{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":26,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":26,"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":"92f54b72ab7b","filters":{"venue":"Molecular Informatics"}},"results":[{"id":"W3009970748","doi":"10.1002/minf.202000028","title":"Rapid Identification of Potential Inhibitors of SARS‐CoV‐2 Main Protease by Deep Docking of 1.3 Billion Compounds","year":2020,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":518,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute on Deafness and Other Communication Disorders; Canadian Institutes of Health Research","keywords":"Docking (animal); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Virtual screening; Coronavirus disease 2019 (COVID-19); Drug discovery; Protease; Coronavirus; Computational biology; Drug development; 2019-20 coronavirus outbreak; Drug; Computer science; Virology; Infectious disease (medical specialty); Medicine; Chemistry; Outbreak; Biology; Bioinformatics; Pharmacology; Disease; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.01770774515941695,"gpt":0.2675397446277249,"spread":0.2498319994683079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000548538,0.000127321,0.000256075,0.0001578871,0.00003175701,0.00004750022,0.0005906628,0.00005630055,0.000001552178],"category_scores_gemma":[0.0001810599,0.000130918,0.000128304,0.0006829659,0.00008296314,0.0005344343,0.0002802553,0.00009846952,0.000002931578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002646148,"about_ca_system_score_gemma":0.00009912228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009069945,"about_ca_topic_score_gemma":1.547731e-7,"domain_scores_codex":[0.9977773,0.0001513383,0.001159707,0.0001228827,0.0006503648,0.0001383451],"domain_scores_gemma":[0.9984233,0.00006343013,0.0008915254,0.0003425742,0.000224822,0.00005438801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000274981,0.0001161654,0.00004649526,0.0007267531,0.00006011453,0.000003516054,0.004676588,0.1225891,0.8478622,0.00595331,0.0004129103,0.01752541],"study_design_scores_gemma":[0.000209265,0.00005985113,0.00007171182,0.00002992168,0.000009883341,0.000002977155,0.00007806553,0.4812697,0.5172444,0.0008678485,0.00008169526,0.00007475061],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3354263,0.00005894709,0.6639325,0.0001617696,0.00006984203,0.0002283043,0.0000162642,0.00001853764,0.00008758295],"genre_scores_gemma":[0.9111981,0.000005463473,0.08859154,0.0001519416,0.000009323682,0.000005830558,0.000029348,0.00000775156,6.825388e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5757719,"threshold_uncertainty_score":0.533868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061937956","doi":"10.1002/minf.201200141","title":"Chemically Advanced Template Search (CATS) for Scaffold‐Hopping and Prospective Target Prediction for ‘Orphan’ Molecules","year":2013,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Ministry of Earth Sciences; Ministry of Education, India; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Drug discovery; Scaffold; Computational biology; Nanotechnology; Chemistry; Computer science; Combinatorial chemistry; Materials science; Medicine; Biology; Biomedical engineering; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01078410717972747,"gpt":0.2691825093482484,"spread":0.2583984021685209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004063243,0.000184237,0.0001999939,0.0001329196,0.0001623096,0.0003112101,0.0003997184,0.00007496328,0.000002551889],"category_scores_gemma":[0.0002059014,0.0001836939,0.00009048478,0.0002331272,0.0000544075,0.001205322,0.0002460473,0.00009101204,0.000008719035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007830945,"about_ca_system_score_gemma":0.0001036624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003065509,"about_ca_topic_score_gemma":1.860129e-7,"domain_scores_codex":[0.99862,0.00003328727,0.0004464249,0.0002321652,0.0003137506,0.0003543403],"domain_scores_gemma":[0.9987488,0.0002577319,0.000138078,0.0002996699,0.0004370732,0.0001186493],"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":[0.0001707621,0.0002865423,0.0005846291,0.002051648,0.0004806041,0.000005242537,0.01290384,0.414563,0.1499529,0.2063424,0.002202678,0.2104559],"study_design_scores_gemma":[0.0008399282,0.0001775271,0.0005896761,0.00004047711,0.000009939086,0.0000131087,0.0001215945,0.9057102,0.05572153,0.0360531,0.0005191581,0.0002037939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1464882,0.00005648746,0.8508934,0.0002396121,0.0001019646,0.001725909,0.00003137747,0.0001030383,0.0003599464],"genre_scores_gemma":[0.1819297,0.000003980942,0.8170596,0.0003626209,0.00002354905,0.0005337793,0.000044729,0.00001705442,0.00002505292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4911472,"threshold_uncertainty_score":0.7490819,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206247747","doi":"10.1002/minf.202100264","title":"An AI‐based Prediction Model for Drug‐drug Interactions in Osteoporosis and Paget's Diseases from SMILES","year":2022,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Bone health and treatments","field":"Medicine","cited_by":89,"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":"Ministry of Science and Technology, Taiwan","keywords":"Drug; Cheminformatics; Osteoporosis; Computer science; Medicine; Pharmacology; Chemistry; Internal medicine; Computational chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01321261440398536,"gpt":0.2909295781902771,"spread":0.2777169637862917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006869038,0.0001072209,0.0001673017,0.0001373373,0.0001583279,0.00002180927,0.00004239524,0.00001467521,0.00002145969],"category_scores_gemma":[0.00002477921,0.0001053091,0.00005048489,0.00009546839,0.00001898235,0.0002003071,0.00002953042,0.0001421066,0.000001566939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001204135,"about_ca_system_score_gemma":0.0001383645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002512109,"about_ca_topic_score_gemma":0.0001135019,"domain_scores_codex":[0.9991899,0.00002793949,0.0003368298,0.00009538321,0.0001854686,0.0001644529],"domain_scores_gemma":[0.999458,0.0000423257,0.00008505015,0.0002111184,0.00003752765,0.0001659409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004662042,0.007390724,0.5113311,0.002457964,0.0006158403,0.0001886019,0.07016734,0.3036207,0.002110324,0.0006014291,0.02103933,0.07581467],"study_design_scores_gemma":[0.002938228,0.0001335701,0.009365642,0.00004132088,0.0001529111,0.00000467423,0.001646648,0.9839728,0.0004044596,0.0003465887,0.0009046583,0.00008846031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829968,0.0001489952,0.01396983,0.0006927078,0.00009025085,0.0007778752,0.001184897,0.00005708182,0.00008157283],"genre_scores_gemma":[0.9880461,0.0000108921,0.006624827,0.002917919,0.000008733502,0.0004200777,0.001900848,0.00001565434,0.00005492297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6803522,"threshold_uncertainty_score":0.4294381,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220753843","doi":"10.1002/minf.202100240","title":"A Descriptor Set for Quantitative Structure‐property Relationship Prediction in Biologics","year":2022,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Quantitative structure–activity relationship; In silico; Computer science; Stability (learning theory); Drug development; Artificial intelligence; Machine learning; Drug discovery; Set (abstract data type); Process (computing); Biochemical engineering; Data mining; Biological system; Computational biology; Drug; Chemistry; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.08329791264474877,"gpt":0.3406507462846687,"spread":0.2573528336399199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003106398,0.0001023528,0.0001710988,0.0001819167,0.0001842892,0.00001606632,0.0000994714,0.0000540511,0.0001272901],"category_scores_gemma":[0.0003177493,0.0000702498,0.00007504346,0.0002919831,0.00005243915,0.00008132739,0.00009941314,0.0003398008,0.00001013413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001279071,"about_ca_system_score_gemma":0.0001164658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003365313,"about_ca_topic_score_gemma":0.000007393693,"domain_scores_codex":[0.9989302,0.00006444004,0.0003747457,0.00008723947,0.000316606,0.0002267801],"domain_scores_gemma":[0.9995208,0.0001025209,0.00007703144,0.0001421691,0.00009065749,0.00006680885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01121695,0.001109371,0.5493319,0.004219989,0.0008339863,0.000331972,0.0495617,0.03314192,0.09466515,0.1649799,0.07301317,0.01759394],"study_design_scores_gemma":[0.008103685,0.008115471,0.0965722,0.0001722232,0.0001760066,0.0005243369,0.0165949,0.435315,0.009090535,0.01850537,0.4059686,0.0008616752],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893162,0.0001429701,0.006214928,0.0007825803,0.0001316368,0.0009301435,0.0006336771,0.00003255648,0.001815297],"genre_scores_gemma":[0.9757973,0.000008294314,0.02089969,0.001006918,0.00002055897,0.0001389363,0.0009622611,0.00001260137,0.001153445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4527597,"threshold_uncertainty_score":0.2864704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313816625","doi":"10.1002/minf.202200186","title":"A comparison between 2D and 3D descriptors in QSAR modeling based on bio‐active conformations","year":2023,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":52,"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 Hospital","funders":"","keywords":"Quantitative structure–activity relationship; Cheminformatics; Random forest; Protein Data Bank (RCSB PDB); Molecular descriptor; Lasso (programming language); Computer science; Set (abstract data type); Artificial intelligence; Test set; Data mining; Pattern recognition (psychology); Machine learning; Chemistry; Computational chemistry; Stereochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.05288652475164202,"gpt":0.337118736541096,"spread":0.284232211789454,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005813729,0.0001549235,0.0002220751,0.0006010355,0.0001005798,0.000194942,0.0003701615,0.00006449034,0.000001340889],"category_scores_gemma":[0.0001412478,0.0001599244,0.00004575588,0.0009246145,0.00003217741,0.0007481369,0.0002066132,0.0002068386,0.00005082448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008399111,"about_ca_system_score_gemma":0.000115081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001523063,"about_ca_topic_score_gemma":0.00000211924,"domain_scores_codex":[0.9985234,0.0001019062,0.0005572874,0.0001254292,0.0004259127,0.0002661353],"domain_scores_gemma":[0.9991214,0.0002904858,0.0001259847,0.0003075422,0.00006596492,0.00008862424],"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":[0.000003312613,0.00001554887,0.0006604315,0.00003555571,0.000009164802,0.000003067679,0.003355332,0.9774364,0.00001055339,0.006188762,0.00003926079,0.01224266],"study_design_scores_gemma":[0.00036027,0.00004647159,0.002595428,0.00005656252,0.000006040687,0.000001069131,0.0003993179,0.9936429,0.0005473159,0.001984952,0.0001857926,0.0001739246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3587815,0.000005770657,0.639679,0.0001588539,0.0000587237,0.0001618406,0.000008611248,0.00009646696,0.001049197],"genre_scores_gemma":[0.8969265,0.000001944604,0.1025368,0.0004439336,0.000007416606,0.00001723523,0.00005531823,0.00000803681,0.000002795027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.538145,"threshold_uncertainty_score":0.6521526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1899644141","doi":"10.1002/minf.201400118","title":"Towards Better BBB Passage Prediction Using an Extensive and Curated Data Set","year":2015,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":50,"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":"Linear discriminant analysis; Set (abstract data type); Test set; Computer science; Data set; Artificial intelligence; Machine learning; Regression; Linear regression; Data mining; Variance (accounting); Drug discovery; Linear model; Regression analysis; Statistics; Mathematics; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1242311728463903,"gpt":0.3528909864422495,"spread":0.2286598135958592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007028318,0.0001334717,0.000135312,0.0001061778,0.00006500066,0.0003382708,0.0006871906,0.00005744737,0.000001082505],"category_scores_gemma":[0.0001848313,0.0001287786,0.0000170887,0.000290899,0.00004421029,0.002897689,0.000930203,0.0001224088,0.000007447783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004992128,"about_ca_system_score_gemma":0.0002003565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002203811,"about_ca_topic_score_gemma":9.540042e-7,"domain_scores_codex":[0.9986936,0.000143795,0.0003400674,0.0001813454,0.0004569434,0.0001842855],"domain_scores_gemma":[0.9985667,0.00003512827,0.0001317385,0.0008578171,0.0002440302,0.0001645223],"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":[0.00004540771,0.0002429418,0.001032352,0.0002532612,0.0002848537,0.0002779331,0.03806779,0.6790442,0.002904475,0.02348295,0.00860625,0.2457575],"study_design_scores_gemma":[0.0002877592,0.00005293104,0.0005562938,0.000015556,0.00001523075,0.00009468554,0.0002421912,0.9908257,0.0006582327,0.005897702,0.001209735,0.000143986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.291077,0.00002870701,0.7080379,0.0001598682,0.0001647748,0.000108862,0.00004740776,0.00006760285,0.0003079246],"genre_scores_gemma":[0.2664935,0.000003007314,0.7314016,0.001738319,0.00004402527,0.00000305376,0.0003006923,0.00001206337,0.000003733977],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3117814,"threshold_uncertainty_score":0.5251441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008947010","doi":"10.1002/minf.201200031","title":"Chemical Descriptors Are More Important Than Learning Algorithms for Modelling","year":2012,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Mitacs","keywords":"Computer science; Cheminformatics; Machine learning; Artificial intelligence; Algorithm; Chemistry; Computational chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03754151563592349,"gpt":0.2965459023265248,"spread":0.2590043866906013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000668073,0.0001740507,0.0001880102,0.00009963492,0.0001063625,0.0001503308,0.0005042905,0.00007552464,0.000001358709],"category_scores_gemma":[0.0001399143,0.0001698489,0.0001380601,0.0002481069,0.00002991382,0.0009688247,0.0002471734,0.0001936353,0.000009478475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007092285,"about_ca_system_score_gemma":0.00005919385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002967694,"about_ca_topic_score_gemma":5.252805e-8,"domain_scores_codex":[0.9984939,0.00003887973,0.0004961992,0.0001176119,0.0004065538,0.0004469311],"domain_scores_gemma":[0.9990334,0.0001249164,0.000259376,0.0002977922,0.0001194012,0.0001651412],"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":[0.000008297542,0.00008465828,0.0009927864,0.0001447366,0.00006763163,0.000005373122,0.00934972,0.9365596,0.0009055401,0.03953344,0.000190082,0.0121582],"study_design_scores_gemma":[0.0001866999,0.00001462484,0.00006497659,0.0000230613,0.00001138355,0.00002121748,0.0003305555,0.9840844,0.0114328,0.00194134,0.001668545,0.000220445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1592683,0.0001236083,0.8398244,0.00008908925,0.0002402663,0.0001864044,0.000003409226,0.0001071721,0.0001573176],"genre_scores_gemma":[0.3683028,0.000002989205,0.6313574,0.0002194183,0.00005009977,0.00002409404,0.00001743872,0.00001315816,0.00001269954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2090345,"threshold_uncertainty_score":0.6926237,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032729355","doi":"10.1002/minf.201000018","title":"Finding Inspiration in the Protein Data Bank to Chemically Antagonize Readers of the Histone Code","year":2010,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Click Chemistry and Applications","field":"Chemistry","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; University of New Brunswick; Structural Genomics Consortium; University of Toronto","funders":"Knut och Alice Wallenbergs Stiftelse; Natural Sciences and Engineering Research Council of Canada; Karolinska Institutet; Stiftelsen för Strategisk Forskning; Canadian Institutes of Health Research; Genome Canada; Ontario Genomics; Wellcome Trust; Ontario Genomics Institute; Ontario Innovation Trust","keywords":"Protein Data Bank (RCSB PDB); Protein Data Bank; Pharmacophore; Histone; Epigenetics; Chemistry; Cheminformatics; Computational biology; Affinities; Stereochemistry; Acetylation; Drug discovery; Biology; Biochemistry; Protein structure; Bioinformatics; DNA; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02806135310030598,"gpt":0.2972882026075814,"spread":0.2692268495072754,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002361171,0.00009659898,0.00009540751,0.00001652797,0.00007145051,0.0000312285,0.001142963,0.0001013729,0.00004510714],"category_scores_gemma":[0.0003529051,0.00006807483,0.00003327316,0.000232577,0.00007660242,0.00009546138,0.0002334562,0.0003714944,0.000007830799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002315223,"about_ca_system_score_gemma":0.00005866213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000015419,"about_ca_topic_score_gemma":0.00002702762,"domain_scores_codex":[0.9991056,0.000006360512,0.0004103096,0.00009324535,0.0002458966,0.0001385588],"domain_scores_gemma":[0.9983881,0.000037663,0.000171637,0.001333376,0.00003753704,0.00003176264],"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":[0.000003886539,0.00003828963,0.00008279562,0.0001014528,0.000004930578,4.791158e-7,0.001687096,0.00003667155,0.9965779,0.0004535874,0.0004559531,0.0005570201],"study_design_scores_gemma":[0.0001710063,0.000002642433,0.00006982914,0.00004503629,0.0000113751,0.000007096577,0.0006141944,0.001369995,0.9803843,0.0001075647,0.01712633,0.00009055837],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890746,0.000004576249,0.0008528043,0.001322595,0.00001428864,0.0002224665,0.00008401105,0.00001581443,0.008408838],"genre_scores_gemma":[0.9958594,8.044948e-7,0.003276838,0.000513701,0.00002348453,0.00005721705,0.0001693348,0.000008183861,0.00009099636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01667038,"threshold_uncertainty_score":0.2776011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003032055","doi":"10.1002/minf.201100053","title":"Target‐Driven Subspace Mapping Methods and Their Applicability Domain Estimation","year":2011,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":22,"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; Deutsche Forschungsgemeinschaft","keywords":"Subspace topology; Estimation; Computer science; Domain (mathematical analysis); Data mining; Artificial intelligence; Computational biology; Pattern recognition (psychology); Mathematics; Biology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0257763614147911,"gpt":0.2729227023296965,"spread":0.2471463409149053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000892684,0.0001463257,0.0001640559,0.00008579562,0.0001308507,0.000129752,0.0003777236,0.00006794091,0.00001295663],"category_scores_gemma":[0.00008991372,0.0001283854,0.00005065193,0.0003043938,0.00006720973,0.0005479555,0.0002292263,0.000156336,0.00002659495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000281361,"about_ca_system_score_gemma":0.00003089468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005253891,"about_ca_topic_score_gemma":4.181509e-7,"domain_scores_codex":[0.9989918,0.0001385429,0.0003563094,0.0001418557,0.0001506915,0.0002208005],"domain_scores_gemma":[0.9991288,0.00007135588,0.0001771468,0.0004504251,0.00006159528,0.0001107136],"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":[0.00001212679,0.0001029501,0.0009185252,0.0002688615,0.00009476967,0.00001354322,0.2096829,0.005222574,0.0105614,0.2608115,0.0001354556,0.5121753],"study_design_scores_gemma":[0.0002502378,0.00003349157,0.001776499,0.00001485843,0.000003084473,0.00002474937,0.001905049,0.950323,0.006139279,0.03392504,0.005384224,0.0002204531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02613704,0.00004604321,0.9647795,0.000106109,0.0000590269,0.0002131912,7.194152e-7,0.0001516452,0.008506736],"genre_scores_gemma":[0.2153191,0.000003381364,0.7842712,0.0003671362,0.000003946435,0.00001469804,0.000003307947,0.000006069915,0.00001116096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9451005,"threshold_uncertainty_score":0.5235404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059197104","doi":"10.1002/minf.201200020","title":"Prospective Prediction of Antitarget Activity by Matched Molecular Pairs Analysis","year":2012,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Quantitative structure–activity relationship; Computer science; Aggregate (composite); Data mining; Machine learning; Nanotechnology; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.00911041723449239,"gpt":0.2583840696909916,"spread":0.2492736524564993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007022143,0.0001730055,0.0003074778,0.0002812679,0.00005338525,0.00006802918,0.0004587673,0.00007809842,0.000007945536],"category_scores_gemma":[0.0001011921,0.0001742781,0.0002162468,0.001491512,0.00005182042,0.001372497,0.0001991422,0.0001392035,0.00001213038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008803266,"about_ca_system_score_gemma":0.00006075217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001534609,"about_ca_topic_score_gemma":2.373279e-7,"domain_scores_codex":[0.9983266,0.0001522839,0.0004440736,0.0001351997,0.0006346623,0.000307152],"domain_scores_gemma":[0.9987801,0.00008145829,0.0003083812,0.0005431049,0.0001659364,0.0001209899],"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":[0.00007285102,0.001921746,0.1144869,0.0005802133,0.005514429,0.00001792153,0.02655051,0.488684,0.1755018,0.1656705,0.002064026,0.0189351],"study_design_scores_gemma":[0.0003630794,0.0000686722,0.0482285,0.00001170785,0.0002458805,0.000006843889,0.0001515509,0.688823,0.2590284,0.00257867,0.0002210653,0.0002726382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4052214,0.00006341441,0.5932068,0.00003713938,0.00007832801,0.0001458731,0.00002946757,0.00005576839,0.001161836],"genre_scores_gemma":[0.8551501,0.000003102593,0.1446767,0.0001010959,0.000007457256,0.00001474328,0.00003088774,0.000007786655,0.000008135519],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4499287,"threshold_uncertainty_score":0.7106853,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2919214297","doi":"10.1002/minf.201800160","title":"Application of an Iterative Fragment Selection (IFS) Method to Estimate Entropies of Fusion and Melting Points of Organic Chemicals","year":2019,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; ASL Environmental Sciences (Canada); ARC Resources (Canada); The Scarborough Hospital; Greenfield Research (Canada)","funders":"European Chemical Industry Council","keywords":"Selection (genetic algorithm); Mean squared error; Computer science; Biological system; Mathematics; Artificial intelligence; Biology; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.005338842299840955,"gpt":0.3057756650376185,"spread":0.3004368227377776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005872184,0.0000884994,0.0002103651,0.0001257356,0.00001818064,0.00002314905,0.0002428477,0.00003620574,0.000003120078],"category_scores_gemma":[0.0000918268,0.00008530278,0.00003002864,0.0003743414,0.00001583103,0.0003502533,0.000248085,0.00005106667,0.000002032466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817036,"about_ca_system_score_gemma":0.00003837617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006027094,"about_ca_topic_score_gemma":4.836418e-7,"domain_scores_codex":[0.9988896,0.00009552862,0.0005074844,0.0001135123,0.0003013103,0.00009253807],"domain_scores_gemma":[0.9989836,0.0001309977,0.0003717674,0.0002400002,0.0002314202,0.00004219709],"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":[0.00001284696,0.00004997083,0.0004879208,0.0002597401,0.00002448797,1.087165e-7,0.006346634,0.07967437,0.8655264,0.01279677,0.000001476306,0.03481923],"study_design_scores_gemma":[0.0001166986,0.00008017843,0.0009601449,0.00002912965,0.000005190574,0.00000286799,0.00006572004,0.5099705,0.4869739,0.001741706,0.000008071335,0.00004583537],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4767861,0.00000565195,0.5229549,0.00002192184,0.00001135371,0.0001690394,0.000001457862,0.000007844676,0.00004166146],"genre_scores_gemma":[0.4715683,5.035922e-7,0.5283828,0.00003533691,0.000001567268,0.000003565317,0.000004283997,0.000002828956,8.110105e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4302961,"threshold_uncertainty_score":0.3478546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015042232","doi":"10.1002/minf.200900019","title":"How to Deal with Batch Effect in Sequential Microarray Experiments?","year":2010,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto; Mount Sinai Hospital","funders":"National Cancer Institute; Canadian Prostate Cancer Research Initiative; Institute for Prostate Cancer Research","keywords":"Computer science; Computational biology; Microarray analysis techniques; Data mining; Chemistry; Biology; Gene; Gene expression; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.005950242800431988,"gpt":0.2494548033599986,"spread":0.2435045605595666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001307341,0.0001501084,0.000111961,0.00008241815,0.00003679562,0.00008476366,0.0001992226,0.0001303793,0.00001006321],"category_scores_gemma":[0.00001705243,0.0001240485,0.00004179721,0.0001387023,0.00003375493,0.00000932581,0.00007344721,0.0001375577,0.00001304848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001390055,"about_ca_system_score_gemma":0.00006061104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005128811,"about_ca_topic_score_gemma":0.00002494552,"domain_scores_codex":[0.9992541,0.00002957305,0.0001786347,0.0001466145,0.0001707793,0.0002203079],"domain_scores_gemma":[0.9994059,0.000003003266,0.00006950384,0.000360751,0.0000493629,0.0001114456],"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":[0.00007128476,0.00001902774,0.0005859902,0.00001696834,0.00001244155,0.000002701518,0.0002493247,0.00006982083,0.9945924,0.00005637805,0.0009543731,0.003369343],"study_design_scores_gemma":[0.0006448224,0.0002350332,0.0004900473,0.00001154095,0.000005468881,0.000009464521,0.0001848759,0.00005284687,0.9195868,0.000006386125,0.0786045,0.0001682202],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713209,0.00002748881,0.02636381,0.000323831,0.00009619156,0.0003074899,0.000003315524,0.00001145322,0.001545565],"genre_scores_gemma":[0.9833565,0.000003621076,0.0152551,0.0009313322,0.00005067181,0.00009259227,0.00006628069,0.0000185616,0.000225355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07765013,"threshold_uncertainty_score":0.5058552,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2981596486","doi":"10.1002/minf.201900096","title":"An <i>in silico</i> Approach for Integrating Phenotypic and Target‐based Approaches in Drug Discovery","year":2019,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Innovation Cluster (Canada)","funders":"Core Research for Evolutional Science and Technology; Japan Society for the Promotion of Science; New Energy and Industrial Technology Development Organization","keywords":"In silico; Drug discovery; Computational biology; Phenotypic screening; Computer science; Deconvolution; Phenotype; Cheminformatics; Drug target; Systems biology; Bioinformatics; Biology; Genetics; Algorithm; Pharmacology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01839675626069718,"gpt":0.2593566582448479,"spread":0.2409599019841507,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100837,0.0001918594,0.0002601093,0.0002595522,0.00003580235,0.0003375609,0.0005715317,0.00005952856,5.600531e-7],"category_scores_gemma":[0.00007588037,0.000181863,0.00005802897,0.000445109,0.00003409443,0.00172292,0.0001554916,0.0001888224,0.000002002348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006824152,"about_ca_system_score_gemma":0.0001371538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000195002,"about_ca_topic_score_gemma":0.000007002995,"domain_scores_codex":[0.9985362,0.0001384808,0.0005073545,0.0002520332,0.0002659942,0.0002999493],"domain_scores_gemma":[0.9990765,0.0002400159,0.0001364936,0.0004536562,0.00003253848,0.00006080494],"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":[0.00001842207,0.0001475974,0.002321009,0.0003077725,0.000007231318,0.000001664263,0.004366676,0.8857165,0.0006497059,0.09876638,0.000008687391,0.007688362],"study_design_scores_gemma":[0.0007180427,0.00004748697,0.0008084945,0.00003347735,0.000002383482,0.000002520504,0.0007727628,0.9888556,0.002661902,0.005821595,0.00004893264,0.0002268299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3315181,0.00004053177,0.6665926,0.00004504629,0.00004421388,0.000485229,0.000004121317,0.00002696393,0.001243112],"genre_scores_gemma":[0.517075,3.488443e-7,0.482543,0.000289483,0.000004994125,0.0000413455,0.00003197055,0.000007994157,0.000005939594],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1855568,"threshold_uncertainty_score":0.7416159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376636211","doi":"10.1002/minf.202300026","title":"Novel Inhibitors of androgen receptor's DNA binding domain identified using an ultra‐large virtual screening","year":2023,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Prostate Cancer Treatment and Research","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"DOD Prostate Cancer Research Program; Canadian Cancer Society Research Institute; U.S. Department of Defense","keywords":"Androgen receptor; Virtual screening; Computational biology; Chemistry; Domain (mathematical analysis); DNA; Computer science; Biology; Genetics; Drug discovery; Biochemistry; Prostate cancer; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04133740417371557,"gpt":0.3232444522595325,"spread":0.281907048085817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005669258,0.0001643721,0.0002845143,0.0004336893,0.0001401014,0.00004767397,0.0001239647,0.0001144833,0.00002694516],"category_scores_gemma":[0.00006520699,0.000144158,0.0001175986,0.0008162015,0.00008077099,0.0003084432,0.00007003167,0.0001802696,0.00004048876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009010464,"about_ca_system_score_gemma":0.0001532535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001469858,"about_ca_topic_score_gemma":0.000001253243,"domain_scores_codex":[0.9982736,0.000028013,0.0005290399,0.0001190947,0.0006087825,0.0004415479],"domain_scores_gemma":[0.9992027,0.000027932,0.0001633019,0.0002963188,0.0001223361,0.0001874104],"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":[0.0001215144,0.0001256968,0.002033405,0.0002334614,0.000198246,0.0000498634,0.004307853,0.0002906101,0.9905117,0.0001586743,0.0002302824,0.001738746],"study_design_scores_gemma":[0.003988625,0.000359453,0.0002547228,0.0003929258,0.00008990113,0.00004258152,0.01037218,0.007808717,0.9751993,0.00002472397,0.001242096,0.0002247524],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848235,0.0000366314,0.01383155,0.00004929204,0.0001388912,0.0004249662,0.00008698259,0.00008924104,0.0005189871],"genre_scores_gemma":[0.9909862,0.00003547272,0.007934826,0.00008069023,0.0000580633,0.00001210211,0.0006754366,0.00004073909,0.0001765191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01531233,"threshold_uncertainty_score":0.5878593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983545523","doi":"10.1002/minf.201100085","title":"Identification of Novel Inhibitors of UDP‐Galactopyranose Mutase by Structure‐Based Virtual Screening","year":2011,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Carbohydrate Chemistry and Synthesis","field":"Chemistry","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Mutase; In silico; Escherichia coli; Virtual screening; Enzyme; Docking (animal); Biochemistry; Klebsiella pneumoniae; Dehydratase; Chemistry; Mycobacterium tuberculosis; Biology; Klebsiella pneumonia; Stereochemistry; Drug discovery; Tuberculosis","retraction":null,"screen_n_in":null,"score":{"opus":0.013410427002871,"gpt":0.2119475518740633,"spread":0.1985371248711922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001193672,0.0001765963,0.0002470969,0.00006361167,0.0000341134,0.00001558721,0.0002594773,0.0001785277,0.0002628539],"category_scores_gemma":[0.0001482729,0.0001831478,0.0001399628,0.0001585391,0.0001286911,0.0001444485,0.00004945368,0.0001362955,0.000001663241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002177427,"about_ca_system_score_gemma":0.00004555209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001846309,"about_ca_topic_score_gemma":4.930646e-7,"domain_scores_codex":[0.9984535,0.000007398757,0.0009243756,0.00009889388,0.000349125,0.0001666824],"domain_scores_gemma":[0.9986389,0.0000406253,0.0006367501,0.0004784769,0.0001287682,0.00007642271],"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":[0.00003905246,0.0001069767,0.0001929375,0.000371137,0.00005001136,0.000001510512,0.0009805667,0.0002855246,0.997052,0.00006236489,0.00006121297,0.0007967003],"study_design_scores_gemma":[0.0005516438,0.00001446183,0.00002191289,0.00007508838,0.00006579189,0.000003030079,0.0007383916,0.009465583,0.9887908,0.00001807419,0.00008259508,0.000172687],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672974,0.0000223813,0.0299699,0.000004389376,0.00003135002,0.00005545618,0.0004434774,0.00002740511,0.002148208],"genre_scores_gemma":[0.9968914,0.000001544491,0.002812445,0.00002845212,0.00001012434,0.000004559568,0.0001985249,0.00001808811,0.0000348484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02959398,"threshold_uncertainty_score":0.746855,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990193701","doi":"10.1002/minf.201400017","title":"Systematic Identification of Matching Molecular Series and Mapping of Screening Hits","year":2014,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Computer science; Series (stratigraphy); Matching (statistics); Identification (biology); Computational biology; Data mining; Information retrieval; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.009911711928669237,"gpt":0.2481507745470005,"spread":0.2382390626183312,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001268258,0.0001139167,0.0002941413,0.0002070303,0.00004359613,0.00009584871,0.0004167477,0.00003869369,3.625727e-7],"category_scores_gemma":[0.0003273236,0.0001141615,0.00006353008,0.0003361766,0.00004827348,0.000686323,0.000271155,0.00006543199,0.000001744392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001127078,"about_ca_system_score_gemma":0.00002625484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004125423,"about_ca_topic_score_gemma":1.602171e-7,"domain_scores_codex":[0.9982045,0.0001816645,0.0009641939,0.0000973595,0.0004273143,0.0001250267],"domain_scores_gemma":[0.9985099,0.0001819982,0.0006728621,0.0004277375,0.0001663292,0.0000411033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005628169,0.00003236681,0.00006286053,0.02654953,0.0001514404,0.000003776885,0.0118513,0.2689653,0.09168188,0.5927194,0.000004923888,0.00797156],"study_design_scores_gemma":[0.0001814352,0.00003994994,0.0006235918,0.001491843,0.00002615886,0.00003582678,0.0005453076,0.8893847,0.08514877,0.02234767,0.000008352369,0.0001663798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2699658,0.00007403017,0.729455,0.00004237717,0.00004216785,0.0001621144,0.000001378717,0.00002396643,0.0002332329],"genre_scores_gemma":[0.6544418,0.000001989741,0.3454854,0.00005150874,0.000002155086,0.000005647805,0.000002694689,0.000005072803,0.000003631148],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6204194,"threshold_uncertainty_score":0.465537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799656935","doi":"10.1002/minf.201800043","title":"Cheminformatics Driven Development of Novel Therapies for Drug Resistant Prostate Cancer","year":2018,"lang":"en","type":"review","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"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; Prevention of Organ Failure","funders":"Canadian Institutes of Health Research; Genome British Columbia; Prostate Cancer Canada","keywords":"Cheminformatics; Androgen receptor; Prostate cancer; Antiandrogens; Drug resistance; Computational biology; Drug development; Regulator; Drug; Chemistry; Pharmacology; Cancer; Cancer research; Bioinformatics; Medicine; Biology; Internal medicine; Biochemistry; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.05123095418060562,"gpt":0.3599071691822451,"spread":0.3086762150016395,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009064805,0.0004877223,0.001174507,0.0003143228,0.0001330353,0.0001934589,0.001656364,0.000151545,0.000002626914],"category_scores_gemma":[0.0001165849,0.0004016435,0.0004080754,0.0005700721,0.00009857118,0.0005156522,0.0006512172,0.0001884121,0.00001046244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002353099,"about_ca_system_score_gemma":0.00209249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001746055,"about_ca_topic_score_gemma":0.000002297392,"domain_scores_codex":[0.9965186,0.00003942318,0.002154458,0.0002027026,0.0006856956,0.0003991066],"domain_scores_gemma":[0.9966357,0.0003310057,0.001690912,0.000763967,0.0004817953,0.00009666725],"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":[0.00000596976,0.00007074825,8.831019e-8,0.03794447,0.0004729285,7.317905e-7,0.01864938,0.001029826,0.000005725501,0.005652942,0.0007816024,0.9353856],"study_design_scores_gemma":[0.0003329676,0.00003067421,4.292127e-7,0.006210884,0.0001368378,0.000006214091,0.000113316,0.04946462,0.0004548074,0.0002934957,0.9424284,0.0005274189],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002781334,0.406438,0.5916602,0.00001511104,0.0002215628,0.001169199,0.0001058306,0.00004950698,0.0003127978],"genre_scores_gemma":[0.000002493261,0.2891875,0.7101366,0.00007493651,0.00002437823,0.00035795,0.0001127752,0.00003131257,0.00007212159],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9416468,"threshold_uncertainty_score":0.9998435,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155678816","doi":"10.1002/minf.201200171","title":"Rendering Molecular Sketches for Publication Quality Output","year":2013,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec","funders":"","keywords":"Rendering (computer graphics); Computer science; Cheminformatics; Computer graphics (images); File format; Graphics; Software; Computer graphics; Computational science; Engineering drawing; Database; Programming language; Bioinformatics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03700972570440528,"gpt":0.3195687943401153,"spread":0.28255906863571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007883534,0.0001683389,0.0001833615,0.0001569647,0.00009306062,0.0006101131,0.0008489756,0.00007214978,0.00000784227],"category_scores_gemma":[0.000617711,0.0001715306,0.0001361472,0.0003674447,0.00003182499,0.001586848,0.0003223417,0.0001053684,0.0001041672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007427893,"about_ca_system_score_gemma":0.0001119167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001821292,"about_ca_topic_score_gemma":3.854107e-7,"domain_scores_codex":[0.9982988,0.00009813843,0.0006561792,0.0001811963,0.0004547337,0.0003109664],"domain_scores_gemma":[0.9982193,0.0002108719,0.0002692558,0.000712928,0.0004706116,0.0001170597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003966362,0.00008322694,0.00005996631,0.0002446104,0.00008757108,0.00000183991,0.002549082,0.06357463,0.005561535,0.6745962,0.002881731,0.2503557],"study_design_scores_gemma":[0.0003836554,0.00004148744,0.001865551,0.0000158144,0.000008552439,0.000008599369,0.0001226371,0.8927083,0.02064237,0.07665672,0.007185528,0.0003607579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05716354,0.00004034353,0.9360439,0.001690282,0.0001417737,0.0005471446,0.000004296323,0.0001719311,0.004196765],"genre_scores_gemma":[0.3490373,0.000001533936,0.6487346,0.001926194,0.00001468613,0.0001759709,0.00003723802,0.00001238839,0.00006006137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8291337,"threshold_uncertainty_score":0.6994817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037787710","doi":"10.1002/minf.202000033","title":"Using Language Representation Learning Approach to Efficiently Identify Protein Complex Categories in Electron Transport Chain","year":2020,"lang":"en","type":"article","venue":"Molecular Informatics","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":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Feature learning; Representation (politics); Word embedding; Natural language processing; Machine learning; Feature (linguistics); Pattern recognition (psychology); Support vector machine; Categorization; Multi-task learning; Embedding; Task (project management)","retraction":null,"screen_n_in":null,"score":{"opus":0.02120448430788708,"gpt":0.3007711008899546,"spread":0.2795666165820676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002985109,0.0002259671,0.000231646,0.0001201506,0.00008645823,0.00006326551,0.0002883544,0.0001357568,0.000005956523],"category_scores_gemma":[0.0002296768,0.0002421394,0.00008463197,0.0004651608,0.00004135546,0.00002048597,0.000120657,0.0003168439,0.00001798744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003691663,"about_ca_system_score_gemma":0.0000666849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004652137,"about_ca_topic_score_gemma":0.000006649594,"domain_scores_codex":[0.9983898,0.00008886103,0.0006171964,0.0001924715,0.0003327182,0.0003789292],"domain_scores_gemma":[0.9993162,0.000004847772,0.0002022251,0.0002748138,0.00006352601,0.0001384257],"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":[0.00006707812,0.00003906804,0.00150757,0.0002399968,0.00002769699,0.000005851279,0.009521412,0.4426733,0.5452502,0.0002163602,0.0000331042,0.000418402],"study_design_scores_gemma":[0.001350041,0.0004933517,0.002068862,0.00005008744,0.00003754171,0.00003415267,0.005199778,0.6635243,0.3223388,0.00001397577,0.004122808,0.0007662158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6733504,0.00003032015,0.3229493,0.00006135764,0.00001254293,0.0005104656,0.000004257813,0.00003384837,0.003047474],"genre_scores_gemma":[0.9486059,0.000002623972,0.04988404,0.0007838116,0.00003625557,0.00002981168,0.0005861628,0.00003281981,0.00003856376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2752555,"threshold_uncertainty_score":0.987416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2944666543","doi":"10.1002/minf.201800110","title":"QSPRs for Molecular Diffusion Coefficients in Polymeric Passive Samplers: A Comparison of Simple Molecular and Quantum‐mechanical Sigma‐moment Descriptors","year":2019,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Trent University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quantitative structure–activity relationship; Molecular descriptor; Low-density polyethylene; Mean squared error; Correlation coefficient; Chemistry; Moment (physics); Diffusion; Computational chemistry; Mathematics; Polyethylene; Thermodynamics; Organic chemistry; Stereochemistry; Statistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01619342216238135,"gpt":0.3002332653078655,"spread":0.2840398431454841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004482982,0.0003019501,0.0005572033,0.0003796133,0.00005656384,0.0001270397,0.0007059388,0.000122268,0.000004406191],"category_scores_gemma":[0.0001766945,0.0003074159,0.0001648716,0.0007133543,0.00006734371,0.0003662615,0.000617953,0.0001842733,0.000005300345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201003,"about_ca_system_score_gemma":0.000136986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003616711,"about_ca_topic_score_gemma":0.000001529587,"domain_scores_codex":[0.9972426,0.0001718822,0.001022545,0.0003331256,0.0007585839,0.0004712336],"domain_scores_gemma":[0.9983491,0.0002943879,0.0004327703,0.0006132953,0.000154465,0.0001559691],"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":[0.0001423704,0.0009434129,0.001927773,0.0008169432,0.0001750826,0.00003455207,0.008438454,0.3646045,0.2163459,0.3508798,0.00009207945,0.05559915],"study_design_scores_gemma":[0.001381839,0.0004059055,0.0003569614,0.00007556949,0.00002081615,0.000006613959,0.0005821413,0.8920299,0.09769723,0.006750945,0.0003508756,0.0003412068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4798098,0.00009500939,0.5192912,0.00006428482,0.0001137569,0.0005549383,0.00001179001,0.00002287355,0.00003640125],"genre_scores_gemma":[0.8899561,0.000003734874,0.1094884,0.0004355811,0.0000034672,0.00004401007,0.00004486348,0.00002155026,0.000002287883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5274254,"threshold_uncertainty_score":0.9999378,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066256098","doi":"10.1002/minf.200900040","title":"Forecasting CYP2D6 and CYP3A4 Risk with a Global/Local Fusion Model of CYP450 Inhibition","year":2010,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Ontario Institute for Cancer Research","funders":"Neurocrine Biosciences","keywords":"Quantitative structure–activity relationship; Computer science; Data mining; Pharmacophore; Similarity (geometry); Set (abstract data type); Machine learning; Artificial intelligence; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01137314563226853,"gpt":0.2389662891251577,"spread":0.2275931434928892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004269199,0.0001319639,0.0001487659,0.00007643249,0.00008157225,0.0000885027,0.00021489,0.00006532222,8.468793e-7],"category_scores_gemma":[0.0001035363,0.0001133753,0.00003985847,0.0003109523,0.0001013823,0.0006226736,0.0003171776,0.0001871117,0.000001796757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002410732,"about_ca_system_score_gemma":0.0001166464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000177847,"about_ca_topic_score_gemma":0.00001445205,"domain_scores_codex":[0.9989092,0.00004043408,0.0003583439,0.000119343,0.0004003561,0.0001722705],"domain_scores_gemma":[0.9991078,0.00007525791,0.0002688866,0.0003051155,0.0001611594,0.00008178928],"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":[0.00001861776,0.00004061488,0.0002998199,0.00009106858,0.00002093349,0.000008175574,0.001923078,0.811675,0.002082854,0.05935776,0.00001698381,0.1244651],"study_design_scores_gemma":[0.0003447373,0.00007140246,0.0002648837,0.0000351427,0.00001264166,0.00007327799,0.00006821688,0.970642,0.005648838,0.02269128,0.00001557484,0.0001319927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.462911,0.000005019072,0.5360582,0.00002611831,0.00002684788,0.00008436444,0.00000890612,0.00002371264,0.0008557679],"genre_scores_gemma":[0.5375397,0.000001492583,0.4623624,0.00008112104,0.000003808514,0.000003125644,0.000003992934,0.000003362733,9.72393e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1589671,"threshold_uncertainty_score":0.4623309,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1980840780","doi":"10.1002/minf.201100111","title":"An Advanced Group Contribution Method for High‐Dimensional, Sparse Data Sets","year":2011,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Group (periodic table); Computer science; Data mining; Chemistry; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.04836593607333022,"gpt":0.3458207124614303,"spread":0.2974547763881001,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001415576,0.000182706,0.0002200325,0.0001190724,0.000122646,0.0001171437,0.00159715,0.00007386776,0.000006959555],"category_scores_gemma":[0.0002637843,0.0001794074,0.00005533674,0.0002782481,0.00003063471,0.002380377,0.0006099426,0.0001082274,0.00002324557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004611455,"about_ca_system_score_gemma":0.000104741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000183683,"about_ca_topic_score_gemma":0.000003582053,"domain_scores_codex":[0.9983164,0.0001805255,0.0005183457,0.0002732468,0.000401124,0.0003103383],"domain_scores_gemma":[0.9976594,0.0002240806,0.0002476307,0.001474865,0.000258335,0.0001356219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006900952,0.0002407967,0.00001237126,0.00006502434,0.00008332882,0.00001626143,0.001141347,0.05764957,0.002494192,0.7394705,0.0006153669,0.1981423],"study_design_scores_gemma":[0.0006955025,0.0001657344,0.000487951,0.00001501326,0.00002129747,0.00002113065,0.00003138798,0.9396367,0.008070864,0.0493638,0.001254574,0.0002360607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02157065,0.00003533197,0.9770817,0.0000862938,0.0002860799,0.0004827639,0.0001100775,0.0001342374,0.0002129214],"genre_scores_gemma":[0.1504334,0.000001632798,0.8478223,0.001042989,0.00001304829,0.00002959242,0.000643139,0.00001130494,0.000002586796],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8819871,"threshold_uncertainty_score":0.7316023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2621981149","doi":"10.1002/minf.201700022","title":"Non a Priori Automatic Discovery of 3D Chemical Patterns: Application to Mutagenicity","year":2017,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"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":"European Regional Development Fund; Région Normandie","keywords":"Cheminformatics; A priori and a posteriori; Computer science; Relation (database); Set (abstract data type); Feature (linguistics); Property (philosophy); Function (biology); Fragment (logic); Data mining; Biological system; Theoretical computer science; Algorithm; Chemistry; Computational chemistry; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01040611623854909,"gpt":0.291363309884864,"spread":0.2809571936463149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003996658,0.0001481892,0.0002250958,0.00009792166,0.0001007577,0.0003730492,0.001610881,0.00005786348,0.000001420401],"category_scores_gemma":[0.0002091589,0.0001455379,0.00008714476,0.0001353342,0.00004303946,0.00121691,0.0009199969,0.00009928895,0.00003636546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006291422,"about_ca_system_score_gemma":0.0001008464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002731365,"about_ca_topic_score_gemma":0.000001411413,"domain_scores_codex":[0.998569,0.0000270511,0.0005347406,0.0001564707,0.0005076074,0.0002051791],"domain_scores_gemma":[0.9979346,0.00006564146,0.0004303091,0.001378065,0.0001083024,0.00008309604],"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":[0.00003684926,0.0005800451,0.00443033,0.001989457,0.0002360988,0.00003840765,0.01734622,0.1125017,0.1316745,0.07615142,0.0003136008,0.6547013],"study_design_scores_gemma":[0.0002568916,0.00003714965,0.01103868,0.00006928621,0.00001234335,0.00000904965,0.00002761554,0.9005623,0.08565643,0.0020341,0.00009125844,0.0002048619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4618256,0.000002026432,0.5373017,0.00009883908,0.00006036484,0.0002217752,0.000004925422,0.00002770099,0.0004571199],"genre_scores_gemma":[0.7350508,7.192964e-7,0.2646234,0.0002640127,0.00001291417,0.00002839972,0.00000637246,0.000006559328,0.000006814726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7880606,"threshold_uncertainty_score":0.5934862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947303722","doi":"10.1002/minf.201900024","title":"Molecular Modelling of Potential Candidates for the Treatment of Depression","year":2019,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Pharmacophore; Quantitative structure–activity relationship; Computational biology; Serotonin transporter; Docking (animal); Mode of action; Isoquinoline; Chemistry; Pharmacology; Serotonin; Stereochemistry; Biology; Medicine; Receptor; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01543643617665239,"gpt":0.2676626665438475,"spread":0.2522262303671951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001705753,0.00009864452,0.0001651509,0.00006811896,0.00003067109,0.00003209207,0.0004175569,0.00003338167,0.000001776361],"category_scores_gemma":[0.0000121287,0.00006772693,0.0001432054,0.0001451852,0.0000238262,0.0001821127,0.00008240034,0.00002726471,0.000002843625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002330837,"about_ca_system_score_gemma":0.00006848206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001591691,"about_ca_topic_score_gemma":1.969733e-7,"domain_scores_codex":[0.9991056,0.00003182638,0.0003695473,0.0000804989,0.0002851324,0.0001273662],"domain_scores_gemma":[0.9990085,0.0001778971,0.0002152339,0.0004508233,0.0001217204,0.00002583506],"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":[0.00001207135,0.00004243887,0.00003425615,0.00005258775,0.00004724387,6.698494e-7,0.0008945244,0.9767762,0.003230251,0.009178157,0.000004581697,0.00972696],"study_design_scores_gemma":[0.0003674659,0.000122986,0.00002916845,0.00001662581,0.00002082698,0.000002583072,0.00004034757,0.8464956,0.1499612,0.002658407,0.0002236398,0.0000612172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3475242,0.0001925898,0.6517237,0.00002811967,0.00008688006,0.0002953888,0.000006140647,0.000008288908,0.0001347534],"genre_scores_gemma":[0.780273,0.00001998567,0.2196304,0.00003960737,0.000003974134,0.00001366553,0.00000721774,0.000005179018,0.000006975075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4327488,"threshold_uncertainty_score":0.2761824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409979195","doi":"10.1002/minf.202500018","title":"Deep Modeling of Gain‐of‐Function Mutations on Androgen Receptor","year":2025,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Prostate Cancer Treatment and Research","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":"Androgen receptor; Prostate cancer; Mutant; Computational biology; Mutation; Antiandrogens; Function (biology); Computer science; Biology; Bioinformatics; Genetics; Gene; Cancer","retraction":null,"screen_n_in":null,"score":{"opus":0.01792586232352345,"gpt":0.3033978119549671,"spread":0.2854719496314437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007990647,0.00005829668,0.0001327668,0.0001741542,0.00002752227,0.000004443957,0.00003737575,0.00004463895,0.00001930426],"category_scores_gemma":[0.00005255835,0.00004678368,0.00005922648,0.0002330514,0.00003164629,0.00004151403,0.00001770866,0.00007232737,0.000008966092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004537977,"about_ca_system_score_gemma":0.0001105956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005626049,"about_ca_topic_score_gemma":4.575649e-7,"domain_scores_codex":[0.9993981,0.000009519084,0.000275802,0.00003728114,0.0001867941,0.00009255965],"domain_scores_gemma":[0.9995746,0.0000178688,0.00005512303,0.0001538462,0.0001670726,0.00003148907],"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":[0.00471086,0.001849027,0.007437673,0.009288666,0.003638462,0.000038041,0.01895609,0.6455329,0.1075084,0.04168015,0.002673503,0.1566862],"study_design_scores_gemma":[0.002809781,0.0006735027,0.0001015844,0.0004744197,0.0002247765,0.000002460865,0.00176437,0.7551043,0.2366405,0.001245849,0.0008627499,0.000095667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7745622,0.0004383453,0.1974779,0.0002470492,0.00009192393,0.0004908585,0.00001006022,0.00002393134,0.02665776],"genre_scores_gemma":[0.9962957,0.00006607378,0.003158038,0.0001688832,0.000004807958,0.0000148248,0.0001006373,0.00000501627,0.0001860453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2217335,"threshold_uncertainty_score":0.1907783,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408701827","doi":"10.1002/minf.70029","title":"The Use of DeepQSAR Models for the Discovery of Peptides With Enhanced Antimicrobial and Antibiofilm Potential","year":2025,"lang":"en","type":"preprint","venue":"Molecular Informatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Antimicrobial; Antimicrobial peptides; Chemistry; Biochemical engineering; Nanotechnology; Computational biology; Microbiology; Biology; Materials science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01057461734984583,"gpt":0.2379863335103369,"spread":0.2274117161604911,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002977226,0.0003009273,0.0003455472,0.00005991853,0.0001573169,0.0001700755,0.0005451588,0.0002774048,2.403169e-7],"category_scores_gemma":[0.0001970534,0.0001795879,0.0002033487,0.00007436312,0.0004124668,0.00002481087,0.0009339858,0.0002883888,1.209034e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008915586,"about_ca_system_score_gemma":0.0002375768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002708617,"about_ca_topic_score_gemma":0.00001398254,"domain_scores_codex":[0.9985258,0.00004703815,0.0007915526,0.0001484961,0.0002372255,0.0002498854],"domain_scores_gemma":[0.9978071,0.0001188083,0.0008362742,0.0008889413,0.0003197023,0.00002911761],"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":[0.0006611763,0.00005773888,0.00008977929,0.003340505,0.001128112,8.807418e-7,0.001097437,0.8896707,0.09721723,0.001712593,0.001270763,0.003753124],"study_design_scores_gemma":[0.001054785,0.0003352752,0.00008182585,0.0005268531,0.0004867997,0.00002208596,0.0003959559,0.4015478,0.591944,0.0002614058,0.002858115,0.0004851189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3641914,0.0002499727,0.6340546,0.00007530281,0.0001203129,0.000808574,0.0003142355,0.00000659554,0.0001790298],"genre_scores_gemma":[0.9296734,0.001153336,0.06820277,0.0002684279,0.00003333937,0.00003286256,0.0003722411,0.00002587151,0.0002377845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5658518,"threshold_uncertainty_score":0.7323382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}