Large-Scale Molecular Dynamics Simulation: Direct Interatomic Modeling with Dilated Message Passing

Haokai Hong, Wanyu Lin, KC Tan

Keywords: Molecular Dynamics, Graph Neural Network, Machien Learning Force Field

TL;DR: A new machine learning framework overcomes scalability-accuracy trade-offs in large-scale molecular dynamics by employing dilated star-structured message-passing.

Abstract: Large-scale molecular dynamics simulation is essential in understanding chemical and biological processes, necessitating the accurate and efficient modeling of interatomic interactions. Existing learning-based methods generally are based on message passing mechanisms; they either are not scalable or are too coarse to offer accurate modeling. We propose a new message passing framework that can effectively and efficiently model interatomic interactions for simulating large-scale molecular dynamics at full atomic resolution. Specifically, our framework is stacked with a sequence of message passing neural network layers, each realizing the message passing over a distinct and dilated star-structured path. These star-structured paths are constructed progressively along dilated regions to capture the distance-dependent interactions. The crux of our framework is that it resolves the problem of dense interatomic interactions of large-scale atomic systems with sparser and region-based message passing graphs. We evaluate the framework on four benchmarks: the MD22 (molecules with 42–370 atoms), the Chignolin (a 166-atom protein featuring diverse conformations), the AdK dataset (a protein trajectory with up to 3,000 atoms), and the MISATO dataset (over 10,000 heterogeneous protein-ligand complexes, including systems with up to 40,000 atoms). Comprehensive evaluations demonstrate that our approach delivers state-of-the-art performance overall across various benchmarks. In particular, it is the first learning-based method to achieve atomic-level accuracy in protein-ligand dynamics simulation while preserving computational efficiency.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 3311