arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.18201physics.bio-phcs.LGq-bio.QM

Loop-Diffusion:一种用于设计和评分蛋白质环的等变扩散模型

Loop-Diffusion: an equivariant diffusion model for designing and scoring protein loops

University of Washington(华盛顿大学);Paul G. Allen School of Computer Science and Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);Department of Applied Mathematics, University of Washington(华盛顿大学应用数学系);Fred Hutch Cancer Research Center(弗雷德·哈钦森癌症研究中心)

Kevin Borisiak, Gian Marco Visani, Armita Nourmohammad

AI总结:

针对蛋白质功能预测中数据稀缺及物理方法局限的问题,提出基于能量的等变扩散模型Loop-Diffusion,利用全局蛋白质环数据学习能量函数,在TCR-pMHC界面评分及识别结合增强突变上取得最优结果。

摘要:

从结构预测蛋白质功能特征仍是蛋白质科学的核心问题,对理解疾病机制和设计新疗法具有广泛影响。然而,当前机器学习方法受限于稀缺且有偏的实验数据,而基于物理学的方法要么太慢无法实用,要么过于简化而不够准确。在本研究中,我们提出了Loop-Diffusion,这是一种基于能量的扩散模型,它利用来自整个蛋白质宇宙的通用蛋白质环数据集,学习到一个可泛化至功能预测任务的能量函数。我们在评分TCR-pMHC界面上评估了Loop-Diffusion的性能,并在识别结合增强突变方面展现了最先进的结果。

英文摘要:

Predicting protein functional characteristics from structure remains a central problem in protein science, with broad implications from understanding the mechanisms of disease to designing novel therapeutics. Unfortunately, current machine learning methods are limited by scarce and biased experimental data, and physics-based methods are either too slow to be useful, or too simplified to be accurate. In this work, we present Loop-Diffusion, an energy based diffusion model which leverages a dataset of general protein loops from the entire protein universe to learn an energy function that generalizes to functional prediction tasks. We evaluate Loop-Diffusion's performance on scoring TCR-pMHC interfaces and demonstrate state-of-the-art results in recognizing binding-enhancing mutations.

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。

↑