Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics

• URL: http://arxiv.org/abs/2604.03911v1
• Date: Sun, 05 Apr 2026 00:37:28 GMT
• Title: Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
• Abstract summary: We propose a novel framework that leverages structure pretraining for MD trajectory generation.<n>Our approach effectively harnesses abundant structural data to mitigate the scarcity of MD trajectory data.<n> Experimental results confirm that our approach excels in generating chemically realistic MD trajectories.
• Score: 57.2871599860811
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating molecular dynamics (MD) trajectories using deep generative models has attracted increasing attention, yet remains inherently challenging due to the limited availability of MD data and the complexities involved in modeling high-dimensional MD distributions. To overcome these challenges, we propose a novel framework that leverages structure pretraining for MD trajectory generation. Specifically, we first train a diffusion-based structure generation model on a large-scale conformer dataset, on top of which we introduce an interpolator module trained on MD trajectory data, designed to enforce temporal consistency among generated structures. Our approach effectively harnesses abundant structural data to mitigate the scarcity of MD trajectory data and effectively decomposes the intricate MD modeling task into two manageable subproblems: structural generation and temporal alignment. We comprehensively evaluate our method on the QM9 and DRUGS small-molecule datasets across unconditional generation, forward simulation, and interpolation tasks, and further extend our framework and analysis to tetrapeptide and protein monomer systems. Experimental results confirm that our approach excels in generating chemically realistic MD trajectories, as evidenced by remarkable improvements of accuracy in geometric, dynamical, and energetic measurements.

Related papers

• Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics [23.265257394398102]
  ATMOS is a novel generative framework designed to generate atom-level MD trajectories for biomolecular systems.<n>We demonstrate that ATMOS achieves state-of-the-art performance in generating conformation trajectories for both protein monomers and complex protein-ligand systems.
  arXiv  Detail & Related papers  (2026-03-18T11:53:45Z)
• Unified Biomolecular Trajectory Generation via Pretrained Variational Bridge [19.279397111680115]
  We present the Pretrained Variational Bridge (PVB), which maps the initial structure into a noised latent space and transports it toward stage-specific targets.<n>This unifies training on both single-structure and paired trajectory data, enabling consistent use of cross-domain structural knowledge.<n>Experiments on proteins and protein-ligand complexes demonstrate that PVB faithfully reproduces thermodynamic and kinetic observables from MD while delivering stable and efficient generative dynamics.
  arXiv  Detail & Related papers  (2026-02-07T15:32:37Z)
• Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics [51.85385061275941]
  Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics.<n>Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation.<n>We present STAR-MD, a scalable diffusion model that generates physically plausible protein trajectories over micro-scale timescales.
  arXiv  Detail & Related papers  (2026-02-02T14:13:28Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression [45.49904590474368]
  ConfRover is an autoregressive model that simultaneously learns protein conformation and dynamics from MD trajectories.<n>It supports both time-dependent and time-independent sampling.<n>Experiments on ATLAS, a large-scale protein MD dataset, demonstrate the effectiveness of our model.
  arXiv  Detail & Related papers  (2025-05-23T05:00:15Z)
• Enhanced Sampling, Public Dataset and Generative Model for Drug-Protein Dissociation Dynamics [10.80659641278556]
  Drug-protein binding and dissociation dynamics are fundamental to understanding molecular interactions in biological systems.<n>We propose a novel research paradigm that combines molecular dynamics simulations, enhanced sampling, and AI generative models to address this issue.<n>Our ongoing efforts focus on expanding this methodology to encompass a broader spectrum of drug-protein complexes and exploring novel applications in pathway prediction.
  arXiv  Detail & Related papers  (2025-04-25T14:10:06Z)
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials [62.72989417755985]
  We present UniGenX, a unified generative model for function in natural systems.<n>UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens.<n>It achieves state-of-the-art or competitive performance for the function-aware generation across domains.
  arXiv  Detail & Related papers  (2025-03-09T16:43:07Z)
• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [88.65168366064061]
  We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference. Our framework leads to a family of three novel objectives that are all simulation-free, and thus scalable. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
  arXiv  Detail & Related papers  (2024-10-10T17:18:30Z)
• Generative Modeling of Molecular Dynamics Trajectories [12.255021091552441]
  We introduce generative modeling of molecular trajectories as a paradigm for learning flexible multi-task surrogate models of MD from data. We show such generative models can be adapted to diverse tasks such as forward simulation, transition path sampling, and trajectory upsampling.
  arXiv  Detail & Related papers  (2024-09-26T13:02:28Z)
• A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics [73.35846234413611]
  In drug discovery, molecular dynamics (MD) simulation provides a powerful tool for predicting binding affinities, estimating transport properties, and exploring pocket sites. We propose NeuralMD, the first machine learning (ML) surrogate that can facilitate numerical MD and provide accurate simulations in protein-ligand binding dynamics. We demonstrate the efficiency and effectiveness of NeuralMD, achieving over 1K$times$ speedup compared to standard numerical MD simulations.
  arXiv  Detail & Related papers  (2024-01-26T09:35:17Z)
• Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling [23.74897713386661]
  The dynamic nature of proteins is crucial for determining their biological functions and properties. Existing learning-based approaches perform direct sampling yet heavily rely on target-specific simulation data for training. We propose Str2Str, a novel structure-to-structure translation framework capable of zero-shot conformation sampling.
  arXiv  Detail & Related papers  (2023-06-05T15:19:06Z)
• Dynamic Mode Decomposition in Adaptive Mesh Refinement and Coarsening Simulations [58.720142291102135]
  Dynamic Mode Decomposition (DMD) is a powerful data-driven method used to extract coherent schemes. This paper proposes a strategy to enable DMD to extract from observations with different mesh topologies and dimensions.
  arXiv  Detail & Related papers  (2021-04-28T22:14:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.