Rethinking Cancer Gene Identification through Graph Anomaly Analysis

TL;DR

This paper introduces HIPGNN, a novel graph neural network that captures biological anomalies like weight heterogeneity in protein interaction networks to improve cancer gene identification.

Contribution

It pioneers the modeling of biological anomalies as graph anomalies and develops HIPGNN to better analyze complex protein interaction patterns for cancer genes.

Findings

HIPGNN outperforms existing methods on STRINGdb and CPDB datasets.

Weight heterogeneity is a distinctive anomaly in cancer gene graphs.

Spectral analysis reveals energy concentration shifts due to anomalies.

Abstract

Graph neural networks (GNNs) have shown promise in integrating protein-protein interaction (PPI) networks for identifying cancer genes in recent studies. However, due to the insufficient modeling of the biological information in PPI networks, more faithfully depiction of complex protein interaction patterns for cancer genes within the graph structure remains largely unexplored. This study takes a pioneering step toward bridging biological anomalies in protein interactions caused by cancer genes to statistical graph anomaly. We find a unique graph anomaly exhibited by cancer genes, namely weight heterogeneity, which manifests as significantly higher variance in edge weights of cancer gene nodes within the graph. Additionally, from the spectral perspective, we demonstrate that the weight heterogeneity could lead to the "flattening out" of spectral energy, with a concentration towards the extremes of the spectrum. Building on these insights, we propose the HIerarchical-Perspective Graph Neural Network (HIPGNN) that not only determines spectral energy distribution variations on the spectral perspective, but also perceives detailed protein interaction context on the spatial perspective. Extensive experiments are conducted on two reprocessed datasets STRINGdb and CPDB, and the experimental results demonstrate the superiority of HIPGNN.