Xie Jun, Zhang Youli, Wang Ziyang, Jin Xiaocheng, Lu Xiaoli, Ge Shengxiang, Min Xiaoping
Institute of Artificial Intelligence, School of Informatic, Xiamen University, No. 422 Siming South Rd, Xiamen, 361005, China.
National Institute of Diagnostics and Vaccine Development in Infectious Diseases, School of Public Health, Xiamen University, No. 422 Siming South Rd, Xiamen, 361005, China.
BMC Bioinformatics. 2025 Apr 29;26(1):116. doi: 10.1186/s12859-025-06123-2.
Protein-protein interactions (PPIs) refer to the phenomenon of protein binding through various types of bonds to execute biological functions. These interactions are critical for understanding biological mechanisms and drug research. Among these, the protein binding interface is a critical region involved in protein-protein interactions, particularly the hotspot residues on it that play a key role in protein interactions. Current deep learning methods trained on large-scale data can characterize proteins to a certain extent, but they often struggle to adequately capture information about protein binding interfaces. To address this limitation, we propose the PPI-Graphomer module, which integrates pretrained features from large-scale language models and inverse folding models. This approach enhances the characterization of protein binding interfaces by defining edge relationships and interface masks on the basis of molecular interaction information. Our model outperforms existing methods across multiple benchmark datasets and demonstrates strong generalization capabilities.
蛋白质-蛋白质相互作用（PPIs）是指蛋白质通过各种类型的键结合以执行生物学功能的现象。这些相互作用对于理解生物学机制和药物研究至关重要。其中，蛋白质结合界面是参与蛋白质-蛋白质相互作用的关键区域，特别是其上的热点残基在蛋白质相互作用中起关键作用。当前在大规模数据上训练的深度学习方法可以在一定程度上对蛋白质进行表征，但它们往往难以充分捕捉有关蛋白质结合界面的信息。为了解决这一局限性，我们提出了PPI-Graphomer模块，该模块整合了来自大规模语言模型和反向折叠模型的预训练特征。这种方法通过基于分子相互作用信息定义边关系和界面掩码来增强对蛋白质结合界面的表征。我们的模型在多个基准数据集上优于现有方法，并展示出强大的泛化能力。
