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

2025-08-08

AI Summary

To address the challenge of low accuracy in cancer subtyping caused by strong heterogeneity and complex coupling relationships among multi-omics data, this paper proposes GTMancer—a unified framework integrating graph neural networks and graph Transformers to construct a cross-omics semantic embedding space. It introduces a dual-attention mechanism to jointly model intra-omics feature dependencies and inter-omics semantic associations, while leveraging global graph smoothing priors and contrastive learning for robust representation optimization. Extensive experiments across seven real-world cancer cohorts demonstrate that GTMancer significantly outperforms state-of-the-art methods. It enables fine-grained dissection of intratumoral heterogeneity and identifies novel cancer subtypes with enhanced biological coherence and clinical interpretability. By providing a scalable, integrative paradigm for multi-omics fusion, GTMancer advances precision oncology through improved molecular stratification.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• Integrating multi-omics data for cancer subtype classification
• Addressing coupling neglect in heterogeneous omics analysis
• Improving precision oncology via graph-based contrastive learning

Innovation

• Unrolling multiplex graph optimization for multi-omics
• Dual attention coefficients capture structural priors
• Contrastive learning embeds multi-omics data