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

arXiv:2506.03157v4 Announce Type: replace-cross 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 extbf{Uni}fied extbf{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.

Related

• Nonparametric Sparse Online Learning of the Koopman Operator
• Transformers for dynamical systems learn transfer operators in-context
• Conditional flow matching for physics-constrained inverse problems with finite training data
• Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems
• Non-intrusive Learning of Physics-Informed Spatio-temporal Surrogate for Accelerating Design
• Amortized Filtering and Smoothing with Conditional Normalizing Flows

Source: arXiv cs.LG | 2026-04-21