MS-ConTab: Multi-Scale Contrastive Learning of Mutation Signatures for Pan Cancer Representation and Stratification

TL;DR

This paper introduces a novel unsupervised contrastive learning framework that clusters cancer types based on mutation signatures, providing biologically meaningful groupings aligned with known mutational processes and tissue origins.

Contribution

It is the first application of contrastive learning for cohort-level cancer clustering using mutation data, combining gene-level and chromosome-level signatures for improved representation.

Findings

Clusters align with known mutational processes

Framework is scalable and interpretable

Effective in grouping 43 cancer types

Abstract

Motivation. Understanding the pan-cancer mutational landscape offers critical insights into the molecular mechanisms underlying tumorigenesis. While patient-level machine learning techniques have been widely employed to identify tumor subtypes, cohort-level clustering, where entire cancer types are grouped based on shared molecular features, has largely relied on classical statistical methods. Results. In this study, we introduce a novel unsupervised contrastive learning framework to cluster 43 cancer types based on coding mutation data derived from the COSMIC database. For each cancer type, we construct two complementary mutation signatures: a gene-level profile capturing nucleotide substitution patterns across the most frequently mutated genes, and a chromosome-level profile representing normalized substitution frequencies across chromosomes. These dual views are encoded using TabNet encoders and optimized via a multi-scale contrastive learning objective (NT-Xent loss) to learn unified cancer-type embeddings. We demonstrate that the resulting latent representations yield biologically meaningful clusters of cancer types, aligning with known mutational processes and tissue origins. Our work represents the first application of contrastive learning to cohort-level cancer clustering, offering a scalable and interpretable framework for mutation-driven cancer subtyping.