When Does Machine Learning Add Value over Theory? Predicting API Solubility in Binary Mixtures with COSMO-RS and...

Predicting the solubility of active pharmaceutical ingredients (APIs) in binary aqueous-organic mixtures is critical for formulation design, yet remains challenging. Physics-based models such as COSMO-RS provide a solid theoretical foundation but often struggle with non-ideal mixing behavior in complex systems. This study asks a practical question: when does machine learning actually add value beyond established theory? We compared COSMO-RS with DOOIT2 (Dual-Objective Optimization with Iterative Feature Pruning), a hybrid COSMO-RS/machine-learning correction workflow, across two complementary datasets: 85 structurally diverse APIs and related formulation-relevant compounds (10,140 data points) and 37 acid-centered solutes (6030 data points). The datasets also incorporate newly measured solubilities of lidocaine, benzocaine, and vanillic acid in aqueous 4-formylmorpholine mixtures. DOOIT2 employs rigorous API-out Structured Group K-Fold validation with fold-specific ensemble models to ensure realistic assessment of generalization to unseen compounds. The obtained results are dataset-dependent. For the homogeneous acid series, COSMO-RS already delivers strong predictive performance (RMSD = 0.321, R² = 0.925), and DOOIT2 brings no meaningful improvement (RMSD = 0.310, R² = 0.923). In contrast, for the diverse API set, DOOIT2 reduces RMSD from 0.686 to 0.527 and increases R² from 0.829 to 0.849. Residual analysis indicates that prediction uncertainty is driven primarily by the low-solubility region rather than by a simple monotonic dependence on molecular weight alone. These findings delineate the practical boundaries of machine-learning assistance in solubility prediction and offer clear guidance for formulation scientists.