New Peptide-Drug Conjugates for Precise Targeting of SORT1-Mediated Vasculogenic Mimicry in the Tumor Microenvironment of TNBC-Derived MDA-MB-231 Breast and Ovarian ES-2 Clear Cell Carcinoma Cells

Abstract

Vasculogenic mimicry (VM) is defined as the formation of microvascular channels by genetically deregulated cancer cells and is often associated with high tumor grade and cancer therapy resistance. This microcirculation system, independent of endothelial cells, provides oxygen and nutrients to tumors, and contributes also in part to metastasis. VM has been observed in ovarian cancer and in triple negative breast cancer (TNBC) and shown to correlate with decreased overall cancer patient survival. Thus, strategies designed to inhibit VM may improve cancer patient treatments. In this study, sortilin (SORT1) receptor was detected in in vitro 3D capillary-like structures formed by ES-2 ovarian cancer and MDA-MB-231 TNBC-derived cells when grown on Matrigel. SORT1 gene silencing or antibodies directed against its extracellular domain inhibited capillary-like structure formation. In vitro, VM also correlated with increased gene expression of matrix metalloproteinase-9 (MMP-9) and of the cancer stem cell marker CD133. In vivo ES-2 xenograft model showed PAS⁺/CD31^- VM structures (staining positive for both SORT1 and CD133). TH1904, a Doxorubicin-peptide conjugate that is internalized by SORT1, significantly decreased in vitro VM at low nM concentrations. In contrast, VM was unaffected by unconjugated Doxorubicin or Doxil (liposomal Doxorubicin) up to μM concentrations. TH1902, a Docetaxel-peptide conjugate, altered even more efficiently in vitro VM at pM concentrations. Overall, current data evidence for the first time that 1) SORT1 itself exerts a crucial role in both ES-2 and MDA-MB-231 VM, and that 2) VM in these cancer cell models can be efficiently inhibited by the peptide-drug conjugates TH1902/TH1904. These new findings also indicate that both peptide-drug conjugates, in addition to their reported cytotoxicity, could possibly inhibit VM in SORT1-positive TNBC and ovarian cancer patients.

Keywords: Docetaxel; Doxorubicin; breast cancer; ovarian cancer; peptide-drug conjugates; sortilin; vasculogenic mimicry.

Figure 1

In vitro vasculogenic mimicry by ES-2 ovarian cancer cells and by TNBC-derived MDA-MB-231 cells. (A) Increasing amounts of ES-2 and MDA-MB-231 cancer cells were seeded ontop of Matrigel and left to form 3D capillary-like structures for 24 h as described in the Methods section. Scale bar = 1000 μm (B) Immunolabeling of sortilin in 3D capillary-like structures formed by ES-2 or MDA-MB-231 cancer cells was performed using confocal fluorescent microscopy. Control stainings were performed with only the secondary anti-rabbit antibody. Representative 3D structure stainings are shown for each cell model. Scale bar = 100 μm.

Figure 2

Gene expression of SORT1, CD133 and MMP-9 during in vitro vasculogenic mimicry. (A) ES-2 ovarian cancer and MDA-MB-231 TNBC-derived cells were seeded ontop of Matrigel and in vitro VM assessed for up to 24 h. Scale bar = 1000 μm. (B) Total RNA was isolated from ES-2 and MDA-MB-231 cells at initial (t = 0 h), at early maturation (t = 6 h) and complete maturation (t = 24 h) of 3D capillary-like structures. Gene expression levels of SORT1, CD133, and MMP-9 were assessed in triplicate by RT-qPCR from three independent experiments as described in the Methods sections.

Figure 3

SORT1 and CD133 expression in ES-2 ovarian tumor xenografts. Tumor xenografts were established by subcutaneous inoculation of 7x10⁶ ES-2 ovarian cancer cells, resuspended in 100 μL of HBSS and injected in the right flank of CD-1 nude mice. Tumors were collected when they reached 1500 mm³. (A) Sortilin, CD133, CD31 and PAS stainings were performed as described in the Methods section. (B) Co-staining with PAS was also performed for CD31 (CD31-PAS), sortilin (Sortilin-PAS) and CD133 (CD133-PAS). VM structures (blue arrows) and blood vessels (red arrows) are indicated. Scale bars represent 2500, 250, 100 and 50 µm respectively (left to right column). Representative images are shown from two different ES-2 xenograft tumors.

Figure 4

Effect of sortilin gene silencing on in vitro vasculogenic mimicry. Cells were transiently transfected with either scrambled siRNA (siScr) or specific sortilin siRNA (siSortilin) as described in the Methods section. The extent of sortilin silencing was assessed in ES-2 and MDA-MB-231 cells at (A) the protein level by immunoblotting of cell lysates, and at (B) the gene expression levels by RT-qPCR from total RNA. MMP-9 gene expression was also assessed in both cell models transfected with either siScr or specific siSortilin. Transfected cells were then seeded ontop of Matrigel for 12 h (ES-2 cells), or 24 h (MDA-MB-231 cells). Quantitation of total number of loops was performed for (C) ES-2 cells and (D) MDA-MB-231 cells as described in the Methods section. Quantitation performed in (A–D) results from 3 independent experiments. Scale bar = 1000 μm.

Figure 5

Effect of TH1904, Doxorubcin and liposomal Doxorubicin (Doxil) on in vitro vasculogenic mimicry. (A) Representative pictures of 3D capillary-like structures formed at 12 h from ES-2 ovarian cancer cells seeded ontop of Matrigel in the presence of increasing concentrations of TH1904, Doxorubicin, or Doxil. Control (vehicle) was 0.1% DMSO and was kept constant through out the range of cencentrations tested. Scale bar = 1000 μm. (B) 3D capillary-like structures were quantified for total loop numbers as described in the Methods section. Results represent the mean ± SD for n=2 (Doxil, Doxorubicin) and n=4 (TH1904).

Figure 6

Effect of TH1902 and Docetaxel on in vitro vasculogenic mimicry. (A) Representative pictures of 3D capillary-like structures fromed at 24 h from TNBC-derived MDA-MB-231 cells seeded ontop of Matrigel in the presence of increasing concentrations of either Docetaxel or TH1902. Scale bar = 1000 μm. (B) 3D capillary-like structures were quantified at 24 h for total loop numbers as described in the Methods section. Results represent the mean ± SD for n=3 (Docetaxel, TH1902).

Figure 7

Inhibition of MDA-MB-231 and ES-2 cancer cell migration by TH1902 and TH1904. MDA-MB-231 and ES-2 cancer cells were transiently transfected with either scrambled siRNA (siScr) or specific SORT1 siRNA (siSORT1) as described in the Methods section. (A) Transfected siScr (open circles) or siSORT1 (closed circles) MDA-MB-231 TNBC cells were then pre-incubated for 2 h with vehicle or with 2 µM of TH1902 respectively in siScr (open triangels) or siSORT1 (closed triangles). (B) Control siScr (open circles) or siSORT1 (closed circles) ES-2 cells were then pre-incubated with vehicle or for 2 h with 2 µM of TH1904 respectively in siScr (open triangles) or siSORT1 (closed triangles). Cells in (A, B) were harvested and metastatic potential assessed by following migration in real-time as described in the Methods section. Results are expressed as relative to initial time-point measurements. Data represent the mean ± SEM of two independent experiments, performed in duplicate wells.

Figure 8

Inhibition of ES-2 ovarian cancer cells in vitro vasculogenic mimicry by an anti-sortilin antibody directed against the sortilin extracellular domain. (A) ES-2 ovarian cancer cells were seeded ontop of Matrigel in the presence of 25 nM of either mouse IgG1, rabbit IgG, anti-SORT1 mouse mAb, or anti-SORT1 rabbit pAb. Pictures were taken after 12 h of 3D capillary-like structures formation. The number of loops (blue) and area covered upon tube branchings (red) formed by the cells were quantified as described in the Methods section. Scale bar = 1000 μm. (B) Quantification of total loop numbers. (n=3 ± SD).

Figure 9

Inhibition of TNBC-derived MDA-MB-231 cells in vitro vasculogenic mimicry by an anti-SORT1 antibody directed against the SORT1 extracellular domain. (A) MDA-MB-231 cells were seeded ontop of Matrigel in the presence of 25 nM of either mouse IgG1, rabbit IgG, anti-SORT1 mouse mAb, or anti-SORT1 rabbit pAb. Pictures were taken after 24 h of 3D capillary-like structures formation. The number of loops (blue) and branching (red) formed by the cells were quantified as described in the Methods section. Scale bar = 1000 μm. (B) Quantification of total number of loops. (n=3 ± SD).

Figure 10

Dual mechanism of action for TH1902/TH1904 targeting of SORT1-positive cancers. VM (depicted in blue) is observed in SORT1-positive ovarian cancer and TNBC and can contribute to chemoresistance and metastasis by connecting to pre-existing blood vessels (depicted in red). A dual mechanism of action takes place with TH1902/TH1904 as, first, vasculogenic mimicry is inhibited at low nM concentrations and second, inhibition of cancer cell proliferation through the pharmacological action of the conjugated cytotoxic agent, namely Docetaxel/Doxorubucin, internalized through SORT1 functions. Altogether, this leads to precise and specific targeted inhibition of tumor growth (adapted from Science 2016; 352(6292);1381-1383, with the permission of the American Association for the Advancement of Science).