Enhancing Multi-Label Protein Interaction Prediction via Hypergraph Modeling of Higher-Order Patterns

Protein-protein interactions (PPIs) are central to understanding cellular mechanisms and disease pathogenesis. While conventional graph-based models have achieved significant success in predicting PPIs, they are limited to pairwise interactions, failing to capture higher-order relational patterns prevalent in biological systems. In this study, we propose HGNN-PPI, a novel framework that integrates hypergraph neural networks with traditional graph neural models to enhance multi-label PPI prediction. Our method combines three complementary perspectives: global graph structure, local subgraph features, and higher-order interaction motifs modeled through a hypergraph constructed from biologically meaningful feedforward and feedback loops. To address the class imbalance inherent in PPI datasets, we use an asymmetric loss function tailored for multi-label learning. Experimental results on benchmark datasets (SHS27k and SHS148k) demonstrate that HGNN-PPI consistently outperforms state-of-the-art methods, particularly in capturing rare interaction types. These findings highlight the effectiveness of incorporating higher-order biological motifs and hypergraph structures in improving PPI prediction.