Vasculogenic mimicry of HT1080 tumour cells in vivo: critical role of HIF-1α-neuropilin-1 axis

Abstract

HT1080 - a human fibrosarcoma-derived cell line - forms aggressive angiogenic tumours in immuno-compromised mice. In spite of its extensive use as a model of tumour angiogenesis, the molecular event(s) initiating the angiogenic program in these cells are not known. Since hypoxia stimulates tumour angiogenesis, we examined the hypoxia-induced events evoked in these cells. In contrast to cells grown under normoxic conditions, hypoxia-primed (1% O(2)) HT1080 cells formed robust tubules on growth factor-reduced matrigel and formed significantly larger tumours in xenograft models in a chetomin-sensitive manner, indicating the role of HIF-1α-mediated transcription in these processes. Immuno-histochemical analyses of tumours formed by GFP-expressing HT1080 cells clearly showed that the tumour cells themselves expressed various angiogenic markers including Neuropilin-1 (NRP-1) and formed functional vessels containing red blood cells, thereby unambiguously demonstrating the vasculogenic mimicry of HT1080 cells in vivo. Experiments performed with the HT1080 cells stably transfected with plasmid constructs expressing shNRP-1 or full-length NRP-1 clearly established that the HIF1α-mediated up-regulation of NRP-1 played a deterministic role in the process. Hypoxia-exposure resulted in an up-regulation of c-Myc and OCT3/4 and a down-regulation of KLF4 mRNAs, suggesting their involvement in the tumour formation and angiogenesis. However, silencing of NRP-1 alone, though not affecting proliferation in culture, was sufficient to abrogate the tumour formation completely; clearly establishing that the hypoxia-mediated HIF-1α-dependent up-regulation of NRP-1 is a critical molecular event involved in the vasculogenic mimicry and tumor formation by HT1080 cells in vivo.

Figure 1. HT1080 tumours are highly angiogenic and show presence of in situ hypoxia. A.

An image of a haematoxylin and eosin (HE)-stained section of HT1080 tumours showing the presence of abundant vascular channels containing red blood cells is illustrated. A magnified image of these vascular channels is depicted on the right hand side. (Original magnifications 100X and 400X respectively) B. Paraffin sections of HT1080 tumours were subjected to immuno histochemistry (IHC) analyses using antibodies to various angiogenic markers. The tumour cells were positive for PECAM, VE-Cadherin, VEGF, NRP-1, VEGF₁₆₅ and VEGFR-2 (violet colour). PECAM positive micro-vessel formation is indicated by a black arrow (top layer, right panel). C. Nuclear localization of HIF-1α in the tumour cells confirms the presence of in situ hypoxia. The sections were counterstained with hematoxylin to demarcate the nuclei (blue).

Figure 2. HT1080 cells respond to hypoxia by up-regulation of growth-promoting cytokine, VEGF₁₆₅. A.

Growth kinetics of the HT1080 cells was studied under normoxia and hypoxia. Cell proliferation rate was higher under hypoxic conditions as compared to the normoxic conditions. B. Quantitative PCR experiments were performed on the HT1080 cells incubated under normoxia and hypoxia for quantification of VEGF₁₆₅ mRNA. The hypoxic cells showed ∼9 folds higher expression of VEGF₁₆₅ mRNA compared to the normoxic ones (6 hours time point, N = 3, *** P<0.001). C. Confocal microscopy analysis of the cells incubated under normoxia vs. Hypoxia (48 hours) using an antibody to VEGF₁₆₅ shows that the hypoxic cells secret this growth-promoting cytokine at high levels. Nuclei are demarcated by DAPI (Blue) D. Consistent with the high level of VEGF₁₆₅ at gene and protein levels, the hypoxia-primed HT1080 cells undergo a robust tubule formation on growth factor-reduced matrigel (middle panel) compared to the normoxic cells (left hand panel). The tubule formation was sensitive to the presence of chetomin in the medium (right hand panel) indicating that the HIF1-α-mediated transcription is involved in the process. (Original magnification: 40 X).

Figure 3. HT1080 tumour cells employ vasculogenic mimicry to accommodate in situ hypoxia. A.

Visualization of GFP⁺ tumour cells in the cryosections of the tumours formed by HT1080/WT/GFP cells showed that the tumour cells themselves form vessels that run criss-cross in the tumour mass. DAPI was used to demarcate the nuclei (bar - 10 µm) B. Double IHC experiments performed on the paraffin sections of the tumours formed by HT1080-GFP cells with anti-GFP and anti-PECAM antibodies show that the entire tumour mass was filled with GFP⁺ tumour cells with the vessels formed by the double positive cells. The intensity of PECAM staining was maximal in the cells forming tubes. (Original magnification 200X). A part of the image has been magnified to show the details (original magnification 400 X). C. A vessel formed by the double positive cells is shown (original magnification 200X). The inset clearly shows that the cells forming the vessels have brown nuclei (GFP – indicated by a brown arrow) and violet border (PECAM – indicated by a violet arrow) (original magnification 630 X). D. Image shows absence of PECAM staining in the tumour section of HT1080 where anti-PECAM antibody has not been applied; whereas the GFP signal is clearly seen (Original magnification is 200X). E. A cross section of the blood vessel formed by GFP-PECAM double positive cells is depicted. Presence of red blood cells in the lumen is marked by a red arrow (original magnification 630X).

Figure 4. Hypoxia up-regulates angiogenic program in HT1080 cells.

Confocal microscopy analyses show that the hypoxic cells exhibit up-regulation of NRP-1 (A) and nuclear stabilization of HIF-1α (B). Nuclei are demarcated by DAPI (Blue). Mean fluorescence intensity (M.F.I.) of the cells was measured by Image J software (NIH) at membrane (for NRP-1) and in the nuclear region (for HIF-1α). The M.F.I. of 30 randomly selected cells was used to calculate mean ± S.E.M. The analyses have been graphically depicted (b and d for NRP-1 and HIF-1α respectively) ** p<0.01 and *** p<0.001. C. Quantitative PCR analyses for NRP-1 and HIF-1α mRNA show 2.4 and 1.7 folds up-regulation of these genes in the cells incubated under hypoxia compared to normoxia. (N = 3; *p<.05 and ** p<.01). D. Western blot experiments performed on the cells grown under normoxia vs. hypoxia show that the protein levels of both HIF-1α (upper panel) and NRP-1 (middle panel) are up-regulated in the hypoxic cells compared to the normoxic ones (∼1.4 and 3.2 folds respectively). E. Results of quantitative PCR experiments showed that the hypoxia-induced up-regulation of NRP-1 and VEFG₁₆₅ mRNA was sensitive to the presence of chetomin in the medium, indicating that these genes are down-stream events in the HIF-1α-mediated transcription process. F. Confocal microscopy analysis shows that the hypoxia-mediated up-regulation of NRP-1 protein (Cyan, upper panel) is abrogated in the presence of chetomin in the medium (lower panel), suggesting that NRP-1 expression critically depends on the HIF-1α -mediated transcription. Nuclei are demarcated by DAPI (Blue).

Figure 5. Characterization of HT/shNRP-1 and HT/flNRP-1 clones. A.

Silencing of NRP-1 expression in the HT/shNRP-1 cells was validated at transcript level by performing quantitative PCR experiments. The NRP-1 mRNA was ∼500 folds down-regulated in the shNRP-1 clone (N = 3; ***p<0.001) showing that the shRNA constructs used were effective. B. The results obtained in the PCR experiments were validated by western blot experiments. The NRP-1 expression was down-regulated in the HT/shNRP-1 cells at protein level as well. C. Quantitative PCR analyses confirmed the higher expression of NRP-1 transcript in the HT/flNRP-1 clone compared to the HT1080/Scr cells (∼2 folds, N = 3; *p<0.05). D. Western blot experiments were performed on the HT1080/Scr, HT/shNRP-1 and HT/flNRP-1 cells. Data show the presence of a 150 kDa band of the NRP-GFP fusion protein in the HT/flNRP-1 cells when the blot was probed with antibodies to NRP-1 (upper panel) and GFP (middle panel). The down-regulation of NRP-1 in the HT/shNRP-1 clone is also seen (upper panel). E. Confocal microscopy analyses show a higher expression of NRP-1 in the HT/flNRP-1 clone (upper panel) and a reduced expression of NRP-1 in HT/shNRP-1 clone (Lower panel) compared to the HT1080/Scr cells (middle panel). Membrane-localized NRP-1-GFP fusion protein is seen in the HT/flNRP-1 cells. The RFP fluorescence is seen in the nuclei of HT1080/Scr and HT/shNRP-1 cells respectively. Nuclei are demarcated by DAPI (Blue).

Figure 6. NRP-1 controls the hypoxia-induced angiogenic program in HT1080 cells. A.

Expression of PECAM and VEGFR-2 mRNA was quantified by performing real time PCR experiments on the HT1080/WT cells that were incubated under normoxia and hypoxia – with or without chetomin. Both PECAM and VEGFR-2 mRNAs were up-regulated by hypoxia. Presence of chetomin abrogated the up-regulation of PECAM and VEGFR2 genes by hypoxia indicating that these genes are regulated by the HIF-1α-mediated transcription. B. Quantitative PCR experiments performed on the HT1080/Scr and HT/shNRP-1 cells incubated under hypoxia show that hypoxia failed to up-regulate the expression of PECAM, VEGF₁₆₅ as well as VEGFR-2 in the HT/shNRP-1 cells, indicating that the hypoxia-induced angiogenic program in the HT1080 cells is controlled by NRP-1. C. Tubule formation on matrigel by HT1080/Scr and HT/shNRP-1 cells under normoxia and hypoxia is depicted. The HT/shNRP-1 cells failed to form tubules even after priming with hypoxia (lower right hand panel), indicating that NRP-1 expression in critical for the enhanced tubule formation by the hypoxia-primed HT1080 cells. The hypoxia-primed wild type cells formed robust tubules as seen in the earlier experiments (upper right hand panel). D. HT/flNRP-1 cells form dense tubules even without the hypoxia-priming. The tubule formation by these cells started very early (2 hours) and became very dense by 6 hours (upper right hand panel). After 6 hours, the tubules collapsed as the HT/flNRP-1 cells invaded the matrigel vigorously (lower panel) forming a monolayer in the well. NRP-1 controls the tumorigenic properties of HT1080 cells. E. Matrigel-invasion property of HT1080/Scr cells was compared with that of HT/flNRP-1 and HT/shNRP-1 cells. A representative image of the invaded cells stained with crystal violet is depicted (Original magnification: 100X). Quantification of the invaded cells showed that the HT/flNRP-1 cells possessed significantly enhanced invasive property (N = 3; ** p<0.01) while the HT/shNRP-1 cells showed a significantly reduced invasive ability (N = 3; ***p<0.001). F. Anchorage-independent growth of HT1080/Scr, HT/shNRP-1 and HT/flNRP-1 was examined by performing soft agar colony assay. A representative phase contrast image of the colonies formed by these cells is illustrated (original magnification: 100X). The HT/flNRP-1 cells formed large colonies having loose migrating cells at the border (middle panel), while the HT/shNRP-1 cells formed very small compact colonies. Quantification of the colony formation shows that the number of colonies formed by the HT/flNRP-1 cells was significantly higher (**p<0.01) while that by the HT/shNRP-1 cells was significantly lower (* p<0.05) compared to the HT1080/Scr cells. Data show that NRP-1 expression is necessary for the anchorage-independent growth of HT1080 cells. Data are represented as mean ± S.E.M.

Figure 7. NRP-1 plays a crucial role in tumour growth and angiogenesis in vivo. A.

HT1080/Scr, HT/flNRP-1 and HT/shNRP-1 cells were injected subcutaneously in the flanks of NOD/SCID mice (9 mice per set) to compare their tumorgenic potential. HT/flNRP-1 cells formed larger tumours (mouse in the middle) compared to those formed by the HT1080/Scr cells (mouse on the left). HT/shNRP-1 cells did not form tumour (mouse on right, 0/9). B. A comparative image of the tumours formed by the HT1080/Scr and the HT/flNRP-1 cells is depicted. The tumours formed by HT1080/Scr and HT/flNRP-1 cells were weighed. The mean weight of the tumours formed by the HT/flNRP-1 was significantly higher than that of the HT1080/Scr cells. (N = 9, ***p<0.001) C. The kinetics of tumour formation by the HT/flNRP-1 cells was significantly higher compared to that of HT1080/Scr cells (**p<0.01, ***p<0.001). D. HT/flNRP-1 tumor sections were subjected to IHC analyses using antibodies to various angiogenic markers like PECAM, VE-Cadherin, VEGF, VEGF₁₆₅, NRP-1 and VEGFR-2. The sections showed a strong expression of all these markers indicating that the HT/flNRP-1 tumours are highly angiogenic (original magnification: 200X). E. Paraffin sections of the tumours formed by the HT1080/Scr and the HT/flNRP-1 were immuno-stained with an anti-PECAM antibody. The HT/flNRP-1 tumours showed a high density of PECAM-positive tube-like structures (indicated by arrows) compared to the HT1080/Scr tumours indicating a high level of angiogenesis (original magnification: 100X) F. The strong nuclear localization of HIF-1α seen in these tumours confirms a high level of in situ hypoxia (original magnification: 200X). Hypoxia-priming enhances the in vivo tumour formation. G. HT1080/Scr and HT/flNRP-1 cells – primed or not with hypoxia – were injected sub-cutaneously in the skin of NOD/SCID mice. The size of the tumours formed by the hypoxia-primed cells was significantly larger that their respective normoxic controls. Quantification of the tumour weights (N = 9) shows that hypoxia-priming significantly enhances the tumour formation by both HT1080/Scr as well as by the HT/flNRP-1 cells (Data are represented as mean± S.E.M., N = 9, ***p<.001 and **p<.01.) H. The kinetics of tumour formation by the hypoxia-primed cells at various time points was significantly higher compared to their normoxic counterparts (*p<0.05, **p<0.01, ***p<0.001).

Figure 8. Hypoxia modulates the expression of cancer stem cell markers in the HT1080 cells. A.

Quantitative PCR analyses for OCT3/4, c-Myc and KLF4 mRNA shows that hypoxia up-regulated the expression of OCT3/4 and c-Myc while down-regulates that of KLF4. B. Presence of chetomin in the incubation medium of cells incubated under hypoxia resulted in a further up-regulation of the expression of OCT3/4 and c-Myc mRNA indicting that these genes are independent of HIF-1α-mediated transcription and is under the control of a mechanism that is negatively regulated by the HIF-1α-mediated transcription. The down-regulation of KLF4 by hypoxia was however, rescued by chetomin showing that it was a HIF1-α-dependent process. C. Quantification of OCT3/4, c-Myc and KLF4 mRNA in the hypoxia-primed HT1080/Scr and HT/shNRP-1 cells shows that the expression of OCT3/4 and c-Myc is significantly higher in the hypoxia-primed HT/shNRP-1 cells compared to the hypoxia-primed HT1080/Scr cells, showing that the up-regulation of these genes by hypoxia is not only NRP-1 independent, but also gets further enhanced when NRP-1 is silenced.The suppression of KLF4 expression by hypoxia was partially rescued by silencing of NRP-1 indicating the role of HIF-1α-NRP-1 axis in its down-regulation by hypoxia. (Data in all panels are represented as mean ± S.E.M; N = 3 and *** p<0.001, ** p<0.01 and *p<0.5).