Autosome-wide copy number variation association analysis for rheumatoid arthritis using the WTCCC high-density SNP genotype data

Abstract

Objective: Rheumatoid arthritis (RA) is a complex autoimmune rheumatic disease that is strongly influenced by genetic factors. Numerous genes are convincingly associated with RA, including genes in tumor necrosis factor signaling (TNF) and the nuclear factor-κB pathway. To date, except for genes within the HLA region, no data exist regarding potential copy number variations (CNV) involving RA-associated genes. We set out to identify genes affected by CNV that are associated with RA at a genome-wide level.

Methods: Data from the Wellcome Trust Case Control Consortium (WTCCC) were used in our analyses. The initial WTCCC cohort genotyped 3004 controls and 1999 RA cases using the GeneChip 500k Mapping Array Set. We performed a comparative intensity analysis using the PennCNV algorithm, which uses a hidden Markov model to detect CNV. A total of 2271 controls and 1572 RA samples passed quality control criteria and were included for association analysis. Association analysis was performed in 2 phases: (1) to identify CNV that are < 1 Mb with a population frequency < 5%; and (2) to identify large CNV that are > 1 Mb. Fishers' exact test was performed to quantify significance of the CNV.

Results: We observed that the genome-wide CNV burden is 2-fold higher in patients with RA compared with controls. We identified 11 rare copy number variable regions with < 5% frequency that had an association with RA that reached a p < 1 × 10(-4). These include TNFAIP3 and TNIP1, which has been implicated in association studies for RA, systemic lupus erythematosus, and psoriasis. We identified CNV involving IRF1, which functions as a transcription activator of genes induced by interferons; ALOX5AP and LCP2, involved in inflammatory mediation; B2M, an MHC-class I associated gene; and PRKCH, a gene involved in T cell signaling pathways. A 57 kb deletion with 1% frequency in RA cases at 7p21.3 was also observed. Six of these loci overlap with CNV catalogued in the Database of Genomic Variants.

Conclusion: This is the first study to identify non-HLA RA-associated CNV using genome-wide analyses. Validation and functional significance of these deletions/duplications in RA and other autoimmune diseases need to be further investigated.