MVSOPPIS 数据集

预测蛋白质-蛋白质相互作用 （PPI） 位点对于促进我们对蛋白质相互作用的理解至关重要，因为准确的预测可以显著降低实验成本和时间。虽然在单个氨基酸残基水平上鉴定结合位点方面取得了相当大的进展，但过渡边界处残基子序列的预测准确性——例如由奇异结构（连续相互作用残基片段的突变特征）或边缘结构（相互作用/非相互作用残基片段之间的边界转换）等模式表示的序列——仍然需要改进。为了应对这一挑战，我们提出了一种名为 MVSO-PPIS 的新型 PPI 位点预测方法。该方法集成了两个互补的特征提取模块，一个基于子图的模块和一个增强的图注意力模块。提取的特征使用基于注意力的融合机制进行融合，产生一种复合表示，可以捕获局部蛋白质亚结构和全局上下文依赖关系。MVSO-PPIS 经过训练，可共同优化三个目标：PPI 位点的整体预测准确性、边缘结构一致性以及识别 PPI 位点序列中的独特结构模式。基准数据集的实验结果表明，MVSO-PPIS 在准确性和结构可解释性方面都优于现有的基线模型。

Predicting Protein-Protein Interaction (PPI) sites is crucial for advancing our understanding of protein interactions, as accurate predictions can significantly reduce experimental costs and time. While considerable progress has been made in identifying binding sites at the level of individual amino acid residues, the prediction accuracy of subsequences of residues at transition boundaries—such as sequences represented by patterns like singular structures (mutational characteristics of continuous interacting residue segments) or edge structures (boundary transitions between interacting and non-interacting residue segments)—still needs improvement. To address this challenge, we propose a novel PPI site prediction method called MVSO-PPIS. This method integrates two complementary feature extraction modules: a subgraph-based module and an enhanced graph attention module. The extracted features are fused using an attention-based fusion mechanism to generate a composite representation that captures local protein substructures and global contextual dependencies. MVSO-PPIS is trained to jointly optimize three objectives: overall prediction accuracy of PPI sites, edge structure consistency, and identification of unique structural patterns in PPI site sequences. Experimental results on benchmark datasets show that MVSO-PPIS outperforms existing baseline models in both accuracy and structural interpretability.