{"id":"W4327555752","doi":"10.1021/acs.jcim.2c01373","title":"Using Machine Learning To Predict Partition Coefficient (Log<i>P</i>) and Distribution Coefficient (Log<i>D</i>) with Molecular Descriptors and Liquid Chromatography Retention Time","year":2023,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Innovation and Technology Fund; Hong Kong Government; Innovation and Technology Commission","keywords":"Partition coefficient; Chemistry; Analyte; Chromatography; Retention time; Octanol; Distribution (mathematics); Partition (number theory); Analytical Chemistry (journal); Mathematics","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":[0.0008075847,0.000118181,0.0001712009,0.0002376623,0.0001191113,0.000211849,0.00009114094,0.00005049069,7.0765e-7],"category_scores_gemma":[0.0001192082,0.0001007716,0.00004060738,0.0004738235,0.0000399897,0.001024182,0.0001341962,0.0001682421,0.000001023211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004839872,"about_ca_system_score_gemma":0.00004666927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004981037,"about_ca_topic_score_gemma":1.074971e-7,"domain_scores_codex":[0.9987903,0.00006481836,0.0004650439,0.0001285437,0.0003842407,0.0001670436],"domain_scores_gemma":[0.9992254,0.00005453774,0.0002330774,0.00006830857,0.0002517249,0.0001669202],"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":[0.0001091927,0.00001976388,0.00007779522,0.00004280924,0.00002044197,0.000003023154,0.0007304528,0.9623997,0.03396996,0.0006471823,0.00002005206,0.001959633],"study_design_scores_gemma":[0.0004450336,0.0002018813,0.00005212732,0.0001419448,0.00002342442,0.0001380292,0.0000672555,0.9900092,0.008477606,0.000217196,0.0001125208,0.0001137925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.503248,0.00005553827,0.4964318,0.0001343933,0.00003066651,0.00006468505,0.000003829645,0.00002600732,0.000005006784],"genre_scores_gemma":[0.978666,0.00003994815,0.02109606,0.0001281971,0.00001784029,0.000002287367,0.00004393711,0.000005013504,6.988275e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.475418,"threshold_uncertainty_score":0.4109346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02306168832052962,"score_gpt":0.2655526638927191,"score_spread":0.2424909755721895,"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."}}