DoMiNO: Decomposing Molecular Dynamics with Multi-Scale Neural Graph Ordinary Differential Equations
Open Access
- 19 June 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-29
Abstract
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 are 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 .Keywords
Funding Information
- National Science Foundation (NSF 2211557, NSF 2119643, NSF 2303037, NSF 2312501)
- NAIRR Pilot Program (NSF 2202693, NSF 2312501)
- SRC JUMP 2.0 Center
- Amazon Research Awards; Snapchat Gifts
- C-CAS (NSF CHE-2202693)
This publication has 29 references indexed in Scilit:
- Navigating protein landscapes with a machine-learned transferable coarse-grained modelNature Chemistry, 2025
- A compact chemically driven [2]catenane rotary motor operated through alternate pumping and dischargingChemical Science, 2024
- Machine learning coarse-grained potentials of protein thermodynamicsNature Communications, 2023
- DESCINet: A hierarchical deep convolutional neural network with skip connection for long time series forecastingExpert Systems with Applications, 2023
- Fast, Accurate, and System-Specific Variable-Resolution Modeling of ProteinsJournal of Chemical Information and Modeling, 2023
- Molecular Dynamics Simulation for AllNeuron, 2018
- An improved wavelet–ARIMA approach for forecasting metal pricesResources Policy, 2014
- Protein dynamics and enzyme catalysis: Insights from simulationsBiochimica et Biophysica Acta (BBA) - Proteins and Proteomics, 2011
- Ab Initio Molecular Dynamics2009
- Day-Ahead Electricity Price Forecasting Using the Wavelet Transform and ARIMA ModelsIEEE Transactions on Power Systems, 2005