EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY-NC 4.0

A survey on deep learning for polygenic risk scores

Max Schuran iD, Benjamin Goudey iD, Gillian S Dite iD, Enes Makalic iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf373 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Max Schuran und 3 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, University of Melbourne, 207 Bouverie St, Carlton, VIC 3…. Hauptthemen laut MEDLINE: Deep Learning, Multifactorial Inheritance, Genetic Predisposition to Disease. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Australian Government through the Department of Education's National Industry, Australian Government, Australian Government through the Department of Education’s National Industry.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Polygenic risk scores (PRS) combine the effects of multiple genetic variants to predict an individual’s genetic predisposition to a disease. PRS typically rely on linear models, which assume that all genetic variants act independently. They often fall short in predictive accuracy and are not able to explain the genetic variability of a trait to the full extent. There is growing interest in applying deep learning neural networks to model PRS given their ability to model non-linear relationships and strong performance in other domains. We conducted a survey of the literature to investigate how neural networks model PRS. We categorize deep learning-based approaches by their underlying architecture, highlighting their modeling assumptions, likely strengths and potential weaknesses of the architectures. Several categories of neural network architectures exhibited promising signs for the improvement of PRS’ predictive power, namely sequence-based architectures, graph neural networks and those that incorporated biological knowledge. Additionally, the use of latent representations in autoencoders has improved predictive performance across diverse ancestries. However, a lack of existing model benchmarks on consistent datasets and phenotypes makes it challenging to understand the extent to which different architectures improve performance. Interpretability of deep learning-based PRS is also challenging with great care required when inferring causation. To address these challenges, we suggest the establishment and adherence to reporting standards and benchmarks to aid the development of deep learning-based PRS to find quantifiable trends in neural network architectures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMultifactorial InheritanceGenetic Predisposition to DiseaseHumansNeural Networks, ComputerGenetic Risk Score

Stichwörter der Autor:innen

deep learningmachine learningpolygenic-risk score

Autor:innen und Institutionen

  • Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, University of Melbourne, 207 Bouverie St, Carlton, VIC 3053, Australia.
  • Australia BioCommons, University of Melbourne, 21 Bedford St, North Melbourne, VIC 3051, Australia.
  • Florey Institute of Neuroscience and Mental Health, University of Melbourne, 30 Royal Parade, Parkville, VIC 3052, Australia.
  • ARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, 700 Swanston Street, Carlton, VIC 3010, Australia.
  • Rhythm Biosciences, Bio21 Institute, 30 Flemington Road, Parkville, VIC 3010, Australia.
  • Department of Data Science and AI, Faculty of Information Technology, Monash University, Woodside Building (20 Exhibition Walk), Monash University Clayton Campus, VIC 3800, Australia.

ORCID-Profile: Max Schuran, Benjamin Goudey, Gillian S Dite, Enes Makalic

Förderung

  • Australian Government through the Department of Education's National Industry
  • Australian Government
  • Australian Government through the Department of Education’s National Industry

Zitieren

APA

Schuran, M., Goudey, B., Dite, G. S., & Makalic, E. (2025). A survey on deep learning for polygenic risk scores. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf373

Vancouver

Schuran M, Goudey B, Dite GS, Makalic E. A survey on deep learning for polygenic risk scores. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf373

BibTeX
@article{Schuran2025,
  author = {Schuran, Max and Goudey, Benjamin and Dite, Gillian S and Makalic, Enes},
  title = {A survey on deep learning for polygenic risk scores},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf373}
}
Kostenlos starten →