{"id":"W4403833137","doi":"10.1186/s13321-024-00911-3","title":"Towards the prediction of drug solubility in binary solvent mixtures at various temperatures using machine learning","year":2024,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Structural Genomics Consortium; Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Leslie Dan Faculty of Pharmacy, University of Toronto; Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Canada First Research Excellence Fund; University of Toronto","keywords":"Solubility; Machine learning; Computer science; Solvent; Binary number; Gradient boosting; Hildebrand solubility parameter; Artificial intelligence; Biochemical engineering; Materials science; Chemistry; Mathematics; Organic chemistry; Random forest","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":[0.001802128,0.0001119952,0.000212106,0.00018873,0.00007581795,0.0001313053,0.000468483,0.00004139772,0.000006177066],"category_scores_gemma":[0.0002436747,0.00007257728,0.0001428114,0.0004088272,0.00005020416,0.0007977117,0.0002900008,0.0005078211,6.785696e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002325078,"about_ca_system_score_gemma":0.0003117709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000164202,"about_ca_topic_score_gemma":0.000002210686,"domain_scores_codex":[0.9983459,0.00006971622,0.0008030002,0.00007656767,0.0005675156,0.0001373331],"domain_scores_gemma":[0.9988397,0.0004446089,0.0003604913,0.0001678881,0.000142755,0.00004459389],"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":[0.0001014497,0.0002129993,0.002796482,0.001314332,0.0002235005,0.00009735425,0.05277989,0.8863504,0.03148442,0.002239624,0.002223572,0.020176],"study_design_scores_gemma":[0.0001698997,0.00005418792,0.001252471,0.0002602127,0.00002029644,0.0003426882,0.0001325688,0.9589044,0.03593063,0.002293118,0.0005752585,0.00006430125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9189506,0.002080644,0.07719579,0.0005121582,0.000781315,0.0001045829,0.000007833819,0.0000242078,0.0003428962],"genre_scores_gemma":[0.9620016,0.00007326659,0.03774768,0.00005012747,0.00008259818,8.234315e-7,0.000002517581,0.000005858928,0.00003559805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07255398,"threshold_uncertainty_score":0.2959616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02363015548913669,"score_gpt":0.2887526564082504,"score_spread":0.2651225009191137,"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."}}