DeepU-PRS: nonlinear and uncertainty-aware SNP heritability modeling for annotation-informed polygenic risk scoring.
- 1Graduate School of Data Science, Seoul National University, Seoul, South Korea.
- 2Department of Biostatistics, Epidemiology & Informatics, The Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States.
Abstract
Polygenic risk scores (PRSs) are widely used to quantify genetic predisposition to complex traits, and their predictive accuracy can be enhanced by incorporating functional annotations into single-nucleotide polymorphism (SNP) effect-size estimation. Existing approaches typically assume linear relationships between annotations and SNP effects, neglecting predictive aleatoric variance and potential nonlinear regulatory interactions. To evaluate the gains of nonlinear and uncertainty-aware modeling, we developed DeepU-PRS, a deep ensemble framework that extends the linear BLD-LDAK model with a neural network trained on functional annotations to jointly estimate SNP heritability and its aleatoric uncertainty, which are then integrated into a Bayesian PRS model. Across 28 continuous and 8 disease phenotypes in the UK Biobank, DeepU-PRS improved the mean continuous R2 by approximately 10% over linear BLD-LDAK, with the largest gains for traits whose association signals were concentrated, whereas the more diffuse disease traits favored BLD-LDAK. These patterns were reproduced in individual-level data from All of Us. Against a panel of established methods (C + T, Lassosum, PRS-CS, LDpred-funct, and SBayesRC), DeepU-PRS was among the strongest single methods on continuous traits, and ensembles combining DeepU-PRS with the linear baseline and SBayesRC further improved accuracy, indicating complementary predictive signal. These findings highlight the value of modeling nonlinear and uncertain regulatory effects to advance PRS prediction.
Related
- Bayesian Uncertainty Quantification of Breast-Cancer Pathology AI Agreement under Reader- and Annotation-Condition-Dependent Reference Labels
- Uncertainty-aware integration of deuterium metabolic imaging with genome-scale metabolic modeling reveals diet-associated feasible-space remodeling in mouse skeletal muscle
- Quantifying heritability in functional regions of the coding and non-coding genome across diverse individuals
- Estimating latent neuronal nonlinear dynamics by sequential Monte Carlo method and sparse modeling
- Self-Attributed Innateness Beliefs Moderate the Heritability of Psychological Traits
BibTeX
@article{lee2026deepuprs,
title = {{DeepU-PRS: nonlinear and uncertainty-aware SNP heritability modeling for annotation-informed polygenic risk scoring.}},
author = {Junhyeong Lee and Dokyoon Kim and Seunggeun Lee},
journal = {Briefings in bioinformatics},
year = {2026},
month = sep,
doi = {10.1093/bib/bbag563},
url = {https://europepmc.org/article/MED/42879316},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - DeepU-PRS: nonlinear and uncertainty-aware SNP heritability modeling for annotation-informed polygenic risk scoring.
AU - Junhyeong Lee
AU - Dokyoon Kim
AU - Seunggeun Lee
PY - 2026
DA - 2026/09/01
JO - Briefings in bioinformatics
DO - 10.1093/bib/bbag563
UR - https://europepmc.org/article/MED/42879316
AB - Polygenic risk scores (PRSs) are widely used to quantify genetic predisposition to complex traits, and their predictive accuracy can be enhanced by incorporating functional annotations into single-nucleotide polymorphism (SNP) effect-size estimation. Existing approaches typically assume linear relationships between annotations and SNP effects, neglecting predictive aleatoric variance and potential nonlinear regulatory interactions. To evaluate the gains of nonlinear and uncertainty-aware modeling, we developed DeepU-PRS, a deep ensemble framework that extends the linear BLD-LDAK model with a neural network trained on functional annotations to jointly estimate SNP heritability and its aleatoric uncertainty, which are then integrated into a Bayesian PRS model. Across 28 continuous and 8 disease phenotypes in the UK Biobank, DeepU-PRS improved the mean continuous R2 by approximately 10% over linear BLD-LDAK, with the largest gains for traits whose association signals were concentrated, whereas the more diffuse disease traits favored BLD-LDAK. These patterns were reproduced in individual-level data from All of Us. Against a panel of established methods (C + T, Lassosum, PRS-CS, LDpred-funct, and SBayesRC), DeepU-PRS was among the strongest single methods on continuous traits, and ensembles combining DeepU-PRS with the linear baseline and SBayesRC further improved accuracy, indicating complementary predictive signal. These findings highlight the value of modeling nonlinear and uncertain regulatory effects to advance PRS prediction.
SN - 1467-5463
SN - 1477-4054
ER -