DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations
ACM Transactions on Knowledge Discovery from Data · 31.07.2026 · 20 (6) · 1-29
DOI: 10.1145/3822365 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 20.07.2026. Verfasst von Fang Sun und 5 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. National Science Foundation, NAIRR Pilot Program, SRC JUMP 2.0 Center.
Abstract (Originalsprache)
Molecular dynamics (MD) simulations are crucial for understanding and predicting the behavior of molecular systems in biology and chemistry. Yet, predicting long-term dynamics is still challenging. On one hand, it is hard to employ small-timestep models for long-term prediction, due to substantial rollout errors accumulated at each step, not to mention their extremely high time complexity due to the large number of rollout steps. On the other hand, it is hard to use large-timestep models to achieve high accuracy, due to their inability to capture subtle details of the dynamics. To bridge this dichotomy, we propose DoMiNO , a multi-scale framework that decomposes MD dynamics into several temporal resolutions, each governed by a neural graph ordinary differential equation (GraphODE) and is adaptively fused for final predictions. Concretely, DoMiNO operates through three key components: (1) an E(n)-equivariant graph neural network (EGNN) encoder that initializes latent states from a single observed molecular structure, maintaining SE(3) symmetries throughout; (2) a hierarchy of GraphODEs where each level captures scale-specific dynamics over normalized local time intervals, ranging from slow global motions to fast bond vibrations; and (3) an attention-based fusion module that adaptively combines multi-level predictions and reconstructs SE(3)-equivariant 3D coordinates. This design enables each hierarchical level to specialize in its characteristic timescale while preserving molecular symmetries. During inference, DoMiNO flexibly assembles predictions across different temporal resolutions, providing superior performance over both short-term and long-term dynamics. Empirical results on challenging MD benchmarks demonstrate that DoMiNO achieves significant improvements in prediction accuracy, particularly for molecules with pronounced timescale separation. The method exhibits significantly slower error growth over extended horizons compared to both single-scale baselines and state-of-the-art multi-step approaches. Our implementation is available at https://github.com/FrancoTSolis/DoMiNO-TKDD-Code .
Förderung
- U.S. National Science Foundation
- NAIRR Pilot Program
- SRC JUMP 2.0 Center
- Amazon Research Awards; Snapchat Gifts
- C-CAS
Zitieren
APA
Sun, F., Huang, Z., Cao, Y., Luo, X., Wang, W., & Sun, Y. (2026). DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations. ACM Transactions on Knowledge Discovery from Data, 20(6), 1-29. https://doi.org/10.1145/3822365
Vancouver
Sun F, Huang Z, Cao Y, Luo X, Wang W, Sun Y. DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations. ACM Transactions on Knowledge Discovery from Data. 2026;20(6):1-29. doi:10.1145/3822365
BibTeX
@article{Sun2026,
author = {Sun, Fang and Huang, Zijie and Cao, Yadi and Luo, Xiao and Wang, Wei and Sun, Yizhou},
title = {DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2026},
volume = {20},
number = {6},
pages = {1--29},
doi = {10.1145/3822365}
}
EUVIMED