{"id":"W4417050512","doi":"10.1016/j.ejpb.2025.114954","title":"From physics to prediction: genetic algorithm-optimized neural network using hansen solubility parameters for pharmaceutical solubility in neat and mixed solvents","year":2025,"lang":"en","type":"article","venue":"European Journal of Pharmaceutics and Biopharmaceutics","topic":"Crystallization and Solubility Studies","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Iran National Science Foundation","keywords":"Solubility; Naproxen; Artificial neural network; Solvent; Active ingredient; Hildebrand solubility parameter; Genetic algorithm; Dissolution","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007672036,0.0008444134,0.0005160885,0.0004825608,0.0002661308,0.0006490846,0.0005936847,0.0009111528,0.0008950172],"category_scores_gemma":[0.002283536,0.0003816301,0.0004428379,0.0003526339,0.0004360562,0.0007882408,0.0004234135,0.0008322163,0.0001409859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001047338,"about_ca_system_score_gemma":0.001267167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0143606,"about_ca_topic_score_gemma":0.01082384,"domain_scores_codex":[0.9998478,0.00005660145,0.000008162367,0.00003673228,0.00003025162,0.00002045319],"domain_scores_gemma":[0.9994457,0.0003887657,0.0000470825,0.00002024698,0.00008571086,0.00001254554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002264082,0.00001568664,0.0003756332,0.00001012557,0.000007710208,0.00001446309,0.000008203435,0.9930463,0.0004332676,0.00034597,0.0000855594,0.005634508],"study_design_scores_gemma":[0.000001635212,0.000005955055,0.0000350712,8.403602e-7,0.000001198112,8.840171e-7,0.0000012033,0.9996167,0.0001542914,0.0001635384,0.0000177741,8.84012e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5073336,0.0007741008,0.4827397,0.0008495683,0.00009101139,0.0001406902,0.0002252193,0.001258109,0.006587891],"genre_scores_gemma":[0.9269298,0.0001635798,0.07079137,0.000109411,0.00001796349,0.0001239234,0.0001467296,0.00004981105,0.001667331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0143606,"threshold_uncertainty_score":0.02855402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07832545389211763,"score_gpt":0.3517014501021655,"score_spread":0.2733759962100479,"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."}}