ConfSolv: Prediction of solute conformer free energies across a range of solvents

Abstract

Predicting Gibbs free energy of solution is key to understanding solvent effects on thermodynamics and reaction rates for kinetic modelling. Accurately computing solution free energies requires enumeration and evaluation of relevant solute conformers in solution. However, even after generation of relevant conformers, determining their free energy of solution requires an expensive workflow consisting of several ab initio computational chemistry calculations. To help address this challenge, we generate a large dataset of solution free energies for nearly 44000 solutes with almost 9 million conformers calculated in 41 different solvents using density functional theory and COSMO-RS and quantify the impact of solute conformers on the solution free energy. We then train a message passing neural network to predict the relative solution free energies of a set of solute conformers, enabling identification of a small subset of thermodynamically relevant conformers. The model offers substantial computational time savings with predictions usually substantially within 1 kcal/mol of the free energy of solution calculated using computational chemical methods.