Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics

Liang Shi, Jiarui Lu, Junqi Liu, Chence Shi, Zhi Yang, Jian Tang

Abstract

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.

Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics

Abstract

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.
Paper Structure (26 sections, 15 equations, 3 figures, 5 tables, 5 algorithms)

This paper contains 26 sections, 15 equations, 3 figures, 5 tables, 5 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Generative Modeling of Protein Ensembles.
  4. Generative Modeling of Molecular Trajectories.
  5. Method
  6. Preliminaries
  7. An Atomic Trajectory Modeling Framework
  8. Model Architecture
  9. Training Objectives
  10. Trajectory Sampling
  11. Experiments
  12. Experimental Settings
  13. Protein Dynamics
  14. Protein-Ligand Dynamics
  15. Ablation Study
  16. ...and 11 more sections

Figures (3)

  • Figure 1: Overview of the Proposed Atomic Trajectory Modeling Framework.
  • Figure 2: Case Study on 1s79a00, a target from the test set of mdCATH. (A) the visualization of ensemble from MD simulation (reference) or ATMOS (sampled). (B) The visualization of snapshot at specific frame index. (C) The RMSF versus the residue index. (D) The moving RMSD to the initial structure (frame 0) along the trajectory frames.
  • Figure 3: Detailed architecture of our framework. BIF: Bidirectional Information Flow.