Solvation Free Energies from Neural Thermodynamic Integration
arXiv:2410.15815 · doi:10.1063/5.0251736
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.
References in corpus (10)
- Best Practices for Alchemical Free Energy Calculations
- Targeted free energy estimation via learned mappings
- Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
- Skipping the Replica Exchange Ladder with Normalizing Flows
- Hydration free energies from kernel-based machine learning: Compound-database bias
- Improving and generalizing flow-based generative models with minibatch optimal transport
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Building Normalizing Flows with Stochastic Interpolants
- Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
- Learning Interpolations between Boltzmann Densities