{"id":"W4402350721","doi":"10.1039/d4dd00065j","title":"A machine learning approach for the prediction of aqueous solubility of pharmaceuticals: a comparative model and dataset analysis","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Solubility; Aqueous solution; Machine learning; Computer science; Artificial intelligence; Chemistry; Biochemical engineering; Engineering; Organic chemistry","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":[0.0004430778,0.0001157094,0.0002627553,0.0001305486,0.00005740093,0.0003412649,0.000304088,0.00002382693,7.143916e-7],"category_scores_gemma":[0.0001042391,0.00008074805,0.0001570895,0.0006086399,0.0001604256,0.00156526,0.0002974754,0.000113878,2.564954e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002292929,"about_ca_system_score_gemma":0.00008748395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001511948,"about_ca_topic_score_gemma":0.000001614057,"domain_scores_codex":[0.9988781,0.00007758424,0.0003046087,0.0003621017,0.0002544536,0.0001231362],"domain_scores_gemma":[0.9982727,0.001296707,0.00008137405,0.0002602506,0.00005290141,0.0000360567],"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":[0.00005117367,0.0001290995,0.0005270793,0.0001560778,0.0006017275,5.135819e-7,0.0007281153,0.9671263,0.0001184196,0.01991661,0.0001213376,0.01052358],"study_design_scores_gemma":[0.000126319,0.00004937382,0.00067779,0.00001068382,0.0001915361,0.000002948702,0.00005656976,0.9921827,0.0002779107,0.006172253,0.0001841661,0.00006777899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02947451,0.001317593,0.960968,0.00005698778,0.00003878484,0.0002605607,0.00756378,0.0000315447,0.0002882222],"genre_scores_gemma":[0.9867046,0.00002387932,0.01212805,0.00001555332,0.00001245221,0.00002750413,0.001043564,0.0000049989,0.00003942226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9572301,"threshold_uncertainty_score":0.329281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09472786522244901,"score_gpt":0.3669694291482491,"score_spread":0.2722415639258001,"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."}}