Multiethnic polygenic risk prediction in diverse populations through transfer learning

Abstract

Polygenic risk scores (PRS) leverage the genetic contribution of an individual’s genotype to a complex trait by estimating disease risk. Traditional PRS prediction methods are predominantly for the European population. The accuracy of PRS prediction in non-European populations is diminished due to much smaller sample size of genome-wide association studies (GWAS). In this article, we introduced a novel method to construct PRS for non-European populations, abbreviated as TL-Multi, by conducting a transfer learning framework to learn useful knowledge from the European population to correct the bias for non-European populations. We considered non-European GWAS data as the target data and European GWAS data as the informative auxiliary data. TL-Multi borrows useful information from the auxiliary data to improve the learning accuracy of the target data while preserving the efficiency and accuracy. To demonstrate the practical applicability of the proposed method, we applied TL-Multi to predict the risk of systemic lupus erythematosus (SLE) in the Asian population and the risk of asthma in the Indian population by borrowing information from the European population. TL-Multi achieved better prediction accuracy than the competing methods, including Lassosum and meta-analysis in both simulations and real applications.

MUSSEL: Enhanced Bayesian Polygenic Risk Prediction Leveraging Information across Multiple Ancestry Groups

“…We apply eight existing approaches for comparison, which include two single-ancestry methods applied to GWAS and LD reference data from the target population: (1) C+T, (2) LDpred2; the same single-ancestry methods applied to GWAS and LD reference data for EUR: (3) EUR C+T, (4) EUR LDpred2; and three existing multi-ancestry methods applied to ancestry-specific GWAS and LD reference data for all ancestry groups: (5) weighted C+T (weighted PRS using C+T as the base method), (6) weighted LDpred2 (weighted PRS using LDpred2 as the base method), (7) PRS-CSx 9 , and (8) CT-SLEB 13 . Results from another two recently proposed multi-ancestry methods, PolyPred+ 19 and XPASS 10 , on the same simulated dataset are reported in Zhang et al (2022) 13 . Table 1 provides a comparison of the various methods in terms of data requirement, similarities, and differences.…”

“…One simple approach is the weighted PRS 8 , which trains a linear combination of the PRS developed using single-ancestry methods (e.g., LD clumping and P-value thresholding, C+T) applied separately to available GWAS data across different ancestry groups 8 . More recent methods attempt to borrow information across ancestry at the level of individual SNPs based on Bayesian methods 9,10 , penalized regressions 11,12 , or through the extension of C+T 13 . However, applications show that no single method performs uniformly the best, and their performance depends on many aspects, including the underlying genetic architecture of the trait, the absolute and relative sample sizes across populations, and the algorithm for the estimation of LD based on the underlying reference dataset 13 .…”

Multi-trait genome-wide analysis identified novel risk loci and candidate drugs for heart failure

“…Our data were derived from European populations, thus potentially limiting the generalizability of our study to other ethnicities. However, recent advancements have introduced methods for transferring genetic findings from European populations to others, increasing the applicability of our research [87,88].…”

MUSSEL: Enhanced Bayesian polygenic risk prediction leveraging information across multiple ancestry groups

“… 7 One simple approach is the weighted PRS, 8 which trains a linear combination of the PRS developed using single-ancestry methods (e.g., LD clumping and p value thresholding, C + T) applied separately to available GWAS data across different ancestry groups. 8 More recent methods attempt to borrow information across ancestry at the level of individual SNPs based on Bayesian methods 9 , 10 and penalized regressions, 11 , 12 or through the extension of C + T. 13 However, applications show that no single method performs uniformly the best, and their performance depends on many aspects, including the underlying genetic architecture of the trait, the absolute and relative sample sizes across populations, and the algorithm for the estimation of LD based on the underlying reference dataset. 13 …”