美国康奈尔大学Haiyuan Yu和美国勒纳研究所Feixiong Cheng共同合作，近期取得重要工作进展。他们通过人类蛋白质-蛋白质相互作用结构信息组揭示了由疾病突变引起的蛋白质组范围扰动。相关研究成果2024年10月24日在线发表于《自然—生物技术》杂志上。

为了帮助将遗传发现转化为疾病病理生物学和治疗学发现，研究人员提出了一个集成深度学习框架，称为PIONEER（蛋白质-蛋白质相互作用iNtErfacE-pRediction），该框架预测人类和其他七种常见模式生物中，所有已知蛋白质相互作用的蛋白质结合伴侣特异性界面，以生成全面的结构信息蛋白质相互作用体。研究人员证明PIONEER优于现有的最先进的方法，并通过实验验证了其预测。

研究人员发现，疾病相关突变在PIONEER预测的蛋白质-蛋白质界面中富集，并探讨了它们对疾病预后和药物反应的影响。

通过对33种癌症类型的约11000个完整外显子的分析，研究人员确定了586个富含PIONEER预测的界面体细胞突变（称为oncoPPI）的显著蛋白质-蛋白质相互作用（PPI），并显示了oncoPPI与患者生存率和药物反应的显著关联。

PIONEER作为网络服务器平台和软件包实现，可识别疾病相关等位基因的功能后果，并在多尺度交互组网络级别为精准医学提供深度学习工具。

附：英文原文

Title: A structurally informed human protein–protein interactome reveals proteome-wide perturbations caused by disease mutations

Author: Xiong, Dapeng, Qiu, Yunguang, Zhao, Junfei, Zhou, Yadi, Lee, Dongjin, Gupta, Shobhita, Torres, Mateo, Lu, Weiqiang, Liang, Siqi, Kang, Jin Joo, Eng, Charis, Loscalzo, Joseph, Cheng, Feixiong, Yu, Haiyuan

Issue&Volume: 2024-10-24

Abstract: To assist the translation of genetic findings to disease pathobiology and therapeutics discovery, we present an ensemble deep learning framework, termed PIONEER (Protein–protein InteractiOn iNtErfacE pRediction), that predicts protein-binding partner-specific interfaces for all known protein interactions in humans and seven other common model organisms to generate comprehensive structurally informed protein interactomes. We demonstrate that PIONEER outperforms existing state-of-the-art methods and experimentally validate its predictions. We show that disease-associated mutations are enriched in PIONEER-predicted protein–protein interfaces and explore their impact on disease prognosis and drug responses. We identify 586 significant protein–protein interactions (PPIs) enriched with PIONEER-predicted interface somatic mutations (termed oncoPPIs) from analysis of approximately 11,000 whole exomes across 33 cancer types and show significant associations of oncoPPIs with patient survival and drug responses. PIONEER, implemented as both a web server platform and a software package, identifies functional consequences of disease-associated alleles and offers a deep learning tool for precision medicine at multiscale interactome network levels.

DOI: 10.1038/s41587-024-02428-4

Source: https://www.nature.com/articles/s41587-024-02428-4