{"id":"W2563115000","doi":"10.1093/toxsci/kfw207","title":"How Adverse Outcome Pathways Can Aid the Development and Use of Computational Prediction Models for Regulatory Toxicology","year":2016,"lang":"en","type":"article","venue":"Toxicological Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Pacific Northwest National Laboratory; Technological University Dublin; Rijksinstituut voor Volksgezondheid en Milieu; U.S. Department of Energy; European Commission; National Institute of Environmental Health Sciences; University of Leeds; Universität des Saarlandes; Liverpool John Moores University; U.S. Army Corps of Engineers; University of Ottawa; Battelle; U.S. Environmental Protection Agency","keywords":"Adverse Outcome Pathway; Computer science; Risk analysis (engineering); Risk assessment; Inference; Outcome (game theory); Regulatory science; Computational model; Skin sensitization; Chemical toxicity; Drug development; Biochemical engineering; Data science; Management science; Computational biology; Artificial intelligence; Biology; Engineering; Medicine; Toxicity; Computer security; Pharmacology; Drug","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":[0.001382344,0.0001206617,0.000177722,0.000080885,0.0003518335,0.00009920648,0.0005817338,0.00007095072,0.000003835723],"category_scores_gemma":[0.0004410193,0.00005970183,0.00005444796,0.00026845,0.0007293224,0.0007656593,0.0003200036,0.00005032415,5.906314e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007807297,"about_ca_system_score_gemma":0.0002493345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001587042,"about_ca_topic_score_gemma":0.0000158967,"domain_scores_codex":[0.9983327,0.0002150117,0.0003217989,0.0004382508,0.0004311358,0.0002611299],"domain_scores_gemma":[0.9967852,0.002691099,0.0001754708,0.0001504672,0.000112685,0.00008510094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002427815,0.0001136338,0.005512823,0.00001119356,0.00001729591,0.000001417931,0.0005738968,0.1373014,0.001896351,0.7815524,0.0001349202,0.07286034],"study_design_scores_gemma":[0.0006379553,0.0006064289,0.2581762,0.00002042148,0.000008097817,0.00001671834,0.0001079277,0.4352159,0.001823047,0.3014404,0.001720708,0.0002262707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5041163,0.00001198442,0.4918795,0.00355046,0.0001307208,0.0002211888,0.0000156989,0.00003478425,0.00003933443],"genre_scores_gemma":[0.7617835,0.000001521612,0.2377855,0.0002959637,0.00001996111,0.00004632934,9.662768e-7,0.000002008078,0.00006431043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4801121,"threshold_uncertainty_score":0.2706055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1684858454864167,"score_gpt":0.3165441525820624,"score_spread":0.1480583070956457,"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."}}