{"id":"W3196422877","doi":"10.1016/j.yrtph.2021.105029","title":"Species selection for nonclinical safety assessment of drug candidates: Examples of current industry practice","year":2021,"lang":"en","type":"article","venue":"Regulatory Toxicology and Pharmacology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Xenon Pharmaceuticals (Canada)","funders":"Roche","keywords":"Documentation; Process (computing); Drug development; Risk analysis (engineering); Risk assessment; Business; Selection (genetic algorithm); Similarity (geometry); Pharmaceutical industry; Best practice; Animal species; Drug; Computer science; Knowledge management; Biotechnology; Biology; Pharmacology; Political science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1196885,0.0008329155,0.000669133,0.003657239,0.003111925,0.004691828,0.002033557,0.002559008,0.008643864],"category_scores_gemma":[0.1378276,0.0004608132,0.0009604362,0.00477858,0.003595602,0.00532926,0.004968408,0.002432537,0.00303214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002918524,"about_ca_system_score_gemma":0.006291899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002015442,"about_ca_topic_score_gemma":0.003155764,"domain_scores_codex":[0.903402,0.06585687,0.007773579,0.003925679,0.01751198,0.001529878],"domain_scores_gemma":[0.7320815,0.1987079,0.01716512,0.01825438,0.030191,0.003600029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007473945,0.0008911508,0.03476961,0.006218213,0.0001228657,0.001749018,0.03986627,0.002457211,0.01700273,0.02332833,0.0318518,0.8409954],"study_design_scores_gemma":[0.0001412997,0.002497834,0.05277607,0.01043964,0.0001647129,0.005651795,0.05565367,0.00590044,0.01921754,0.03710372,0.8100018,0.0004515126],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3637347,0.03000797,0.3830948,0.09030902,0.001637192,0.005540366,0.002270754,0.002352356,0.1210529],"genre_scores_gemma":[0.5784975,0.02026359,0.3653911,0.01720239,0.0004460434,0.002514188,0.00186476,0.0008965306,0.01292389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1196885,"threshold_uncertainty_score":0.6329806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06230056510234336,"score_gpt":0.4375420190671659,"score_spread":0.3752414539648226,"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."}}