A dynamic shift of VEGF isoforms with a transient and selective progesterone-induced expression of VEGF189 regulates angiogenesis and vascular permeability in human uterus

Abstract

A key mechanism underlying physiological angiogenesis of the human endometrium is its ability to regenerate the vascular capillary network and to perform vascular remodeling (i.e., development of spiral arteries). Vascular endothelial growth factor (VEGF) is associated with angiogenesis and capillary permeability in this tissue. VEGF is expressed as several spliced variants, its main human isoforms contain 121 and 165 aa; 17beta-estradiol (E(2)) increases endometrial VEGF, possibly in all isoforms. Here we show that progesterone (P) selectively increases the expression of the VEGF(189) (V(189)) isoform in the human uterus. V(189) is identified in the conditioned medium of stromal cells treated with E(2) + P; its presence in this in vitro model of decidual stromal cells is detected after 6-8 days, using ELISA, and after 8-10 days, using Western blot analysis with different antibodies, including one specific for V(189). The secretion pattern of V(189) parallels that of the decidual protein IGFBP-1. V(189) is secreted as a native isoform, as compared with the migration of recombinant V(189) by SDS/PAGE. In situ hybridization and immunocytochemistry(,) performed on the same biopsies, suggest that decidual cells express V(189) during the mid-late secretory phase of the menstrual cycle and early gestation. Finally, using an in vivo permeability assay, we show that native V(189) increases capillary permeability. These observations demonstrate that P regulates V(189) expression in decidual cells, which could have important implications for understanding uterine vascular remodeling and implantation, and may be relevant in a range of disease states such as edema and irregular bleeding.

Figure 1

Expression level of VEGF transcripts in stromal cells incubated with both estradiol and progesterone. Total RNA was extracted every 2 days from cells subjected to EGF + E₂ + P for 14 days. This figure shows an ethidium bromide gel of RT-PCR analysis from stromal cells incubated with hormones for 4, 8, and 14 days.

Figure 2

VEGF₁₈₉ expression in the conditioned media from decidual stromal cells. (A) Western blot analysis of proteins (100 μg) from conditioned media after 2, 4, and 6 days of cell treatment with E₂, or after 8, 10, 12, and 14 days with E₂ + P (15 μg proteins). Antibodies to human VEGF (A-20) (Upper) or to IGFBP-1 (Lower) were used for immunoblotting of proteins. Treatment with E₂ + P markedly increases the synthesis of a 29–30 kDa VEGF isoform after 10–12 days (maximum on day 12 in this experiment) and of IGFBP-1. Depending on the human sample, the expression of V₁₈₉ can be observed over 4 days, starting on day 8–10. (B) Western blot analysis of proteins (50 μg) immunoprecipitated with anti-V₁₈₉ antibody (P2) and blotted with the anti-VEGF A-20 antibody. (C) SDS/PAGE analysis of recombinant V₁₈₉, native (5 ng), or cleaved (10 ng) (18), and proteins (35 μg) of conditioned medium from E₂ + P-treated stromal cells (12 days treatment) using A-20 antibody. The 29–30-kDa protein seen at day 12 is comparable to that of recombinant native V₁₈₉.

Figure 3

In situ expression of VEGF by decidual cells. Sections from early (A, day 20) and mid-late (B–D, day 24; E, day 26) secretory endometrium were immunostained with rabbit anti-VEGF (A-20) (A and B), anti-smooth muscle α-actin (C), or anti-VEGF₁₈₉ (E) antibodies. Stromal cells are weakly stained for VEGF in the early secretory phase (A); note in B the strong immunolabeling for total VEGF in stromal cells having a decidual-like appearance, located close to vessels (v), and positive for smooth α-actin (C, arrow). Note in E the strong pericellular labeling for V₁₈₉ isoform in decidual cells. Hematoxylin/eosin section in D. Light counterstaining with hematoxylin/eosin in A and B. a, arteriole. (Magnification, ×400.)

Figure 4

In situ hybridization for VEGF₁₈₉ mRNA in human endometrium. Sections were hybridized with a radiolabeled antisense V₁₈₉ probe (A–D) or a probe for all VEGF transcripts (E and F). (A and B) Late secretory phase (day 28), strong V₁₈₉ expression in decidual cells. (C and D) Early pregnancy, stromal cells near a blood vessel (v); dark-field in A and C and bright-field in B and D. (Inset) No staining is detected with the corresponding sense probe on sections adjacent to those shown in panels C and D. (E and F) Proliferative (day 11) and secretory (day 25) phase, expression of all VEGF mRNA by using exon 4 antisense probe is moderate in stromal cells. Hematoxylin/eosin counterstaining. (Magnification, ×400.)

Figure 5

VEGF₁₈₉ increases capillary permeability. (A) V₁₈₉ increases CP in a dose-dependent manner. No effect is detected with saline. Histamine (100 μM) as a positive control increases CP. (B and C) Preincubation of V₁₈₉ (B) or V₁₆₅ (C) with neutralizing anti-VEGF antibody (clone 26503) (1 μg IgG/10 ng VEGF) completely inhibits V₁₈₉ (or V₁₆₅)-mediated CP; preincubation of VEGF with an unrelated antibody (used in the same conditions) does not inhibit VEGF-mediated CP.