Transfer learning in genome-wide association studies with knockoffs

TL;DR

This paper explores transfer learning methods to enhance the power of knockoff-based conditional testing in GWAS, especially across diverse populations, leading to improved detection of genetic associations.

Contribution

It introduces and compares transfer learning techniques tailored for knockoffs in GWAS, addressing population diversity and improving association discovery.

Findings

Transfer learning increases association detection in minority populations.

Methods improve the efficiency of genetic variation analysis across ancestries.

Application to UK Biobank data shows more associations identified.

Abstract

This paper presents and compares alternative transfer learning methods that can increase the power of conditional testing via knockoffs by leveraging prior information in external data sets collected from different populations or measuring related outcomes. The relevance of this methodology is explored in particular within the context of genome-wide association studies, where it can be helpful to address the pressing need for principled ways to suitably account for, and efficiently learn from the genetic variation associated to diverse ancestries. Finally, we apply these methods to analyze several phenotypes in the UK Biobank data set, demonstrating that transfer learning helps knockoffs discover more numerous associations in the data collected from minority populations, potentially opening the way to the development of more accurate polygenic risk scores.