分子动力学（MD）模拟仍然是研究蛋白质动力学的黄金标准，但其计算成本限制了对生物相关时间尺度的访问。最近的生成模型在加速模拟方面表现出潜力，但因架构限制、误差累积和对时空动态建模不足而难以处理长时间尺度生成。我们提出了STAR-MD（Spatio-Temporal Autoregressive Rollout for Molecular Dynamics），一种可扩展的SE(3)-等变扩散模型，能够生成在微秒时间尺度上物理合理的蛋白质轨迹。我们的关键创新是一个具有联合时空注意力的因果扩散变压器，能够高效捕捉复杂的时空依赖关系，同时避免现有方法的记忆瓶颈。在标准的ATLAS基准上，STAR-MD在所有指标上均取得最佳性能——与先前方法相比，显著提高了构象覆盖、结构有效性以及动态保真度。STAR-MD能够外推生成稳定的微秒级轨迹，其中基线方法会灾难性地失败，整个扩展滚动过程中保持高质量的结构特性。我们的全面评估揭示了当前模型在长时间尺度生成方面的严重局限性，同时展示了STAR-MD的联合时空建模能够实现生物相关时间尺度的稳健动态模拟，为加速探索蛋白质功能铺平了道路。
英文摘要：
Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics, but their computational cost limits access to biologically relevant timescales. Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation due to architectural constraints, error accumulation, and inadequate modeling of spatio-temporal dynamics. We present STAR-MD (Spatio-Temporal Autoregressive Rollout for Molecular Dynamics), a scalable SE(3)-equivariant diffusion model that generates physically plausible protein trajectories over microsecond timescales. Our key innovation is a causal diffusion transformer with joint spatio-temporal attention that efficiently captures complex space-time dependencies while avoiding the memory bottlenecks of existing methods. On the standard ATLAS benchmark, STAR-MD achieves state-of-the-art performance across all metrics--substantially improving conformational coverage, structural validity, and dynamic fidelity compared to previous methods. STAR-MD successfully extrapolates to generate stable microsecond-scale trajectories where baseline methods fail catastrophically, maintaining high structural quality throughout the extended rollout. Our comprehensive evaluation reveals severe limitations in current models for long-horizon generation, while demonstrating that STAR-MD's joint spatio-temporal modeling enables robust dynamics simulation at biologically relevant timescales, paving the way for accelerated exploration of protein function.
Improving AlphaFlow for Efficient Protein Ensembles Generation
The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）；Xi’an Jiaotong University（西安交通大学）；Shanghai Institute of Materia Medica, Chinese Academy of Sciences（中国科学院上海药物研究所）
DyneTrion: A Spatio-temporally Coherent Generative Emulator for Protein Dynamics Across Timescales
Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化院）；Shanghai Academy of AI for Science（上海人工智能科学研究院）；School of Data Science, Fudan University（复旦大学数据科学学院）；Institute for Big Data, Fudan University（复旦大学大数据研究院）；MOE Laboratory for National Development and Intelligent Governance, Fudan University（复旦大学教育部国家发展与智能治理实验室）
Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO(3)-Equivariant Autoencoders
Center for Bits and Atoms（比特与原子中心）；MIT Media Lab, Molecular Machines（麻省理工学院媒体实验室，分子机器）；Atomic Architects（原子建筑师）；MIT Research Laboratory of Electronics（麻省理工学院电子研究实验室）
Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language Models
School of Information Science and Engineering, East China University of Science and Technology（华东理工大学信息科学与工程学院）；Institute of Natural Sciences, Shanghai Jiao Tong University（上海交通大学自然科学学院）
Towards Intelligent Energy Security: A Unified Spatio-Temporal and Graph Learning Framework for Scalable Electricity Theft Detection in Smart Grids
Department of Chemical and Petroleum Engineering, Abiola Ajimobi Technical University（阿比奥拉·阿吉莫比技术大学化学与石油工程系）；Department of Computer Science, Abiola Ajimobi Technical University（阿比奥拉·阿吉莫比技术大学计算机科学系）
SiDGen: Structure-informed Diffusion for Generative modeling of Ligands for Proteins
Department of Computer Science, Indian Institute of Technology, Delhi, India（计算机科学系，印度理工学院，德里，印度）；Department of Chemistry, Indian Institute of Technology, Delhi, India（化学系，印度理工学院，德里，印度）
