美国哈佛医学院Mohammed AlQuraishi和Peter K. Sorger研究团队合作，利用机器学习对蛋白质-肽相互作用和信号网络进行生物物理预测。相关论文在线发表在2020年1月6日的《自然—方法学》上。

研究人员介绍了一种定制的机器学习方法，即分层统计机械建模（HSM），它能够准确预测跨多个蛋白质家族的PBD-肽相互作用的亲和力。通过在现代机器学习框架内合成生物物理先验，HSM优于现有的计算方法和高通量实验分析。HSM模型可以在三个空间尺度上以熟悉的生物物理术语来解释：蛋白质-肽结合的能量学，蛋白质-蛋白质相互作用的多齿组织和信号网络的整体架构。

研究人员表示，在哺乳动物细胞中，许多信号转导是由球形蛋白结合结构域（PBD）与伴侣蛋白中非结构化肽基序之间的弱蛋白-蛋白相互作用介导的。这些PBD的数量和多样性（已知1,800多种）、低结合亲和力和结合特性对微小序列变异的敏感性，对PBD特异性和PBD创建的网络的实验和计算分析提出了重大挑战。

附：英文原文

Title: Biophysical prediction of protein–peptide interactions and signaling networks using machine learning

Author: Joseph M. Cunningham, Grigoriy Koytiger, Peter K. Sorger, Mohammed AlQuraishi

Issue&Volume: 2020-01-06

Abstract: In mammalian cells, much of signal transduction is mediated by weak protein–protein interactions between globular peptide-binding domains (PBDs) and unstructured peptidic motifs in partner proteins. The number and diversity of these PBDs (over 1,800 are known), their low binding affinities and the sensitivity of binding properties to minor sequence variation represent a substantial challenge to experimental and computational analysis of PBD specificity and the networks PBDs create. Here, we introduce a bespoke machine-learning approach, hierarchical statistical mechanical modeling (HSM), capable of accurately predicting the affinities of PBD–peptide interactions across multiple protein families. By synthesizing biophysical priors within a modern machine-learning framework, HSM outperforms existing computational methods and high-throughput experimental assays. HSM models are interpretable in familiar biophysical terms at three spatial scales: the energetics of protein–peptide binding, the multidentate organization of protein–protein interactions and the global architecture of signaling networks.

DOI: 10.1038/s41592-019-0687-1

Source: https://www.nature.com/articles/s41592-019-0687-1