发表机构
DBB and SciLifeLab at Stockholm University; Max Planck Institute for Polymer Research; Heidelberg Institute for Theoretical Studies; IWR, Heidelberg University（斯德哥尔摩大学生物生物学与系统生物学中心及科学生命实验室; 马克斯·普朗克聚合物研究所; 海德尔堡理论研究所; 海德尔堡大学计算与数学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对蛋白质动力学预测成本高的问题，提出SE(3)等变图神经网络BackFlip-2，直接从平衡结构预测方向性柔性等动力学描述符，精度媲美大模型且速度提升多个数量级。
AI 中文摘要
预测蛋白质动力学是计算结构生物学中一个长期存在的问题。通常，蛋白质功能关键依赖于局部定向运动，如铰链运动、催化环重排和结构域重定向，这些运动可以通过蛋白质骨架的方向性柔性和相关结构运动来表征。虽然分子动力学（MD）模拟提供了一种成熟但往往代价高昂的方法，但最近的深度生成模型旨在通过直接预测构象系综来模拟MD，从而降低这一成本。然而，由于这些模型规模庞大，且需要生成多个状态直到导出的动力学性质收敛，它们仍然昂贵。在本工作中，我们提出了BackFlip-2：一种快速SE(3)等变图神经网络，训练用于直接从平衡结构预测动力学描述符，如方向性骨架柔性和成对动态相关性。在一系列实验中，我们表明我们的模型在精度上匹配了规模大得多的系综生成模型，同时速度快了几个数量级，并证明了所提出的等变架构特别适合捕捉蛋白质中的各向异性运动。BackFlip-2模型权重、训练和推理代码可在以下网址获取：此https URL。
英文摘要
Predicting protein dynamics is a long-standing problem in computational structural biology. Often, protein function critically depends on local directed motions, such as hinge movements, catalytic loop rearrangements and domain reorientations, which can be characterized by directional flexibility and correlated structural motions of the protein backbone. While Molecular Dynamics (MD) simulations provide an established but often prohibitively expensive approach, recent deep generative models aim to reduce this cost by directly predicting conformational ensembles, emulating MD. However, due to their large size and the need to generate several states until the derived dynamical properties converge, these models remain expensive. In this work, we propose BackFlip-2: a fast SE(3)-equivariant graph neural network trained to directly predict dynamical descriptors, such as directional backbone flexibility and pairwise dynamic correlations, from an equilibrium structure. In a series of experiments, we show that our model matches the accuracy of substantially larger ensemble generation models while being orders of magnitude faster, and demonstrate that the proposed equivariant architecture is especially well-suited for capturing anisotropic motions in proteins. BackFlip-2 model weights, training and inference code are available at https://github.com/graeter-group/backflip.
