Solvation Free Energies from Neural Thermodynamic Integration

TL;DR

This paper introduces a neural network-based method for calculating free-energy differences in molecular systems through thermodynamic integration, improving accuracy and efficiency in simulating solvation processes.

Contribution

The authors develop a neural potential that interpolates between Hamiltonians at the sample level, enabling precise free-energy calculations for complex molecular interactions.

Findings

Accurate free-energy estimates for Lennard-Jones and solvation systems

Neural thermodynamic integration matches benchmark results

Method effectively models molecular rotations and interactions

Abstract

We present a method for computing free-energy differences using thermodynamic integration with a neural network potential that interpolates between two target Hamiltonians. The interpolation is defined at the sample distribution level, and the neural network potential is optimized to match the corresponding equilibrium potential at every intermediate time-step. Once the interpolating potentials and samples are well-aligned, the free-energy difference can be estimated using (neural) thermodynamic integration. To target molecular systems, we simultaneously couple Lennard-Jones and electrostatic interactions and model the rigid-body rotation of molecules. We report accurate results for several benchmark systems: a Lennard-Jones particle in a Lennard-Jones fluid, as well as the insertion of both water and methane solutes in a water solvent at atomistic resolution using a simple three-body neural-network potential.