EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep integrative models for large-scale human genomics

Arnór I Sigurdsson iD, Ioannis Louloudis, Karina Banasik iD, David Westergaard iD, Ole Winther, Ole Lund, Sisse Rye Ostrowski iD, Christian Erikstrup iD, Ole Birger Vesterager Pedersen, Mette Nyegaard iD, DBDS Genomic Consortium, Søren Brunak iD und 2 weitere

Nucleic Acids Research · 07.07.2023 · 51 (12) · e67-e67

DOI: 10.1093/nar/gkad373 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 24.05.2023. Verfasst von Arnór I Sigurdsson und 13 weiteren Autor:innen. Beteiligte Einrichtung: Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, 2200 Copenhagen N, Denmark. Hauptthemen laut MEDLINE: Multifactorial Inheritance, Polymorphism, Single Nucleotide, Models, Genetic. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Novo Nordisk Foundation, Lundbeck Foundation, Danish National Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Polygenic risk scores (PRSs) are expected to play a critical role in precision medicine. Currently, PRS predictors are generally based on linear models using summary statistics, and more recently individual-level data. However, these predictors mainly capture additive relationships and are limited in data modalities they can use. We developed a deep learning framework (EIR) for PRS prediction which includes a model, genome-local-net (GLN), specifically designed for large-scale genomics data. The framework supports multi-task learning, automatic integration of other clinical and biochemical data, and model explainability. When applied to individual-level data from the UK Biobank, the GLN model demonstrated a competitive performance compared to established neural network architectures, particularly for certain traits, showcasing its potential in modeling complex genetic relationships. Furthermore, the GLN model outperformed linear PRS methods for Type 1 Diabetes, likely due to modeling non-additive genetic effects and epistasis. This was supported by our identification of widespread non-additive genetic effects and epistasis in the context of T1D. Finally, we constructed PRS models that integrated genotype, blood, urine, and anthropometric data and found that this improved performance for 93% of the 290 diseases and disorders considered. EIR is available at https://github.com/arnor-sigurdsson/EIR.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Multifactorial InheritancePolymorphism, Single NucleotideModels, GeneticHumansGenetic Predisposition to DiseaseGenome, HumanGenome-Wide Association StudyGenomicsGenotypeRisk Factors

Autor:innen und Institutionen

  • Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, 2200 Copenhagen N, Denmark.
  • The Novo Nordisk Foundation Center for Genomic Mechanisms of Disease, Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA.
  • Section for Cognitive Systems, Department of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kgs. Lyngby, Denmark.
  • Bioinformatics Centre, Department of Biology, University of Copenhagen, 2200 Copenhagen N, Denmark.
  • Center for Genomic Medicine, Rigshospitalet (Copenhagen University Hospital), Copenhagen 2100, Denmark.
  • Danish National Genome Center, Ørestads Boulevard 5, 2300 Copenhagen S, Denmark.

ORCID-Profile: Arnór I Sigurdsson, Karina Banasik, David Westergaard, Sisse Rye Ostrowski, Christian Erikstrup, Mette Nyegaard, Søren Brunak, Simon Rasmussen

Förderung

  • Novo Nordisk Foundation
  • Lundbeck Foundation
  • Danish National Research Foundation
  • UK Biobank Resource
  • Danish National Committee on Health Research Ethics
  • National Life Science Supercomputing Center – Computerome at DTU and UCPH

Zitieren

APA

Sigurdsson, A. I., Louloudis, I., Banasik, K., Westergaard, D., Winther, O., Lund, O., Ostrowski, S. R., Erikstrup, C., Pedersen, O. B. V., Nyegaard, M., DBDS Genomic Consortium, Brunak, S., Vilhjálmsson, B. J., & Rasmussen, S. (2023). Deep integrative models for large-scale human genomics. Nucleic Acids Research, 51(12), e67-e67. https://doi.org/10.1093/nar/gkad373

Vancouver

Sigurdsson AI, Louloudis I, Banasik K, Westergaard D, Winther O, Lund O, et al. Deep integrative models for large-scale human genomics. Nucleic Acids Research. 2023;51(12):e67-e67. doi:10.1093/nar/gkad373

BibTeX
@article{Sigurdsson2023,
  author = {Sigurdsson, Arnór I and Louloudis, Ioannis and Banasik, Karina and Westergaard, David and Winther, Ole and Lund, Ole and Ostrowski, Sisse Rye and Erikstrup, Christian and Pedersen, Ole Birger Vesterager and Nyegaard, Mette and DBDS Genomic Consortium, DBDS Genomic Consortium and Brunak, Søren and Vilhjálmsson, Bjarni J and Rasmussen, Simon},
  title = {Deep integrative models for large-scale human genomics},
  journal = {Nucleic Acids Research},
  year = {2023},
  volume = {51},
  number = {12},
  pages = {e67--e67},
  doi = {10.1093/nar/gkad373}
}
Kostenlos starten →