Endocrine regulation of male fertility by the skeleton

Abstract

Interactions between bone and the reproductive system have until now been thought to be limited to the regulation of bone remodeling by the gonads. We now show that, in males, bone acts as a regulator of fertility. Using coculture assays, we demonstrate that osteoblasts are able to induce testosterone production by the testes, though they fail to influence estrogen production by the ovaries. Analyses of cell-specific loss- and gain-of-function models reveal that the osteoblast-derived hormone osteocalcin performs this endocrine function. By binding to a G protein-coupled receptor expressed in the Leydig cells of the testes, osteocalcin regulates in a CREB-dependent manner the expression of enzymes that is required for testosterone synthesis, promoting germ cell survival. This study expands the physiological repertoire of osteocalcin and provides the first evidence that the skeleton is an endocrine regulator of reproduction.

Figure 1. Osteoblasts enhance testosterone biosynthesis by Leydig cells

(A) Schematic representation of the cell-based assay used to determine the role of various mesenchymal cells in sex steroid hormone production. Various primary mesenchymal cells from mice were cultured in Leydig cell medium and supernatants were collected after 24 h. Then, testis or ovary explants or primary Leydig cells were cultured for 1 h with these supernatants and radioimmunoassays (RIAs) were performed to measure levels of testosterone, estradiol or progesterone. (B–D) Testis explants cultured in the presence of supernatants of different mesenchymal cell cultures: RIA measurement of (B) testosterone, (C) estradiol and (D) progesterone levels. (E–G) Ovary explants cultured in presence of supernatants of different mesenchymal cells cultures: RIA measurement of (E) testosterone, (F) estradiol and (G) progesterone levels. (H) Testosterone production by primary Leydig cells cultured in the presence of supernatants of different mesenchymal cell cultures. Error bars represent SEM. Student’s t test (*) P<0.05.

Figure 2. Osteocalcin favors male fertility by increasing testosterone production by Leydig cells

(A) Testosterone production by primary Leydig cells cultured in the presence of supernatants of wild type (WT) or Ocn−/− osteoblast cultures. (B) Testosterone production by primary Leydig cells following stimulation with increasing doses of osteocalcin. (C) Circulating testosterone levels in WT mice 1 h, 4 h and 8 h after vehicle or osteocalcin injection (3 ng/g of body weight). (D–E) Comparison between the average litter size (D) and frequency (E) generated by WT, Ocn−/− or Esp−/− male littermate mice crossed with WT females (breeding was tested from 8 to 16 weeks of age). (F–J) Testis size (F), testis weight (G), epididymis weight (H), seminal vesicle weights (I) and sperm counts (J) in Ocn−/− and Esp−/− compared to WT non-breeder littermate mice. (K) Circulating sex steroid levels in Ocn−/− and Esp−/− compared to WT littermate mice. The analyses were performed on breeders and non-breeder mice. (L) Circulating LH levels in Ocn−/− compared to WT non-breeder littermate mice. Error bars represent SEM. Student’s t test (*) P<0.05, (**) P<0.001.

Figure 3. Osteocalcin promotes male fertility through its expression in osteoblasts

(A) qPCR analysis of Osteocalcin expression in bone, testes and ovaries of 3 month-old non-breeder WT mice. (B) Western blot analysis of osteocalcin in femur, calvaria and testis. (C) In situ hybridization analysis of Osteocalcin expression in bone and testis of 3 month-old WT mice. (D) Analysis of mCherry fluorescent protein in bone and testis of Osteocalcin-mCherry knock-in mice. (E–H) Fertility in mice lacking Ocn specifically in osteoblasts (Ocn_osb−/−) or Leydig cells (Ocn_Leydig−/−) compared to WT non-breeder littermates: (E) testes weight, (F) sperm count, (G) epididymis and (H) seminal vesicle weights. (I) Ratio of circulating testosterone levels measured in WT and Ocn_osb−/− or in WT and Ocn_Leydig−/− non-breeder littermate mice. (J) Linear regression representation of circulating testosterone levels versus circulating osteocalcin levels in Ocn_osb−/− (n=11) non-breeder mice. Each dot represents one Ocn_osb−/− mouse. In WT littermate mice, the levels of osteocalcin varied from 106 to 177 ng/ml (on average, 133 ng/ml). For Ocn_osb−/− the average osteocalcin level was 68.4 ng/ml. (K–M) Fertility in mice lacking Esp specifically in osteoblasts (Esp_osb−/−) or Leydig cells (Esp_Leydig−/−) compared to WT non-breeder littermates: (K) Testis weight, (L) sperm count and (M) seminal vesicle weight. (N) Ratio of circulating testosterone levels measured in WT and Esp_osb−/− or in WT and Esp_Leydig−/− non-breeder littermate mice. Error bars represent SEM. Student’s t test (*) P<0.05, (**) P<0.001.

Figure 4. Cellular and molecular events triggered by osteocalcin in Leydig cells

(A–C) Histological analyses of Leydig cells in Ocn−/− and Esp−/− non-breeder mice (A) Absolute number of Leydig cells per testis was quantified by the number of 3β-HSD positive cells. (B) Ratio between Leydig cells (immunopositive for 3β-HSD) versus testis interstitial areas in WT, Ocn−/− and Esp−/− non-breeder mice. (C) 3β-HSD immunohistochemistry staining of WT, Ocn−/− and Esp−/− testes. (D) Quantification of the different testicular cell types in WT and Ocn−/− non-breeder mice. (E) Germ cell apoptosis analysis by TUNEL assay in WT, Ocn−/− and Esp−/− non-breeder testes. (F–H) qPCR analysis of the expression of steroidogenic acute regulatory protein (StAR), cholesterol side-chain cleavage enzyme (Cyp11a), cytochrome P-450 17 alpha (Cyp17), 3-β-hydroxysteroid dehydrogenase (3β-HSD), aromatase enzyme (Cyp19) and 17-β-hydroxysteroid dehydrogenase (HSD-17) in primary Leydig cells treated with 3 ng/ml of osteocalcin (F), in Ocn−/− compared to WT non-breeder littermate testes (G) and in Esp−/− compared to WT non-breeder littermate testes (H). (I) qPCR analysis of Grth/Ddx25 expression in WT, Ocn−/−, Esp−/− and WT non-breeder mice treated with vehicle or osteocalcin (3 ng/g of body weight). (J) Western blot analysis of cleaved caspase 3 and tACE in WT and Ocn−/− non-breeder testes. Error bars represent SEM. Student’s t test (*) P<0.05, (**) P<0.001.

Figure 5. G-protein coupled receptor Gprc6a is a receptor for osteocalcin

(A) Anti-phospho-tyrosine antibody Western blot analysis of TM3 Leydig cells treated with increasing concentrations of osteocalcin, or 10% FBS or insulin as positive controls, for 1 min (upper panel). Proteins phosphorylated on tyrosine residues appear in positive controls (asterisks) but not in osteocalcin treated cells. Equal loading was assessed using an anti-actin antibody (lower panel). (B) Western blot analysis of TM3 Leydig cells showing the absence of ERK1/2 phosphorylation upon stimulation with vehicle or osteocalcin. (C) Calcium fluxes in primary Leydig cells upon stimulation with increasing doses of osteocalcin. 10% FBS and ionophore (A23187) were used as positive controls. (D) cAMP production upon osteocalcin stimulation is increased in TM3 Leydig cells. (E) Schematic representation of the results obtained by the differential expression search for osteocalcin receptors. Among the 103 orphan GPCRs expressed in testis and ovary 22 were predominantly expressed in testis and only four were enriched in primary Leydig cells compared to the expression in whole testis. (F) Relative expression of Gprc6a, Gpr45, Gpr112 and Gpr139 in Leydig cells compared to whole testis. (G) qPCR analysis of Gprc6a expression in human testis and ovary. (H) Immunofluorescence analysis of Gprc6a expression in mice and human testis coronal sections. Anti-IgG was used as negative control. (I) qPCR analysis of Gprc6a expression in 1, 4, 6 and 12 week-old WT testes. (J) Cross sections of testes from WT and Gprc6a-deficient mice stained with biotinylated osteocalcin (b-osteocalcin). Upper left panel: WT testis stained with avidin-biotin complex only; upper middle panel: WT testis stained with 10 nM of b-osteocalcin; upper right panel: testis from Gprc6a-deficient mice stained with 10 nM of b-osteocalcin; lower left panel: WT testis stained with 10 nM of b-osteocalcin in the presence of 1000 nM hCG; lower middle panel: WT testis stained with 10 nM of b-osteocalcin in the presence of 1000 nM lysine; lower right panel: WT testis stained with 10 nM of b-osteocalcin in the presence of 1000 nM of unlabeled osteocalcin. Error bars represent SEM. Student’s t test (*) P<0.05, (**) P<0.001.

Figure 6. Specific deletion of Gprc6a in Leydig cells decreases male fertility

(A–E) Fertility in mice lacking Gprc6a in Leydig cells only (Gprc6a_Leydig−/−) or lacking one allele of Ocn or one allele of Gprc6a in Leydig cells only (Ocn+/− or Gprc6a_Leydig+/−), or in compound heterozygous mice (Ocn+/−; Gprc6a_Leydig+/−) compared to control littermates. (A) Testis size, (B) testis weight, (C) sperm count, (D-E) epididymis and seminal vesicle weights. (F) qPCR analysis of Grth expression in mice of indicated genotypes. (G) Ratio between Leydig cells (stained by immunohistochemistry of 3β-HSD) versus testis interstitial areas. (H) Ratio of circulating testosterone levels measured in WT and Gprc6a_Leydig−/− mice. (I) qPCR analysis of StAR, Cyp11a, 3β-HSD in Gprc6a_Leydig−/− and Ocn+/−; Gprc6a_Leydig+/− compared to WT littermate testes. (J) Germ cell apoptosis analysis by TUNEL assay. All the analyses were performed in non-breeder mice. Error bars represent SEM. Student’s t test (*) P<0.05, (**) P<0.001.

Figure 7. CREB is a transcription factor mediating osteocalcin-evoked gene expression in Leydig cells

(A) Western blot analysis of CREB activation upon stimulation with osteocalcin. (B–F) Fertility in mice lacking Creb in Leydig cells (Creb_Leydig−/−) or of compound heterozygous mice (Creb_Leydig+/−; Gprc6a_Leydig+/−) compared to control littermates. (B) Testis size, (C) testis weight, (D) sperm count, (E–F) epididymis and seminal vesicle weights. (G) Quantification of circulating testosterone levels represented as fold change compared to WT. (H) qPCR analysis of Grth expression in mice of indicated genotypes. (I) qPCR analysis of StAR, Cyp11a, Cyp17, 3β-HSD, Cyp19 and HSD-17 in Creb_Leydig−/− compared to control littermate testes. (J) Chromatin immunoprecipitation (ChIP) using anti-CREB antibody and unspecific isotype IgG antibody in the TM3 cell line. (K) Model representing current knowledge about the regulation of male fertility by the skeleton. All the analyses were performed in non-breeders mice. Error bars represent SEM. Student’s t test (*) P<0.05.