Kaposi's sarcoma-associated herpesvirus-induced upregulation of the c-kit proto-oncogene, as identified by gene expression profiling, is essential for the transformation of endothelial cells

Abstract

Kaposi's sarcoma (KS), the most frequent malignancy afflicting AIDS patients, is characterized by spindle cell formation and vascularization. Infection with KS-associated herpesvirus (KSHV) is consistently observed in all forms of KS. Spindle cell formation can be replicated in vitro by infection of dermal microvascular endothelial cells (DMVEC) with KSHV. To study the molecular mechanism of this transformation, we compared RNA expression profiles of KSHV-infected and mock-infected DMVEC. Induction of several proto-oncogenes was observed, particularly the receptor tyrosine kinase c-kit. Consistent with increased c-Kit expression, KHSV-infected DMVEC displayed enhanced proliferation in response to the c-Kit ligand, stem cell factor (SCF). Inhibition of c-Kit activity with either a pharmacological inhibitor of c-Kit (STI 571) or a dominant-negative c-Kit protein reversed SCF-dependent proliferation. Importantly, inhibition of c-Kit signal transduction reversed the KSHV-induced morphological transformation of DMVEC. Furthermore, overexpression studies showed that c-Kit was sufficient to induce spindle cell formation. Together, these data demonstrate an essential role for c-Kit in KS tumorigenesis and reveal a target for pharmacological intervention.

FIG. 1.

Comparison matrix of normalized intensity values from microarray slides by scatter plot. Normalized logarithmic intensity values obtained from each individual array were compared between each sample and depicted as a scatter plot. The annotation of the x axis is shown to the right of the matrix, whereas the y axis annotation is shown on top. Values that differ more than 1.8-fold are shown in red (high) or green (low). Also shown is the correlation coefficient r² for each comparison. The highest correlation was observed when for results obtained from the same sample hybridized to two arrays. Comparisons between the two different infected samples, I-8 versus I-9, were more similar to each other than comparisons between infected samples and mock-infected DMVEC isolated in parallel.

FIG. 2.

Induction of c-Kit protein on immortalized and primary DMVEC following KSHV infection. (A) Immunofluorescence microscopy illustrating upregulation of c-Kit protein on the surface of E6/E7-immortalized KSHV-infected DMVEC monolayers (KSHV). In contrast, low levels of constitutive c-Kit expression were detected on mock-infected monolayers (Mock). Cells were stained for c-Kit at 3 weeks p.i., when ±60% of the culture was KSHV-infected. (B) Immunofluorescence microscopy illustrating induction of c-Kit (red) on the surface of pDMVEC infected with GFP-KSHV (green) relative to constitutive levels of c-Kit expressed on adjacent uninfected cells in the same monolayer. The corresponding phase image is also shown. Cells were stained for c-Kit at 1 week p.i., when <50% of the cells were KSHV-infected. GFP expression indicates the KSHV-infected cell in the dark-field image.

FIG. 3.

SCF-dependent proliferation of DMVEC is enhanced by KSHV infection. (A) Proliferative response of mock (open squares)- and KSHV (filled squares)-infected DMVEC to exogenous SCF. Proliferation was measured using an XTT-based assay. Results from triplicate wells (± standard deviations [error bars]) are expressed as the percentage increase over basal proliferation measured in the absence of exogenous SCF. Representative results from one of three independent experiments are shown. (B) An inhibitor of c-Kit tyrosine kinase activity (STI 571) eliminates SCF-dependent DMVEC proliferation. KSHV-infected DMVEC were cultured in the presence of increasing doses of STI 571 and in the presence (solid line) or absence (dashed line) of exogenous SCF (50 ng/ml). Proliferation of KSHV-infected DMVEC was measured with an XTT-based assay as described above, but STI 571 was added at the same time as SCF (50 ng/ml). Results for triplicate wells (± standard deviations [error bars]) are expressed as a percentage of basal proliferation measured in the absence of SCF and STI 571 (expressed as 100%). Representative results from one of three independent experiments are shown.

FIG. 4.

Inhibition of c-Kit tyrosine kinase activity reverses the transformed phenotype of KSHV-infected DMVEC. (A) KSHV-infected DMVEC exhibiting disorganized growth and focus formation were left untreated (Control) or treated with STI 571 (0.1 and 1 μM) for 5 days. The STI 571-induced focus loss and monolayer reorganization were observed and recorded with a Nikon light microscope. (B) KSHV-infected DMVEC exhibiting disorganized growth and focus formation were left untreated (0) or infected with an adenovirus vector expressing a dominant negative c-Kit protein (Ad/c-KitDN) at an MOI of 10 or 100 for 5 days, and the elimination of focus formation was recorded as for panel A. For both the pharmacological and dominant negative protein inhibition protocols, results from one of three independent experiments are shown. Fields photographed were representative of the entire monolayer of treated cells.

FIG. 5.

Ectopic expression of c-Kit in normal DMVEC induces morphological changes. DMVEC monolayers infected with a control adenovirus vector expressing GFP (Ad/GFP) at an MOI of 100 maintain a normal cobblestone morphology. In contrast, DMVEC infected with a recombinant adenovirus expressing c-Kit (Ad/c-KitWT) exhibit spindle morphology and disorganized growth. A dose-dependent effect was observed in DMVEC monolayers infected with Ad/c-KitWT at an MOI of 10, supporting the argument for a direct effect of c-Kit on spindle formation. This was confirmed by immunofluorescence microscopy on monolayers infected with Ad/c-KitWT at an MOI of 10. The dark-field enlargement illustrates strong expression of c-Kit protein specifically on a cell exhibiting spindle morphology.