A Stacking Framework for Polygenic Risk Prediction in Admixed Individuals

Abstract

Polygenic risk scores (PRS) are summaries of an individual's personalized genetic risk for a trait or disease. However, PRS often perform poorly for phenotype prediction when the ancestry of the target population does not match the population in which GWAS effect sizes were estimated. For many populations this can be addressed by performing GWAS in the target population. However, admixed individuals (whose genomes can be traced to multiple ancestral populations) lie on an ancestry continuum and are not easily represented as a discrete population. Here, we propose slaPRS (stacking local ancestry PRS), which incorporates multiple ancestry GWAS to alleviate the ancestry dependence of PRS in admixed samples. slaPRS uses ensemble learning (stacking) to combine local population specific PRS in regions across the genome. We compare slaPRS to single population PRS and a method that combines single population PRS globally. In simulations, slaPRS outperformed existing approaches and reduced the ancestry dependence of PRS in African Americans. In lipid traits from African British individuals (UK Biobank), slaPRS again improved on single population PRS while performing comparably to the globally combined PRS. slaPRS provides a data-driven and flexible framework to incorporate multiple population-specific GWAS and local ancestry in samples of admixed ancestry.

Figure 1.

Diagram of local window and level 0 population specific PRS model predictions. Admixed genomes split into 5Mb windows and in each window a local population A and B PRS are computed using population-specific effect sizes. Local ancestry further computed to form covariate vector for level 1 stacking model.

Figure 2.

Boxplots comparing performance of slaPRS (differing in choice of level 0 predictors from each block), ${\mathit{\text{PRS}}}_{\mathit{\text{Marquez}}}$, and single population PRS: ${\mathit{\text{PRS}}}_{\mathit{\text{EUR}}}$ & ${\mathit{\text{PRS}}}_{\mathit{\text{AFR}}}$ (see methods) quantified through adjusted $R^2$. Testing samples stratified by overall % of European ancestry.

Figure 3.

Line graph comparing PRS performance across methods (quantified by median adjusted $R^2$ between estimated PRS and phenotype value) as the African GWAS sample size changes (n=2000, 5000, 10,000). and Testing admixed samples stratified by European ancestry quantile.

Figure 4.

Line graph comparing PRS performance as quantified through median adjusted $R^2$ between the estimated PRS and phenotype value. Transethnic genetic correlation varies from $\rho =\{0.2,05,0.8\}$ and testing admixed samples stratified by European ancestry quantile.

Figure 5.

Line graph comparing PRS Performance for UKB lipid phenotypes. Performance quantified through median adjusted $R^2$ from model PHENO ~ PRS + PC1 + PC2 + PC3 + PC4. Testing admixed samples are stratified by European ancestry quantile.