Genetic diversity fuels gene discovery for tobacco and alcohol use

Abstract

Tobacco and alcohol use are heritable behaviours associated with 15% and 5.3% of worldwide deaths, respectively, due largely to broad increased risk for disease and injury^1-4. These substances are used across the globe, yet genome-wide association studies have focused largely on individuals of European ancestries⁵. Here we leveraged global genetic diversity across 3.4 million individuals from four major clines of global ancestry (approximately 21% non-European) to power the discovery and fine-mapping of genomic loci associated with tobacco and alcohol use, to inform function of these loci via ancestry-aware transcriptome-wide association studies, and to evaluate the genetic architecture and predictive power of polygenic risk within and across populations. We found that increases in sample size and genetic diversity improved locus identification and fine-mapping resolution, and that a large majority of the 3,823 associated variants (from 2,143 loci) showed consistent effect sizes across ancestry dimensions. However, polygenic risk scores developed in one ancestry performed poorly in others, highlighting the continued need to increase sample sizes of diverse ancestries to realize any potential benefit of polygenic prediction.

Fig. 1. Ancestry composition and effect size moderation.

a, Ancestry compositions of contributing studies (each point is a study). Colours are coded by primary ancestry of individuals in the cohort. Studies with less than 90% of individuals assignable to a single ancestry group are shown in grey. Ancestry component 3 was a north–south EUR cline, which was omitted here as we did not conduct meta-analyses stratified by northern versus southern Europe. TOPMed, Trans-Omics for Precision Medicine. b, Extent of effect size moderation as a function of the same ancestry dimensions as shown in a. The full moderation results are in Supplementary Table 2. Each point in b represents an independent variant with the standardized MDS component coefficient from our trans-ancestry models (that is, γ) along the x axes, and the corresponding mean difference in effect sizes (β) for the ancestry-stratified meta-analysis of the given ancestry versus all other ancestries along the y axes. The grey circles indicate variants showing little to no evidence of effect size heterogeneity across ancestry, whereas the coloured circles represent variants with adequate evidence of effect size heterogeneity. The plots highlight that the majority of variants have similar effect sizes across all ancestry clines, with some potentially interesting exceptions in which the variant effects sizes differ substantially between ancestry clines.

Fig. 2. Within-ancestry and across-ancestry performance of polygenic scores in an independent target sample (Add Health).

a, Incremental variance explained for each target ancestry group. The colour of the stacked bars indicates the ancestry from which the polygenic score was derived; the total height of each set of the stacked bars (and 95% confidence intervals) correspond to the total variance explained by all four ancestry-stratified scores combined. For example, in the target EUR subsample, non-EUR polygenic scores add little over and above the EUR score. Note that some comparisons are underpowered to detect differences in predictive accuracy across ancestry (see Supplementary Note). Heritabilities, estimated by LD score regression, of each phenotype–ancestry combination are depicted by the grey dashed bar (with 95% confidence intervals) and corresponding sample sizes; these represent the maximum expected accuracy of the polygenic risk score (PRS). b, The manner in which the phenotype mean in the target sample changes as a function of the EUR PRS deciles. c, Results from an interaction model, in which each phenotype was modelled as a function of an interaction between the EUR-based PRS and target ancestry (coded as a factor with EUR ancestry as the reference and scores scaled within ancestry). The bands around each line denote the 95% confidence intervals. Significant interactions are noted with text. Using SmkInit as an example, the purple line represents the predicted proportion of regular smokers as a function of the EUR PRS in the EUR subsample of Add Health, the blue lines show the predicted proportion of regular smokers by standard deviation of the EUR PRS in the EAS subsample, and so on. In this case, the magnitude of the association between the EUR-based PRS and SmkInit (that is, the slope) was significantly greater in the EUR target ancestry than all other ancestries. Full PRS results are in Supplementary Table 12.

Extended Data Fig. 1. Ancestry space of studies contributing to meta-analysis (panel a), versus individuals from TOPMed and 1000 Genomes (panel b).

The meta-regression within the MEMO model requires specification of ancestry clines. To ensure consistency in the meaning of ancestry clines across all five MEMO analyses (one for each phenotype) we created a single multidimensional scaling solution based on allele frequencies from all phenotypes in all participating cohorts. These solutions are plotted in panel a (circles correspond to TOPMed cohorts, squares are all other cohorts which used imputed microarray genotypes, and triangles are 1000 Genomes ancestry groups). Colors of points correspond to the primary assigned ancestry of each cohort (studies with < 90% of individuals coming from a single ancestry group are shown in grey). Panel b shows projection of principal components (after OADP transformation) of TOPMed individuals onto PCs of 1000 Genomes individuals, in colored triangles. Each 1000 Genomes individual is colored by their known ancestry. This PC information was used in assigning ancestry to TOPMed individuals for the purpose of reference panel creation (individuals of South Asian ancestry were not included in analyses). The PCs in panel b were reordered or reversed in some cases to align with panel a. These transformations are noted in the axis labels.

Extended Data Fig. 2. Multi-ancestry meta-analysis Manhattan plots.

Black horizontal line corresponds to P = 5 × 10⁻⁹, the GWAS significance threshold used for all analyses. Note that some y-axis scales are discontinuous to better illustrate variants with very small P-values (e.g., the Drinks per Week y-axis is cut at 30 with a maximum value of 307.7, denoting a P-value of 1.9 × 10⁻³⁰⁸). All P-values are from two-sided statistical tests.

Extended Data Fig. 3. Tissue expression and brain cell type enrichment in high priority genes.

Panel a shows tissue expression enrichment in ‘high priority’ genes. We define high priority genes here as those located nearest to the variants in fine-mapped credible intervals containing less than five variants. These genes were compared to ‘control’ genes identified in the same way, but from variants in credible intervals with PIP < 0.01 from the trans-ancestry fine-mapping. The x-axis denotes GTEx tissue types. The y-axis represents relative risk estimates comparing high priority to control genes. Panel b shows similar relative risk comparisons with 39 brain cell types. Data are presented as relative risk values with error bars denoting bootstrapped 95% confidence intervals. Further details on estimating relative risk are included in the Supplementary Note section ‘Functional enrichment’.