Graph Neural Networks Accelerated Molecular Dynamics

TL;DR

This paper introduces GNN Accelerated Molecular Dynamics (GAMD), a deep learning approach that predicts atomic forces directly, enabling faster and scalable molecular simulations without explicit energy calculations.

Contribution

The paper presents a novel GNN-based model that accelerates molecular dynamics simulations by directly predicting forces, scalable to larger systems and competitive with traditional MD software.

Findings

GAMD accurately predicts molecular dynamics for Lennard-Jones and Water systems.

GAMD scales effectively to larger systems at test time.

GAMD demonstrates competitive performance in large-scale simulations.

Abstract

Molecular Dynamics (MD) simulation is a powerful tool for understanding the dynamics and structure of matter. Since the resolution of MD is atomic-scale, achieving long time-scale simulations with femtosecond integration is very expensive. In each MD step, numerous iterative computations are performed to calculate energy based on different types of interaction and their corresponding spatial gradients. These repetitive computations can be learned and surrogated by a deep learning model like a Graph Neural Network (GNN). In this work, we developed a GNN Accelerated Molecular Dynamics (GAMD) model that directly predicts forces given the state of the system (atom positions, atom types), bypassing the evaluation of potential energy. By training the GNN on a variety of data sources (simulation data derived from classical MD and density functional theory), we show that GAMD can predict the dynamics of two typical molecular systems, Lennard-Jones system and Water system, in the NVT ensemble with velocities regulated by a thermostat. We further show that GAMD's learning and inference are agnostic to the scale, where it can scale to much larger systems at test time. We also perform a comprehensive benchmark test comparing our implementation of GAMD to production-level MD softwares, showing GAMD's competitive performance on the large-scale simulation.