EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GEiPRS: a fast and powerful machine learning method for polygenic risk score prediction by leveraging genotype–environment interactions

Le Huang, Wujuan Zhong, Song Zhai, Judong Shen iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag164 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Le Huang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Curriculum in Bioinformatics and Computational Biology, University of North Carolina at Chapel Hill, 120 Mason Farm Road, Chapel Hill, NC 27514, Unit…. Hauptthemen laut MEDLINE: Gene-Environment Interaction, Machine Learning, Genome-Wide Association Study, Multifactorial Inheritance. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Penalized regression methods are widely used for variant selection and polygenic risk score (PRS) analysis in disease genome-wide association studies (GWASs). However, the existing penalized regression-based PRS methods often neglect genotype–environment interaction (GEI) and struggles with high-dimensional GWAS data. To overcome these challenges, we propose a novel machine learning-based PRS method Genotype–Environment interaction-based Polygenic Risk Score (GEiPRS). GEiPRS simultaneously models both genotype (G) and GEI effects and efficiently handle high-dimensional GWAS data in terms of variant selection and PRS construction and prediction. A novel algorithm called Group ITerative LAsso with Batch Screening (GITLABS) is developed for efficiently calculating iterative Group Lasso (GL) or Sparse Group Lasso (SGL) solutions for variant selection in GEiPRS, enabling high-dimensional variant selection and PRS construction in a computationally efficient manner. GITLABS consists of three steps: screening variants using strong rules, fitting GL/SGL model with the selected variants, and checking validity of the model solutions based on safe rules. Extensive simulations show GEiPRS outperforms existing PRS methods in terms of GEI–PRS association P-values, prediction accuracy, subgroup risk stratification, and computational efficiency. We further apply the GEiPRS method to large-scale UK Biobank GWAS data for three pairs of quantitative traits and environment variables and the results demonstrate superior performance of GEiPRS over existing PRS methods and support the main conclusions from our simulations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene-Environment InteractionMachine LearningGenome-Wide Association StudyMultifactorial InheritanceGenetic Risk ScoreHumansAlgorithmsGenotypePolymorphism, Single NucleotidePrediction Algorithms

Stichwörter der Autor:innen

GEiPRSGroup ITerative LAsso with batch screeninggenotype–environment interactionpenalized regressionpolygenic risk score

Autor:innen und Institutionen

  • Curriculum in Bioinformatics and Computational Biology, University of North Carolina at Chapel Hill, 120 Mason Farm Road, Chapel Hill, NC 27514, United States.
  • GE HealthCare, 1100 112 Ave NE, Suite 100, Bellevue, WA 98004, United States.
  • Biostatistics and Research Decision Sciences, Merck & Co., Inc., 126 East Lincoln Avenue, Rahway, NJ 07065, United States.

ORCID-Profile: Judong Shen

Zitieren

APA

Huang, L., Zhong, W., Zhai, S., & Shen, J. (2026). GEiPRS: a fast and powerful machine learning method for polygenic risk score prediction by leveraging genotype–environment interactions. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag164

Vancouver

Huang L, Zhong W, Zhai S, Shen J. GEiPRS: a fast and powerful machine learning method for polygenic risk score prediction by leveraging genotype–environment interactions. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag164

BibTeX
@article{Huang2026,
  author = {Huang, Le and Zhong, Wujuan and Zhai, Song and Shen, Judong},
  title = {GEiPRS: a fast and powerful machine learning method for polygenic risk score prediction by leveraging genotype–environment interactions},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag164}
}
Kostenlos starten →