Meng Lu, Wei Lishuai, Wu Rina
College of Information Science and Engineering, Northeastern University, China.
College of Information Science and Engineering, Northeastern University, China.
Int J Biol Macromol. 2025 Apr;300:140096. doi: 10.1016/j.ijbiomac.2025.140096. Epub 2025 Jan 21.
Protein-protein interactions (PPI) are crucial for understanding numerous biological processes and pathogenic mechanisms. Identifying interaction sites is essential for biomedical research and targeted drug development. Compared to experimental methods, accurate computational approaches for protein-protein interaction sites (PPIS) prediction can save significant time and costs. In this study, we propose a novel model named MVGNN-PPIS. To the best of our knowledge, it is the first to utilize predicted structures generated by AlphaFold3, and combined with transfer learning techniques, for predicting PPIS. This approach addresses the limitations of traditional methods that depend on native protein structures and multiple sequence alignments (MSA). Additionally, we introduced a multi-view graph framework based on two types of graph structures: the k-nearest neighbor graph and the adjacency matrix. By alternately employing a Graph Transformer and Graph Convolutional Networks (GCN) to aggregate node information, this framework effectively captures both local and global dependencies of each residue in the predicted structures, thereby significantly enhancing the model's sensitivity to binding sites. This framework further integrates direction, distances and angular information between the 3D coordinates of side-chain atom centroids to construct a relative coordinate system, generating enhanced edge features that ensure the model's equivariance to molecular translations and rotations in space. During training, the Focal Loss function is employed to effectively address the class imbalance in the dataset. Experimental results demonstrate that MVGNN outperforms the current state-of-the-art methods across multiple PPIS benchmark datasets. To further validate the model's generalization capability, we extended MVGNN to the domain of predicting protein-nucleic acid interaction sites, where it also achieved superior performance.
蛋白质-蛋白质相互作用（PPI）对于理解众多生物过程和致病机制至关重要。识别相互作用位点对于生物医学研究和靶向药物开发至关重要。与实验方法相比，用于预测蛋白质-蛋白质相互作用位点（PPIS）的准确计算方法可以节省大量时间和成本。在本研究中，我们提出了一种名为MVGNN-PPIS的新型模型。据我们所知，它是第一个利用AlphaFold3生成的预测结构，并结合迁移学习技术来预测PPIS的模型。这种方法解决了传统方法依赖于天然蛋白质结构和多序列比对（MSA）的局限性。此外，我们引入了一种基于两种图结构的多视图图框架：k近邻图和邻接矩阵。通过交替使用图变换器和图卷积网络（GCN）来聚合节点信息，该框架有效地捕捉了预测结构中每个残基的局部和全局依赖性，从而显著提高了模型对结合位点的敏感性。该框架进一步整合了侧链原子质心的3D坐标之间的方向、距离和角度信息，以构建相对坐标系，生成增强的边特征，确保模型在空间中对分子平移和旋转的等变性。在训练过程中，采用焦点损失函数有效地解决了数据集中的类别不平衡问题。实验结果表明，MVGNN在多个PPIS基准数据集上优于当前最先进的方法。为了进一步验证模型的泛化能力，我们将MVGNN扩展到预测蛋白质-核酸相互作用位点的领域，在该领域它也取得了优异的性能。
