用扩散模型设计蛋白环，提升功能预测准确率。
Loop-Diffusion: an equivariant diffusion model for designing and scoring protein loops
- 基于蛋白质环的通用数据集训练能量型扩散模型
- 在TCR-pMHC结合界面评分上达到领先效果
- 适合蛋白设计与药物研发人员参考
从结构预测蛋白质功能仍是蛋白科学的核心问题，对疾病机制理解与新药设计具有重要意义。然而，当前机器学习方法受限于实验数据稀缺且偏倚，而基于物理的方法要么速度太慢，要么过于简化。本文提出Loop-Diffusion，一种基于能量的扩散模型，利用整个蛋白质宇宙中的通用蛋白环数据集，学习可泛化的能量函数，用于功能预测任务。我们在TCR-pMHC接口评分任务上评估其性能，结果表明该模型在识别增强结合的突变方面达到当前最优水平。
原文摘要 · Abstract (English)
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.
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。