Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach

2026-05-11

AI Summary

This work proposes L3-PPI, a model-agnostic graph prompt learning framework for protein–protein interaction (PPI) prediction that explicitly incorporates the biological “L3 rule” as a tunable prior—a principle previously unexploited in learning-based approaches. Addressing the common limitation of existing methods that rely solely on generic aggregation strategies without modeling biological priors, L3-PPI reformulates pairwise PPI classification as a graph-level classification task by constructing prompt graphs. It introduces a lightweight, plug-and-play graph prompt module to universally enhance diverse backbone predictors. By integrating L3-path regularization with synthetic path generation, the method significantly boosts the performance of state-of-the-art PPI predictors across multiple benchmark datasets, demonstrating both the efficacy of the L3 rule and the broad applicability of the proposed framework.

Abstract

Protein-protein interactions (PPIs) are fundamental to cellular function and disease mechanisms. Current learning-based PPI predictors focus on learning powerful protein representations but neglect designing specialized classification heads. They mainly rely on generic aggregating methods like concatenation or dot products, which lack biological insight. Motivated by the biological "L3 rule", where multiple length-3 paths between a pair of proteins indicate their interaction likelihood, our study addresses this gap by designing a biologically informed PPI classifier. In this paper, we provide empirical evidence that popular PPI datasets strongly support the L3 rule. We propose an L3-path-regularized graph prompt learning method called L3-PPI, which can generate a prompt graph with virtual L3 paths based on protein representations and controls the number of paths. L3-PPI reformulates the classification of protein embedding pairs into a graph-level classification task over the generated prompt graph. This lightweight module seamlessly integrates with PPI predictors as a plug-and-play component, injecting the interaction prior of complementarity to enhance performance. Extensive experiments show that L3-PPI achieves superior performance enhancements over advanced competitors.

Problem

• Protein-Protein Interaction
• Interaction Prior
• L3 Rule
• Classification Head
• Biological Insight

Innovation

• L3 rule
• graph prompt learning
• protein-protein interaction prediction
• model-agnostic
• interaction prior