Genome-wide association studies in Crohn's disease: Past, present and future

Abstract

Over the course of the past decade, genome-wide association studies (GWAS) have revolutionised our understanding of complex disease genetics. One of the diseases that has benefitted most from this technology has been Crohn's disease (CD), with the identification of autophagy, the IL-17/IL-23 axis and innate lymphoid cells as key players in CD pathogenesis. Our increasing understanding of the genetic architecture of CD has also highlighted how a failure to suppress aberrant immune responses may contribute to disease development - a realisation that is now being incorporated into the design of new treatments. However, despite these successes, a significant proportion of disease heritability remains unexplained. Similarly, most of the causal variants at associated loci have not yet been identified, and even fewer have been functionally characterised. Because of the inarguable rise in the incidence of CD in regions of the world that previously had low disease rates, GWAS studies will soon have to shift from a largely Caucasian focus to include populations from other ethnic backgrounds. Future studies should also move beyond conventional studies of disease susceptibility into phenotypically driven 'within-cases' analyses in order to explore the role of genetics in other important aspects of disease biology. These studies are likely to include assessments of prognosis and/or response to treatments and may be critical if personalised medicine is ever to become a reality.

Keywords: Crohn's disease; GWAS; Pharmacogenetics; prognosis; susceptibility.

Figure 1

Basic principles of GWAS. GWAS has been made possible because of the haplotype structure of the human genome. Every chromosome consists of multiple haplotypes – regions that are inherited together during meiosis. Within each haplotype, there are typically many SNPs, which are co‐inherited within the larger genetic region, and thus, their alleles are inherited nonrandomly (i.e. they are in linkage disequilibrium). This means that it is possible to infer the genotypes at multiple SNPs within the haplotype (shown in grey) if the genotype at one or more SNPs is known. GWAS SNPs (shown in black) are selected so as to tag each haplotype, but where association is observed, they are unlikely to be the causal variant at the locus (shown in red). By genotyping SNPs from each haplotype in the genome in disease cases and healthy controls, it is possible to identify SNPs where the allele frequency is significantly different between the cases and controls, and which are associated with the disease.

Figure 2

Moving from SNPs to biology. Due to linkage disequilibrium, it is not possible to know which is the causal SNP at an associated locus without additional studies such as fine‐mapping or functional analyses to systematically dissect the effects of each variant. Once this is known the mechanism by which the effect occurs and the downstream cellular consequences can be determined – for example, a SNP might introduce a binding site for a tissue‐specific transcription factor (TF) and the resulting effect on gene expression could confer an altered cellular phenotype that could provide new insights into disease biology or provide an opportunity for therapy.

Figure 3

The difference between a conventional GWAS analysis and ‘within‐cases’ analysis. Schematic depicting the different analytical strategies employed by a conventional (susceptibility) GWAS in which the genetic profiles of cases and ethnically matched controls are compared, and the design of ‘within‐cases’ GWAS in which the genetic profiles of patients with distinct (and ideally contrasting) subphenotypes of a disease are compared.