Structure-Guided Adaptive Propagation for Protein-Protein Interaction Site Prediction
2026-06-01 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed a new method called SGAP-PPIS to better predict where proteins interact with each other. Unlike previous models that treat all parts of a protein the same, their method adjusts how information spreads based on each part's unique local shape and environment. This adaptive approach helps the model tell real interaction sites apart from similar-looking but non-interacting areas. Their experiments show that SGAP-PPIS performs well compared to existing techniques.
protein-protein interaction sitesgraph neural networksequivariant networksadaptive propagationstructural bioinformaticsresidue-level featuresgeometric microenvironmentdeep learninginteraction site prediction
Authors
Enqiang Zhu, Yizi Liu, Yilong Luo, Yao Chen, Yu Zhang, Baoshan Ma
Abstract
Accurate prediction of protein-protein interaction sites (PPIS) is essential for understanding cellular processes, disease mechanisms, and therapeutic target discovery. Graph-based deep learning has advanced PPIS prediction by incorporating residue-level structural context. However, most graph-based models still rely on fixed propagation schemes that treat all residues similarly, despite the structural and functional heterogeneity of protein interfaces. Such propagation may limit the ability to adapt information diffusion to local geometric environments, making it difficult to distinguish true interaction sites from structurally similar non-interacting neighbors. We present SGAP-PPIS, a structure-guided adaptive propagation model for PPIS prediction. Rather than using a fixed propagation mechanism, SGAP-PPIS leverages multi-scale geometric states from an equivariant graph neural network to generate residue-wise propagation coefficients. This design allows each residue to adaptively balance local feature preservation and neighborhood diffusion according to its geometric microenvironment. Experimental results show that SGAP-PPIS achieves competitive performance among the state-of-the-art methods on Test\_60. Ablation studies show that geometry-conditioned adaptive propagation, scale-aligned geometric guidance, and multi-step propagation-state representation jointly drive these improvements.