# Joint representation learning for oncology applications

## TL;DR

This paper introduces a new method for combining cancer imaging and molecular data to better understand tumor biology and improve computational approaches in oncology.

## Contribution

The novel contribution is an unsupervised manifold alignment approach called Joint MDS3 for multi-modal data integration in oncology.

## Key findings

- Joint MDS outperforms baseline methods in label transfer accuracy and reduces incorrect matches in real-world datasets.
- The method achieves an average label transfer accuracy of 74.8%, significantly higher than existing approaches.
- Joint MDS3 is demonstrated on both synthetic and real-world examples, showing its potential for diverse data integration.

## Abstract

The integration of tumour imaging data and molecular sequencing information can advance our understanding of cancer biology by combining complementary perspectives of tumour phenotype and genotype. However, integrating multi-modal data across heterogeneous and high-dimensional data domains remains a significant computational challenge.

Here, we introduce an unsupervised manifold alignment approach for real-world data integration based on Joint Multidimensional Scaling (Joint MDS) and extend it to a three-modality framework (Joint MDS3). We apply this method to integrate radiomic features from magnetic resonance imaging (MRI) with transcriptomic, epigenomic, and copy number variation (CNV) data from patients with glioblastoma multiforme (GBM) and lower-grade gliomas (LGG). Compared to baselines such as Pamona and single-cell optimal transport (SCOTv2), Joint MDS consistently outperforms baseline Pamona in cases and achieves competitive performance relative to baseline SCOTv2, outperforming its fraction of samples closer to an incorrect match (FOSCTTM) in four out of six cases. Joint MDS attains an average label transfer accuracy of 74.8%, approximately 4% higher than that of Pamona and SCOTv2, and reduces FOSCTTM to 51% or less across real-world datasets. We further demonstrate our extension JointMDS3 on both synthetic and real-world examples. Our results highlight the potential of Joint MDS to enhance the integration of diverse data types into a unified representation, ultimately advancing computational approaches in complex diseases.

The implementation of our work is available at gitlab.ethz.ch/BMDSlab/publications/oncology/joint-representation-learning-for-oncology-applications and archived at doi.org/10.5281/zenodo.17219404