{"meta":{"query_hash":"92f54b72ab7b","filters":{"venue":"Molecular Informatics"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/92f54b72ab7b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Molecular+Informatics"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1242311728463903,"score_gpt":0.35289098644224953,"score_spread":0.22865981359585924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1899644141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29107702,0.000028707009,0.70803785,0.00015986824,0.00016477481,0.000108862005,0.000047407757,0.00006760285,0.00030792464],"genre_scores_gemma":[0.26649347,0.0000030073145,0.7314016,0.0017383188,0.000044025273,0.0000030537597,0.00030069228,0.000012063372,0.000003733977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986936,0.00014379495,0.0003400674,0.00018134539,0.00045694338,0.00018428548],"domain_scores_gemma":[0.99856675,0.00003512827,0.0001317385,0.0008578171,0.0002440302,0.0001645223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007028318,0.00013347167,0.000135312,0.0001061778,0.00006500066,0.00033827082,0.0006871906,0.000057447367,0.000001082505],"category_scores_gemma":[0.00018483131,0.00012877864,0.000017088701,0.00029089896,0.00004421029,0.0028976887,0.000930203,0.00012240879,0.0000074477834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045407705,0.00024294182,0.0010323519,0.0002532612,0.00028485368,0.00027793305,0.038067788,0.67904425,0.0029044752,0.023482947,0.00860625,0.24575754],"study_design_scores_gemma":[0.00028775918,0.000052931042,0.0005562938,0.000015555997,0.000015230754,0.00009468554,0.00024219122,0.9908257,0.0006582327,0.005897702,0.0012097353,0.00014398599],"about_ca_topic_score_codex":0.000022038106,"about_ca_topic_score_gemma":9.540042e-7,"teacher_disagreement_score":0.31178144,"about_ca_system_score_codex":0.00004992128,"about_ca_system_score_gemma":0.00020035646,"threshold_uncertainty_score":0.5251441},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Group (periodic table); Computer science; Data mining; Chemistry; Organic chemistry","score_opus":0.04836593607333022,"score_gpt":0.3458207124614303,"score_spread":0.2974547763881001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980840780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021570647,0.00003533197,0.97708166,0.000086293796,0.00028607986,0.0004827639,0.000110077504,0.00013423739,0.00021292135],"genre_scores_gemma":[0.15043342,0.0000016327976,0.8478223,0.0010429887,0.000013048289,0.000029592424,0.000643139,0.0000113049355,0.000002586796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983164,0.00018052555,0.0005183457,0.00027324678,0.000401124,0.00031033828],"domain_scores_gemma":[0.99765944,0.0002240806,0.00024763073,0.0014748649,0.000258335,0.00013562186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014155757,0.00018270603,0.00022003247,0.000119072385,0.00012264597,0.00011714368,0.00159715,0.00007386776,0.0000069595553],"category_scores_gemma":[0.00026378426,0.00017940743,0.000055336735,0.00027824813,0.000030634714,0.0023803771,0.0006099426,0.00010822741,0.00002324557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006900952,0.00024079665,0.000012371257,0.00006502434,0.00008332882,0.000016261425,0.0011413473,0.05764957,0.0024941922,0.7394705,0.00061536685,0.19814226],"study_design_scores_gemma":[0.0006955025,0.0001657344,0.00048795095,0.0000150132555,0.000021297466,0.000021130654,0.00003138798,0.9396367,0.008070864,0.0493638,0.0012545738,0.00023606072],"about_ca_topic_score_codex":0.000018368299,"about_ca_topic_score_gemma":0.0000035820526,"teacher_disagreement_score":0.8819871,"about_ca_system_score_codex":0.00004611455,"about_ca_system_score_gemma":0.00010474104,"threshold_uncertainty_score":0.73160225},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.013410427002871003,"score_gpt":0.21194755187406325,"score_spread":0.19853712487119224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983545523","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96729743,0.000022381297,0.0299699,0.0000043893756,0.00003135002,0.000055456178,0.00044347745,0.000027405105,0.0021482082],"genre_scores_gemma":[0.99689144,0.0000015444908,0.0028124454,0.00002845212,0.000010124337,0.0000045595684,0.0001985249,0.000018088114,0.000034848395],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984535,0.000007398757,0.0009243756,0.000098893885,0.00034912495,0.0001666824],"domain_scores_gemma":[0.9986389,0.000040625302,0.00063675013,0.00047847687,0.00012876818,0.00007642271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119367214,0.00017659625,0.00024709693,0.00006361167,0.000034113396,0.000015587208,0.0002594773,0.00017852767,0.0002628539],"category_scores_gemma":[0.00014827287,0.0001831478,0.00013996284,0.0001585391,0.00012869107,0.00014444845,0.000049453683,0.00013629552,0.0000016632408],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039052462,0.000106976746,0.00019293748,0.000371137,0.00005001136,0.0000015105119,0.0009805667,0.00028552458,0.997052,0.00006236489,0.00006121297,0.0007967003],"study_design_scores_gemma":[0.00055164384,0.000014461833,0.000021912887,0.000075088385,0.00006579189,0.0000030300794,0.0007383916,0.009465583,0.98879075,0.00001807419,0.00008259508,0.00017268701],"about_ca_topic_score_codex":0.000018463086,"about_ca_topic_score_gemma":4.930646e-7,"teacher_disagreement_score":0.029593982,"about_ca_system_score_codex":0.000021774269,"about_ca_system_score_gemma":0.000045552093,"threshold_uncertainty_score":0.746855},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.009911711928669237,"score_gpt":0.2481507745470005,"score_spread":0.23823906261833125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990193701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26996577,0.00007403017,0.729455,0.000042377174,0.00004216785,0.00016211436,0.0000013787169,0.000023966428,0.00023323286],"genre_scores_gemma":[0.65444183,0.000001989741,0.34548545,0.00005150874,0.0000021550863,0.0000056478048,0.0000026946889,0.000005072803,0.0000036311478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820447,0.00018166454,0.0009641939,0.0000973595,0.00042731428,0.00012502674],"domain_scores_gemma":[0.99850994,0.00018199823,0.00067286205,0.00042773748,0.00016632918,0.0000411033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012682581,0.0001139167,0.00029414133,0.00020703033,0.00004359613,0.00009584871,0.00041674773,0.00003869369,3.6257268e-7],"category_scores_gemma":[0.0003273236,0.00011416148,0.00006353008,0.0003361766,0.00004827348,0.000686323,0.000271155,0.00006543199,0.0000017443916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005628169,0.000032366806,0.00006286053,0.026549526,0.00015144041,0.0000037768846,0.011851304,0.26896527,0.09168188,0.59271944,0.0000049238884,0.00797156],"study_design_scores_gemma":[0.00018143517,0.00003994994,0.00062359177,0.0014918428,0.00002615886,0.000035826775,0.00054530764,0.88938475,0.08514877,0.022347668,0.000008352369,0.00016637979],"about_ca_topic_score_codex":0.0000041254234,"about_ca_topic_score_gemma":1.6021711e-7,"teacher_disagreement_score":0.62041944,"about_ca_system_score_codex":0.000011270778,"about_ca_system_score_gemma":0.000026254842,"threshold_uncertainty_score":0.46553698},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.025776361414791102,"score_gpt":0.27292270232969645,"score_spread":0.24714634091490534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003032055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026137039,0.000046043206,0.9647795,0.000106109015,0.0000590269,0.0002131912,7.194152e-7,0.00015164519,0.008506736],"genre_scores_gemma":[0.21531911,0.000003381364,0.7842712,0.00036713618,0.0000039464353,0.000014698043,0.0000033079466,0.0000060699153,0.000011160955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989918,0.00013854289,0.00035630938,0.00014185568,0.00015069147,0.00022080049],"domain_scores_gemma":[0.99912876,0.00007135588,0.00017714675,0.0004504251,0.00006159528,0.00011071363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089268404,0.00014632566,0.0001640559,0.00008579562,0.00013085072,0.000129752,0.00037772363,0.000067940906,0.000012956627],"category_scores_gemma":[0.00008991372,0.00012838539,0.00005065193,0.0003043938,0.00006720973,0.00054795545,0.00022922628,0.00015633598,0.000026594955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012126793,0.00010295012,0.00091852515,0.0002688615,0.00009476967,0.000013543221,0.20968293,0.0052225743,0.010561397,0.26081154,0.0001354556,0.5121753],"study_design_scores_gemma":[0.00025023782,0.000033491568,0.0017764991,0.000014858428,0.0000030844728,0.000024749372,0.0019050491,0.95032305,0.006139279,0.033925038,0.005384224,0.00022045313],"about_ca_topic_score_codex":0.0000052538912,"about_ca_topic_score_gemma":4.181509e-7,"teacher_disagreement_score":0.9451005,"about_ca_system_score_codex":0.000028136104,"about_ca_system_score_gemma":0.00003089468,"threshold_uncertainty_score":0.52354044},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.037541515635923485,"score_gpt":0.2965459023265248,"score_spread":0.2590043866906013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008947010","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1592683,0.00012360832,0.83982444,0.00008908925,0.00024026626,0.00018640442,0.0000034092259,0.00010717207,0.0001573176],"genre_scores_gemma":[0.36830276,0.0000029892046,0.6313574,0.00021941835,0.00005009977,0.00002409404,0.000017438717,0.000013158157,0.000012699544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849385,0.000038879727,0.00049619924,0.00011761194,0.00040655382,0.0004469311],"domain_scores_gemma":[0.9990334,0.00012491642,0.00025937601,0.00029779217,0.000119401164,0.0001651412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000668073,0.00017405071,0.00018801019,0.00009963492,0.00010636245,0.0001503308,0.0005042905,0.00007552464,0.0000013587089],"category_scores_gemma":[0.00013991432,0.0001698489,0.00013806015,0.00024810692,0.000029913823,0.00096882466,0.0002471734,0.00019363534,0.0000094784755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008297542,0.000084658284,0.0009927864,0.00014473655,0.000067631634,0.0000053731223,0.00934972,0.93655956,0.00090554013,0.03953344,0.00019008204,0.012158202],"study_design_scores_gemma":[0.00018669988,0.00001462484,0.00006497659,0.000023061299,0.0000113835495,0.000021217482,0.00033055554,0.98408437,0.011432799,0.00194134,0.0016685447,0.00022044496],"about_ca_topic_score_codex":0.0000029676937,"about_ca_topic_score_gemma":5.252805e-8,"teacher_disagreement_score":0.20903446,"about_ca_system_score_codex":0.00007092285,"about_ca_system_score_gemma":0.000059193848,"threshold_uncertainty_score":0.69262373},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.005950242800431988,"score_gpt":0.2494548033599986,"score_spread":0.2435045605595666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015042232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97132087,0.000027488806,0.026363812,0.00032383096,0.000096191565,0.00030748994,0.0000033155236,0.000011453222,0.0015455651],"genre_scores_gemma":[0.9833565,0.0000036210758,0.015255095,0.0009313322,0.000050671813,0.00009259227,0.00006628069,0.000018561605,0.00022535503],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992541,0.000029573046,0.0001786347,0.00014661449,0.00017077927,0.00022030795],"domain_scores_gemma":[0.9994059,0.0000030032663,0.00006950384,0.00036075097,0.000049362898,0.000111445566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013073406,0.0001501084,0.000111961,0.00008241815,0.00003679562,0.00008476366,0.00019922262,0.00013037928,0.000010063214],"category_scores_gemma":[0.000017052427,0.00012404853,0.000041797208,0.00013870234,0.00003375493,0.0000093258095,0.000073447205,0.00013755771,0.00001304848],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007128476,0.000019027742,0.0005859902,0.000016968344,0.000012441547,0.0000027015176,0.0002493247,0.00006982083,0.99459237,0.000056378052,0.0009543731,0.003369343],"study_design_scores_gemma":[0.00064482243,0.00023503324,0.0004900473,0.000011540949,0.0000054688808,0.000009464521,0.00018487591,0.000052846866,0.9195868,0.0000063861253,0.078604504,0.00016822015],"about_ca_topic_score_codex":0.000005128811,"about_ca_topic_score_gemma":0.000024945522,"teacher_disagreement_score":0.07765013,"about_ca_system_score_codex":0.000013900554,"about_ca_system_score_gemma":0.000060611037,"threshold_uncertainty_score":0.5058552},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.028061353100305983,"score_gpt":0.2972882026075814,"score_spread":0.2692268495072754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032729355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890746,0.000004576249,0.0008528043,0.001322595,0.000014288636,0.00022246646,0.00008401105,0.00001581443,0.008408838],"genre_scores_gemma":[0.99585944,8.0449485e-7,0.0032768378,0.000513701,0.000023484528,0.00005721705,0.00016933485,0.000008183861,0.000090996364],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910563,0.000006360512,0.00041030964,0.000093245355,0.0002458966,0.00013855884],"domain_scores_gemma":[0.99838805,0.000037662998,0.00017163699,0.0013333762,0.00003753704,0.00003176264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023611706,0.00009659898,0.000095407515,0.000016527967,0.00007145051,0.000031228497,0.0011429631,0.00010137292,0.000045107143],"category_scores_gemma":[0.00035290507,0.00006807483,0.000033273158,0.000232577,0.00007660242,0.00009546138,0.00023345619,0.00037149445,0.000007830799],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003886539,0.00003828963,0.000082795625,0.00010145284,0.0000049305777,4.7911584e-7,0.001687096,0.00003667155,0.99657786,0.00045358736,0.00045595306,0.00055702013],"study_design_scores_gemma":[0.00017100626,0.0000026424334,0.00006982914,0.000045036293,0.0000113751,0.000007096577,0.0006141944,0.0013699948,0.98038435,0.00010756467,0.017126331,0.000090558366],"about_ca_topic_score_codex":0.000015419004,"about_ca_topic_score_gemma":0.000027027621,"teacher_disagreement_score":0.016670378,"about_ca_system_score_codex":0.000023152226,"about_ca_system_score_gemma":0.00005866213,"threshold_uncertainty_score":0.2776011},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Quantitative structure–activity relationship; Computer science; Aggregate (composite); Data mining; Machine learning; Nanotechnology; Materials science","score_opus":0.00911041723449239,"score_gpt":0.25838406969099165,"score_spread":0.24927365245649927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059197104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40522143,0.00006341441,0.59320676,0.000037139376,0.00007832801,0.00014587311,0.000029467572,0.00005576839,0.001161836],"genre_scores_gemma":[0.8551501,0.0000031025934,0.14467666,0.000101095946,0.000007457256,0.000014743278,0.000030887735,0.000007786655,0.000008135519],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983266,0.00015228394,0.00044407355,0.00013519972,0.0006346623,0.000307152],"domain_scores_gemma":[0.99878013,0.00008145829,0.00030838116,0.0005431049,0.00016593638,0.000120989906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070221425,0.00017300548,0.00030747778,0.00028126794,0.000053385247,0.00006802918,0.0004587673,0.00007809842,0.000007945536],"category_scores_gemma":[0.00010119215,0.00017427806,0.00021624679,0.0014915123,0.000051820418,0.0013724974,0.00019914223,0.00013920349,0.000012130383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007285102,0.0019217456,0.1144869,0.0005802133,0.0055144294,0.000017921528,0.026550509,0.488684,0.17550181,0.16567047,0.0020640262,0.0189351],"study_design_scores_gemma":[0.00036307942,0.0000686722,0.0482285,0.0000117078525,0.00024588054,0.0000068438885,0.00015155092,0.68882304,0.25902838,0.0025786697,0.0002210653,0.00027263822],"about_ca_topic_score_codex":0.000015346086,"about_ca_topic_score_gemma":2.3732792e-7,"teacher_disagreement_score":0.4499287,"about_ca_system_score_codex":0.000088032655,"about_ca_system_score_gemma":0.00006075217,"threshold_uncertainty_score":0.7106853},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.010784107179727472,"score_gpt":0.26918250934824844,"score_spread":0.25839840216852095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061937956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14648823,0.000056487464,0.85089344,0.00023961205,0.00010196457,0.0017259088,0.00003137747,0.000103038285,0.00035994637],"genre_scores_gemma":[0.18192966,0.0000039809424,0.8170596,0.00036262086,0.000023549053,0.00053377927,0.000044728997,0.000017054423,0.000025052916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862003,0.000033287266,0.0004464249,0.00023216524,0.0003137506,0.0003543403],"domain_scores_gemma":[0.9987488,0.00025773185,0.00013807799,0.00029966992,0.0004370732,0.00011864933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040632428,0.00018423697,0.00019999388,0.00013291957,0.00016230965,0.0003112101,0.00039971835,0.00007496328,0.0000025518889],"category_scores_gemma":[0.00020590138,0.00018369388,0.000090484784,0.00023312715,0.000054407497,0.001205322,0.0002460473,0.00009101204,0.000008719035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017076205,0.00028654234,0.00058462913,0.002051648,0.00048060413,0.000005242537,0.012903845,0.41456297,0.14995286,0.20634235,0.002202678,0.21045588],"study_design_scores_gemma":[0.0008399282,0.00017752708,0.00058967614,0.000040477113,0.000009939086,0.000013108703,0.00012159451,0.90571016,0.055721525,0.036053102,0.00051915814,0.00020379393],"about_ca_topic_score_codex":0.0000030655085,"about_ca_topic_score_gemma":1.8601285e-7,"teacher_disagreement_score":0.49114722,"about_ca_system_score_codex":0.00007830945,"about_ca_system_score_gemma":0.000103662416,"threshold_uncertainty_score":0.74908185},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011373145632268525,"score_gpt":0.23896628912515772,"score_spread":0.2275931434928892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066256098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46291104,0.000005019072,0.53605825,0.00002611831,0.000026847876,0.000084364445,0.00000890612,0.00002371264,0.00085576787],"genre_scores_gemma":[0.5375397,0.0000014925834,0.46236238,0.00008112104,0.0000038085136,0.000003125644,0.0000039929337,0.0000033627327,9.72393e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890924,0.00004043408,0.00035834385,0.000119342985,0.00040035608,0.00017227053],"domain_scores_gemma":[0.9991078,0.00007525791,0.00026888656,0.00030511548,0.00016115938,0.00008178928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042691987,0.00013196394,0.00014876592,0.00007643249,0.000081572245,0.0000885027,0.00021488997,0.00006532222,8.4687935e-7],"category_scores_gemma":[0.00010353629,0.00011337527,0.000039858474,0.00031095228,0.00010138235,0.0006226736,0.00031717762,0.00018711167,0.0000017967575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018617762,0.000040614883,0.00029981986,0.000091068585,0.00002093349,0.000008175574,0.0019230777,0.81167495,0.0020828538,0.059357762,0.000016983815,0.124465145],"study_design_scores_gemma":[0.0003447373,0.00007140246,0.0002648837,0.0000351427,0.000012641658,0.00007327799,0.000068216876,0.97064203,0.005648838,0.022691283,0.000015574842,0.00013199265],"about_ca_topic_score_codex":0.000017784698,"about_ca_topic_score_gemma":0.0000144520545,"teacher_disagreement_score":0.15896706,"about_ca_system_score_codex":0.000024107318,"about_ca_system_score_gemma":0.000116646355,"threshold_uncertainty_score":0.4623309},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03700972570440528,"score_gpt":0.3195687943401153,"score_spread":0.28255906863571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155678816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05716354,0.000040343526,0.9360439,0.0016902817,0.00014177368,0.00054714456,0.0000042963234,0.00017193113,0.0041967654],"genre_scores_gemma":[0.34903735,0.0000015339357,0.64873457,0.0019261938,0.000014686128,0.00017597085,0.000037238024,0.000012388392,0.000060061368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829876,0.00009813843,0.0006561792,0.00018119632,0.00045473373,0.00031096642],"domain_scores_gemma":[0.99821925,0.00021087195,0.00026925583,0.000712928,0.00047061156,0.00011705972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007883534,0.00016833894,0.00018336145,0.0001569647,0.00009306062,0.0006101131,0.00084897556,0.00007214978,0.00000784227],"category_scores_gemma":[0.00061771105,0.00017153064,0.00013614721,0.00036744474,0.000031824995,0.001586848,0.00032234174,0.00010536842,0.00010416722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039663623,0.00008322694,0.000059966307,0.00024461036,0.000087571076,0.0000018399103,0.0025490818,0.063574634,0.0055615352,0.6745962,0.002881731,0.25035566],"study_design_scores_gemma":[0.00038365542,0.00004148744,0.0018655513,0.000015814403,0.000008552439,0.000008599369,0.00012263707,0.8927083,0.020642368,0.07665672,0.0071855276,0.00036075787],"about_ca_topic_score_codex":0.00001821292,"about_ca_topic_score_gemma":3.8541074e-7,"teacher_disagreement_score":0.8291337,"about_ca_system_score_codex":0.00007427893,"about_ca_system_score_gemma":0.00011191673,"threshold_uncertainty_score":0.69948167},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.010406116238549094,"score_gpt":0.291363309884864,"score_spread":0.2809571936463149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621981149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46182558,0.0000020264322,0.53730166,0.00009883908,0.000060364837,0.00022177516,0.0000049254218,0.000027700986,0.00045711992],"genre_scores_gemma":[0.7350508,7.192964e-7,0.2646234,0.00026401266,0.000012914166,0.000028399718,0.00000637246,0.000006559328,0.0000068147265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856895,0.000027051095,0.00053474057,0.00015647073,0.0005076074,0.00020517912],"domain_scores_gemma":[0.9979346,0.00006564146,0.0004303091,0.0013780646,0.00010830244,0.00008309604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039966582,0.00014818924,0.0002250958,0.000097921664,0.000100757694,0.00037304923,0.0016108811,0.00005786348,0.0000014204005],"category_scores_gemma":[0.00020915888,0.00014553788,0.000087144756,0.00013533421,0.00004303946,0.0012169098,0.0009199969,0.000099288955,0.000036365458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003684926,0.0005800451,0.0044303304,0.0019894573,0.00023609881,0.000038407652,0.017346224,0.11250174,0.13167454,0.07615142,0.00031360076,0.6547013],"study_design_scores_gemma":[0.00025689157,0.00003714965,0.011038677,0.00006928621,0.000012343348,0.00000904965,0.000027615537,0.90056235,0.085656434,0.0020341002,0.00009125844,0.00020486195],"about_ca_topic_score_codex":0.000027313647,"about_ca_topic_score_gemma":0.0000014114135,"teacher_disagreement_score":0.7880606,"about_ca_system_score_codex":0.00006291422,"about_ca_system_score_gemma":0.00010084636,"threshold_uncertainty_score":0.59348625},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.051230954180605616,"score_gpt":0.35990716918224513,"score_spread":0.3086762150016395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799656935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027813345,0.406438,0.5916602,0.000015111039,0.00022156285,0.0011691995,0.000105830586,0.000049506976,0.0003127978],"genre_scores_gemma":[0.000002493261,0.28918746,0.7101366,0.00007493651,0.000024378232,0.00035795005,0.00011277524,0.000031312567,0.00007212159],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965186,0.000039423176,0.0021544583,0.00020270259,0.0006856956,0.00039910665],"domain_scores_gemma":[0.9966357,0.00033100566,0.0016909116,0.000763967,0.00048179532,0.00009666725],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009064805,0.0004877223,0.0011745074,0.0003143228,0.00013303533,0.00019345887,0.0016563638,0.00015154501,0.0000026269142],"category_scores_gemma":[0.00011658492,0.00040164348,0.0004080754,0.0005700721,0.00009857118,0.00051565224,0.0006512172,0.00018841213,0.000010462441],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059697595,0.000070748254,8.8310195e-8,0.03794447,0.0004729285,7.317905e-7,0.01864938,0.0010298259,0.000005725501,0.0056529418,0.0007816024,0.9353856],"study_design_scores_gemma":[0.00033296764,0.000030674215,4.2921266e-7,0.0062108836,0.00013683784,0.000006214091,0.00011331603,0.049464624,0.0004548074,0.00029349574,0.94242835,0.0005274189],"about_ca_topic_score_codex":0.0000017460554,"about_ca_topic_score_gemma":0.0000022973923,"teacher_disagreement_score":0.94164675,"about_ca_system_score_codex":0.00023530985,"about_ca_system_score_gemma":0.0020924902,"threshold_uncertainty_score":0.99984354},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.005338842299840955,"score_gpt":0.30577566503761855,"score_spread":0.3004368227377776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919214297","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47678614,0.00000565195,0.52295494,0.000021921838,0.000011353705,0.0001690394,0.0000014578624,0.0000078446765,0.000041661464],"genre_scores_gemma":[0.47156832,5.0359216e-7,0.5283828,0.000035336907,0.0000015672678,0.0000035653165,0.0000042839974,0.0000028289558,8.110105e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988896,0.000095528616,0.00050748436,0.00011351226,0.0003013103,0.000092538074],"domain_scores_gemma":[0.9989836,0.00013099774,0.00037176735,0.00024000018,0.00023142023,0.000042197094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005872184,0.0000884994,0.0002103651,0.00012573556,0.000018180643,0.00002314905,0.00024284766,0.000036205744,0.0000031200784],"category_scores_gemma":[0.0000918268,0.00008530278,0.000030028643,0.0003743414,0.000015831027,0.0003502533,0.000248085,0.000051066672,0.0000020324662],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012846964,0.000049970826,0.0004879208,0.0002597401,0.000024487972,1.0871646e-7,0.0063466337,0.07967437,0.86552644,0.012796771,0.0000014763059,0.034819227],"study_design_scores_gemma":[0.00011669863,0.000080178426,0.0009601449,0.000029129646,0.0000051905745,0.0000028679904,0.00006572004,0.5099705,0.48697394,0.0017417062,0.000008071335,0.00004583537],"about_ca_topic_score_codex":0.0000060270936,"about_ca_topic_score_gemma":4.836418e-7,"teacher_disagreement_score":0.43029612,"about_ca_system_score_codex":0.000028170363,"about_ca_system_score_gemma":0.000038376173,"threshold_uncertainty_score":0.34785464},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.016193422162381347,"score_gpt":0.3002332653078655,"score_spread":0.28403984314548414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944666543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47980982,0.00009500939,0.51929116,0.000064284824,0.0001137569,0.00055493833,0.000011790006,0.000022873553,0.00003640125],"genre_scores_gemma":[0.8899561,0.0000037348736,0.109488405,0.00043558105,0.0000034672005,0.00004401007,0.00004486348,0.000021550255,0.0000022878826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972426,0.00017188223,0.0010225449,0.0003331256,0.00075858395,0.00047123356],"domain_scores_gemma":[0.99834913,0.00029438786,0.00043277032,0.0006132953,0.00015446503,0.00015596912],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044829817,0.00030195012,0.0005572033,0.00037961328,0.000056563844,0.0001270397,0.0007059388,0.00012226799,0.000004406191],"category_scores_gemma":[0.00017669454,0.00030741587,0.0001648716,0.0007133543,0.00006734371,0.00036626152,0.00061795296,0.00018427327,0.0000053003455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014237042,0.00094341295,0.001927773,0.0008169432,0.0001750826,0.00003455207,0.008438454,0.36460447,0.21634594,0.3508798,0.00009207945,0.055599146],"study_design_scores_gemma":[0.0013818393,0.0004059055,0.0003569614,0.00007556949,0.000020816153,0.0000066139587,0.00058214134,0.8920299,0.09769723,0.006750945,0.0003508756,0.00034120682],"about_ca_topic_score_codex":0.00003616711,"about_ca_topic_score_gemma":0.000001529587,"teacher_disagreement_score":0.5274254,"about_ca_system_score_codex":0.00012010031,"about_ca_system_score_gemma":0.00013698603,"threshold_uncertainty_score":0.9999378},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01543643617665239,"score_gpt":0.2676626665438475,"score_spread":0.2522262303671951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947303722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34752417,0.0001925898,0.6517237,0.000028119672,0.000086880056,0.00029538877,0.0000061406467,0.000008288908,0.00013475343],"genre_scores_gemma":[0.78027296,0.000019985666,0.21963042,0.00003960737,0.0000039741344,0.000013665534,0.0000072177404,0.000005179018,0.0000069750754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910563,0.000031826385,0.00036954734,0.0000804989,0.0002851324,0.00012736616],"domain_scores_gemma":[0.9990085,0.00017789709,0.00021523389,0.00045082328,0.00012172039,0.000025835063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017057528,0.000098644516,0.00016515094,0.000068118956,0.000030671086,0.000032092066,0.00041755688,0.00003338167,0.0000017763608],"category_scores_gemma":[0.000012128699,0.000067726935,0.00014320537,0.00014518516,0.000023826204,0.00018211274,0.000082400344,0.00002726471,0.0000028436252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012071355,0.00004243887,0.000034256154,0.00005258775,0.000047243866,6.698494e-7,0.0008945244,0.97677624,0.0032302511,0.009178157,0.000004581697,0.00972696],"study_design_scores_gemma":[0.00036746587,0.00012298599,0.00002916845,0.000016625807,0.000020826985,0.000002583072,0.000040347568,0.84649557,0.14996119,0.0026584072,0.00022363977,0.0000612172],"about_ca_topic_score_codex":0.000015916912,"about_ca_topic_score_gemma":1.969733e-7,"teacher_disagreement_score":0.43274882,"about_ca_system_score_codex":0.000023308374,"about_ca_system_score_gemma":0.000068482055,"threshold_uncertainty_score":0.2761824},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.018396756260697183,"score_gpt":0.2593566582448479,"score_spread":0.2409599019841507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981596486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33151814,0.000040531766,0.6665926,0.000045046294,0.000044213877,0.000485229,0.0000041213175,0.000026963926,0.0012431124],"genre_scores_gemma":[0.517075,3.4884425e-7,0.48254296,0.00028948297,0.000004994125,0.000041345498,0.00003197055,0.000007994157,0.0000059395943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853617,0.00013848081,0.0005073545,0.0002520332,0.00026599423,0.00029994926],"domain_scores_gemma":[0.9990765,0.00024001594,0.0001364936,0.00045365616,0.00003253848,0.000060804938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010083696,0.0001918594,0.0002601093,0.00025955215,0.000035802346,0.00033756092,0.00057153165,0.000059528556,5.600531e-7],"category_scores_gemma":[0.000075880365,0.00018186303,0.000058028967,0.00044510904,0.00003409443,0.0017229203,0.00015549158,0.00018882236,0.000002002348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018422066,0.00014759735,0.0023210086,0.00030777248,0.0000072313182,0.0000016642628,0.004366676,0.8857165,0.00064970594,0.09876638,0.000008687391,0.0076883617],"study_design_scores_gemma":[0.00071804266,0.000047486967,0.00080849446,0.00003347735,0.0000023834816,0.000002520504,0.0007727628,0.9888556,0.0026619025,0.0058215945,0.000048932638,0.00022682988],"about_ca_topic_score_codex":0.000019500201,"about_ca_topic_score_gemma":0.000007002995,"teacher_disagreement_score":0.18555681,"about_ca_system_score_codex":0.00006824152,"about_ca_system_score_gemma":0.00013715384,"threshold_uncertainty_score":0.7416159},"labels":[],"label_agreement":null},{"id":"W3009970748","doi":"10.1002/minf.202000028","title":"Rapid Identification of Potential Inhibitors of SARS‐CoV‐2 Main Protease by Deep Docking of 1.3 Billion Compounds","year":2020,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":518,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01770774515941695,"score_gpt":0.2675397446277249,"score_spread":0.24983199946830795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009970748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33542627,0.000058947095,0.6639325,0.0001617696,0.000069842026,0.00022830433,0.000016264199,0.000018537643,0.00008758295],"genre_scores_gemma":[0.91119814,0.0000054634734,0.08859154,0.00015194161,0.000009323682,0.000005830558,0.000029348004,0.00000775156,6.8253877e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777734,0.00015133835,0.0011597065,0.00012288273,0.00065036485,0.00013834513],"domain_scores_gemma":[0.9984233,0.000063430125,0.0008915254,0.00034257417,0.00022482204,0.00005438801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000548538,0.00012732101,0.00025607503,0.00015788712,0.000031757012,0.00004750022,0.00059066276,0.00005630055,0.0000015521784],"category_scores_gemma":[0.00018105986,0.00013091798,0.00012830397,0.0006829659,0.00008296314,0.0005344343,0.00028025534,0.00009846952,0.000002931578],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027498096,0.00011616537,0.00004649526,0.00072675315,0.000060114533,0.0000035160542,0.0046765883,0.12258906,0.8478622,0.00595331,0.00041291027,0.017525412],"study_design_scores_gemma":[0.00020926504,0.000059851132,0.00007171182,0.000029921683,0.000009883341,0.0000029771547,0.00007806553,0.48126966,0.5172444,0.0008678485,0.00008169526,0.00007475061],"about_ca_topic_score_codex":0.000009069945,"about_ca_topic_score_gemma":1.547731e-7,"teacher_disagreement_score":0.57577187,"about_ca_system_score_codex":0.000026461483,"about_ca_system_score_gemma":0.000099122284,"threshold_uncertainty_score":0.533868},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.02120448430788708,"score_gpt":0.3007711008899546,"score_spread":0.27956661658206755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037787710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6733504,0.000030320154,0.32294935,0.00006135764,0.00001254293,0.00051046564,0.000004257813,0.000033848366,0.0030474744],"genre_scores_gemma":[0.9486059,0.0000026239723,0.049884044,0.0007838116,0.000036255566,0.000029811677,0.0005861628,0.000032819808,0.000038563758],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838984,0.00008886103,0.00061719643,0.00019247147,0.0003327182,0.00037892922],"domain_scores_gemma":[0.99931616,0.000004847772,0.00020222514,0.0002748138,0.000063526015,0.00013842569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029851095,0.00022596706,0.00023164596,0.00012015055,0.000086458225,0.00006326551,0.0002883544,0.0001357568,0.0000059565227],"category_scores_gemma":[0.00022967682,0.00024213945,0.000084631974,0.0004651608,0.000041355455,0.00002048597,0.00012065695,0.00031684394,0.00001798744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006707812,0.00003906804,0.0015075698,0.00023999679,0.000027696986,0.000005851279,0.009521412,0.4426733,0.5452502,0.00021636025,0.0000331042,0.000418402],"study_design_scores_gemma":[0.0013500411,0.00049335166,0.0020688619,0.00005008744,0.000037541708,0.00003415267,0.005199778,0.6635243,0.32233885,0.000013975771,0.004122808,0.0007662158],"about_ca_topic_score_codex":0.00004652137,"about_ca_topic_score_gemma":0.000006649594,"teacher_disagreement_score":0.27525553,"about_ca_system_score_codex":0.000036916626,"about_ca_system_score_gemma":0.0000666849,"threshold_uncertainty_score":0.987416},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.013212614403985358,"score_gpt":0.2909295781902771,"score_spread":0.27771696378629174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206247747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98299676,0.00014899517,0.013969829,0.00069270784,0.00009025085,0.0007778752,0.0011848971,0.00005708182,0.000081572834],"genre_scores_gemma":[0.9880461,0.0000108920985,0.006624827,0.0029179193,0.000008733502,0.00042007767,0.0019008481,0.000015654343,0.000054922966],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991899,0.00002793949,0.00033682978,0.00009538321,0.00018546857,0.00016445291],"domain_scores_gemma":[0.999458,0.000042325697,0.00008505015,0.00021111843,0.000037527647,0.00016594089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006869038,0.0001072209,0.00016730171,0.00013733732,0.00015832792,0.000021809274,0.000042395244,0.000014675205,0.000021459695],"category_scores_gemma":[0.000024779209,0.00010530912,0.000050484887,0.000095468386,0.00001898235,0.00020030714,0.000029530418,0.00014210661,0.0000015669393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004662042,0.0073907236,0.5113311,0.0024579638,0.00061584025,0.00018860195,0.07016734,0.30362067,0.0021103243,0.0006014291,0.021039331,0.07581467],"study_design_scores_gemma":[0.0029382284,0.00013357007,0.009365642,0.00004132088,0.00015291115,0.0000046742302,0.0016466482,0.98397285,0.0004044596,0.00034658873,0.00090465834,0.00008846031],"about_ca_topic_score_codex":0.00025121093,"about_ca_topic_score_gemma":0.00011350195,"teacher_disagreement_score":0.68035215,"about_ca_system_score_codex":0.000120413475,"about_ca_system_score_gemma":0.00013836446,"threshold_uncertainty_score":0.4294381},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08329791264474877,"score_gpt":0.3406507462846687,"score_spread":0.2573528336399199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220753843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893162,0.00014297012,0.006214928,0.00078258035,0.00013163683,0.00093014346,0.00063367706,0.000032556476,0.001815297],"genre_scores_gemma":[0.9757973,0.000008294314,0.020899687,0.0010069183,0.000020558968,0.00013893632,0.00096226105,0.000012601368,0.0011534448],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989302,0.000064440035,0.0003747457,0.00008723947,0.00031660605,0.00022678007],"domain_scores_gemma":[0.99952084,0.00010252091,0.000077031444,0.00014216913,0.00009065749,0.000066808854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003106398,0.000102352766,0.00017109876,0.00018191671,0.00018428924,0.00001606632,0.0000994714,0.000054051103,0.00012729014],"category_scores_gemma":[0.00031774933,0.0000702498,0.000075043456,0.00029198313,0.00005243915,0.00008132739,0.00009941314,0.0003398008,0.000010134128],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011216945,0.0011093707,0.5493319,0.004219989,0.00083398627,0.00033197203,0.0495617,0.03314192,0.094665155,0.16497992,0.07301317,0.01759394],"study_design_scores_gemma":[0.008103685,0.008115471,0.0965722,0.00017222317,0.0001760066,0.0005243369,0.0165949,0.43531495,0.009090535,0.01850537,0.40596864,0.0008616752],"about_ca_topic_score_codex":0.000033653134,"about_ca_topic_score_gemma":0.000007393693,"teacher_disagreement_score":0.4527597,"about_ca_system_score_codex":0.00012790713,"about_ca_system_score_gemma":0.00011646584,"threshold_uncertainty_score":0.28647035},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05288652475164202,"score_gpt":0.337118736541096,"score_spread":0.28423221178945396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313816625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35878152,0.000005770657,0.639679,0.00015885389,0.000058723697,0.00016184062,0.000008611248,0.00009646696,0.0010491967],"genre_scores_gemma":[0.8969265,0.0000019446045,0.102536805,0.00044393362,0.000007416606,0.000017235232,0.000055318233,0.00000803681,0.0000027950268],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852335,0.00010190615,0.0005572874,0.00012542921,0.00042591267,0.0002661353],"domain_scores_gemma":[0.9991214,0.00029048577,0.00012598466,0.0003075422,0.000065964916,0.00008862424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005813729,0.00015492347,0.00022207515,0.0006010355,0.00010057981,0.000194942,0.00037016146,0.00006449034,0.0000013408886],"category_scores_gemma":[0.00014124776,0.00015992436,0.00004575588,0.00092461455,0.000032177413,0.0007481369,0.00020661321,0.00020683861,0.000050824485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003312613,0.000015548865,0.00066043145,0.000035555713,0.000009164802,0.0000030676795,0.0033553317,0.97743636,0.000010553385,0.0061887624,0.00003926079,0.012242658],"study_design_scores_gemma":[0.00036026997,0.00004647159,0.0025954277,0.00005656252,0.000006040687,0.0000010691311,0.0003993179,0.99364287,0.0005473159,0.0019849523,0.00018579261,0.0001739246],"about_ca_topic_score_codex":0.000015230632,"about_ca_topic_score_gemma":0.00000211924,"teacher_disagreement_score":0.538145,"about_ca_system_score_codex":0.00008399111,"about_ca_system_score_gemma":0.00011508097,"threshold_uncertainty_score":0.6521526},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04133740417371557,"score_gpt":0.3232444522595325,"score_spread":0.28190704808581696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376636211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98482347,0.0000366314,0.0138315465,0.000049292044,0.00013889122,0.00042496622,0.00008698259,0.00008924104,0.00051898713],"genre_scores_gemma":[0.99098617,0.000035472716,0.007934826,0.00008069023,0.0000580633,0.000012102114,0.00067543663,0.000040739087,0.00017651908],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99827355,0.000028012995,0.0005290399,0.00011909469,0.0006087825,0.0004415479],"domain_scores_gemma":[0.9992027,0.000027931997,0.00016330194,0.00029631876,0.00012233606,0.00018741043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005669258,0.00016437212,0.0002845143,0.0004336893,0.00014010142,0.000047673966,0.00012396468,0.00011448332,0.000026945156],"category_scores_gemma":[0.000065206994,0.00014415802,0.00011759855,0.0008162015,0.00008077099,0.00030844324,0.000070031674,0.0001802696,0.000040488758],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121514386,0.00012569678,0.0020334052,0.00023346137,0.00019824604,0.000049863396,0.0043078526,0.00029061013,0.99051166,0.00015867426,0.00023028244,0.0017387457],"study_design_scores_gemma":[0.0039886246,0.000359453,0.00025472284,0.0003929258,0.00008990113,0.000042581516,0.010372184,0.0078087174,0.97519934,0.00002472397,0.0012420956,0.00022475237],"about_ca_topic_score_codex":0.00001469858,"about_ca_topic_score_gemma":0.0000012532427,"teacher_disagreement_score":0.01531233,"about_ca_system_score_codex":0.00009010464,"about_ca_system_score_gemma":0.0001532535,"threshold_uncertainty_score":0.58785933},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.010574617349845829,"score_gpt":0.2379863335103369,"score_spread":0.22741171616049108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408701827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36419138,0.00024997274,0.6340546,0.000075302814,0.000120312914,0.00080857397,0.00031423548,0.00000659554,0.00017902978],"genre_scores_gemma":[0.9296734,0.0011533361,0.06820277,0.0002684279,0.000033339373,0.000032862557,0.0003722411,0.000025871514,0.00023778448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985258,0.000047038146,0.0007915526,0.0001484961,0.00023722545,0.00024988543],"domain_scores_gemma":[0.99780715,0.000118808275,0.0008362742,0.00088894134,0.0003197023,0.00002911761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002977226,0.00030092726,0.00034554725,0.000059918533,0.00015731693,0.00017007552,0.0005451588,0.00027740485,2.4031687e-7],"category_scores_gemma":[0.00019705344,0.0001795879,0.00020334874,0.00007436312,0.00041246685,0.00002481087,0.0009339858,0.00028838884,1.2090344e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006611763,0.000057738882,0.000089779285,0.0033405053,0.0011281121,8.807418e-7,0.001097437,0.88967067,0.09721723,0.0017125926,0.0012707625,0.0037531236],"study_design_scores_gemma":[0.0010547846,0.00033527522,0.00008182585,0.00052685314,0.00048679975,0.000022085964,0.0003959559,0.40154782,0.591944,0.00026140577,0.0028581151,0.0004851189],"about_ca_topic_score_codex":0.000027086175,"about_ca_topic_score_gemma":0.000013982539,"teacher_disagreement_score":0.5658518,"about_ca_system_score_codex":0.0000089155865,"about_ca_system_score_gemma":0.00023757678,"threshold_uncertainty_score":0.73233825},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01792586232352345,"score_gpt":0.3033978119549671,"score_spread":0.2854719496314437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409979195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7745622,0.00043834533,0.1974779,0.00024704917,0.00009192393,0.00049085845,0.000010060217,0.000023931345,0.026657764],"genre_scores_gemma":[0.9962957,0.00006607378,0.0031580378,0.00016888323,0.000004807958,0.000014824804,0.0001006373,0.00000501627,0.00018604529],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939805,0.000009519084,0.000275802,0.000037281145,0.0001867941,0.00009255965],"domain_scores_gemma":[0.9995746,0.0000178688,0.000055123026,0.00015384622,0.00016707263,0.000031489068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079906466,0.000058296682,0.00013276676,0.00017415422,0.000027522272,0.000004443957,0.00003737575,0.000044638953,0.000019304258],"category_scores_gemma":[0.00005255835,0.000046783684,0.00005922648,0.00023305137,0.000031646287,0.000041514028,0.000017708664,0.00007232737,0.000008966092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047108596,0.0018490265,0.007437673,0.009288666,0.0036384622,0.000038041,0.018956088,0.6455329,0.107508406,0.041680146,0.0026735028,0.15668625],"study_design_scores_gemma":[0.0028097806,0.0006735027,0.000101584425,0.00047441968,0.00022477652,0.0000024608653,0.0017643697,0.7551043,0.23664051,0.0012458492,0.00086274993,0.000095667005],"about_ca_topic_score_codex":0.0000056260487,"about_ca_topic_score_gemma":4.575649e-7,"teacher_disagreement_score":0.22173353,"about_ca_system_score_codex":0.000045379773,"about_ca_system_score_gemma":0.0001105956,"threshold_uncertainty_score":0.19077833},"labels":[],"label_agreement":null}]}