Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models
Namrata Anand、Tudor Achim
Abstract
Proteins are macromolecules that mediate a significant fraction of the cellular processes that underlie life. An important task in bioengineering is designing proteins with specific 3D structures and chemical properties which enable targeted functions. To this end, we introduce a generative model of both protein structure and sequence that can operate at significantly larger scales than previous molecular generative modeling approaches. The model is learned entirely from experimental data and conditions its generation on a compact specification of protein topology to produce a full-atom backbone configuration as well as sequence and side-chain predictions. We demonstrate the quality of the model via qualitative and quantitative analysis of its samples. Videos of sampling trajectories are available at https://nanand2.github.io/proteins.
中文速览
蛋白质的三维结构设计是生物工程中的核心难题，以往的机器学习生成模型要么只能处理远比蛋白质小的小分子，要么只能应对单一拓扑类型的蛋白质，覆盖范围极为有限。这项工作提出了一种基于去噪扩散概率模型（denoising diffusion probabilistic model）的全数据驱动生成框架，能够同时生成蛋白质的三维骨架结构、氨基酸序列和侧链构象，原子数量比此前同类方法大100到1000倍，并可横跨蛋白质数据库（PDB）中数百种结构域拓扑类型。模型通过不变点注意力（invariant point attention）实现旋转等变性，采用球面线性插值（SLERP）处理旋转变量的扩散，并用类掩码语言模型的离散扩散方法生成序列；用户只需提供二级结构拓扑的紧凑描述，即可引导模型定向采样。实验表明生成的蛋白质在结构合理性和序列质量上均表现优异，是首个能在完整蛋白质域拓扑范围内合成物理上可信的大型蛋白质结构与序列的生成模型，为数据驱动的蛋白质设计开辟了新路径。
原文 arXiv:2205.15019;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2205.15019v1