Epistatic Features and Machine Learning Improve Alzheimer's Disease Risk Prediction Over Polygenic Risk Scores.

Journal: Journal of Alzheimer's disease : JAD
PMID:

Abstract

BACKGROUND: Polygenic risk scores (PRS) are linear combinations of genetic markers weighted by effect size that are commonly used to predict disease risk. For complex heritable diseases such as late-onset Alzheimer's disease (LOAD), PRS models fail to capture much of the heritability. Additionally, PRS models are highly dependent on the population structure of the data on which effect sizes are assessed and have poor generalizability to new data.

Authors

  • Stephen Hermes
    Parabon NanoLabs, Inc., Reston, VA, USA.
  • Janet Cady
    Parabon NanoLabs, Inc., Reston, VA, USA.
  • Steven Armentrout
    Parabon NanoLabs, Inc., Reston, VA, USA.
  • James O'Connor
    Division of Cancer Sciences, The University of Manchester, Manchester, UK.
  • Sarah Carlson Holdaway
    Parabon NanoLabs, Inc., Reston, VA, USA.
  • Carlos Cruchaga
    Washington University in St. Louis, St. Louis, Missouri, USA.
  • Thomas Wingo
    Goizueta Alzheimer's Disease Center, Emory University School of Medicine, Atlanta, GA, USA.
  • Ellen McRae Greytak
    Parabon NanoLabs, Inc., Reston, VA, USA.