A genome-wide survey for SNPs altering microRNA seed sites identifies functional candidates in GWAS

Abstract

Background: Gene variants within regulatory regions are thought to be major contributors of the variation of complex traits/diseases. Genome wide association studies (GWAS), have identified scores of genetic variants that appear to contribute to human disease risk. However, most of these variants do not appear to be functional. Thus, the significance of the association may be brought up by still unknown mechanisms or by linkage disequilibrium (LD) with functional polymorphisms. In the present study, focused on functional variants related with the binding of microRNAs (miR), we utilized SNP data, including newly released 1000 Genomes Project data to perform a genome-wide scan of SNPs that abrogate or create miR recognition element (MRE) seed sites (MRESS).

Results: We identified 2723 SNPs disrupting, and 22295 SNPs creating MRESSs. We estimated the percent of SNPs falling within both validated (5%) and predicted conserved MRESSs (3%). We determined 87 of these MRESS SNPs were listed in GWAS association studies, or in strong LD with a GWAS SNP, and may represent the functional variants of identified GWAS SNPs. Furthermore, 39 of these have evidence of co-expression of target mRNA and the predicted miR. We also gathered previously published eQTL data supporting a functional role for four of these SNPs shown to associate with disease phenotypes. Comparison of FST statistics (a measure of population subdivision) for predicted MRESS SNPs against non MRESS SNPs revealed a significantly higher (P = 0.0004) degree of subdivision among MRESS SNPs, suggesting a role for these SNPs in environmentally driven selection.

Conclusions: We have demonstrated the potential of publicly available resources to identify high priority candidate SNPs for functional studies and for disease risk prediction.

Figure 1

A measure of SNP density (SNPs/kb) generated from the analysis of a 6 base window sliding over a 42-base region - centered on the first position of the seed site - of 606 validated MREs. The black line indicates the number of SNPs/kB across the 42 base region. The red line indicates the average SNP density across the 6 windows of seed positions 2-7.

Figure 2

Four SNPs found to associate, or be in LD with a SNP that associates, with a trait(s) relevant to disease. Each panel depicts the mRNA-miR interaction and the effect of the SNP on this interaction. Plots were generated using the Genvar web tool and published expression data from Nica, et al. rho = correlation between genotype and transcript levels. p = t = test statistic for correlation. padj = adjusted pvalue for correlation. F = -Fat cell biopsy (n = 160), L = LCL cells (n = 166), and S = skin cell biopsy (n = 160). Twin1 = Unrelated twin group 1. Twin2 = unrelated twin group 2.

Figure 3

A plot showing the number of combined MRESS and CNM SNPs or non MRESS and non CNM 3'UTR SNPs across 10 F_ST bins. Data plotted compares 2448 MRESS and CNM SNPs with F_ST data and a random sample of 2448 F_ST values from the remainder of 3'UTR SNPs. A significant difference between mean FST values for combined MRESS and CNM SNPs and FST values for the remaining 3'UTR SNPs was observed (P = 0.0004).