Portal de Periódicos da CAPES

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

2024; IOS Press; Volume: 99; Issue: 4 Linguagem: Inglês

10.3233/jad-230236

1875-8908

Stephen Hermes, Janet Cady, Steven Armentrout, James P.B. O’Connor, Sarah Carlson Holdaway, Carlos Cruchaga, Thomas S. Wingo, Ellen M. Greytak,

Gene expression and cancer classification

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.