Caucasian and Asian specific rheumatoid arthritis risk loci reveal limited replication and apparent allelic heterogeneity in north Indians

Abstract

Genome-wide association studies and meta-analysis indicate that several genes/loci are consistently associated with rheumatoid arthritis (RA) in European and Asian populations. To evaluate the transferability status of these findings to an ethnically diverse north Indian population, we performed a replication analysis. We investigated the association of 47 single-nucleotide polymorphisms (SNPs) at 43 of these genes/loci with RA in a north Indian cohort comprising 983 RA cases and 1007 age and gender matched controls. Genotyping was done using Infinium human 660w-quad. Association analysis by chi-square test implemented in plink was carried out in two steps. Firstly, association of the index or surrogate SNP (r2>0.8, calculated from reference GIH Hap-Map population) was tested. In the second step, evidence for allelic/locus heterogeneity at aforementioned genes/loci was assessed for by testing additional flanking SNPs in linkage equilibrium with index/surrogate marker.Of the 44 European specific index SNPs, neither index nor surrogate SNPs were present for nine SNPs in the genotyping array. Of the remaining 35, associations were replicated at seven genes namely PTPN22 (rs1217407, p = 3×10(-3)); IL2-21 (rs13119723, p = 0.008); HLA-DRB1 (rs660895, p = 2.56×10(-5); rs6457617, p = 1.6×10(-09); rs13192471, p = 6.7×10(-16)); TNFA1P3 (rs9321637, p = 0.03); CCL21 (rs13293020, p = 0.01); IL2RA (rs2104286, p = 1.9×10(-4)) and ZEB1 (rs2793108, p = 0.006). Of the three Asian specific loci tested, rs2977227 in PADI4 showed modest association (p<0.02). Further, of the 140 SNPs (in LE with index/surrogate variant) tested, association was observed at 11 additional genes: PTPRC, AFF3, CD28, CTLA4, PXK, ANKRD55, TAGAP, CCR6, BLK, CD40 and IL2RB. This study indicates limited replication of European and Asian index SNPs and apparent allelic heterogeneity in RA etiology among north Indians warranting independent GWAS in this population. However, replicated associations of HLA-DRB1, PTPN22 (which confer ∼50% of the heritable risk to RA) and IL2RA suggest that cross-ethnicity fine mapping of such loci is apposite for identification of causal variants.

Figure 1. Quantile-Quantile plot of chi-square test of association p-values of 48 SNPs (presented in Table S1).

Figure 2

A) LD plot of PTPRC among north-Indians, B) LD plot of PTPRC among CEU population, C) PTPRC haplotypes among north-Indians, D) PTPRC haplotypes among CEU population.

Figure 3

A) LD plot of CD28 among north-Indians, B) LD plot of CD28 among CEU population, C) CD28 haplotypes among north-Indians, D) CD28 haplotypes among CEU population.