Haplotypes at ATM identify coding-sequence variation and indicate a region of extensive linkage disequilibrium

Abstract

Genetic variation in the human population may lead to functional variants of genes that contribute to risk for common chronic diseases such as cancer. In an effort to detect such possible predisposing variants, we constructed haplotypes for a candidate gene and tested their efficacy in association studies. We developed haplotypes consisting of 14 biallelic neutral-sequence variants that span 142 kb of the ATM locus. ATM is the gene responsible for the autosomal recessive disease ataxia-telangiectasia (AT). These ATM noncoding single-nucleotide polymorphisms (SNPs) were genotyped in nine CEPH families (89 individuals) and in 260 DNA samples from four different ethnic origins. Analysis of these data with an expectation-maximization algorithm revealed 22 haplotypes at this locus, with three major haplotypes having frequencies > or = .10. Tests for recombination and linkage disequilibrium (LD) show reduced recombination and extensive LD at the ATM locus, in all four ethnic groups studied. The most striking example was found in the study population of European ancestry, in which no evidence for recombination could be discerned. The potential of ATM haplotypes for detection of genetic variants through association studies was tested by analysis of 84 individuals carrying one of three ATM coding SNPs. Each coding SNP was detected by association with an ATM haplotype. We demonstrate that association studies with haplotypes for candidate genes have significant potential for the detection of genetic backgrounds that contribute to disease.

Figure 1

Schematic of ATM. The 184 kb of the ATM locus is illustrated, with the 64 exons represented by black boxes. Twenty-nine ∼500-bp regions were amplified by PCR in five unrelated individuals. These regions were sequenced and found to contain 17 SNPs.

Figure 2

ATM SNP allele frequencies for 14 ATM SNPs in each of four ethnic groups. A total of 260 individuals (71 African American, 39 Asian American, 77 white European American, and 73 Hispanic) were genotyped by ASO hybridization.

Figure 3

Four-gamete test for recombination in ATM. White boxes denote site pairs having four gametic types, which implies that recombination has occurred between these two sites. Also shown is the Hudson and Kaplan recombination statistic R, which is an estimate of the number and sites of recombination events needed to explain the results of the four-gamete matrix. A white box containing an “×” denotes a potential site of recombination. The asterisk (*) denotes an SNP that is not polymorphic in the sample population.

Figure 4

Fisher's exact test for LD in ATM. White boxes denote site pairs that do not have a significant value by Fisher’s exact test, indicating linkage equilibrium. Gray columns and rows denote SNPs that have a minor-allele frequency ⩽.05. The asterisk (*) denotes an SNP that is not polymorphic in the sample population.

Figure 5

D′, measured as D^′=D/|D|max in a pairwise fashion across 14 SNP loci. A score of either 1 or −1 is considered perfect disequilibrium. Black boxes denote site pairs with perfect disequilibrium; white boxes denote site pairs with |D^′|<1. The asterisk (*) pair denotes an SNP that is not polymorphic in the sample population.