Trans-ethnic meta-regression of genome-wide association studies accounting for ancestry increases power for discovery and improves fine-mapping resolution

Abstract

Trans-ethnic meta-analysis of genome-wide association studies (GWAS) across diverse populations can increase power to detect complex trait loci when the underlying causal variants are shared between ancestry groups. However, heterogeneity in allelic effects between GWAS at these loci can occur that is correlated with ancestry. Here, a novel approach is presented to detect SNP association and quantify the extent of heterogeneity in allelic effects that is correlated with ancestry. We employ trans-ethnic meta-regression to model allelic effects as a function of axes of genetic variation, derived from a matrix of mean pairwise allele frequency differences between GWAS, and implemented in the MR-MEGA software. Through detailed simulations, we demonstrate increased power to detect association for MR-MEGA over fixed- and random-effects meta-analysis across a range of scenarios of heterogeneity in allelic effects between ethnic groups. We also demonstrate improved fine-mapping resolution, in loci containing a single causal variant, compared to these meta-analysis approaches and PAINTOR, and equivalent performance to MANTRA at reduced computational cost. Application of MR-MEGA to trans-ethnic GWAS of kidney function in 71,461 individuals indicates stronger signals of association than fixed-effects meta-analysis when heterogeneity in allelic effects is correlated with ancestry. Application of MR-MEGA to fine-mapping four type 2 diabetes susceptibility loci in 22,086 cases and 42,539 controls highlights: (i) strong evidence for heterogeneity in allelic effects that is correlated with ancestry only at the index SNP for the association signal at the CDKAL1 locus; and (ii) 99% credible sets with six or fewer variants for five distinct association signals.

Figure 1.

Power to detect association, at genome-wide significance (P < 5 × 10⁻⁸), using alternative approaches to aggregate GWAS across diverse populations: fixed-effects meta-analysis; random-effects (RE2) meta-analysis; and meta-regression including axes of genetic variation as covariates as implemented in MR-MEGA. Power is presented as a function of the allelic odds-ratio for each of five scenarios for heterogeneity in effects between populations, described in Supplementary Material, Table S1.

Figure 2.

Metrics of fine-mapping resolution, with ‘perfect data’, across alternative approaches to aggregate GWAS across diverse populations: fixed-effects meta-analysis; random-effects meta-analysis; meta-regression including axes of genetic variation as covariates as implemented in MR-MEGA; MANTRA; and PAINTOR. Two metrics are presented: (i) the median number of variants in the 99% credible set on a log₁₀-scale; and (ii) the mean posterior probability ascribed to the causal variant. Metrics are presented for each of five scenarios for heterogeneity in effects between populations, described in Supplementary Material, Table S1. In each scenario, the odds ratio has been fixed to obtain approximately 80% power to detect association at genome-wide significance (P < 5 × 10⁻⁸) in the meta-regression analysis.

Figure 3.

Metrics of fine-mapping resolution, with imputed data, across alternative approaches to aggregate GWAS across diverse populations: fixed-effects meta-analysis; random-effects meta-analysis; meta-regression including axes of genetic variation as covariates as implemented in MR-MEGA; MANTRA; and PAINTOR. Two metrics are presented: (i) the median number of SNPs in the 99% credible set on a log₁₀-scale; and (ii) the mean posterior probability ascribed to the causal variant. Metrics are presented for each of five scenarios for heterogeneity in effects between populations, described in Supplementary Material, Table S1. In each scenario, the odds ratio has been fixed to obtain approximately 80% power to detect association at genome-wide significance (P < 5 × 10⁻⁸) in the meta-regression analysis.