发表机构
BIT; HUST; SJTU; Tsinghua University; Shanghai AI Laboratory（北京理工大学; 华中科技大学; 上海交通大学; 清华大学; 上海人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出DynaPPI动态蛋白质数据集，填补现有数据集忽略多体结合动态过程的空白，助力扩散模型预测未知蛋白质复合物结构，推动AI驱动的蛋白质互作组学发展。
AI 中文摘要
扩散模型因强大的生成能力已被广泛应用于蛋白质主链生成，但在当前AI驱动的生物研究中，预测未知多链蛋白质聚集体（生物学中称为“复合物”）的结构仍是未解决的问题。这是因为现有的静态或动态蛋白质数据集仅关注静态快照或单实体轨迹，忽略了多个单体形成复合物的动态过程。为缓解这一困境，我们提出DynaPPI，这是一个动态蛋白质数据集，包含从解离链到结合状态的蛋白质复合物形成的分子动力学（MD）轨迹，作为弥合静态结构生物学与动态分子固有时序特性之间差距的关键资源。通过该数据集，扩散模型可明确学习已知复合物的动态结合轨迹，并基于其多样的生成特性准确预测未知复合物的结构，进而推动AI驱动的结构生物学和蛋白质互作组学发展。
英文摘要
Diffusion models have been widely explored in protein backbone generation due to their powerful generation capabilities.However, in today's AI-driven biological research, predicting the structure of unknown multi-chain protein aggregates (called "complexes" in biology) remains an unsolved challenge.This is because existing static or dynamic protein datasets focus solely on static snapshots or single-entity trajectories, neglecting the dynamic process of multiple monomers forming complexes.To alleviate this dilemma, we present DynaPPI, a dynamic protein dataset comprising molecular dynamics (MD) trajectories of protein complex formation from dissociated chains to the bound state, as a pivotal resource to bridge the gap between static structural biology and the inherently temporal nature of dynamic molecular interactions.Benefiting from this dataset, diffusion models can explicitly learn the dynamic binding trajectories of known complexes and accurately predict the structures of unknown complexes based on their diverse generative properties, thereby further catalyzing AI-driven structural biology and protein interactomics.
Comments9 pages, 1 figure, 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI4Science
