Breast carcinoma cells re-express E-cadherin during mesenchymal to epithelial reverting transition

Abstract

Background: Epithelial to mesenchymal transition (EMT), implicated as a mechanism for tumor dissemination, is marked by loss of E-cadherin, disruption of cell adhesion, and induction of cell motility and invasion. In most intraductal breast carcinomas E-cadherin is regulated epigenetically via methylation of the promoter. E-cadherin expression is therefore dynamic and open to modulation by the microenvironment. In addition, it has been observed that metastatic foci commonly appear more differentiated than the primary tumor, suggesting that cancer cells may further undergo a mesenchymal to epithelial reverting transition (MErT) in the secondary organ environment following the EMT that allows for escape.

Results: We first examined E-cadherin expression in primary breast tumors and their corresponding metastases to liver, lung and brain and discovered that 62% (10/16) of cases showed increased E-cadherin expression in the metastases compared to the primaries. These observations led to the question of whether the positive metastatic foci arose from expansion of E-cadherin-positive cells or from MErT of originally E-cadherin-negative disseminated cells. Thus, we aimed to determine whether it was possible for the mesenchymal-like MDA-MB-231 breast cancer cells to undergo an MErT through the re-expression of E-cadherin, either through exogenous introduction or induction by the microenvironment. Ectopic expression of full-length E-cadherin in MDA-MB-231 cells resulted in a morphological and functional reversion of the epithelial phenotype, with even just the cytosolic domain of E-cadherin yielding a partial phenotype. Introduction of MDA-MB-231 cells or primary explants into a secondary organ environment simulated by a hepatocyte coculture system induced E-cadherin re-expression through passive loss of methylation of the promoter. Furthermore, detection of E-cadherin-positive metastatic foci following the spontaneous metastasis of MDA-MB-231 cells injected into the mammary fat pad of mice suggests that this re-expression is functional.

Conclusions: Our clinical observations and experimental data indicate that the secondary organ microenvironment can induce the re-expression of E-cadherin and consequently MErT. This phenotypic change is reflected in altered cell behavior and thus may be a critical step in cell survival at metastatic sites.

Figure 1

E-cadherin expression is increased in metastases compared to primary tumors. A) Percentage of E-cadherin-positve cells is increased in metastases compared to the primary tumors. Organ sites of metastases are organized by color: liver (red), lung (blue), and brain (yellow) B) Example of a case showing strong expression of E-cadherin in the metastasis (right) compared to negative expression in primary (left). C) Heterogeneous expression of E-cadherin in the center (dashed inset) versus edge (solid inset) of a liver metastasis. "C" denotes tumor and "H" denotes hepatocytes. D) Quantification of E-cadherin staining in the center and edge of the liver metastasis.

Figure 2

E-cadherin expression alters cell morphology. A) Cell morphology as examined by phase contrast microscopy (left column) and E-cadherin expression (red) as detected by immunofluorescence (right column) B) Immunblot analysis illustrates ectopic expression of E-cadherin in 231-Ecad cells as well as expression of various epithelial and mesenchymal markers in the E-cadherin mutants. C) Immunofluorescence of vimentin, cytokeratin-18 and actin cytoskeleton (rhodamine phalloidin). Shown are representative of at least three different assessments using one of two independent clones of each cell variant. D) Quantification of fluorescence using ImageJ, n = 20 cells, p < 0.05.

Figure 3

E-cadherin expression suppresses migration (A) and invasion (B). Cell migration was analyzed using a scratch assay. Scratch closure was measured over a period of 24 hours and the fraction closure was quanitified by Metamorph software (n = 3). Invasion was measured in using a Matrigel invasion assay in which cells were allowed to migrate through a Matrigel-coated transwell insert for a period of 24 hours. N = 3 in triplicate; mean ± s.e.m. Results shown are representative of one of two independent clones of each mutant.

Figure 4

Hepatocytes drive the re-expression of E-cadherin in MDA-MB-231 breast cancer cells. A) Immunoblot of proteins lysates from MDA-MB-231/hepatocyte co-cultures using a human-specific antibody. B) Flow cytometry of the MDA-MB-231 population using a human-specific antibody shows a unimodal population on day 0 and a bimodal population on day 6. C) MDA-MB-231 cells do not express E-cadherin without hepatocytes. D) RT-PCR using human-specific primers of MDA-MB-231 cells after 6 days of co-culture with hepatocytes. Means (n = 4) ± s.d. Note that species-specific primers do not amplify E-cadherin or GAPDH from hepatocytes.

Figure 5

Breast cancer cells cultured with hepatocytes revert to an epithelial morphology. Phase contrast images of 231, 231-H2kd, 231-Ecad, and 231-shEcad breast cancer cells cultured with rat hepatocytes for 6 days.

Figure 6

Breast cancer cells culture with hepatocytes re-express E-cadherin but maintain vimentin A) Immunostaining of RFP-labeled breast cancer cells in hepatocyte coculture; E-cadherin (green), RFP (red), DAPI (blue) B) Immunostaining for vimentin (green), RFP (red), DAPI (blue). Shown are representative of at least three different assessments using at least two independent clones of each cell variant.

Figure 7

A subset of primary breast carcinoma explants re-express E-cadherin when cocultured with primary hepatocytes. A) Flow cytometry analysis of primary explants using a human-specific E-cadherin antibody. A fluorescence unit of 1 indicates that the fluorescence intensity was equal to the same gate performed without addition of antibody. B) Confocal microscopy of two positive explants. Explants (C), hepatocytes (H). Human-specific E-cadherin, blue; actin, red; nuclei, green.

Figure 8

Breast cancer cells lose methylation of E-cadherin promoter methylation following hepatocyte coculture. A) Nested PCR method to detect methylation status of the E-cadherin promoter in a six day time course of hepatocye coculture. Above, bisulfite-treated DNA is amplified with primers that exclude CpG islands to amplify a 270 bp region independent of methylation status. Below, nested primers anneal to the 270 bp target to amplify a methylated (112 bp) or unmethylated (120 bp) fragment in the six day time course. MCF7 is used an unmethylated control. B) Bisulfite sequencing of CpG islands in the E-cadherin promoter. Figure adapted from Corn et al . CpG islands are indicated as vertical lines on map; each CpG island is represented a circle. MCF7, MDA-MB-231, and MDA-MB-435 were sequenced on days 1,3, and 5 coculture. Open circle, unmethylated CpG; closed circle, methylated CpG; filled circle, mixed quality values.

Figure 9

Re-expression of E-cadherin follows a proliferation-dependent demethylation of the E-cadherin promoter. A) MS-PCR of MDA-MB-231 cultured alone in hepatocyte growth media B) MS-PCR using human-specific primers that amplify the imprinted H19 gene. C) MS-PCR of E-cadherin promoter following addition of MMC D) Addition of MMC prevents E-cadherin re-expression at the protein level. E) The maintenance demethylase DNMT1 does not change in localization or intensity in MDA-MB-231 cancer cells when cocultured with hepatocytes. DNMT1, red; DAPI, blue.

Figure 10

E-cadherin positive metastatic foci originate from E-cadherin negative primary tumors. A) Left, human MDA-MB-231 breast cancer cell xenograft in a mouse inguinal fat pad (H&E); middle, human-specific E-cadherin antibody indicates the absence of E-cadherin expression in the center of the primary tumor; right, absence of human-specific E-cadherin labeling at the periphery of the tumor. B) Micrometastases in the lung originating from the primary xenograft in A. Immunoperoxidase labeling of diseased portions of the mouse lung indicate the presence of human E-cadherin-positive MDA-MB-231 cancer cells; bottom adjacent.