A novel role of the Sp/KLF transcription factor KLF11 in arresting progression of endometriosis

Abstract

Endometriosis affects approximately 10% of young, reproductive-aged women. Disease associated pelvic pain; infertility and sexual dysfunction have a significant adverse clinical, social and financial impact. As precise disease etiology has remained elusive, current therapeutic strategies are empiric, unfocused and often unsatisfactory. Lack of a suitable genetic model has impaired further translational research in the field. In this study, we evaluated the role of the Sp/KLF transcription factor KLF11/Klf11 in the pathogenesis of endometriosis. KLF11, a human disease-associated gene is etiologically implicated in diabetes, uterine fibroids and cancer. We found that KLF11 expression was diminished in human endometriosis implants and further investigated its pathogenic role in Klf11-/- knockout mice with surgically induced endometriotic lesions. Lesions in Klf11-/- animals were large and associated with prolific fibrotic adhesions resembling advanced human disease in contrast to wildtype controls. To determine phenotype-specificity, endometriosis was also generated in Klf9-/- animals. Unlike in Klf11-/- mice, lesions in Klf9-/- animals were neither large, nor associated with a significant fibrotic response. KLF11 also bound to specific elements located in the promoter regions of key fibrosis-related genes from the Collagen, MMP and TGF-β families in endometrial stromal cells. KLF11 binding resulted in transcriptional repression of these genes. In summary, we identify a novel pathogenic role for KLF11 in preventing de novo disease-associated fibrosis in endometriosis. Our model validates in vivo the phenotypic consequences of dysregulated Klf11 signaling. Additionally, it provides a robust means not only for further detailed mechanistic investigation but also the ability to test any emergent translational ramifications thereof, so as to expand the scope and capability for treatment of endometriosis.

Figure 1. KLF11 expression in human urogenital tissues, uterine eutopic endometrium and endometriosis.

(A) Pooled Human Organ-specific RNA (1 µg/reaction) was analyzed for KLF11 mRNA expression by PCR. mRNA levels of the housekeeping gene GAPDH were simultaneously assessed as loading control. Relative organ-specific KLF11 mRNA expression levels were determined by densitometric comparison to corresponding GAPDH levels. KLF11 mRNA expression levels were increased in urogenital tissues such as the kidney, ovary, placenta, testes and uterus (Figure 1A, arrows) compared to other non-urogenital tissues. (B) Expression of KLF11 mRNA and protein were also assessed in two cell lines Ishikawa, a well-differentiated endometrial adenocarcinoma cell line and Human Endometrial Stromal Cells (T-HESC), which are frequently used as model endometrial epithelial and stromal cell lines respectively. KLF11/KLF11 were expressed in both cell-lines; GAPDH/α-TUBULIN were used as a reference controls. To qualitatively demonstrate KLF11 expression in each of these endometrial cell lines, lysate for RNA or protein extraction was obtained from one 10-cm cell culture dish of confluent cells. Due to much lower abundance of stromal compared to epithelial cells there appears to be differential KLF11/KLF11 expression between the cell-types. However, this difference was also reflected in expression of the loading controls GAPDH/α-TUBULIN between the two cell lines. (C, D) KLF11 expression was also evaluated by immunohistochemistry in eutopic endometrium as well as in ectopic endometrial implants (magnification: 200×: panel; 400×: inset). KLF11 was expressed in the nuclei and cytoplasm of epithelial as well as stromal cells in both eutopic endometrium as well as in endometriotic implants. KLF11 expression was diminished in endometriotic implants compared to eutopic endometrium. Representative samples shown. (E) KLF11 expression levels were compared and scored in paired eutopic endometrium and ectopic endometriotic implants obtained from the same patient (N = 28 paired samples). The expression was significantly reduced in the implants (epithelium: 103±2.6; stroma: 40.4±3.9) compared to that in eutopic uterine endometrium (epithelium: 278±2.5; stroma: 114±8.7). * and. = p<0.05 and represent comparisons between epithelial and stromal cells in eutopic and ectopic endometrium respectively.

Figure 2. Role of Klf11 on lesion size in endometriosis.

(A) Endometriosis was surgically induced in 8 week old Klf11-/- and wildtype female mice (N = 7/group). All animals were weighed prior to initial surgery and at necropsy 3 weeks later. There was no difference in weight between the groups either prior to implantation surgery or before subsequent necropsy. Comparative weight profile prior to necropsy shown (p>0.05; NS). (B, C) At induction, 0.5cm endometrial implants were implanted on to the parietal peritoneum of Klf11-/- and wildtype mice. Lesion size was evaluated at necropsy three weeks after initial surgery. The peritoneal lesions (white arrows; box) in Klf11-/- mice (C) were larger and more cystic compared to those observed in wildtype controls (B). (D) The lesions in Klf11-/- animals (6.8±0.044mm) were significantly larger than those observed in wildtype controls (4.5 ± 0.029mm). [*  = p<0.05; 14 lesions per genotype].

Figure 3. Role of Klf11 in endometriosis-associated fibrosis.

Endometriotic lesions in Klf11-/- mice were associated with prolific de novo scar tissue formation in contrast to wildtype controls. (A) Adhesions in Klf11-/- animals were thick, opaque, dense and unyielding to mechanical disruption by pressure. The adhesions had a broad base (black arrows) and involved adjacent viscera such as the small and large intestine, stomach and liver, thereby resulting in obliteration of physiological tissue planes. (B) Progressive fibrosis further involved the intestinal mesentery in these animals, resulting in straightening of the bowel with apparent shortening of length (white arrows). (C) In contrast, in wildtype animals, the lesions remained discrete (white arrows and box in C and D) with minimal adhesions (black arrow). Any adhesions that formed were slender, transparent, non-obliterating and very easily disrupted by pressure. (D) Lack of progressive and prolific fibrosis in wildtype animals preserved normal intra-abdominal anatomy with no peritoneal obliteration or mesenteric fibrosis.

Figure 4. Application of a Novel Fibrosis Adhesion Scoring System to evaluate murine endometriotic lesions.

A murine peritoneal sclerosis scoring system was modified and adapted to the revised ASRM endometriosis staging system. Accordingly, anatomic landmarks in the region of the lesions were incorporated and weighted scores were assigned in accordance with the established human disease scoring system.

Figure 5. Comparison of the role of Klf9 and Klf11 in an animal endometriosis model.

(A) Endometriotic Lesions (circled) in Klf9-/- animals were either unchanged or had regressed in size from the time of initial peritoneal implantation, when evaluated at necropsy 3 weeks later. (B) Endometriotic lesions in these animals also did not elicit a progressive fibrotic response as seen in Klf11-/- animals. Any adhesions in Klf9-/- animals (black arrow) were flimsy, transparent and peri-lesional in extent. (C) Tissue planes were unaltered with preservation of intra-abdominal anatomy. Consequently, intestinal length was not foreshortened due to lack of mesenteric fibrosis (unraveled intestinal loops denoted by white arrows). (D): A composite adhesion score for each mouse was determined and compared between Klf11-/-, Klf9-/- and wildtype genotypes, based on the Murine Adhesion Scoring System. The adhesion score for Klf11-/- mice (81.7±4.8) was significantly different from that calculated in either Klf9-/- (12.3±1.8) or wildtype animals (9.17±0.8); (* = p<0.05, 14 lesions/genotype). The scores objectively reflected observed anatomical findings in these animals.

Figure 6. Evaluation of the Role of KLF11 in the regulation of fibrogenic signaling.

(A) KLF11 binding to the promoters of known fibrosis associated genes was evaluated by Chromatin immunoprecipitation in vivo in endometrial stromal cells. Representative targets from diverse families of fibrogenic genes are shown (Collagens, MMP, TGF-β signaling pathway). KLF11 but not a control species and isotype-specific IgG bound candidate promoter GC-elements in these putative target genes. (B) Functional competence of the KLF11-binding promoter element was tested in promoter-luciferase reporter assays. T-HESC endometrial cells were transfected with 2.5 µg of either pcDNA3/His-KLF11 or corresponding pcDNA3/His-EV and 3 µg of pGL3/promoter-reporter construct for 48 hours. Normalized luciferase expression levels obtained with KLF11 compared to EV are shown. Compared to corresponding empty vector, KLF11 significantly repressed COL1A1, 1A2, MMP3, 10 and TGFβR1- promoter luciferase levels, whereas it activated expression from the COL3A1-reporter (* = p<0.05).

Figure 7. Role of Klf11 in the regulation of Col1a1 expression.

(A) Collagen 1A1 mRNA expression levels were determined from one of two endometriotic implants in each animal (Klf11-/- and wildtype). Col1a1 mRNA expression levels were increased 7.55±0.48 fold (p<0.05) in implants from Klf11-/- animals compared to wildtype. (B, C) Histochemical evaluation using Masson′s trichrome staining showed that collagen deposition (blue stain, white arrow) was increased in the tissue surrounding peritoneal endometriosis implants in Klf11-/- animals (C) in contrast to wildtype controls (B) Magnification: 100×.