Performance of deep-learning-based approaches to improve polygenic scores.

Journal: Nature communications
Published Date:

Abstract

Polygenic scores, which estimate an individual's genetic propensity for a disease or trait, have the potential to become part of genomic healthcare. Neural-network based deep-learning has emerged as a method of intense interest to model complex, nonlinear phenomena, which may be adapted to exploit gene-gene and gene-environment interactions to potentially improve polygenic scores. We fit neural-network models to both simulated and 28 real traits in the UK Biobank. To infer the amount of nonlinearity present in a phenotype, we also present a framework using neural-networks, which controls for the potential confounding effect of linkage disequilibrium. Although we found evidence for small amounts of nonlinear effects, neural-network models were outperformed by linear regression models for both genetic-only and genetic+environmental input scenarios. In this work, we find that the usefulness of neural-networks for generating polygenic scores may currently be limited and confounded by joint tagging effects due to linkage disequilibrium.

Authors

  • Martin Kelemen
    British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK. mk907@medschl.cam.ac.uk.
  • Yu Xu
    Panzhihua Central Hospital, Panzhihua, Sichuan, China.
  • Tao Jiang
    Department of Respiratory and Critical Care Medicine, Center for Respiratory Medicine, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, China.
  • Jing Hua Zhao
    British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK.
  • Carl A Anderson
    Wellcome Sanger Institute, Hinxton, Cambridgeshire, UK.
  • Chris Wallace
    Cambridge Institute of Therapeutic Immunology & Infectious Disease, University of Cambridge, Cambridge, UK.
  • Adam Butterworth
    British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK.
  • Michael Inouye
    Cambridge Baker Systems Genomics Initiative, Baker Heart Research Institute - BHRI, Melbourne, Victoria, Australia minouye@baker.edu.au.