{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":43,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":43,"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":"09521ba2f298","filters":{"venue":"Journal of Cheminformatics"}},"results":[{"id":"W2548357532","doi":"10.1186/s13321-016-0174-y","title":"ClassyFire: automated chemical classification with a comprehensive, computable taxonomy","year":2016,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1587,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"The Metabolomics Innovation Centre; Alberta Innovates; Athabasca University; Ottawa Hospital; University of Ottawa; University of Alberta","funders":"Alberta Innovates; National Institutes of Health; Genome Alberta; U.S. National Library of Medicine; University of Alberta; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Taxonomy (biology); Class (philosophy); Druggability; Information retrieval; Chemical database; Artificial intelligence; Data science; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.04246514513245019,"gpt":0.2767156684727564,"spread":0.2342505233403062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003628768,0.0001713569,0.0003261828,0.0001528054,0.0000477237,0.0001358101,0.0008087388,0.00006953075,0.000007867893],"category_scores_gemma":[0.0001031573,0.0001026329,0.00009628348,0.0003979507,0.00009459633,0.001797332,0.0001464151,0.000165863,0.00002477599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001855454,"about_ca_system_score_gemma":0.0003585092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.726375e-7,"about_ca_topic_score_gemma":5.447978e-8,"domain_scores_codex":[0.9981908,0.00002886727,0.0008103041,0.0001130386,0.0006198549,0.0002371324],"domain_scores_gemma":[0.9972426,0.0006378684,0.0009530674,0.0003194467,0.0006832212,0.0001637882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00052871,0.001038957,0.002121184,0.0006397567,0.0009052214,0.0001325223,0.003017465,0.02299565,0.1091127,0.05639686,0.1323903,0.6707206],"study_design_scores_gemma":[0.002633015,0.0002243667,0.002104221,0.0003943216,0.0000370605,0.001299566,0.0001232268,0.8974704,0.05642163,0.001807921,0.03707732,0.0004069787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1048676,0.00003420639,0.890677,0.001218393,0.0001854312,0.0001441132,0.000002705005,0.0001419021,0.002728712],"genre_scores_gemma":[0.5290284,0.00001244816,0.4705911,0.0002300384,0.00008122114,0.000005524155,0.000001571981,0.000009204754,0.00004050544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8744747,"threshold_uncertainty_score":0.418525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2907470641","doi":"10.1186/s13321-018-0324-5","title":"BioTransformer: a comprehensive computational tool for small molecule metabolism prediction and metabolite identification","year":2019,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":513,"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":"Eidgenössische Anstalt für Wasserversorgung Abwasserreinigung und Gewässerschutz; Genome Alberta; Agence Nationale de la Recherche; Alberta Innovates; Alberta Innovates - Health Solutions; Joint Programming Initiative A healthy diet for a healthy life; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Identification (biology); In silico; Computational biology; Metabolomics; Data mining; Machine learning; Bioinformatics; Chemistry; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.00830872921048072,"gpt":0.2322572317208913,"spread":0.2239485025104106,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002627696,0.0001214168,0.0002615514,0.00009538334,0.00004953792,0.00004112017,0.000099941,0.00007692399,0.000003988419],"category_scores_gemma":[0.00006547109,0.0001037,0.0001321508,0.00007228806,0.00003649466,0.00002376881,0.00003232498,0.00007626066,0.000001581922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009144994,"about_ca_system_score_gemma":0.00005128553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.488144e-7,"about_ca_topic_score_gemma":1.458581e-7,"domain_scores_codex":[0.9990301,0.000007117816,0.0005848545,0.00008835447,0.0001543951,0.0001351797],"domain_scores_gemma":[0.9989191,0.00003115895,0.0004298079,0.0001080081,0.0004624045,0.00004950707],"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":[0.0002368212,0.00006582936,0.0004998425,0.0003108935,0.0005951822,2.911991e-7,0.0004277238,0.0005189803,0.9884903,0.002097409,0.001510971,0.005245711],"study_design_scores_gemma":[0.004192153,0.0004903492,0.01113022,0.00003686945,0.0004233799,0.0001744999,0.0007235361,0.005496242,0.8411136,0.001551318,0.1342979,0.0003699072],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9664196,0.002197384,0.0302713,0.0001127007,0.0002812537,0.0002918995,0.000092251,0.000003591939,0.0003300555],"genre_scores_gemma":[0.9766408,0.001720076,0.020783,0.0002432133,0.0002129564,0.00001002179,0.0001460898,0.00001535392,0.0002284867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1473767,"threshold_uncertainty_score":0.4228764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2605952223","doi":"10.1186/s13321-017-0209-z","title":"SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":509,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Benchmark (surveying); Computer science; Binding affinities; Binary number; Boosting (machine learning); Drug discovery; Drug target; Affinities; Gradient boosting; Machine learning; Binary classification; Artificial intelligence; Data mining; Bioinformatics; Support vector machine; Random forest; Mathematics; Chemistry; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06109063848381403,"gpt":0.3506717947180562,"spread":0.2895811562342422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002596968,0.0002055158,0.000396856,0.0001372718,0.0009208538,0.001087234,0.001423402,0.00005717106,0.000001123242],"category_scores_gemma":[0.00205195,0.0001788413,0.0002246725,0.0001053777,0.00009116451,0.003113128,0.0005214381,0.0002790877,5.413373e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001354026,"about_ca_system_score_gemma":0.0002050542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004961287,"about_ca_topic_score_gemma":3.438979e-7,"domain_scores_codex":[0.9978514,0.00002256636,0.001036197,0.0001271898,0.000562957,0.000399713],"domain_scores_gemma":[0.995802,0.0008332785,0.002391178,0.0004203856,0.000420639,0.0001325185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002459804,0.0005077032,0.0222003,0.00377555,0.0007814259,0.00006643806,0.1478195,0.6253841,0.002282974,0.01154064,0.001568731,0.1838266],"study_design_scores_gemma":[0.0005870513,0.00004643034,0.0002742142,0.0002312637,0.0000246637,0.0003204383,0.001403382,0.9899146,0.004450691,0.002140689,0.0004030989,0.0002034786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3312326,0.00006072224,0.6654793,0.0001009382,0.0005423938,0.0001443581,0.00001770241,0.00002470625,0.002397204],"genre_scores_gemma":[0.3024243,0.00000625333,0.6971593,0.00004924451,0.0002675636,0.000003234742,0.000004036769,0.00001329157,0.00007272822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3645305,"threshold_uncertainty_score":0.9999498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044334750","doi":"10.1186/s13321-020-00450-7","title":"A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions","year":2020,"lang":"en","type":"review","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":391,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Drug repositioning; Computer science; Drug discovery; Process (computing); Data science; Multidisciplinary approach; Drug development; Computational model; Drug; Field (mathematics); Risk analysis (engineering); Artificial intelligence; Bioinformatics; Medicine; Pharmacology","retraction":null,"screen_n_in":null,"score":{"opus":0.2181327886717617,"gpt":0.3515936227001733,"spread":0.1334608340284116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001497642,0.0003385066,0.00179736,0.000285606,0.00006196021,0.0001371991,0.0008187839,0.0001091116,0.000004166084],"category_scores_gemma":[0.0002710078,0.0002855757,0.0004777066,0.000394372,0.00008915738,0.001286539,0.0003047861,0.000571431,0.000001374051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384257,"about_ca_system_score_gemma":0.002633035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.805091e-7,"about_ca_topic_score_gemma":1.161242e-7,"domain_scores_codex":[0.996305,0.0001603857,0.002498222,0.0001666628,0.0007076909,0.0001620553],"domain_scores_gemma":[0.9941668,0.00097678,0.003891917,0.0003016914,0.0004529719,0.0002098227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001024509,0.00003644765,6.829781e-9,0.1131272,0.0001921696,0.00001591917,0.0008058241,0.00009479559,7.187852e-9,0.01811893,0.002396567,0.8652111],"study_design_scores_gemma":[0.000115699,0.00005195759,3.481725e-7,0.07955093,0.000379804,0.002638835,0.0002175658,0.003842719,7.672243e-7,0.00373689,0.9092293,0.0002351831],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.000637e-7,0.9578421,0.03416902,0.0005456329,0.0001732407,0.000259228,0.00002068876,0.00002048325,0.006969477],"genre_scores_gemma":[9.128872e-7,0.8903353,0.1093511,0.0001237671,0.0001022254,0.000008767922,0.0000440959,0.00001543953,0.00001835894],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9068328,"threshold_uncertainty_score":0.9999596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2603853601","doi":"10.1186/s13321-017-0207-1","title":"Critical Assessment of Small Molecule Identification 2016: automated methods","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":192,"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":"Academy of Finland; Leibniz-Gemeinschaft; Deutsche Forschungsgemeinschaft; Metabolomics Innovation Centre; European Commission","keywords":"Computer science; Identification (biology); CONTEST; Machine learning; Annotation; Ranking (information retrieval); Artificial intelligence; Metadata; Data mining; Information retrieval; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04345306440196599,"gpt":0.4468853515237422,"spread":0.4034322871217762,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003002667,0.0001048309,0.0002907833,0.0001427659,0.0001234453,0.000391259,0.00151003,0.00005850248,0.000006004409],"category_scores_gemma":[0.002331357,0.00009082755,0.0001445616,0.0001011204,0.0001008896,0.001808233,0.0003037644,0.0001926821,0.000002855589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007037338,"about_ca_system_score_gemma":0.0004056337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001454299,"about_ca_topic_score_gemma":9.196629e-8,"domain_scores_codex":[0.9981001,0.00007022702,0.001111156,0.0000744274,0.0004962886,0.0001478215],"domain_scores_gemma":[0.9959522,0.0006947928,0.001735009,0.0006105831,0.0009030925,0.000104282],"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":[0.00005870364,0.001286178,0.0008961589,0.00202772,0.0006906356,0.00007889093,0.007877853,0.03189563,0.174738,0.2463879,0.01664539,0.5174169],"study_design_scores_gemma":[0.0002577977,0.00005331823,0.008185129,0.00009775092,0.00002780632,0.00008075585,0.0000413191,0.8714378,0.1126281,0.006896026,0.0001976337,0.00009662846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01406535,0.00003503473,0.978816,0.0006090649,0.0005348738,0.00005505007,0.000002202581,0.00002732391,0.005855137],"genre_scores_gemma":[0.257116,0.00001102151,0.7427555,0.00004403237,0.00003716557,0.00000107338,7.774818e-7,0.000004207122,0.00003031064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8395422,"threshold_uncertainty_score":0.377292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146538435","doi":"10.1186/1758-2946-3-19","title":"Linked open drug data for pharmaceutical research and development","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":187,"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":"Pfizer","keywords":"Data science; Computer science; Task (project management); Open data; Data sharing; External Data Representation; Web application; World Wide Web; Data mining; Medicine; Engineering; Alternative medicine; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.4477610663788747,"gpt":0.4690782952067872,"spread":0.02131722882791248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777505,0.00006693842,0.0001406274,0.00003823934,0.00007179774,0.00004013087,0.0008641396,0.00008881729,0.0000112302],"category_scores_gemma":[0.0004975687,0.00004899784,0.00001624488,0.00003865247,0.0001562989,0.00001923443,0.0008014014,0.000163157,0.000001795891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008497494,"about_ca_system_score_gemma":0.0002193108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.814792e-7,"about_ca_topic_score_gemma":0.000001237946,"domain_scores_codex":[0.9991701,0.000008947189,0.0003907795,0.00007797948,0.0001725563,0.0001796959],"domain_scores_gemma":[0.9992051,0.00005947576,0.0001464036,0.0002314334,0.0002313992,0.0001261963],"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":[0.001490536,0.0005223246,0.001141418,0.0005934747,0.0005050643,0.00001372363,0.008481905,3.241893e-7,0.02189137,0.0002035907,0.3590345,0.6061218],"study_design_scores_gemma":[0.001148015,0.0002950776,0.0001586787,0.00005146884,0.0000146074,0.00008879074,0.001422071,0.0001066527,0.156973,0.0002345836,0.8394071,0.00009987457],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9540431,0.003451564,0.01917966,0.001290888,0.00062419,0.0008901816,0.00007217746,0.00001513941,0.0204331],"genre_scores_gemma":[0.494962,0.0006026084,0.5020807,0.0004651792,0.0003996233,0.00001286971,0.0001148485,0.00002052614,0.001341689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6060219,"threshold_uncertainty_score":0.1998074,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963037859","doi":"10.1186/s13321-019-0349-4","title":"DNAmod: the DNA modification database","year":2019,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; Canada Research Chairs; Princess Margaret Cancer Centre; Fleming College; University of Toronto","funders":"Canadian Institutes of Health Research; China Scholarship Council; Ontario Ministry of Research, Innovation and Science; Government of Ontario; University of Toronto; Canadian Cancer Society; Ontario Institute for Cancer Research; Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Computer science; Database; Computational biology; DNA; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01057123793612273,"gpt":0.2545547639121071,"spread":0.2439835259759844,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002832938,0.00006314433,0.00007977842,0.00002312494,0.00003433417,0.00002684466,0.0002657435,0.00004685115,0.00003534447],"category_scores_gemma":[0.00004568078,0.00003988339,0.00007028232,0.00005621028,0.00002737903,0.00001720526,0.00003394559,0.0000920294,0.00002610101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001402012,"about_ca_system_score_gemma":0.00008496025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.227668e-7,"about_ca_topic_score_gemma":2.719553e-7,"domain_scores_codex":[0.999379,0.000005417916,0.0003240182,0.00004104685,0.0001638611,0.00008664535],"domain_scores_gemma":[0.9990982,0.00001048628,0.0003460684,0.0003391398,0.0001674883,0.00003863833],"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":[0.00006747806,0.00005788792,0.0004295884,0.00006321524,0.00007977964,4.139845e-7,0.0004216904,0.0004720633,0.945078,0.000574304,0.04220343,0.01055217],"study_design_scores_gemma":[0.0006641813,0.0001374458,0.0007813471,0.00003447007,0.00003879177,0.0001072727,0.0008879086,0.001570551,0.6634436,0.00009323581,0.3320971,0.0001441744],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863659,0.0003588156,0.003244123,0.0004028603,0.0001924841,0.0001008457,0.000009732796,0.000001998694,0.009323303],"genre_scores_gemma":[0.9972215,0.0003236666,0.0008898695,0.0002860526,0.0001779497,0.000002611712,0.00003038654,0.000006388057,0.001061625],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2898936,"threshold_uncertainty_score":0.1626398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1495258543","doi":"10.1186/s13321-015-0085-3","title":"ChemDoodle Web Components: HTML5 toolkit for chemical graphics, interfaces, and informatics","year":2015,"lang":"en","type":"review","venue":"Journal of Cheminformatics","topic":"Various Chemistry Research Topics","field":"Chemistry","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Research Canada; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"HTML5; JavaScript; Computer science; World Wide Web; Graphics; Multimedia; Web application; Computer graphics; Computer graphics (images)","retraction":null,"screen_n_in":null,"score":{"opus":0.0822703604728123,"gpt":0.3506828443376288,"spread":0.2684124838648164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001234193,0.0008176999,0.00301141,0.000256697,0.00008508759,0.0003116272,0.001467747,0.001061766,0.00007313111],"category_scores_gemma":[0.001239436,0.0006654758,0.0008000862,0.0002713128,0.0002918403,0.0006794288,0.0005484528,0.002049286,0.00001246306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005750855,"about_ca_system_score_gemma":0.001360834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.498363e-7,"about_ca_topic_score_gemma":2.434181e-7,"domain_scores_codex":[0.9940679,0.00001028531,0.003852727,0.0001689776,0.001190178,0.0007099109],"domain_scores_gemma":[0.9932107,0.0005303718,0.003789983,0.0006719184,0.001086528,0.0007104786],"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":[0.000104367,0.0002821581,0.000005111076,0.267072,0.001783125,0.0000226868,0.001708097,0.000001311512,0.0004437605,0.0001128072,0.06958638,0.6588782],"study_design_scores_gemma":[0.001431563,0.00005997532,1.138734e-8,0.01091123,0.000965183,0.001510558,0.0004276796,0.0005746333,0.00357294,0.0001650302,0.9797533,0.0006279144],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009095944,0.9858796,0.00007877762,0.00004626434,0.0002207087,0.0004351216,0.0004773271,0.00005593893,0.01189664],"genre_scores_gemma":[0.00005444792,0.9921098,0.005801448,0.00003698043,0.0006585475,0.00003560768,0.0004008357,0.00009967797,0.0008026721],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9101669,"threshold_uncertainty_score":0.9995797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2745961286","doi":"10.1186/s13321-017-0234-y","title":"Comparative analysis of chemical similarity methods for modular natural products with a hypothetical structure enumeration algorithm","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"MacEwan University; McMaster University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Cheminformatics; Chemical space; Chemical similarity; Computer science; Natural product; Similarity (geometry); Enumeration; Modular design; Data mining; Drug discovery; Biochemical engineering; Algorithm; Structural similarity; Artificial intelligence; Bioinformatics; Chemistry; Mathematics; Biology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0263425672799847,"gpt":0.3490112789775224,"spread":0.3226687116975377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004949116,0.0001595274,0.0009075613,0.0001505449,0.00008152588,0.00005354501,0.0002095751,0.0001154061,0.00001410651],"category_scores_gemma":[0.001007414,0.00009303703,0.0002243914,0.0001868788,0.0001805593,0.0003204473,0.00003468938,0.0003413813,1.260414e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098624,"about_ca_system_score_gemma":0.0001271412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001341003,"about_ca_topic_score_gemma":4.43442e-7,"domain_scores_codex":[0.9987836,0.00001227961,0.0006609708,0.00009986486,0.0002891623,0.0001541167],"domain_scores_gemma":[0.996932,0.0001118856,0.001188483,0.0003511381,0.001333911,0.00008262714],"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":[0.0007239667,0.0001253655,0.00005480687,0.0003623079,0.002509079,0.00000283319,0.001204493,0.00002076026,0.9525944,0.00004128785,0.0005758635,0.04178486],"study_design_scores_gemma":[0.0008964211,0.0002114867,0.000572041,0.00008879452,0.002976505,0.0001294215,0.00009803187,0.02635158,0.967682,0.00007613672,0.0008047406,0.0001128184],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859273,0.0002734721,0.01064689,0.002202087,0.0001793443,0.0005033786,0.00007777465,0.000007161859,0.0001825283],"genre_scores_gemma":[0.6284381,0.000007495432,0.3713139,0.00005470517,0.0001355296,2.233396e-7,0.00001934185,0.000004057822,0.00002668531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.360667,"threshold_uncertainty_score":0.379394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2994270865","doi":"10.1186/s13321-019-0398-8","title":"The chemfp project","year":2019,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Discovery Air (Canada)","funders":"","keywords":"Computer science; x86; Benchmark (surveying); Cheminformatics; Data mining; Implementation; Software; Information retrieval; Parallel computing; Operating system; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.009351925075971965,"gpt":0.278540231171479,"spread":0.269188306095507,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108675,0.00006881,0.0001260847,0.00005814465,0.00005026954,0.0001990902,0.0009677685,0.00002459766,0.000003667236],"category_scores_gemma":[0.0001959864,0.00004040276,0.00009878394,0.0002338558,0.00002058227,0.0009671653,0.0001524477,0.0001786898,0.00003447822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004780513,"about_ca_system_score_gemma":0.0002911891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.542416e-7,"about_ca_topic_score_gemma":5.37563e-8,"domain_scores_codex":[0.998846,0.00001319478,0.0004896272,0.00003604962,0.0004813439,0.000133812],"domain_scores_gemma":[0.9983978,0.0005787257,0.0005055169,0.0002536332,0.0002266191,0.0000376937],"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":[0.00009765834,0.0001837577,0.0007085281,0.0003712579,0.0003404418,0.00002308094,0.01896125,0.01968146,0.001681387,0.1888597,0.1016773,0.6674142],"study_design_scores_gemma":[0.001277143,0.0002818549,0.0009586039,0.0001420609,0.00002093485,0.001027033,0.0009768632,0.6526332,0.03848971,0.03203433,0.2718057,0.0003524884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2601517,0.0005067436,0.6097674,0.003637752,0.003244522,0.0004656203,0.000001647923,0.0000599869,0.1221646],"genre_scores_gemma":[0.4892328,0.000145652,0.5072028,0.0009500262,0.0003708394,0.000003418745,9.299037e-7,0.00001572862,0.002077789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6670617,"threshold_uncertainty_score":0.1919831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110899240","doi":"10.1186/1758-2946-1-4","title":"A constructive approach for discovering new drug leads: Using a kernel methodology for the inverse-QSAR problem","year":2009,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Quantitative structure–activity relationship; Kernel (algebra); Feature vector; Molecular descriptor; Computer science; Support vector machine; Kernel method; Feature (linguistics); Artificial intelligence; Inverse; Algorithm; Pattern recognition (psychology); Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.09032694935977614,"gpt":0.348785861803831,"spread":0.2584589124440548,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002116592,0.0001699157,0.000379365,0.0001290382,0.0001408693,0.0001943546,0.0008930204,0.00005665287,7.725192e-7],"category_scores_gemma":[0.0006289441,0.000117774,0.0002744684,0.000257081,0.00006730517,0.00145041,0.000107722,0.0002204252,2.501976e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001360203,"about_ca_system_score_gemma":0.0006010194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002853208,"about_ca_topic_score_gemma":5.304055e-7,"domain_scores_codex":[0.9984393,0.00004063323,0.0008045998,0.0001133937,0.0003269818,0.0002751287],"domain_scores_gemma":[0.9962044,0.002139259,0.0009951064,0.0002271422,0.0003293037,0.0001048132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002744389,0.00011391,0.00002375837,0.0003630991,0.0003391317,0.000002259389,0.03341384,0.6748015,0.00193805,0.06038781,0.01062374,0.2177185],"study_design_scores_gemma":[0.001093372,0.0001125247,0.00002267201,0.00005545693,0.00007876349,0.0003777436,0.001344412,0.9233211,0.007324283,0.06482232,0.001288004,0.0001592988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005937594,0.000110894,0.9919283,0.0007310699,0.0002992259,0.000477634,0.000004924135,0.0000139875,0.0004963414],"genre_scores_gemma":[0.01063071,0.000008977364,0.9884928,0.0004976506,0.0002944421,0.000005371573,0.000001496254,0.000007966671,0.00006054395],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2485196,"threshold_uncertainty_score":0.4802683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4322102662","doi":"10.1186/s13321-023-00698-9","title":"ABT-MPNN: an atom-bond transformer-based message-passing neural network for molecular property prediction","year":2023,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of Manitoba","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Cystic Fibrosis Canada; Manitoba Medical Service Foundation","keywords":"Computer science; Interpretability; Message passing; Molecular graph; Theoretical computer science; Embedding; Artificial neural network; Graph embedding; Artificial intelligence; Graph; Distributed computing","retraction":null,"screen_n_in":null,"score":{"opus":0.02954166971114737,"gpt":0.3017053752043101,"spread":0.2721637054931628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001697861,0.0001702311,0.0002822873,0.0001871764,0.0001472477,0.0002616762,0.0006460701,0.00007644729,0.000002520042],"category_scores_gemma":[0.0001114734,0.0001232703,0.00021986,0.0006722367,0.00003801564,0.002101879,0.00003777967,0.0002528169,0.000002652762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009096505,"about_ca_system_score_gemma":0.0003641247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.77563e-7,"about_ca_topic_score_gemma":3.186323e-7,"domain_scores_codex":[0.9978868,0.00003251753,0.0008849828,0.0001136579,0.0007386673,0.0003433556],"domain_scores_gemma":[0.9983773,0.0003196351,0.0005005165,0.0002456948,0.0003871639,0.0001697483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007076633,0.00006712381,0.00005057814,0.0002435088,0.00006174669,0.00002005934,0.00185276,0.8688375,0.001770723,0.001282519,0.007782562,0.1179602],"study_design_scores_gemma":[0.000775672,0.0002577568,0.0003472424,0.0001018505,0.00003413082,0.00007991971,0.0001099809,0.9723008,0.01874657,0.003204057,0.003889092,0.0001529606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1152679,0.00002933861,0.8823461,0.000838005,0.0005875521,0.0002311308,0.000009546388,0.00008399932,0.0006063912],"genre_scores_gemma":[0.3505002,0.00001180221,0.6481273,0.0007564825,0.0004529257,0.00002004727,0.00003956353,0.00003141589,0.00006027415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2352323,"threshold_uncertainty_score":0.5026819,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017222169","doi":"10.1186/1758-2946-6-1","title":"Prediction of novel drug indications using network driven biological data prioritization and integration","year":2014,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Prioritization; Data integration; Data science; Data mining; Drug; Risk analysis (engineering); Management science; Pharmacology; Medicine; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03665510091314504,"gpt":0.2588013996024858,"spread":0.2221462986893407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005604444,0.00007810976,0.0001458935,0.00003842056,0.0000491813,0.00002136983,0.0001993897,0.00009467916,0.000001571938],"category_scores_gemma":[0.0001465547,0.00006269159,0.00002872021,0.00007282665,0.0000646066,0.00003585664,0.0001243311,0.0001042374,1.536069e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009787385,"about_ca_system_score_gemma":0.00005404222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.929791e-7,"about_ca_topic_score_gemma":0.000001254861,"domain_scores_codex":[0.999112,0.000008773511,0.0006224072,0.00005317605,0.0001104627,0.00009319173],"domain_scores_gemma":[0.9988058,0.00002444717,0.0007428138,0.0002143884,0.0001606881,0.0000519247],"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":[0.0004667808,0.0007383655,0.02136413,0.000695274,0.0007573625,5.745381e-7,0.004204762,0.03996794,0.7311539,0.00542725,0.05465855,0.1405651],"study_design_scores_gemma":[0.001938243,0.0006507087,0.003172035,0.0002956332,0.0001530504,0.0002073993,0.0006012032,0.9612254,0.01892428,0.0006570945,0.01192663,0.0002483453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4261308,0.000240177,0.5727218,0.0000506713,0.0001749365,0.0001074249,0.00004554656,0.000003054412,0.0005256508],"genre_scores_gemma":[0.9381517,0.0004377534,0.0606862,0.0000694736,0.00037836,4.468382e-7,0.000262338,0.000005113608,0.000008575877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9212574,"threshold_uncertainty_score":0.2556489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2518754389","doi":"10.1186/s13321-016-0156-0","title":"Post-acquisition filtering of salt cluster artefacts for LC-MS based human metabolomic studies","year":2016,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Agriculture and Agri-Food Canada; Lawson Health Research Institute","funders":"Agriculture and Agri-Food Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Metabolomics; Metabolome; Mass spectrometry; Metabolite; Electrospray ionization; Chromatography; Chemistry; Liquid chromatography–mass spectrometry; Computer science; Analytical Chemistry (journal)","retraction":null,"screen_n_in":null,"score":{"opus":0.0186171425508876,"gpt":0.2941809020641183,"spread":0.2755637595132308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004684673,0.0001479621,0.0004065933,0.0001086566,0.00005665367,0.00001135447,0.0001646696,0.00007783532,0.00001356683],"category_scores_gemma":[0.0003449112,0.00009389046,0.0002254905,0.00004676226,0.00007756879,0.00002259158,0.00007347466,0.00004941823,8.778319e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002411419,"about_ca_system_score_gemma":0.00005112538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.818757e-7,"about_ca_topic_score_gemma":0.000001140065,"domain_scores_codex":[0.9988254,0.000008975435,0.0007382474,0.00007460616,0.0001660724,0.0001866502],"domain_scores_gemma":[0.998277,0.00006941272,0.0008109711,0.0001777751,0.0006081294,0.00005668494],"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":[0.0001802366,0.00003496646,0.00006378395,0.0001871642,0.0003197874,3.674203e-7,0.0001358313,0.00001296517,0.9936581,0.00008198254,0.003942986,0.001381852],"study_design_scores_gemma":[0.001679825,0.0006243585,0.000272673,0.00009555582,0.0001135358,0.00001753146,0.0002280112,0.00002788394,0.9845359,0.0002155737,0.0120588,0.0001303525],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867776,0.001192151,0.01059955,0.0005434763,0.0002509626,0.000155681,0.00006679032,0.000003401103,0.0004103695],"genre_scores_gemma":[0.9895954,0.0005560726,0.009050569,0.0003087035,0.0002446343,0.0000065596,0.0000129487,0.00001412339,0.000211041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009122174,"threshold_uncertainty_score":0.3828742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110732896","doi":"10.1186/1758-2946-3-16","title":"Semantic Web integration of Cheminformatics resources with the SADI framework","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canarie; Pfizer","keywords":"Computer science; Cheminformatics; Interoperability; Workflow; Semantic Web; Ontology; SPARQL; Web service; RDF; World Wide Web; Social Semantic Web; Data science; Database; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.100751003651935,"gpt":0.3231345185300068,"spread":0.2223835148780718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005817573,0.0001392601,0.000341986,0.0002880949,0.000115656,0.0002626429,0.001500866,0.00006400691,0.0001677708],"category_scores_gemma":[0.002511197,0.00006494075,0.0001359241,0.0008901011,0.0002154611,0.0008016237,0.000217791,0.0003192269,0.00003617249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002637118,"about_ca_system_score_gemma":0.00008998412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000204671,"about_ca_topic_score_gemma":0.000002719912,"domain_scores_codex":[0.9960254,0.00001641765,0.001724969,0.00008374441,0.001955874,0.0001935954],"domain_scores_gemma":[0.994824,0.000924184,0.002610665,0.0007265409,0.0008188605,0.00009576027],"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":[0.0004012178,0.0003650359,0.003468985,0.0003259924,0.0003661912,0.00001845615,0.2666886,0.0004098333,0.0006009344,0.005627299,0.4298818,0.2918457],"study_design_scores_gemma":[0.00283416,0.001635186,0.006435337,0.002970581,0.0007369293,0.0008269373,0.3403362,0.1186459,0.09374271,0.03236471,0.3982816,0.001189705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7551349,0.0001173669,0.1074883,0.0008147885,0.0008357665,0.0002515582,0.00001320703,0.00002476937,0.1353194],"genre_scores_gemma":[0.9621915,0.00001919049,0.03673821,0.0001769466,0.00008123522,7.806859e-7,0.000001345985,0.000005784472,0.0007850621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.290656,"threshold_uncertainty_score":0.3006319,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1850375728","doi":"10.1186/s13321-015-0092-4","title":"Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Computer science; Cheminformatics; Interpretability; Quantitative structure–activity relationship; Feature selection; Applicability domain; Visual analytics; Data mining; Machine learning; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Property (philosophy); Software; Feature (linguistics); Process (computing); Generality; Domain (mathematical analysis); Visualization; Bioinformatics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0632942398036562,"gpt":0.3859116379978224,"spread":0.3226173981941662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004599899,0.000224034,0.0005149078,0.0004963413,0.00004920826,0.0002575143,0.0008831806,0.0001280088,0.000004114598],"category_scores_gemma":[0.002000207,0.0002015458,0.0002115275,0.0008757816,0.00003704015,0.003166735,0.0001702023,0.000333707,0.000005364156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004581618,"about_ca_system_score_gemma":0.0008286216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000258748,"about_ca_topic_score_gemma":0.000001327642,"domain_scores_codex":[0.997089,0.0000505493,0.001689547,0.0001034287,0.0007138501,0.0003536101],"domain_scores_gemma":[0.996581,0.000822238,0.001006859,0.0002221044,0.001087333,0.0002804465],"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":[0.0006408967,0.001181498,0.002669447,0.001797168,0.0006258414,0.00001828233,0.06090997,0.2252506,0.006005872,0.01793501,0.05007359,0.6328918],"study_design_scores_gemma":[0.00162561,0.0002613504,0.0000751764,0.00008154478,0.00003375506,0.0001573436,0.0009791657,0.9356,0.0485418,0.005268021,0.007144367,0.0002318141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03652942,0.00006597223,0.9609706,0.0002119683,0.0005457301,0.0002118919,0.000002240915,0.00002828872,0.001433895],"genre_scores_gemma":[0.03950497,0.00001261581,0.9599023,0.0003187016,0.0001545222,0.000007725563,0.000004681391,0.00001396336,0.0000804607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7103494,"threshold_uncertainty_score":0.8218801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155459813","doi":"10.1186/1758-2946-3-20","title":"Chemical Entity Semantic Specification: Knowledge representation for efficient semantic cheminformatics and facile data integration","year":2011,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Cheminformatics; Representation (politics); Semantic Web; Semantics (computer science); Knowledge representation and reasoning; Chemical database; Domain (mathematical analysis); Data science; Information retrieval; Artificial intelligence; Chemistry; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08371741914909708,"gpt":0.3216287515449943,"spread":0.2379113323958972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002152344,0.0001898011,0.0003742425,0.0001278505,0.0001270827,0.0002145674,0.0009026948,0.00009828655,0.0001879064],"category_scores_gemma":[0.001484284,0.0001531385,0.00006375415,0.0001939291,0.0001883864,0.001229687,0.0003005939,0.0001811922,0.000051106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006951664,"about_ca_system_score_gemma":0.0001110384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004850567,"about_ca_topic_score_gemma":0.000001057997,"domain_scores_codex":[0.9977262,0.00001829894,0.001352443,0.0001698947,0.0004672389,0.000265946],"domain_scores_gemma":[0.9972175,0.0002183334,0.001347509,0.0005972754,0.000477873,0.0001414658],"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":[0.0002360177,0.0003910358,0.0003973458,0.001692926,0.00004099807,0.000003652591,0.03751549,0.0002749069,0.9374316,0.001196539,0.009706947,0.01111255],"study_design_scores_gemma":[0.0006445894,0.00007780271,0.0003221415,0.0001857474,0.00009137793,0.0002034595,0.001499304,0.1568438,0.8385962,0.0003673696,0.0009419913,0.0002261508],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8880899,0.00008016077,0.1060483,0.00008714356,0.0007837354,0.0003975903,0.00004796436,0.00004116911,0.00442406],"genre_scores_gemma":[0.8973515,0.00003889011,0.1022023,0.00003223688,0.0002020181,0.0000069626,0.00005239133,0.0000131622,0.0001005725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1565689,"threshold_uncertainty_score":0.6244806,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2727000434","doi":"10.1186/s13321-017-0242-y","title":"A posteriori metadata from automated provenance tracking: integration of AiiDA and TCOD","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Horizon 2020 Framework Programme; European Commission; SCIEX; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Metadata; Protocol (science); Interoperability; Interface (matter); Field (mathematics); Process (computing); Proof of concept","retraction":null,"screen_n_in":null,"score":{"opus":0.02286013274966573,"gpt":0.305870177292973,"spread":0.2830100445433072,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167897,0.0001259516,0.0003821461,0.00005771463,0.0001437079,0.0006531468,0.0007962201,0.00006334599,0.0000635664],"category_scores_gemma":[0.001690757,0.00009064309,0.00004628152,0.00003854802,0.000200251,0.003113195,0.0001761439,0.0001393132,0.000006102638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002574134,"about_ca_system_score_gemma":0.00009122652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004012676,"about_ca_topic_score_gemma":0.000002950509,"domain_scores_codex":[0.9984145,0.00001970603,0.0008959926,0.0000836937,0.000434103,0.0001519678],"domain_scores_gemma":[0.9962709,0.00009423121,0.002846464,0.0004291168,0.0002834403,0.00007582425],"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":[0.00004601118,0.00001932392,0.000385643,0.00008700228,0.000008568598,0.000003757535,0.001781427,0.00003786757,0.994606,0.00008976558,0.000264003,0.002670672],"study_design_scores_gemma":[0.0004776548,0.00012346,0.01118066,0.0003565772,0.00004188283,0.0000890115,0.000238165,0.01536502,0.9712143,0.0004012343,0.0003925049,0.0001195266],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996425,0.00005336688,0.001868397,0.0002091281,0.0004733806,0.00007989076,0.00003531123,0.00002458396,0.0008309223],"genre_scores_gemma":[0.94914,0.00002618934,0.05065461,0.00003957437,0.00007548411,8.178129e-7,0.000002879949,0.000006864955,0.00005365441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04878621,"threshold_uncertainty_score":0.629831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146172880","doi":"10.1186/1758-2946-4-5","title":"Blind trials of computer-assisted structure elucidation software","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Molecular spectroscopy and chirality","field":"Chemistry","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); Canadian Institute for Advanced Research","funders":"","keywords":"Software; Computer science; Set (abstract data type); Process (computing); Data mining; Data science; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.03362422348583312,"gpt":0.31109870900898,"spread":0.2774744855231469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008100082,0.0001322779,0.0005464008,0.0000613404,0.00003160321,0.0000266375,0.0002191584,0.0001558903,0.0006025227],"category_scores_gemma":[0.000487567,0.0001015847,0.000261661,0.00009017505,0.00003303358,0.0004005643,0.0000374338,0.0002798185,0.000001896094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005629361,"about_ca_system_score_gemma":0.00007275584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.410146e-7,"about_ca_topic_score_gemma":2.426059e-7,"domain_scores_codex":[0.9977591,0.00001426853,0.00158533,0.00003427176,0.0004260056,0.0001810197],"domain_scores_gemma":[0.9968331,0.0001412464,0.002478983,0.000204879,0.0002153128,0.0001264484],"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":[0.001078434,0.0007127368,0.01021876,0.003698477,0.001088369,0.000008241828,0.009981812,0.000186831,0.875706,0.0002768302,0.0132023,0.08384123],"study_design_scores_gemma":[0.001280528,0.00005067687,0.0004493284,0.0001465799,0.0001307977,0.0001452394,0.0001775969,0.00009549031,0.993686,0.0001185259,0.00360508,0.000114163],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846022,0.0002380788,0.01182714,0.00003437734,0.0002831242,0.00004489105,0.00004772359,0.00001185406,0.00291063],"genre_scores_gemma":[0.9615833,0.00002417623,0.03765893,0.00005538467,0.0005870011,3.840993e-7,0.00003612821,0.000009534878,0.00004519294],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.11798,"threshold_uncertainty_score":0.6597201,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220847490","doi":"10.1186/s13321-022-00596-6","title":"Deep learning-driven prediction of drug mechanism of action from large-scale chemical-genetic interaction profiles","year":2022,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; Cystic Fibrosis Canada","keywords":"Computer science; Mechanism (biology); Scale (ratio); Action (physics); Drug discovery; Artificial intelligence; Machine learning; Data science; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01529976250053821,"gpt":0.2669032819701505,"spread":0.2516035194696122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005868317,0.0001013255,0.0002631477,0.0001911822,0.00006661474,0.00002648922,0.0004890787,0.0000370492,0.00005306969],"category_scores_gemma":[0.0001279623,0.000100663,0.0001490655,0.000288599,0.00002047692,0.0008276978,0.0002907481,0.0004054293,0.000001195454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001572337,"about_ca_system_score_gemma":0.0001121227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000380022,"about_ca_topic_score_gemma":3.165475e-7,"domain_scores_codex":[0.9980139,0.00007040756,0.0009569034,0.00008217533,0.0007580462,0.0001185661],"domain_scores_gemma":[0.9974812,0.0002789953,0.001720968,0.0001710642,0.0002922736,0.00005549136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002122896,0.0006808839,0.001045634,0.000410983,0.0002867892,0.000005706952,0.0455775,0.7097335,0.1858547,0.001676372,0.001052074,0.05346357],"study_design_scores_gemma":[0.0003937333,0.0001134989,0.0004357486,0.00004430801,0.00003082895,0.00006032553,0.002338144,0.717417,0.2757072,0.003058872,0.0003376279,0.00006268409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5121275,0.00002953786,0.4870487,0.00005136783,0.0004318518,0.00006753087,0.00001338361,0.00001224391,0.0002179025],"genre_scores_gemma":[0.8609643,0.00002257915,0.1388749,0.00001927712,0.00007202625,0.000004410352,0.0000161278,0.000006596944,0.00001974033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3488367,"threshold_uncertainty_score":0.4104919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118054110","doi":"10.1186/1758-2946-2-8","title":"Basic primitives for molecular diagram sketching","year":2010,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Quebec Labrador Foundation","funders":"","keywords":"Computer science; Software; Construct (python library); Set (abstract data type); Process (computing); Interface (matter); Theoretical computer science; Programming language; Parallel computing","retraction":null,"screen_n_in":null,"score":{"opus":0.003713436710431373,"gpt":0.2402804689753334,"spread":0.236567032264902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002929372,0.0001038928,0.0001902732,0.00003714988,0.00003540052,0.00003516188,0.0002067911,0.0001135494,0.00001543036],"category_scores_gemma":[0.0008100122,0.00008147214,0.000307308,0.00004774681,0.00003988935,0.00001113457,0.00003906295,0.0001567028,0.000001162273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006177655,"about_ca_system_score_gemma":0.00004976253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.787061e-7,"about_ca_topic_score_gemma":6.623298e-7,"domain_scores_codex":[0.9992135,0.000003118435,0.0004254635,0.00005961542,0.0001491506,0.0001492222],"domain_scores_gemma":[0.9991427,0.00005283442,0.0003576328,0.0001567209,0.0001890198,0.000101091],"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":[0.00002218574,0.00003922498,0.0001419164,0.00003775809,0.00008912064,8.363561e-7,0.00006454118,0.000006855873,0.9779138,0.00008687142,0.001567681,0.02002924],"study_design_scores_gemma":[0.0003223675,0.00006782123,0.00005246008,0.00001684607,0.00006956115,0.00003760621,0.00006926402,0.0002051474,0.9624373,0.0002899153,0.03632347,0.0001081938],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9850408,0.0001024802,0.01228242,0.0002049681,0.00009667068,0.00005799891,0.000006400208,0.000002645941,0.002205551],"genre_scores_gemma":[0.9851271,0.00005593184,0.01412393,0.0002628467,0.0003160922,0.000003134178,0.00001411946,0.00001158105,0.00008530394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03475579,"threshold_uncertainty_score":0.3322337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403833137","doi":"10.1186/s13321-024-00911-3","title":"Towards the prediction of drug solubility in binary solvent mixtures at various temperatures using machine learning","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Structural Genomics Consortium; Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Leslie Dan Faculty of Pharmacy, University of Toronto; Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Canada First Research Excellence Fund; University of Toronto","keywords":"Solubility; Machine learning; Computer science; Solvent; Binary number; Gradient boosting; Hildebrand solubility parameter; Artificial intelligence; Biochemical engineering; Materials science; Chemistry; Mathematics; Organic chemistry; Random forest","retraction":null,"screen_n_in":null,"score":{"opus":0.02363015548913669,"gpt":0.2887526564082504,"spread":0.2651225009191137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001802128,0.0001119952,0.000212106,0.00018873,0.00007581795,0.0001313053,0.000468483,0.00004139772,0.000006177066],"category_scores_gemma":[0.0002436747,0.00007257728,0.0001428114,0.0004088272,0.00005020416,0.0007977117,0.0002900008,0.0005078211,6.785696e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002325078,"about_ca_system_score_gemma":0.0003117709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000164202,"about_ca_topic_score_gemma":0.000002210686,"domain_scores_codex":[0.9983459,0.00006971622,0.0008030002,0.00007656767,0.0005675156,0.0001373331],"domain_scores_gemma":[0.9988397,0.0004446089,0.0003604913,0.0001678881,0.000142755,0.00004459389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001014497,0.0002129993,0.002796482,0.001314332,0.0002235005,0.00009735425,0.05277989,0.8863504,0.03148442,0.002239624,0.002223572,0.020176],"study_design_scores_gemma":[0.0001698997,0.00005418792,0.001252471,0.0002602127,0.00002029644,0.0003426882,0.0001325688,0.9589044,0.03593063,0.002293118,0.0005752585,0.00006430125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9189506,0.002080644,0.07719579,0.0005121582,0.000781315,0.0001045829,0.000007833819,0.0000242078,0.0003428962],"genre_scores_gemma":[0.9620016,0.00007326659,0.03774768,0.00005012747,0.00008259818,8.234315e-7,0.000002517581,0.000005858928,0.00003559805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07255398,"threshold_uncertainty_score":0.2959616,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144342206","doi":"10.1186/s13321-015-0056-8","title":"Atom-Atom-Path similarity and Sphere Exclusion clustering: tools for prioritizing fragment hits","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Discovery Centre","funders":"","keywords":"Fragment (logic); Cluster analysis; Similarity (geometry); Atom (system on chip); Path (computing); Computer science; Data mining; Information retrieval; Combinatorics; Algorithm; Artificial intelligence; Mathematics; Parallel computing","retraction":null,"screen_n_in":null,"score":{"opus":0.06401385121419086,"gpt":0.3221815610132692,"spread":0.2581677097990784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001572759,0.0001438637,0.0002873928,0.00007802418,0.00008050266,0.0003839568,0.0004880848,0.00007069206,0.000001575664],"category_scores_gemma":[0.0004425829,0.0001248288,0.00009528848,0.0001502328,0.00002647826,0.002376235,0.0004664243,0.000191917,0.000001468138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001627236,"about_ca_system_score_gemma":0.0003418629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.919194e-7,"about_ca_topic_score_gemma":5.432602e-7,"domain_scores_codex":[0.9983326,0.0000201051,0.0007379124,0.00009279689,0.0006088712,0.0002076693],"domain_scores_gemma":[0.9979306,0.0005353052,0.0005963655,0.0001979026,0.0004980435,0.0002417817],"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":[0.0002913265,0.0003613319,0.0005139073,0.001660829,0.0002189068,0.00008287924,0.04144129,0.03904526,0.001339653,0.01995102,0.02478084,0.8703128],"study_design_scores_gemma":[0.002452117,0.0003754598,0.0007431518,0.0003889885,0.00004030706,0.0007683836,0.001347649,0.9033938,0.005487935,0.01558323,0.06904548,0.0003734965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1694345,0.0002053181,0.8280441,0.0005482189,0.0004097259,0.0001630366,0.000004071054,0.00001827631,0.001172712],"genre_scores_gemma":[0.136409,0.00003599432,0.8629053,0.0003977967,0.0001925519,0.000003048597,0.000002420663,0.000009617483,0.00004436194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8699393,"threshold_uncertainty_score":0.5090369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128119041","doi":"10.1186/1758-2946-4-9","title":"A chemical specialty semantic network for the Unified Medical Language System","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Unified Medical Language System; Computer science; Ontology; Semantics (computer science); Semantic network; Natural language processing; Information retrieval; Artificial intelligence; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01239012271738021,"gpt":0.2734242568030976,"spread":0.2610341340857174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001153811,0.0001031621,0.0002068221,0.00001577232,0.00005826635,0.00001706377,0.0003467401,0.0002188122,0.00001361978],"category_scores_gemma":[0.0008130344,0.00005936135,0.0001565456,0.00006412881,0.0001119798,0.000006325105,0.00007548393,0.00018584,0.000003600069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002019323,"about_ca_system_score_gemma":0.0001043522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.120146e-7,"about_ca_topic_score_gemma":8.506844e-7,"domain_scores_codex":[0.9988291,0.00001029291,0.0004947226,0.00004079054,0.0003292675,0.0002958456],"domain_scores_gemma":[0.9990647,0.0001703173,0.0003234363,0.0001706808,0.00009057472,0.0001803211],"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":[0.0009924368,0.000380975,0.002500484,0.001761925,0.001394779,0.00002679957,0.006647563,0.00006784026,0.03931373,0.002034464,0.7508441,0.1940349],"study_design_scores_gemma":[0.004053226,0.00053211,0.0008036747,0.0006620518,0.0004974558,0.003062814,0.01459693,0.003536037,0.2330516,0.00006563998,0.7384957,0.0006426967],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8966529,0.0119044,0.0783807,0.002442813,0.003467637,0.0004745387,0.00002418186,0.00004437207,0.00660847],"genre_scores_gemma":[0.987142,0.0001109896,0.007658232,0.0004701998,0.004458813,0.000004915746,0.00001323008,0.00001101434,0.0001305494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1937379,"threshold_uncertainty_score":0.2420686,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399175963","doi":"10.1186/s13321-024-00853-w","title":"Identifying uncertainty in physical–chemical property estimation with IFSQSAR","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; The Scarborough Hospital; ARC Resources (Canada)","funders":"","keywords":"Property (philosophy); Computer science; Estimation; Data mining; Data science; Systems engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.009905848516422483,"gpt":0.2654185823120778,"spread":0.2555127337956553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002276811,0.0001079271,0.00019584,0.00008614906,0.00001797443,0.00005487478,0.0001188411,0.00004907932,0.000003618982],"category_scores_gemma":[0.0000982253,0.00006045415,0.00007708638,0.0001625373,0.00004129579,0.00002365075,0.00004702567,0.0001688962,0.000002767689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003461411,"about_ca_system_score_gemma":0.00008915312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001416933,"about_ca_topic_score_gemma":0.000001243086,"domain_scores_codex":[0.9992524,0.000004656879,0.0003404011,0.00007056499,0.0001943649,0.000137545],"domain_scores_gemma":[0.9996063,0.00001727158,0.0001403112,0.0001009261,0.00009091143,0.00004427765],"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":[0.0002485178,0.0001839471,0.0002574548,0.0008460167,0.0004149787,0.00004365182,0.002887135,0.002173607,0.9367302,0.0005273598,0.007761585,0.04792554],"study_design_scores_gemma":[0.001116491,0.000473382,0.0001482666,0.0004964938,0.0001332657,0.0003922943,0.001055226,0.04568912,0.9241969,0.00115814,0.02477645,0.0003639646],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928328,0.0006996205,0.003549334,0.0001775886,0.0001116137,0.00007791891,0.000003267038,0.000005517031,0.002542277],"genre_scores_gemma":[0.9922578,0.0002201544,0.007107608,0.00004387188,0.0001768537,0.00000285943,0.000009472139,0.000009961012,0.0001714605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04756157,"threshold_uncertainty_score":0.2465249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045213199","doi":"10.1186/s13321-020-00449-0","title":"rMSIcleanup: an open-source tool for matrix-related peak annotation in mass spectrometry imaging and its application to silver-assisted laser desorption/ionization","year":2020,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Natural Sciences and Engineering Research Council of Canada; Universitat Rovira i Virgili; Horizon 2020; Ministerio de Economía y Competitividad","keywords":"Mass spectrometry imaging; Mass spectrometry; Computer science; Annotation; Workflow; Matrix-assisted laser desorption/ionization; Matrix (chemical analysis); Principal component analysis; Desorption; Analyte; MALDI imaging; Chemistry; Analytical Chemistry (journal); Data mining; Artificial intelligence; Chromatography; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.009794563412108884,"gpt":0.2652821827372376,"spread":0.2554876193251288,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003876259,0.0001236042,0.0002247174,0.0001187306,0.00006026409,0.00008587623,0.0002056304,0.00006615155,0.00000488064],"category_scores_gemma":[0.000325135,0.0001182693,0.00004122206,0.0003386916,0.00001251599,0.00007798811,0.00009099448,0.0000942108,0.000001842296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003580354,"about_ca_system_score_gemma":0.00003947175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.380207e-7,"about_ca_topic_score_gemma":0.000001278081,"domain_scores_codex":[0.9989697,0.000012256,0.0006002632,0.0001271646,0.0001405656,0.000150027],"domain_scores_gemma":[0.9990748,0.00002027746,0.0004329512,0.0001027529,0.0002634549,0.0001057798],"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":[0.0001998199,0.0000534432,0.0007849898,0.00008185464,0.0000464606,6.319489e-7,0.0005729125,0.0008786519,0.9900018,0.0001643566,0.0006631733,0.006551889],"study_design_scores_gemma":[0.005331176,0.001345353,0.009863999,0.0000734861,0.0001620338,0.00009546483,0.002779878,0.0588524,0.9035416,0.0005360714,0.01679883,0.0006197509],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9371597,0.000291255,0.06106089,0.0008240024,0.00004601743,0.0004415376,0.00001400979,0.000006440568,0.0001561911],"genre_scores_gemma":[0.9809601,0.0002041318,0.01811442,0.0004282416,0.0001193604,0.00001290787,0.0000800674,0.00001724292,0.00006350342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08646026,"threshold_uncertainty_score":0.4822884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3155267227","doi":"10.1186/s13321-021-00527-x","title":"Twitter integration of chemistry software tools","year":2021,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":9,"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":"Japan Society for the Promotion of Science","keywords":"Cheminformatics; Computer science; Software; Data science; World Wide Web; Social media; Social software; Measure (data warehouse); Chemistry; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1353156810662002,"gpt":0.3682735598607179,"spread":0.2329578787945177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002601646,0.00006606662,0.0002287696,0.00008211505,0.00003267463,0.000294753,0.0005703085,0.00003731961,0.0004322835],"category_scores_gemma":[0.008825139,0.00004499938,0.0001399577,0.0004625133,0.00003988447,0.000630901,0.0001901694,0.0001306237,0.00002511292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002602425,"about_ca_system_score_gemma":0.0001302903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.233529e-7,"about_ca_topic_score_gemma":1.568177e-7,"domain_scores_codex":[0.9972355,0.000009729571,0.001298661,0.00007640617,0.001281922,0.00009771756],"domain_scores_gemma":[0.9966065,0.0005280793,0.001095358,0.0004763603,0.001228685,0.00006506163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002429186,0.0001237569,0.0006588419,0.0001180578,0.00005782251,0.00002757944,0.004552528,0.0004347124,0.02571301,0.00005738631,0.5055724,0.4626596],"study_design_scores_gemma":[0.0005723838,0.00003529802,0.001048021,0.0002483728,0.00004349973,0.0002344096,0.01114487,0.003222381,0.8793874,0.004402228,0.09950671,0.0001544363],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7636255,0.0001199571,0.2028277,0.0007249303,0.001143088,0.0000506201,0.00001916832,0.00001181459,0.03147719],"genre_scores_gemma":[0.9164962,0.0000198773,0.07388017,0.0003814574,0.0002084398,4.26855e-7,0.00001940819,0.000005913086,0.008988081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8536744,"threshold_uncertainty_score":0.9995239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103126992","doi":"10.1186/s13321-015-0064-8","title":"Creation of a free, Internet-accessible database: the Multiple Target Ligand Database","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Jewish General Hospital","funders":"Fundamental Research Funds for the Central Universities","keywords":"Computer science; The Internet; Database; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04316942399164634,"gpt":0.3173300065991756,"spread":0.2741605826075292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001885008,0.0001085857,0.0002215032,0.0001296769,0.00002934548,0.0001373935,0.001601432,0.00003122253,0.000006254535],"category_scores_gemma":[0.001786337,0.00007154154,0.00007831262,0.0003464083,0.00006118948,0.002773872,0.0006105949,0.000206767,0.000004586638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005618516,"about_ca_system_score_gemma":0.0003779065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000107238,"about_ca_topic_score_gemma":0.00000167013,"domain_scores_codex":[0.9981822,0.00003530164,0.0008324826,0.0000652802,0.0007519676,0.0001327264],"domain_scores_gemma":[0.9971744,0.0005780989,0.001026593,0.0005387394,0.0005578909,0.0001242357],"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":[0.0007639077,0.001515096,0.007920303,0.00173306,0.0008355214,0.0001082773,0.0760114,0.1380757,0.01607151,0.05560197,0.6077716,0.09359165],"study_design_scores_gemma":[0.001297151,0.0001101001,0.0002738736,0.0002110598,0.0000268481,0.0001810062,0.000499354,0.7819304,0.1980852,0.004846482,0.0123968,0.0001416829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07583115,0.0002259033,0.9190818,0.0004747779,0.0003991566,0.0000943881,0.00003002152,0.00001159372,0.003851222],"genre_scores_gemma":[0.4096273,0.00002866125,0.5897903,0.0002203449,0.0001474667,0.000002203762,0.0000228473,0.00000758185,0.00015326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6438548,"threshold_uncertainty_score":0.2975885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2019688884","doi":"10.1186/1758-2946-4-24","title":"mol2chemfig, a tool for rendering chemical structures from molfile or SMILES format to LATE X code","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Python (programming language); Rendering (computer graphics); Documentation; Programming language; Source code; Software; Graphics; Computer graphics (images); Coding (social sciences)","retraction":null,"screen_n_in":null,"score":{"opus":0.04167029244958156,"gpt":0.3269340572626618,"spread":0.2852637648130802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005770423,0.0001848356,0.000343544,0.0001239772,0.00005769979,0.0002251055,0.0008581299,0.00008137089,0.00001707225],"category_scores_gemma":[0.0006963305,0.0001383745,0.0001678664,0.0002083889,0.00001959466,0.002390468,0.0002954999,0.0001934417,0.000005640381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001465155,"about_ca_system_score_gemma":0.0001418938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.868469e-7,"about_ca_topic_score_gemma":2.593084e-7,"domain_scores_codex":[0.9981075,0.0000104954,0.0009085161,0.00008299094,0.0005234621,0.0003670569],"domain_scores_gemma":[0.9979316,0.0007617534,0.0005477842,0.0002782429,0.0002335887,0.0002470229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001565392,0.0006120249,0.0004876366,0.001450701,0.001096531,0.00003433437,0.07859544,0.0744599,0.09672961,0.03684669,0.1130932,0.5950285],"study_design_scores_gemma":[0.001782231,0.0001699089,0.0005306581,0.0002268627,0.00007762223,0.000441248,0.0004976294,0.2437669,0.6725637,0.02790027,0.05136374,0.0006791663],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3398294,0.00009245877,0.658865,0.0002719362,0.0004144074,0.0001435581,0.00004040511,0.00002607585,0.0003167997],"genre_scores_gemma":[0.2432732,0.000009622569,0.7557175,0.0005301877,0.0003752227,0.000008302822,0.000007840998,0.00001261115,0.00006553759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5943494,"threshold_uncertainty_score":0.5642747,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407140906","doi":"10.1186/s13321-025-00962-0","title":"Improving drug repositioning with negative data labeling using large language models","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Drug repositioning; Drug; Data mining; Natural language processing; Data science; Medicine; Pharmacology","retraction":null,"screen_n_in":null,"score":{"opus":0.02494095244085814,"gpt":0.320357368948671,"spread":0.2954164165078128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001325864,0.0001113462,0.0002131302,0.0001770772,0.0001313784,0.0002868896,0.001017457,0.00002851802,0.00000137183],"category_scores_gemma":[0.0002783719,0.00009025695,0.00004226475,0.0004104422,0.00002107299,0.003264909,0.0006146576,0.0002642249,4.654704e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001113233,"about_ca_system_score_gemma":0.0004834307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034619,"about_ca_topic_score_gemma":0.000001736721,"domain_scores_codex":[0.9986566,0.00002600927,0.0006217649,0.0001056989,0.0004090748,0.000180907],"domain_scores_gemma":[0.998018,0.0003905023,0.0007333148,0.0004699116,0.0003333088,0.00005496788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005815889,0.0001233996,0.00007680999,0.0004502568,0.0002822975,0.00009173303,0.02706813,0.9137406,0.001998638,0.01646819,0.001185493,0.03845625],"study_design_scores_gemma":[0.0004661363,0.00001316952,0.000007604454,0.0003647425,0.00003700094,0.0001195743,0.001457985,0.9843794,0.01043801,0.002583855,0.00003498066,0.00009750843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0707828,0.0001438429,0.9260804,0.0001290106,0.0001370872,0.00005878156,0.000006123865,0.00001917313,0.002642787],"genre_scores_gemma":[0.2575648,0.000002984204,0.7420886,0.0002306112,0.00004509957,3.624439e-7,0.00000385222,0.000004781439,0.00005902261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.186782,"threshold_uncertainty_score":0.3680572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401589835","doi":"10.1186/s13321-024-00892-3","title":"Metis: a python-based user interface to collect expert feedback for generative chemistry models","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Horizon 2020; Engineering and Physical Sciences Research Council; Vetenskapsrådet; UK Research and Innovation; Knut och Alice Wallenbergs Stiftelse; Finnish Center for Artificial Intelligence; European Commission; Chalmers Tekniska Högskola","keywords":"Computer science; Python (programming language); Graphical user interface; Human–computer interaction; Interface (matter); User interface; Generative grammar; Generative model; Human-in-the-loop; Software engineering; Data science; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03071467042314193,"gpt":0.3335950207731636,"spread":0.3028803503500216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007993894,0.0001860008,0.0003068756,0.0001536069,0.00005706991,0.0004810021,0.0007764824,0.00006743371,0.00001426713],"category_scores_gemma":[0.0002607592,0.0001549807,0.0002276442,0.0005051119,0.00002331769,0.001231416,0.0001430735,0.000201754,0.000007525407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002585515,"about_ca_system_score_gemma":0.0007332294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.102147e-7,"about_ca_topic_score_gemma":1.678822e-7,"domain_scores_codex":[0.9983682,0.00001667523,0.0007528566,0.000137026,0.0004988766,0.0002263683],"domain_scores_gemma":[0.9980884,0.0007853872,0.0002423221,0.0002410497,0.0004645965,0.0001782726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009545411,0.0000813775,4.313432e-7,0.0004903393,0.0002031833,0.00001546136,0.01325772,0.8366096,0.01196865,0.00244116,0.1097357,0.02510095],"study_design_scores_gemma":[0.0002788735,0.00007558076,5.076711e-7,0.0002210396,0.00001245746,0.0000607242,0.0001461122,0.7154567,0.2685973,0.002778125,0.01223389,0.0001386411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006965022,0.0004476238,0.9884219,0.001912694,0.000462383,0.0001985623,0.00001318697,0.00004312237,0.001535472],"genre_scores_gemma":[0.07819162,0.00001432424,0.9198524,0.0009854689,0.0002552878,0.0000277167,0.000002615178,0.00002128581,0.0006493187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2566287,"threshold_uncertainty_score":0.6319929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145210171","doi":"10.1186/1758-2946-6-s1-o9","title":"Development of cannabinoid receptor (CB 2 R) ligands for application in PET studies - where to attach the radiolabel?","year":2014,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Pharmacological Receptor Mechanisms and Effects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Cannabinoid receptor; Positron emission tomography; Receptor; Chemistry; Cannabinoid; High resolution; Ligand (biochemistry); Docking (animal); Carbazole; Stereochemistry; Biochemistry; Nuclear medicine; Medicine; Organic chemistry; Antagonist","retraction":null,"screen_n_in":null,"score":{"opus":0.01606237169248702,"gpt":0.3144542415294359,"spread":0.2983918698369489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008502654,0.00009163409,0.0002056433,0.0000324654,0.00004002076,0.000007400591,0.0002067782,0.00004968926,0.000002419999],"category_scores_gemma":[0.0003119556,0.00005672206,0.00006155201,0.0000727338,0.00002045476,0.000007330154,0.00005688642,0.00007678941,0.000001409316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003791296,"about_ca_system_score_gemma":0.00007123713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.047982e-7,"about_ca_topic_score_gemma":0.000004672109,"domain_scores_codex":[0.9991651,0.000005575117,0.0005054736,0.00005364908,0.0001341165,0.0001360652],"domain_scores_gemma":[0.9992401,0.00004813447,0.0003371155,0.00009474468,0.0002164155,0.00006346334],"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":[0.0001154744,0.00003895743,0.00005182425,0.0001800689,0.00005936333,8.009091e-8,0.001093994,0.0001138181,0.9638678,0.00003512959,0.01378555,0.02065796],"study_design_scores_gemma":[0.0005161511,0.0002810883,0.00004959194,0.00004747047,0.00001441905,0.000006890447,0.0004977424,0.0002169561,0.8753508,0.00003848285,0.1229085,0.00007190528],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924108,0.0002965752,0.006502425,0.0003127562,0.0001328941,0.0002446841,0.000003110278,0.000001478015,0.00009521824],"genre_scores_gemma":[0.9783071,0.000242374,0.02078669,0.000347523,0.0001722237,0.0000478648,0.00000870499,0.000007822249,0.000079681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1091229,"threshold_uncertainty_score":0.2313059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408693799","doi":"10.1186/s13321-025-00979-5","title":"An interpretable deep geometric learning model to predict the effects of mutations on protein–protein interactions using large-scale protein language model","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Children’s Health Research Institute; Lawson Health Research Institute; University of Manitoba; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Scale (ratio); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.004592795866963382,"gpt":0.2806849373223361,"spread":0.2760921414553727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005691525,0.0001895864,0.0002705109,0.0003523517,0.000154773,0.0000631959,0.0004382721,0.0001191263,0.000005052233],"category_scores_gemma":[0.001374512,0.0001436012,0.0001457237,0.0004054539,0.00004316569,0.00006540283,0.0001440565,0.0005619621,0.000002009928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006539605,"about_ca_system_score_gemma":0.0001922876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003918121,"about_ca_topic_score_gemma":0.000003511548,"domain_scores_codex":[0.9984952,0.00003715788,0.0008037224,0.00009088867,0.0003244444,0.0002485732],"domain_scores_gemma":[0.9984716,0.00004912352,0.0007020334,0.0003655113,0.000311029,0.0001007634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009980873,0.0001256433,0.00006017326,0.0004717925,0.00008713307,6.22236e-7,0.004055362,0.5207611,0.4722017,0.00004938801,0.0001081046,0.001979169],"study_design_scores_gemma":[0.0003563969,0.0003187895,0.00001073802,0.0004149175,0.00004478027,0.000009449468,0.0008511692,0.6234721,0.37425,0.00005640056,0.0001238337,0.00009138699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.605496,0.0000392395,0.3925684,0.00003938149,0.00003581811,0.0004234482,0.000006701992,0.000007678932,0.00138322],"genre_scores_gemma":[0.9419887,0.000003115225,0.05682559,0.0001534932,0.00004616778,0.0000299861,0.00001954011,0.0000179821,0.0009154473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3364926,"threshold_uncertainty_score":0.5855888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414507809","doi":"10.1186/s13321-025-01084-3","title":"Cache: Utilizing ultra-large library screening in Rosetta to identify novel binders of the WD-repeat domain of Leucine-Rich Repeat Kinase 2","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institutes of Health; Alexander von Humboldt-Stiftung; Enamine; Max Kade Foundation; University of Toronto; Bundesministerium für Bildung und Forschung; German Network for Bioinformatics Infrastructure; Deutscher Akademischer Austauschdienst; Structural Genomics Consortium; Vanderbilt University; Deutsche Forschungsgemeinschaft; Universität Leipzig; Michael J. Fox Foundation for Parkinson's Research","keywords":"Enamine; Virtual screening; Benchmark (surveying); Drug discovery; Domain (mathematical analysis); Docking (animal); Chemical space","retraction":null,"screen_n_in":null,"score":{"opus":0.01974529490835166,"gpt":0.3157505918754207,"spread":0.2960052969670691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001719257,0.0001680177,0.0004267352,0.000524277,0.00006020793,0.0001021633,0.001477193,0.00007792552,0.000004731824],"category_scores_gemma":[0.0006968392,0.0001306683,0.0002148605,0.001646409,0.00005280347,0.001662427,0.0005423356,0.0003800694,5.552963e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006843111,"about_ca_system_score_gemma":0.0004193686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005178974,"about_ca_topic_score_gemma":0.000001797864,"domain_scores_codex":[0.9972585,0.00005385501,0.001581175,0.0001218837,0.0007269148,0.0002576076],"domain_scores_gemma":[0.9975082,0.0006586942,0.001030633,0.0005105155,0.000205381,0.00008658496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000641059,0.001869233,0.06489809,0.004404094,0.0009895994,0.00008233999,0.07946678,0.4458061,0.2341349,0.05992981,0.02794545,0.07983257],"study_design_scores_gemma":[0.003637361,0.0001344725,0.06345556,0.003283509,0.00007903428,0.0001724981,0.005983947,0.08704156,0.8274775,0.006575278,0.001701884,0.000457371],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5884187,0.0001281403,0.405914,0.001142676,0.0003186874,0.0001605016,0.00001213087,0.00001100984,0.003894232],"genre_scores_gemma":[0.812109,0.00001129613,0.1872553,0.0005016773,0.00002725274,0.000001488015,0.000001853701,0.000008415755,0.0000836903],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5933427,"threshold_uncertainty_score":0.5328497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2905553692","doi":"10.1186/s13321-018-0319-2","title":"SIA: a scalable interoperable annotation server for biomedical named entities","year":2018,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Bundesministerium für Wirtschaft und Energie; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Annotation; Interoperability; Workflow; Scalability; Server; Information extraction; Named-entity recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.01346299653045058,"gpt":0.2791543102239871,"spread":0.2656913136935365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003936667,0.00008978418,0.0001684593,0.0000561098,0.00005884458,0.00003452629,0.0001979811,0.000154659,0.00003277705],"category_scores_gemma":[0.0005288591,0.00006593343,0.00009900281,0.00006928802,0.0002355812,0.00001477646,0.00005086287,0.00008740738,0.000007058787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001665114,"about_ca_system_score_gemma":0.0001052699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.912826e-7,"about_ca_topic_score_gemma":0.000001492396,"domain_scores_codex":[0.9991143,0.000006206018,0.0004571986,0.00005713909,0.0001881754,0.0001769698],"domain_scores_gemma":[0.9991532,0.00002761768,0.0002682646,0.0001142829,0.0003467437,0.00008988581],"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":[0.0008893787,0.0003461481,0.0006160965,0.000691291,0.0005325563,0.000006603731,0.004277355,0.000007814628,0.2216297,0.000171791,0.6358796,0.1349517],"study_design_scores_gemma":[0.001507084,0.002009792,0.0000849683,0.0001315522,0.00004800162,0.0001455245,0.001708018,0.0007840138,0.4001986,0.0002795324,0.5929443,0.0001586566],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9715034,0.0003697929,0.02378841,0.000614025,0.0007697864,0.000109324,0.00001506616,0.00001137346,0.002818795],"genre_scores_gemma":[0.9688134,0.0001010798,0.02770338,0.0005445377,0.000977862,0.000005521723,0.0000430307,0.00001224111,0.001798982],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1785689,"threshold_uncertainty_score":0.2688687,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1722424871","doi":"10.1186/1758-2946-5-s1-p40","title":"A 3D-QSAR model for cannabinoid receptor (CB2) ligands derived from aligned pharmacophors","year":2013,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Pharmacological Receptor Mechanisms and Effects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Pharmacophore; Cannabinoid receptor; Cannabinoid receptor type 2; Positron emission tomography; Radioligand; Neuroscience; Drug discovery; Cannabinoid; Computational biology; Quantitative structure–activity relationship; Receptor; Chemistry; Computer science; Biology; Biochemistry; Stereochemistry; Agonist","retraction":null,"screen_n_in":null,"score":{"opus":0.01240622678339249,"gpt":0.2623695383210627,"spread":0.2499633115376703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000241472,0.0002078381,0.0003075627,0.00004373534,0.00006520088,0.00004727714,0.0003216925,0.0001953742,0.000170312],"category_scores_gemma":[0.0001873792,0.0001612867,0.0002258747,0.00005578238,0.0000395959,0.00003662954,0.00007870595,0.0001183156,0.0000187652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004093539,"about_ca_system_score_gemma":0.0001450803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004237748,"about_ca_topic_score_gemma":4.574873e-7,"domain_scores_codex":[0.9987558,0.000007635823,0.0006089867,0.0001088575,0.0002096263,0.0003091668],"domain_scores_gemma":[0.9986709,0.00003827184,0.0005053036,0.0001390384,0.0003692276,0.0002772082],"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":[0.0001513061,0.00006921427,0.00000651957,0.00004875426,0.0001016695,5.214517e-7,0.0003031778,0.0004495943,0.9341132,0.000002224966,0.0599874,0.004766426],"study_design_scores_gemma":[0.001608517,0.0003693178,0.000007404141,0.00002377957,0.00007251548,0.000008629779,0.0001262832,0.04750874,0.9431547,0.0002188323,0.006700659,0.0002006497],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9790602,0.0002331859,0.01937299,0.000213308,0.0004152525,0.0003410099,0.0000511102,0.00000810835,0.0003048457],"genre_scores_gemma":[0.9706963,0.0003387424,0.0265867,0.00136263,0.0005189852,0.00005136668,0.00007566138,0.00002442274,0.0003452356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05328674,"threshold_uncertainty_score":0.6577083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415517900","doi":"10.1186/s13321-025-01104-2","title":"VNFlow: integration of variational autoencoders and normalizing flows for novel molecular design","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"National Research Council Canada; Defence Research and Development Canada","keywords":"Generative grammar; Key (lock); Inverse; Range (aeronautics); Sampling (signal processing); Generative model; Inverse problem; Chemical space","retraction":null,"screen_n_in":null,"score":{"opus":0.0154423853595157,"gpt":0.2801444683022938,"spread":0.2647020829427781,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001894864,0.00009405724,0.0002331777,0.0001423177,0.00006425909,0.00009000773,0.0002519023,0.00005584731,0.00002887346],"category_scores_gemma":[0.001282755,0.00007590708,0.00005188013,0.000127932,0.00005961798,0.0005241969,0.00004781344,0.00008512984,8.918957e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004144602,"about_ca_system_score_gemma":0.0001990902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003033836,"about_ca_topic_score_gemma":2.95518e-7,"domain_scores_codex":[0.9987095,0.00001519872,0.0007846018,0.0000589667,0.0003003756,0.0001313577],"domain_scores_gemma":[0.9984316,0.0003035891,0.0007477268,0.0001002691,0.0003755798,0.00004122661],"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":[0.0000523574,0.0000204866,0.00001541515,0.0001765892,0.00000963911,2.934797e-7,0.0008842716,0.05089595,0.9441741,0.002856659,0.0003207279,0.0005935193],"study_design_scores_gemma":[0.0004519081,0.00007391313,0.00009418636,0.000156755,0.00003279199,0.00002315474,0.0001508222,0.4154783,0.5816693,0.00157962,0.0002258421,0.00006332162],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.125631,0.00003284385,0.87323,0.0001870204,0.0003225364,0.0001207057,0.000006824235,0.000007024952,0.0004619859],"genre_scores_gemma":[0.2387244,0.000007175257,0.761066,0.0001328413,0.00002878172,0.000003537681,0.000001719955,0.000004199567,0.00003138454],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3645824,"threshold_uncertainty_score":0.3095401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413807406","doi":"10.1186/s13321-025-01073-6","title":"FusionCLM: enhanced molecular property prediction via knowledge fusion of chemical language models","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Children’s Health Research Institute; Western University; Lawson Health Research Institute; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Property (philosophy); Artificial intelligence; Ensemble learning; Inference; Machine learning; Representation (politics); Feature (linguistics); Feature learning; Deep learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.009688278155474715,"gpt":0.2810880372370465,"spread":0.2713997590815717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006200328,0.0001189306,0.0002758824,0.0002069362,0.00002684755,0.00003793825,0.0006403869,0.0000796187,0.000004971604],"category_scores_gemma":[0.0001809544,0.00008283663,0.0001450479,0.0004674325,0.00003829422,0.0008877436,0.0003202023,0.0002128971,0.000001991616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009932482,"about_ca_system_score_gemma":0.0003779311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001049926,"about_ca_topic_score_gemma":7.460952e-8,"domain_scores_codex":[0.9984515,0.00002654486,0.0008713493,0.00008244756,0.0004331051,0.0001350842],"domain_scores_gemma":[0.9984957,0.0001560565,0.0005071478,0.0002621867,0.0005085022,0.00007042393],"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":[0.00005956923,0.0002687706,0.000004415237,0.000456526,0.00008462689,0.000006249261,0.00931282,0.02470787,0.7235529,0.005646149,0.001579843,0.2343202],"study_design_scores_gemma":[0.0003161971,0.00003275232,0.000008271265,0.0001652397,0.00001509261,0.00002325026,0.00007259229,0.4585054,0.5348874,0.005825244,0.00009654317,0.00005201657],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.165051,0.0001842724,0.8198065,0.0001354183,0.0002487816,0.00009171663,0.000001903629,0.00001751657,0.01446282],"genre_scores_gemma":[0.8475435,0.00001993267,0.1521616,0.000100149,0.00003965473,0.000002197278,0.000002727241,0.000004718666,0.0001255717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6824924,"threshold_uncertainty_score":0.337798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412435986","doi":"10.1186/s13321-025-01038-9","title":"SuperMetal: a generative AI framework for rapid and precise metal ion location prediction in proteins","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Vanderbilt University","keywords":"Metal ions in aqueous solution; Generative grammar; Computer science; Ion; Generative model; Metal; Zinc; Chemistry; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.009415692670339681,"gpt":0.2635056148016386,"spread":0.2540899221312989,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004140669,0.00009633007,0.0001709033,0.00009548185,0.00003866173,0.0000300175,0.00008884547,0.0001649805,0.000005761035],"category_scores_gemma":[0.0004845577,0.00008069324,0.00006574273,0.0000983604,0.00002595897,0.00002869185,0.00002736368,0.000105798,3.219108e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002118356,"about_ca_system_score_gemma":0.0001138308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.324115e-7,"about_ca_topic_score_gemma":9.486013e-7,"domain_scores_codex":[0.9992468,0.00001473776,0.0004583726,0.00006774037,0.0001072558,0.0001051004],"domain_scores_gemma":[0.9993932,0.00003221034,0.0002201539,0.000106966,0.0002104468,0.00003703773],"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":[0.0004048303,0.00009238475,0.0001509238,0.0003344503,0.0001467607,6.224536e-7,0.0007016133,0.0001482266,0.9538426,0.001307923,0.001306436,0.04156324],"study_design_scores_gemma":[0.0005774611,0.0003347713,0.00008667547,0.0001907791,0.00004437766,0.00001787373,0.0002337493,0.0008313829,0.9882433,0.004581426,0.004785417,0.00007278781],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4846271,0.001276432,0.5120053,0.0005187313,0.000278554,0.000711922,0.00001489789,0.000004319671,0.0005627504],"genre_scores_gemma":[0.9343913,0.0004083512,0.06428118,0.0003127468,0.0002230114,0.00006807685,0.00002278387,0.00001015454,0.0002823503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4497642,"threshold_uncertainty_score":0.3290575,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411371888","doi":"10.1186/s13321-025-00958-w","title":"Crossover operators for molecular graphs with an application to virtual drug screening","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institutes of Health; German Network for Bioinformatics Infrastructure; Novo Nordisk Fonden; Universität Leipzig; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; Max Kade Foundation; Alexander von Humboldt-Stiftung","keywords":"Crossover; Computer science; Theoretical computer science; Context (archaeology); Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.007400817636468401,"gpt":0.2996973154753661,"spread":0.2922964978388977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000673933,0.0001090382,0.0001820341,0.0002234148,0.00007981957,0.0002466245,0.0006994518,0.00002983075,6.544059e-7],"category_scores_gemma":[0.0001077757,0.00008869436,0.00007527508,0.0005300308,0.0000221768,0.001296815,0.0001025184,0.000115132,9.372076e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000048895,"about_ca_system_score_gemma":0.0002282077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001011908,"about_ca_topic_score_gemma":6.024151e-7,"domain_scores_codex":[0.9989015,0.00001192323,0.0004868393,0.00009010076,0.0003622721,0.0001473231],"domain_scores_gemma":[0.998684,0.0001840849,0.0002789266,0.0002494256,0.000489633,0.0001138954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002885695,0.0001340157,0.0001463138,0.0001220253,0.0001643064,0.000005126884,0.005099574,0.5594928,0.002940299,0.2092428,0.003322728,0.2190415],"study_design_scores_gemma":[0.00176195,0.0004484755,0.0004072577,0.0001954504,0.00004909663,0.00006049923,0.0006555475,0.837464,0.133735,0.01652527,0.008372128,0.0003252962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1533112,0.00001357126,0.8455198,0.0004077541,0.00008370794,0.0001725782,0.000002257916,0.00001379108,0.0004754133],"genre_scores_gemma":[0.3522431,9.472129e-7,0.6465817,0.001088557,0.00002300566,0.00001028781,0.000002297691,0.000005357953,0.00004478247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2779713,"threshold_uncertainty_score":0.3616851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W174610764","doi":"10.1186/1758-2946-4-s1-p3","title":"Targeting protein-protein interactions using methods of cheminformatics","year":2012,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":0,"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":"","keywords":"Cheminformatics; Computer science; Computational biology; Data science; Data mining; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.03652210535660062,"gpt":0.3495431929085641,"spread":0.3130210875519635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001413815,0.0001665535,0.000525178,0.0001830211,0.00005480697,0.00002013041,0.0001421003,0.0001052327,0.0001632054],"category_scores_gemma":[0.001479771,0.0001151319,0.0002120575,0.0002437984,0.00006031832,0.0009516655,0.00006674555,0.0004867888,0.000005808703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140949,"about_ca_system_score_gemma":0.000119395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002484321,"about_ca_topic_score_gemma":2.602203e-8,"domain_scores_codex":[0.9978465,0.00001162697,0.001486152,0.00003689276,0.0003372766,0.0002815072],"domain_scores_gemma":[0.9973243,0.00007694269,0.001647459,0.0001850733,0.0005797931,0.0001864659],"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":[0.00007895549,0.0001095865,0.00005599273,0.001076607,0.0001241592,9.440203e-7,0.00227173,0.000006179161,0.9812602,0.00002509789,0.0009233059,0.01406728],"study_design_scores_gemma":[0.0003920338,0.0000719923,0.00002345117,0.0008514335,0.0001954753,0.0004677746,0.001153677,0.0008739614,0.9864313,0.0000248242,0.009392053,0.0001220191],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877315,0.0005421694,0.005838119,0.0002967271,0.0003353408,0.0004121454,0.0000063917,0.00001385544,0.00482374],"genre_scores_gemma":[0.6726769,0.00001702583,0.3266177,0.00007221862,0.0003745212,2.827871e-7,0.000002781695,0.0000111821,0.0002273792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3207796,"threshold_uncertainty_score":0.4694943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2083474203","doi":"10.1186/1758-2946-6-s1-p43","title":"Exploiting solvent effects in drug design and optimization","year":2014,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vertex Pharmaceuticals (Canada)","funders":"","keywords":"Ligand (biochemistry); Solvent; Computer science; Molecule; Computational chemistry; Binding energy; Chemistry; Computational science; Physics; Atomic physics; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01266885748002854,"gpt":0.2551218885689458,"spread":0.2424530310889172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001684086,0.00007035473,0.0001548097,0.000142587,0.00002592753,0.0001024985,0.0002461341,0.00002171012,6.873886e-7],"category_scores_gemma":[0.0004794027,0.00006134916,0.00003081973,0.0001623272,0.00001308944,0.001114032,0.00008673099,0.0001194647,7.925939e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004343869,"about_ca_system_score_gemma":0.0000539635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.926687e-7,"about_ca_topic_score_gemma":5.678014e-8,"domain_scores_codex":[0.9990827,0.00005149512,0.0004576934,0.00004417203,0.0002583745,0.0001055215],"domain_scores_gemma":[0.99837,0.001012303,0.000376234,0.00008993453,0.00009223341,0.00005933264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004223418,0.00001670332,0.00002914827,0.00007186444,0.000005034934,0.000002569463,0.002396401,0.9608854,0.0000657665,0.002564107,0.0001567555,0.03380201],"study_design_scores_gemma":[0.0003957102,0.00003924058,0.0001089809,0.0001308173,0.000003933074,0.00006364938,0.00005383588,0.9865924,0.006992491,0.005480141,0.00007334955,0.00006550598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02226921,0.00003881371,0.9768689,0.0001410064,0.0001240496,0.00006104408,3.66175e-8,0.000007642579,0.0004893469],"genre_scores_gemma":[0.1968175,0.00001371069,0.8030035,0.0001216411,0.00003463614,0.000001043501,1.843148e-7,0.000002958995,0.000004818729],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1745483,"threshold_uncertainty_score":0.2501746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169151607","doi":"10.1186/1758-2946-2-s1-p35","title":"Prediction of highly-connected 'hub'-proteins in protein interaction networks using QSAR","year":2010,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"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":"","keywords":"Quantitative structure–activity relationship; Computer science; Interpretability; Cheminformatics; Computational biology; Machine learning; Proteome; Artificial intelligence; Drug discovery; Virtual screening; Data mining; Chemistry; Biology; Biochemistry; Computational chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02758602513347887,"gpt":0.2815810124379254,"spread":0.2539949873044465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089641,0.0001076071,0.0002399751,0.0003045858,0.0000296896,0.0000696683,0.0004449558,0.00009697189,0.000007034063],"category_scores_gemma":[0.0004413911,0.00009678975,0.00008922807,0.0004900229,0.00003261099,0.001955895,0.0001060585,0.0005770939,7.790111e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009055862,"about_ca_system_score_gemma":0.000183701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000676151,"about_ca_topic_score_gemma":0.00000281137,"domain_scores_codex":[0.9982856,0.00003155625,0.001055465,0.00006643224,0.00041184,0.0001491087],"domain_scores_gemma":[0.9980356,0.0001990294,0.001127278,0.0002085454,0.0003619396,0.00006761473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000154551,0.0004227823,0.0009020228,0.0003426968,0.0001079063,0.00002051311,0.005260295,0.6023017,0.3143534,0.008587497,0.0002687178,0.06727796],"study_design_scores_gemma":[0.0004529786,0.00007696345,0.001263125,0.0001990604,0.000007919688,0.0001365949,0.00007508107,0.9056948,0.09016311,0.001699578,0.0001550442,0.00007574838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5705808,0.000008312507,0.4285649,0.0000578498,0.0003966779,0.0001039006,0.000001082304,0.000008744252,0.000277762],"genre_scores_gemma":[0.776325,0.00000257973,0.2235163,0.00002072917,0.0001228607,0.0000015346,0.000001104361,0.000004742722,0.000005182541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3033932,"threshold_uncertainty_score":0.3946972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}