{"id":"W2998862306","doi":"10.1101/2019.12.31.891812","title":"Crowdsourced mapping extends the target space of kinase inhibitors","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Chemistry; National Institutes of Health; Ministero dello Sviluppo Economico; Syöpäjärjestöt; University of Toronto; Genome Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo; Academy of Finland; Ontario Ministry of Economic Development and Innovation; Novartis Pharma; Nvidia; Wellcome Trust; Sigrid Juséliuksen Säätiö; Pfizer; National Science Foundation","keywords":"Kinome; Druggability; Kinase; Chemical space; Computational biology; Computer science; Boosting (machine learning); Benchmarking; Small molecule; Artificial intelligence; Machine learning; Biology; Drug discovery; Bioinformatics; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001526772,0.0006208022,0.0007129233,0.0003414104,0.0002177591,0.0004533361,0.002888398,0.0003124263,0.00001549831],"category_scores_gemma":[0.0007552736,0.0005659885,0.0003545324,0.001596021,0.0002170345,0.0003482513,0.003381279,0.001061345,0.0000385829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002094012,"about_ca_system_score_gemma":0.001080521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004469432,"about_ca_topic_score_gemma":2.968207e-7,"domain_scores_codex":[0.9956682,0.0006497663,0.0008290097,0.001363282,0.0009277869,0.0005618939],"domain_scores_gemma":[0.9955766,0.0004999573,0.0008566078,0.002209461,0.0005625243,0.000294801],"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":[0.00004322474,0.0003352377,0.002280147,0.001205977,0.0005169924,0.000222442,0.0004856123,0.05303821,0.8573518,0.08149712,0.002968281,0.00005492593],"study_design_scores_gemma":[0.0008185682,0.0001031536,0.08377175,0.0009284337,0.00009931203,7.952489e-8,0.00001923918,0.2271542,0.6659788,0.0006313468,0.01854089,0.00195415],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2364486,0.001365247,0.7530044,0.005093866,0.002502978,0.0008242299,0.0001048963,0.0006135256,0.00004231906],"genre_scores_gemma":[0.7930393,0.00002665129,0.2059754,0.0003281193,0.0004750113,0.00008056896,1.837215e-7,0.00007173313,0.000003082496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5565907,"threshold_uncertainty_score":0.9996791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0222420001847141,"score_gpt":0.2430124758618172,"score_spread":0.2207704756771031,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}