An alternatively spliced variant of CXCR3 mediates the inhibition of endothelial cell growth induced by IP-10, Mig, and I-TAC, and acts as functional receptor for platelet factor 4

Abstract

The chemokines CXCL9/Mig, CXCL10/IP-10, and CXCL11/I-TAC regulate lymphocyte chemotaxis, mediate vascular pericyte proliferation, and act as angiostatic agents, thus inhibiting tumor growth. These multiple activities are apparently mediated by a unique G protein-coupled receptor, termed CXCR3. The chemokine CXCL4/PF4 shares several activities with CXCL9, CXCL10, and CXCL11, including a powerful angiostatic effect, but its specific receptor is still unknown. Here, we describe a distinct, previously unrecognized receptor named CXCR3-B, derived from an alternative splicing of the CXCR3 gene that mediates the angiostatic activity of CXCR3 ligands and also acts as functional receptor for CXCL4. Human microvascular endothelial cell line-1 (HMEC-1), transfected with either the known CXCR3 (renamed CXCR3-A) or CXCR3-B, bound CXCL9, CXCL10, and CXCL11, whereas CXCL4 showed high affinity only for CXCR3-B. Overexpression of CXCR3-A induced an increase of survival, whereas overexpression of CXCR3-B dramatically reduced DNA synthesis and up-regulated apoptotic HMEC-1 death through activation of distinct signal transduction pathways. Remarkably, primary cultures of human microvascular endothelial cells, whose growth is inhibited by CXCL9, CXCL10, CXCL11, and CXCL4, expressed CXCR3-B, but not CXCR3-A. Finally, monoclonal antibodies raised to selectively recognize CXCR3-B reacted with endothelial cells from neoplastic tissues, providing evidence that CXCR3-B is also expressed in vivo and may account for the angiostatic effects of CXC chemokines.

Figure 1.

Identification, molecular characterization, and tissue distribution of CXCR3-B. (a) Structure of the human CXCR3 gene. Upper case, the exons; lower case, the intron; arrow, the CXCR3-B transcription start; underline, the CXCR3-B translation start site (ATG); light shading, the donor (AG/gt, common for both CXCR3-A and CXCR3-B) and acceptor (ag/GG, CXCR3-B; AG/GT, CXCR3-A) splice sites. The nested primers used for 5′ and 3′ RACE are boxed and the direction is pointed by the arrow. The 182-bp probe (recognizing CXCR3-B) and the 401-bp probe (recognizing both CXCR3-A and CXCR3-B) used for Northern blot analysis are evidenced in yellow and light green, respectively. (b) RACE performed on primary cultures of HMVEC. Lane 1, DNA ladder Marker VIII; lane 2, 5′ RACE product; lane 3, 3′ RACE product; lane 4, DNA ladder 1 Kb plus. (c) Schematic representation illustrating the generation of CXCR3-A and CXCR3-B mRNA through alternative splicing. (d) Multiple tissue Northern blot hybridization with the 182-bp probe (top) or the 401-bp probe (bottom). These sequence data are available from GenBank/EMBL/DDBJ under accession no. AF469635.

Figure 2.

CXCR3-A and CXCR3-B expression by HMEC-1 transfectants and their binding affinity to cognate ligands. (a) Flow cytometric analysis of surface CXCR3-A. (b) Flow cytometric analysis of surface CXCR3-B. (c) CXCL10, CXCL9, and CXCL11 displacement of ¹²⁵I-labeled CXCL10 bound to CXCR3-A transfectants. (d) CXCL10, CXCL9, and CXCL11 displacement of ¹²⁵I-labeled CXCL10 bound to CXCR3-B transfectants. (e) Lack of significant displacement by cold CXCL4 of ¹²⁵I-labeled CXCL10 bound to CXCR3-A transfectants. (f) CXCL4 displacement of ¹²⁵I-labeled CXCL10 bound to CXCR3-B transfectants. (g) Lack of significant binding of CXCL4 to CXCR3-A transfectants. (h) High affinity binding of CXCL4 to CXCR3-B transfectants. Figures show mean displacement curves generated by analysis with the Allfit software obtained in eight separate experiments.

Figure 3.

Functional properties of CXCR3-A- and CXCR3-B-transfected cells. (a) Apoptosis in CXCR3-B transfectants as assessed by detection with flow cytometry of the percentage of cells with a sub-G1 DNA content or of cells showing DNA fragmentation by using the TUNEL technique (inset). Results are from one representative of four experiments. (b) In vitro vessel formation capability of CXCR3-B transfectants as assessed by the Matrigel assay. Data are from one representative of four independent experiments. (c) Apoptosis in CXCR3-A–transfected cells (for details see Fig. 4 a). (d) In vitro vessel formation capability of CXCR3-A transfectants (for details see Fig. 4 b). (e) Detection of CXCL11 mRNA expression by HMEC-1 as assessed by real-time quantitative RT-PCR. Columns represent mean values (±SD) of four separate experiments. (f) Flow cytometric analysis on HMEC-1 of CXCL9, CXCL10, and CXCL11 protein. Black line, isotype control mAb; green line, CXCL10; light blue, CXCL9; pink line, CXCL11. Data are from one representative of five independent experiments. (g) Opposite effects of neutralizing anti-CXCL11 mAb on the proliferation of CXCR3-A (open bar) and CXCR3-B (solid bar) transfectants. Results represent mean values (±SD) of the percentage of proliferation over isotype controls obtained in four separate experiments. (h) Opposite effects of CXCL10 on the proliferation of CXCR3-A (left bars) and CXCR3-B (right bars) transfectants. (i) Effects of CXCL4 on the proliferation of CXCR3-A (left bars) and CXCR3-B (right bars) transfectants. Results represent mean values (±SD) of the percentage of proliferation over controls (unstimulated cells) from four separate experiments *, P < 0.05; **, P < 0.001.

Figure 4.

Activation of distinct signal transduction pathways in CXCR3-A and CXCR3-B transfectants. (a) Increased proliferative activity in CXCR3-A transfectants is strongly reduced by PTX both in basal conditions and after treatment with 500 nM CXCL10. (b) PTX has no effect on the proliferation of CXCR3-B transfectants both in basal conditions and after treatment with 4 μM CXCL10. Cells were incubated for 60 h with 1 μg/ml PTX and thymidine incorporation was assessed in the last 12 h. Columns represent mean values (±SD) of three separate experiments. *, P < 0.05. (c) Induction by CXCL10, CXCL9, and CXCL11 (1 μM), but not by CXCL4 (1 μM), of Ca⁺⁺ mobilization in CXCR3-A transfectants. Results are from one representative of four experiments. (d) Effect of CXCL10, CXCL9, CXCL11, and CXCL4 (2 μM) on basal cAMP production and of CXCL10 and CXCL4 (2 μM) on forskolin (1 μM)-stimulated cAMP production in CXCR3-B transfectants. Columns represent mean values (±SD) of six separate experiments. *, P < 0.05; **, P < 0.001. (e) Absence of p21Cip1/Waf1 and p53 regulation by CXCL4 in CXCR3-A transfectants as assessed by real-time quantitative RT-PCR. (f) Up-regulation in CXCR3-B transfectants of p21Cip1/Waf1, but not of p53, mRNA levels by increasing concentrations of CXCL4 as assessed by real-time quantitative RT-PCR.

Figure 5.

Cellular expression of CXCR3-A (solid bars) and CXCR3-B (hatched bars) and their opposite effects on the proliferation of different cell types. (a) CXCR3-A and CXCR3-B expression by peripheral blood–activated T cells, HMC, and HMVEC as assessed by real-time quantitative RT-PCR. Columns represent mean values (±SD) of eight separate experiments. (b) Up-regulation of HMC growth by CXCL10 and its inhibition by an anti-CXCR3 mAb. (c) Inhibitory effect of CXCL4 and of CXCL10 on the proliferation of HMVEC. The inhibitory effects of both CXCL4 and CXCL10 are reverted by an anti-CXCR3 mAb. (d) Selective expression of CXCR3-B mRNA by the ACHN cell line as detected by quantitative RT-PCR. (e) Surface expression of CXCR3 on the membrane of ACHN cells as detected by FACS^® analysis performed with the 49801.111 mAb. (f) Demonstration of a single type of surface receptor in ACHN cells with an IC50 for CXCL10 and CXCL4 comparable to that observed for CXCR3-B. (g) Inhibitory effect of CXCL4 and of CXCL10 on the proliferation of ACHN cells. The inhibitory effects of both CXCL4 and CXCL10 are reverted by an anti-CXCR3 mAb. (h) Effect of CXCL10 (2 μM) on basal cAMP production and of CXCL10 (2 μM) on forskolin (1 μM)-stimulated cAMP production in CXCR3-B transfectants. Columns represent mean values (±SD) of six separate experiments. *, P < 0.05; **, P < 0.001. (i) Up-regulation in CXCR3-B transfectants of p21Cip1/Waf1, but not of p53, mRNA levels by increasing concentrations of CXCL4 as assessed by real-time quantitative RT-PCR. Symbols represent mean values (±SD) of four separate experiments. *, P < 0.01. ▪, CXCL4 plus 20 μg/ml isotype mAb; □, CXCL4 plus 20 μg/ml anti-CXCR3 mAb; •, CXCL10 plus 15 μg/ml isotype mAb; ○, CXCL10 plus 15 μg/ml anti-CXCR3 mAb (clone 49801.111).

Figure 6.

Detection of CXCR3-B protein expression by different types of cell cultures and by endothelial cells of human neoplastic tissues by CXCR3-B–specific mAbs. (a) Absence of reactivity in mock transfectants stained with an anti-CXCR3-B mAb. ×100. (b) Intense staining of CXCR3-B transfectants with an anti–CXCR3-B mAb. ×100. (c) Absence of reactivity in CXCR3-A transfectants stained with an anti–CXCR3-B mAb. ×100. (d) Absence of reactivity in primary cultures of HMC stained with an anti–CXCR3-B mAb. ×100. (e) Positive staining of primary cultures of HMVEC as well as the ACHN cell line (f) with an anti–CXCR3-B mAb. ×100. (g) Absence of reactivity in normal human renal tissue stained with PL1 anti–CXCR3-B mAb. ×10. (h) Staining with the same mAb of endothelial cells in a specimen of renal cell carcinoma. (i) Staining of both endothelial and tumor cells with the anti-CXCR3 mAb 49801.111 tested in an adjacent section. (j) Absence of reactivity in an adjacent section stained with an isotype-matched control mAb. (k and l) Reactivity of endothelial cells from the same renal carcinoma specimen before and after adsorption of PL1 mAb with the peptide used for mouse immunization. (m) Reactivity with PL1 mAb of endothelial cells from a group of vessels in a renal cell carcinoma specimen as detected at a higher power magnification. ×250. (n) Staining of an adjacent section with PL2 anti–CXCR3-B mAb. (o) Double label immunohistochemistry for CXCR3-B (red) and vWf (blue-gray), showing costaining (brown). (p) Absence of CXCR3-B reactivity in normal human lung tissue stained with PL1 anti–CXCR3-B mAb. (q) Staining with the same mAb of endothelial cells in a specimen of NSCLC. (r) Staining of both endothelial cells and other cell types with the anti-CXCR3 mAb 49801.111 in an adjacent section.