Protein kinase Czeta represses the interleukin-6 promoter and impairs tumorigenesis in vivo

Abstract

Gene alterations in tumor cells that confer the ability to grow under nutrient- and mitogen-deficient conditions constitute a competitive advantage that leads to more-aggressive forms of cancer. The atypical protein kinase C (PKC) isoform, PKCzeta, has been shown to interact with the signaling adapter p62, which is important for Ras-induced lung carcinogenesis. Here we show that PKCzeta-deficient mice display increased Ras-induced lung carcinogenesis, suggesting a new role for this kinase as a tumor suppressor in vivo. We also show that Ras-transformed PKCzeta-deficient lungs and embryo fibroblasts produced more interleukin-6 (IL-6), which we demonstrate here plays an essential role in the ability of Ras-transformed cells to grow under nutrient-deprived conditions in vitro and in a mouse xenograft system in vivo. We also show that PKCzeta represses histone acetylation at the C/EBPbeta element in the IL-6 promoter. Therefore, PKCzeta, by controlling the production of IL-6, is a critical signaling molecule in tumorigenesis.

FIG. 1.

Ras-induced lung tumorigenesis is enhanced in the absence of PKCζ. (A and B) Lung tumor burden of PKCζ^+/+ and PKCζ^−/− mice expressing the inducible Ras transgene as a result of treatment with doxycycline (Dox) for 2 or 3 months. Representative H&E staining of lung sections (n = 6 per treatment and genotype) is shown. ***, P < 0.001. (C and D) Tumor grades in PKCζ^+/+ and PKCζ^−/− mice after 3 months' exposure to doxycycline. Representative H&E staining showing the different tumor grades in each genotype is shown. ***, P < 0.001.

FIG. 2.

Ras-induced cell proliferation is enhanced in the absence of PKCζ. (A) Quantitation of Ki-67 staining of samples from grade II lung tumors taken from mice treated with doxycycline for 3 months. ***, P < 0.001. (B) Immunohistochemical analysis of cyclin D1 expression levels in PKCζ^+/+ and PKCζ^−/− Ras-expressing lung tumors (n = 6 per treatment and genotype; scale bars, 50 μm). (C) Immunohistochemical analysis of activated caspase-3 levels, as in panel B. (D) Quantitation of intratumoral CD31-positive microvessel density. Ten tumor areas (10,000 μm²) were counted (n = 6 per treatment and genotype). ***, P < 0.001. (E) Immunohistochemical analysis of CD31 in lung samples, as in panel B. (F) Immunohistochemical analysis of VEGF receptor 2 (KDR) levels in lung samples, as in panel B.

FIG. 3.

IL-6 production is enhanced in PKCζ-deficient lung tumors and cells. (A) Immunohistochemical analysis of IL-6 expression in PKCζ^+/+ and PKCζ^−/− Ras-expressing lung tumors (n = 6 per treatment and genotype; scale bars, 50 μm). (B) Immunohistochemical analysis of phospho-Stat3 levels in lung samples, as in panel A. (C) IL-6 secretion by PKCζ^+/+ and PKCζ^−/− immortalized Ras-expressing EFs. Results are shown as means ± standard deviations. ***, P < 0.001. (D) Immunoblot analysis of phospho-Stat3, actin, and oncogenic Ras levels of EFs, as in panel C. The experiment shown is representative of two others with similar results.

FIG. 4.

Growth properties of PKCζ^−/−-deficient Ras-expressing cells. (A and B) Soft-agar growth of Ras-transformed PKCζ^+/+ and PKCζ^−/− EFs and quantitation of number of colonies at 11 days. The experiment shown in panel A is representative of another two with similar results. Results shown in panel B are means ± standard deviations. ***, P < 0.001. (C) Growth of Ras-transformed PKCζ^+/+ and PKCζ^−/− EFs in the presence of 10% FCS. (D) Growth of Ras-transformed PKCζ^+/+ and PKCζ^−/− EFs in 0.1% FCS. (E) IL-6 secretion by PKCζ^+/+ and PKCζ^−/− immortalized Ras-expressing EFs at day 1 or 7 of incubation in the absence of serum. Results are shown as means ± standard deviations. (F to H) mRNA levels of IL-6 (F), IL-6R (G), and gp130 (H) in PKCζ^+/+ and PKCζ^−/− immortalized Ras-expressing EFs incubated as for panel E. Results are shown as means ± standard deviations.

FIG. 5.

Role of IL-6 overproduction in the growth of PKCζ^−/−-deficient Ras-expressing cells. (A) Growth of Ras-transformed PKCζ^+/+ EFs in the absence or in the presence of recombinant mouse IL-6 (10 ng/ml) in 0.1% FCS. (B) Cell cycle analysis of PKCζ^+/+ EFs in the absence or in the presence of recombinant mouse IL-6 (10 ng/ml) in 0.1% FCS at day 7. (C) Growth of Ras-transformed PKCζ^+/+ or PKCζ^−/− EFs in the absence or in the presence of neutralizing anti-IL-6 in 0.1% FCS. All results are means ± standard deviations. ***, P < 0.001. (D) Phospho-Stat3 levels of Ras-transformed EFs, either wild-type of PKCζ deficient, incubated in the absence or in the presence of neutralizing anti-IL-6 for 3 days in the absence of mitogens. This is a representative experiment of another two with very similar results.

FIG. 6.

Role of IL-6 overproduction in tumor growth of PKCζ^−/−-deficient Ras-expressing cells. (A) Suspensions of Ras-transformed PKCζ^+/+ (WT) or PKCζ^−/− (KO) EFs (8 × 10⁵), transduced with a control or an shRNA IL-6 lentiviral vector, were intradermally injected into each flank of nude mice, and tumors were allowed to develop for 13 days. Tumor size was measured every other day. Results are means ± standard deviations (n = 5). (B) Representative mice injected with the different cell genotypes and left to develop for 13 days. (C) Extracts from 293 cells expressing HA-tagged versions of the PKCζ wild type (WT), a kinase-dead mutant form (K281R), or a mutant in which Ser514 was mutated to Phe (S514F) were immunoprecipitated, and their levels and activity were determined in vitro. The experiment shown is representative of another two with similar results. (D) Extracts from Ras-transformed NIH-3T3 fibroblasts expressing HA-tagged versions of the PKCζ wild type (WT), a kinase-dead mutant form (K281R), or a mutant in which Ser514 was mutated to Phe (S514F) were analyzed by immunoblotting. (E) Suspensions of Ras-transformed NIH-3T3 fibroblasts as described above were intradermally injected into each flank of nude mice, and tumors were allowed to develop for 15 days. Tumor size was measured every other day. Results are means ± standard deviations (n = 5). (F) Representative mice injected with the different NIH-3T3 Ras transformants expressing the different types of PKCζ constructs and left to develop for 15 days.

FIG. 7.

PKCζ regulates IL-6 promoter activity. (A) Q-PCR analysis of IL-6 mRNA levels in Ras-transformed EFs (PKCζ^+/+ or PKCζ^−/−). Results are shown as means ± standard deviations. ***, P < 0.001. (B) Q-PCR analysis of IL-6 mRNA levels of Ras-transformed EFs (PKCζ^+/+ or PKCζ^−/−) treated with DRB for different durations. The experiment shown is representative of two others with similar results. (C and D) Ras-transformed PKCζ^+/+ or PKCζ^−/− cells were transfected with two amounts of IL-6-luciferase promoter constructs, either wild type (wt) (C and D) or with mutations in the NF-κB (C) or C/EBPβ (D) enhancer elements, along with a Renilla control plasmid, for 24 h. Afterwards, luciferase activity was determined and normalized for Renilla. Results are the means ± standard deviations for triplicates. Luc., luciferase. (E) C/EBPβ protein levels were determined in Ras-transformed PKCζ^+/+ or PKCζ^−/− cells. (F, G, and H) ChIP determining the in vivo binding of C/EBPβ (F), acetylated histone H4 (G), or HDAC1 (H) to the IL-6 promoter in Ras-transformed PKCζ^+/+ or PKCζ^−/−cells. Relative IL-6 promoter binding was plotted as means ± standard deviations.