DyneTrion: A Spatio-temporally Coherent Generative Emulator for Protein Dynamics Across Timescales

2026-07-15

AI Summary

Molecular dynamics simulations struggle to efficiently explore protein conformational changes at microsecond and longer timescales. To address this challenge, this work proposes a generative protein dynamics simulator that jointly models geometric symmetry, structural consistency, and temporal coherence within a unified framework. The model innovatively integrates a tripartite attention mechanism—comprising SE(3)-invariant invariant point attention (IPA), reference-conformation-anchored spatial attention, and explicit temporal attention—enabling multiscale dynamic modeling within a single architecture for the first time. Experiments on the dynamicPDB dataset demonstrate that the method accurately reproduces flexible features, ensemble distributions, and interaction-related observables at timescales ranging from hundreds of nanoseconds to microseconds, while preserving stereochemical validity and successfully capturing large-scale conformational transitions such as apo-to-holo transformations.

Abstract

Proteins function through coordinated motion across multiple spatial and temporal scales, underpinning processes such as ligand binding, allostery, and catalysis. However, accessing long-timescale conformational change through molecular dynamics (MD) simulations remains prohibitively expensive for systematic exploration across diverse systems. Here, we present DyneTrion, a generative protein dynamics emulator that jointly enforces geometric symmetry, structural consistency and temporal coherence within a single framework. DyneTrion uses a tri-attention architecture that integrates invariant point attention (IPA) for SE(3)-robust geometric updates, spatial attention anchored to a reference conformation to preserve structural integrity, and temporal attention to model correlated evolution across time frames. Across 100-ns MD trajectory simulation benchmarks, DyneTrion reproduces MD-derived flexibility, ensemble distributions and interaction observables while maintaining stereochemical validity during extrapolation. To evaluate long time-scale generalization, we introduce dynamicPDB, a dataset of over 10,000 proteins with up to 1-$μ$s all-atom trajectories at 10-ps resolution and accompanying physical annotations. On microsecond trajectories, DyneTrion preserves free-energy landscapes and metastable-state populations, and it supports large conformational propagation in apo-to-holo transitions and fast folders. Together, DyneTrion provides a scalable path from static structure prediction toward time-resolved, ensemble-faithful protein modeling. The code is publicly available at https://github.com/fudan-generative-vision/DyneTrion

Problem

• protein dynamics
• long-timescale simulation
• conformational change
• molecular dynamics
• ensemble modeling

Innovation

• generative emulator
• tri-attention architecture
• temporal coherence
• protein dynamics
• SE(3)-equivariant modeling