Mtf2-PRC2 control of canonical Wnt signaling is required for definitive erythropoiesis

Abstract

Polycomb repressive complex 2 (PRC2) accessory proteins play substoichiometric, tissue-specific roles to recruit PRC2 to specific genomic loci or increase enzymatic activity, while PRC2 core proteins are required for complex stability and global levels of trimethylation of histone 3 at lysine 27 (H3K27me3). Here, we demonstrate a role for the classical PRC2 accessory protein Mtf2/Pcl2 in the hematopoietic system that is more akin to that of a core PRC2 protein. Mtf2^-/- erythroid progenitors demonstrate markedly decreased core PRC2 protein levels and a global loss of H3K27me3 at promoter-proximal regions. The resulting de-repression of transcriptional and signaling networks blocks definitive erythroid development, culminating in Mtf2^-/- embryos dying by e15.5 due to severe anemia. Gene regulatory network (GRN) analysis demonstrated Mtf2 directly regulates Wnt signaling in erythroblasts, leading to activated canonical Wnt signaling in Mtf2-deficient erythroblasts, while chemical inhibition of canonical Wnt signaling rescued Mtf2-deficient erythroblast differentiation in vitro. Using a combination of in vitro, in vivo and systems analyses, we demonstrate that Mtf2 is a critical epigenetic regulator of Wnt signaling during erythropoiesis and recast the role of polycomb accessory proteins in a tissue-specific context.

Fig. 1. Mtf2^−/− mice die at e15.5 due to severe anemia.

a Schematic of the gene-targeted ESCs used to create Mtf2 knockout mice. Mtf2 protein domains (Tudor, PHD) are indicated. b A PCR-based genotyping strategy was used to identify homozygous mutants. c Mtf2^−/− embryos readily display anemia and growth defects, dying by e15.5. d The e15.5 Mtf2^−/− embryos are significantly smaller than their wild-type littermates but have e, f normal fetal liver (FL) weight as a measure of body size. g Peripheral blood taken from e15.5 Mtf2^−/− embryos contains fewer cells than wild-type littermates, large nucleated erythroid precursors (arrows) and very few enucleated red blood cells (arrowheads). h Null embryos have a lower hematocrit and i fail to express adult β1 hemoglobin transcript at the appropriate level, while embryonic (εY) hemoglobin expression was elevated. P value was calculated using Student's t test. All data are shown as mean ± SEM, n = 3, *p < 0.05. See also Supplementary Figure S1

Fig. 2. Mtf2 is required for normal erythroid differentiation.

a, b Mtf2^−/− FL cells have increased frequency of pro-erythroblasts (stages S0–S2) and fewer CD71⁺Ter119⁺ erythroblasts (stage S3). c Representative pictures from imaging flow cytometry on Mtf2^−/− e14.5 peripheral blood. Mtf2^−/− Ter119⁺ cells have more centrally located nuclei (analyzed by imaging flow cytometry) than their wild-type counterparts (Delta XY centroid values 0.69 ± 0.01 vs. 0.83 ± 0.01, p < 0.01). BF brightfield, TO thiazole orange. d, e FL cells from Mtf2^−/− embryos contain fewer erythroid progenitors (colony-forming unit-erythroid (CFU-E)) but have higher numbers of multipotent clonogenic progenitors (colony-forming unit-granulocyte, erythrocyte, macrophage, megakaryocyte (CFU-GEMM)). CFU-G colony-forming unit-granulocyte, CFU-M colony-forming unit-macrophage, CFU-GM colony-forming unit-granulocyte, macrophage, BFU-E burst-forming unit-erythroid. Data are shown as number of colonies per 2 × 10⁵ FL cells plated, mean ± SEM for n = 4 mice, in triplicate. f Schematic showing primary repopulation experiments using donor wild-type and Mtf2^−/− e14.5 FL cells. g Mtf2^−/− FL cells are able to home to the bone marrow 17 h after injection as well as WT cells. h The percentage of CD45.2⁺ donor-derived cells in the peripheral blood of recipient animals is similar when either wild-type or Mtf2^−/− FL donor cells are injected. i Erythroid defects observed in Mtf2^−/− FL are cell-intrinsic and recapitulated in recipient mice. A higher frequency of Mtf2^−/− FL donor-derived pro-erythroblasts (ProE) and fewer mature erythroblasts (EryC) were observed compared to WT FL donor cells. P value was calculated using Student's t test. *p < 0.05, **p < 0.01, ***p < 0.001, n = 3. See also Supplementary Figure S2

Fig. 3. Mtf2 is required for promoter-proximal histone trimethylation of lysine 27 within fetal liver erythroid progenitors.

a Transcript levels of PRC2 complex members, Suz12, Ezh1/2 and Jarid2, as well as PRC1 component Ring1b are unchanged in Mtf2^−/− CD45⁺ FL cells as determined by RT-qPCR. b Core PRC2 proteins Ezh2, Suz12 and Eed are downregulated along with Mtf2 in both CD45⁺ and CD45^- FL cells from Mtf2^−/− mice. H3 was used as a protein loading control, and representative images are shown. c The k-mean clustering identifies patterns of H3K27me3 enrichment in primary CD71⁺ Ter119⁺ erythroblasts. Globally, a loss of enrichment centered around transcriptional start sites (TSS) is observed in CD71⁺ Ter119⁺ cells lacking Mtf2, which correlates with non-methylated CpG islands in ESCs within the same genomic regions. d H3K27me3 ChIP-seq density of reads is plotted within 5 kb of the TSS within one cluster of approximately 2400 genes (Cluster 5). In these genes, H3K27me3 binding is specifically reduced immediately around the TSS in Mtf2-null CD71⁺ Ter119⁺ cells. e WT and Rescue conditions are compared to KO. Validation of targets and non-targets from H3K27me3 ChIP-seq results performed by ChIP-qPCR. Rescuing Mtf2 expression by overexpressing Mtf2 within Mtf2-deficient CD71⁺ Ter119⁺ cells resulted in increased H3K27me3 binding at positive target loci. f, g ChIP-qPCR analysis revealed f a loss of Ezh2 binding and g no changes in Ring 1B binding within TSS regions that showed loss of H3K27me3 marks, when WT and Rescue conditions are compared to KO. h Overlap of genes associated with binding sites identified by ChIP-seq. In all, 1131 genes have lost H3K27me3 marks upon loss of Mtf2/PRC2 and 550 of those targets also show Mtf2 binding. See also Supplementary Figures S3-S4. ***P < 0.001

Fig. 4. Mtf2 regulates Wnt-dependent erythroid maturation.

a, b An erythroid-specific GRN was drafted using RNA-seq data from WT and Mtf2-null mouse CD71⁺ Ter119⁺ erythroblasts and integrating genes that have lost H3K27me3 upon loss of Mtf2. Node color represents change in gene expression. b GO analysis revealed regulatory pathways involved in canonical Wnt signaling, hematopoiesis, cell cycle and transcription are misregulated upon loss of Mtf2. c, d RT-qPCR and ChIP-qPCR analysis in WT and KO FL HSPCs revealed that c β-catenin is overexpressed in Mtf2^−/− FL HSPCs and d there is loss of H3K27me3 levels within the promoter region of β-catenin in Mtf2^−/− FL HSPCs. Rescue of Mtf2 levels within Mtf2^−/− FL HSPCs repressed β-catenin mRNA expression, rescued H3K27me3 levels and e reduced nuclear localization of β-catenin (detected by imaging flow cytometry, where a mask is created within the nucleus and the mean pixel intensity of β-catenin within the nucleus is compared to that within the entire cell (nucleus+cytoplasm). Knockdown of Mtf2 using two independent shRNAs (Sh3 and Sh7) within adult BM HSPCs led to f loss of H3K27me3 levels within the promoter region of β-catenin and g increased mRNA expression of β-catenin. h Experimental schematic of CFU-C assay, where scramble transduced HSPCs and Mtf2-deficient HSPCs (transduced with two independent shRNAs against Mtf2) were treated with DMSO or Wnt inhibitors (either ICG001 or JW74), respectively, and where all individual treatments of Sh3 and Sh7 KD cells are compared to all individual treatments of Scr transduced cells. Wnt inhibition via ICG001 or JW74 small-molecule treatment in Mtf2-deficient HSPCs gave rise to significantly more BFU-E colonies. ***P < 0.001, n = 3. See also Supplementary Figures S5 and S6

Fig. 5. Mtf2-dependent epigenetic regulation of Wnt signaling also affects negative regulators of erythropoiesis.

a Experimental schematic of ex vivo erythroid differentiation assay using FACS sorted Mtf2-deficient or WT/scramble transduced CD71⁺Ter119^- cells. b–d FACS sorted Mtf2-deficient pro-erythroblasts (CD71⁺Ter119^- cells), treated with Wnt inhibitors (ICG001 or JW74) for 2 days in erythroid differentiation culture media, show an increased capacity to differentiate into CD71⁺Ter119⁺ cells. e–h Mtf2 knockout (e, h) or knockdown (f, g) CD71⁺Ter119⁺ cells treated with Wnt inhibitors show inhibition of de-repressed erythroid genes, including Gata2, Myb, Fli1 and Stat5b. In (e), WT and rescue conditions are compared to KO. In (f), Sh3 KD cells treated with DMSO are compared to Sh3 KD cells treated with ICG001 and Sh3 KD cells treated with JW74. In (g), Sh7 KD cells treated with DMSO are compared to Sh7 KD cells treated with ICG001 and Sh7 KD cells treated with JW74, and in (h), KO cells treated with DMSO are compared to KO cells treated with Wnt inhibitors (ICG001 or JW74). ***P < 0.001, n = 3

Fig. 6. Mechanistic overview of erythroid maintenance via Mtf2 repression of Wnt signaling.

In a wild-type erythroblast (left), Mtf2-PRC2 repression of important negative regulators of erythropoiesis and repression of canonical Wnt signaling results in proper erythroid maturation. In the absence of Mtf2 (right), de-repression of erythroid regulators and Wnt signaling results in a block in erythroid differentiation, which can be largely rescued by chemical inhibition of β-catenin