Deep resequencing of GWAS loci identifies independent rare variants associated with inflammatory bowel disease

Abstract

More than 1,000 susceptibility loci have been identified through genome-wide association studies (GWAS) of common variants; however, the specific genes and full allelic spectrum of causal variants underlying these findings have not yet been defined. Here we used pooled next-generation sequencing to study 56 genes from regions associated with Crohn's disease in 350 cases and 350 controls. Through follow-up genotyping of 70 rare and low-frequency protein-altering variants in nine independent case-control series (16,054 Crohn's disease cases, 12,153 ulcerative colitis cases and 17,575 healthy controls), we identified four additional independent risk factors in NOD2, two additional protective variants in IL23R, a highly significant association with a protective splice variant in CARD9 (P < 1 × 10(-16), odds ratio ≈ 0.29) and additional associations with coding variants in IL18RAP, CUL2, C1orf106, PTPN22 and MUC19. We extend the results of successful GWAS by identifying new, rare and probably functional variants that could aid functional experiments and predictive models.

Figure 1. (a) Schematic overview of the Crohn’s disease rare variant phenotype project. (b) Power to detect single-marker rare variant association in follow-up sample sets

Here we report the results of the Crohn’s pooled resequencing project with follow up genotypes in over 13167 CD patients, 12153 UC patients, 15331 healthy controls. We report that of the 70 markers successfully genotyped 22%,60%,79%,88%,91% have at least 80% power to detect association at minor allele frequency odds ratios of 1.5,2,3,4, and 5 respectively (Figure 1b,S3a,S3b), implying that we are well positioned to address the contribution of rare and low frequency polymorphisms in GWAS loci to IBD.

Figure 2. CARD9 protective splice site variant and predicted transcript

(a) A splice-site variant IVS11+1C>G (OR = 0.29) conferring protection against Crohn’s disease with predicted transcript. This hypothetical transcript has been observed in spleen, lymph-node and peripheral blood mononuclear cell (PBMC) derived CDNA libraries. We predict exon 11 to be skipped and alternative transcript to include exon 9 mRNA sequence continuing to exon 12 including 21 AA before reaching a premature stop.

Figure 3. (a) Identification of additional rare variants associated with Crohn’s disease and its haplotype structure (b) NOD2 haplotypes observed in 700 individuals with overlapping genotype data (R311W, S431L, R702W, R703C, V793M, N852S, M863V, G908R, fs1007insC)

(a) Five additional risk variants are discovered in NOD2 demonstrating the – log10(P value) and the minor allele odds ratio with 95% CI along with their haplotype block. (b) Note that S431L and V793M are in tight LD and we regard this as one unit S431L + V793M, R703C has a higher frequency than R311W although they share haplotypes conditional analysis (Table S3) demonstrates independent contributions. M863V lies on the background haplotype of fs1007insC.

Figure 4. Functional analyses of NOD2 variants

HEK293T cells were transfected with NOD2 constructs and fixed using paraformaldehyde 4% at 24h post transfection. Cells were then subjected to immunofluorescent staining to detect NOD2 and fluorescence was collected using a confocal microscope. Image gallery displays a single confocal section. HEK293T cells were transfected with NOD2 constructs and reporter plasmids encoding firefly luciferase cloned under a promoter containing NF-kB elements and with a plasmid encoding renilla luciferase as a transfection control. After 24h, cells were then stimulated with MDP-LL or MDP-LD (1ug/ml) for 6h. Transcriptional activation was quantified by ratios of firefly luciferase activity to renilla luciferase activity. Data were normalized to the unstimulated condition with empty vector transfection. Statistical analyses were performed using Student t-test. (* p<0.05). Cell lysates were also collected and subjected to western blot analysis to detect NOD2 and actin expression levels.