{"id":"W2609462956","doi":"10.1021/acs.jcim.7b00137","title":"Best Practices of Computer-Aided Drug Discovery: Lessons Learned from the Development of a Preclinical Candidate for Prostate Cancer with a New Mechanism of Action","year":2017,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada; Movember Foundation; U.S. Department of Defense","keywords":"Drug discovery; Computer science; Computational biology; Construct (python library); Mechanism (biology); Class (philosophy); Process (computing); Drug development; Small molecule; Computer-aided; Data science; Drug; Biochemical engineering; Bioinformatics; Chemistry; Pharmacology; Artificial intelligence; Engineering; Medicine; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.01969781,0.001338483,0.001032415,0.003018074,0.001815135,0.008977937,0.004095031,0.003192617,0.001935322],"category_scores_gemma":[0.02648516,0.0007132371,0.0007515151,0.003351347,0.01206136,0.00682744,0.003394192,0.006934536,0.001334614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004899348,"about_ca_system_score_gemma":0.00812575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008466945,"about_ca_topic_score_gemma":0.00840143,"domain_scores_codex":[0.9889652,0.004813673,0.0007290727,0.0009323675,0.004166344,0.0003933425],"domain_scores_gemma":[0.9795907,0.01084132,0.0008528506,0.004323251,0.003479529,0.0009123323],"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":[0.0001192943,0.0004080874,0.003008323,0.002105752,0.0001317868,0.0002346496,0.001497374,0.03869995,0.001376864,0.2851202,0.02832763,0.6389701],"study_design_scores_gemma":[0.0001338345,0.0002895145,0.001134853,0.003208505,0.00007417783,0.0003025628,0.001043538,0.04139199,0.003867929,0.669614,0.2787817,0.0001576086],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02075648,0.1973217,0.4916766,0.2107828,0.002105125,0.0004294722,0.000466398,0.001656806,0.07480472],"genre_scores_gemma":[0.1993273,0.1785237,0.6043183,0.009350045,0.001572224,0.0004578154,0.0005315414,0.0003889867,0.005530217],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01969781,"threshold_uncertainty_score":0.1041732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2073617976209536,"score_gpt":0.4345723715585672,"score_spread":0.2272105739376137,"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."}}