HIF1alpha synergizes with glucocorticoids to promote BFU-E progenitor self-renewal

Abstract

With the aim of finding small molecules that stimulate erythropoiesis earlier than erythropoietin and that enhance erythroid colony-forming unit (CFU-E) production, we studied the mechanism by which glucocorticoids increase CFU-E formation. Using erythroid burst-forming unit (BFU-E) and CFU-E progenitors purified by a new technique, we demonstrate that glucocorticoids stimulate the earliest (BFU-E) progenitors to undergo limited self-renewal, which increases formation of CFU-E cells > 20-fold. Interestingly, glucocorticoids induce expression of genes in BFU-E cells that contain promoter regions highly enriched for hypoxia-induced factor 1α (HIF1α) binding sites. This suggests activation of HIF1α may enhance or replace the effect of glucocorticoids on BFU-E self-renewal. Indeed, HIF1α activation by a prolyl hydroxylase inhibitor (PHI) synergizes with glucocorticoids and enhances production of CFU-Es 170-fold. Because PHIs are able to increase erythroblast production at very low concentrations of glucocorticoids, PHI-induced stimulation of BFU-E progenitors thus represents a conceptually new therapeutic window for treating erythropoietin-resistant anemia.

Figure 1

Enrichment of BFU-E and CFU-E cells by flow cytometric cell sorting. (A) Day 14.5-15.5 mouse fetal liver cells stained with biotin-conjugated antibodies against murine Ter119, B220, Mac-1, CD3, Gr-1, CD32/CD16, Sca-1, CD41, and CD34 were first depleted by magnetic beads (supplemental Table 1). The enriched negative fraction (FLEP) was then stained with streptavidin-phycoerythrin (PE), CD71 fluorescein isothiocyanate (FITC), and CD117 allophycocyanin (APC) antibodies, and the phycoerythrin-negative cells were sorted by FACS into 2 fractions, called BFU-E and CFU-E. The BFU-E fraction is the 10% lowest CD71-expressing part of the Kit (CD117)⁺ fraction, which has a CD71 signal intensity that is similar to or slightly higher than that of unstained cells. The CFU-E fraction is the 20% highest CD71-expressing part of the Kit⁺ fraction. Eighty-six percent of colonies formed by sorted BFU-E cells were BFU-E colonies, 11% CFU-E colonies, and 3% other myeloid colonies. Thus, the purity of these sorted BFU-E cells is ∼ 86%. The purity of CFU-E cells is slightly higher because they form 97% CFU-E colonies, 3% late-BFU-E colonies, and no other myeloid colonies (supplemental Table 2). The same FACS setup was later used to separate BFU-E and CFU-Es with higher purities with the use o f CD24a and a combination of CD24a and CD71 (supplemental Table 2). (B) Micrographs of sorted CFU-E (Kit⁺ CD71^20%high) cells and BFU-E (Kit⁺ CD71^0%low) cells stained with May-Grünewald-Giemsa. BFU-E cells have a high nuclear/cytoplasmic ratio and very fine nuclear chromatin. CFU-E cells are larger than BFU-E cells with a lower nuclear/cytoplasmic ratio and more regions of heterochromatin. CFU-E cells have multiple large, well-defined nucleoli (red arrows) in the nuclei. The CFU-E cytoplasm is very basophilic and sometimes bulges out from the cell. The morphology and relatively smaller size of BFU-E cells compared with CFU-E cells agree with previous studies on less pure populations of CFU-E and BFU-E cells.^, FS indicates forward scatter; SS, side scatter.

Figure 2

GCs stimulate stress erythropoiesis by enhancing erythroblast output predominantly from BFU-E progenitors. We determined whether adding 100nM Dex changes the maximum number of erythroblasts that sorted CFU-E and BFU-E cells produce in SFELE medium with or without 100nM Dex. (A) Production of erythroblasts from sorted CFU-E (CD71^20%high) cells peaks at day 3 with 28- and 15-fold expansion with and without Dex, respectively (n = 4). Error bars show 1 SD. (B) BFU-E (CD71^10%low) cells cultured with 100nM Dex expand 8800-fold (13 cell divisions) with a peak at day 8 and expand 650-fold (9 cell divisions) without Dex with the peak at day 5 (n = 5). At the endpoint of the BFU-E cell cultures cells were routinely stained with May-Grünewald-Giemsa stain, which consistently showed that virtually all cells were erythroblasts equivalent to the cells depicted in Figure 6C (data not shown). Error bars show 1 SD.

Figure 3

The effect of GCs on mRNA expression in BFU-E cells determined by next-generation sequencing. Sorted CD71^10%low BFU-E cells were cultured as detailed in Figure 1 for 4 hours either in the absence or presence of 100nM Dex, after which mRNA was extracted and subjected to Illumina next-generation sequencing. mRNA expression was normalized with the RPKM method, which determines the relative expression of each gene, normalized to the total transcriptome, by giving each gene an RPKM count. The mRNA expression R-I plot shows on the y-axis the log2 ratio of expression of individual mRNAs in Dex-stimulated versus nonstimulated cells. Positive values mean higher expression in BFU-E cells treated with 100nM Dex (+1 = 100% up; +2 = 400% up; −1 = 50% down; −2 = 75% down, etc). The x-axis shows the average expression of individual mRNAs, plotted as the log2 of the product of expression of the mRNA in stimulated and nonstimulated cells.

Figure 4

The PHI DMOG and Dex have overlapping effects on gene expression in BFU-E cells. Next-generation mRNA sequencing was performed on mRNA extracted from BFU-E (CD71 and CD24a^10%high) cells cultured 4 hours in SFELE medium with 100nM Dex, with 333mM DMOG; or with both 100nM Dex and 333mM DMOG. Expression of the 9636 most highly expressed genes (multiplied RPKM > 0 from the 4 groups) from cells treated with Dex, DMOG, and DEX + DMOG was compared with cells cultured in SFELE medium only. The left Venn diagram shows the overlap of the genes that increased > 50%, whereas the Venn diagram to the right shows overlap of genes that decreased to < 50% of that in unstimulated BFU-Es. Significance of the overlapping genes was computed with the use of hypergeometric distribution over all genes detected in any of the samples. The statistical significance of each respective overlap is presented below each diagram. The individual genes in each overlapping group are listed in supplemental Tables 5 and 6.

Figure 5

DMOG synergizes with Dex to increase the number of erythroblasts formed from a BFU-E cell 300-fold. The experimental protocol was similar to that used in Figure 2A and B except that the CFU-E and BFU-E cells were purer (CD71andCD24a^20%high and CD71andCD24a^10%low, respectively). The improved method provided a BFU-E population that formed 94% BFU-E, 5% CFU-E, and 1% other myeloid colonies in colony-forming assays with a plating efficiency of 70% (supplemental Table 2). Cultures contained or not 100nM Dex and/or 333μM DMOG. (A) Proliferation of sorted CFU-E cells. Cells do not increase proliferation in response to Dex or DMOG alone, whereas a combination of both Dex and DMOG increase proliferation 1.7-fold (P < .05; n = 6). Error bars show 1 SD. (B) Proliferation of sorted BFU-E cells (n = 4). The maximum increase in proliferation (compared with day 6 with no Dex or DMOG) was 2-fold with DMOG (day 7), 42-fold with 100nM Dex (day 9), and 306-fold with both Dex and DMOG (day 10). The synergistic effect is shown by the fact that DMOG increases the stimulatory effect of Dex on proliferation 7.3-fold (more than the additive 1.7-fold increase). Error bars show 1 SD. (C) BFU-E cells were cultured in SFELE medium containing 0nM, 1nM. 10nM, or 100nM Dex with different concentrations of DMOG. Cells were counted from day 4 until the day cell counts dropped. The y-axis shows the average expansion of several thousand BFU-E cells plated in each experiment. Without Dex 333μM DMOG had little effect on BFU-E proliferation, whereas adding 1nM Dex allows 333μM DMOG to enhance maximum BFU-E proliferation 12-fold. (n = 4) At the endpoint of the BFU-E cell cultures, 95% of cells were erythroblasts (Figure 6C; supplemental Figure 6B,D).

Figure 6

Proliferation of erythroid progenitors in the Lin⁻, Sca-1⁻, Kit⁺ mouse bone marrow progenitor population is synergistically enhanced by DMOG and Dex. (A) Lin⁻, Kit⁺, Sca-1⁻ mouse bone marrow cells were cultured in SFELE medium with no additions (control), 333μM DMOG, 1nM or 100nM Dex, 333μM DMOG plus 1nM Dex, or 333μM DMOG plus 100nM Dex. Total cell number was counted daily and normalized to the number of cells added to the culture. Error bars show 1 SD. (B) May-Grünewald-Giemsa staining of bone marrow Lin⁻, Kit⁺, Sca-1⁻ cells after 11 days of culture in medium with 333μM DMOG plus 100nM Dex. The erythroid morphology of these cells is further confirmed by FACS and benzidine-Giemsa staining (supplemental Figure 6A,C). (C) Fetal liver BFU-E cells after 10 days of culture in the same medium as panel B. The erythroid morphology is further confirmed by FACS and benzidine-Giemsa (supplemental Figure 6B,D). By these assays 80%-95% of cells are erythroid.