发表机构
Artificial Intelligence Innovation and Incubation Institute, Fudan University; Shanghai Academy of AI for Science; School of Data Science, Fudan University; Institute for Big Data, Fudan University; MOE Laboratory for National Development and Intelligent Governance, Fudan University（复旦大学人工智能创新与孵化院; 上海人工智能科学研究院; 复旦大学数据科学学院; 复旦大学大数据研究院; 复旦大学教育部国家发展与智能治理实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对蛋白质跨时间尺度动力学模拟成本高的问题，提出DyneTrion模拟器，采用三注意力架构，在多基准测试中表现良好，能重现相关特性，还引入数据集评估其长时间尺度泛化能力，为蛋白质建模提供可扩展路径。
AI 中文摘要
蛋白质通过跨多个空间和时间尺度的协同运动发挥功能，然而通过分子动力学（MD）模拟获取长时间尺度的构象变化对于系统探索不同系统来说成本过高。本文提出DyneTrion，一种生成式蛋白质动力学模拟器，在单个框架内联合强制几何对称性、结构一致性和时间相干性。它使用三注意力架构，在100纳秒MD轨迹模拟基准测试中，DyneTrion能重现MD衍生的灵活性、系综分布和相互作用观测值。为评估长时间尺度泛化能力，引入dynamicPDB数据集。在微秒轨迹上，DyneTrion能保留自由能景观和亚稳态种群，支持从无配体到有配体转变和快速折叠蛋白中的大构象传播。DyneTrion为从静态结构预测到时间分辨、系综忠实的蛋白质建模提供了一条可扩展路径。
英文摘要
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
