Heritable epigenetic variation among maize inbreds

Abstract

Epigenetic variation describes heritable differences that are not attributable to changes in DNA sequence. There is the potential for pure epigenetic variation that occurs in the absence of any genetic change or for more complex situations that involve both genetic and epigenetic differences. Methylation of cytosine residues provides one mechanism for the inheritance of epigenetic information. A genome-wide profiling of DNA methylation in two different genotypes of Zea mays (ssp. mays), an organism with a complex genome of interspersed genes and repetitive elements, allowed the identification and characterization of examples of natural epigenetic variation. The distribution of DNA methylation was profiled using immunoprecipitation of methylated DNA followed by hybridization to a high-density tiling microarray. The comparison of the DNA methylation levels in the two genotypes, B73 and Mo17, allowed for the identification of approximately 700 differentially methylated regions (DMRs). Several of these DMRs occur in genomic regions that are apparently identical by descent in B73 and Mo17 suggesting that they may be examples of pure epigenetic variation. The methylation levels of the DMRs were further studied in a panel of near-isogenic lines to evaluate the stable inheritance of the methylation levels and to assess the contribution of cis- and trans- acting information to natural epigenetic variation. The majority of DMRs that occur in genomic regions without genetic variation are controlled by cis-acting differences and exhibit relatively stable inheritance. This study provides evidence for naturally occurring epigenetic variation in maize, including examples of pure epigenetic variation that is not conditioned by genetic differences. The epigenetic differences are variable within maize populations and exhibit relatively stable trans-generational inheritance. The detected examples of epigenetic variation, including some without tightly linked genetic variation, may contribute to complex trait variation.

Figure 1. Synopsis of chromosome-level methylation and variation.

(A–B) A Gbrowse view is presented for 140 kb of chromosome 8 (3,380 kb–3,520 kb) and a closer view of 22 kb (97,273–97,294K) that includes a differentially methylated region (red box). The top track shows the regions that are annotated as repetitive sequences using the MIPS/Recat repeat catalog. The next two tracks show the B73 (red) and Mo17 (blue) relative methylation levels for each of the probes within these regions. Methylation levels are defined as the normalized log2 ratio of IP enriched sample to un-enriched genomic DNA on a scale of −3 to 3 indicating methylation enrichment (>0) and depletion (<0) respectively. The bottom tracks illustrate the gene models. The gray arrows indicate gene models that were rejected from the FGS. (C) Shows a chromosomal view of methylation levels in B73 and Mo17. The percentage of methylation is plotted as a 5 Mb window sliding 1 Mb downstream across the chromosome Blue and red lines indicate percent methylation of all probes for B73 and Mo17 respectively. The green line indicates centromere position. The black line shows the cm/Mb across the chromosome. The first heatmap provides a visualization of gene density. Yellow and black values indicate lower and higher relative gene density values respectively. The second heatmap provides visualization for the genomic structural variation between B73 and Mo17 using Comparative Genomic Hybridization (CGH) values. A 5 Mb sliding window across the chromosome indicates regions of high diversity (black) to low diversity (yellow). The differential methylation regions (DMRs) are shown using red (Mo17 hypermethylation) and blue (B73 hypermethylation) arrows. The next track shows the location of individual probes that have significant (q<0.001) methylation variation between B73 and Mo17. The final heat map indicates the relative enrichment for differentially methylation probes across the chromosome with enriched regions indicated by red and regions with depleted levels of methylation variation in green.

Figure 2. Gene body methylation and expression levels in maize genes.

(A) The relative methylation levels (log2(IP/input)) were assessed for probes within 1000 bp of the transcription start and termination site. The relative position for probes within the gene was normalized to a scale of 1000. The genes in the filtered gene set (FGS) exhibit a lower methylation and a more dynamic pattern across the length of the gene than the rejected genes. The vertical dashed lines indicated the beginning and end of transcription for each gene. (B) The relative expression level for all FGS genes was assessed using published RNAseq data from B73 leaf tissue and genes were assigned as not expressed or quartile 1–4 based on their expression level. In general, the genes show similar patterns of methylation but the higher expressed genes exhibit lower levels of methylation within and around the gene. (C) Each of the FGS genes was also classified according to whether it was located in a syntenic position relative to sorghum and/or rice or in a non-syntenic position. The syntenic genes exhibit much lower levels of methylation than the non-syntenic genes. This difference between syntenic and non-syntenic genes can also be seen in the regions immediately surrounding the gene.

Figure 3. DMRs in B73 and Mo17.

(A) The relative methylation levels for all probes were used to perform DNAcopy segmentation followed by expectation maximization. The black dashed lines show the observed distribution of the segment means. This distribution can be approximated (red dashed line) by a model that is derived from three normal distributions including B73 hypermethylation (right peak), Mo17 hypermethylation (left peak) and unchanged regions (middle peak). (B) The structural variation across chromosome 8 is shown in the plot with black spots. The blue spots show relative methylation in B73 and Mo17. The region of low structural diversity (boxed region) is magnified in (C). (D) Gbrowse views for three DMRs located within this region are shown. The data tracks show the position of repeats, genes, B73 methylation, Mo17 methylation and relative methylation. Each bar showing methylation values represents an individual probe. The actual DMRs are shown by the red boxes.

Figure 4. Variable DNA methylation patterns in near-isogenic lines and diverse inbreds.

(A) The relative DNA methylation levels in selected near-isogenic lines was tested by digestion with the methylation dependent restriction enzyme MspjI followed by qPCR. Different subsets of NILs were selected and analyzed for each of 13 DMRs. The first two columns show the data from B73 and Mo17. Open circles reflect low methylation levels and black circles indicate high methylation levels. Intermediate methylation levels are indicated by gray color. The next group of 2–7 genotypes show the data from NILs that have B73 as the recurrent parent (>95% of the genome) and have introgression of the Mo17 haplotype in the region containing the DMR. The variable number of genotypes tested reflects the fact that some DMR loci are have more NILs with an introgression than others. The next group of 1–3 genotypes are NILs that are primarily Mo17 but have B73 introgressed at the DMR. The next two groups provide “control” genotypes of B73-like or Mo17-like NILs that do not have an introgression at the DMR. The expected patterns for cis (local) inheritance of DNA methylation or trans (unlinked) control of DNA methylation are shown. Note that the expected pattern for trans control would include a small number of genotypes with the methylation pattern from the introgressed genotype in cases where the trans-acting locus is introgressed. (B) The same type of assays were performed on a panel of 12 diverse inbred genotypes, including two inbred teosinte lines, to monitor the frequency for the hyper- and hypo-methylated states.