Necroptosis in pancreatic cancer promotes cancer cell migration and invasion by release of CXCL5

Abstract

Background: Necroptosis is a form of programmed cell death that is accompanied by release of intracellular contents, and reportedly contributes to various diseases. Here, we investigate the significance of necroptosis in pancreatic cancer.

Methods: We used immunohistochemistry and western blot analysis to evaluate expression of the key mediators of necroptosis-receptor-interacting serine/threonine protein kinase 3 (RIP3) and mixed lineage kinase domain-like (MLKL)-in human pancreatic cancer. We also tested the effects of conditioned media (CM) from necroptotic cells on pancreatic cancer cells in Transwell migration and Matrigel invasion assays. Protein array analysis was used to investigate possible mediators derived from necroptotic cells.

Results: RIP3 and MLKL are highly expressed in human pancreatic cancer tissues compared with normal pancreas. MLKL expression was particularly intense at the tumor invasion front. CM derived from necroptotic cells promoted cancer cell migration and invasion, but not CM derived from apoptotic cells. C-X-C motif chemokine 5 (CXCL5) was upregulated in CM derived from necroptotic cells compared with CM derived from control or apoptotic cells. Moreover, expression of the receptor for CXCL5, C-X-C-motif chemokine receptor-2 (CXCR2), was upregulated in pancreatic cancer cells. Inhibition of CXCR2 suppressed cancer cell migratory and invasive behavior enhanced by necroptosis.

Conclusion: These findings indicate that necroptosis at the pancreatic cancer invasion front can promote cancer cell migration and invasion via the CXCL5-CXCR2 axis.

Fig 1. Detection of RIP3 and MLKL, key mediators of necroptosis in human pancreatic cancer.

(a) RIP3 and MLKL immunohistochemistry in resected specimens of human pancreatic cancer and surrounding normal pancreatic tissues (scale bars = 100 μm). (b) Representative images of MLKL expression at the invasive front and the center of the tumor (scale bars = 100 μm). (c) DAB intensity of MLKL in pancreatic cancer cells was significantly higher at the tumor invasive front than at the center. Five fields at a magnification of 200× per 21 patients were analyzed. (d) Western blot analyses of RIP3 and MLKL in human pancreatic cancer cells and HPDE. *P<0.01.

Fig 2. Induction of necroptosis in pancreatic cancer cells.

(a) Fluorescent images of pancreatic cancer cells treated with TNF-α, Smac mimetic, zVAD-FMK and necrostatin-1 (nec-1). TS: TNF-α + smac mimetic; TSZ: TS + zVAD-FMK. Cells stained by Hoeschst 33342 and EthD-Ⅲ. EthD-Ⅲ staining (red) indicates dead cells (scale bars = 100 μm). (b) Rate of dead cells treated with each agent for 12 hours. (c) Morphological features of dead cells. Pancreatic cancer cells were treated with TSZ or TS for 6 hours. After treatment, cells were stained by Hoechst 33342 (blue), EthD-Ⅲ (red) and Annexin V (green; scale bars = 100 μm). (d) Western blot analysis of p-MLKL (direct activator of necroptosis), MLKL and cleaved caspase-8 p43/41 (activator of apoptosis signal pathway). Graph shows mean ± SE. *P<0.01.

Fig 3. Effects of conditioned medium derived dead cells on pancreatic cancer.

Wound healing assay; (a) representative images of AsPC-1 wound closure, (b) quantitative data (scale bars = 100 μm). Transwell migration assay; (c) representative images of migrated cells, (d) quantitative data of migrated cells (scale bars = 100 μm). Transwell-Matrigel invasion assay; (e) representative images of invaded cells, (f) quantitative data of invaded cells (scale bars = 100 μm). (g) CCK-8 proliferation assay; effect on pancreatic cancer cell proliferation by conditioned medium derived from dead cells or DMSO (control) after 48 hours. Absorbance relative to 0 hour. (h) Images of dead cell localization and subsequent cell invasion at 0, 6, and 12 hours. BxPC-3 spheroids (green) were treated with TSZ or DMSO (control) for 3 hours, and stained by EthD-Ⅲ (scale bars = 100 μm). (i) Representative images of 3D spheroid invasion assay. (j) Quantitative data for spheroid-invaded area. Graphs show mean ± SE. *P < 0.05; **P<0.01; n.s; not significant.

Fig 4. Detection of cytokines in conditioned medium from necroptotic cells.

(a) Images of human cytokine antibody array (120 targets) of conditioned medium derived from AsPC-1 treated with necroptotic stimuli or DMSO (control). Boxes: positive controls; circles: CXCL5, MIP-3α and IL-8. (b) Signals were quantified relative to CM-control. (c) Human cytokine antibody array of conditioned medium from PANC-1, which was treated with apoptotic stimuli or DMSO (control). (d) Signals relative to CM-control. (e, f) Analysis of mRNA expression of chemokine receptors, CXCR2 and CCR6 by qRT-PCR. Results are shown relative to gene expression in non-cancerous HPDE cells after normalization against 18S rRNA. (g) Western blot analysis of CXCR2 in human pancreatic cancer cells and in HPDE. (h) Concentration of CXCL5 in conditioned medium from AsPC-1 or BxPC-3, which were treated with TSZ ± nec-1 or DMSO (control), and measured by ELISA. Graphs show mean ± SE. *P < 0.05; **P<0.01.

Fig 5. Effect of CXCR2 inhibition by selective antagonist, SB225002, or knockdown with siRNA in PC cells.

(a-d) The inhibitory effect of SB225002 (10 nM) on CXCR2 in pancreatic cancer cells was enhanced by conditioned medium from necroptotic cells, and is shown through Transwell migration assay, Matrigel invasion assay and proliferation assay. (a) Representative images of Transwell migration assay. (b) Quantitative data of migrated cells. (c) Quantitative data of invaded cells in Matrigel invasion assay. (d) Effect of SB225002 on pancreatic cancer cell proliferation after 48 hours. Absorbance relative to 0 hour. (e-j) CXCR2 knockdown with siRNA in PC cells. (e) CXCR2 silencing was confirmed by western blot analysis. (f) Representative images of Transwell migration assay. Quantitative data of Transwell migration assays performed with (g) AsPC-1 and (h) BxPC-3 cells, and Matrigel invasion assays performed with (i) AsPC-1 and (j) BxPC-3 cells downregulated for CXCR2 with siRNA. Graph show mean ± SE. *P<0.05; *P<0.01; n.s: not significant.

Fig 6. Effect of human recombinant CXCL5 (rh CXCL5) on PC cell motility.

PC cell motility was evaluated by Transwell migration and Transwell-Matrigel invasion assays. PC cells pretreated with rh CXCL5 (10 ng/ml) or vehicle for 12 hours. (a) Representative images of migrated cells. scale bars = 100 μm. (b) Quantitative data of migrated cells. (c) Quantitative data of invaded cells. Graphs show mean ± SE. *P < 0.05; **P<0.01.

Fig 7. Induction of cell death in human PC cells by chemotherapeutic agents, and detection of CXCR2.

(a) Fluorescence images of pancreatic cancer cells treated with PTX and PTX + nec-1. Blue; Hoechst 33342. Red; EthD-Ⅲ. Scale bars = 100 μm. (b) Rate of dead cells treated with each agent for 12 hours. (c) Analysis of CXCR2 mRNA expression in PC cells treated with programmed cell death-inductive agents. Results are shown as relative to gene expression in ctrl after normalization against 18S rRNA. Cells were treated with TSZ, PTX (40 nM), or PTX (40 nM) + nec-1 (30 μM) for 12 hours. (d) Western blot analyses of p-MLKL and CXCR2. Graph shows the mean ± SE. *P<0.01.