Detecting gene-environment interactions to guide personalized intervention: Boosting distributional regression for polygenic scores.

Abstract excerpt

Polygenic risk scores can be used to model the individual genetic liability for human traits. Current methods primarily focus on modeling the mean of a phenotype while neglecting the variance. However, genetic variants associated with phenotypic variance can provide important insights into gene-environment interaction studies. We propose snpboostlss, a cyclical gradient boosting algorithm for a Gaussian...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Algorithms
• Share to Cross-Sectional Studies