Improving genetic risk prediction across diverse population by disentangling ancestry representations

TL;DR

This paper introduces a deep learning framework that disentangles ancestry from phenotype information in genetic data, improving risk prediction accuracy across diverse and admixed populations, especially for minority groups.

Contribution

The study presents a novel deep learning approach that separates ancestry from phenotype signals, enhancing genetic risk prediction across diverse populations.

Findings

Improved risk prediction accuracy in minority populations.

Significant performance gains for admixed individuals.

Outperforms standard linear and nonlinear models.

Abstract

Risk prediction models using genetic data have seen increasing traction in genomics. However, most of the polygenic risk models were developed using data from participants with similar (mostly European) ancestry. This can lead to biases in the risk predictors resulting in poor generalization when applied to minority populations and admixed individuals such as African Americans. To address this bias, largely due to the prediction models being confounded by the underlying population structure, we propose a novel deep-learning framework that leverages data from diverse population and disentangles ancestry from the phenotype-relevant information in its representation. The ancestry disentangled representation can be used to build risk predictors that perform better across minority populations. We applied the proposed method to the analysis of Alzheimer's disease genetics. Comparing with standard linear and nonlinear risk prediction methods, the proposed method substantially improves risk prediction in minority populations, particularly for admixed individuals.