{"id":"W4296396772","doi":"10.3389/ftox.2022.981928","title":"Novel machine learning models to predict endocrine disruption activity for high-throughput chemical screening","year":2022,"lang":"en","type":"article","venue":"Frontiers in Toxicology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada","funders":"","keywords":"Tier 1 network; Prioritization; Androgen receptor; In silico; Computer science; Machine learning; Estrogen receptor; Estrogen; Computational model; Adverse Outcome Pathway; Drug discovery; Computational biology; Artificial intelligence; Bioinformatics; Biology; Medicine; Internal medicine; World Wide Web; Engineering; Process management; Endocrinology","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":[0.0007635741,0.0001724272,0.000327731,0.0003094052,0.0002246832,0.00004229501,0.0007499421,0.00005416453,0.00001177223],"category_scores_gemma":[0.0001931496,0.0002060238,0.00007892243,0.0005674367,0.00004188032,0.0004438953,0.001569482,0.0004576477,8.04925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004233883,"about_ca_system_score_gemma":0.00009840145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000646347,"about_ca_topic_score_gemma":0.000009721309,"domain_scores_codex":[0.9979579,0.0003288068,0.0002720671,0.0006686348,0.0003118204,0.0004607005],"domain_scores_gemma":[0.9990783,0.0003982972,0.0001145422,0.0002735659,0.00003949441,0.00009575352],"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":[0.0002121985,0.0002099632,0.0005348924,0.00001015037,0.00002515956,0.000008466151,0.0004291587,0.8963093,0.007545236,0.01200153,0.0009040824,0.08180992],"study_design_scores_gemma":[0.001082917,0.0003282866,0.001019659,0.000004273989,0.000006734001,0.00003184962,0.00004217946,0.970295,0.002308023,0.0227173,0.001962398,0.0002013776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09827827,0.00005570929,0.8976701,0.001897886,0.001354649,0.0005053281,0.00004991213,0.0001119247,0.00007616147],"genre_scores_gemma":[0.495403,0.000001594016,0.5039032,0.0002502797,0.00005923709,0.0002727322,0.00002609807,0.00001259389,0.00007126149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3971247,"threshold_uncertainty_score":0.8401406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0460003538887334,"score_gpt":0.3027725542937609,"score_spread":0.2567722004050275,"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."}}