Allelic skewing of DNA methylation is widespread across the genome

Abstract

DNA methylation is assumed to be complementary on both alleles across the genome, although there are exceptions, notably in regions subject to genomic imprinting. We present a genome-wide survey of the degree of allelic skewing of DNA methylation with the aim of identifying previously unreported differentially methylated regions (DMRs) associated primarily with genomic imprinting or DNA sequence variation acting in cis. We used SNP microarrays to quantitatively assess allele-specific DNA methylation (ASM) in amplicons covering 7.6% of the human genome following cleavage with a cocktail of methylation-sensitive restriction enzymes (MSREs). Selected findings were verified using bisulfite-mapping and gene-expression analyses, subsequently tested in a second tissue from the same individuals, and replicated in DNA obtained from 30 parent-child trios. Our approach detected clear examples of ASM in the vicinity of known imprinted loci, highlighting the validity of the method. In total, 2,704 (1.5%) of our 183,605 informative and stringently filtered SNPs demonstrate an average relative allele score (RAS) change > or =0.10 following MSRE digestion. In agreement with previous reports, the majority of ASM ( approximately 90%) appears to be cis in nature, and several examples of tissue-specific ASM were identified. Our data show that ASM is a widespread phenomenon, with >35,000 such sites potentially occurring across the genome, and that a spectrum of ASM is likely, with heterogeneity between individuals and across tissues. These findings impact our understanding about the origin of individual phenotypic differences and have implications for genetic studies of complex disease.

Figure 1

Outline of the Experimental Approach Used to Identify Allele-Specific DNA Methylation Genomic DNA samples were digested with a cocktail of three methylation-sensitive restriction enzymes (MSREs). In parallel, artificially unmethylated DNA from each individual was digested using the same cocktail of enzymes to act as a control for the effect of genetic variation at MSRE cut-sites. Samples were subsequently genotyped on Affymetrix 6.0 genotyping microarrays with complete allele-specific DNA methylation (ASM), causing a switch from a heterozygous genotype call to a monoallelic genotype call in digested samples. To assess more quantitatively skewed ASM, we assessed relative allele score (RAS) changes in digested samples. Black circles denote methylated CpG dinucleotides. White circles denote unmethylated CpG dinucleotides.

Figure 2

Strong ASM in the SNRPN Promoter Overlaps with a Region Previously Identified as a DMR Regulating Monoallelic Expression across the 15q11.2 Imprinted Gene Cluster (A) The location of potentially informative fragments are shown in black, with the average RAS change in each of the five MZ twin pairs for individual SNPs within each fragment shown as blue bars. This figure was adapted from an annotated UCSC Genome Browser track containing all our microarray data, available for download from our laboratory website. Large RAS changes are seen in both twin pairs heterozygous for SNP_A-1932077 (rs220030), located immediately upstream of the SNRPN transcription start site. (B) Heat map of normalized array signal data for the three probes representing SNP_A-1932077 (rs220030). The genotype (G) demonstrates a clear switch to monoallelic signal in the digested samples (D) for both members of twin pairs 2411 and 1990, who are heterozygous for this polymorphism. A different allele is methylated in each pair, as might be expected in an imprinted locus. The remaining three pairs are homozygous for SNP_A-1932077 (rs220030) and do not change in genotype call with digested DNA (column D), but show reduced signal intensity consistent with the loss of one parental allele. The unmethylated and digested samples (U) show a total loss of signal across all samples assessed, so this pattern is not due to polymorphic MSRE cut-sites. (C) Verification of the microarray data using SNuPE confirms a switch to monoallelic genotype in digested heterozygous samples. Shown are data from one member of each twin pair, confirming the loss of alternative alleles in each family. (D) MS-SNuPE analysis of a HhaI MSRE cut-site in the SNP_A-1932077 amplicon confirms this region is hemimethylated. (E) Data from 90 familial CEPH samples showing complete loss of heterozygosity after MSRE digestion, with a variable direction of ASM across individuals.

Figure 3

Evidence for Tissue-Specific ASM Associated with Parental Origin at SNP_A-1782879 (rs17427250), Located at 5q34 Upstream of ATP10B (A and B) Location of the SNP showing an average RAS change of 0.30 in heterozygous individuals corresponding to almost complete loss of signal from one allele following MSRE digestion (B). (C) These findings were verified using SNuPE in the original blood DNA, but there is no evidence of ASM in buccal cell DNA from the same individuals. (D) Clonal bisulfite sequencing confirmed this is a DMR, with a biphasic DNA methylation pattern at an informative AciI MSRE cut-site in the Affymetrix SNP amplicon. (E) Bisulfite sequencing in samples from family 1990 confirms tissue-specific differences in ASM, with blood samples showing a mixture of methylated and unmethylated alleles but buccal samples being fully methylated, including at an informative AciI site in the Affymetrix SNP amplicon. (F) Analysis of ASM at this SNP in 30 CEPH family trios (n = 90 individuals) demonstrated consistent loss of heterozygosity following MSRE digestion, although the effect was not in cis with genotype and likely due to genomic imprinting.

Figure 4

Confirmation of Previously Identified cis-Acting ASM (A–D) We confirmed several previously identified examples of ASM with large RAS changes following MSRE digestion identified for SNPs near LOC374491 (A), CYP2F1 (B), GCNT3 (C), FGD2-PIM1 (D), and LTF (see Figure 5). See also Table 3.

Figure 5

Intron 13 of the LTF Gene Contains Three SNPs Associated with ASM in cis (A) Location of SNP_A-1972595 (rs6441990), SNP_A-2149420 (rs6441991), and SNP_A-1876897 (rs6441992) with the average RAS change across heterozygous individuals shown as blue bars. (B) Heat map of normalized array signal data for the three probes representing SNP_A-1972595 (rs6441990), demonstrating a consistent loss of heterozygosity following MSRE digestion. (C and D) Microarray data were verified using SNuPE analyses. Shown are examples for (C) (SNP_A-1972595 [rs6441990]) and (D) (SNP_A-2149420 [rs6441991]). (E and F) cis-acting ASM was confirmed in the 30 CEPH family trios. Shown are data for (E) (SNP_A-1972595 [rs6441990]) and (F) (SNP_A-2149420 [rs6441991]). (G) Clonal bisulfite sequencing confirmed that G-A-A haplotypes are associated with lower DNA methylation (10%) compared to C-T-T haplotypes for four CpG sites spanning the three SNPs, including an informative HpaII site.

Figure 6

Analysis of SNP_A-1921713 (rs6760544) Located Upstream of RAB6C, which Shows Strong Evidence for a cis-Regulated ASM (A) Location of the SNP ∼43 kb upstream of RAB6C showing an average RAS change of 0.36. (B) Heat map of normalized microarray signal data for the three probes representing this SNP. Signals for the G allele do not differ between columns G and D, but the T allele signals are reduced to nearly the levels of the U (unmethylated) column. This complete MSRE digestion shows that the T allele carrying haplotype is unmethylated. (C) A pattern of cis-acting ASM associated with SNP_A-1921713 (rs6760544) was confirmed in the 30 CEPH family trios. (D) Bisulfite analysis at the HhaI and AciI MSRE cut-sites in the fragment incorporating rs6760544 confirms that DNA molecules containing allele T are unmethylated and DNA molecules containing allele G are methylated. This pattern is consistent across blood and buccal cell DNA and observed in all samples tested. (E) Clonal bisulfite sequencing confirmed a clear allelic association with DNA methylation across six CpG sites, including two located in informative MSRE cut-sites contained within the Affymetrix genotyping amplicon.

Figure 7

Analysis of SNP_A-2002432 (rs4936180) Located within OPCML, which Shows Evidence of Tissue-Specific cis-Mediated ASM (A–C) Location of the SNP, which shows an average RAS change of 0.19 across heterozygous individuals and is characterized by reduction of the C allele signal following MSRE digestion in blood DNA (B). The loss of allele C is not always complete; C/C homozygotes show some residual microarray signal, and loss of heterozygosity is not total in all heterozygotes, an observation confirmed in both our SNuPE verification assays and replication analysis (C) on the 30 CEPH family trios. (D) Bisulfite analysis of an AciI MSRE site support these data and highlight heterogeneity between samples, with some residual DNA methylation present on some C alleles; a biphasic, although not complete, pattern of DNA methylation at this MSRE site is confirmed by clonal bisulfite sequencing. (E) ASM at this locus is characterized by considerable tissue heterogeneity. (F) OPCML expression in blood is significantly associated with genotype at both SNP_A-2002432 (p < 0.02) and another nearby ASM-associated locus, SNP_A-2121632 (rs10791256) (p < 0.04), which shows an average RAS change of 0.12 across heterozygous individuals.

Figure 8

Examples of Association between Genotype at ASM-Associated SNPs and Gene Expression Genotype was compared with gene expression at nearby (<5 kb) genes using a linear model. An unadjusted p < 0.0001 cutoff was applied. Of the 5 genes presented, 2 are represented by more than one microarray probe set; shown are the most significant probe sets, but in each case the other probes in the same transcript show significant (p < 0.005) expression changes in the same direction (205462_at in HPCAL1 and 64432_at and 1553987_at in C12orf47). In total, >16% of loci demonstrating a change in RAS >0.10 following MSRE digestion, for which reliable expression data are available, show a significant linear association between genotype and transcript abundance.

Figure 9

cis-Acting ASM Near COL18A1 Is Associated with Gene Expression The abundance of COL18A1 transcripts, as measured by two Affymetrix gene expression microarray probe sets, is associated with genotype at SNP_A-2020619 (rs2236472), suggesting that ASM at this locus has a direct effect on transcription.