Performance of deep-learning based approaches to improve polygenic scores

Background/Objectives Polygenic scores (PGS), which estimate an individual’s genetic propensity for a disease or trait, have the potential to become part of genomic healthcare. In maximising the predictive performance of PGS, neural-network (NN) based deep learning has emerged as a method of intense interest to model complex, nonlinear phenomena, which may be adapted to exploit gene-gene (GxG) and gene-environment (GxE) interactions.

To infer the amount of nonlinearity present in a phenotype, we present a framework for using NNs, which controls for the potential confounding effect of correlation between genetic variants, i.e. linkage disequilibrium (LD). We fit NN models to both simulated traits and 28 real disease and anthropometric traits in the UK Biobank.

Simulations confirmed that our framework adequately controls LD and can infer nonlinear effects, when such effects genuinely exist. Using this approach on real data, we found evidence for small amounts of nonlinearity due to GxG and GxE which mildly improved prediction performance (r2) by ∼7% and ∼4%, respectively. Despite evidence for nonlinear effects, NN models were outperformed by linear regression models for both genetic-only and genetic+environmental input scenarios with ∼7% and ∼5% differences in r2, respectively. Importantly, we found substantial evidence for confounding by joint tagging effects, whereby inferred GxG was actually LD with due to unaccounted for additive genetic variants.

Our results indicate that the usefulness of NNs for generating polygenic scores for common traits and diseases may currently be limited and may be confounded by joint tagging effects due to LD. Competing Interest Statement M.I. is a trustee of the Public Health Genomics (PHG) Foundation, a member of the Scientific Advisory Board of Open Targets, and has research collaborations with AstraZeneca, Nightingale Health and Pfizer which are unrelated to this study. CW receives funding from MSD and GSK and is a part-time employee of GSK. These companies had no involvement in the work presented here. The rest of the authors have declared no competing interest. Funding Statement M.K. is funded by the BHF Cambridge CRE (RE/18/1/34212). This research was supported by the NIHR Cambridge Biomedical Research Centre (NIHR203312). The views expressed are those of the authors and not necessarily those of the NIHR or the Department of Health and Social Care. This research was funded by the MRC (MR/R013926, MC_UU_00002/4, MC_UU_00040/01), Wellcome Trust (WT220788) and supported by the NIHR Cambridge Biomedical Research Centre (NIHR203312), BHF Chair Award (CH/12/2/29428) and by Health Data Research UK, which is funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation and the Wellcome Trust. M.I. is supported by the Munz Chair of Cardiovascular Prediction and Prevention and the NIHR Cambridge Biomedical Research Centre (NIHR203312) [*] as well as by the UK Economic and Social Research 878 Council (ES/T013192/1). Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: This research has been conducted using the UK Biobank Resource under Application Number 7439. Genotype and phenotype data can be accessed via the UKB research analysis platform (RAP): https://ukbiobank.dnanexus.com/landing. The Research Analysis Platform is open to researchers who are listed as collaborators on UKB-approved access applications. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care. For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising from this submission. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Data Availability Code to perform all analyses reported in this manuscript is available at github.com/mkelcb/dl-prs-paper.