From physics to prediction: genetic algorithm-optimized neural network using hansen solubility parameters for pharmaceutical solubility in neat and mixed solvents.

Reliable prediction of active pharmaceutical ingredient (API) solubility in complex solvent systems remains challenging. Existing models often sacrifice generalizability for accuracy or have limited applicability due to implementation complexity. The current study presents a practical, streamlined modeling framework requiring only temperature, solvent composition, and Hansen solubility parameters (HSPs) - information that is simple and readily accessible. These parameters serve as inputs for an effective and easy-to-apply model: the multilayer perceptron artificial neural network (MLPANN). Beyond optimizing the network architecture with a genetic algorithm (GA), model accuracy is further supported by six input scenarios designed to explore alternative HSP formulations and dimensional reduction strategies. To ensure generality, the MLPANN was trained on 496 experimental solubility values of acetaminophen, diazepam, ibuprofen, lorazepam, and naproxen in both neat and binary solvent systems, including water, ethanol, isopropanol, dioxane, NMP, and propylene glycol. Two scenarios, using the optimized networks, achieved R2 values exceeding 0.99 across training, validation, and testing subsets. Graphical validation-an important aspect often overlooked in previous studies-demonstrated excellent predictive performance for unseen testing data of acetaminophen in isopropanol-water and naproxen in ethanol-water mixtures.