Multi-Omics Analysis for Cancer Subtype Inference via Unrolling Graph Smoothness Priors

TL;DR

This paper introduces GTMancer, a novel graph transformer framework that unrolls multiplex graph optimization with dual attention to improve multi-omics cancer subtype classification, outperforming existing methods on real datasets.

Contribution

The paper presents a new multi-omics integration framework using graph transformers with unrolled optimization and dual attention, enhancing cancer subtype inference.

Findings

GTMancer outperforms state-of-the-art algorithms on seven cancer datasets.

The method effectively captures complex multi-omics relationships.

Unrolling graph optimization improves representation quality.

Abstract

Integrating multi-omics datasets through data-driven analysis offers a comprehensive understanding of the complex biological processes underlying various diseases, particularly cancer. Graph Neural Networks (GNNs) have recently demonstrated remarkable ability to exploit relational structures in biological data, enabling advances in multi-omics integration for cancer subtype classification. Existing approaches often neglect the intricate coupling between heterogeneous omics, limiting their capacity to resolve subtle cancer subtype heterogeneity critical for precision oncology. To address these limitations, we propose a framework named Graph Transformer for Multi-omics Cancer Subtype Classification (GTMancer). This framework builds upon the GNN optimization problem and extends its application to complex multi-omics data. Specifically, our method leverages contrastive learning to embed multi-omics data into a unified semantic space. We unroll the multiplex graph optimization problem in that unified space and introduce dual sets of attention coefficients to capture structural graph priors both within and among multi-omics data. This approach enables global omics information to guide the refining of the representations of individual omics. Empirical experiments on seven real-world cancer datasets demonstrate that GTMancer outperforms existing state-of-the-art algorithms.