PathMoG: A Pathway-Centric Modular Graph Neural Network for Multi-Omics Survival Prediction

TL;DR

PathMoG is a novel pathway-centric graph neural network that improves multi-omics cancer survival prediction by integrating diverse genomic data and providing interpretable risk stratification.

Contribution

It introduces a hierarchical modulation and dual-level attention mechanism within a pathway-based GNN for enhanced survival prediction and interpretability.

Findings

Consistently outperforms baseline survival models across 10 TCGA cancer types.

Provides multi-level interpretability at gene, pathway, and patient levels.

Demonstrates the effectiveness of pathway-centric modular design in multi-omics data analysis.

Abstract

Cancer survival prediction from multi-omics data remains challenging because prognostic signals are high-dimensional, heterogeneous, and distributed across interacting genes and pathways. We propose PathMoG, a pathway-centric modular graph neural network for multi-omics survival prediction. PathMoG reorganizes genome-scale inputs into 354 KEGG-informed pathway modules, introduces a Hierarchical Omics Modulation module to condition gene-expression representations on mutation, copy number variation, pathway, and clinical context, and uses dual-level attention to capture both intra-pathway driver signals and inter-pathway clinical relevance. We evaluated PathMoG on 5,650 patients across 10 TCGA cancer types and observed consistent improvements over representative survival baselines. The framework further provides gene-level, pathway-level, and patient-level interpretability, supporting biologically grounded and clinically relevant risk stratification.