{"id":"W3198806124","doi":"10.1021/acs.est.1c01418","title":"Novel Bayesian Method to Derive Final Adjusted Values of Physicochemical Properties: Application to 74 Compounds","year":2021,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; Trent University; Occupational Cancer Research Centre; Cancer Care Ontario; Environment and Climate Change Canada; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Sveriges Regering; University of Toronto","keywords":"In silico; Workflow; Bayesian probability; Computer science; Consistency (knowledge bases); Benchmark (surveying); Heteroscedasticity; Data mining; Bayes' theorem; Chemistry; Machine learning; Artificial intelligence; Database","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":[0.0004751314,0.0001644348,0.0002356409,0.0003826468,0.0001730725,0.00004973832,0.001574356,0.00007548874,0.000009642802],"category_scores_gemma":[0.0001000663,0.0001646156,0.00005220684,0.002297264,0.0005925685,0.0003431022,0.001763559,0.0001476195,0.00004429855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003297211,"about_ca_system_score_gemma":0.0001673455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001576941,"about_ca_topic_score_gemma":0.000002270832,"domain_scores_codex":[0.9977728,0.00006093486,0.000290321,0.0008955809,0.0006025222,0.0003778181],"domain_scores_gemma":[0.9989254,0.0000775556,0.00009515576,0.0007139223,0.00003977068,0.0001481811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005500001,0.0002016935,0.0001819382,0.0000040018,0.000004819766,0.00000185191,0.00035454,0.01140222,0.9181901,0.008425312,0.00001730959,0.06121066],"study_design_scores_gemma":[0.0001537748,0.0001147876,0.004944834,0.00001852389,0.000005027479,0.00006200771,0.000277336,0.08280829,0.9062779,0.004335105,0.0008087467,0.0001936497],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2523028,0.00003155973,0.7448436,0.002317172,0.00005675503,0.0002321486,0.000006119605,0.00007806006,0.0001317336],"genre_scores_gemma":[0.5564048,9.600559e-7,0.4432585,0.0002472773,0.00001132713,0.00004598328,0.000002000392,0.000005004988,0.00002417334],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3041019,"threshold_uncertainty_score":0.6712829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02082511378347706,"score_gpt":0.2891323448002796,"score_spread":0.2683072310168025,"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."}}