Back

Breast Cancer Subtyping with HyperCLSA: A Hypergraph Contrastive Learning Pipeline for Multi-Omics Data Integration

Bhole, G.; HC, P.; Jayachandran, M.; Vinod, P.; Bhimalapuram, P.

2025-10-12 cancer biology
10.1101/2025.09.22.677517 bioRxiv
Show abstract

Accurate molecular subtyping of cancer is crucial for advancing personalized medicine. Although multiomics data contain valuable predictive information, effectively integrating them is challenging due to differences across modalities, high dimensionality, and complex cross-modal biological interactions. We propose HyperCLSA (Hyper-graph Contrastive Learning with Self-Attention), a novel deep learning framework for efficient multi-omics integration in breast cancer subtyping. HyperCLSA combines hypergraph-based sample encoding, supervised contrastive learning for latent space alignment, and multi-head self-attention for adaptive fusion of omics modalities. Evaluated on The Cancer Genome Atlas Breast Cancer dataset (TCGA-BRCA) for PAM50 subtype classification, HyperCLSA achieves a state-of-the-art accuracy of 90.1%, significantly outperforming established baselines. Our results demonstrate HyperCLSAs effectiveness in extracting complementary information across heterogeneous omics sources, providing a robust framework for molecular characterization of breast cancer.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.