Joint representation learning for oncology applications
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btaf597 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Tanya Nandan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biosystems Sciences and Engineering (D BSSE), ETH Zürich, Zürich 8092, Switzerland. Hauptthemen laut MEDLINE: Computational Biology, Machine Learning, Brain Neoplasms. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss National Science Foundation, Basel Research Center for Child Health Postdoctoral Excellence Fellowship.
Abstract (Originalsprache)
Motivation 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. Results 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. Availability and implementation 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
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biosystems Sciences and Engineering (D BSSE), ETH Zürich, Zürich 8092, Switzerland.
- Department of Health Sciences and Technology (D HEST), ETH Zürich, Zürich 8092, Switzerland.
- Department of Quantitative Medicine, University of Zürich, Zürich 8006, Switzerland.
- Department of Medical Oncology & Haematology, University Hospital Zürich, Zürich 8091, Switzerland.
- Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern 3012, Switzerland.
ORCID-Profile: Tanya Nandan, Sarah C Brüningk
Förderung
- Swiss National Science Foundation
- Basel Research Center for Child Health Postdoctoral Excellence Fellowship
Zitieren
APA
Nandan, T., Fan, B., Håkansson, S., Jutzeler, C. R., & Brüningk, S. C. (2026). Joint representation learning for oncology applications. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf597
Vancouver
Nandan T, Fan B, Håkansson S, Jutzeler CR, Brüningk SC. Joint representation learning for oncology applications. Bioinformatics. 2026. doi:10.1093/bioinformatics/btaf597
BibTeX
@article{Nandan2026,
author = {Nandan, Tanya and Fan, Bowen and Håkansson, Samuel and Jutzeler, Catherine R and Brüningk, Sarah C},
title = {Joint representation learning for oncology applications},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btaf597}
}
EUVIMED