ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential

2026-06-23

AI Summary

This work addresses the limited applicability of existing implicit-solvent machine learning potentials, which are predominantly restricted to aqueous solutions and struggle to accurately describe solute interactions in non-aqueous solvents. The authors propose a solvent-conditioned implicit-solvent machine learning potential that incorporates solvent information via an attention mechanism and leverages a hybrid training strategy combining experimental and ab initio data. This approach achieves, for the first time, transferability across 66 organic solvents within a single model, enabling generalization to unseen solvents while maintaining interpretability. The method outperforms both classical explicit-solvent models and certain ab initio implicit-solvent approaches on multiple solvation free energy benchmarks, with predictions showing excellent agreement with NMR experimental data for γ-fluoroalcohols in chloroform.

Abstract

Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulations. However, existing models have largely focused on aqueous environments, overlooking the diverse and important roles of non-aqueous solvents in areas such as organic synthesis and battery technology. Here, we present ConSolv, a solvent-conditional MLP architecture that explicitly incorporates solvent effects on solute interactions through an attention-based solvent-embedding block. By combining experimental solvation free energy data with ab initio data, we train a single implicit solvent MLP that is transferable across 66 common organic solvents. ConSolv outperforms classical explicit solvent methods and selected ab initio implicit solvent approaches across multiple solvation free energy benchmarks, and demonstrates generalization to unseen solvents. Beyond solvation free energies, the model shows close agreement with experimental nuclear magnetic resonance (NMR) data for $γ$-fluorohydrin molecules in chloroform. ConSolv's architecture is readily extensible to broader chemical spaces and alternative training strategies, while its attention-based design supports explainable artificial intelligence (AI) analysis that can help elucidate complex, solvent-dependent molecular interactions.

Problem

• implicit solvent
• machine learning potential
• non-aqueous solvents
• solvation free energy
• molecular simulation

Innovation

• solvent-conditional MLP
• implicit solvent model
• attention-based embedding
• solvation free energy
• explainable AI