{"id":"W4401242507","doi":"10.1007/s11095-024-03742-x","title":"Machine Learning Prediction of On/Off Target-driven Clinical Adverse Events","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centennial College","funders":"","keywords":"Adverse effect; Computer science; Artificial intelligence; Medicine; Machine learning; Pharmacology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.007125237,0.0001281604,0.0002039328,0.0003876468,0.0001412953,0.00005003038,0.0008156771,0.00008378981,0.0001978068],"category_scores_gemma":[0.001950047,0.0001131901,0.0001746084,0.001134849,0.0001971419,0.0003890138,0.0007342981,0.001762962,0.0004559664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223865,"about_ca_system_score_gemma":0.0003486079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007180922,"about_ca_topic_score_gemma":2.976912e-7,"domain_scores_codex":[0.9943855,0.002410092,0.0004961782,0.0006259914,0.001606479,0.000475732],"domain_scores_gemma":[0.9933468,0.005759362,0.00003365727,0.0003140702,0.0002417076,0.0003044263],"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":[0.0004035503,0.001117992,0.02388799,0.0003630208,0.0002960773,0.0002609469,0.0005797787,0.207573,0.001633282,0.2713574,0.002474951,0.490052],"study_design_scores_gemma":[0.0003372784,0.0002653358,0.005195486,0.00008923865,0.000006766087,0.000006881859,0.000007070003,0.9200948,0.001007594,0.01007437,0.06283817,0.00007699302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2334043,0.00331481,0.7302397,0.008428143,0.003849981,0.001227781,0.0001071495,0.0007943165,0.01863382],"genre_scores_gemma":[0.9803406,0.000324279,0.01832173,0.000101678,0.0002799917,0.00002479661,0.00001337813,0.00001971638,0.0005738398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7469363,"threshold_uncertainty_score":0.7659292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3271439234270387,"score_gpt":0.5617736059562758,"score_spread":0.2346296825292371,"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."}}