{"id":"W4280575072","doi":"10.21203/rs.3.rs-1630646/v1","title":"ToxTree: Descriptor-based machine learning models to predict hERG and Nav1.5 cardiotoxicity","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"hERG; Artificial intelligence; Machine learning; Computer science; Test set; Support vector machine; Classifier (UML); Cardiotoxicity; PubChem; Binary classification; Medicine; Potassium channel; Computational biology; Internal medicine; 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":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006584418,0.0003996804,0.0005551476,0.0009574637,0.0007518012,0.0008544488,0.002352099,0.0001977542,0.00008671027],"category_scores_gemma":[0.0006482785,0.0004279002,0.0002367908,0.00125905,0.0001274648,0.0003752339,0.01162328,0.0033502,0.00001519027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000869528,"about_ca_system_score_gemma":0.001423986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00131431,"about_ca_topic_score_gemma":0.00006342617,"domain_scores_codex":[0.9894464,0.004394899,0.0004351922,0.00167397,0.003157169,0.000892388],"domain_scores_gemma":[0.9957125,0.001674238,0.0001081882,0.001394986,0.0005638706,0.0005461996],"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":[0.0000598997,0.00008791307,0.001762115,0.0003688043,0.00005225763,0.0001149441,0.0009164233,0.9754408,0.00006812869,0.006012228,0.000676094,0.01444036],"study_design_scores_gemma":[0.0003011331,0.0003250664,0.002875242,0.0002335392,0.000006678962,0.000009073869,0.0000991726,0.970839,0.0001653308,0.01582026,0.008921343,0.0004041607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1067404,0.001830773,0.8849224,0.001721243,0.0005015649,0.001666162,0.0002185667,0.0003723862,0.002026554],"genre_scores_gemma":[0.8875173,0.00008951789,0.1103998,0.000166916,0.0002250172,0.0007435298,0.0001435649,0.00007061294,0.0006437757],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7807769,"threshold_uncertainty_score":0.9998173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1663221990308993,"score_gpt":0.4052413420650591,"score_spread":0.2389191430341599,"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."}}