{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1681,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":1681,"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":"ba1d3b953f25","filters":{"venue":"Nucleic Acids Research"}},"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":"W1989277387","doi":"10.1093/nar/gkv1351","title":"The Reactome pathway Knowledgebase","year":2015,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6014,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health","keywords":"Visualization; Interface (matter); Computer science; Biology; Zoom; Data visualization; User interface; Computational biology; The Internet; Usability; Graph drawing; Information retrieval; Data mining; Bioinformatics; World Wide Web; Human–computer interaction; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05227478967398648,"gpt":0.3313396891802437,"spread":0.2790648995062572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002269676,0.0001017074,0.00008364393,0.00004027723,0.0003097664,0.000114956,0.0005192146,0.0001590942,0.00001715019],"category_scores_gemma":[0.0003345932,0.00006824987,0.00005613172,0.0001829172,0.0002857865,0.000004195978,0.0004237915,0.0003270302,0.0004456176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003844148,"about_ca_system_score_gemma":0.0002861661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001013841,"about_ca_topic_score_gemma":0.00002875943,"domain_scores_codex":[0.9985813,0.0001481768,0.0001881264,0.000201612,0.0003668331,0.0005139726],"domain_scores_gemma":[0.9986524,0.00004883427,0.00003331458,0.0006403286,0.0003778064,0.0002472882],"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":[0.0005740373,0.0001728166,0.001710961,0.00003134464,0.0001281569,0.0000211179,0.0009707081,0.00003397587,0.0841022,0.009918377,0.6413162,0.2610202],"study_design_scores_gemma":[0.0004170025,0.0003003668,0.0002584266,0.000006206504,0.000001721249,0.00001362004,0.0005058137,0.0006794923,0.006712312,0.001912954,0.9890766,0.0001155535],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.77228,0.004822602,0.0008529034,0.001682406,0.0006850945,0.0005781446,0.00002146029,0.00003785583,0.2190395],"genre_scores_gemma":[0.9878916,0.0002656951,0.0003244728,0.0001226376,0.0006514615,0.00003011938,0.00003681532,0.00002562555,0.01065158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3477604,"threshold_uncertainty_score":0.5727661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1985213868","doi":"10.1093/nar/gkq537","title":"The GeneMANIA prediction server: biological network integration for gene prioritization and predicting gene function","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5113,"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":"Biology; Function (biology); Model organism; Organism; Computer science; Set (abstract data type); Exploit; Caenorhabditis elegans; Computational biology; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02415407617581905,"gpt":0.2863397790352,"spread":0.2621857028593809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001979543,0.0001179627,0.00009081305,0.00003355947,0.0009363434,0.0001530867,0.0001805465,0.0003656141,0.000006990471],"category_scores_gemma":[0.0002239127,0.00008505524,0.00004900634,0.000139038,0.0001902569,0.00001271707,0.0001681002,0.0003869729,0.0000038713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001761778,"about_ca_system_score_gemma":0.00005654244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007692109,"about_ca_topic_score_gemma":0.0001044029,"domain_scores_codex":[0.9987453,0.00009056366,0.0002680007,0.0002899879,0.0002031593,0.0004029599],"domain_scores_gemma":[0.9991348,0.00007713613,0.00007137153,0.0003062851,0.0003208992,0.00008947898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003971005,0.00003307462,0.01437423,0.00002132632,0.00007116265,3.156868e-7,0.0001033623,0.0002048678,0.8701767,0.003006911,0.006931036,0.1046799],"study_design_scores_gemma":[0.004159368,0.005398194,0.2186211,0.00007560426,0.0001044565,0.0001429958,0.001079196,0.2807336,0.1188182,0.0274662,0.3423782,0.001022964],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.952791,0.0005744456,0.04474521,0.000218341,0.0006161127,0.0007025345,0.00002703034,0.00002596096,0.0002993347],"genre_scores_gemma":[0.9918398,0.0008747786,0.004033586,0.00007357041,0.002378775,0.0001151557,0.0004204929,0.00002196743,0.0002418748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7513585,"threshold_uncertainty_score":0.7201691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095724872","doi":"10.1093/nar/gkg500","title":"Multiple sequence alignment with the Clustal series of programs","year":2003,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4899,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Genetics; Centre National de la Recherche Scientifique","keywords":"Biology; Multiple sequence alignment; Software portability; Phylogenetic tree; Sequence alignment; Web server; Indel; Robustness (evolution); Bioinformatics; Set (abstract data type); Computational biology; Computer science; The Internet; Genetics; World Wide Web; Peptide sequence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04682860158214395,"gpt":0.3062734391288656,"spread":0.2594448375467216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000536609,0.00009255511,0.00009442717,0.00002070341,0.0001865956,0.00002139393,0.0002308597,0.00005611901,0.00001345862],"category_scores_gemma":[0.00007582756,0.00005716788,0.00003765189,0.0001362373,0.0005593729,6.446039e-7,0.000144973,0.0001023729,0.000003640365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001279607,"about_ca_system_score_gemma":0.00009635699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003867349,"about_ca_topic_score_gemma":0.0001067104,"domain_scores_codex":[0.9989254,0.0001388492,0.000106071,0.0002255763,0.0002919043,0.0003122011],"domain_scores_gemma":[0.9993275,0.00002271979,0.00003140926,0.0003608621,0.0002085389,0.00004901089],"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":[0.0001437226,0.00008449787,0.02889669,0.000023539,0.00009648964,0.000003194315,0.0004262846,0.00004075735,0.9653292,0.001244645,0.0008402486,0.002870765],"study_design_scores_gemma":[0.0008217259,0.002372494,0.007543965,0.00001808527,0.00001296079,0.0000391076,0.004434898,0.0000277553,0.6171357,0.0003405912,0.3670281,0.000224592],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954774,0.0005111826,0.00006110827,0.000327687,0.00002407859,0.0003283502,0.00001481578,0.000001527936,0.003253814],"genre_scores_gemma":[0.997499,0.0002118067,0.001285987,0.00002758807,0.00003862836,0.00006189357,0.000008021805,0.00001554939,0.0008515488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3661879,"threshold_uncertainty_score":0.2331239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103296919","doi":"10.1093/nar/gkt1209","title":"The SILVA and “All-species Living Tree Project (LTP)” taxonomic frameworks","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4140,"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":"Max-Planck-Institut für Terrestrische Mikrobiologie; Deutsche Forschungsgemeinschaft","keywords":"Biology; Taxonomy (biology); Taxon; Phylogenetic tree; Ribosomal RNA; Three-domain system; Phylogenetics; Evolutionary biology; Archaea; Ecology; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0452538826125229,"gpt":0.311679006085694,"spread":0.2664251234731712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006459948,0.0001453798,0.0001264787,0.00005314805,0.0005422247,0.0002394626,0.0003930713,0.0002280241,0.00004762042],"category_scores_gemma":[0.0003812722,0.000102312,0.00005663528,0.0001051969,0.0004961747,0.00000158493,0.0007139469,0.0004210051,0.00004317203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002215372,"about_ca_system_score_gemma":0.00007202058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001619204,"about_ca_topic_score_gemma":0.0001560974,"domain_scores_codex":[0.9985315,0.0001604235,0.0001715091,0.0003729814,0.0002127842,0.0005508339],"domain_scores_gemma":[0.9990084,0.0002198512,0.00003551384,0.0004660916,0.0001863451,0.00008375371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005508973,0.00006661677,0.02577086,0.00002863615,0.0002956837,0.000001990582,0.0007147642,0.000006350766,0.8233691,0.001158823,0.09238124,0.05615079],"study_design_scores_gemma":[0.0003483383,0.0006556367,0.2051474,0.00003279843,0.00001570068,0.00001354316,0.00340335,0.0003780933,0.00927371,0.001068875,0.7792838,0.0003787607],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9828036,0.003714724,0.00003641551,0.001081312,0.00009604485,0.0005009422,0.000008108457,0.000004170155,0.01175469],"genre_scores_gemma":[0.9899312,0.004860375,0.0006150816,0.0001314577,0.0003476719,0.0001685871,0.000003683865,0.00002721836,0.003914781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8140954,"threshold_uncertainty_score":0.4172162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3159995035","doi":"10.1093/nar/gkab382","title":"MetaboAnalyst 5.0: narrowing the gap between raw spectra and functional insights","year":2021,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health; Canada Research Chairs; Génome Québec; Compute Canada; Genome Canada","keywords":"Pipeline (software); Computer science; Raw data; Data mining; Session (web analytics); Modular design; Network analysis; Biology; Information retrieval; World Wide Web; Operating system; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06453298421460983,"gpt":0.3262573713541874,"spread":0.2617243871395776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008486279,0.0001370897,0.0002118823,0.0001008439,0.0005966133,0.0001076313,0.0001918422,0.0001077073,0.0001620174],"category_scores_gemma":[0.0003649406,0.0000972796,0.0001005553,0.0004742004,0.0003031912,0.00000648152,0.0004883423,0.0003540882,0.00002402377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001862085,"about_ca_system_score_gemma":0.0001204856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001643641,"about_ca_topic_score_gemma":0.00004058632,"domain_scores_codex":[0.9981675,0.0003082075,0.0001865192,0.0004699198,0.0004722958,0.0003956272],"domain_scores_gemma":[0.9990168,0.00009807916,0.00003158413,0.000454746,0.0002926029,0.0001062213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003831204,0.00004012475,0.007693985,0.0000191886,0.0005168818,0.00001620356,0.0001402643,0.00000405421,0.9747137,0.0072073,0.007483482,0.00212652],"study_design_scores_gemma":[0.0008202042,0.0002198341,0.1151106,0.0000121076,0.0000863837,0.000038358,0.00162062,0.00005678015,0.4068382,0.004684608,0.4701927,0.0003194869],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714328,0.01442256,0.0004814724,0.00248775,0.0001164592,0.000136387,0.00001193872,0.000009837218,0.01090079],"genre_scores_gemma":[0.9933704,0.002196604,0.0004331736,0.0001489666,0.000768709,0.00001782015,0.00005900144,0.00002124653,0.002984126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5678754,"threshold_uncertainty_score":0.4588727,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163485494","doi":"10.1093/nar/gkj109","title":"BioGRID: a general repository for interaction datasets","year":2005,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; Princess Margaret Cancer Centre","funders":"National Cancer Institute; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Biology; Graphical user interface; Visualization; Computational biology; Gene interaction; Drosophila melanogaster; Saccharomyces cerevisiae; User interface; Computer science; Gene; Genetics; Data mining; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03074157569373361,"gpt":0.3461435266353305,"spread":0.315401950941597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005655611,0.00009503373,0.00008625141,0.00007436166,0.0002221096,0.00007725167,0.0002730141,0.0001563343,0.00003057505],"category_scores_gemma":[0.00004519939,0.00008803108,0.00007015729,0.0000859249,0.00009276409,0.0000101812,0.0001933576,0.0001897123,0.00005547211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003898453,"about_ca_system_score_gemma":0.0000624399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001885443,"about_ca_topic_score_gemma":0.00002127576,"domain_scores_codex":[0.9989373,0.00005211372,0.0002081669,0.000250724,0.0001797155,0.0003719924],"domain_scores_gemma":[0.9992892,0.00002116064,0.00004178003,0.0004264246,0.0001194503,0.0001020467],"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":[0.0003105259,0.00009835967,0.0002358124,0.00003382233,0.00007099249,0.000001788662,0.000105385,0.0001719983,0.3877731,0.0004960049,0.5260863,0.08461592],"study_design_scores_gemma":[0.0004436382,0.0002719804,0.0001978533,0.000008536987,0.000004845544,0.00002392403,0.00007788173,0.008898081,0.05674274,0.00009802281,0.933107,0.0001255566],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746292,0.001004164,0.007014688,0.00134349,0.0005643832,0.0008962231,0.0003051134,0.00003356826,0.01420922],"genre_scores_gemma":[0.9838551,0.0001493664,0.009060563,0.0003197347,0.002350589,0.00007883155,0.001071041,0.00002892938,0.003085864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4070206,"threshold_uncertainty_score":0.3589803,"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":"W2803664483","doi":"10.1093/nar/gky310","title":"MetaboAnalyst 4.0: towards more transparent and integrative metabolomics analysis","year":2018,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3820,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Metabolomics; Identification (biology); Computer science; Biology; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.04950750720783706,"gpt":0.3708966744716163,"spread":0.3213891672637792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001246929,0.0002398025,0.0005143448,0.0005320059,0.0003649684,0.00008580792,0.0003926817,0.000160344,0.0001914921],"category_scores_gemma":[0.0003158785,0.0001824425,0.0002333535,0.00149008,0.0009333599,0.000008247442,0.0003484592,0.0002901921,0.00001779095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002778576,"about_ca_system_score_gemma":0.0000882414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001630824,"about_ca_topic_score_gemma":0.0003975345,"domain_scores_codex":[0.9976845,0.0002604412,0.0002887381,0.0007072153,0.0004975413,0.0005615675],"domain_scores_gemma":[0.9984934,0.00003150955,0.00005908563,0.0005805503,0.0006455861,0.0001899146],"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":[0.0007467635,0.0003444672,0.03267448,0.00004693205,0.01438227,0.0000141272,0.002669309,0.00001627966,0.8957973,0.008219222,0.007708206,0.03738063],"study_design_scores_gemma":[0.001726812,0.001800811,0.1709121,0.00001531455,0.002193483,0.00001454081,0.005802045,0.002133973,0.4695154,0.001373787,0.3435257,0.0009860572],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981819,0.005104151,0.004839924,0.0009444124,0.00009464507,0.0002420951,0.00008729327,0.00001685381,0.006851615],"genre_scores_gemma":[0.9905033,0.004123824,0.003236299,0.0001306195,0.0003374321,0.00003886819,0.00006971459,0.00002667879,0.001533285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.426282,"threshold_uncertainty_score":0.7439788,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2345791363","doi":"10.1093/nar/gkw387","title":"PHASTER: a better, faster version of the PHAST phage search tool","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3760,"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; Genome Alberta; Genome Canada","keywords":"Genome; Graphical user interface; Biology; Software; Annotation; Visualization; GenBank; Metagenomics; Bacterial genome size; Computational biology; Identification (biology); Perl; User interface; Computer science; Data mining; Operating system; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03202363239463116,"gpt":0.3069429724436617,"spread":0.2749193400490305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006351569,0.0001166792,0.0001284433,0.00005851689,0.0001870421,0.00001906143,0.0005610184,0.0001031504,0.0001747748],"category_scores_gemma":[0.00009338954,0.00006570739,0.000110852,0.0001553415,0.0004341629,0.00000137158,0.0008439702,0.0001286021,0.00006108064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002338025,"about_ca_system_score_gemma":0.0000797062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001625066,"about_ca_topic_score_gemma":0.000008112046,"domain_scores_codex":[0.9984033,0.0002006592,0.0001823139,0.000332336,0.0004553761,0.000426015],"domain_scores_gemma":[0.9989862,0.00005119798,0.00003424293,0.0006285702,0.000241236,0.00005858046],"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":[0.0001115289,0.00005580574,0.01406294,0.00001472413,0.00004747562,9.737317e-7,0.0001114811,8.677274e-7,0.9530571,0.00003344095,0.003535751,0.02896789],"study_design_scores_gemma":[0.001579843,0.0005224357,0.0271719,0.00004464779,0.000008813532,0.00000725965,0.0001979976,0.00001403099,0.847475,0.0001311373,0.1226955,0.0001514612],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995179,0.000316032,0.0001083313,0.001128282,0.0001196857,0.0002487052,0.00009186924,0.000001634585,0.002806471],"genre_scores_gemma":[0.9965365,0.0002240603,0.0001681322,0.00009672364,0.0002079176,0.00001528292,0.000003327502,0.00002244561,0.002725634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1191597,"threshold_uncertainty_score":0.267947,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2767683865","doi":"10.1093/nar/gkx1089","title":"HMDB 4.0: the human metabolome database for 2018","year":2017,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3554,"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":"Genome Alberta; Alberta Innovates; Alberta Innovates - Health Solutions; Canadian Institutes of Health Research; Genome Canada; World Health Organization","keywords":"Metabolome; Metabolomics; Metabolite; Biology; Identification (biology); Database; Computer science; Computational biology; Bioinformatics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.09984199163691135,"gpt":0.4088378265351218,"spread":0.3089958348982105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002051292,0.0001479295,0.0001954216,0.00007373287,0.002589733,0.0002263368,0.001321589,0.0001077785,0.00008634709],"category_scores_gemma":[0.001080567,0.0001005645,0.0001278005,0.00007279118,0.0006771007,0.000009785867,0.001112991,0.0002515208,0.00004776763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001509002,"about_ca_system_score_gemma":0.00005963941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008915027,"about_ca_topic_score_gemma":0.00008550466,"domain_scores_codex":[0.9982995,0.0001129738,0.0001772569,0.0004694297,0.0003492427,0.0005916217],"domain_scores_gemma":[0.9977148,0.00005325213,0.00008497707,0.001776301,0.0002728686,0.00009778239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006581227,0.00006064627,0.00188715,0.00002164347,0.0001496519,0.00000190539,0.00003352675,2.698548e-7,0.8860852,0.01370422,0.09587232,0.002117727],"study_design_scores_gemma":[0.0007303347,0.0002921031,0.01390659,0.000005989019,0.00002407986,0.000003510015,0.0001563505,0.00002255211,0.1156639,0.001891105,0.8671308,0.0001726452],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9705337,0.002711377,0.0006562664,0.004096945,0.00038403,0.0008734764,0.0002406162,0.00001596424,0.02048762],"genre_scores_gemma":[0.986349,0.0009975953,0.00124804,0.0001374174,0.0009476692,0.0001765473,0.00009230667,0.00003788009,0.01001347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7712585,"threshold_uncertainty_score":0.9987088,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982531601","doi":"10.1093/nar/gkz935","title":"CARD 2020: antibiotic resistome surveillance with the comprehensive antibiotic resistance database","year":2019,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Antibiotic Resistance in Bacteria","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3312,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Agency of Canada; University of Manitoba; Simon Fraser University; BC Centre for Disease Control; University of British Columbia; Dalhousie University; Hamilton Health Sciences; McMaster University","funders":"Michael G. DeGroote Institute for Infectious Disease Research, McMaster University; Cisco Systems Canada; Canadian Institutes of Health Research; Mitacs; Genome Canada; University of Washington; McMaster University; Cisco Systems","keywords":"Resistome; Biology; Antibiotics; Antibiotic resistance; Microbiology; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02146543060323834,"gpt":0.3031591970341395,"spread":0.2816937664309011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001255678,0.000360652,0.0004210637,0.0001093669,0.0004422704,0.0001876324,0.001271234,0.0002380098,0.0001164018],"category_scores_gemma":[0.0002134195,0.0002533546,0.0001155825,0.0007814691,0.001112054,0.00002162178,0.0005800545,0.000656023,0.0005744102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009094005,"about_ca_system_score_gemma":0.0003007478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005620223,"about_ca_topic_score_gemma":0.0003630604,"domain_scores_codex":[0.9956335,0.0007474032,0.0003399444,0.001137317,0.001082224,0.001059547],"domain_scores_gemma":[0.9963493,0.0002276188,0.0001432476,0.002373136,0.0007161784,0.0001904795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0016187,0.0001086612,0.1589879,0.0003483825,0.0001839116,0.0000958422,0.00008664219,0.00002402256,0.7695053,0.0004095642,0.06838686,0.0002442252],"study_design_scores_gemma":[0.002136653,0.0009687871,0.6143268,0.000404654,0.00002881579,0.00007799399,0.001512384,0.00005550884,0.06009887,0.00003444427,0.3193868,0.0009683455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841478,0.001801574,0.00007202318,0.00138879,0.0002086227,0.0009261604,0.0001162069,0.00003766062,0.01130111],"genre_scores_gemma":[0.9831218,0.0007195666,0.0009183969,0.0002230353,0.0003044924,0.000004615414,0.0001802187,0.00009939837,0.01442849],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7094064,"threshold_uncertainty_score":0.9999919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165681080","doi":"10.1093/nar/gkl923","title":"HMDB: the Human Metabolome Database","year":2007,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3265,"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 Calgary; University of Alberta","funders":"Genome Alberta; Genome Canada","keywords":"Metabolome; Biology; Metabolite; Metabolomics; Database; Computational biology; Computer science; Bioinformatics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.05618736265646457,"gpt":0.3793652041356149,"spread":0.3231778414791503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004159151,0.000151578,0.0001694876,0.0001560089,0.000700049,0.00006082991,0.0006796833,0.0001142962,0.0001974701],"category_scores_gemma":[0.0004152593,0.0001030452,0.00009666731,0.0004634256,0.0004524396,0.000005097258,0.0007639159,0.0004278109,0.0001058165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002186886,"about_ca_system_score_gemma":0.00004818809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006684601,"about_ca_topic_score_gemma":0.0001058184,"domain_scores_codex":[0.9978548,0.0001703271,0.000235817,0.000443057,0.0005479985,0.0007479863],"domain_scores_gemma":[0.9986234,0.00007208648,0.00004255484,0.0008882958,0.0002406892,0.0001329969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004646508,0.00006731384,0.003105965,0.000008906912,0.00009052433,0.00000946602,0.000055081,3.729171e-7,0.96171,0.01155789,0.02104371,0.002304284],"study_design_scores_gemma":[0.0004341917,0.0002235671,0.02401457,0.000004246884,0.00001493553,0.00001191891,0.0005415682,0.000004365603,0.2440665,0.000706184,0.7297967,0.0001812083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9622004,0.003149336,0.0006349418,0.0007710058,0.0001534193,0.000288424,0.00002781255,0.00001762231,0.03275706],"genre_scores_gemma":[0.9921523,0.0007479067,0.0007610525,0.0002363533,0.0006708284,0.00002243827,0.00006459765,0.00003219079,0.005312292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7176435,"threshold_uncertainty_score":0.5384282,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4233698560","doi":"10.1093/nar/gkx1132","title":"The Reactome Pathway Knowledgebase","year":2017,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute","keywords":"Biology; Computational biology; Computer science; Information retrieval; Bioinformatics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04006357190179961,"gpt":0.3409879473299789,"spread":0.3009243754281793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001666043,0.0001031907,0.00008638423,0.00002819305,0.001963518,0.0003996752,0.00113764,0.0001651381,0.00003311765],"category_scores_gemma":[0.0004328283,0.00006970074,0.00007345182,0.0000439713,0.0005586696,0.00000667889,0.0007781267,0.000350081,0.0003206264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002053212,"about_ca_system_score_gemma":0.0001382414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001635915,"about_ca_topic_score_gemma":0.00005959013,"domain_scores_codex":[0.9987251,0.00008400316,0.0001701397,0.0002199416,0.0002778117,0.0005230491],"domain_scores_gemma":[0.9980265,0.00004466232,0.00007024776,0.0014971,0.0002260967,0.0001353548],"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":[0.0003805376,0.0001338244,0.004526554,0.00004651701,0.0001553227,0.00002445857,0.0003495518,0.000005139711,0.2169358,0.01301629,0.1774692,0.5869567],"study_design_scores_gemma":[0.0003716884,0.0001882237,0.005272026,0.00001210918,0.000002195055,0.000009472186,0.0001330827,0.000485809,0.01290723,0.001710971,0.9787713,0.0001359341],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.763813,0.001658491,0.0003205088,0.002119084,0.0005755284,0.000445894,0.00002211066,0.00001912657,0.2310262],"genre_scores_gemma":[0.9856359,0.0005623664,0.0001762981,0.00006617409,0.000638294,0.00002603595,0.00001725178,0.00002212525,0.01285553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.801302,"threshold_uncertainty_score":0.9993358,"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":"W2063028213","doi":"10.1093/nar/gks1065","title":"HMDB 3.0—The Human Metabolome Database in 2013","year":2012,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2904,"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":"Genome Alberta; Canadian Institutes of Health Research; Alberta Innovates; Genome Canada","keywords":"Metabolome; Biology; Metabolomics; Metabolite; Database; Bioinformatics; Computational biology; Computer science; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.06294234742338028,"gpt":0.3721048319621013,"spread":0.309162484538721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002669598,0.0001475271,0.0001894857,0.0001864988,0.0003224356,0.00004023811,0.0005270683,0.0001121792,0.0002824891],"category_scores_gemma":[0.00027523,0.0001057089,0.00007098684,0.0004615543,0.0002968944,0.00001223543,0.0007443316,0.0004328335,0.0001702282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002680945,"about_ca_system_score_gemma":0.00003779463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002068487,"about_ca_topic_score_gemma":0.000134748,"domain_scores_codex":[0.9978616,0.0003212437,0.0002204973,0.0003287303,0.0004078025,0.0008600979],"domain_scores_gemma":[0.9989352,0.00004560027,0.00003594504,0.0007307837,0.0001134509,0.0001389949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000335542,0.0001933508,0.03772231,0.00001602747,0.00006796177,0.000002856305,0.0001518044,0.000001114438,0.9065779,0.009866803,0.04430643,0.001059832],"study_design_scores_gemma":[0.0006114522,0.000143902,0.0775236,0.000007468146,0.00001228757,0.000009101403,0.0006471163,0.00001038837,0.0664588,0.0003343264,0.8540081,0.0002334031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793377,0.008415801,0.00003994496,0.001166374,0.000159809,0.0002855248,0.00002450029,0.000008925763,0.01056143],"genre_scores_gemma":[0.9938086,0.00202572,0.000422242,0.0001397582,0.0005718137,0.00007697221,0.00006124983,0.00002852868,0.002865172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8401191,"threshold_uncertainty_score":0.4310685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2544493586","doi":"10.1093/nar/gkw1004","title":"CARD 2017: expansion and model-centric curation of the comprehensive antibiotic resistance database","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Antibiotic Resistance in Bacteria","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2819,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; McMaster University","funders":"Army Research Office; Canadian Institutes of Health Research; Wellcome Trust","keywords":"Resistome; Biology; Data curation; Ontology; Computational biology; Identifier; Database; Controlled vocabulary; Genome; Computer science; Data science; Information retrieval; Genetics; Gene; Mobile genetic elements","retraction":null,"screen_n_in":null,"score":{"opus":0.04384185969850549,"gpt":0.3283800612574203,"spread":0.2845382015589147,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003771147,0.0001216523,0.0001500632,0.00006372639,0.0001811612,0.00002429415,0.0003664349,0.0001295251,0.00001009079],"category_scores_gemma":[0.0003190732,0.00007328352,0.00005077676,0.0001967282,0.0006199347,0.00001971378,0.0004213513,0.0001249961,0.000009759271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000334736,"about_ca_system_score_gemma":0.0001375318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001122348,"about_ca_topic_score_gemma":0.00002926575,"domain_scores_codex":[0.9983477,0.0002507472,0.0002222037,0.00041064,0.0004412905,0.0003274249],"domain_scores_gemma":[0.9985586,0.00006393561,0.00008599662,0.0008314695,0.0003839537,0.00007598828],"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":[0.0001964861,0.00003112566,0.009461201,0.00006808381,0.00001635423,0.000002052586,0.00003462693,0.000004552597,0.9824791,0.0005069984,0.006318924,0.0008804916],"study_design_scores_gemma":[0.001608653,0.0002230171,0.1183817,0.0005762418,0.00002417197,0.00001509728,0.0002751031,0.0005515463,0.8622729,0.0006055136,0.01511452,0.0003515341],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956633,0.0008410331,0.00160332,0.0005135025,0.00008086899,0.0003138853,0.00008172152,0.00000628706,0.0008960559],"genre_scores_gemma":[0.9950824,0.001687416,0.000983478,0.00003166329,0.00007139633,0.000002250523,0.00001703304,0.00002103187,0.002103323],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1202062,"threshold_uncertainty_score":0.2988415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1976327004","doi":"10.1093/nar/gkv380","title":"MetaboAnalyst 3.0—making metabolomics more meaningful","year":2015,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2747,"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; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Interactivity; Upgrade; Computer science; Visualization; Rendering (computer graphics); Web server; World Wide Web; The Internet; Data mining; Operating system; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08126158021009874,"gpt":0.376384817327871,"spread":0.2951232371177722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00267092,0.0002400089,0.0003895849,0.0003131308,0.0002795066,0.0001093763,0.0006532971,0.000193701,0.00007027439],"category_scores_gemma":[0.001338391,0.0002106873,0.0001666977,0.0007370219,0.0003291209,0.00001072279,0.0008118167,0.0004204191,0.0001129982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006015053,"about_ca_system_score_gemma":0.0002161932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003849353,"about_ca_topic_score_gemma":0.00003315288,"domain_scores_codex":[0.997059,0.0003002267,0.0003232374,0.0006547125,0.0008650424,0.0007977304],"domain_scores_gemma":[0.9980741,0.00003731252,0.00008113033,0.000791563,0.0007473422,0.0002686119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006449305,0.0003498932,0.01776245,0.00005385993,0.001516479,0.00005514329,0.001215745,0.0001837797,0.8483256,0.01867981,0.1005947,0.01061772],"study_design_scores_gemma":[0.001194841,0.0004318716,0.002942263,0.00001136038,0.00008493893,0.00003109103,0.002918911,0.0004271707,0.06589267,0.001500004,0.9240859,0.0004789725],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9432597,0.01048417,0.00152477,0.001326674,0.0003884858,0.0003701957,0.00003180729,0.00004879548,0.04256547],"genre_scores_gemma":[0.9877982,0.0008494543,0.007319094,0.0002515442,0.0006387696,0.00004342605,0.0000439405,0.00005988969,0.002995754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8234912,"threshold_uncertainty_score":0.8591579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3211402536","doi":"10.1093/nar/gkab1028","title":"The reactome pathway knowledgebase 2022","year":2021,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2542,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health; National Human Genome Research Institute; University of Toronto; European Bioinformatics Institute","keywords":"Biology; Computational biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02636071070354901,"gpt":0.312288632364832,"spread":0.285927921661283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001379758,0.0001051954,0.00009447578,0.00003192904,0.0005334867,0.0001379726,0.0004195658,0.0001680815,0.000149623],"category_scores_gemma":[0.0003104031,0.00007737599,0.00008755244,0.0002768224,0.0002302792,0.00000360451,0.0005894078,0.0004291062,0.0002844557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002955748,"about_ca_system_score_gemma":0.0003434696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004999036,"about_ca_topic_score_gemma":0.00006194379,"domain_scores_codex":[0.9984487,0.0002008197,0.0002056932,0.0002666269,0.0003392348,0.0005389667],"domain_scores_gemma":[0.9985659,0.00007960436,0.00003212699,0.000780459,0.0004024325,0.0001395447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001437408,0.0001354188,0.0005839907,0.00003708738,0.0001183914,0.00005674766,0.0002514079,0.000008776296,0.548242,0.00702374,0.2259403,0.2174584],"study_design_scores_gemma":[0.0002850693,0.0001211738,0.0004334166,0.000008940755,0.000002386528,0.0000303966,0.0004163467,0.0003897311,0.05155402,0.001157049,0.9454803,0.0001211403],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7903232,0.01519212,0.0008577789,0.003745198,0.0008840686,0.0004936897,0.00005429398,0.00003595134,0.1884137],"genre_scores_gemma":[0.9644911,0.002144047,0.000387104,0.0002626247,0.0007625998,0.00004096195,0.0001239576,0.00003585707,0.03175177],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.71954,"threshold_uncertainty_score":0.4103203,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206447491","doi":"10.1093/nar/gkab1062","title":"HMDB 5.0: the Human Metabolome Database for 2022","year":2021,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2449,"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; Canadian Institutes of Health Research; Genome Alberta; Canada Foundation for Innovation; Alberta Machine Intelligence Institute","keywords":"Metabolome; Metabolomics; Identification (biology); Computer science; Metabolite; Biology; Interface (matter); Data mining; Database; Bioinformatics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.06413457580120722,"gpt":0.3800104074604811,"spread":0.3158758316592739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001660159,0.0001378111,0.0001947167,0.00007692399,0.0007572082,0.00008178278,0.0004948378,0.00009838743,0.0003066904],"category_scores_gemma":[0.0008143375,0.0001011337,0.0001421763,0.0003932579,0.0002591614,0.000004699272,0.0008097246,0.000292627,0.00003071121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001770719,"about_ca_system_score_gemma":0.0001298092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001781091,"about_ca_topic_score_gemma":0.0000613152,"domain_scores_codex":[0.9980711,0.0002459057,0.0001951805,0.0005215682,0.0003995738,0.0005667112],"domain_scores_gemma":[0.99841,0.00008879581,0.00003648308,0.0008981141,0.0004739231,0.00009266084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003125867,0.00007196527,0.0004834711,0.00002073599,0.0001342392,0.000005606721,0.00003260035,6.607586e-7,0.924097,0.01427017,0.05948295,0.00136935],"study_design_scores_gemma":[0.0004586995,0.0001422853,0.001617483,0.00000341693,0.00001908781,0.000008664285,0.0004221629,0.00001668496,0.3018577,0.001248109,0.6940832,0.0001225747],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9690264,0.01309983,0.001015612,0.003882186,0.0003023097,0.0006048056,0.0002919879,0.00001802831,0.01175881],"genre_scores_gemma":[0.9722061,0.002850367,0.00235559,0.000466913,0.0009702433,0.0002707211,0.0005189246,0.00005457386,0.02030663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6346002,"threshold_uncertainty_score":0.5823909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2408483783","doi":"10.1093/nar/gkw419","title":"Heatmapper: web-enabled heat mapping for all","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2437,"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":"Computer science; Upload; Geographic coordinate system; Graphical user interface; Information retrieval; Database; Computer graphics (images); Data mining; World Wide Web; Cartography; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.05192131662497756,"gpt":0.3406509099659314,"spread":0.2887295933409538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134333,0.0001610426,0.000221349,0.0001626414,0.0002627785,0.00004317841,0.0003598219,0.0001585667,0.0001380614],"category_scores_gemma":[0.0005609447,0.0001094734,0.0001338876,0.0001951389,0.0001915008,0.000005722557,0.0003596727,0.0001191255,0.00008398757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005710869,"about_ca_system_score_gemma":0.0001111895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277939,"about_ca_topic_score_gemma":0.00001704258,"domain_scores_codex":[0.998045,0.0001091324,0.0002089835,0.0005339974,0.0003053441,0.0007975968],"domain_scores_gemma":[0.9989188,0.0001019904,0.00002141337,0.0005119421,0.0002990122,0.000146853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001217873,0.00004544562,0.001307839,0.00002291698,0.0001127,0.000001675211,0.00002633601,2.858453e-7,0.9428332,0.001250391,0.04968229,0.004595159],"study_design_scores_gemma":[0.001229804,0.0004325233,0.0008855053,0.00001813548,0.000006582563,0.000005393851,0.0001194082,0.00003347092,0.1497544,0.0008684288,0.846471,0.0001754051],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747638,0.002227586,0.002828476,0.006909677,0.0002314765,0.0007371129,0.00007974171,0.00003367567,0.01218849],"genre_scores_gemma":[0.9830579,0.00261153,0.002498486,0.0002544757,0.0005588667,0.0001858423,0.00002481895,0.0000462957,0.01076184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7967887,"threshold_uncertainty_score":0.4464195,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4231254854","doi":"10.1093/nar/gkz1031","title":"The reactome pathway knowledgebase","year":2019,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2363,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; European Bioinformatics Institute","keywords":"Upload; Annotation; Biology; Visualization; Computational biology; Computer science; Information retrieval; Bioinformatics; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02164495633081961,"gpt":0.3030615880552884,"spread":0.2814166317244687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001427351,0.0001031817,0.00009061716,0.00004064359,0.0002893441,0.0001039244,0.0005281985,0.0001648125,0.0001157397],"category_scores_gemma":[0.0001001774,0.00006954144,0.00007263928,0.000166467,0.000180629,0.000003994164,0.0003972545,0.0003573665,0.001476698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002539974,"about_ca_system_score_gemma":0.0001417774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005947011,"about_ca_topic_score_gemma":0.00001415219,"domain_scores_codex":[0.9986452,0.0001120635,0.0001839683,0.0002309455,0.0003012976,0.00052655],"domain_scores_gemma":[0.9988235,0.00006975482,0.00003447693,0.0007588556,0.0001997195,0.0001136547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004826795,0.0001532939,0.00635923,0.00008340869,0.0001613152,0.000009347373,0.0004674119,0.00003040869,0.5928024,0.01413763,0.142142,0.2431709],"study_design_scores_gemma":[0.0003759516,0.0002953528,0.001272064,0.00001088823,0.000001507794,0.000008859873,0.00025757,0.0007971702,0.01190627,0.0008189646,0.9841229,0.0001324972],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8857967,0.00125037,0.0001088748,0.0004572245,0.0003284738,0.0003957331,0.000009473223,0.00001395697,0.1116392],"genre_scores_gemma":[0.9775521,0.0003543419,0.0001431118,0.0001159647,0.0003457333,0.00002101752,0.00003166603,0.00002459806,0.02141149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8419809,"threshold_uncertainty_score":0.9993008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982185581","doi":"10.1093/nar/gkp356","title":"MetaboAnalyst: a web server for metabolomic data analysis and interpretation","year":2009,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2320,"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; Genome Alberta; Genome Canada","keywords":"Metabolomics; Computer science; Identification (biology); Profiling (computer programming); Data pre-processing; Web server; Database normalization; Data mining; Bioinformatics; Cluster analysis; Biology; Artificial intelligence; The Internet; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04978538770464962,"gpt":0.3734938341497964,"spread":0.3237084464451467,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019014,0.0001538703,0.0003626362,0.0004439863,0.0002133283,0.00009731545,0.0005565283,0.0001142815,0.00003912237],"category_scores_gemma":[0.0005667628,0.00013271,0.0001382724,0.0008578069,0.0001191116,0.00001635493,0.0004260766,0.0001535489,0.00000585297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001337372,"about_ca_system_score_gemma":0.00006304721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002179802,"about_ca_topic_score_gemma":0.0001460025,"domain_scores_codex":[0.9981441,0.0001699233,0.0002483714,0.0007273519,0.0003004327,0.0004097916],"domain_scores_gemma":[0.99854,0.00005629327,0.00006095318,0.0009924425,0.0002440459,0.0001062877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000677043,0.0001506719,0.004913185,0.00003384264,0.003826777,0.000002418621,0.0001193736,0.00001875333,0.9312568,0.003330916,0.007942723,0.04772745],"study_design_scores_gemma":[0.00537322,0.002881446,0.2124456,0.00002512097,0.005279552,0.0000204944,0.001240909,0.0877106,0.1633284,0.008563193,0.5115235,0.001608031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807374,0.006952784,0.009355959,0.001134365,0.00005565987,0.0004189304,0.0001960363,0.00001541794,0.001133384],"genre_scores_gemma":[0.9895479,0.002440419,0.006333367,0.0001760399,0.000155172,0.00002558691,0.000438482,0.00001517216,0.0008678787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7679284,"threshold_uncertainty_score":0.5411758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215596355","doi":"10.1093/nar/gkab1113","title":"JASPAR 2022: the 9th release of the open-access database of transcription factor binding profiles","year":2021,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"European Research Council; Biotechnology and Biological Sciences Research Council; Helse Sør-Øst RHF; Medical Research Council; Canadian Institutes of Health Research; Universitetet i Oslo; Natural Sciences and Engineering Research Council of Canada; Universiteit Gent; Kreftforeningen; Norges Forskningsråd; Novo Nordisk Fonden; Institut National de la Santé et de la Recherche Médicale; Carlsbergfondet; National Human Genome Research Institute; Agence Nationale de la Recherche; Wellcome Trust","keywords":"Biology; Transcription factor; Database; Transcription (linguistics); Computational biology; Genetics; Gene; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1213211694457997,"gpt":0.4122231191157809,"spread":0.2909019496699812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005025553,0.00006797729,0.00009529399,0.00003367651,0.0002119607,0.00008589045,0.0012485,0.00006580833,0.0003348706],"category_scores_gemma":[0.0002110217,0.00004181722,0.00006610267,0.0004344035,0.0002606237,0.00001917295,0.0007209135,0.0001905278,0.00000388456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001778295,"about_ca_system_score_gemma":0.0003813693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001344358,"about_ca_topic_score_gemma":0.00005954906,"domain_scores_codex":[0.9987245,0.0003036,0.0001817548,0.0002534972,0.0003508095,0.0001858993],"domain_scores_gemma":[0.998665,0.00002438449,0.00006603659,0.0008498916,0.0003535744,0.000041092],"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":[0.00005988456,0.00007908988,0.001909061,0.00004975119,0.00002651113,7.915469e-7,0.00008076688,0.000006391073,0.9893253,0.0005850666,0.00454574,0.003331659],"study_design_scores_gemma":[0.0002565514,0.00005236464,0.007135348,0.00004334863,0.000007327789,0.000002938237,0.0005079856,0.00005795811,0.9576508,0.00004497832,0.03418557,0.0000548521],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950536,0.001130205,0.0001999378,0.0009104431,0.0001189256,0.0003586918,0.000300544,0.000001976201,0.001925654],"genre_scores_gemma":[0.9950479,0.001110384,0.0001154693,0.00003555523,0.00005798698,0.00005766947,0.00008621894,0.00001371106,0.003475073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03167452,"threshold_uncertainty_score":0.3666598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306871314","doi":"10.1093/nar/gkac920","title":"CARD 2023: expanded curation, support for machine learning, and resistome prediction at the Comprehensive Antibiotic Resistance Database","year":2022,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Antibiotic Resistance in Bacteria","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University; Simon Fraser University; University of Manitoba; Public Health Agency of Canada; McMaster University","funders":"Michael G. DeGroote Institute for Infectious Disease Research, McMaster University; Cisco Systems Canada; Simon Fraser University; Institute of Infection and Immunity; Canadian Institutes of Health Research; Genome Canada; Canada Foundation for Innovation; Natural Sciences and Engineering Research Council of Canada; McMaster University; Cisco Systems","keywords":"Resistome; Biology; Database; Data curation; Genetics; Computational biology; Antibiotic resistance; Gene nomenclature; Genome; Gene; Antibiotics; Computer science; Mobile genetic elements; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0331706186225609,"gpt":0.3320995253678785,"spread":0.2989289067453176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001210616,0.000168951,0.000184687,0.00009276163,0.001738629,0.00007233475,0.0003628122,0.00009315424,0.0002575302],"category_scores_gemma":[0.0003968925,0.0001464397,0.00007220779,0.0002578094,0.0004867949,0.00001831586,0.000839155,0.0004205166,0.00001401709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001310241,"about_ca_system_score_gemma":0.0001446858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003277508,"about_ca_topic_score_gemma":0.0001888025,"domain_scores_codex":[0.997404,0.000582378,0.0002873504,0.0006462977,0.0006047754,0.0004751552],"domain_scores_gemma":[0.9987223,0.0001500128,0.000105099,0.0005991487,0.0003207879,0.0001026607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001989714,0.00007531894,0.04681141,0.0001581155,0.00009512994,0.0000140339,0.0001609543,0.00003084513,0.8443558,0.0002961041,0.105704,0.0003085397],"study_design_scores_gemma":[0.001206501,0.0008239763,0.03618331,0.00002150639,0.00002657377,0.00004441443,0.0009127384,0.0002643405,0.02256802,0.0000691158,0.9376421,0.0002373949],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919656,0.002420236,0.0002476192,0.000780181,0.000210767,0.000997721,0.001035976,0.00002651908,0.002315385],"genre_scores_gemma":[0.9523959,0.001122926,0.0004141058,0.00009471605,0.0001961191,0.00007449026,0.002074234,0.00005028678,0.04357724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8319381,"threshold_uncertainty_score":0.999561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100363512","doi":"10.1093/nar/gkr485","title":"PHAST: A Fast Phage Search Tool","year":2011,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":2099,"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; Genome Alberta; Genome Canada","keywords":"Prophage; GenBank; Biology; Genome; Genetics; Reference genome; Computational biology; Bacteriophage; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.07767852593840542,"gpt":0.3349419860426489,"spread":0.2572634601042435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001042776,0.000127631,0.0001242193,0.0001028369,0.0004063247,0.00009033333,0.0005851968,0.00009350327,0.09388412],"category_scores_gemma":[0.00006230476,0.0001148335,0.00007834336,0.0005273038,0.0005086468,0.0004468499,0.0007001166,0.0006463395,0.02190429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002232107,"about_ca_system_score_gemma":0.00002448032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001632528,"about_ca_topic_score_gemma":0.0001268522,"domain_scores_codex":[0.9978959,0.0002308502,0.0001907418,0.0004149852,0.0005219026,0.0007456362],"domain_scores_gemma":[0.99922,0.00006630518,0.00002066093,0.0004683209,0.00004021471,0.0001845522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001383787,0.0004123912,0.003618162,0.00001012579,0.0000197628,0.00007556362,0.003840384,0.000002359549,0.8944381,0.0002065215,0.01795274,0.07928552],"study_design_scores_gemma":[0.001234717,0.0008360519,0.5385345,0.00005228634,0.00001539205,0.000164574,0.002231716,0.000690407,0.1665504,0.0004996948,0.2885343,0.0006560414],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7843102,0.00001154163,0.0002072656,0.0001588638,0.0001072427,0.0002440252,0.00001388813,0.00005170768,0.2148952],"genre_scores_gemma":[0.9788177,0.00002850138,0.001811421,0.0001073799,0.00008510434,0.00002976466,0.000004805447,0.00003084416,0.01908449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7278877,"threshold_uncertainty_score":0.9788573,"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":"W2165565773","doi":"10.1093/nar/gkm276","title":"PDB2PQR: expanding and upgrading automated preparation of biomolecular structures for molecular simulations","year":2007,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2030,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Research Resources; National Institute of General Medical Sciences; Centre National de la Recherche Scientifique; Canada Excellence Research Chairs, Government of Canada; Deutsche Forschungsgemeinschaft; National Institutes of Health; Science Foundation Ireland; National Science Foundation","keywords":"Computer science; Software; Computational science; File format; Protein Data Bank (RCSB PDB); XML; Biomolecule; Source code; Force field (fiction); Interface (matter); Biological system; Bioinformatics; Data mining; Biology; Nanotechnology; Materials science; Database; Programming language; Operating system; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02297938988240914,"gpt":0.391952499106739,"spread":0.3689731092243298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000642786,0.0001159712,0.0001327589,0.0001882049,0.0001820745,0.00003502634,0.0001543924,0.0001994562,0.000005755874],"category_scores_gemma":[0.0003172056,0.0001132036,0.00005643243,0.0002346328,0.0001741733,0.000007980379,0.0001170733,0.0001022535,4.159485e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002313792,"about_ca_system_score_gemma":0.00005505536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001220401,"about_ca_topic_score_gemma":0.000008853979,"domain_scores_codex":[0.9987705,0.00006381542,0.0002338179,0.0003146162,0.0002694399,0.0003478275],"domain_scores_gemma":[0.9992334,0.0000529638,0.00006191227,0.0002970677,0.0002660202,0.00008862071],"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":[0.0002289379,0.00001350902,0.001034773,0.00004447988,0.00004644977,0.000001871289,0.00008503319,0.0002987103,0.9933074,0.003193703,0.00009639819,0.001648776],"study_design_scores_gemma":[0.0007389577,0.0005645065,0.004031499,0.00001662723,0.00001533332,0.000009372857,0.0001014943,0.01396326,0.9752228,0.004116635,0.001052428,0.000167122],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9037358,0.000356349,0.09499797,0.00002893223,0.00003568616,0.0004967689,0.00002896641,0.00002862025,0.0002908927],"genre_scores_gemma":[0.9895522,0.0000143032,0.01014229,0.00002382778,0.00006775196,0.00001086437,0.0001245315,0.00002600391,0.00003823427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08581638,"threshold_uncertainty_score":0.461631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2935024989","doi":"10.1093/nar/gkz240","title":"NetworkAnalyst 3.0: a visual analytics platform for comprehensive gene expression profiling and meta-analysis","year":2019,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1976,"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; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Génome Québec; Genome Canada","keywords":"Biology; Gene expression profiling; Profiling (computer programming); Computational biology; Gene expression; Meta-analysis; Visual analytics; Analytics; Gene; Bioinformatics; Data science; Genetics; Visualization; Data mining; Computer science; Internal medicine; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.09194025591472658,"gpt":0.3672860128216967,"spread":0.2753457569069701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008717488,0.0002021965,0.000589327,0.0002181201,0.0002277074,0.0001131446,0.0002757643,0.0002598373,0.00009962819],"category_scores_gemma":[0.00003167189,0.0001589054,0.0005031347,0.0004557721,0.0001251639,0.00001109193,0.0004000681,0.0002563185,0.00002219017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002176536,"about_ca_system_score_gemma":0.00006211975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001054553,"about_ca_topic_score_gemma":0.00001266392,"domain_scores_codex":[0.9981549,0.00007523119,0.0003637088,0.0004784795,0.0003727674,0.0005549445],"domain_scores_gemma":[0.9987044,0.0001002944,0.0001055113,0.0005212607,0.0004012636,0.0001672202],"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":[0.001286915,0.0002513223,0.006211082,0.0004251939,0.1256596,0.000007088607,0.0004206808,0.01892727,0.8289126,0.001466365,0.01339689,0.003034952],"study_design_scores_gemma":[0.003603271,0.002664807,0.001424165,0.00001312283,0.0612631,0.00002567315,0.00223626,0.6604204,0.2148254,0.001790231,0.05012682,0.001606833],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655164,0.003457942,0.0276404,0.0001898115,0.00007008242,0.001408962,0.0001106475,0.00002399619,0.001581691],"genre_scores_gemma":[0.9858612,0.0001645877,0.01192024,0.0001704975,0.0001721875,0.00006299773,0.000381592,0.0000305984,0.001236113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6414931,"threshold_uncertainty_score":0.6479976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2608515760","doi":"10.1093/nar/gkx295","title":"MicrobiomeAnalyst: a web-based tool for comprehensive statistical, visual and meta-analysis of microbiome data","year":2017,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1965,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Profiling (computer programming); Visualization; Microbiome; Biology; Metagenomics; Data visualization; Shotgun sequencing; Data science; Computational biology; Human Microbiome Project; Computer science; Annotation; Data mining; Bioinformatics; Human microbiome; DNA sequencing","retraction":null,"screen_n_in":null,"score":{"opus":0.2050305439053096,"gpt":0.4663702266663905,"spread":0.2613396827610809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001192989,0.0001911132,0.0007842833,0.0003689684,0.0005543316,0.0001622141,0.001036369,0.0001928219,0.0001684974],"category_scores_gemma":[0.0003118406,0.0001625732,0.0002896014,0.0002445147,0.0008643863,0.00001131327,0.0008784398,0.0001654741,0.000009102356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001784693,"about_ca_system_score_gemma":0.0002979722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000167153,"about_ca_topic_score_gemma":0.0001893726,"domain_scores_codex":[0.9978566,0.0002241952,0.0003850234,0.0007919822,0.0002299747,0.0005122257],"domain_scores_gemma":[0.9969729,0.0001616399,0.0001805003,0.0019317,0.0006154513,0.0001377612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002056736,0.0001259012,0.0006077151,0.0001550112,0.01854127,0.000002744722,0.00001570133,0.000003548035,0.9639848,0.00006114912,0.01606165,0.000234766],"study_design_scores_gemma":[0.009082539,0.003604015,0.07042958,0.00002378939,0.1727352,0.00002622308,0.0004008919,0.01909503,0.3159011,0.0001137391,0.406844,0.001743969],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822488,0.001425012,0.003617818,0.001135729,0.00003647792,0.0008763695,0.01055213,0.00001192188,0.00009576462],"genre_scores_gemma":[0.9868867,0.00010291,0.009690845,0.0002116946,0.00004251062,0.00002852089,0.002640893,0.00003024765,0.0003656937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6480838,"threshold_uncertainty_score":0.6629544,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394578957","doi":"10.1093/nar/gkae253","title":"MetaboAnalyst 6.0: towards a unified platform for metabolomics data processing, analysis and interpretation","year":2024,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1961,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; McGill University","funders":"JDRF; Natural Sciences and Engineering Research Council of Canada; Genome Canada; Canadian Institutes of Health Research; National Cancer Institute; Diabetes Canada; National Institutes of Health; Cummings Foundation","keywords":"Annotation; Computer science; Benchmark (surveying); Visualization; Data processing; Data mining; Computational biology; Biology; Database; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.07042803838880195,"gpt":0.3876739563480883,"spread":0.3172459179592863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002133366,0.0001768463,0.0003530837,0.0006194487,0.0002382887,0.0003174668,0.0005366408,0.0001414172,0.00002916306],"category_scores_gemma":[0.0005068409,0.0001448647,0.0001359427,0.001283667,0.0002013134,0.00002983387,0.0007225667,0.0002222234,0.000004936402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002428721,"about_ca_system_score_gemma":0.0001819103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005683905,"about_ca_topic_score_gemma":0.000166164,"domain_scores_codex":[0.9980549,0.00007752629,0.0002804943,0.0008266376,0.0003421583,0.0004183479],"domain_scores_gemma":[0.9988053,0.0000636813,0.00004347588,0.0006847666,0.0002972031,0.0001055264],"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":[0.0008400516,0.0001579907,0.001675293,0.0006978287,0.01119038,0.00001111606,0.0008696254,0.00003154628,0.408701,0.01040788,0.01164536,0.5537719],"study_design_scores_gemma":[0.001019264,0.0006606653,0.005750902,0.00004474978,0.003110064,0.0000151002,0.001479731,0.2359829,0.04887032,0.003713887,0.6986338,0.0007186491],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7851225,0.05970571,0.1468619,0.001503658,0.0002791261,0.001023223,0.0008656368,0.00008285036,0.004555386],"genre_scores_gemma":[0.9849982,0.003622694,0.008787062,0.00005227378,0.0002235048,0.00007145391,0.0008008727,0.0000346877,0.001409247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6869884,"threshold_uncertainty_score":0.5907412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043764521","doi":"10.1093/nar/gkt1115","title":"The MIntAct project—IntAct as a common curation platform for 11 molecular interaction databases","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1957,"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 of Toronto; Ontario Institute for Cancer Research","funders":"National Heart, Lung, and Blood Institute; British Heart Foundation","keywords":"Data curation; Database; Merge (version control); Digital curation; Biology; Computer science; World Wide Web; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.05508653696391626,"gpt":0.3751211313076371,"spread":0.3200345943437209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007161005,0.0001365223,0.0001090482,0.00006732754,0.000461829,0.0002399939,0.0003602405,0.000121993,0.00004645388],"category_scores_gemma":[0.0001991792,0.00009785958,0.0000900427,0.0001293036,0.0001247723,0.00004215815,0.0002454566,0.0002522958,0.0001046237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005028177,"about_ca_system_score_gemma":0.0001214641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005107129,"about_ca_topic_score_gemma":0.0003001527,"domain_scores_codex":[0.9986661,0.00007307417,0.0002729034,0.0002477877,0.000275494,0.0004646305],"domain_scores_gemma":[0.9989143,0.00011908,0.00007905965,0.0005324401,0.0002749391,0.00008015943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007248336,0.0002014768,0.0008563286,0.000130437,0.0002154064,0.000003922658,0.0004941433,0.00005709229,0.5326935,0.0154005,0.237645,0.2115773],"study_design_scores_gemma":[0.0009052015,0.00114768,0.0005708815,0.00005063812,0.00001639551,0.00004290745,0.002581958,0.01917997,0.1202635,0.003449278,0.8514448,0.0003468741],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857315,0.0002749315,0.005582273,0.001016384,0.000207919,0.001779332,0.00003247275,0.0000172943,0.005357842],"genre_scores_gemma":[0.9964654,0.000206771,0.001134952,0.0001979208,0.0002493081,0.0003751162,0.0004585208,0.00002999874,0.0008820124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6137998,"threshold_uncertainty_score":0.3990598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4237335579","doi":"10.1093/nar/gkt1102","title":"The Reactome pathway knowledgebase","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1957,"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","funders":"National Human Genome Research Institute","keywords":"Biology; Annotation; Computational biology; Proteome; Human proteome project; Human disease; Computer science; Bioinformatics; Genetics; Proteomics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02466854049174342,"gpt":0.3002926963206068,"spread":0.2756241558288633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001030086,0.0001073869,0.00008233293,0.00004016611,0.0004687952,0.0001817065,0.0005323524,0.0001633053,0.0001670001],"category_scores_gemma":[0.0001633294,0.00007023841,0.00006681098,0.0001637789,0.000295293,0.000006136168,0.0003926357,0.0003445457,0.001450845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002334105,"about_ca_system_score_gemma":0.0001138475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002603225,"about_ca_topic_score_gemma":0.00002001474,"domain_scores_codex":[0.9986178,0.000119275,0.0002010873,0.0002094571,0.0002788024,0.0005735478],"domain_scores_gemma":[0.9987668,0.00006787011,0.00003368052,0.0006608115,0.0003145603,0.0001562451],"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":[0.0000777252,0.00009463276,0.001011865,0.00002823826,0.00008409548,0.000004004402,0.0002633359,0.000006314499,0.290734,0.004371885,0.3534112,0.3499127],"study_design_scores_gemma":[0.0003221655,0.0002554282,0.002440637,0.000009645324,0.000001825309,0.00001110816,0.0003645546,0.001150249,0.01329988,0.002735398,0.9792445,0.000164574],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8863155,0.001914076,0.0003783791,0.001567464,0.0002923257,0.0006842423,0.000009279011,0.00002467328,0.1088141],"genre_scores_gemma":[0.9855243,0.0004146089,0.0002924574,0.0001582178,0.0004705981,0.0000900614,0.00002822316,0.00002528569,0.01299623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6258333,"threshold_uncertainty_score":0.9993266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2988716798","doi":"10.1093/nar/gkz1001","title":"JASPAR 2020: update of the open-access database of transcription factor binding profiles","year":2019,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1923,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Helse Sør-Øst RHF; Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Lundbeckfonden; CHIST-ERA; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Agence Nationale de la Recherche; Genome British Columbia; H. Lundbeck A/S; Western Canada Research Grid; Canadian Institutes of Health Research; Danmarks Frie Forskningsfond; Compute Canada; Weston Brain Institute; BC Children's Hospital; Michael Smith Health Research BC; Norges Forskningsråd; Kreftforeningen; Children's Hospital Foundation; Universitetet i Oslo; Genome Canada","keywords":"Biology; Transcription factor; DNA binding site; Computational biology; Genetics; Database; Promoter; Gene; Gene expression; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.0868363027045841,"gpt":0.4024198451276514,"spread":0.3155835424230673,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004286153,0.00006790177,0.0001081819,0.00004769662,0.00008096293,0.00005919909,0.001324629,0.00007236588,0.0005692677],"category_scores_gemma":[0.00004756607,0.00004858255,0.00005233508,0.0002918348,0.0001508555,0.00002567185,0.0006090959,0.000136232,0.00002241851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001608721,"about_ca_system_score_gemma":0.0001599542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001070072,"about_ca_topic_score_gemma":0.00001765169,"domain_scores_codex":[0.9989434,0.0001381828,0.0001779045,0.000252469,0.0003002166,0.0001878289],"domain_scores_gemma":[0.9989799,0.000009828053,0.00007076687,0.0006901151,0.00021069,0.00003867181],"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":[0.00008453501,0.00005380537,0.01042872,0.00006959211,0.00002094164,1.246259e-7,0.00003846288,0.000007406766,0.984682,0.0004164381,0.002493577,0.001704446],"study_design_scores_gemma":[0.0003792178,0.0001033388,0.02018966,0.00004975125,0.000004360325,8.822546e-7,0.0001486714,0.00007264357,0.9529382,0.00003660933,0.0260063,0.00007034282],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963217,0.0002779762,0.00008357059,0.0002878251,0.00008476288,0.0005190744,0.0002628274,0.000002064636,0.002160207],"genre_scores_gemma":[0.9975215,0.0005393849,0.0001510068,0.00002099617,0.00003933393,0.00003353304,0.00008745943,0.00001433565,0.00159251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03174372,"threshold_uncertainty_score":0.6233082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2053385401","doi":"10.1093/nar/gkn810","title":"HMDB: a knowledgebase for the human metabolome","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1894,"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 Calgary; University of Alberta","funders":"Canadian Institutes of Health Research; Genome Alberta; Ministry of Advanced Education, Government of Alberta; Genome Canada","keywords":"Metabolome; Metabolomics; Matching (statistics); Software; Biology; Computer science; Database; Information retrieval; Computational biology; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.08576156402712931,"gpt":0.3756688929976746,"spread":0.2899073289705453,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00118395,0.0001477633,0.0001969252,0.000113965,0.001250316,0.00003171948,0.0005381465,0.0001143827,0.000109904],"category_scores_gemma":[0.0005521941,0.0001006813,0.0001633985,0.0003065062,0.0005150838,0.000003562477,0.0003861756,0.0002453475,0.00005758867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001928641,"about_ca_system_score_gemma":0.00009311206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002594988,"about_ca_topic_score_gemma":0.00002948696,"domain_scores_codex":[0.9983674,0.0001276155,0.0001917631,0.0004121572,0.0003228909,0.0005781503],"domain_scores_gemma":[0.9987255,0.000119321,0.00003622309,0.000625773,0.0003949589,0.00009824768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001155295,0.0001558457,0.00252908,0.00002457446,0.0002629721,0.000005545548,0.0001864159,0.000002607049,0.8727955,0.007923637,0.1131102,0.002888105],"study_design_scores_gemma":[0.0008068433,0.0004357076,0.009341404,0.000003130544,0.00002103098,0.00001732881,0.0002169323,0.00005481919,0.08689798,0.0006818284,0.9013485,0.000174465],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9773073,0.009457916,0.001027177,0.00115226,0.0002012282,0.0007318113,0.0000413401,0.00002095384,0.01006007],"genre_scores_gemma":[0.9823847,0.00223758,0.0009100913,0.0001251831,0.0007431166,0.0002595795,0.00003085152,0.00003810153,0.01327079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7882383,"threshold_uncertainty_score":0.961655,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2266356262","doi":"10.1093/nar/gkw027","title":"Foxo3 circular RNA retards cell cycle progression via forming ternary complexes with p21 and CDK2","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1859,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Biology; Circular RNA; Cyclin-dependent kinase 2; Cell cycle; Cyclin A; Cyclin-dependent kinase; Cell biology; Cyclin E1; Small nucleolar RNA; Cyclin E; Restriction point; Cyclin D; Cyclin A2; Non-coding RNA; microRNA; Cell; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02059666658953464,"gpt":0.3183531616178557,"spread":0.2977564950283211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005042632,0.0001975909,0.0001740322,0.0001073732,0.0002908621,0.00006834757,0.0004062512,0.0001638166,0.00009326168],"category_scores_gemma":[0.0001142105,0.0001320279,0.0000725175,0.0001523957,0.0004526042,0.00002014184,0.0005239872,0.0001826265,0.00003406459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004973153,"about_ca_system_score_gemma":0.0001158084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002622939,"about_ca_topic_score_gemma":0.000009270758,"domain_scores_codex":[0.9977304,0.0001810884,0.000187157,0.0006158303,0.0006769457,0.0006085557],"domain_scores_gemma":[0.9987239,0.00004185681,0.00005734367,0.0006997736,0.0002174234,0.0002597167],"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":[0.0002813081,0.000112642,0.02689733,0.00008803455,0.00004137812,0.00005930904,0.00004113824,0.000001277194,0.9359708,0.00002318728,0.001053509,0.03543013],"study_design_scores_gemma":[0.002590588,0.001304061,0.0324147,0.0003489856,0.00002704298,0.0001472195,0.000165575,0.0002101485,0.9291146,0.0007426728,0.03241207,0.0005222877],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928279,0.001446161,0.001710199,0.0002611832,0.0000314066,0.0007123704,0.00001810352,0.00003203077,0.00296068],"genre_scores_gemma":[0.9978158,0.0002039469,0.001084642,0.00005223091,0.0002033776,0.0001343573,0.00002128011,0.00006366691,0.0004207337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03490784,"threshold_uncertainty_score":0.5383942,"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":"W2028133290","doi":"10.1093/nar/gkq1018","title":"Reactome: a database of reactions, pathways and biological processes","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1799,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute","keywords":"Ensembl; Biology; Annotation; chEMBL; Biological pathway; SBML; Computational biology; Database; World Wide Web; Computer science; Bioinformatics; Genomics; Genome; Genetics; Drug discovery; XML; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.04776990182388198,"gpt":0.3233706450189272,"spread":0.2756007431950452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008472068,0.0000839209,0.0001050056,0.00006587837,0.000110474,0.00002701801,0.0002156042,0.0002048983,0.00004282356],"category_scores_gemma":[0.000519971,0.00006607878,0.00002423949,0.000172023,0.0003650772,0.000005297222,0.0002991727,0.0003890618,0.00001017632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003733842,"about_ca_system_score_gemma":0.0001255125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002734552,"about_ca_topic_score_gemma":0.00003696779,"domain_scores_codex":[0.9991146,0.00004398707,0.0001946409,0.0002162824,0.0001706134,0.0002599157],"domain_scores_gemma":[0.9991768,0.00005415185,0.00004987437,0.000375461,0.0002359136,0.0001078112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007241883,0.00006296401,0.002349138,0.00009904417,0.00001575796,0.000001596601,0.00007636404,2.931843e-7,0.983667,0.001045738,0.001674236,0.01093542],"study_design_scores_gemma":[0.001606589,0.001679787,0.01663317,0.0001167815,0.00001566893,0.0001861685,0.001455823,0.0006083807,0.4082085,0.004423736,0.5644433,0.0006220511],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951895,0.0003897528,0.0001768585,0.0001236092,0.00005644686,0.0001616301,0.00005249,0.000008227707,0.003841412],"genre_scores_gemma":[0.9960089,0.001297007,0.002194587,0.00003940556,0.0001616284,0.00001639384,0.0001010781,0.00001069387,0.0001703532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5754585,"threshold_uncertainty_score":0.2694615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4308616307","doi":"10.1093/nar/gkac1010","title":"The NHGRI-EBI GWAS Catalog: knowledgebase and deposition resource","year":2022,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1733,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Canadian Institutes of Health Research; Chief Scientist Office, Scottish Government Health and Social Care Directorate; National Institutes of Health; Department of Health and Social Care; Health and Social Care Research and Development Division; National Institute for Health and Care Research; European Bioinformatics Institute; Medical Research Council; Biogen; Celgene; Scottish Government; British Heart Foundation; National Human Genome Research Institute; Wellcome Trust; Public Health Agency; Engineering and Physical Sciences Research Council; European Molecular Biology Laboratory; NIHR Cambridge Biomedical Research Centre; Economic and Social Research Council; Sanofi","keywords":"Genome-wide association study; Interoperability; Biology; Population; Metadata; Data science; Computational biology; Computer science; World Wide Web; Genetics; Medicine; Single-nucleotide polymorphism; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02876071940963539,"gpt":0.3282563603218645,"spread":0.2994956409122291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002400568,0.00008577328,0.0000953467,0.00005444583,0.001746995,0.00003946949,0.0003164767,0.00009161136,0.00004717362],"category_scores_gemma":[0.0005370497,0.00007028464,0.00004645746,0.0001929457,0.0002631707,0.000001891173,0.0007914038,0.0003694698,0.00002603027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005730219,"about_ca_system_score_gemma":0.00009360215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006809087,"about_ca_topic_score_gemma":0.00008364404,"domain_scores_codex":[0.9978858,0.0009045713,0.0001754191,0.0003306903,0.0002666373,0.0004368336],"domain_scores_gemma":[0.9991634,0.000176889,0.00004401573,0.0004048803,0.0001163376,0.00009446549],"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":[0.0005635698,0.0003314561,0.07496564,0.00003628008,0.0002243254,0.00002605492,0.001006008,0.0003855173,0.2648748,0.002430151,0.5409357,0.1142205],"study_design_scores_gemma":[0.0005050648,0.0007468638,0.04233411,0.00000306138,0.000009663161,0.00006199744,0.001782447,0.0008469526,0.002708098,0.0008385129,0.9499924,0.0001708738],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874206,0.002753637,0.0001464932,0.00304506,0.00008392875,0.0002311613,0.00002997743,0.00001083314,0.006278293],"genre_scores_gemma":[0.9945122,0.0003220469,0.0002492665,0.0002088929,0.0001869685,0.0001297124,0.0001571521,0.00001929902,0.004214438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4090567,"threshold_uncertainty_score":0.9995526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4368358104","doi":"10.1093/nar/gkad326","title":"Proksee: in-depth characterization and visualization of bacterial genomes","year":2023,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1720,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Public Health Agency of Canada; University of Alberta","funders":"Alliance de recherche numérique du Canada; Genome Alberta; Genome Canada","keywords":"JSON; GenBank; Visualization; Computer science; Graphical user interface; Web server; Reference genome; Biology; Contig; Genome; File format; Information retrieval; Data mining; Database; The Internet; World Wide Web; Operating system; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03928388929651389,"gpt":0.336911381044976,"spread":0.2976274917484621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004447113,0.00006336923,0.00009704851,0.0001483,0.00005873116,0.00001713111,0.00009251879,0.00007853077,0.00001648789],"category_scores_gemma":[0.00007878049,0.00006209876,0.00001674956,0.0002953227,0.0001049912,9.516077e-7,0.0002078055,0.00004614531,0.000006215481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008051877,"about_ca_system_score_gemma":0.00004311744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001059982,"about_ca_topic_score_gemma":0.00002286161,"domain_scores_codex":[0.9992149,0.00008447928,0.0001466136,0.0002068815,0.000145051,0.0002020813],"domain_scores_gemma":[0.999671,0.00001351873,0.00002941377,0.0001402094,0.0001134522,0.00003236251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005194002,0.00001779382,0.05242594,0.00002958496,0.00001166617,7.302469e-7,0.0003038737,0.000002419364,0.9379447,0.0001502228,0.00008327216,0.008977904],"study_design_scores_gemma":[0.0005404042,0.0003291688,0.8349279,0.00001396412,0.000002999998,0.000001657639,0.0002372301,0.0002432184,0.1319139,0.0001392155,0.03153496,0.000115386],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990774,0.0001512228,0.00002855274,0.00007081629,0.00005692105,0.0002054888,0.00002574833,0.000002652507,0.000381218],"genre_scores_gemma":[0.9973211,0.001902179,0.00005044094,0.000009242483,0.0001177472,0.00002388541,0.0001925192,0.0000160026,0.0003668702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8060308,"threshold_uncertainty_score":0.2532314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157658519","doi":"10.1093/nar/gkr1122","title":"PhosphoSitePlus: a comprehensive resource for investigating the structure and function of experimentally determined post-translational modifications in man and mouse","year":2011,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Ubiquitin and proteasome pathways","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1705,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism; University of California, San Francisco; McGill University","keywords":"Biology; Computational biology; Scripting language; Visualization; Computer science; Bioinformatics; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.06443778859794261,"gpt":0.3120259387157122,"spread":0.2475881501177696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001971308,0.00006889959,0.0000701734,0.00004936687,0.000145228,0.00001547091,0.0001015044,0.00008240349,0.00001380966],"category_scores_gemma":[0.00006251506,0.00005586161,0.00001869086,0.00006728565,0.0002896212,0.00000589396,0.00007731233,0.0001105691,2.936333e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005578261,"about_ca_system_score_gemma":0.00003605674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005815139,"about_ca_topic_score_gemma":0.00003417068,"domain_scores_codex":[0.9993104,0.00009699488,0.0001286435,0.0001980451,0.0001209963,0.0001448597],"domain_scores_gemma":[0.9995781,0.00004774072,0.00003351277,0.0001579378,0.0001362901,0.00004641454],"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":[0.0002242273,0.00001879848,0.003577534,0.0000320828,0.00001379583,1.619546e-7,0.002244544,0.000002726481,0.9911021,0.0003524896,0.00006046119,0.002371089],"study_design_scores_gemma":[0.0006673566,0.000468801,0.03553418,0.00001701775,0.00000506259,0.000005222855,0.0019778,0.0004369849,0.9587724,0.0006740353,0.001359246,0.00008187773],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984316,0.0005463744,0.0001145214,0.0001306251,0.000007457956,0.0004743776,0.00006849907,0.000003501255,0.0002230566],"genre_scores_gemma":[0.9976215,0.00001936887,0.002051838,0.0001013314,0.00002878505,0.00004328632,0.0000650784,0.00001211579,0.00005669097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03232967,"threshold_uncertainty_score":0.227797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770178180","doi":"10.1093/nar/gkx1126","title":"JASPAR 2018: update of the open-access database of transcription factor binding profiles and its web framework","year":2017,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1605,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Directorate for Biological Sciences; H. Lundbeck A/S; Vlaamse regering; University of Oxford; Centre National de la Recherche Scientifique; Lundbeckfonden; Norges Forskningsråd; Wellcome Trust; Agence Nationale de la Recherche; Canadian Institutes of Health Research; Weston Brain Institute; Genome Canada; Universitetet i Oslo; Innovationsfonden","keywords":"Biology; Bioconductor; Genome; Genome browser; Database; Transcription factor; Computational biology; Computer science; Genomics; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.08434196445863076,"gpt":0.3908931129192929,"spread":0.3065511484606621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004892534,0.00009132266,0.00014007,0.00004375084,0.0003450464,0.0002072124,0.001894706,0.0001368893,0.00005848229],"category_scores_gemma":[0.0002673084,0.00006909244,0.00004193809,0.00006851523,0.0002750921,0.0000299705,0.00191349,0.0002028084,0.000003242867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001080421,"about_ca_system_score_gemma":0.0001226692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005106523,"about_ca_topic_score_gemma":0.00003636241,"domain_scores_codex":[0.9989991,0.00009561314,0.0001829003,0.0002618183,0.0002385521,0.0002219827],"domain_scores_gemma":[0.9987979,0.00001590468,0.000141715,0.0008290084,0.0001552087,0.00006028176],"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":[0.00006025436,0.00004183971,0.009711382,0.0001192625,0.00002832103,4.906776e-7,0.00005703996,0.00000205411,0.9878156,0.001016188,0.0003938155,0.0007537768],"study_design_scores_gemma":[0.000583041,0.0001697111,0.04551688,0.0001904,0.00001208452,0.000003229524,0.0001358338,0.001310996,0.9473995,0.0005273405,0.003997753,0.0001532154],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977245,0.0002964433,0.00006038352,0.0003333903,0.00009461654,0.0003697373,0.0004476943,0.000001752891,0.0006715156],"genre_scores_gemma":[0.9977561,0.001237947,0.0006175214,0.00001408647,0.00004868091,0.00001381715,0.00003909753,0.00001852481,0.0002541913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04041606,"threshold_uncertainty_score":0.3520867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2610656577","doi":"10.1093/nar/gkx343","title":"IslandViewer 4: expanded prediction of genomic islands for larger-scale datasets","year":2017,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1587,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Nuclear Security Administration; Simon Fraser University; Genome British Columbia; Genome Canada; U.S. Department of Energy; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Biology; Genome; Visualization; Genomics; Adaptability; Computational biology; Comparative genomics; Bioinformatics; Data mining; Genetics; Computer science; Ecology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.05211454835590884,"gpt":0.3484007595310954,"spread":0.2962862111751866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007127752,0.0001091714,0.0001728864,0.00005252784,0.0004973046,0.00005120577,0.0005166685,0.0001329825,0.00005785454],"category_scores_gemma":[0.0001793576,0.00009784887,0.0000883816,0.00002513501,0.0002516129,0.000001646553,0.0004255273,0.00009830766,0.00001210324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001186523,"about_ca_system_score_gemma":0.00004650137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002470911,"about_ca_topic_score_gemma":0.00005216299,"domain_scores_codex":[0.9988636,0.00005347095,0.0001971743,0.0003473101,0.0001966006,0.0003418724],"domain_scores_gemma":[0.998687,0.00002620068,0.00008530138,0.0009174951,0.000216452,0.00006753697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001329531,0.00007053813,0.03719265,0.00004695725,0.00008047927,5.207794e-7,0.0001877917,0.000001894363,0.9154763,0.00002070269,0.04366757,0.003121658],"study_design_scores_gemma":[0.002503428,0.001157624,0.2463694,0.00002628685,0.00003496481,0.000006265042,0.0002698483,0.0004620834,0.1608954,0.000638405,0.5873878,0.0002485921],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923266,0.0008785151,0.0001805581,0.0001892689,0.0001784504,0.0003851689,0.00291383,0.00000190406,0.002945759],"genre_scores_gemma":[0.9966589,0.00107924,0.00062911,0.00002915327,0.0003775983,0.00007153563,0.0003473154,0.00002381406,0.0007833099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7545809,"threshold_uncertainty_score":0.3990161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123280311","doi":"10.1093/nar/29.1.242","title":"BIND--The Biomolecular Interaction Network Database","year":2001,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1572,"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; University of Toronto","funders":"Medical Research Council; Canadian Institutes of Health Research","keywords":"Biology; Database; Computational biology; Small molecule; Interaction network; Protein–protein interaction; Proteomics; Computer science; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03752559453523122,"gpt":0.3377666707405587,"spread":0.3002410762053275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001314431,0.000129105,0.0000978699,0.00006047581,0.0004043693,0.0001100095,0.000506286,0.000155182,0.000175977],"category_scores_gemma":[0.0000815106,0.00009671188,0.00007818921,0.0003968494,0.0002121234,0.000009016255,0.0004706609,0.0004256834,0.0002811088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002861429,"about_ca_system_score_gemma":0.00006995322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003749789,"about_ca_topic_score_gemma":0.0000396195,"domain_scores_codex":[0.9983932,0.0001760917,0.000222598,0.0002802238,0.000335425,0.0005924371],"domain_scores_gemma":[0.9988812,0.0000365628,0.00004821075,0.0007594607,0.000153078,0.0001215068],"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":[0.0006319803,0.0001809219,0.004362771,0.00004077555,0.000205482,0.00006232817,0.0002559798,0.0009319364,0.3966509,0.002561444,0.4820115,0.1121041],"study_design_scores_gemma":[0.0003708075,0.0002351937,0.0005965137,0.00002346344,0.000008036196,0.00008214717,0.000248788,0.003638072,0.004779652,0.0005566941,0.9892806,0.0001800186],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.920748,0.002126256,0.02912925,0.002970148,0.0008206294,0.0008289812,0.00002552423,0.00004386113,0.04330733],"genre_scores_gemma":[0.9942282,0.0009108701,0.0008664666,0.0005893926,0.001167428,0.00003292052,0.0001846162,0.00003161141,0.001988471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5072691,"threshold_uncertainty_score":0.3943796,"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":"W2127096898","doi":"10.1093/nar/gkn179","title":"The CGView Server: a comparative genomics tool for circular genomes","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1527,"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":"Genome; Biology; GenBank; Comparative genomics; Sequence (biology); Genomics; Computational biology; Reference genome; Feature (linguistics); Sequence analysis; Sequence alignment; Genetics; Sequence database; Gene; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.09087942816515893,"gpt":0.3477091687792871,"spread":0.2568297406141282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008427257,0.0001566334,0.0001974458,0.0000380913,0.00122112,0.00005165997,0.0005280316,0.000108659,0.00001084671],"category_scores_gemma":[0.000103808,0.0001187924,0.0001521841,0.0001338289,0.000489564,8.814871e-7,0.0003457893,0.0001600511,0.00003249559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004595162,"about_ca_system_score_gemma":0.0002140145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000177659,"about_ca_topic_score_gemma":0.00001957402,"domain_scores_codex":[0.9983982,0.0001475787,0.0002277407,0.0003956819,0.0002652843,0.0005655392],"domain_scores_gemma":[0.9987642,0.0001212757,0.00004546735,0.0005758344,0.0004116361,0.00008159146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003595669,0.0001255478,0.005178789,0.00007475012,0.0005560051,0.000008555895,0.002217907,0.0001090343,0.9501464,0.001444202,0.032626,0.00715321],"study_design_scores_gemma":[0.0005730759,0.0004277175,0.006962282,0.000004694662,0.00001075417,0.00002509902,0.0005995716,0.0001438451,0.03093212,0.0008335498,0.9592782,0.0002091408],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9844832,0.01298647,0.000133957,0.0004768311,0.0001092808,0.0007408982,0.00006050193,0.00000340953,0.001005392],"genre_scores_gemma":[0.9879842,0.008731665,0.0008851899,0.000106744,0.0004680489,0.0002123577,0.00003042522,0.00003037972,0.001550946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9266521,"threshold_uncertainty_score":0.9391988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809000676","doi":"10.1093/nar/gky311","title":"GeneMANIA update 2018","year":2018,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1435,"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":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health","keywords":"Biology; Function (biology); Model organism; Set (abstract data type); Computer science; Genomics; Caenorhabditis elegans; Computational biology; Gene; Genome; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02920307701016343,"gpt":0.3218955130479575,"spread":0.2926924360377941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008400894,0.0001144904,0.0001007144,0.00007243285,0.0002950746,0.00007266863,0.0004625516,0.0002003803,0.0004528643],"category_scores_gemma":[0.00004901064,0.000102876,0.00005596687,0.0001849314,0.0004382524,0.000004632415,0.0004535057,0.0002190285,0.001893194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002177037,"about_ca_system_score_gemma":0.00009014584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001471045,"about_ca_topic_score_gemma":0.00003466526,"domain_scores_codex":[0.9985943,0.00007376629,0.0001908937,0.0002855216,0.0002977193,0.0005578094],"domain_scores_gemma":[0.9989335,0.000009144388,0.00003253104,0.0006177549,0.0002577539,0.0001493117],"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":[0.0001910366,0.00007421216,0.001101222,0.00002622446,0.0000902737,0.000005680958,0.0002045515,0.00000497645,0.2472705,0.002698704,0.6986222,0.04971043],"study_design_scores_gemma":[0.0003898133,0.0005683877,0.001240573,0.00000947569,0.000004033557,0.00001674527,0.00009877079,0.001013772,0.03481274,0.001503576,0.9601469,0.0001951973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986777,0.0006843143,0.00417232,0.0008930566,0.0004620273,0.0003498707,0.00002424761,0.000031542,0.09470493],"genre_scores_gemma":[0.9902838,0.000269528,0.002776037,0.0005645373,0.001668079,0.00001387357,0.00005788969,0.00003174725,0.004334465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2615247,"threshold_uncertainty_score":0.998884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2918086501","doi":"10.1093/nar/gkw199","title":"g:Profiler—a web server for functional interpretation of gene lists (2016 update)","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1412,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"European Regional Development Fund; Eesti Teadusagentuur","keywords":"Ensembl; Biology; Gene; Database; KEGG; Computational biology; Python (programming language); Interface (matter); Computer science; Gene ontology; Genetics; Gene expression; Genomics; Genome; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02453850231463121,"gpt":0.2983178263307848,"spread":0.2737793240161536,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007653114,0.00009511985,0.0001138413,0.00007509405,0.00008329342,0.00001920921,0.000232106,0.0001746865,0.0001931711],"category_scores_gemma":[0.0001126067,0.00006672987,0.00009068441,0.00008665117,0.0001631554,0.000009675553,0.0001365352,0.00008200356,0.00007283695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002997373,"about_ca_system_score_gemma":0.0001704537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003456677,"about_ca_topic_score_gemma":0.00000828358,"domain_scores_codex":[0.9989135,0.00005580183,0.0002506047,0.0002248752,0.0002417611,0.0003134576],"domain_scores_gemma":[0.9990866,0.00004876667,0.00006564982,0.0003413047,0.0003780253,0.00007962313],"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":[0.0007339123,0.00005470733,0.0006178273,0.00006577968,0.0000907869,4.065265e-7,0.00005527609,0.0000235272,0.8538336,0.001443601,0.07473188,0.06834865],"study_design_scores_gemma":[0.005128774,0.001760343,0.007450611,0.0002101186,0.00003120983,0.00002239774,0.000206993,0.01363331,0.591177,0.005178875,0.3745615,0.0006388636],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8999322,0.0005508199,0.09365138,0.0009814892,0.0003661138,0.0006293746,0.0002223053,0.00001559019,0.003650733],"genre_scores_gemma":[0.9945639,0.0001917967,0.001782234,0.00009932572,0.0003266945,0.0000506944,0.0001380051,0.0000217569,0.002825553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2998296,"threshold_uncertainty_score":0.2721165,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166657289","doi":"10.1093/nar/gkt958","title":"The Database of Genomic Variants: a curated collection of structural variation in the human genome","year":2013,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1408,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Genome; Biology; Database; Computational biology; Genomics; Structural variation; Visualization; Genome browser; Genetics; Data mining; Computer science; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02641085562594491,"gpt":0.3022236331060938,"spread":0.2758127774801489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009697745,0.00007455494,0.00009185135,0.00007875923,0.0003096937,0.000045815,0.0004267504,0.00007686816,0.0001724319],"category_scores_gemma":[0.0001031104,0.00004757978,0.00003669125,0.0002742131,0.000177322,0.00001232959,0.0001448915,0.000158051,0.00001248381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003436796,"about_ca_system_score_gemma":0.0001147217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001458937,"about_ca_topic_score_gemma":0.0001389969,"domain_scores_codex":[0.9986818,0.0003865365,0.0002950238,0.0001645023,0.0002413002,0.0002308259],"domain_scores_gemma":[0.999103,0.00005812203,0.00009089502,0.0004220022,0.0003024404,0.00002360879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002839098,0.00003106678,0.002620737,0.00001832181,0.0000273936,3.231077e-7,0.0008558813,0.00003199775,0.9936256,0.00234899,0.0003111166,0.0001001929],"study_design_scores_gemma":[0.0006311375,0.0003754689,0.9714338,0.00001066568,0.000009053651,0.00001212115,0.002079841,0.0008007676,0.02180326,0.001635989,0.001100101,0.0001077746],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978762,0.0001799464,0.00005248189,0.0002049732,0.00003582187,0.000418625,0.00003673676,0.000002176846,0.001193028],"genre_scores_gemma":[0.999101,0.00008270144,0.0001519775,0.00001423357,0.00007156793,0.00005895424,0.00008741208,0.000009597704,0.0004225409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9718223,"threshold_uncertainty_score":0.2381945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052685738","doi":"10.1093/nar/gks1147","title":"InnateDB: systems biology of innate immunity and beyond—recent updates and continuing curation","year":2012,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Immune responses and vaccinations","field":"Immunology and Microbiology","cited_by":1386,"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":"Canadian Institutes of Health Research; National Institutes of Health; Teagasc; European Commission; Genome British Columbia; FP7 Health; Michael Smith Health Research BC; Foundation for the National Institutes of Health","keywords":"Innate immune system; Biology; Computational biology; Data curation; Relevance (law); Ontology; Immunity; World Wide Web; Computer science; Immunology; Immune system","retraction":null,"screen_n_in":null,"score":{"opus":0.03856752615121419,"gpt":0.3420461626258681,"spread":0.303478636474654,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001903407,0.0001127358,0.0002465763,0.0003189643,0.0003016664,0.00002880935,0.0001503462,0.0002557622,0.0001993592],"category_scores_gemma":[0.0004666336,0.00009522439,0.00002227166,0.0002992254,0.0004106019,0.000262044,0.0002953463,0.0004842385,0.00005092903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003336827,"about_ca_system_score_gemma":0.00003041459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002053249,"about_ca_topic_score_gemma":0.000003595795,"domain_scores_codex":[0.9979533,0.001045933,0.0002989464,0.0001649607,0.00005158865,0.0004852677],"domain_scores_gemma":[0.9989354,0.0003804778,0.00008751882,0.0002281571,0.0003318363,0.00003662126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002574414,0.0001578279,0.02492261,0.00006403372,0.0001216424,5.25147e-7,0.003283315,3.776542e-7,0.8618003,0.03568126,0.0007883433,0.07292233],"study_design_scores_gemma":[0.005828915,0.001589212,0.323638,0.0002528316,0.0000938739,0.0003505072,0.02092397,0.0002753046,0.2489417,0.001468047,0.3958724,0.0007651689],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655585,0.03209893,0.00004737252,0.0004448602,0.0002748999,0.0002876887,0.00003191514,0.00002604673,0.00122978],"genre_scores_gemma":[0.9954959,0.003829033,0.00003482669,0.00001097102,0.00002250998,0.00002245895,0.00007923001,0.00001348831,0.0004916119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6128586,"threshold_uncertainty_score":0.3883138,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}