UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules

TL;DR

UniSim is a versatile molecular dynamics simulator that uses cross-domain learning and a stochastic framework to model atomic interactions across various molecular types efficiently.

Contribution

It introduces a unified simulation approach leveraging multi-head pretraining and force guidance for transferability across molecular domains.

Findings

UniSim performs well on small molecules, peptides, and proteins.

The model effectively learns long-term state transitions from MD data.

UniSim adapts rapidly to different chemical environments.

Abstract

Molecular Dynamics (MD) simulations are essential for understanding the atomic-level behavior of molecular systems, giving insights into their transitions and interactions. However, classical MD techniques are limited by the trade-off between accuracy and efficiency, while recent deep learning-based improvements have mostly focused on single-domain molecules, lacking transferability to unfamiliar molecular systems. Therefore, we propose \textbf{Uni}fied \textbf{Sim}ulator (UniSim), which leverages cross-domain knowledge to enhance the understanding of atomic interactions. First, we employ a multi-head pretraining approach to learn a unified atomic representation model from a large and diverse set of molecular data. Then, based on the stochastic interpolant framework, we learn the state transition patterns over long timesteps from MD trajectories, and introduce a force guidance module for rapidly adapting to different chemical environments. Our experiments demonstrate that UniSim achieves highly competitive performance across small molecules, peptides, and proteins.