Solvation Free Energies from Neural Thermodynamic Integration
This work addresses the challenge of accurately predicting free-energy differences in molecular systems, which is crucial for computational chemistry and drug design, representing an incremental improvement with a novel hybrid approach.
The authors tackled the problem of computing solvation free energies by introducing a neural thermodynamic integration method that interpolates between Hamiltonians using a neural network potential, achieving accurate results for benchmark systems including water and methane solutes in water solvent.
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.