Transposable elements: targets for early nutritional effects on epigenetic gene regulation

Abstract

Early nutrition affects adult metabolism in humans and other mammals, potentially via persistent alterations in DNA methylation. With viable yellow agouti (A(vy)) mice, which harbor a transposable element in the agouti gene, we tested the hypothesis that the metastable methylation status of specific transposable element insertion sites renders them epigenetically labile to early methyl donor nutrition. Our results show that dietary methyl supplementation of a/a dams with extra folic acid, vitamin B(12), choline, and betaine alter the phenotype of their A(vy)/a offspring via increased CpG methylation at the A(vy) locus and that the epigenetic metastability which confers this lability is due to the A(vy) transposable element. These findings suggest that dietary supplementation, long presumed to be purely beneficial, may have unintended deleterious influences on the establishment of epigenetic gene regulation in humans.

FIG. 1.

IAP insertion site in A^vy allele. (A) Exon 1A of the murine agouti gene lies within an interrupted 4.1-kb inverted duplication (shaded block arrows). The duplication gave rise to pseudoexon 1A (PS1A). On the A allele, PS1A is located ≈100 kb upstream of exon 2 and ≈15 kb downstream of the contraoriented exon 1A (6). The A^vy mutation was caused by a contraoriented IAP insertion (striped bar; tall arrowhead shows direction of IAP transcription). A cryptic promoter within the long terminal repeat proximal to the agouti gene (short arrowhead labeled A^vy) drives ectopic agouti expression in A^vy animals. In A and a animals, transcription starts from a hair cycle-specific promoter in exon 2 (short arrowhead labeled A, a). Small arrows show the positions of PCR primers used to selectively amplify the exon 1A and PS1A regions. (B) Agarose gel showing products of long-range PCR of A^vy/a genomic DNA. Forward (F) and reverse (R) primers are described relative to the direction of the inverted duplicate regions and are shown in A. The same forward primer was used in all reactions. Three different reverse primers specific to the PS1A region (lanes 5 to 7) amplified fragments of ≈1.4 kb (the a allele) and ≈6 kb (the A^vy allele, including the IAP insert). Three different reverse primers specific to the exon 1A region (lanes 2 to 4) amplified only the smaller fragments (≈1.6 kb). The exon 1A fragments are larger than the PS1A a fragments due to the more distal location of the exon 1A reverse primers.

FIG. 2.

Maternal dietary methyl supplementation and coat color phenotype of A^vy/a offspring. (A) Isogenic A^vy/a animals representing the five coat color classes used to classify phenotype. The A^vy alleles of yellow mice are hypomethylated, allowing maximal ectopic agouti expression. A^vy hypermethylation silences ectopic agouti expression in pseudoagouti animals (15), recapitulating the agouti phenotype. (B) Coat color distribution of all A^vy/a offspring born to nine unsupplemented dams (30 offspring; shaded bars) and 10 supplemented dams (39 offspring; black bars). The coat color distribution of supplemented offspring is shifted toward the pseudoagouti phenotype compared to that of unsupplemented offspring (P = 0.008).

FIG. 3.

CpG methylation within the A^vy PS1A of A^vy/a offspring from unsupplemented and methyl-supplemented dams. (A) Percentage of cells methylated at each of seven CpG sites in the A^vy PS1A in all A^vy/a offspring of nine unsupplemented and 10 supplemented dams. DNA was isolated from tail tips at weaning. The seven CpG sites studied are located ≈600 bp downstream from the A^vy IAP insertion site. Percent methylation is distributed bimodally in unsupplemented offspring, with less than 20% of the cells being methylated at each site in most animals. Maternal methyl supplementation increases mean methylation at each site, generating a more uniform distribution. Dotted lines show the average percent methylation across the seven sites in all A^vy/a offspring according to coat color phenotype. (B) Mediational regression analysis (3) of supplementation, A^vy methylation, and coat color. Supplementation significantly affects offspring coat color (top), but this relationship is nullified when A^vy PS1A methylation is included in the regression model (bottom). This indicates that A^vy CpG methylation is solely responsible for the effect of supplementation on coat color.

FIG. 4.

A^vy PS1A methylation as a function of tissue type and animal age. (A) Average percent methylation of seven CpG sites in the A^vy PS1A in tail (T), liver (L), kidney (K), and brain (B) samples from five A^vy/a animals representing the five coat color classes shown in Fig. 2A. A^vy methylation in the tail correlates highly with that in other tissues (r² > 0.98 for all comparisons). (B) Average percent methylation of A^vy PS1A in day 100 liver versus that in day 21 tail tip DNA. Percent methylation in day 21 tail predicts that in day 100 liver (r² = 0.95). Open triangles, unsupplemented offspring; solid triangles, supplemented offspring. Neither group departed significantly from the line of identity (shown). Hence, A^vy PS1A methylation is maintained with high fidelity into adulthood.

FIG. 5.

Percentage of cells methylated at each of seven CpG sites in A^vy exon 1A (A), A^vy PS1A (B), a exon 1A (C), and a PS1A (D). Each graph shows data from the same two slightly mottled and two pseudoagouti A^vy/a animals (four total). In the A^vy PS1A region (B), CpG methylation correlates with coat color; the pseudoagouti animals (circles) were heavily methylated, and the slightly mottled animals (triangles) were hypomethylated. In the other three regions (A, C, and D), methylation was independent of coat color (each point shows the mean ± standard error of the mean). On the a allele, methylation was tightly regulated and site dependent and did not differ significantly between the exon 1A and PS1A regions (C and D). Note that CpG site 5 is missing in the exon 1A region of the a allele in C due to a single-nucleotide polymorphism. The A^vy exon 1A region (A) was hypermethylated relative to consensus sites on the a allele (P < 0.0001). Given the 99% sequence identity of these four regions, the epigenetic metastability of A^vy PS1A is clearly associated with the neighboring IAP.