Complex host genetics influence the microbiome in inflammatory bowel disease

Abstract

Background: Human genetics and host-associated microbial communities have been associated independently with a wide range of chronic diseases. One of the strongest associations in each case is inflammatory bowel disease (IBD), but disease risk cannot be explained fully by either factor individually. Recent findings point to interactions between host genetics and microbial exposures as important contributors to disease risk in IBD. These include evidence of the partial heritability of the gut microbiota and the conferral of gut mucosal inflammation by microbiome transplant even when the dysbiosis was initially genetically derived. Although there have been several tests for association of individual genetic loci with bacterial taxa, there has been no direct comparison of complex genome-microbiome associations in large cohorts of patients with an immunity-related disease.

Methods: We obtained 16S ribosomal RNA (rRNA) gene sequences from intestinal biopsies as well as host genotype via Immunochip in three independent cohorts totaling 474 individuals. We tested for correlation between relative abundance of bacterial taxa and number of minor alleles at known IBD risk loci, including fine mapping of multiple risk alleles in the Nucleotide-binding oligomerization domain-containing protein 2 (NOD2) gene exon. We identified host polymorphisms whose associations with bacterial taxa were conserved across two or more cohorts, and we tested related genes for enrichment of host functional pathways.

Results: We identified and confirmed in two cohorts a significant association between NOD2 risk allele count and increased relative abundance of Enterobacteriaceae, with directionality of the effect conserved in the third cohort. Forty-eight additional IBD-related SNPs have directionality of their associations with bacterial taxa significantly conserved across two or three cohorts, implicating genes enriched for regulation of innate immune response, the JAK-STAT cascade, and other immunity-related pathways.

Conclusions: These results suggest complex interactions between genetically altered host functional pathways and the structure of the microbiome. Our findings demonstrate the ability to uncover novel associations from paired genome-microbiome data, and they suggest a complex link between host genetics and microbial dysbiosis in subjects with IBD across independent cohorts.

Figure 1

Schematic of multiomics genotype-microbiome association testing methodology. Host genome-microbiome association testing involves potentially thousands or millions of genetic polymorphisms and hundreds or thousands of bacterial taxa and genes. Full feature-by-feature association testing is likely to be underpowered in all but the largest cohorts or meta-analyses; therefore, our methodology includes careful feature selection from both data types. Raw genetic polymorphisms were derived from Immunochip data and filtered by known IBD associations from a large-cohort GWAS study [1]. Microbiome sequences were binned by lineage at all taxonomic levels. After data normalization and filtering (see Methods), a simple linear test was performed for association between minor allele count and bacterial taxon relative abundance while controlling for clinical covariates. QTL, quantitative trait loci.

Figure 2

NOD2 fine mapping reveals association with taxonomic and metabolic dysbiosis. (a) Scatterplot of NOD2-bacterial taxon regression coefficients in one study versus the corresponding regression coefficients in another study. We included only those taxa with a nominally significant (P < 0.05) association in a least one of the cohorts being compared. (b) Comparison of residual distributions of Enterobacteriaceae with and without incorporating the six independent known causal NOD2 variants; considering variant rs5743293, only 6.3% of subjects have one or more risk alleles; aggregating risk allele counts across the six variants increases this to 21.8%, and reveals much stronger associations with the microbiome. The strip charts and violin plots show the distribution of standardized residual relative abundance of Enterobacteriaceae versus NOD2 risk allele dosage after data transformation and regression on clinical covariates. Violin plots show the conditional density of residual relative abundance within each dosage level. (c) Relative positions of six NOD2 variants in NOD2 exons [29].

Figure 3

Host genes with reproducible microbiome associations across cohorts. Network analysis of host signaling and metabolic pathways enriched for association with microbial taxa (FDR <0.25, Matthew’s correlation test). The visualization of gene-gene interaction network for the subset of 49 genes with significantly conserved directionalities of association with the microbiome is supported by several types of gene-gene connection [30]. This enrichment analysis identified enriched functional networks in innate immune response, inflammatory response, and the JAK-STAT pathway, all of which play roles in immune response to pathogen infection [1].

Figure 4

Top gene-bacteria associations. Beeswarm plots of the relative abundance of six bacteria stratified by the number of risk alleles present in SNPs in the given genes. The associations shown are the six most significant associations between bacteria and genes in the subset of genes with conserved bacterial associations across cohorts and belonging to the JAK-STAT pathway or the innate immune pathway response as shown in Figure 3. Relative abundances shown are transformed with the arcsine-square root transformation to stabilize variance and to make distributions more normal.

Figure 5

Host factors associated with the IBD microbiome. A complex network of host factors associated with the IBD microbiome (all associations FDR <0.05); only taxa with at least four significant associations are included in the network; green and purple edges indicate positive and negative associations, respectively; the width of an edge indicates the strength of the association. The effects of these factors on individual taxa are highly overlapping. The analysis identified covariates representing each type of host factor, consistent with previous results [4]. Biopsy location and medication history had the strongest and most comprehensive effects on microbiome profile; the effect of NOD2 was moderate in comparison. Cohort membership (not shown) also affected microbiome profile. These results demonstrate the need for study designs and analysis methodologies that control carefully for numerous host genetic and environmental factors when performing microbiome-based biomarker discovery. Abx, antibiotics within 1 month; Imm, immunosuppressants within 1 month; L2, no ileal involvement; PPI, biopsy from pre-pouch ileum.

Figure 6

Association of IBD-related dysbiosis and recent antibiotics usage. A beeswarm plot [41] of the previously published microbial dysbiosis index [20] (MDI) stratified by recent antibiotics usage by patients. The test for this association between MDI and antibiotics (P = 0.039, linear regression t-test) included NOD2 risk allele count to control for the effects of NOD2 genetics on the microbiome.