EMT inducers catalyze malignant transformation of mammary epithelial cells and drive tumorigenesis towards claudin-low tumors in transgenic mice

Abstract

The epithelial-mesenchymal transition (EMT) is an embryonic transdifferentiation process consisting of conversion of polarized epithelial cells to motile mesenchymal ones. EMT-inducing transcription factors are aberrantly expressed in multiple tumor types and are known to favor the metastatic dissemination process. Supporting oncogenic activity within primary lesions, the TWIST and ZEB proteins can prevent cells from undergoing oncogene-induced senescence and apoptosis by abolishing both p53- and RB-dependent pathways. Here we show that they also downregulate PP2A phosphatase activity and efficiently cooperate with an oncogenic version of H-RAS in malignant transformation of human mammary epithelial cells. Thus, by down-regulating crucial tumor suppressor functions, EMT inducers make cells particularly prone to malignant conversion. Importantly, by analyzing transformed cells generated in vitro and by characterizing novel transgenic mouse models, we further demonstrate that cooperation between an EMT inducer and an active form of RAS is sufficient to trigger transformation of mammary epithelial cells into malignant cells exhibiting all the characteristic features of claudin-low tumors, including low expression of tight and adherens junction genes, EMT traits, and stem cell-like characteristics. Claudin-low tumors are believed to be the most primitive breast malignancies, having arisen through transformation of an early epithelial precursor with inherent stemness properties and metaplastic features. Challenging this prevailing view, we propose that these aggressive tumors arise from cells committed to luminal differentiation, through a process driven by EMT inducers and combining malignant transformation and transdifferentiation.

Figure 1. Twist1 promotes tumor progression in vivo.

Transgene expression was driven by the MMTV-Cre. While MMTV-Cre; Twist1 mice (TWIST1; n = 71) do not develop skin lesions, MMTV-Cre;K-rasG12D animals (RAS; n = 89) spontaneously develop anal and oral papillomas. In MMTV-Cre;K-rasG12D;Twist1 mice (RAS+TWIST1; n = 19) papillomas evolve into squamous carcinomas. (A) HPS staining of skins either from K-rasG12D or K-rasG12D;Twist1 transgenic mice. Transgene expression is induced by the MMTV-Cre. (B) Kaplan-Meier survival curves of transgenic mice. Survival corresponds to the end point of the experiment, the tumor burden requiring euthanasia of the animal. Open circles indicate mice censored from the dataset.

Figure 2. Twist1 promotes tumor initiation in vivo.

Transgene expression was driven by WAP-Cre. While WAP-Cre;Twist1 (TWIST1; n = 25) and WAP-Cre;K-RasG12D (RAS; n = 19) mice remained healthy, WAP-Cre;K-RasG12D;Twist1 females (RAS+TWIST1; n = 21) developed metaplastic mammary carcinomas. (A) Kaplan-Meier survival curves of transgenic mice. Survival corresponds to the end point of the experiment, the tumor burden requiring euthanasia of the animal. Open circles indicate mice censored from the dataset. (B) HPS staining of mammary glands from either wild-type (wt), Twist1 or K-rasG12D transgenic mice. (C) Expression analysis of ectopic TWIST1 in mammary glands of nulliparous WAP-Cre;Twist1 mice as assessed by IHC shows that the WAP promoter is active in a few epithelial cells. (D) Characterization of the WAP-Cre;K-RasG12D;Twist1 mice-derived mammary carcinomas (RAS+TWIST1). RAS and TWIST coexpression leads to the development of metaplastic carcinomas characterized by a predominant E-cadherin⁻, vimentin⁺ fusiform contingent (tumors A, C, E, F) or the presence of two epithelial-like (E-cadherin⁺) and fusiform (vimentin⁺) cell contingents (tumors B and D). For tumors B and D, both epithelial (upper panel) and fusiform (lower panel) cell contingents express the tagged-TWIST1 transgenic protein, demonstrating that fusiform cells originate from the epithelial ones. Normal epithelial cells are arrowed.

Figure 3. EMT induction by embryonic transcription factors facilitates HMEC transformation by an activated form of RAS.

Sequentially, HMECs were immortalized with hTERT (control) and infected with retroviral expression constructs for TWIST1, ZEB1, or ZEB2 and H-RAS^G12V (as depicted on top). (A) Representative photomicrographs of cells obtained by phase contrast microscopy. (B) E-cadherin expression analysis by immunofluorescence. (C) Cell morphology in 3D culture. (D) Transformation potential analysis by means of a soft agar colony formation assay. Numbers of colonies are indicated ± SD of three replicates. (E) Mammosphere formation assay under low adherence conditions. Numbers of mammospheres per 20 000 cells are indicated ± SD of three replicates. (F–G) Expression analysis of TWIST1, ZEB1, ZEB2, H-RAS, and of epithelial and mesenchymal markers by western blotting. Quantification of E-cadherin, vimentin and fibronectin signals, normalized with respect to β-actin expression and HMEC-hTERT-RAS derivatives is shown.

Figure 4. Mesenchymal HMEC-derivatives display a claudin-low gene expression signature.

(A) Statistical values of the Pearson's correlation to the centroids of intrinsic gene clusters determined according to the cell line gene expression data set of Neve and collaborators . (B) The expression of significative genes from the claudin-low signature , is shown. Relative transcript abundance with highest expression is labeled in red and with lowest expression is labeled in green, respectively. MCF7 and MDA-MB157 were used as internal luminal and claudin-low controls, respectively.

Figure 5. Combined expression of H-RAS^G12V and EMT–inducing transcription factors provides HMEC cells with a stem cell–like antigenic phenotype.

Analysis by flow cytometry of the expression of CD44, CD24 (A) and EpCAM (B). Solid blue lines represent staining with FITC-anti-EpCAM antibody and dotted red lines represent staining with FITC-conjugated isotype control. B.D.L.: Below Detection Limit. The claudin-low mesenchymal breast cancer cell line MDA-MB231 was used as a negative EpCAM staining control.

Figure 6. Expression of EMT–inducing transcription factors triggers a dedifferentiation of HMEC cells.

Mammary stem cells (MaSC), luminal progenitor and luminal mature signatures of human cell line are defined according to Lim and collaborators , respectively. High scores are indicative of a good correlation between the analyzed gene expression profiles and the established signatures. Cells lines with an epithelial morphology are labeled in green while cell lines harboring a mesenchymal morphology are labeled in red.

Figure 7. Characterization of epithelial and mesenchymal hTERT-shp53/RAS HMEC-derivative subpopulations.

(A, B) Migratory and invasive properties analyses as assessed by Boyden chamber migration and Matrigel invasion assays, respectively. (C) Cellular morphology in 3D culture. (D) Transformation potential analysis assessed by a soft agar colony formation assay. Numbers of colonies are indicated ± SD of triplicate counting. (E) Tumorigenic potential analysis assessed by homotopically xenografts in nude mice. Numbers of mice developing tumors are indicated. (F) Tumor histology: Hematoxylin-Phloxin Saffranin staining (HPS) and cytokeratin, E-cadherin and vimentin expression analysis assessed by immunohistochemistry.

Figure 8. Assessment of PP2A activity in hTERT-HMEC derivatives.

PP2A phosphatase activity was assessed and normalized with respect to the parental hTERT-HMEC cells. Activities are expressed in arbitrary units ± SD of triplicate experiments. hTERT-HMECs transduced with SV40 T/t antigens and H-RAS^G12V (HMLER, [29]) were used as an internal positive control.