OmicsCL: Unsupervised Contrastive Learning for Cancer Subtype Discovery and Survival Stratification

TL;DR

OmicsCL is an unsupervised contrastive learning framework that integrates multi-omics data to discover cancer subtypes and stratify patient survival, showing strong clinical relevance and robustness.

Contribution

It introduces a novel survival-aware contrastive loss for joint embedding of heterogeneous omics data in an unsupervised manner.

Findings

Uncovers clinically meaningful cancer subtypes.

Achieves strong concordance with patient survival.

Enhances predictive power through survival-aware loss.

Abstract

Unsupervised learning of disease subtypes from multi-omics data presents a significant opportunity for advancing personalized medicine. We introduce OmicsCL, a modular contrastive learning framework that jointly embeds heterogeneous omics modalities-such as gene expression, DNA methylation, and miRNA expression-into a unified latent space. Our method incorporates a survival-aware contrastive loss that encourages the model to learn representations aligned with survival-related patterns, without relying on labeled outcomes. Evaluated on the TCGA BRCA dataset, OmicsCL uncovers clinically meaningful clusters and achieves strong unsupervised concordance with patient survival. The framework demonstrates robustness across hyperparameter configurations and can be tuned to prioritize either subtype coherence or survival stratification. Ablation studies confirm that integrating survival-aware loss significantly enhances the predictive power of learned embeddings. These results highlight the promise of contrastive objectives for biological insight discovery in high-dimensional, heterogeneous omics data.