Shared genetic origin of asthma, hay fever and eczema elucidates allergic disease biology

Abstract

Asthma, hay fever (or allergic rhinitis) and eczema (or atopic dermatitis) often coexist in the same individuals, partly because of a shared genetic origin. To identify shared risk variants, we performed a genome-wide association study (GWAS; n = 360,838) of a broad allergic disease phenotype that considers the presence of any one of these three diseases. We identified 136 independent risk variants (P < 3 × 10^-8), including 73 not previously reported, which implicate 132 nearby genes in allergic disease pathophysiology. Disease-specific effects were detected for only six variants, confirming that most represent shared risk factors. Tissue-specific heritability and biological process enrichment analyses suggest that shared risk variants influence lymphocyte-mediated immunity. Six target genes provide an opportunity for drug repositioning, while for 36 genes CpG methylation was found to influence transcription independently of genetic effects. Asthma, hay fever and eczema partly coexist because they share many genetic risk variants that dysregulate the expression of immune-related genes.

Figure 1. Loci containing genetic risk variants independently associated with the risk of allergic disease at P<3x10^-8.

The 136 sentinel risk variants were located in 50 previously reported (86 variants) and 49 novel (50 variants) risk loci. The numbers of plausible target genes of sentinel risk variants identified for each locus are shown, with target gene names listed in blue font. For loci with many target genes, only a selection is listed. When no target gene was identified (black font), square brackets are used to indicate the location of the sentinel risk variant relative to the nearest gene(s). Specifically, when the risk variant was intergenic (indicated by "gene1--[]--gene2"), the two closest genes (upstream and downstream) are shown; the distance to each gene is proportional to the number of "-" shown. Otherwise, when the risk variant was located within a gene, the respective gene name is shown between square brackets (i.e. [gene]). Red vertical line in Manhattan plot shows genome-wide significance threshold used (P=3x10^-8).

Figure 2. Sentinel variants with significant allele-frequency differences in pairwise case-only association analyses contrasting individuals suffering from a single allergic disease.

For each sentinel variant, we performed three case-only association analyses, comparing asthma-only cases (n=12,268) against hay fever-only cases (n=33,305); asthma-only cases against eczema-only cases (n=6,276); and hay fever-only cases against eczema-only cases. After accounting for multiple testing, significant associations for at least one of these analyses were only observed for six of the 136 sentinel variants, which are shown in the first two rows of the figure. For a given variant, the vertices of the inner triangle point to the position along the edges of the outer triangle that corresponds to the allele frequency difference observed between pairs of single-disease cases. For example, the rs61816761:A allele, which is located in the Fillagrin gene (FLG), was 1.32-fold more common in individuals suffering only from eczema when compared to individuals suffering only from hay fever (P=7.2x10^-8), consistent with this SNP being a stronger risk factor for eczema than for hay fever. A similar result (OR = 1.26, P=0.0004) was observed for this variant when contrasting eczema-only cases against asthma-only cases. For comparison, a variant with no allele frequency differences in all three pairwise single-disease association analyses is also shown (rs2228145, in the IL6R gene). In this case, the three estimated odds ratios were approximately equal to 1. The color of the OR font reflects the significance of the association: red for P<1.2x10^-4 (correction for multiple testing), blue for P<0.05 and black for P>0.05.

Figure 3. Tissues and biological processes influenced by allergy risk variants.

(A) Enrichment of tissue-specific gene expression in 25 broad tissues studied by the GTEx consortium. We used the TSEA approach to test if genes specifically expressed in a given tissue were enriched amongst the list of plausible target genes when compared to other genes in the genome. The enrichment (y-axis) is shown as the -log10 of the Fisher’s exact test P-value. For comparison, we analyzed 1,000 lists of random genes instead of the plausible target genes. We selected genes at random using three strategies (see Methods for details). First, genes were randomly drawn from the 98 non-MHC allergy risk loci identified in our GWAS, matching on the number selected per locus and in total. The enrichment P-value for each of the 1,000 lists of random genes is shown by a grey circle. The black-solid line shows the P-value for the 50^th most significant random list (i.e. corresponding to the 5^th percentile): under the null hypothesis of no enrichment, this P-value should be close to 0.05 (horizontal grey line). Second, genes were drawn at random from 2 Mb loci selected at random from the genome, matching on the number of genes selected (and available for selection) per locus and in total. Third, genes were drawn at random from all 18,300 genes available for analysis. For the latter two strategies, the P-value for the 50^th most significant random gene list is shown by the blue and yellow lines, respectively; enrichment results for each individual random dataset are not shown. Similar results were obtained after restricting the random genes and the background gene list to the subset of genes with eQTLs (Supplementary Fig. 5). Genes in the MHC were excluded from these analyses. (B) Enrichment of SNP-based heritability in 220 individual cell type-specific regulatory annotations. We used stratified LD score regression analysis to quantify the contribution of SNPs that overlap cell type-specific regulatory annotations to the SNP-based disease heritability. Annotations with an enrichment in SNP heritability (-log10 of the P-value of the regression coefficient, y-axis) that was significant after correcting for multiple testing (P<0.0002) are shown in black circles (top 10 listed in blue font; all results in Supplementary Table 19). SNPs in the MHC were excluded from these analyses. (C) Biological processes enriched amongst the list of plausible target genes. We used GeneNetwork to test if the plausible target genes as a group were more likely to be part of a specific biological process category when compared to the rest of the genes in the genome. The enrichment (y-axis) is shown as the –log10 of the Wilcoxon rank-sum test P-value (see Methods for details). The top 10 pathways are listed in blue font. For comparison, we analyzed 1,000 lists of random genes generated using the same three strategies described above. For each of these strategies, the P-value for the 50^th most significant random gene list is shown by the black (random genes from allergy loci), blue (random genes from random loci) and yellow (random genes selected from all available genes) lines. Similar results were obtained after restricting the random genes and the background gene list to the subset of genes with eQTLs (not shown). Genes in the MHC were excluded from these analyses.