Essential roles of epithelial bone morphogenetic protein signaling during prostatic development

Abstract

Prostate is a male sex-accessory organ. The prostatic epithelia consist primarily of basal and luminal cells that differentiate from embryonic urogenital sinus epithelia. Prostate tumors are believed to originate in the basal and luminal cells. However, factors that promote normal epithelial differentiation have not been well elucidated, particularly for bone morphogenetic protein (Bmp) signaling. This study shows that Bmp signaling prominently increases during prostatic differentiation in the luminal epithelia, which is monitored by the expression of phosphorylated Smad1/5/8. To elucidate the mechanism of epithelial differentiation and the function of Bmp signaling during prostatic development, conditional male mutant mouse analysis for the epithelial-specific Bmp receptor 1a (Bmpr1a) was performed. We demonstrate that Bmp signaling is indispensable for luminal cell maturation, which regulates basal cell proliferation. Expression of the prostatic epithelial regulatory gene Nkx3.1 was significantly reduced in the Bmpr1a mutants. These results indicate that Bmp signaling is a key factor for prostatic epithelial differentiation, possibly by controlling the prostatic regulatory gene Nkx3.1.

Figure 1.

Bmp signaling was enhanced with the prostatic epithelial cell differentiation. A and B, Coronal sections of caudal body of ICR mice at P1; pSmad1/5/8 was weakly detected in the immature prostatic epithelia. C–F, Coronal sections of AP at P7 (C and D) and P14 (E and F). E and F, pSmad1/5/8 signal was more prominently observed in the differentiated luminal cells (F, red arrowhead) than that of the basal cells (F, black arrow) in the AP. UR, urethra. Epi, epithelia; M, mesenchyme. Scale bars, 100 μm.

Figure 2.

Defective prostatic epithelial differentiation was induced in the Bmpr1a-CKO mutants prostate. A, C, E, G, I, and K, Epithelial differentiation in the AP of control mice. B, D, F, H, J, and L, Epithelial differentiation in the AP of epithelial-specific Bmpr1a-CKO mutant mice. A and B, Costaining for green fluorescent protein (GFP) and pSmad1/5/8 in the AP at P14. Mosaic expression of GFP was detected only in the AP epithelia but not in the stroma of both control and Bmpr1a-CKO specimens (green). A and C, pSmad1/5/8 was localized primarily in the prostatic epithelia. B and D, Decreased pSmad1/5/8 expression was detected in the Bmpr1a-CKO specimens. E, Control AP ducts at P14. F, Bmpr1a-CKO mutant AP at P14. G and H, Histologic section of the control (G) and Bmpr1a-CKO mutant prostate (H). I–L, Costaining for K19 and K8 at P7 and P14. K, K19 was localized in basal epithelia and K8 was localized in the luminal epithelia of the control mouse prostate at P14 (K′, white arrows). K8 and K19 were aberrantly coexpressed at P14 in the Bmpr1a-CKO specimens (L). A–D and G and H, scale bars, 50 μm. I–L, scale bars, 20 μm.

Figure 3.

Abnormal stratification and decreased mRNA level of secretory protein in the Bmpr1a-CKO mutant prostate. A, Control AP ducts at P28. B, Bmpr1a-CKO mutant AP at P28. C, Histologic section of the control prostate. Inset, Luminal cells (red arrowhead) and basal cells (black arrow) were observed. D, Histology of the Bmpr1a-CKO mutant prostate. Inset, Abnormally stratified epithelia were observed (black arrowhead). Scale bars, 100 μm. E, Probasin mRNA expression was decreased in the mutant AP at P28. The relative RNA equivalents for each sample were normalized by the RNA levels for ribosomal protein L8. Error bars represent the mean ± SE of 7 tissue samples. Statistical significance was indicated by an asterisk. F and G, Expression of K8 in control (F) and mutant (G) prostate. K8-positive basal side epithelia were indicated (G, black arrow). H and I, Expression of K14 in control (H) and mutant (I) prostate. K14-positive luminal side epithelia were indicated (I, black arrow). Increased levels of K8 (G) and K14 (I) were detected in the Bmpr1a-CKO mutants at P49. Scale bars, 20 μm.

Figure 4.

Basal cell proliferation increases in the Bmpr1a-CKO mutants. A–D, Costaining for Ki67 and p63 at P14 (A and B) and P28 (C and D) was performed. E, Ki67-positive epithelia were quantified at P14 and P28. F, Cells positive for both Ki67 and p63 were quantified at P14 and P28. Scale bars, 50 μm. Significantly increased ratios of proliferative epithelia (E) and proliferative basal cells at P28 (F) were detected. Data are presented as means of 3 values ± SE. Statistical significance was calculated using Student's t test followed by the F test (*, P < .05).

Figure 5.

Decreased expression of Nkx3.1 in the Bmpr1a-CKO mutants. A and B, Nkx3.1 expression decreased in mutant prostate at P1 (A) and in the mutant AP at P28 (B). The relative mRNA equivalents for each sample were normalized by the RNA levels for ribosomal protein L8. Bars represent the mean ± SE of triplicate assays of RNA from pooled tissues (A) and 6 tissue samples (B). Statistical significance was indicated by asterisks (*, P < .05). C, Nkx3.1 was detected in the luminal epithelia of the control AP at P28. D, Significantly reduced levels of Nkx3.1 protein were detected in the mutant AP. E, The ratios of Nkx3.1-positive cells were shown in the graph. F, Colocalization of Nkx3.1 and Bmpr1a in the AP luminal epithelia of adult mice. G, Colocalization of pSmad1/5/8 and Nkx3.1 in the AP luminal epithelia of adult mice. F and G, Cryosections were used. Scale bars, 20 μm. H, Genomic sequences of the mouse Nkx3.1 aligned with its orthologous loci in human and opossum. The sequence alignment was performed using MultiPipMaker. A noncoding region conserved from human to opossum was indicated with black boxes in the C1 and C2 regions. The black arrow indicated exons of mouse Nkx3.1. Coding and untranslated sequences were shaded with red and yellow, respectively. A 5-kb (5399 base) region in the 3′-genomic region of Nkx3.1 contained a candidate enhancer region for the mouse prostate. The scale at the bottom of the alignment indicated relative positions in the mouse Nkx3.1 locus. I, The candidate 5-kb prostatic regulatory enhancer activated expression of a luciferase reporter in response to Smad1/4 expression (by 6 independent assays). It also responded to the addition of Bmp7 (by 3 independent assays) (means ± SE) (*, P < .05). a, Control. b, Transfected with Smad1/4 gene. c, Control. d, Transfected with Smad1/4 gene + addition of Bmp7. J, ChIP/PCR assay on bladder neck of ICR mice including prostate region at P2 showed pSmad1/5/8 binding to regions of C1 and C2 in the 3′-region of mouse Nkx3.1. Both regions were enriched in chromatin immunoprecipitated with antiacetylated histone H3 as a positive control.

Figure 6.

Stromal hyperplasia and inflammation with enlarged epithelial nuclear structures were observed in the Bmpr1a-CKO mutants. A, Morphology of AP in wild-type, ShhCreERT2/+;Bmpr1a-flox/+ (Control), and ShhCreERT2/+; Bmpr1a-flox/− mice at 6 months of age. B, D, and G, Histology of control AP. C, E, F, H, and I, The sections of the epithelial-specific Bmpr1a-CKO mutant AP. B–I, Sections stained with hematoxylin and eosin showed inflammatory cells in the stroma (E), stromal hyperplasia (F, black arrow head), inflammatory cells (H, black arrows), and enlarged nuclear structures (I) in the AP of Bmpr1a-CKO mice. A and B, Scale bars, 200 μm. D–F, Scale bars, 20 μm.