arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09236cs.LGq-bio.BM
收藏

用于蛋白质设计基序支架的条件扩散建模框架

A framework for conditional diffusion modelling with applications in motif scaffolding for protein design

University of Cambridge(剑桥大学)

Kieran Didi, Francisco Vargas, Simon V Mathis, Vincent Dutordoir, Emile Mathieu, Urszula J Komorowska, Pietro Lio

AI总结:

本研究提出基于Doob h-变换的统一条件扩散框架,连接现有方法并提出新协议,在图像外推和蛋白质基序支架任务中优于标准方法。

摘要:

许多蛋白质设计应用,如粘合剂或酶设计,需要高精度地构建结构基序。基于去噪扩散过程的生成建模范式已成为解决这一基序支架问题的主要候选方法,并在某些情况下显示出早期的实验成功。在扩散范式中,基序支架被视为条件生成任务,并提出了几种条件生成协议或从计算机视觉文献中引入。然而,这些协议大多基于启发式动机,例如通过朗之万动力学的类比,缺乏统一框架,模糊了不同方法之间的联系。在这项工作中,我们将条件训练和条件采样程序统一在一个基于数学上充分理解的Doob h-变换的公共框架下。这一新视角使我们能够建立现有方法之间的联系,并提出对现有条件训练协议的新变体。我们在图像外推和基序支架两个任务中展示了这一新协议的有效性,并发现其优于标准方法。

英文摘要:

Many protein design applications, such as binder or enzyme design, require scaffolding a structural motif with high precision. Generative modelling paradigms based on denoising diffusion processes emerged as a leading candidate to address this motif scaffolding problem and have shown early experimental success in some cases. In the diffusion paradigm, motif scaffolding is treated as a conditional generation task, and several conditional generation protocols were proposed or imported from the Computer Vision literature. However, most of these protocols are motivated heuristically, e.g. via analogies to Langevin dynamics, and lack a unifying framework, obscuring connections between the different approaches. In this work, we unify conditional training and conditional sampling procedures under one common framework based on the mathematically well-understood Doob's h-transform. This new perspective allows us to draw connections between existing methods and propose a new variation on existing conditional training protocols. We illustrate the effectiveness of this new protocol in both, image outpainting and motif scaffolding and find that it outperforms standard methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑