GPR133 (ADGRD1), an adhesion G-protein-coupled receptor, is necessary for glioblastoma growth

Abstract

Glioblastoma (GBM) is a deadly primary brain malignancy with extensive intratumoral hypoxia. Hypoxic regions of GBM contain stem-like cells and are associated with tumor growth and angiogenesis. The molecular mechanisms that regulate tumor growth in hypoxic conditions are incompletely understood. Here, we use primary human tumor biospecimens and cultures to identify GPR133 (ADGRD1), an orphan member of the adhesion family of G-protein-coupled receptors, as a critical regulator of the response to hypoxia and tumor growth in GBM. GPR133 is selectively expressed in CD133+ GBM stem cells (GSCs) and within the hypoxic areas of PPN in human biospecimens. GPR133 mRNA is transcriptionally upregulated by hypoxia in hypoxia-inducible factor 1α (Hif1α)-dependent manner. Genetic inhibition of GPR133 with short hairpin RNA reduces the prevalence of CD133+ GSCs, tumor cell proliferation and tumorsphere formation in vitro. Forskolin rescues the GPR133 knockdown phenotype, suggesting that GPR133 signaling is mediated by cAMP. Implantation of GBM cells with short hairpin RNA-mediated knockdown of GPR133 in the mouse brain markedly reduces tumor xenograft formation and increases host survival. Analysis of the TCGA data shows that GPR133 expression levels are inversely correlated with patient survival. These findings indicate that GPR133 is an important mediator of the hypoxic response in GBM and has significant protumorigenic functions. We propose that GPR133 represents a novel molecular target in GBM and possibly other malignancies where hypoxia is fundamental to pathogenesis.

Figure 1

GPR133 is expressed in the CD133+ cell population of human GBM. (a) The experimental model consists of harvesting human GBM tissue during surgery and growing primary tumorsphere cultures. RNA-seq analysis of FACS-sorted CD133+ and CD133− cells from GBML8 in duplicates revealed 314 differentially expressed genes (fold-change cutoff: 1.5, false discovery rate (FDR)<0.05). GPR133 was among the top 20 genes overexpressed in CD133+ cells, as shown in the heatmap. GPR133's membrane topology and important domains within the extracellular N terminus are shown. (bi) Flow cytometry using a rabbit polyclocal antibody against GPR133 and a mouse monoclonal antibody against CD133 showed enrichment of GPR133 within the CD133+ cell population in three primary cultures. (ii) Cumulative statistics showing the percentage of GPR133+ cells within the CD133+ and CD133− populations in three cultures GBML8, GBML20 and GBML33 (n=3 experiments per culture, P<0.04, t-test; refer to Supplementary Figure 2 for individual statistics for each patient sample used). (c) Relative CD133 and GPR133 mRNA expression in FACS-isolated CD133+ and CD133− populations in three primary cultures (n=3 FACS experiments per culture). (d) Representative immunohistochemical analysis for GPR133 expression in GBML8's parental tumor and normal brain tissue.

Figure 2

Expression of GPR133 overlaps with hypoxia markers in GBM biospecimens. (ai) Hematoxylin and eosin (H&E) of a human GBM showing the necrotic (N) and psesudopalisading necrosis (PPN) regions within the tumor. (ii–iv) Representative images of immunohistochemistry in human GBM biospecimens. A rabbit polyclonal anti-GPR133 antibody reveals selective expression of GPR133 in PPN (ii), along with hypoxic markers Hif1α (iii) and CA9 (iv). (b) Validation of mouse monoclonal GPR133 antibody using CHO cells inducibly overexpressing GPR133. (i) Permeabilized cells showed immunoreactivity at the cell membrane and intracellularly, likely reflecting trafficking of GPR133 along the secretory pathway. (ii) Immunoreactivity was confined to the cell membrane in non-permeabilized cells. In both (i) and (ii), GPR133 immunoreactivity was detected only after induction with doxycycline (200 ng/ml). (c) GPR133 immunoreactivity was abolished by the blocking peptide. (d, i–iii) Immunofluorescent analysis of GPR133 and CA9 in biospecimens. Costaining using a mouse monoclonal antibody against GPR133 in formalin-fixed paraffin-embedded (FFPE) biospecimens also confirms that GPR133 expression highly overlaps with CA9 in (7/8 biospecimens, one biospecimen failed to show PPN). (iv) Normal brain shows neither CA9 nor GPR133 immunoreactivity (using the mouse monoclonal antibody). Ab, antibody.

Figure 3

GPR133 expression is upregulated by hypoxia. (a) Hypoxia upregulates GPR133 mRNA in 6/8 primary cultures (n=3 measurements per culture; ANOVA F_(1,12)=14.82; P<0.003). (b). Analysis of the GPR133 genomic locus reveals numerous HRE motifs, including immediately upstream of the TSS. The schematic also shows primers used for Hif1α ChIP-PCR experiment (green arrows). (c) Western blot shows effects of Hif1α knockdown (HIF1A-KD) on Hif1α protein levels in two primary cultures. β-Actin was used as a loading control. (d) Hif1α knockdown downregulates HIF1A and GPR133 mRNA under normoxic (i, HIF1A: n=3 experiments per culture, t-test, P<0.002; and ii, GPR133: n=3 experiments per culture t-test, P<0.05) and hypoxic conditions (iii, HIF1A: n=3 experiments per culture, t-test, P<0.02; and iv, GPR133: n=3 experiments per culture, t-test, P<0.04) in two primary cultures: GBML8 (top row) and GBML20 (bottom row). (e) Fold enrichment (i) and percent of input (ii) representations of ChIP-PCR using Hifα antibody reveal that GPR133′s promoter region containing the HRE binds Hifα directly (i, n=3 primary cultures, two-tailed t-test, P<0.001; ii, n=3 primary cultures, one-tailed t-test, P<0.05). CA9 promoter was used as a positive control (i, n=3 primary cultures, two-tailed t-test, P<0.008; ii, n=3 primary cultures, one-tailed t-test, P<0.04). Immunoglobulin G (IgG) alone was used as a negative control.

Figure 4

In vitro effects of GPR133 knockdown in GBML20. (a) Schematic of GPR133 mRNA (full-length isoform) showing the recognition sites of the shRNA target sequences (target no. 1 in blue and target no. 2 in black) used. (b) GPR133 knockdown (GPR133-KD no. 1) reduces the number of GPR133+ cells, as shown by flow cytometry (n=3 experiments, t-test, P<0.01). (c) GPR133 knockdown (GPR133-KD no. 1) decreases GPR133 mRNA levels (n=5, t-test, P<0.04). (d) Flow cytometry (i) indicates reduction in the abundance of CD133+ cells after GPR133 knockdown (GPR133-KD no. 1) (ii) (n=5 experiments, t-test, P<0.004). (e and f). Knockdown of GPR133 (GPR133-KD no. 1) reduces the percentage of Ki-67+ cells in both normoxia (i) (upper panel: n=3 experiments, t-test, P<0.002) and hypoxia (ii) (lower panel: n=3 experiments, t-test, P<0.01) (g). GPR133 knockdown impairs tumorsphere formation in normoxia (i) (n=3 experiments, t-test, P<0.006) and hypoxia (ii) (n=3 experiments, t-test, P<0.002). (h and i) GPR133 knockdown with the second shRNA construct (GPR133-KD no. 2) also reduces GPR133 mRNA (h) (n=4 experiments, t-test, P<0.02) and CD133 mRNA (i) (n=3 experiments, t-test, P<0.02) levels. (j and k) GPR133-KD no. 2 impairs tumorsphere formation in normoxia (j) (n=3 experiments, t-test, P<0.04) and hypoxia (k) (n=3 experiments, t-test, P<0.01) in GBML20.

Figure 5

Forskolin rescues effects of GPR133 knockdown. (a) The GPR133-KD no. 1-induced impairment of tumorsphere formation in hypoxia is rescued by Forskolin treatment (10 μM) in GBML8 (i) (n=3 experiments, two-way ANOVA F_(3,6)=7.726, P<0.02) and GBML20 (ii) (n=3 experiments, two-way ANOVA F_(3,6)=9.655, P<0.01). Multiple comparisons were performed with Tukey's post hoc tests. (b) Ten micromolar Forskolin treatment increases cAMP levels in GBML8 (i) (n=3 experiments, t-test, P<0.0006) and GBML20 (ii) (n=3 experiments, t-test, P<0.009) under hypoxic conditions. (c) GPR133 knockdown decreases cAMP levels in GBML8 and GBML20 under normoxic conditions (n=3 experiments per condition, ANOVA F_(1,8)=17.96, P<0.003).

Figure 6

GPR133 knockdown prevents tumor formation and death in vivo. (a and b) Representative MRI images (a) and tumor volumetric estimates (b) show marked reduction in tumor xenograft size in mice implanted with GBM cells bearing GPR133 shRNA knockdown construct no. 1 (GPR133-KD no. 1) (GBML20, n=4 animals per group). (c) Histology of tumor xenografts. Tumor xenografts were identified by human nuclear antigen (hNA) immunoreactivity. The arrow indicates scattered tumor cells in the GPR133-KD condition, in the absence of formed tumor. (d) Cumulative statistics for tumor size obtained from MRI-based volumetric estimates (GBML20, P<0.002, t-test, n=4 animals per group). (e) Kaplan–Meier survival curves of the GPR133-KD no. 1 and control groups (log-rank Mantel–Cox test, P=0.0143). (f) The TCGA data from 160 patients with GBM were analyzed for GPR133 expression. We studied outcomes in two cohorts GPR133 high (in red) and GPR133 low (in blue) based on ranked GPR133 mRNA levels. (g) Kaplan–Meier curves of the two patient cohorts indicate an inverse relation between GPR133 expression and survival (log-rank Mantel–Cox test, P=0.0062).