{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001843259,0.001717257,0.001430933,0.001394329,0.0005812811,0.001520682,0.001398871,0.001875093,0.001659736],"category_scores_gemma":[0.005566147,0.0005502919,0.002219617,0.001199731,0.0006378077,0.002026286,0.0009275594,0.002600895,0.00196428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001582299,"about_ca_system_score_gemma":0.002032416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009693057,"about_ca_topic_score_gemma":0.01008953,"domain_scores_codex":[0.9992692,0.0001829782,0.00004903042,0.0002534745,0.0001726888,0.00007254461],"domain_scores_gemma":[0.9982168,0.0008668766,0.0001955914,0.0002010631,0.0004177339,0.0001018624],"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":[0.0007572005,0.0009045053,0.01946422,0.001065614,0.000288231,0.0002695307,0.0001137963,0.8213681,0.03126818,0.003083542,0.02191627,0.09950076],"study_design_scores_gemma":[0.00003413651,0.00007636083,0.001129058,0.00002702987,0.00002366182,0.00003199473,0.00001601998,0.9806395,0.01347934,0.002013151,0.002499873,0.00002989503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5188651,0.006939537,0.4144322,0.002714504,0.0006464557,0.000409386,0.02937364,0.0210055,0.005613769],"genre_scores_gemma":[0.6893915,0.001885995,0.2666398,0.0008170599,0.0001980962,0.0004795945,0.0367824,0.0008540926,0.002951502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009693057,"threshold_uncertainty_score":0.01927328,"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."}}