2026-10-09T08:38:23Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34021396 2026-09-29T05:33:00Z category_4 category_19 category_873 category_734 category_931 portal_87 item_type_3 month_year_09_2026

Benchmarking machine learning algorithms for solubility prediction of pharmaceuticals in ethanol Elaheh Rahimpour (16273199) Dmitriy M. Makarov (1600432) Emilya Balayeva (25135468) Tahir Suleymanov (25135471) Abolghasem Jouyban (578282) Biochemistry Pharmacology Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified Solubility prediction simulation model drugs ethanol machine learning <p>The solubility of pharmaceutical compounds in organic solvents is a key physicochemical property governing drug formulation, purification, and processing. In this study, the experimental mole fraction solubility data for drugs in ethanol at various temperatures are collected from the literature and refined based on low solubility values, inconsistencies in similar systems, prediction errors, and enthalpic analysis. A curated dataset comprising 784 experimental mole-fraction solubility measurements for 77 pharmaceutical compounds in ethanol over a range of temperatures is assembled to develop predictive mathematical models. Herein, the van’t Hoff equation is integrated with Abraham-Hansen solubility parameters and RDkit parameters to establish conventional linear correlation models. Moreover, six regression algorithms including multiple linear regression, support vector regression , random forest , LightGBM, CatBoost, and an artificial neural network are evaluated using three descriptor representations: Abraham-Hansen solvation descriptors, RDKit molecular descriptors, and a combined descriptor set obtained through feature selection. SHAP analysis is performed for both assessment of descriptor importance across the entire dataset and local interpretation of individual predictions. Finally, to investigate the robustness of the developed models, the cross-validation strategies are done and discussed.</p> 2026-09-29T05:33:00Z Dataset Dataset 10.6084/m9.figshare.34021396.v1 https://figshare.com/articles/dataset/Benchmarking_machine_learning_algorithms_for_solubility_prediction_of_pharmaceuticals_in_ethanol/34021396 CC BY 4.0