仅用骨架几何信息生成蛋白构象，速度快且无序列依赖。
Learning conformational ensembles of proteins based on backbone geometry
- 基于骨架几何构建流匹配模型，不依赖进化信息。
- 推理速度比现有方法快多个数量级，准确率相当。
- 可直接训练，适用于天然与设计蛋白，适合新药研发。
深度生成模型最近被用于从玻尔兹曼分布中采样蛋白构象，作为计算成本高昂的分子动力学模拟的替代方案。然而，当前最先进的方法依赖于预训练折叠模型和进化序列信息，限制了其适用性与效率，并可能引入偏差。本文提出一种仅基于骨架几何信息的流匹配模型——BBFlow。通过将骨架平衡结构的几何编码作为输入，并同时以该结构条件化流模型与先验分布，避免了对进化信息的依赖。实验表明，该模型在保持相当准确率的前提下，推理速度比现有方法快多个数量级，具备多链蛋白的迁移能力，可在数天内从头训练完成。在天然蛋白和全新设计蛋白（缺乏进化信息）的基准测试中均表现优异。代码已开源：https://github.com/graeter-group/bbflow。
原文摘要 · Abstract (English)
Deep generative models have recently been proposed for sampling protein conformations from the Boltzmann distribution, as an alternative to often prohibitively expensive Molecular Dynamics simulations. However, current state-of-the-art approaches rely on fine-tuning pre-trained folding models and evolutionary sequence information, limiting their applicability and efficiency, and introducing potential biases. In this work, we propose a flow matching model for sampling protein conformations based solely on backbone geometry - BBFlow. We introduce a geometric encoding of the backbone equilibrium structure as input and propose to condition not only the flow but also the prior distribution on the respective equilibrium structure, eliminating the need for evolutionary information. The resulting model is orders of magnitudes faster than current state-of-the-art approaches at comparable accuracy, is transferable to multi-chain proteins, and can be trained from scratch in a few GPU days. In our experiments, we demonstrate that the proposed model achieves competitive performance with reduced inference time, across not only an established benchmark of naturally occurring proteins but also de novo proteins, for which evolutionary information is scarce or absent. BBFlow is available at https://github.com/graeter-group/bbflow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。