Reciprocal activating crosstalk between c-Met and caveolin 1 promotes invasive phenotype in hepatocellular carcinoma

Abstract

c-Met, the receptor for Hepatocyte Growth Factor (HGF), overexpressed and deregulated in Hepatocellular Carcinoma (HCC). Caveolin 1 (CAV1), a plasma membrane protein that modulates signal transduction molecules, is also overexpressed in HCC. The aim of this study was to investigate biological and clinical significance of co-expression and activation of c-Met and CAV1 in HCC. We showed that c-Met and CAV1 were co-localized in HCC cells and HGF treatment increased this association. HGF-triggered c-Met activation caused a concurrent rise in both phosphorylation and expression of CAV1. Ectopic expression of CAV1 accelerated c-Met signaling, resulted in enhanced migration, invasion, and branching-morphogenesis. Silencing of CAV1 downregulated c-Met signaling, and decreased migratory/invasive capability of cells and attenuated branching morphogenesis. In addition, activation and co-localization of c-Met and CAV1 were elevated during hepatocarcinogenesis. In conclusion reciprocal activating crosstalk between c-Met and CAV1 promoted oncogenic signaling of c-Met contributed to the initiation and progression of HCC.

Figure 1

A. HGF induced association of CAV1 with c-Met. Serum starved SNU-449 cells were exposed to HGF for 15, 30 and 60 min. Whole cell lysates were immunoprecipitated with anti-c-Met antibody, resolved by SDS-PAGE and immunoblotted with antibody to CAV1 and c-Met. Anti-c-Met antibody was probed to the membrane as a loading control. There was no detectable c-Met and CAV1 band in immunoprecipitates prepared with IgG as an IP-control. B. The relative CAV1 intensities for the different treatments relative to the corresponding levels of c-Met were calculated. Different treatments relative to the present in the untreated control sample are compared in the bar graphs. Data were expressed as mean ± standard error (SE) of three independently experiments. C. Overnight starved SNU-449 cells were treated without (upper row)/with HGF (lower row) for 60 min. Representative image showing protein expression by double CM of CAV1 (red, Alexa 455) 1 (a, b), c-Met (green, Alexa 488) (c, d). Overlapping of red and green signals shown in yellow indicate the co-localization of the two proteins (e, f). Nuclei were stained with DAPI (blue). Blue boxed areas were enlarged in the insets to reveal the incidence of colocalization (g, h). Scale bar: 200 µm.

Figure 2. HGF mediated CAV1 activation.

A. WB showing the expression of the indicated proteins in SNU-449 cells, overnight starved and treated with or without HGF at different time points. Calnexin was used as a loading control. B. Representative images for co-localization of phospho-CAV1 with phospho-Met increased by HGF treatment. Induced or non-induced SNU-449 cells by HGF for 60 min were assessed for c-Met (Y1234/1235) (green) (a, b) and CAV1 (Y14) (red) (c, d) phosphorylation by immune fluorescent staining. Subsequent images were merged (e and f) and overlapping of red and green signals were shown in yellow, indicating the co-localization of two proteins. A higher magnification view of the SNU-449 cells was also shown (see boxed areas) (g, h). Bar: 200 µm.

Figure 3. SU11274 inhibited c-Met and downstream signaling.

A. After overnight starvation and SU11274 pretreatment, SNU-449 cells were stimulated with HGF for 15, 30, 60 min or left un-stimulated. Lysates were immunoblotted with indicated antibodies. Calnexin was used as loading control. B. Band intensities of phospho-CAV1 were quantified by densitometry and normalized to CAV1 (n = 3) (*p<0,05, NS: not significant). The relative phospho-Met/c-Met and p-MAPK/MAPK for the different treatments relative to the levels present in corresponding untreated control samples are compared in the bar graphs (n = 3).

Figure 4. Ectopic expression of CAV1 enhanced HGF-mediated c-Met activation.

A. Huh-7-mock and HuH-7-pCAV1 cells were starved for overnight prior to stimulation with HGF for 15, 30 and 60 min. Expression of phosphorylated and total c-Met and MAPK were examined by WB. Overexpression of CAV1 was also verified by WB. Calnexin is shown as a loading control. B. After 60 min treatment with HuH-7-mock, cells stably expressing CAV1 were fixed and stained for c-Met (green) (a, b) and CAV1 (red) (c, d), colocalization signal (yellow) (e, f). Representative fluorescence micrographs were obtained by CM. Higher magnification images were presented to reveal the incidence of colocalization (g, h). Bar: 200 µm.

Figure 5. Ectopic expression of CAV1 enhanced c-Met signaling to drive cellular motility and invasion and branching morphogenesis in response to HGF stimulation.

Cells transfected with mock or CAV1 plasmid were treated with or without HGF and then tested in migration and invasion assays. The cells that migrated and invaded through membrane were stained, counted under a light microscope at 25× magnification. The results are representative of three independent experiments, done in quadruplicate. Fold change were calculated by data from non-induced conditions. Bars represent fold change in mean number ± S.E. of migrating and invading cells; A. HuH-7-mock, B. HuH-pCAV1 and invading cells; C. HuH-7-mock, D. HuH-7- pCAV1 Student's t-test was used in the comparison of the means of non-induced and HGF-induced conditions. E. Branching-morphogenesis assay performed by HuH-7-mock and HuH-7-pCAV1 cells in DMEM supplemented with or without HGF. F. Columns shows mean number ± S.E derived from three separate experiments done in quadruplicate. ANOVA was used in comparison of groups. (***p<0,0001, **p<0,001, *p<0,05; Bar: 200 µm.).

Figure 6. CAV1 knockdown inhibited HGF evoked activation of c-Met signaling pathway.

A. SNU-449 cells transfected with CAV1-siRNA or NT-siRNA for 72 h, stimulated with HGF for 30 min were subjected to WB analysis with indicated antibodies. Calnexin was used as a loading control. B. The graph depicting results from densitometry quantitation of CAV1 band which was normalized to calnexin. Error bars represent S.E. (n = 5). Band intensities of phospho-Met and p-MAPK were quantified by densitometry and normalized to c-Met and MAPK, respectively (n = 3). Values from NT-siRNA were set at 1. ANOVA was used in comparison of groups. (*p<0,05, NS: not significant).

Figure 7. Silencing of CAV1 inhibited the migration and invasion of SNU-449 cells and decreased the formation of complex branching tubular structures.

NT- and CAV1 siRNA transfected SNU-449 cells were seeded in the upper chamber of Boyden chambers. Medium with or without HGF was added to the lower chamber. After 24 h incubation, migrated and invaded. Cells were counted. Bars represent the mean three independent experiment ± S.E. of A. migrating or B. invading cell number. C. SNU-449 cells were transiently transfected with CAV1 or NT-siRNA were grown in collagen I gel for 21 days. HGF was added as indicated. Branching-morphogenesis responses were followed up to 21 days and tubule formation was evaluated. D. Images show a representative experiment that had been performed in quadruplicate for each clone of each group. All data are represented as fold change± S.E. compared with control cells. Photographs were taken at 21 st day by Phase-contrast microscopy. ANOVA was used in comparison of groups, (***p<0,0001, **p<0,001, *p<0,05, Bar: 200 µm).

Figure 8. Immunohistochemical assesment of phospho-Met and phospho-CAV1 expressions in normal, cirrhotic and HCC tissues.

Negative phosphor-Met expression in normal hepatocytes (a), cirrhotic liver tissue showed weak, phospho-Met staining (b). HCC displayed intense phospho-Met staining. Each column represents histologically classified liver tissues (normal liver, cirrhotic liver, HCC) with the height representing the ratio of positive staining for phospho-Met (d). Negative phospho-CAV1 expression in normal liver tissue (e), diffuse phospho-CAV1 staining in hepatocytes in the cirrhotic liver tissue (g), HCC displayed strong phospho-CAV1 staining (h). Comparison of the ratios of positive staining for phospho-CAV1 in normal liver, cirrhotic liver, and HCC tissues. Each column represents the immunoreactivity of both phospho-Met and phospho-CAV1 in the same liver tissue samples (i). Trend in χ²-test was performed to determine the trend between groups (*p<0,05, NS: not significant, Bar = 200 µm).

Figure 9. Immunofluorescence analysis of co-localization between phospho- CAV1 and phospho- Met in cirrhotic and HCC tissues.

Image representing phospho-CAV1 (red) (a) and phospho-Met (green) (b) and no colocalization (yellow) (c) in cirrhotic tissue section. Representative image showing phospho-CAV1 (red) (d) and phospho-Met (green)(e) and colocalization (yellow) (f) in HCC tissue section. Nuclei were stained with DAPI (blue). (Bar = 200 µm).

Figure 10. Immunohistochemical staining in well-, moderate-, and poorly differentiated HCC tissues revealed an increasing trend towards well to poor differentiation.

Representative images shows Serial sections were stained with anti-phospho-Met (a, b, c) and anti-phospho-CAV1(d, e, f) antibodies. Each column represents the ratio of positive staining for phospho-Met (g) and phospho-CAV1 (h), co-expression of phospho-Met and phospho-CAV1 (i) in well-, moderate-, and poorly-differentiated HCC. Trend in χ²-test was performed to determine the trend between groups (*p<0,05, NS: not significant, Bar = 200 µm).

Figure 11. Model for Regulation of c-Met Receptor signaling by CAV1 in HCC cells.

A. In the absence of CAV1 c-Met activation is in stationary phase B. CAV1 expression induces c-Met and MAPK activation and, c-Met driven motility, invasion and morphogenesis. C. HGF induced c-Met activation elevates migration, invasion and branching-morphogenesis in the absence of CAV1. D. HGF treatment induces the highest motility, invasion and morphogenesis in CAV1 expressing cells.