{"id":"W4220847490","doi":"10.1186/s13321-022-00596-6","title":"Deep learning-driven prediction of drug mechanism of action from large-scale chemical-genetic interaction profiles","year":2022,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; Cystic Fibrosis Canada","keywords":"Computer science; Mechanism (biology); Scale (ratio); Action (physics); Drug discovery; Artificial intelligence; Machine learning; Data science; Bioinformatics; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005868317,0.0001013255,0.0002631477,0.0001911822,0.00006661474,0.00002648922,0.0004890787,0.0000370492,0.00005306969],"category_scores_gemma":[0.0001279623,0.000100663,0.0001490655,0.000288599,0.00002047692,0.0008276978,0.0002907481,0.0004054293,0.000001195454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001572337,"about_ca_system_score_gemma":0.0001121227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000380022,"about_ca_topic_score_gemma":3.165475e-7,"domain_scores_codex":[0.9980139,0.00007040756,0.0009569034,0.00008217533,0.0007580462,0.0001185661],"domain_scores_gemma":[0.9974812,0.0002789953,0.001720968,0.0001710642,0.0002922736,0.00005549136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002122896,0.0006808839,0.001045634,0.000410983,0.0002867892,0.000005706952,0.0455775,0.7097335,0.1858547,0.001676372,0.001052074,0.05346357],"study_design_scores_gemma":[0.0003937333,0.0001134989,0.0004357486,0.00004430801,0.00003082895,0.00006032553,0.002338144,0.717417,0.2757072,0.003058872,0.0003376279,0.00006268409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5121275,0.00002953786,0.4870487,0.00005136783,0.0004318518,0.00006753087,0.00001338361,0.00001224391,0.0002179025],"genre_scores_gemma":[0.8609643,0.00002257915,0.1388749,0.00001927712,0.00007202625,0.000004410352,0.0000161278,0.000006596944,0.00001974033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3488367,"threshold_uncertainty_score":0.4104919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01529976250053821,"score_gpt":0.2669032819701505,"score_spread":0.2516035194696122,"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."}}