OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials

TL;DR

OpenMM 8 introduces support for machine learning potentials, enabling flexible, efficient molecular dynamics simulations with pretrained models, demonstrated on protein and chromophore systems, enhancing accuracy with minimal performance impact.

Contribution

The paper presents new features in OpenMM 8 that facilitate integration of machine learning potentials, including user-friendly interfaces and optimized CUDA kernels for faster simulations.

Findings

Supports arbitrary PyTorch models for force and energy calculations.

Enables modeling with pretrained potential functions.

Achieves significant speed improvements in simulations.

Abstract

Machine learning plays an important and growing role in molecular simulation. The newest version of the OpenMM molecular dynamics toolkit introduces new features to support the use of machine learning potentials. Arbitrary PyTorch models can be added to a simulation and used to compute forces and energy. A higher-level interface allows users to easily model their molecules of interest with general purpose, pretrained potential functions. A collection of optimized CUDA kernels and custom PyTorch operations greatly improves the speed of simulations. We demonstrate these features on simulations of cyclin-dependent kinase 8 (CDK8) and the green fluorescent protein (GFP) chromophore in water. Taken together, these features make it practical to use machine learning to improve the accuracy of simulations at only a modest increase in cost.