Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics
This work addresses the need for efficient modeling of biomolecular dynamics, crucial for biological function understanding and drug discovery, by providing a novel method that bridges gaps in existing deep generative approaches.
The paper tackles the problem of generating atom-level molecular dynamics trajectories for biomolecules, which is computationally expensive with traditional methods, by introducing ATMOS, a generative framework based on State Space Models that achieves state-of-the-art performance for protein monomers and protein-ligand systems.
Understanding the dynamic behavior of biomolecules is fundamental to elucidating biological function and facilitating drug discovery. While Molecular Dynamics (MD) simulations provide a rigorous physical basis for studying these dynamics, they remain computationally expensive for long timescales. Conversely, recent deep generative models accelerate conformation generation but are typically either failing to model temporal relationship or built only for monomeric proteins. To bridge this gap, we introduce ATMOS, a novel generative framework based on State Space Models (SSM) designed to generate atom-level MD trajectories for biomolecular systems. ATMOS integrates a Pairformer-based state transition mechanism to capture long-range temporal dependencies, with a diffusion-based module to decode trajectory frames in an autoregressive manner. ATMOS is trained across crystal structures from PDB and conformation trajectory from large-scale MD simulation datasets including mdCATH and MISATO. We demonstrate that ATMOS achieves state-of-the-art performance in generating conformation trajectories for both protein monomers and complex protein-ligand systems. By enabling efficient inference of atomic trajectory of motions, this work establishes a promising foundation for modeling biomolecular dynamics.