Allelic H3K27me3 to allelic DNA methylation switch maintains noncanonical imprinting in extraembryonic cells

Abstract

Faithful maintenance of genomic imprinting is essential for mammalian development. While germline DNA methylation-dependent (canonical) imprinting is relatively stable during development, the recently found oocyte-derived H3K27me3-mediated noncanonical imprinting is mostly transient in early embryos, with some genes important for placental development maintaining imprinted expression in the extraembryonic lineage. How these noncanonical imprinted genes maintain their extraembryonic-specific imprinting is unknown. Here, we report that maintenance of noncanonical imprinting requires maternal allele-specific de novo DNA methylation [i.e., somatic differentially methylated regions (DMRs)] at implantation. The somatic DMRs are located at the gene promoters, with paternal allele-specific H3K4me3 established during preimplantation development. Genetic manipulation revealed that both maternal EED and zygotic DNMT3A/3B are required for establishing somatic DMRs and maintaining noncanonical imprinting. Thus, our study not only reveals the mechanism underlying noncanonical imprinting maintenance but also sheds light on how histone modifications in oocytes may shape somatic DMRs in postimplantation embryos.

Fig. 1. Noncanonical imprinting is independent of oocyte DNA methylation.

(A) Schematic diagram of the experimental strategy for assessing allele-specific gene expression in morulae. (+) Dnmt3l WT allele; (−) Dnmt3l KO allele. Dashed boxes indicate the samples collected for RNA-seq. (B) Heat maps showing the allelic expression bias of oocyte DNA methylation–dependent and maternal H3K27me3–dependent PEGs in morulae. Two independent samples were used for RNA-seq for each genotype. Genes with >20 SNP reads in both replicates are shown. (C and D) Representative genome browser views of an oocyte DNA methylation–dependent PEG Snrpn (C) and a maternal H3K27me3–dependent PEG Gab1 (D). For DNA methylation tracks, gray bars indicate the CpG sites with >5 reads coverage. Published H3K27me3 ChIP-seq data were from (14, 23), and DNA methylation data were from (44, 45).

Fig. 2. Oocyte H3K27me3 controls somatic DMR establishment.

(A) Genome browser views of DNA methylation levels at oocyte H3K27me3–dependent somatic DMRs. Areas shaded by purple indicate the identified somatic DMRs. DNA methylation data of E3.5 trophectoderm (TE) were obtained from a public dataset (16). (B) Genome browser view of DNA methylation levels at the Slc38a4 locus. No SNPs are available to differentiate the allele-specific reads at Slc38a4 promoter. (C and D) Heat maps showing the allelic expression bias of identified noncanonical imprinting loci in B6 and PWK reciprocal crosses in E6.5 ExE (C) and EED CTR and matKO E6.5 ExE (D). The E6.5 ExE RNA-seq data were obtained from previous studies (9, 10). B, B6; P, PWK. The names of the newly identified noncanonical imprinting loci are bolded. (E) Genome browser views of the two newly identified noncanonical imprinting loci. Shaded area (black bars) indicates the associated somatic DMRs. Oocyte H3K27me3 and DNA methylation data were obtained from previous studies (23, 44).

Fig. 3. Somatic DMRs are essential for maintaining noncanonical imprinting.

(A) Schematic diagram of the experimental strategy. Cas9 mRNA and six single-guide RNAs (sgRNAs) (three each targeting Dnmt3a or Dnmt3b) were injected into BDF1/PWK zygotes. Zygotes injected with water were used as the WT control. (B) RT-qPCR results showing relative expression levels of Dnmt3a and Dnmt3b in WT and DKO ExE. The expression levels in WT embryo #1 were set as 1.0. Complementary DNA (cDNA) was synthesized using a small piece of ExE as illustrated in (A). After verification of Dnmt3a/3b depletion by RT-qPCR, cDNA was then used to prepare RNA-seq libraries for next-generation sequencing. (C) Global view of DNA methylation status in TE and ExE of the indicated genotypes. Percentages of 100-bp tiles at four methylation levels are shown. Common CpGs between E3.5 TE WGBS data and E6.5 ExE RRBS data were retrieved, and tiles with >2 CpGs and >10 reads coverage in all samples were used to generate this plot (n = 317,106). For both WT and DKO, three low-input RRBS replicates were pooled and analyzed. Embryos #4, #6, and #7 shown in (B) were used for the RRBS experiments. WGBS data of E3.5 TE and RRBS data of DNMT3A and DNMT3B single-KO ExE were obtained from a previous study (16). (D) Genome browser views of DNA methylation levels covering the somatic DMRs of three maternal H3K27me3–dependent imprinted genes. (E) Genome browser views of DNA methylation levels at representative ICRs of oocyte DNA methylation–dependent imprinted loci KvDMR1 and Peg3. (F) Scatter plot comparing the gene expression levels between WT and DNMT3A/3B DKO E6.5 ExE. Two (WT) and seven (DKO) RNA-seq replicates were used for differential gene expression analyses. (G) Heat map showing the allelic expression bias of canonical and noncanonical imprinting loci. Genes with >20 SNP-containing RNA-seq reads are shown.

Fig. 4. Oocyte-inherited H3K27me3 domains are absent in E6.5 ExE.

(A) Average enrichment of H3K27me3 [log₂(maternal/paternal)] at the maternal H3K27me3 domains in morulae, WT ExE, and DNMT3A/3B DKO ExE. Maternal H3K27me3 domains previously identified in BDF1 × PWK IVF morula embryos (n = 4134) (31) were used to generate the plot. Note that the genetic background of the morula sample is the same as the ExE samples. For both WT and DNMT3A/3B DKO, two H3K27me3 CUT&RUN replicates were pooled for the analyses. For the DKO group, embryos #1 and #5 (Fig. 3B) were used for H3K27me3 CUT&RUN experiments separately and pooled for analysis. (B to D) Genome browser views of allelic H3K27me3 enrichment at Gab1, Platr20, Slc38a4, Smoc1, Phf17, and Sfmbt2 loci. The arrows in (C) points to the maternal allele–biased H3K27me3 peaks that are observed in WT but not in the DNMT3A/3B DKO ExE.

Fig. 5. Oocyte H3K27me3 regulates allelic H3K4me3 in preimplantation embryos.

(A) Genome browser views of DNA methylation and allelic H3K4me3 enrichment in EED CTR and matKO morulae and TE of blastocyst embryos. The shaded areas indicate the somatic DMRs. Morulae were collected at ~78 hpf, and TE samples were dissected from ~120 hpf blastocysts. (B) Genome browser views of allelic H3K4me3 levels at Gab1, Phf17, Platr20, and Smoc1 loci in each stage of preimplantation embryos. The H3K4me3 ChIP-seq data were obtained from a previous publication (24). (C) Heat map showing the allelic enrichment of promoter H3K4me3 peaks. Only noncanonical imprinting loci with sufficient (>50) SNP-containing reads of the associated promoter H3K4me3 peaks are shown. “+”: locus establishes somatic DMR in ExE or overlap with CGI; “−”: locus has no somatic DMR in ExE or does not overlap with CGI. (D) Genome browser views of DNA methylation and allelic H3K4me3 levels at G730013B05Rik, Tle3, and Grik3.

Fig. 6. Model illustrating that maintenance of maternal H3K27me3–dependent imprinting requires somatic DMR establishment in postimplantation embryos.