TGF-β1-induced EMT promotes targeted migration of breast cancer cells through the lymphatic system by the activation of CCR7/CCL21-mediated chemotaxis

Abstract

Tumor cells frequently disseminate through the lymphatic system during metastatic spread of breast cancer and many other types of cancer. Yet it is not clear how tumor cells make their way into the lymphatic system and how they choose between lymphatic and blood vessels for migration. Here we report that mammary tumor cells undergoing epithelial-mesenchymal transition (EMT) in response to transforming growth factor-β (TGF-β1) become activated for targeted migration through the lymphatic system, similar to dendritic cells (DCs) during inflammation. EMT cells preferentially migrated toward lymphatic vessels compared with blood vessels, both in vivo and in 3D cultures. A mechanism of this targeted migration was traced to the capacity of TGF-β1 to promote CCR7/CCL21-mediated crosstalk between tumor cells and lymphatic endothelial cells. On one hand, TGF-β1 promoted CCR7 expression in EMT cells through p38 MAP kinase-mediated activation of the JunB transcription factor. Blockade of CCR7, or treatment with a p38 MAP kinase inhibitor, reduced lymphatic dissemination of EMT cells in syngeneic mice. On the other hand, TGF-β1 promoted CCL21 expression in lymphatic endothelial cells. CCL21 acted in a paracrine fashion to mediate chemotactic migration of EMT cells toward lymphatic endothelial cells. The results identify TGF-β1-induced EMT as a mechanism, which activates tumor cells for targeted, DC-like migration through the lymphatic system. Furthermore, it suggests that p38 MAP kinase inhibition may be a useful strategy to inhibit EMT and lymphogenic spread of tumor cells.

Figure 1

TGF-β1-induced EMT promotes lymphatic dissemination of mammary tumor cells. (a) Schematic drawing of the footpad model used to study the effect of TGF-β1-induced EMT on lymphatic dissemination of mouse mammary tumor cells in syngeneic BALB/c mice. The sites of injection (syringe), primary tumor growth (arrow), draining (ipsilateral) and non-draining (contralateral) PLN (arrowheads) are indicated. (b) Representative confocal immunofluorescence images showing GFP-labeled EpXT (GFP-EpXT) cells at the site of injection in the footpad (upper panel), and in draining PLN (lower panel) at 1, 2 and 6 days after injection. Arrows mark GFP-EpXT cells detected in subcapsular sinuses of PLN at day 2 and day 6 after injection. Scale bars, 200 μm (footpad images) and 50 μm (PLN images). (c) Bar graph showing quantification of GFP-EpXT cells that had migrated to PLN at day 1, 2 and 6 after injection in the footpad. (d) Confocal immunofluorescence images showing GFP-EpRas cells in draining PLN at 2 days after injection in the footpad. Before injection, EpRas cells had been either untreated (−TGF-β1, left panel), or pretreated for 14 days with 10 ng/ml of TGF-β1 (+TGF-β1, right panel). Scale bar, 50 μm. (e) Bar graph showing the quantification of GFP-EpRas cells in draining PLN at 2 days after injection into the mouse footpad. GFP-EpRas cells had been either untreated (−TGF-β1) or pretreated for 14 days with 10 ng/ml of TGF-β1. Calnexin was used as a loading control in immunoblotting experiments. *P<0.05.

Figure 2

EMT cells migrate toward lymphatic vessels in experimental tumors and in 3D beads assays. (a) Representative confocal immunofluorescence images of GFP-EpXT footpad tumors at day 6 after injection. The image of the GFP-EpXT cells were moved from green channel and placed in the blue channel to allow for visualization of lymphatic vessels (green), and blood vessels (red), which are double-stained for LYVE-1 (only labels lymphatic vessels) and CD31 (labels both blood and lymphatic vessels). (b) Black and white image of GFP-EpXT cells. Invasive areas (I) containing elongated GFP-EpXT cells lining up in unidirectional patterns are indicated by arrows in both images. (c) Representative high magnification confocal images showing the presence of lymphatic vessels in noninvasive (left panel) versus invasive areas (right panel) GFP-EpXT tumors. (d and e) Bar graphs showing results from quantification of area density of lymphatic vessels (d) and blood vessels (e) in noninvasive versus invasive areas to GFP-EpXT footpad tumors. (f) Immunofluorescence images showing polymeric beads coated with GFP-EpXT cells (green) and co-cultured in a 3D fibrin matrix with beads coated with DsRed-labeled MS1 vascular endothelial cells (DsRed-MS1; upper panels), or immortalized lymphatic endothelial cells (DsRed-iLEC; lower panels), for 24 h. (g and h) Bar graphs showing quantitative assessment of the capacity of EpXT cells to migrate toward beads coated with iLEC versus MS1 cells (g) and SV-LEC versus MS1 cells (h). *P<0.05, ***P<0.001.

Figure 3

TGF-β1-induced EMT promotes tumor cell migration toward lymphatic endothelial cells via CCR7/CCL21-mediated chemotaxis. (a and b) Results from expression analysis of CCR7 mRNA and protein levels in TGF-β1 treated (10 ng/ml, 48 h) versus nontreated EpRas cells (a), and NMuMG cells (b) as determined by qPCR (bar graphs) and immunoblotting (lower panels). (c) Bar graph showing quantitative assessment of the capacity of NMuMG cells to invade through matrigel and migrate toward a gradient of fetal calf serum (FCS) or CCL21 in invasion assays. (d) Bar graph showing dose-dependent inhibition of migration of NMuMG cells toward CCL21 in the presence of a neutralizing antibody to CCR7. An isotype-matched antibody (IgG2A) was used as a control. (e) Representative confocal immunofluorescence images showing the effect of a neutralizing antibody to CCR7 (20 ng/ml) on the capacity of GFP-EpXT cells to migrate toward beads coated with iLEC. (f) Quantitative results showing the effect of a neutralizing CCR7 antibody (20 ng/ml) on the capacity of EpXT cells to migrate toward lymphatic endothelial cells (iLEC) in the fibrin beads assay. (g) Bar graph showing quantitative assessment of the capacity of GFP-EpXT cells transfected with siRNA against CCR7 (siCCR7), or a scrambled siRNA (siScramble), to disseminate to PLN at 2 days after injection of cells into the footpad of BALB/c mice. Scale bar, 100 μm. Calnexin was used as a loading control in immunoblotting experiments. *P<0.05.

Figure 4

Role of p38 MAPK signaling and the AP-1 factor JunB in the regulation of CCR7 during TGF-β1-induced EMT. (a) Bar graph showing the effects of inhibitors of Smad3 (SIS3, 15 μM) and p38 MAPK (SB203580, 20 μM) on the induction of CCR7 after 48 h of TGF-β1-induced EMT (2 ng/ml of TGF-β1) in NMuMG cells. (b) Bar graph showing the effect of SB203580 (20 μM, 48 h) on the expression of CCR7 mRNA relative to control (cells treated with vehicle). (c) Immunoblot showing the effect of SB203580 (20 μM, 48 h) and SIS3 (15 μM, 48 h) on the expression of CCR7 and E-cadherin in EpXT cells. (d) Schematic drawing of the CCR7 promoter showing the location of AP-1 sites and binding sites for primers used for chromatin immunoprecipitation assays. (e) Bar graph showing changes in mRNA expression of the AP-1 factors c-Fos, c-Jun, Fra1 and JunB in NMuMG cells during TGF-β1-induced EMT. (f) Immunoblot analysis of the effect of TGF-β1 on the expression of c-jun and JunB in NMuMG cells. (g) Results from reporter assays showing the effect of overexpression of C-jun and JunB on the activity of the CCR7 promoter. (h) Immunoblotting results showing the effect of TGF-β1 (2 ng/ml) on the expression of C-jun and JunB in NMuMG cells in the absence or presence of SB203580 (20 μM) after 48 h. (i) RT–PCR results from chromatin immunoprecipitation assays showing binding of JunB to the CCR7 promoter in TGF-β1-treated NMuMG cells. No binding of JunB was detected in a region lacking consensus AP-1-binding sites (control). (j) Bar graph showing the effect of overexpression of siRNA against JunB (siJunB) or control (siControl) on the induction of CCR7 mRNA expression in NMuMG cells during TGF-β1-induced EMT. (k and l) Bar graphs showing the effect of pretreatment with SB203580 (20 μM, 48 h) on the migration of GFP-EpXT cells toward CCL21 in invasion assays (k), and the dissemination of GFP-EpXT cells to draining PLN at 2 days after injection into the footpad of BALB/c mice (l). Calnexin was used as a loading control in immunoblotting experiments. *P<0.05, **P<0.01, ***P<0.001.

Figure 5

CCL21 expression in lymphatic endothelial cells is regulated by TGF-β1 and important for chemoattraction of tumor EMT cells. (a) Representative confocal immunofluorescence images showing staining of CCL21 in LYVE-1-positive lymphatic vessels in GFP-EpH4 and GFP-EpXT footpad tumors at day 6. (b) Bar graph showing quantitative assessment of the expression of CCL21 in endothelial cells of lymphatic vessels in GFP-EpH4 versus GFP-EpXT footpad tumors at day 6 after footpad injections. (c and d) Bar graphs showing the effect of TGF-β1 treatment (10 ng/ml, 24 h) on the expression of CCL21 in SV-LEC cells (c) and in MS1 cells (d). (e) Bar graph showing the effect of overexpression of CCL21 or control siRNA in SV-LEC cells on their capacity to support chemotactic migration of EpXT cells in beads assays. (f) Bar graph showing the effect of overexpression of CCL21 or control cDNA in MS1 cells on their capacity to support chemotactic migration of EpXT cells in beads assays. *P<0.05, **P<0.01.

Figure 6

The expression of CCR7 and CCL21 is linked to EMT in human breast cancer. (a) Representative confocal immunofluorescence images showing the presence of E-cad^low/CCR7^pos/CD45^neg tumor cells (outlined area) within an invasive area (I) of a sample of human breast cancer. Tumor cells in noninvasive areas (NI) were more strongly positive for E-cadherin and were negative for CCR7. (b) Profiling of 51 human breast cancers based on gene expression data from the Gene Expression Atlas at the European Bioinformatics Institute (EMBL-EBI). Three mesenchymal genes (TWIST, SNAIL and VIM) and three epithelial genes (OCLDN, CLDN3 and CDH1), which are induced and repressed, respectively, during EMT were selected to identify tumors with an EMT genotype. The expression of CCR7 and CCL21 was higher in the EMT samples compared with non-EMT samples (P<0.05 for both).

Figure 7

Schematic diagram summarizing the results that indicate that tumor cells undergoing TGF-β1-induced EMT become activated for targeted migration through the lymphatic system, similar to DCs during inflammation. Induction of CCR7 provides both EMT cells and DCs with a capacity to sense and migrate toward a gradient of CCL21, which is produced by lymphatic endothelial cells. TGF-β also induces the expression of CCL21 in lymphatic endothelial cells, which may further promote CCR7/CCL21-mediated migration of EMT cells toward lymphatic vessels.