PuSH - Publikationsserver des Helmholtz Zentrums München

Sens, D. ; Shilova, L. ; Dalca, A.V.* ; Schnabel, J.A. ; Casale, F.P.

GEMCONT: Genetics-based Multimodal Contrastive Learning Enhances Phenotypic embeddings and Boosts Genetic Discovery.

In: (9th International Conference on Medical Imaging with Deep Learning, MIDL 2026, 8-10 July 2026, Chientan). 2026. 3443-3463 (Proceedings of Machine Learning Research ; 315)
Genetic variation provides stable, time-invariant markers of disease risk and can therefore reveal upstream mechanisms underlying complex traits. Genome-wide association studies (GWAS) have identified thousands of loci associated with disease, yet most remain difficult to interpret because the intermediate phenotypes linking genotype to disease are unknown. Here, we address the question whether disease-associated genetic loci can be directly used to extract such risk-related features from quantitative phenotypes, including functional tests and medical imaging. We introduce GEMCONT (GEnetics-based Multimodal CONTrastive Learning), a multimodal contrastive learning framework that aligns genotype and phenotype representations in a shared latent space. Unlike task-agnostic multimodal pretraining, GEMCONT is disease-conditioned: GWAS-informed variant panels act as targeted supervision to learn risk-relevant imaging embeddings. To reflect the weak, additive nature of genetic effects, it employs a linear genetic encoder alongside a deep phenotypic encoder. We validate GEMCONT in controlled simulations and apply it to two real-world settings: spirometry curves for asthma and retinal fundus images for glaucoma. In both, GEMCONT improves disease risk prediction and enhances recovery of genetic associations compared with standard unsupervised or polygenic risk–based models. Altogether, our results demonstrate that incorporating stable genetic supervision into multimodal representation learning enables the extraction of genetically informed risk traits, refining disease phenotypes and improving the interpretability of association studies.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Genome-wide Association Studies ; Imaging Genetics ; Machine Learning–derived Phenotypes ; Medical Imaging ; Multimodal Contrastive Learning
Konferenztitel 9th International Conference on Medical Imaging with Deep Learning, MIDL 2026
Konferzenzdatum 8-10 July 2026
Konferenzort Chientan
Quellenangaben Band: 315, Heft: , Seiten: 3443-3463 Artikelnummer: , Supplement: ,
Institut(e) Institute of AI for Health (AIH)
Institute for Machine Learning in Biomed Imaging (IML)