001783031,0.00002218634,0.00003280677,0.0002357616,0.00354506,0.0004662105,0.008648342,0.6274578,0.004719337,0.3525956],"study_design_scores_gemma":[0.00123218,0.0004915958,0.1083289,0.0001642731,0.000005262691,0.0001016399,0.001262542,0.554803,0.03587939,0.2220338,0.07499593,0.0007014966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5010349,0.0004199981,0.4498962,0.002468977,0.0007395258,0.0005431633,0.000004184752,0.0001137203,0.04477937],"genre_scores_gemma":[0.9619431,0.00004554336,0.03761649,0.00008926891,0.00004075334,0.00004105706,0.000002883534,0.00001342603,0.0002074385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5543368,"threshold_uncertainty_score":0.4570102,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126662293","doi":"10.1021/ci0200467","title":"Property Distributions:  Differences between Drugs, Natural Products, and Molecules from Combinatorial Chemistry","year":2002,"lang":"en","type":"article","venue":"Journal of Chemical Information and Computer Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":921,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Molecule; Heteroatom; Combinatorial chemistry; Chemical space; Combinatorial synthesis; Chemistry; Ring (chemistry); Drug discovery; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01915048392831231,"gpt":0.2456147566528213,"spread":0.226464272724509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004208895,0.0001257849,0.0002166967,0.00006687135,0.0001345069,0.0006821739,0.0006047681,0.00004611415,0.000004148493],"category_scores_gemma":[0.0001212602,0.00007887363,0.00004116449,0.000326609,0.000273034,0.002878255,0.0002905796,0.0002025887,0.000001875928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002506858,"about_ca_system_score_gemma":0.00006223924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000506055,"about_ca_topic_score_gemma":1.938408e-8,"domain_scores_codex":[0.998623,0.00006105763,0.0004915631,0.0001605928,0.0005131866,0.0001506104],"domain_scores_gemma":[0.9989582,0.0002645029,0.0003405917,0.0001009374,0.0002283064,0.0001074334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003281149,0.000230954,0.005043792,0.0001614814,0.0001427723,0.000007088437,0.005808654,0.0002427456,0.00344502,0.02964548,0.005574328,0.9496649],"study_design_scores_gemma":[0.001312012,0.0001961702,0.01282203,0.0001615654,0.00002708924,0.0001418008,0.00008275094,0.9306011,0.02509434,0.02563391,0.003449244,0.0004780362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8451368,0.0006188852,0.149699,0.003684769,0.0005487085,0.00007872152,0.000008263727,0.00003043465,0.0001944381],"genre_scores_gemma":[0.9344443,0.00005000381,0.06508324,0.0001428739,0.0002688124,0.000001179765,0.000004476385,0.00000128988,0.000003841938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9491869,"threshold_uncertainty_score":0.6578219,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034475831","doi":"10.1038/nature11691","title":"Automated design of ligands to polypharmacological profiles","year":2012,"lang":"en","type":"article","venue":"Nature","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":845,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute","funders":"National Institute of Mental Health; Biotechnology and Biological Sciences Research Council; National Institute on Drug Abuse; Wellcome Trust","keywords":"Drug; Drug discovery; Computer science; Computational biology; Drug target; Bioinformatics; Pharmacology; Medicine; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.03147031858431396,"gpt":0.3637176719870286,"spread":0.3322473534027147,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000538477,0.00008519748,0.0001186071,0.00009229391,0.00003284263,0.00002359478,0.0005082639,0.0002847763,0.00001687192],"category_scores_gemma":[0.0001751118,0.0000671438,0.0000364117,0.0005338158,0.00001587073,0.0002786611,0.0002069343,0.0004450566,0.00002957041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002616794,"about_ca_system_score_gemma":0.00006154886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.37509e-7,"about_ca_topic_score_gemma":3.139218e-8,"domain_scores_codex":[0.9991046,0.0001220667,0.0001290073,0.0001584472,0.0002734079,0.0002125312],"domain_scores_gemma":[0.9992511,0.0003374336,0.00004762198,0.0001665277,0.00008285002,0.0001144266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002103313,0.001228476,0.006076417,0.0001005716,0.0001606893,0.00003092803,0.003991222,0.1808351,0.3202164,0.2677895,0.1618301,0.05753028],"study_design_scores_gemma":[0.0003631365,0.000164196,0.1000677,0.00002551653,0.00001223822,0.00002852458,0.00001276937,0.5742444,0.3192417,0.002401111,0.003147509,0.0002912469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2004467,0.0006155082,0.7950874,0.001674598,0.0009373671,0.0003141237,0.000005541765,0.0004676588,0.0004511636],"genre_scores_gemma":[0.7419164,0.00000105676,0.2569798,0.0009729072,0.00008115453,0.000009576012,0.00000109343,0.00000352834,0.0000344899],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5414698,"threshold_uncertainty_score":0.2738045,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2912247484","doi":"10.1038/s41579-018-0141-x","title":"Drug combinations: a strategy to extend the life of antibiotics in the 21st century","year":2019,"lang":"en","type":"review","venue":"Nature Reviews Microbiology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":840,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Canada Research Chairs; Bill and Melinda Gates Foundation","keywords":"Antibiotics; Biology; Antimicrobial; Antibiotic resistance; Intensive care medicine; Modern medicine; Drug; Microbiology; Medicine; Pharmacology","retraction":null,"screen_n_in":null,"score":{"opus":0.05720440746187533,"gpt":0.3878021263910452,"spread":0.3305977189291698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00393812,0.0004945202,0.002192675,0.0003379039,0.00007556257,0.00009307794,0.004396226,0.000538911,0.000009117975],"category_scores_gemma":[0.0007354719,0.0002443212,0.0006574533,0.001965254,0.0001218974,0.0001131091,0.0006731745,0.001866974,0.0001624459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008760981,"about_ca_system_score_gemma":0.0006921896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007892577,"about_ca_topic_score_gemma":0.0000188699,"domain_scores_codex":[0.99221,0.005143851,0.001360915,0.0007371958,0.0001621201,0.0003858948],"domain_scores_gemma":[0.9941263,0.003157062,0.0009328504,0.001586493,0.0001452992,0.00005202982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[9.942808e-7,0.0001165832,5.225476e-7,0.004769354,0.00004986073,0.000002751065,0.0001924557,0.00003858191,0.000004495501,0.1125259,0.004330159,0.8779683],"study_design_scores_gemma":[0.0000983504,0.00004927596,0.000008395111,0.004157052,0.000133897,0.0001177067,0.00002813587,0.00002370803,0.000001176551,0.0004452569,0.9946876,0.0002495042],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002755422,0.9931133,0.0009495079,0.0007561527,0.001126858,0.003315732,0.00008415637,0.00001533238,0.0006361736],"genre_scores_gemma":[0.00005472192,0.9934551,0.004527615,0.001655074,0.00009514485,0.00001924345,0.0001218869,0.00002062032,0.00005067001],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9903574,"threshold_uncertainty_score":0.9963129,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097449851","doi":"10.1038/nbt1186","title":"Statistical practice in high-throughput screening data analysis","year":2006,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":726,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"","keywords":"Replicate; Computer science; False discovery rate; Identification (biology); Data mining; Preprocessor; Drug discovery; Throughput; Multiple comparisons problem; Machine learning; Artificial intelligence; Bioinformatics; Statistics; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01478781202024359,"gpt":0.3463605281296443,"spread":0.3315727161094007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001004378,0.0001598818,0.0003083347,0.0008003686,0.00006391379,0.00009548459,0.002189241,0.0007005792,0.00001097838],"category_scores_gemma":[0.001833102,0.0001587824,0.00003754676,0.003608268,0.000121547,0.000775812,0.001532228,0.001172469,0.00001745225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006570164,"about_ca_system_score_gemma":0.00009115999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007035137,"about_ca_topic_score_gemma":0.0003807031,"domain_scores_codex":[0.9976752,0.0002802113,0.0003364405,0.0009841627,0.0003802379,0.0003437622],"domain_scores_gemma":[0.9964204,0.001660928,0.0001439144,0.001665802,0.0000771351,0.00003177773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001176631,0.000106227,0.0005955409,0.000003160428,0.00009336584,0.0001583273,0.00001168412,0.01353168,0.0001082258,0.9291111,0.001567658,0.05470122],"study_design_scores_gemma":[0.000697034,0.00007144164,0.07417561,0.00001148101,0.0001803172,0.00009197127,0.00003206287,0.7222517,0.001161285,0.1250648,0.07577883,0.00048345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003660105,0.000827772,0.9754744,0.01894254,0.0002281669,0.0001034539,0.00006530785,0.0002694745,0.0004288109],"genre_scores_gemma":[0.3784623,0.0000131339,0.6208953,0.0004038042,0.00004822676,0.000002921197,0.0001551108,0.000005718275,0.00001352353],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8040463,"threshold_uncertainty_score":0.6474959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2306570595","doi":"10.1021/acs.molpharmaceut.5b00982","title":"Applications of Deep Learning in Biomedicine","year":2016,"lang":"en","type":"review","venue":"Molecular Pharmaceutics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":715,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Biomedicine; Deep learning; Computer science; Artificial intelligence; Machine learning; Drug discovery; Data science; Identification (biology); Key (lock); Artificial neural network; Biomarker discovery; Deep neural networks; Bioinformatics; Biology; Proteomics","retraction":null,"screen_n_in":null,"score":{"opus":0.05247626487845024,"gpt":0.4336418701322031,"spread":0.3811656052537528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006938762,0.0002581323,0.0007793223,0.0005911821,0.00002751394,0.00002456984,0.001129565,0.0001203179,0.00001315661],"category_scores_gemma":[0.00007766402,0.0002124618,0.0002300915,0.001404946,0.00007316288,0.00008749199,0.0004519897,0.0003788216,0.0000482454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001173885,"about_ca_system_score_gemma":0.0002379137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001469273,"about_ca_topic_score_gemma":2.972408e-7,"domain_scores_codex":[0.9977428,0.0005542218,0.0006520073,0.0004313213,0.0003712018,0.0002484513],"domain_scores_gemma":[0.9984433,0.000525962,0.0003772352,0.0004817815,0.00008161814,0.00009009626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[5.036939e-7,0.00003696137,7.276235e-7,0.002082174,0.00004200375,0.00002155573,0.00002830571,0.0002906546,0.00001899029,0.00633578,0.00000385967,0.9911385],"study_design_scores_gemma":[0.0001877045,0.0000173605,4.968901e-7,0.001754136,0.00007823011,0.00002384051,0.000001320006,0.0108308,0.00009117502,0.001327918,0.9854766,0.0002103862],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.383979e-7,0.5092935,0.4899303,0.00003795875,0.00007138713,0.0002976495,0.000003144688,0.00003008695,0.0003357802],"genre_scores_gemma":[0.00003298525,0.9719424,0.02769123,0.00006191633,0.00004751945,0.0001274986,0.00002037011,0.00002960689,0.00004647861],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9909281,"threshold_uncertainty_score":0.8663943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2313757172","doi":"10.1093/toxsci/kfu199","title":"Adverse Outcome Pathway (AOP) Development I: Strategies and Principles","year":2014,"lang":"en","type":"article","venue":"Toxicological Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":711,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; Environment and Climate Change Canada","funders":"","keywords":"Adverse Outcome Pathway; Computer science; Modular design; Set (abstract data type); Outcome (game theory); Relevance (law); Conceptual framework; Process management; Risk analysis (engineering); Data science; Computational biology; Biology; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.1184175387031278,"gpt":0.3430100823848082,"spread":0.2245925436816804,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001998805,0.0001316578,0.0001663967,0.00007200335,0.0003839028,0.0003808205,0.000861703,0.00005172869,0.00002940872],"category_scores_gemma":[0.0003344116,0.00007717244,0.00003172531,0.0003729863,0.0004010012,0.0008672718,0.0006097811,0.00009148171,0.00003449587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003250622,"about_ca_system_score_gemma":0.0002006201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005945095,"about_ca_topic_score_gemma":0.00001721795,"domain_scores_codex":[0.9982384,0.0002335093,0.0002796389,0.0005028406,0.0004327307,0.0003129142],"domain_scores_gemma":[0.998889,0.0007114073,0.0000876356,0.000150836,0.00003206042,0.0001290424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000001888889,0.00005521538,0.00503707,0.00000566124,0.000002799617,0.000004140265,0.0002758151,0.01016791,0.0003793841,0.9102053,0.000006947115,0.07385788],"study_design_scores_gemma":[0.000265105,0.0004234059,0.6837527,0.00001357001,0.000002261169,0.00002221568,0.0003129295,0.179802,0.001465725,0.1104404,0.02306482,0.0004349833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7013658,0.00003044423,0.2835713,0.001072185,0.0001830827,0.0001061604,3.136321e-7,0.0001383605,0.01353241],"genre_scores_gemma":[0.7643469,0.000001433163,0.2351481,0.0003796314,0.00002394116,0.00001103826,2.564447e-7,0.000001383436,0.00008734304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7997649,"threshold_uncertainty_score":0.3672261,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990399577","doi":"10.1007/s10822-011-9440-2","title":"Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information","year":2011,"lang":"en","type":"article","venue":"Journal of Computer-Aided Molecular Design","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":687,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Bundesministerium für Bildung und Forschung; Alexander von Humboldt-Stiftung","keywords":"Computer science; Cheminformatics; Chemical database; Set (abstract data type); Database; Resource (disambiguation); World Wide Web; Variety (cybernetics); Web application; Domain (mathematical analysis); Data mining; Data science; Artificial intelligence; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.1270910022138917,"gpt":0.2838176523126851,"spread":0.1567266500987934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018243,0.0002179012,0.000388828,0.0002677542,0.00004207205,0.0002224538,0.001598558,0.0001126897,0.000001024484],"category_scores_gemma":[0.00018597,0.0002090782,0.00009705152,0.0001473442,0.00003905021,0.004093635,0.0009683536,0.0002729878,4.772758e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001209466,"about_ca_system_score_gemma":0.0005550478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001583419,"about_ca_topic_score_gemma":4.648175e-8,"domain_scores_codex":[0.997601,0.00007398938,0.001100541,0.0002854609,0.0006871314,0.0002519122],"domain_scores_gemma":[0.9981109,0.0002322429,0.0006782218,0.0004973035,0.0002986609,0.0001826512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001422801,0.0003242382,0.000002404231,0.00008409517,0.0001531855,0.00001400274,0.001449901,0.8649133,0.0198753,0.005108286,0.000266298,0.1076667],"study_design_scores_gemma":[0.0009454956,0.00009146416,0.000005358978,0.00007936838,0.00002925,0.00009132852,0.00001283112,0.9357615,0.05512292,0.007593591,0.00007162286,0.0001952778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1501888,0.0001230944,0.84924,0.0001033754,0.00009507569,0.0002110488,0.000009877104,0.0000164356,0.00001229643],"genre_scores_gemma":[0.2965167,0.000008439628,0.7032626,0.0001307802,0.00003856526,0.000003043593,0.00002937592,0.00001005662,4.754129e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1463279,"threshold_uncertainty_score":0.8525961,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3087156149","doi":"10.1016/s2589-7500(20)30192-8","title":"Artificial intelligence in COVID-19 drug repurposing","year":2020,"lang":"en","type":"review","venue":"The Lancet Digital Health","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":641,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"Office of Naval Research; National Heart, Lung, and Blood Institute; Frederick National Laboratory for Cancer Research; National Institute on Aging; National Cancer Institute; National Science Foundation; National Institutes of Health; Cleveland Clinic","keywords":"Repurposing; Drug repositioning; Timeline; Coronavirus disease 2019 (COVID-19); Computer science; Big data; Precision medicine; Data science; Drug development; Artificial intelligence; Drug; Medicine; Disease; Infectious disease (medical specialty); Pharmacology; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.219610518325795,"gpt":0.4670025249884717,"spread":0.2473920066626766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002102549,0.0003671986,0.001691758,0.0001822004,0.0001722347,0.0009316215,0.002575475,0.00007119412,0.000003665758],"category_scores_gemma":[0.0009345026,0.0002646923,0.0002576375,0.001636403,0.00009789717,0.0006667573,0.0008696731,0.0007744658,0.0001583585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006380174,"about_ca_system_score_gemma":0.003980302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007698352,"about_ca_topic_score_gemma":0.00003850972,"domain_scores_codex":[0.996062,0.0009489868,0.001106998,0.0007918492,0.0004805965,0.0006096068],"domain_scores_gemma":[0.9952511,0.002899892,0.0005470659,0.000937798,0.00002485086,0.0003392878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004407909,0.00002504006,6.015915e-7,0.00300357,0.00000939294,0.00003429626,0.0006118626,0.0005254284,6.747359e-10,0.05852229,0.000701875,0.9365612],"study_design_scores_gemma":[0.0000236957,0.00002828569,0.000001002462,0.00263244,0.00000600573,0.00008266547,0.00002512772,0.00982097,7.574441e-8,0.1006698,0.8864583,0.0002515961],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.782232e-7,0.7218037,0.2668466,0.009503574,0.0003546206,0.0006966123,0.0000554728,0.000160491,0.000578426],"genre_scores_gemma":[0.0000394518,0.9859362,0.009371082,0.003912501,0.0005820352,0.00005411982,0.00005091845,0.00003017516,0.0000234721],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9363096,"threshold_uncertainty_score":0.9999805,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2954214838","doi":"10.1016/j.cmet.2019.06.009","title":"Bacterial Metabolism and Antibiotic Efficacy","year":2019,"lang":"en","type":"review","venue":"Cell Metabolism","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":616,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institutes of Health Research; Defense Threat Reduction Agency; Broad Institute; Bill and Melinda Gates Foundation","keywords":"Antibiotics; Bacteria; Context (archaeology); Microbial metabolism; Biology; Metabolic pathway; Metabolism; Microbiology; Biochemistry; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.05328764770369514,"gpt":0.3349127596934674,"spread":0.2816251119897722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009245319,0.0008570001,0.003080724,0.0005459038,0.0001269272,0.0006991259,0.002053374,0.0003950943,0.00004321777],"category_scores_gemma":[0.0001551971,0.0007159222,0.0007293855,0.000882987,0.0001026691,0.0006484953,0.001442408,0.0006185813,0.0006954833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004149741,"about_ca_system_score_gemma":0.0006513294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009862745,"about_ca_topic_score_gemma":2.563463e-7,"domain_scores_codex":[0.9953122,0.001138774,0.0009099523,0.001451274,0.0005643999,0.0006233745],"domain_scores_gemma":[0.9963088,0.001178446,0.0006255299,0.001520144,0.00009789106,0.0002691881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002610814,0.00007184764,7.055576e-8,0.003583807,0.00009651115,0.00001177584,0.00008093548,0.00001887903,0.00001047693,0.01914703,0.0002682218,0.9767078],"study_design_scores_gemma":[0.00050159,0.00001454912,0.00006685219,0.0008555113,0.0009086368,0.00005577092,0.000001299666,0.0004053837,0.00003330917,0.0004681476,0.9959313,0.0007576992],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00007269993,0.9786178,0.01119646,0.00002521799,0.006987023,0.001011677,0.00004467808,0.0001725053,0.001871866],"genre_scores_gemma":[0.00001594588,0.9585096,0.0395617,0.00007242608,0.001033055,0.00001633511,0.00006184822,0.00008803683,0.0006411058],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.995663,"threshold_uncertainty_score":0.9995292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2612329522","doi":"10.1039/c7md00381a","title":"A systematic analysis of atomic protein–ligand interactions in the PDB","year":2017,"lang":"en","type":"article","venue":"MedChemComm","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":593,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Structural Genomics Consortium; Toronto Public Health","funders":"Ontario Ministry of Research, Innovation and Science; Fundação de Amparo à Pesquisa do Estado de São Paulo; Ontario Genomics Institute; European Federation of Pharmaceutical Industries and Associations; Novartis Pharma; Wellcome Trust; Genome Canada; Ontario Genomics; Pfizer","keywords":"Protein Data Bank (RCSB PDB); Ligand (biochemistry); Folding (DSP implementation); Stacking; Amide; Hydrogen bond; Chemistry; Protein Data Bank; Protein ligand; Crystallography; Small molecule; Molecule; Stereochemistry; Protein folding; Protein structure; Computational biology; Biology; Biochemistry; Receptor","retraction":null,"screen_n_in":null,"score":{"opus":0.04211556220920454,"gpt":0.3633796546909954,"spread":0.3212640924817908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001482487,0.00008909251,0.0003276278,0.0002714157,0.0001499772,0.0002328054,0.001908184,0.00001702769,0.000005177159],"category_scores_gemma":[0.0006459674,0.00006127195,0.0001538828,0.0005558653,0.0000563057,0.0004001729,0.0002766906,0.0001252794,0.000009973514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004170685,"about_ca_system_score_gemma":0.00004873698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001704297,"about_ca_topic_score_gemma":0.0002696398,"domain_scores_codex":[0.9986646,0.0003615362,0.0003543531,0.0001935349,0.0003030181,0.0001229477],"domain_scores_gemma":[0.9974492,0.0007792301,0.0003384909,0.001348623,0.00005968534,0.00002472969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007508005,0.002146655,0.04363319,0.0101718,0.005964723,0.0001647393,0.06076351,0.03708578,0.0179889,0.8087165,0.0009205787,0.01236861],"study_design_scores_gemma":[0.0003303256,0.00002069445,0.115696,0.001073588,0.0003024556,0.00001390232,0.0002914721,0.8587407,0.007714012,0.01554983,0.00006833983,0.0001986429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8131927,0.00005785005,0.1826282,0.001673387,0.0001289669,0.0004219942,0.000002813724,0.00001849324,0.00187563],"genre_scores_gemma":[0.9901016,8.912273e-7,0.009652462,0.00006590485,0.00001299521,0.00008713343,0.000001530974,0.000003243269,0.00007426277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.821655,"threshold_uncertainty_score":0.3545913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3092125766","doi":"10.1038/s41467-020-18709-w","title":"Crystallographic and electrophilic fragment screening of the SARS-CoV-2 main protease","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":541,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Helen and Martin Kimmel Center for Molecular Design, Weizmann Institute of Science; Novartis Pharma; Medical Research Council; Ministero dello Sviluppo Economico; Astex Pharmaceuticals; Hungarian Science Foundation; Diamond Light Source; Wellcome Trust; European Federation of Pharmaceutical Industries and Associations; Merck KGaA; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; Pfizer; AstraZeneca; Eli Lilly and Company; Ontario Ministry of Economic Development and Innovation; Israel Science Foundation; Cancer Research UK; Israel Cancer Research Fund","keywords":"Protease; Proteases; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Covalent bond; Coronavirus disease 2019 (COVID-19); Electrophile; Chemistry; Virology; Computational biology; Coronavirus; 2019-20 coronavirus outbreak; Dimer; Combinatorial chemistry; Biology; Enzyme; Biochemistry; Medicine; Outbreak","retraction":null,"screen_n_in":null,"score":{"opus":0.03969495528907605,"gpt":0.3189892223445874,"spread":0.2792942670555114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003026344,0.00009405958,0.0001133465,0.00005928352,0.0002218288,0.00005516487,0.00236234,0.00007670261,6.020614e-7],"category_scores_gemma":[0.0002826115,0.00007478116,0.00007519389,0.0009229833,0.0001503933,0.0001737888,0.001505623,0.0006489546,5.500667e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001495342,"about_ca_system_score_gemma":0.00008956909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001075764,"about_ca_topic_score_gemma":0.00003565626,"domain_scores_codex":[0.9987956,0.0004481438,0.000192011,0.0002027532,0.000241405,0.0001200322],"domain_scores_gemma":[0.998102,0.0003310426,0.0001221609,0.001312939,0.00009146798,0.00004039027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002309793,0.0002220614,0.003949106,0.00007000998,0.0001049577,0.000002568652,0.002291668,0.001777257,0.150394,0.821068,0.002283454,0.01781374],"study_design_scores_gemma":[0.001117017,0.000216952,0.1306357,0.0001650899,0.0000680426,0.00006274693,0.0001028299,0.7272209,0.03130656,0.06005227,0.04839554,0.000656368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2541388,0.008751526,0.5877579,0.1468576,0.0001000443,0.001189138,0.00002940077,0.0001693815,0.001006238],"genre_scores_gemma":[0.847701,0.00003552108,0.1504485,0.001767245,0.00001217841,0.00002460709,0.000003328853,0.000005595303,0.000002068185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7610158,"threshold_uncertainty_score":0.4389856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3009970748","doi":"10.1002/minf.202000028","title":"Rapid Identification of Potential Inhibitors of SARS‐CoV‐2 Main Protease by Deep Docking of 1.3 Billion Compounds","year":2020,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":518,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute on Deafness and Other Communication Disorders; Canadian Institutes of Health Research","keywords":"Docking (animal); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Virtual screening; Coronavirus disease 2019 (COVID-19); Drug discovery; Protease; Coronavirus; Computational biology; Drug development; 2019-20 coronavirus outbreak; Drug; Computer science; Virology; Infectious disease (medical specialty); Medicine; Chemistry; Outbreak; Biology; Bioinformatics; Pharmacology; Disease; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.01770774515941695,"gpt":0.2675397446277249,"spread":0.2498319994683079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000548538,0.000127321,0.000256075,0.0001578871,0.00003175701,0.00004750022,0.0005906628,0.00005630055,0.000001552178],"category_scores_gemma":[0.0001810599,0.000130918,0.000128304,0.0006829659,0.00008296314,0.0005344343,0.0002802553,0.00009846952,0.000002931578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002646148,"about_ca_system_score_gemma":0.00009912228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009069945,"about_ca_topic_score_gemma":1.547731e-7,"domain_scores_codex":[0.9977773,0.0001513383,0.001159707,0.0001228827,0.0006503648,0.0001383451],"domain_scores_gemma":[0.9984233,0.00006343013,0.0008915254,0.0003425742,0.000224822,0.00005438801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000274981,0.0001161654,0.00004649526,0.0007267531,0.00006011453,0.000003516054,0.004676588,0.1225891,0.8478622,0.00595331,0.0004129103,0.01752541],"study_design_scores_gemma":[0.000209265,0.00005985113,0.00007171182,0.00002992168,0.000009883341,0.000002977155,0.00007806553,0.4812697,0.5172444,0.0008678485,0.00008169526,0.00007475061],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3354263,0.00005894709,0.6639325,0.0001617696,0.00006984203,0.0002283043,0.0000162642,0.00001853764,0.00008758295],"genre_scores_gemma":[0.9111981,0.000005463473,0.08859154,0.0001519416,0.000009323682,0.000005830558,0.000029348,0.00000775156,6.825388e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5757719,"threshold_uncertainty_score":0.533868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135817448","doi":"10.1038/sj.bjp.0707515","title":"Towards the development of universal, fast and highly accurate docking/scoring methods: a long way to go","year":2007,"lang":"en","type":"review","venue":"British Journal of Pharmacology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":509,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Docking (animal); Computer science; Virtual screening; Drug discovery; Drug development; Data science; Machine learning; Artificial intelligence; Bioinformatics; Drug; Pharmacology; Medicine; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1160150546054236,"gpt":0.4481378550656607,"spread":0.3321228004602371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00550632,0.0003063463,0.001353857,0.0005407545,0.0001714868,0.0001790213,0.001858447,0.0001368454,0.00002154405],"category_scores_gemma":[0.0001981598,0.0002689262,0.000306521,0.0008647499,0.000110528,0.0004187736,0.001061948,0.0007954558,0.00000507969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003038,"about_ca_system_score_gemma":0.001354092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001192549,"about_ca_topic_score_gemma":0.0000123282,"domain_scores_codex":[0.995608,0.001657791,0.001496625,0.0003844931,0.0004569103,0.0003961746],"domain_scores_gemma":[0.9959281,0.001915438,0.001375513,0.0001336906,0.000440351,0.0002069169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000998918,0.00004363311,4.228139e-7,0.0008208319,0.0003397656,0.000467437,0.0004563898,0.0007074343,0.00002547038,0.0002255653,0.0005506473,0.9963524],"study_design_scores_gemma":[0.0006083756,0.0001283082,0.0001903341,0.005564206,0.0004848969,0.008323358,0.00004352839,0.0008236832,0.0005863718,0.0002642935,0.9825409,0.0004417566],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001860005,0.503598,0.4945639,0.000080948,0.001205426,0.0002331923,0.000004615004,0.000009360764,0.0001184999],"genre_scores_gemma":[0.00008850567,0.5976304,0.4018228,0.0001331857,0.0002611479,0.000007020576,0.000001197078,0.00002129164,0.00003450051],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9959106,"threshold_uncertainty_score":0.9999763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2605952223","doi":"10.1186/s13321-017-0209-z","title":"SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":509,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Benchmark (surveying); Computer science; Binding affinities; Binary number; Boosting (machine learning); Drug discovery; Drug target; Affinities; Gradient boosting; Machine learning; Binary classification; Artificial intelligence; Data mining; Bioinformatics; Support vector machine; Random forest; Mathematics; Chemistry; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06109063848381403,"gpt":0.3506717947180562,"spread":0.2895811562342422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002596968,0.0002055158,0.000396856,0.0001372718,0.0009208538,0.001087234,0.001423402,0.00005717106,0.000001123242],"category_scores_gemma":[0.00205195,0.0001788413,0.0002246725,0.0001053777,0.00009116451,0.003113128,0.0005214381,0.0002790877,5.413373e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001354026,"about_ca_system_score_gemma":0.0002050542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004961287,"about_ca_topic_score_gemma":3.438979e-7,"domain_scores_codex":[0.9978514,0.00002256636,0.001036197,0.0001271898,0.000562957,0.000399713],"domain_scores_gemma":[0.995802,0.0008332785,0.002391178,0.0004203856,0.000420639,0.0001325185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002459804,0.0005077032,0.0222003,0.00377555,0.0007814259,0.00006643806,0.1478195,0.6253841,0.002282974,0.01154064,0.001568731,0.1838266],"study_design_scores_gemma":[0.0005870513,0.00004643034,0.0002742142,0.0002312637,0.0000246637,0.0003204383,0.001403382,0.9899146,0.004450691,0.002140689,0.0004030989,0.0002034786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3312326,0.00006072224,0.6654793,0.0001009382,0.0005423938,0.0001443581,0.00001770241,0.00002470625,0.002397204],"genre_scores_gemma":[0.3024243,0.00000625333,0.6971593,0.00004924451,0.0002675636,0.000003234742,0.000004036769,0.00001329157,0.00007272822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3645305,"threshold_uncertainty_score":0.9999498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2346950316","doi":"10.1093/bioinformatics/btw228","title":"Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":470,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Program for New Century Excellent Talents in University; U.S. Food and Drug Administration; National Natural Science Foundation of China; Stowers Institute for Medical Research","keywords":"Similarity (geometry); Drug repositioning; Drug; Computer science; Disease; Random walk; Machine learning; Drug development; Data mining; Artificial intelligence; Mathematics; Medicine; Statistics; Pharmacology","retraction":null,"screen_n_in":null,"score":{"opus":0.02364108547326174,"gpt":0.2691134950196628,"spread":0.2454724095464011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005054561,0.0001622003,0.0001915188,0.0001499713,0.0001980237,0.0002130904,0.0003238339,0.00004509043,0.000004216943],"category_scores_gemma":[0.0001734837,0.0001126104,0.00006417168,0.0002088895,0.000080366,0.0007263161,0.0001674608,0.00008940382,0.00002620953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006381188,"about_ca_system_score_gemma":0.0001019224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000779712,"about_ca_topic_score_gemma":0.00000123,"domain_scores_codex":[0.9985952,0.0001448108,0.0003634389,0.0001955812,0.0004883358,0.0002126511],"domain_scores_gemma":[0.997887,0.001259014,0.0001612273,0.0004022686,0.0001809313,0.0001095946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004480107,0.00008355886,0.0002402257,0.00007579318,0.00004051007,0.00001662855,0.001326389,0.009048631,0.0001354261,0.01115449,0.002175495,0.9756581],"study_design_scores_gemma":[0.001146242,0.0000559922,0.002661139,0.0001145092,0.000007127051,0.00001966971,0.00003214039,0.9879351,0.001237794,0.004278034,0.002313572,0.000198643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005537219,0.00003897664,0.9908693,0.001605967,0.0002572448,0.0001864233,0.00001952836,0.0001400158,0.001345273],"genre_scores_gemma":[0.1084383,0.000014843,0.8899248,0.001493781,0.00005178587,0.00001113863,0.000006207491,0.000008824815,0.00005037913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9788865,"threshold_uncertainty_score":0.4592119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2520082135","doi":"10.1186/s13195-016-0207-9","title":"Drug development in Alzheimer’s disease: the path to 2025","year":2016,"lang":"en","type":"review","venue":"Alzheimer s Research & Therapy","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":455,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Eli Lilly (Canada)","funders":"Biogen; Danone; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; Sanofi; National Institute on Aging; Eli Lilly and Company; Alzheimer's Drug Discovery Foundation","keywords":"Drug development; Disease; Clinical trial; Standardization; Medicine; Risk analysis (engineering); Data sharing; Set (abstract data type); Computer science; Psychology; Drug; Alternative medicine; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.2568617205341319,"gpt":0.4792626595672915,"spread":0.2224009390331596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008306857,0.0006921205,0.001145015,0.001112607,0.0004656954,0.0006124501,0.006654041,0.0001495195,0.0001282537],"category_scores_gemma":[0.0002456608,0.0003961165,0.0004186415,0.003120408,0.0002149587,0.0004681209,0.002191136,0.001122591,0.001959346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002798864,"about_ca_system_score_gemma":0.005112626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008299985,"about_ca_topic_score_gemma":0.00002987905,"domain_scores_codex":[0.9881778,0.005313473,0.001023317,0.00157043,0.002519973,0.001395035],"domain_scores_gemma":[0.9912456,0.005204275,0.0001970946,0.002353762,0.0004039218,0.0005953159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001948019,0.0001098231,0.000002289315,0.0000947162,0.0006175937,0.00005015932,0.0006010643,0.00001665104,1.647177e-7,0.006477795,0.00920058,0.9828097],"study_design_scores_gemma":[0.0002156522,0.00003425697,0.0000982546,0.003218,0.00004581131,0.000004604756,0.000007506089,0.0001264003,0.000008320237,0.00336549,0.9923418,0.0005339599],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003165709,0.9848508,0.007016423,0.00340384,0.0005259397,0.003515932,0.00002236313,0.00009168569,0.000569856],"genre_scores_gemma":[0.00002149193,0.9873414,0.009267572,0.0004181926,0.0003056729,0.002168689,0.00002306862,0.00008878783,0.0003651104],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9831412,"threshold_uncertainty_score":0.9998491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116633922","doi":"10.1038/nrd1523","title":"The role of the medicinal chemist in drug discovery — then and now","year":2004,"lang":"en","type":"review","venue":"Nature Reviews Drug Discovery","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":446,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bombardier (Canada)","funders":"","keywords":"Chemist; Drug discovery; Perspective (graphical); Engineering ethics; Data science; Chemistry; Computer science; Engineering; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01231528339593889,"gpt":0.3197896834229698,"spread":0.3074744000270309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004251414,0.000991897,0.002826272,0.0002141581,0.0003020085,0.000706104,0.004846414,0.0004434042,0.000002703049],"category_scores_gemma":[0.0009611507,0.0004835314,0.001358811,0.001870495,0.0005295445,0.001472341,0.002157973,0.002878797,0.00001312213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004902877,"about_ca_system_score_gemma":0.001817407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007324189,"about_ca_topic_score_gemma":0.0001788187,"domain_scores_codex":[0.9929068,0.001954876,0.001958092,0.001283726,0.001234065,0.0006624057],"domain_scores_gemma":[0.992783,0.002910314,0.001701137,0.002386478,0.00009287464,0.0001262487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006614881,0.0000962076,0.00001892654,0.009811805,0.00009459103,0.000008413896,0.0003419569,0.00004923097,0.000001621049,0.04882272,0.0009509014,0.939797],"study_design_scores_gemma":[0.000216469,0.000008885,0.00005924139,0.03273149,0.0002373304,0.00008209908,0.00004350383,0.00009940106,0.00002234043,0.01599783,0.9499744,0.0005270596],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002891535,0.9935229,0.0006838901,0.0007225972,0.00113768,0.00211815,0.00006511287,0.0000296075,0.001691176],"genre_scores_gemma":[0.000250898,0.9967506,0.001047752,0.0001862935,0.0003133662,0.0002221244,0.00002849751,0.00006056109,0.001139897],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9490234,"threshold_uncertainty_score":0.9997616,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035604179","doi":"10.1038/s41698-020-0122-1","title":"Machine learning approaches to drug response prediction: challenges and recent progress","year":2020,"lang":"en","type":"review","venue":"npj Precision Oncology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":436,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; Vector Institute; Hospital for Sick Children; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Modalities; Predictive modelling; Drug response; Profiling (computer programming); Computational model; Data science; Risk analysis (engineering); Drug; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2922370127074235,"gpt":0.4045351230124214,"spread":0.1122981103049979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004002076,0.000514445,0.001713738,0.0004836039,0.0001781877,0.0001535385,0.001304204,0.0003781124,0.00002015694],"category_scores_gemma":[0.001452345,0.000431697,0.000212321,0.0007492673,0.00009340716,0.0002696589,0.002292182,0.0009940938,0.0001303837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004454919,"about_ca_system_score_gemma":0.0009555305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.096754e-7,"about_ca_topic_score_gemma":0.000003388479,"domain_scores_codex":[0.9900581,0.006568035,0.0008722219,0.001527379,0.0005887768,0.0003855518],"domain_scores_gemma":[0.9930341,0.005384143,0.0004580985,0.0006310592,0.0001057461,0.0003868384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001411182,0.00009093779,7.781845e-7,0.0007141648,0.00006196382,0.00006345662,0.001379798,0.0002905797,4.422209e-8,0.002861255,0.0004935679,0.9939023],"study_design_scores_gemma":[0.0002396141,0.0007508541,0.00003708823,0.001244842,0.00007613268,0.0003049012,0.00002224505,0.01515802,4.458638e-7,0.001214379,0.9806171,0.0003343794],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002375222,0.9535897,0.03336268,0.009354393,0.0009213935,0.001320544,0.00002094441,0.0002695248,0.001158474],"genre_scores_gemma":[0.000003866242,0.8915158,0.1074545,0.0001133206,0.00024157,0.0003638405,0.0000265198,0.00004336192,0.0002371979],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9935679,"threshold_uncertainty_score":0.9998135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034192743","doi":"10.1021/ci600406v","title":"Solvated Interaction Energy (SIE) for Scoring Protein−Ligand Binding Affinities. 1. Exploring the Parameter Space","year":2007,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":427,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Biotechnology Research Institute; McGill University; TransCanada (Canada)","funders":"","keywords":"Solvation; van der Waals force; Chemistry; Binding energy; Thermodynamics; Enthalpy; Intermolecular force; Protein ligand; Affinities; Scaling; Entropy (arrow of time); Interaction energy; Implicit solvation; Ligand (biochemistry); Computational chemistry; Physical chemistry; Molecule; Physics; Atomic physics; Stereochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.08741547101091114,"gpt":0.3126376086117445,"spread":0.2252221376008334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167841,0.00008800242,0.0001227164,0.0001861251,0.00009754367,0.0002834575,0.0001989977,0.00003313829,4.758839e-7],"category_scores_gemma":[0.0003028642,0.00006483444,0.00007378498,0.0001475285,0.00001588429,0.003575298,0.00008168494,0.0001716705,4.461809e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006723475,"about_ca_system_score_gemma":0.00005311143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005754529,"about_ca_topic_score_gemma":3.716604e-7,"domain_scores_codex":[0.9989498,0.00001917954,0.0005620343,0.00006523241,0.0002447238,0.0001590487],"domain_scores_gemma":[0.9988259,0.0004266149,0.0003220181,0.00007917263,0.0002775625,0.00006874205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000424459,0.0000538337,0.00002066332,0.0001461757,0.0001125904,0.000003541164,0.009604728,0.4673785,0.08848019,0.06378272,0.00009879255,0.3698938],"study_design_scores_gemma":[0.0002896976,0.00002570084,0.000002764674,0.00009862604,0.000005932046,0.00004315434,0.0003949568,0.8671982,0.1273671,0.00376715,0.0007290865,0.0000776486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4603328,0.00001614494,0.5391326,0.0002336351,0.0001720448,0.00004746791,2.543453e-7,0.000009840634,0.00005525679],"genre_scores_gemma":[0.913423,0.00001463101,0.08627584,0.0001626675,0.0001077143,0.000007097258,0.000001441021,0.000003904721,0.000003722402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4530902,"threshold_uncertainty_score":0.2733387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3027975282","doi":"10.1021/acscentsci.0c00229","title":"Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery","year":2020,"lang":"en","type":"article","venue":"ACS Central Science","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":425,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Canadian Cancer Society Research Institute","keywords":"Docking (animal); Drug discovery; Virtual screening; Computer science; Chemical database; Deep learning; Artificial intelligence; Training set; Computational biology; Machine learning; Bioinformatics; Biology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02139345603797667,"gpt":0.2861229903752512,"spread":0.2647295343372746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004392377,0.0001437137,0.0001666343,0.00009711413,0.0002764989,0.0003389117,0.001224015,0.00002741394,0.000007970887],"category_scores_gemma":[0.0005292604,0.0001309324,0.00007591303,0.001225594,0.0001943037,0.002596304,0.0002605177,0.0001340981,0.000001480016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215776,"about_ca_system_score_gemma":0.000357019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001632877,"about_ca_topic_score_gemma":0.000009035964,"domain_scores_codex":[0.997912,0.00005631118,0.0002842639,0.0005460996,0.0007296307,0.0004716459],"domain_scores_gemma":[0.9988456,0.0004073617,0.0002100686,0.0002026207,0.0001443533,0.0001899629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004100438,0.00002546144,0.002352176,0.000048611,0.000006663762,0.000001957727,0.003377209,0.8967288,0.02196084,0.03563822,0.000021219,0.03979787],"study_design_scores_gemma":[0.0004312336,0.00007763393,0.01133314,0.00001424274,0.000006418009,0.000001676276,0.000166889,0.9322808,0.0508619,0.004517917,0.0001500245,0.0001581468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3450876,0.00002708171,0.6536611,0.0006975441,0.0002216427,0.0002072981,0.000004270005,0.00004314929,0.00005026042],"genre_scores_gemma":[0.8748867,0.000001778222,0.1245634,0.0004625915,0.00005791965,0.000005995918,0.000009906988,0.000006379091,0.000005318962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.529799,"threshold_uncertainty_score":0.5339268,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389991855","doi":"10.1038/s41586-023-06887-8","title":"Discovery of a structural class of antibiotics with explainable deep learning","year":2023,"lang":"en","type":"article","venue":"Nature","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":420,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Population Health Research Institute","funders":"Hansjörg Wyss Institute for Biologically Inspired Engineering, Harvard University; National Institute of Allergy and Infectious Diseases; Broad Institute; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Princeton University; National Cancer Institute; National Institutes of Health; National Science Foundation; James S. McDonnell Foundation; Volkswagen Foundation","keywords":"Antibiotics; Cytotoxicity; Computational biology; Artificial intelligence; Antibiotic resistance; Staphylococcus aureus; Drug discovery; Computer science; Machine learning; Biology; Chemistry; Bioinformatics; Microbiology; Bacteria; Biochemistry; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.009173553297770023,"gpt":0.2837470612100684,"spread":0.2745735079122983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002531126,0.00009631354,0.000178297,0.0001545206,0.00005003045,0.00004474592,0.00045268,0.0001968936,0.00000157877],"category_scores_gemma":[0.0001486744,0.0000752967,0.00005142211,0.001118619,0.00005506808,0.000520797,0.0002277756,0.0007007082,0.00000195151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002050981,"about_ca_system_score_gemma":0.00008509062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007554479,"about_ca_topic_score_gemma":0.000005169181,"domain_scores_codex":[0.9989423,0.00009619224,0.0001582653,0.0002207009,0.0004095341,0.0001729926],"domain_scores_gemma":[0.9991183,0.0003346096,0.0001397992,0.0002453699,0.0001382536,0.00002371731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008299331,0.00003930505,0.02031778,0.0003159387,0.00009929592,0.00006327299,0.002187534,0.6589045,0.008513318,0.2937456,0.000309165,0.01542132],"study_design_scores_gemma":[0.000518892,0.0002274782,0.1434877,0.0001147943,0.00001408244,0.00002565352,0.0003768998,0.7985713,0.04353112,0.0124906,0.0003954366,0.000246108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8838784,0.000181754,0.1147815,0.0002315647,0.0002153814,0.00008343471,0.00000475464,0.00007455263,0.0005486266],"genre_scores_gemma":[0.9579177,0.000005748724,0.04178811,0.00003756085,0.00002631711,1.995294e-7,0.000009004269,0.000008173487,0.0002071565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2812549,"threshold_uncertainty_score":0.307051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093934881","doi":"10.48550/arxiv.2010.09885","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":397,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Transformer; PubChem; Artificial intelligence; Machine learning; Visualization; Property (philosophy); Transfer of learning; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07861375255540573,"gpt":0.2193217133781824,"spread":0.1407079608227767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000495756,0.0003829208,0.0004085464,0.000172926,0.0001880927,0.0001854608,0.001675105,0.0002917983,0.00001235221],"category_scores_gemma":[0.0001141143,0.0003899346,0.0003743689,0.0006367557,0.00004300055,0.0005370976,0.001979721,0.0005331864,0.00002104731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002689519,"about_ca_system_score_gemma":0.0005074237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000185335,"about_ca_topic_score_gemma":0.000005875572,"domain_scores_codex":[0.9972091,0.0002592341,0.0002862145,0.00162159,0.0001854753,0.0004383533],"domain_scores_gemma":[0.9981419,0.0002132247,0.0002158554,0.0009133155,0.000279792,0.0002359338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009192741,0.0002850884,0.0006179268,0.0005020691,0.0003421789,0.0001377767,0.002945886,0.9055,0.0004601751,0.08591474,0.0007286262,0.002473632],"study_design_scores_gemma":[0.0008228169,0.00008535315,0.000235981,0.00007448326,0.00009986284,0.000003764722,0.00008459933,0.9575139,0.0005491877,0.03899616,0.001119202,0.0004147382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07098959,0.00003137492,0.9241995,0.0004124051,0.0006176859,0.000965506,0.00009334871,0.0006489404,0.002041712],"genre_scores_gemma":[0.7831627,0.00001797479,0.215934,0.0002608376,0.0001436791,0.00001311706,0.0001013003,0.00003973941,0.0003266121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7121732,"threshold_uncertainty_score":0.9998553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044334750","doi":"10.1186/s13321-020-00450-7","title":"A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions","year":2020,"lang":"en","type":"review","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":391,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Drug repositioning; Computer science; Drug discovery; Process (computing); Data science; Multidisciplinary approach; Drug development; Computational model; Drug; Field (mathematics); Risk analysis (engineering); Artificial intelligence; Bioinformatics; Medicine; Pharmacology","retraction":null,"screen_n_in":null,"score":{"opus":0.2181327886717617,"gpt":0.3515936227001733,"spread":0.1334608340284116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001497642,0.0003385066,0.00179736,0.000285606,0.00006196021,0.0001371991,0.0008187839,0.0001091116,0.000004166084],"category_scores_gemma":[0.0002710078,0.0002855757,0.0004777066,0.000394372,0.00008915738,0.001286539,0.0003047861,0.000571431,0.000001374051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384257,"about_ca_system_score_gemma":0.002633035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.805091e-7,"about_ca_topic_score_gemma":1.161242e-7,"domain_scores_codex":[0.996305,0.0001603857,0.002498222,0.0001666628,0.0007076909,0.0001620553],"domain_scores_gemma":[0.9941668,0.00097678,0.003891917,0.0003016914,0.0004529719,0.0002098227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001024509,0.00003644765,6.829781e-9,0.1131272,0.0001921696,0.00001591917,0.0008058241,0.00009479559,7.187852e-9,0.01811893,0.002396567,0.8652111],"study_design_scores_gemma":[0.000115699,0.00005195759,3.481725e-7,0.07955093,0.000379804,0.002638835,0.0002175658,0.003842719,7.672243e-7,0.00373689,0.9092293,0.0002351831],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.000637e-7,0.9578421,0.03416902,0.0005456329,0.0001732407,0.000259228,0.00002068876,0.00002048325,0.006969477],"genre_scores_gemma":[9.128872e-7,0.8903353,0.1093511,0.0001237671,0.0001022254,0.000008767922,0.0000440959,0.00001543953,0.00001835894],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9068328,"threshold_uncertainty_score":0.9999596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386607677","doi":"10.1038/s41573-023-00774-7","title":"Artificial intelligence for natural product drug discovery","year":2023,"lang":"en","type":"review","venue":"Nature Reviews Drug Discovery","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; Simon Fraser University","funders":"Duke Cancer Institute; National Center for Complementary and Integrative Health; Industrial Biotechnology Innovation Centre; U.S. National Library of Medicine; National Institute of Diabetes and Digestive and Kidney Diseases; Biotechnology and Biological Sciences Research Council; Center for Gastrointestinal Biology and Disease, School of Medicine, University of North Carolina at Chapel Hill; Vlaamse regering; Ministry of Science and ICT, South Korea; Novo Nordisk; National Research Foundation of Korea; Directorate for Biological Sciences; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Deutsche Forschungsgemeinschaft; North Carolina Biotechnology Center; Agence Nationale de la Recherche; Novo Nordisk Fonden; Netherlands eScience Center; National Cancer Institute; National Research Foundation; National Science Foundation; UK Research and Innovation; University of Chicago; Universiteit Leiden; Korea Advanced Institute of Science and Technology","keywords":"Drug discovery; Natural product; Drug; Computer science; Data science; Pharmacology; Computational biology; Medicine; Chemistry; Bioinformatics; Biology; Stereochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.09647326018686911,"gpt":0.4166303186912961,"spread":0.320157058504427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.006424513,0.002146056,0.005850778,0.001126755,0.000495039,0.002945397,0.00662292,0.0005637686,0.00000717062],"category_scores_gemma":[0.004071647,0.001617029,0.004445318,0.004554811,0.0002492506,0.005326626,0.002289788,0.003926757,0.0006391933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007612124,"about_ca_system_score_gemma":0.002121268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002091376,"about_ca_topic_score_gemma":0.00007421825,"domain_scores_codex":[0.986818,0.002247594,0.003917394,0.003896602,0.00155898,0.001561445],"domain_scores_gemma":[0.9878814,0.005626142,0.002348142,0.003517578,0.0003355819,0.0002911439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001195176,0.0001340071,2.021984e-7,0.02748945,0.0002245946,0.00002731287,0.0001111512,0.000124244,4.342989e-7,0.08843057,0.01791156,0.8655345],"study_design_scores_gemma":[0.00005576557,0.00002164348,0.000001170071,0.02114831,0.000640093,0.0000697348,0.00001492121,0.001524545,0.00002533151,0.02956017,0.9451371,0.001801201],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001524644,0.856123,0.1245188,0.0006613706,0.01053414,0.007136061,0.000406118,0.0004784024,0.0001406153],"genre_scores_gemma":[0.00001098411,0.9607776,0.02623576,0.0003992847,0.003233523,0.002044517,0.0008861988,0.0002828896,0.006129207],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9272255,"threshold_uncertainty_score":0.999128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210617107","doi":"10.1038/s41596-021-00659-2","title":"Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking","year":2022,"lang":"en","type":"review","venue":"Nature Protocols","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":389,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC; Vancouver Coastal Health Research Institute; Fondazione Zegna","keywords":"Virtual screening; Computer science; Workflow; Chemical database; Docking (animal); Drug discovery; Bioinformatics; Database; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.07732661057771312,"gpt":0.3948962207137753,"spread":0.3175696101360622,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001350226,0.0005998004,0.001610393,0.0004156485,0.0002186762,0.0004231948,0.002876613,0.0005743895,0.0001128807],"category_scores_gemma":[0.0005650067,0.0004755524,0.0004775326,0.002146966,0.0001197077,0.0007541152,0.001006405,0.002666109,0.000006386153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001279966,"about_ca_system_score_gemma":0.001137248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002076617,"about_ca_topic_score_gemma":9.421124e-7,"domain_scores_codex":[0.9952289,0.0007790488,0.00110408,0.001046945,0.001291223,0.0005497792],"domain_scores_gemma":[0.9958344,0.002111191,0.0009021505,0.0008896672,0.000133325,0.0001292986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004422773,0.000121913,0.000001378929,0.002504997,0.0001057561,0.00002940732,0.0001686596,0.001002294,0.000001534584,0.1480833,0.00002463518,0.8479119],"study_design_scores_gemma":[0.0001243568,0.0002812906,6.204226e-7,0.006904732,0.00009947501,0.0001029315,0.00003619826,0.009963805,0.0008209635,0.01256676,0.9683126,0.00078631],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[4.677633e-7,0.2942228,0.6619292,0.0000258919,0.0001332767,0.04303465,0.00003232598,0.0001489969,0.0004723677],"genre_scores_gemma":[0.00007877973,0.102964,0.6366185,0.0002584874,0.000762991,0.2587235,0.0003044108,0.0002331017,0.00005628061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9682879,"threshold_uncertainty_score":0.9997696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2805002767","doi":"10.1021/acs.jcim.7b00690","title":"Reinforced Adversarial Neural Computer for <i>de Novo</i> Molecular Design","year":2018,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research","funders":"Tata Steel; Ministry of Education and Science of the Russian Federation","keywords":"Chemical space; Computer science; Artificial neural network; Artificial intelligence; Reinforcement learning; Deep learning; Generator (circuit theory); Set (abstract data type); Representation (politics); Adversarial system; Differentiable function; Machine learning; Generative grammar; Theoretical computer science; Drug discovery; Programming language; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03560623312534594,"gpt":0.3017826192751583,"spread":0.2661763861498123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006901466,0.00007756464,0.000128976,0.00009503308,0.00004563214,0.0001637876,0.0002484531,0.00004868151,0.0000011577],"category_scores_gemma":[0.0001313854,0.00006854877,0.00007604339,0.00008954227,0.00002543999,0.001714181,0.00007946416,0.0001034994,0.0000011192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003722384,"about_ca_system_score_gemma":0.0001185874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.923124e-7,"about_ca_topic_score_gemma":8.835605e-9,"domain_scores_codex":[0.9990987,0.00003061943,0.0004672236,0.00005864865,0.0002077239,0.0001371272],"domain_scores_gemma":[0.9990243,0.0001442524,0.0002103227,0.00007794094,0.0004454872,0.00009771484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000127088,0.000005431183,4.413328e-7,0.00001449795,0.00001542465,9.629701e-7,0.0009058584,0.9557139,0.009880625,0.008314987,0.0001987639,0.02482205],"study_design_scores_gemma":[0.0007976025,0.0001083908,4.753975e-7,0.00001788848,0.000007393972,0.0001159717,0.000009577232,0.9730382,0.02196175,0.003570337,0.0002949479,0.00007743629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1037937,0.00001113033,0.8953728,0.0004295202,0.0002479393,0.00007880718,6.860747e-7,0.00001418727,0.00005126178],"genre_scores_gemma":[0.4734826,0.000001860314,0.5252,0.001121881,0.0001883787,0.000001094165,0.000001246534,0.000002166505,7.748657e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3701728,"threshold_uncertainty_score":0.2795338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3087284646","doi":"10.1186/s13062-020-00267-2","title":"AMDock: a versatile graphical tool for assisting molecular docking with Autodock Vina and Autodock4","year":2020,"lang":"en","type":"article","venue":"Biology Direct","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":373,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Calgary","funders":"Universidad de Medellín","keywords":"Docking (animal); Graphical user interface; AutoDock; Visualization; Scripting language; Computer science; Structural bioinformatics; Computational biology; Protein–ligand docking; Software; Python (programming language); Programming language; Biology; Bioinformatics; Data mining; Virtual screening; Protein structure; Drug discovery","retraction":null,"screen_n_in":null,"score":{"opus":0.02286481841534719,"gpt":0.2904815327576179,"spread":0.2676167143422707,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003401916,0.0001686349,0.0002597169,0.00006921393,0.0001414738,0.00009071835,0.0003516742,0.00007503916,0.000003560212],"category_scores_gemma":[0.0005154071,0.0001424329,0.0000714801,0.0003488454,0.00009218661,0.0001650635,0.0002551901,0.0001179332,0.000002812172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002514573,"about_ca_system_score_gemma":0.0001140003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001091724,"about_ca_topic_score_gemma":0.000001871213,"domain_scores_codex":[0.9985569,0.0002450242,0.0001925771,0.0006030067,0.0001120459,0.0002904198],"domain_scores_gemma":[0.9985918,0.0009488243,0.00009311198,0.0001986499,0.00006686357,0.0001007288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004574345,0.0001891258,0.06071528,0.0002718555,0.0006299581,0.0001862202,0.002548069,0.03875202,0.02369171,0.4648974,0.001303729,0.4063572],"study_design_scores_gemma":[0.001369588,0.0009009031,0.03786164,0.00004894825,0.0000499679,0.00005248869,0.00001590893,0.926872,0.00365446,0.01659621,0.01195278,0.0006250739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2811547,0.0002038477,0.7151983,0.002274104,0.0001095329,0.0002446315,0.00001049775,0.0002238953,0.0005804102],"genre_scores_gemma":[0.8559179,0.000003362071,0.1430653,0.0008901121,0.00006030415,0.00003893477,0.000007807686,0.0000116119,0.000004627781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.88812,"threshold_uncertainty_score":0.5808246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2920302906","doi":"10.1038/s41564-019-0357-1","title":"Drug repurposing for antimicrobial discovery","year":2019,"lang":"en","type":"review","venue":"Nature Microbiology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"U.S. Food and Drug Administration; Canada Research Chairs; Johns Hopkins University","keywords":"Repurposing; Drug repositioning; Antimicrobial drug; Antimicrobial; Drug discovery; Drug; Drug development; Medicine; Biology; Pharmacology; Bioinformatics; Microbiology","retraction":null,"screen_n_in":null,"score":{"opus":0.03288062829725272,"gpt":0.3663915409701106,"spread":0.3335109126728579,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007988997,0.0006733504,0.00219968,0.0004451932,0.0001385678,0.0003304852,0.002505285,0.001351625,0.000004076551],"category_scores_gemma":[0.0002253392,0.000553076,0.001177275,0.0005686273,0.00009718191,0.0004838579,0.0009912224,0.001472489,0.0001033609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002591428,"about_ca_system_score_gemma":0.001008946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000278516,"about_ca_topic_score_gemma":0.000003319375,"domain_scores_codex":[0.9962877,0.0006668505,0.0007867142,0.001526578,0.00008743807,0.0006447094],"domain_scores_gemma":[0.9955606,0.002423286,0.000654929,0.001153405,0.0001496348,0.00005814414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001132905,0.00006938764,3.030351e-7,0.009576893,0.0002791558,0.00001310001,0.00004734212,0.0000743354,0.0002312613,0.03414873,0.04530162,0.9102466],"study_design_scores_gemma":[0.0002332401,0.00003222355,1.684729e-7,0.002484419,0.0002017081,0.0004753946,6.896323e-7,0.0001220608,0.00008326989,0.0007592035,0.994998,0.000609659],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003087324,0.8631658,0.1283175,0.0002000316,0.006051842,0.001544442,0.0004436876,0.0001246033,0.000149011],"genre_scores_gemma":[0.000003358217,0.895669,0.1000296,0.0007999174,0.0006169346,0.000075641,0.001133594,0.00007719405,0.001594676],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9496964,"threshold_uncertainty_score":0.9999448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951449549","doi":"10.1038/s41467-019-09799-2","title":"Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen","year":2019,"lang":"en","type":"article","venue":"Nature Communications","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":363,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University Health Network; Hospital for Sick Children; Princess Margaret Cancer Centre; University of Toronto","funders":"Medical Research Council; Magyar Tudományos Akadémia; Brain Tumour Charity; European Commission; National Institute of Environmental Health Sciences; National Institute for Health and Care Research; National Cancer Institute; Cancer Research UK; Wellcome Trust; Bayer; AstraZeneca","keywords":"Pharmacogenomics; Drug; Computational biology; Cancer drugs; Drug discovery; Cancer; Drug development; Precision medicine; EGFR inhibitors; Computer science; Bioinformatics; Biology; Pharmacology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0267371721312943,"gpt":0.4012879858361356,"spread":0.3745508137048413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001094106,0.0001500216,0.0002378749,0.0004155118,0.0002341884,0.00005326809,0.002938236,0.00008428052,0.00002081678],"category_scores_gemma":[0.00009231169,0.0001716113,0.00007406646,0.001366283,0.00007235799,0.0005737983,0.001289215,0.00124517,0.00001850131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003555086,"about_ca_system_score_gemma":0.0003891448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000403373,"about_ca_topic_score_gemma":0.0007680791,"domain_scores_codex":[0.997638,0.001032512,0.00047977,0.0002555357,0.0004074866,0.0001866821],"domain_scores_gemma":[0.9961383,0.001434668,0.0002086822,0.001705845,0.000430155,0.00008232462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001521689,0.001677135,0.08378483,0.00003731764,0.00007218743,3.930675e-7,0.002168122,0.5159085,0.001629208,0.3828011,0.001619306,0.01028667],"study_design_scores_gemma":[0.0008722822,0.00004320407,0.4859066,0.00007980752,0.000009977799,0.000001929067,0.0001027941,0.4969805,0.0001779434,0.01152541,0.004146751,0.000152755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7524453,0.002136267,0.2177351,0.01833381,0.0008112112,0.001784723,0.0005451952,0.0002001535,0.006008189],"genre_scores_gemma":[0.7822866,0.00006323113,0.2167805,0.0005506888,0.000009460958,0.0001086775,0.0001380938,0.00001040137,0.00005242269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4021218,"threshold_uncertainty_score":0.6998104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2549286116","doi":"10.1016/j.drudis.2016.11.001","title":"Molecular dynamics-driven drug discovery: leaping forward with confidence","year":2016,"lang":"en","type":"review","venue":"Drug Discovery Today","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":358,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Drug discovery; Computational biology; Drug; Biology; Bioinformatics; Pharmacology","retraction":null,"screen_n_in":null,"score":{"opus":0.01784292173117654,"gpt":0.305276746031819,"spread":0.2874338243006425,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001300764,0.001804785,0.003274682,0.0007963988,0.0003806537,0.002790414,0.005455909,0.0003258925,0.0000242375],"category_scores_gemma":[0.0002305309,0.00127293,0.001461911,0.001616723,0.0004673791,0.006985916,0.002438169,0.001069853,0.0003528682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001622213,"about_ca_system_score_gemma":0.003844458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001160528,"about_ca_topic_score_gemma":0.0001103197,"domain_scores_codex":[0.9904486,0.001564968,0.001624026,0.002960776,0.001912439,0.001489168],"domain_scores_gemma":[0.9922816,0.002444477,0.001458387,0.003153505,0.0002482643,0.0004137501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002696205,0.0001776676,0.0000134891,0.004863993,0.0007384341,0.0005278092,0.0004508896,0.004573497,0.000002751433,0.4309755,0.001280668,0.5563684],"study_design_scores_gemma":[0.001229053,0.0001576917,0.00001584592,0.05244031,0.0009089365,0.0004913965,0.0001175859,0.02043318,0.00007897092,0.02174177,0.8973699,0.005015355],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.00004708036,0.4783971,0.5165585,0.000544797,0.0009556938,0.001097616,0.0003247474,0.000253257,0.001821216],"genre_scores_gemma":[0.001051846,0.9718328,0.01614033,0.0004702085,0.0004548701,0.0005251788,0.0004318554,0.0003557452,0.008737146],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8960893,"threshold_uncertainty_score":0.9999251,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129414710","doi":"10.1002/prot.20551","title":"Assessment of CAPRI predictions in rounds 3–5 shows progress in docking procedures","year":2005,"lang":"en","type":"article","venue":"Proteins Structure Function and Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":347,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Docking (animal); Computational biology; Macromolecular docking; Computer science; Protein–ligand docking; Searching the conformational space for docking; Protein structure; Artificial intelligence; Chemistry; Virtual screening; Biology; Biochemistry; Drug discovery; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01133100212198269,"gpt":0.2838555535211666,"spread":0.272524551399184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003061071,0.0001323529,0.0001686296,0.0003569536,0.00006173711,0.0001048558,0.0001911459,0.00007490948,0.00001088703],"category_scores_gemma":[0.0000411006,0.0001117804,0.00002752993,0.0005628372,0.00006330446,0.001046909,0.0001301258,0.0002062836,4.134219e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001054074,"about_ca_system_score_gemma":0.0002071419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001053949,"about_ca_topic_score_gemma":0.0002688554,"domain_scores_codex":[0.9988012,0.0000520406,0.0004925939,0.0001617027,0.0003140953,0.0001783447],"domain_scores_gemma":[0.9994702,0.00004590718,0.0001828929,0.00018149,0.0000736182,0.00004589953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004787719,0.0002975024,0.2232567,0.0008967955,0.00004790371,0.000002137309,0.006302358,0.2321007,0.0003393818,0.1649061,0.00007061819,0.3717319],"study_design_scores_gemma":[0.0004228184,0.00007943529,0.2888488,0.00006596048,0.000003486869,0.00001245192,0.0001335003,0.7065312,0.0001445449,0.003473906,0.0001821906,0.0001017504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2964485,0.000143858,0.7011347,0.0004621104,0.0001922054,0.0007253602,0.00001233167,0.00005895004,0.0008219556],"genre_scores_gemma":[0.7118155,0.000005692716,0.2880321,0.00006853419,0.0000322942,0.00002886376,0.000006445594,0.000003162663,0.000007370596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4744305,"threshold_uncertainty_score":0.4558273,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4379179468","doi":"10.3390/pharmaceutics15061630","title":"Biomarkers as Biomedical Bioindicators: Approaches and Techniques for the Detection, Analysis, and Validation of Novel Biomarkers of Diseases","year":2023,"lang":"en","type":"review","venue":"Pharmaceutics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":338,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Biomarker; Computational biology; Biomarker discovery; Metabolomics; Bioinformatics; Epigenetics; Medicine; Computer science; Proteomics; Biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1839054498954598,"gpt":0.4405307620192335,"spread":0.2566253121237737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001396427,0.0002681117,0.0008056779,0.00103146,0.0001054519,0.00007330866,0.0005889882,0.0001331799,9.850335e-7],"category_scores_gemma":[0.000369839,0.0001920175,0.0003597124,0.002817862,0.0004545157,0.0001452288,0.0004049134,0.0001162221,3.301186e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004085384,"about_ca_system_score_gemma":0.0002500285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000175961,"about_ca_topic_score_gemma":0.000001061588,"domain_scores_codex":[0.9979799,0.0002629112,0.0007013421,0.0004830447,0.0003935332,0.000179221],"domain_scores_gemma":[0.9953288,0.003391672,0.0007051448,0.0003635769,0.00009239175,0.0001184157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000111226,0.00008696118,0.00003078812,0.00547096,0.003597378,3.796105e-7,0.00005408371,0.00001330127,0.00001988307,0.0005536147,0.00001917203,0.9901423],"study_design_scores_gemma":[0.001102936,0.0003114535,0.0003371553,0.003043196,0.03673611,0.00006584345,0.0001279174,0.4494168,0.008267917,0.002923181,0.4964333,0.001234208],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002450795,0.5024655,0.4963591,0.00006987578,0.00009726428,0.0007044732,0.0002221013,0.00005398659,0.000003161024],"genre_scores_gemma":[0.0008772784,0.9543223,0.04440083,0.00001359073,0.00005585257,0.0001935534,0.0001045529,0.00002861039,0.000003468983],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9889082,"threshold_uncertainty_score":0.7830247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2094091345","doi":"10.1038/nrd2094","title":"Drug development for CNS disorders: strategies for balancing risk and reducing attrition","year":2007,"lang":"en","type":"review","venue":"Nature Reviews Drug Discovery","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":337,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Attrition; Intensive care medicine; Medicine; Drug development; Disease; Quality of life (healthcare); Central nervous system; Productivity; Risk analysis (engineering); Drug; Psychiatry; Pathology; Internal medicine; Economic growth","retraction":null,"screen_n_in":null,"score":{"opus":0.05182690280667102,"gpt":0.3848907689173903,"spread":0.3330638661107193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00610958,0.001066009,0.00289311,0.0005708906,0.0005535645,0.001208901,0.001335157,0.0005516391,0.000001714989],"category_scores_gemma":[0.0009118982,0.0008607322,0.001258817,0.0009325956,0.0000833425,0.002328365,0.000489407,0.001292052,0.000008360924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004578084,"about_ca_system_score_gemma":0.001539027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001584068,"about_ca_topic_score_gemma":0.0001047234,"domain_scores_codex":[0.9941182,0.0008046881,0.001926549,0.001783722,0.0005556392,0.0008112733],"domain_scores_gemma":[0.9933048,0.003860406,0.001567806,0.000912021,0.0001756904,0.0001792038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007338814,0.00006370469,0.000001349558,0.03350848,0.0001052328,0.000001152936,0.0003397579,0.00009444395,1.46099e-7,0.01440798,0.003326034,0.9481444],"study_design_scores_gemma":[0.0003329476,0.00002453254,0.000007283318,0.02145913,0.0004029102,0.0000198533,0.00005632762,0.001067658,0.000002996612,0.008230667,0.9674307,0.0009649962],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000005291373,0.5604151,0.4347735,0.00004698743,0.0009040458,0.003581707,0.0001180245,0.0000708248,0.00008450691],"genre_scores_gemma":[0.000006859282,0.7492583,0.2483546,0.0001087883,0.0004917817,0.001105892,0.0003741978,0.00007669449,0.0002228602],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9641047,"threshold_uncertainty_score":0.9998279,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389479893","doi":"10.1038/s41573-023-00832-0","title":"Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR","year":2023,"lang":"en","type":"review","venue":"Nature Reviews Drug Discovery","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":336,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Coquitlam College; University of British Columbia; University of British Columbia Hospital","funders":"National Institute of General Medical Sciences","keywords":"Quantitative structure–activity relationship; Deep learning; Artificial intelligence; Computer science; Drug discovery; Field (mathematics); Virtual screening; Machine learning; Data science; Bioinformatics; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0457102550202402,"gpt":0.3592855806022173,"spread":0.3135753255819771,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.007762228,0.001293974,0.004068969,0.0007840776,0.0003383887,0.0008539516,0.003551202,0.0005405092,0.000006464292],"category_scores_gemma":[0.001928506,0.0008426014,0.001399458,0.004142492,0.0002368925,0.002952738,0.002127877,0.004721324,0.00003822827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002277286,"about_ca_system_score_gemma":0.0005501287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001632434,"about_ca_topic_score_gemma":0.0003462164,"domain_scores_codex":[0.9886027,0.004397893,0.002990533,0.001938445,0.001181742,0.000888668],"domain_scores_gemma":[0.9906773,0.005119586,0.002262324,0.001637288,0.0001535405,0.0001499679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004837709,0.00006236864,0.00001551905,0.01692145,0.0001303971,0.00002712111,0.001391335,0.0295844,4.728004e-7,0.02860005,0.0002583102,0.9230037],"study_design_scores_gemma":[0.0002360152,0.00003123337,0.00001245872,0.04706139,0.0004967625,0.00006010269,0.0004286792,0.2217589,0.00000373479,0.007705657,0.7206425,0.00156261],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002898024,0.7766371,0.2200836,0.0001371819,0.0009502728,0.001736697,0.00002303084,0.0001000347,0.0003030669],"genre_scores_gemma":[0.0002158619,0.98103,0.01722984,0.0001192175,0.0003042797,0.00029191,0.00009347772,0.0001354803,0.0005799117],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9214411,"threshold_uncertainty_score":0.9999812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155626151","doi":"10.1038/msb.2011.71","title":"Systematic exploration of synergistic drug pairs","year":2011,"lang":"en","type":"article","venue":"Molecular Systems Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":327,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; University of Toronto","funders":"National Human Genome Research Institute; National Institute of General Medical Sciences; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; National Institute of Mental Health; Canadian Institutes of Health Research; National Cancer Institute; National Institutes of Health","keywords":"Drug; Biology; Computational biology; Antifungal drug; Antifungal drugs; Pharmacology; Promiscuity; Bioavailability; Drug discovery; Drug development; Genetics; Bioinformatics; Candida albicans","retraction":null,"screen_n_in":null,"score":{"opus":0.04421310378962579,"gpt":0.2785228367357592,"spread":0.2343097329461334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009549895,0.0001437689,0.0004053146,0.0001825971,0.00003498275,0.00002578972,0.0006709145,0.00006781064,0.000003013082],"category_scores_gemma":[0.0002334738,0.0001229857,0.00009650332,0.0003266983,0.00006082032,0.0002538733,0.00016754,0.00006171505,0.00003747001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003498674,"about_ca_system_score_gemma":0.00006549841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001672417,"about_ca_topic_score_gemma":0.000002698032,"domain_scores_codex":[0.9974136,0.001294243,0.0005954045,0.0003347648,0.0001702737,0.0001917671],"domain_scores_gemma":[0.9986038,0.0002312259,0.0003354072,0.0006119204,0.0001617409,0.00005590521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004745751,0.0000601332,0.0000793434,0.002683113,0.00009411925,0.00003013142,0.001470965,0.004040479,0.01047183,0.9808197,0.00003566219,0.0002097921],"study_design_scores_gemma":[0.0009787686,0.0005648058,0.0006251908,0.003700738,0.0001483096,0.0001490225,0.0008151395,0.7879235,0.07152077,0.1322869,0.0001247973,0.001162022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02699986,0.0009293039,0.9689785,0.00003541205,0.0009126114,0.0004342358,0.000002923295,0.00008694749,0.001620239],"genre_scores_gemma":[0.9807249,0.000002776195,0.01906213,0.00003265615,0.00001916688,0.00009997338,0.000005742973,0.000009874037,0.00004273275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9537251,"threshold_uncertainty_score":0.5015211,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}