SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein-Protein Interaction Prediction

TL;DR

SemiGNN-PPI introduces a self-ensembling multi-graph neural network that effectively predicts protein-protein interactions, especially under limited labels and domain shifts, by modeling correlations and label dependencies with a GNN and Mean Teacher framework.

Contribution

It proposes a novel semi-supervised multi-graph neural network that models protein correlations and label dependencies, enhancing PPI prediction in complex real-world scenarios.

Findings

Outperforms state-of-the-art methods on various PPI datasets.

Effective in scenarios with limited annotations and unseen data.

Leverages unlabeled data through self-ensembling and graph consistency constraints.

Abstract

Protein-protein interactions (PPIs) are crucial in various biological processes and their study has significant implications for drug development and disease diagnosis. Existing deep learning methods suffer from significant performance degradation under complex real-world scenarios due to various factors, e.g., label scarcity and domain shift. In this paper, we propose a self-ensembling multigraph neural network (SemiGNN-PPI) that can effectively predict PPIs while being both efficient and generalizable. In SemiGNN-PPI, we not only model the protein correlations but explore the label dependencies by constructing and processing multiple graphs from the perspectives of both features and labels in the graph learning process. We further marry GNN with Mean Teacher to effectively leverage unlabeled graph-structured PPI data for self-ensemble graph learning. We also design multiple graph consistency constraints to align the student and teacher graphs in the feature embedding space, enabling the student model to better learn from the teacher model by incorporating more relationships. Extensive experiments on PPI datasets of different scales with different evaluation settings demonstrate that SemiGNN-PPI outperforms state-of-the-art PPI prediction methods, particularly in challenging scenarios such as training with limited annotations and testing on unseen data.