EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal deep learning enhances genomic risk prediction for cardiometabolic diseases

Taiyu Zhu iD, Upamanyu Ghose iD, Héctor Climente-González iD, Joanna Howson iD, Sile Hu iD, Alejo Nevado-Holgado iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag550 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Taiyu Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, University of Oxford, Warneford Lane, Warneford Hospital, OX3 7JX Oxford, United Kingdom. Hauptthemen laut MEDLINE: Deep Learning, Genetic Predisposition to Disease, Cardiovascular Diseases, Genomics. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Novo Nordisk, Novo Nordisk Postdoctoral Fellowship, University of Oxford.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiometabolic diseases (CMDs) are multifactorial disorders influenced by numerous genetic variants and their complex interactions. Although recent studies have advanced the understanding of genetic risk prediction, current approaches predominantly rely on linear models that may not fully capture the complex, nonlinear relationships between genetic factors. Here, we present DeepGP (Deep learning-based Genome-wide Predictor), a novel multimodal deep learning framework that incorporates bidirectional state space models to predict CMD risk using genome-wide variants and demographic data. We conducted extensive experiments to evaluate DeepGP’s performance. First, in simulation studies incorporating joint genetic and environmental interactions, we demonstrated DeepGP’s superior prediction performance across varying levels of heritability. When evaluated on eight CMDs in cohorts of European ancestry from the UK Biobank (UKB), DeepGP achieved significantly higher accuracy compared with conventional polygenic risk scores and machine learning methods. Model interpretability analysis identified both well-established genes and potential new signals contributing to the risk of the disease. Evaluation within UKB subpopulations of African and Caribbean ancestry provided preliminary evidence of within-resource transferability for type 2 diabetes. These results demonstrate the potential of deep learning technologies to enhance genetic risk stratification for complex diseases, while underscoring the need for external validation in more diverse cohorts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGenetic Predisposition to DiseaseCardiovascular DiseasesGenomicsMetabolic DiseasesHumansGenetic Risk ScoreGenome-Wide Association StudyUK BiobankDiabetes Mellitus, Type 2Predictive Learning ModelsPrediction Algorithms

Stichwörter der Autor:innen

cardiometabolic diseasesdeep learninggenetic risk predictiongenome-wide variants

Autor:innen und Institutionen

  • Department of Psychiatry, University of Oxford, Warneford Lane, Warneford Hospital, OX3 7JX Oxford, United Kingdom.
  • Novo Nordisk Research Centre Oxford, Innovation Building, Roosevelt Drive, Old Road Campus, OX3 7FZ Oxford, United Kingdom.

ORCID-Profile: Taiyu Zhu, Upamanyu Ghose, Héctor Climente-González, Joanna Howson, Sile Hu, Alejo Nevado-Holgado

Förderung

  • Novo Nordisk
  • Novo Nordisk Postdoctoral Fellowship
  • University of Oxford

Zitieren

APA

Zhu, T., Ghose, U., Climente-González, H., Howson, J., Hu, S., & Nevado-Holgado, A. (2026). Multimodal deep learning enhances genomic risk prediction for cardiometabolic diseases. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag550

Vancouver

Zhu T, Ghose U, Climente-González H, Howson J, Hu S, Nevado-Holgado A. Multimodal deep learning enhances genomic risk prediction for cardiometabolic diseases. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag550

BibTeX
@article{Zhu2026,
  author = {Zhu, Taiyu and Ghose, Upamanyu and Climente-González, Héctor and Howson, Joanna and Hu, Sile and Nevado-Holgado, Alejo},
  title = {Multimodal deep learning enhances genomic risk prediction for cardiometabolic diseases},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag550}
}
Kostenlos starten →