Exploring the application of deep learning methods for polygenic risk score estimation
No Thumbnail Available
Authors
S. W. Squires, M. N.
Oram, R. A.
Issue Date
2025-03-13
Type
Journal Article
Language
eng
Keywords
*Deep Learning , Humans , *Multifactorial Inheritance , Polymorphism, Single Nucleotide , *Genetic Predisposition to Disease , ROC Curve , Risk Assessment , United Kingdom , Genome-Wide Association Study , Risk Factors , Models, Genetic , Algorithms , Genetic Risk Score , deep learning , genetics , machine learning , polygenic risk scores , precision medicine
Alternative Title
Background. Polygenic risk scores (PRS) summarise genetic information into a single number with clinical and research uses. Deep learning (DL) has revolutionised multiple fields, however, the impact of DL on PRSs has been less significant. We explore how DL can improve the generation of PRSs.Methods. We train DL models on known PRSs using UK Biobank data. We explore whether the models can recreate human programmed PRSs, including using a single model to generate multiple PRSs, and DL difficulties in PRS generation. We investigate how DL can compensate for missing data and constraints on performance.Results. We demonstrate almost perfect generation of multiple PRSs with little loss of performance with reduced quantity of training data. For an example set of missing SNPs the DL model produces predictions that enable separation of cases from population samples with an area under the receiver operating characteristic curve of 0.847 (95% CI: 0.828-0.864) compared to 0.798 (95% CI: 0.779-0.818) for the PRS.Conclusions. DL can accurately generate PRSs, including with one model for multiple PRSs. The models are transferable and have high longevity. With certain missing SNPs the DL models can improve on PRS generation; further improvements would likely require additional input data.
Description
Citation
Squires SW, M. N., Oram, R. A. Exploring the application of deep learning methods for polygenic risk score estimation. Biomedical physics & engineering express. 2025;11(2).
Publisher
IOP Publishing
License
© 2025 The Author(s).
Journal
Biomedical physics & engineering express