The G-protein coupled receptor associated sorting protein GASP-1 regulates the signalling and trafficking of the viral chemokine receptor US28

Abstract

Human cytomegalovirus (HCMV) encodes the seven transmembrane(7TM)/G-protein coupled receptor (GPCR) US28, which signals and endocytoses in a constitutive, ligand-independent manner. Here we show that, following endocytosis, US28 is targeted to the lysosomes for degradation as a consequence of its interaction with the GPCR-associated sorting protein-1 (GASP-1). We find that GASP-1 binds to US28 in vitro and that disruption of the GASP-1/US28 interaction by either (i) overexpression of dominant negative cGASP-1 or by (ii) shRNA knock-down of endogenous GASP-1 is sufficient to inhibit the lysosomal targeting of US28 and slow its post-endocytic degradation. Furthermore, we found that GASP-1 affects US28-mediated signalling. The knock-down of endogenous GASP-1 impairs the US28-mediated Galphaq/PLC/inositol phosphate (IP) accumulation as well as the activation of the transcription factors Nuclear Factor-kappaB (NF-kappaB) and cyclic AMP responsive element binding protein (CREB). Overexpression of GASP-1 enhances both IP accumulation and transcription factor activity. Thus, GASP-1 is an important cellular determinant that not only regulates the post-endocytic trafficking of US28, but also regulates the signalling capacities of US28.

Figure 1

US28 interacts with GASP-1 and GASP-2 in vitro. A,B) In vitro translation assay of GASP binding. 35S-methionine-labelled recombinant GASP-1 (A) and GASP-2 (B) bind to GST-fusion proteins containing the CT of US28 and the DOP, but not the GST-protein (C), beads (B) alone or the MOP. The corresponding inputprotein levels are shown below the radiographs. Blots are representative of at least three independent experiments. C) Co-immunoprecipitation of US28 with GASP-1 and GASP-2 in HEK293 cells. HEK293 transiently transfected with pcDNA3.1 (pcDNA), Flag-US28 (US28), Flag-DOP (DOP) or Flag-β2AR (β2AR) were lysed and receptors immunoprecipitated with Flag-antibody sepharose beads (IP). Precipitates were resolved by SDS/PAGE, transferred to PVDF membranes and immunoblotted for GASP-1 and GASP-2 (first panel) and receptor levels (second panel). Lysates were probed for GASP (third panel) and β-actin (fourth panel) levels. As observed before (14), native GASP proteins (C) run at higher molecular weight levels than recombinant proteins (A and B), likely because of post-translational modifications. D) Quantification of multiple experiments performed in C. Data are means of two to four experiments ± SD, *p < 0.05, **p < 0.01.

Figure 2

Post-endocytic sorting of US28 is mediated by GASP-1. A) The dominant negative cGASP-1 binds to GST-fusion proteins containing the CT of US28, the DOP, but not the GST-protein (C), beads (B) alone or the MOP. The corresponding input protein levels are shown below the radiographs. Blots are representative of at least three independent experiments. B) cGASP-1 competes with GASP-1 for the binding site on the US28-CT. MBP-US28 was incubated with increasing concentrations of purified cGASP-1 in the presence of 35S-Met-labelled recombinant GASP-1. MBP-protein was used as control (C). Molecular weight marker (S). The corresponding input protein level is shown below the radiograph. C) US28 is sorted to lysosomes. HEK293 cells transiently transfected with Flag-US28 were ‘fed’ antibody to the extracellular Flag-tag for 45 min, then fixed and permeabilized. Receptors (green) were analysed for colocalization with the lysosomal markers LAMP1 and LAMP2 (red), merge: yellow. D) cGASP-1 alters the localization of US28. Antibody feeding experiments in HEK293 cells stably expressing GFP-cGASP-1 (see insert) and transiently expressing Flag-US28 revealed a redistribution of the receptor to vesicles close to the cell surface (see arrows). Green: Flag-US28, red: LAMP1/2, merge: yellow. E) Knock-down of endogenous GASP-1 in HEK293 cells using a shRNA-lentivirus. HEK293 cells were infected with either shGASP-1 or shScr virus. Forty-eight hours post-infection, cells were lysed, separated by SDS/PAGE and immunoblotted for GASP-1. β-actin staining served as loading control (lower panel). GASP-2 levels remained unchanged in both shScr and shGASP-1 infected cells (see 130-kDa band). F) EGF receptor degradation is not impaired by shGASP-1 knock-down. HEK293 cells infected with shScr or shGASP-1 virus were transiently transfected with Flag-US28 and either left untreated or incubated with EGF (5 μm) for 3 h. Lysates were analysed by SDS/PAGE and immunoblotted for endogenously expressed EGF receptor (first panel, EGFR), GASP-1 and GASP-2, US28 and β-actin (lower panels). G,H) shRNA knock-down of GASP-1 prevents lysosomal targeting of US28. HEK293 cells were infected with either shScr virus (G) or shGASP-1 virus (H) and transfected with Flag-US28. Antibody feeding experiments showed that US28 colocalizes with LAMP1 and LAMP2 in cells infected with scrambled virus (G), whereas the receptor is redistributed to vesicles close to the cell surface in cells infected with shGASP-1 (H, see arrows). Green: Flag-US28, red: LAMP1/2, merge: yellow, insert: EGFP-shRNA-virus. Scale bars = 10 μm.

Figure 3

Colocalization of US28 with the endosomal markers EEA.1 and transferrin. A) Colocalization of US28 with EEA.1. HEK293 cells transiently transfected with Flag-US28 were ‘fed’ antibody to the extracellular Flag-tag for 45 min, then fixed and permeabilized. Receptors (green) were analysed for colocalization with the early endosomal marker EEA.1 (red), merge: yellow. B) US28 does not colocalize with EEA.1 in cGASP-1-overexpressing cells. Antibody feeding experiments in HEK293 cells stably expressing GFP-cGASP-1 and transiently expressing Flag-US28 revealed no colocalization of the receptors with EEA.1. Green: Flag-US28, red: EEA.1, insert: GFP-cGASP-1. C,D) Colocalization of US28 with EEA.1 in shScr and shGASP-1 infected cells. HEK293 cells were infected with either shScr virus (C) or the shGASP-1 virus (D) and transfected with Flag-US28. Antibody feeding experiments showed that US28 partially colocalizes with EEA.1 in cellsinfected with scrambled virus (C), whereas there was no colocalization detectable in cells infected with shGASP-1 (D). Green: Flag-US28, red: EEA.1, merge: yellow, insert: EGFP-shRNA-virus. E) US28 colocalizes with the endosomal marker transferrin. Antibody feeding experiments in HEK293 cells transiently transfected with Flag-US28 were conducted in the presence of AlexaFluor 594-conjugated transferrin (for details see Methods). Receptors (green) were analysed for colocalization with the endosomal marker transferrin (red), merge: yellow. F) US28 colocalizes with transferrin in GFP-cGASP-1-overexpressing cells. Antibody feeding experiments in HEK293 cells stably expressing GFP-cGASP-1 and transiently expressing Flag-US28. Green: Flag-US28, red: transferrin, merge: yellow, insert: GFP-cGASP-1. G,H) Colocalization of US28 with transferrin in shScr and shGASP-1 infected cells. HEK293 cells were transduced with either shScr virus (G) or the shGASP-1 virus (H) and transfected with Flag-US28. Antibody feeding experiments showed that US28 partially colocalizes with transferrin in cells infected with scrambled virus (G) as well as in cells infected with shGASP-1 (H). Green: Flag-US28, red: transferrin, merge: yellow, insert: EGFP-shRNA-virus. Scale bars = 10 μm.

Figure 4

Disrupting the GASP-1/US28 interaction does not affect constitutive internalization of US28, but delays receptor degradation. A) Overexpression of GFP-cGASP-1 does not affect receptor internalization. HEK293 cells (upper left panel) or cells stably expressing GFP-cGASP-1 (upper right panel) were transiently transfected with Flag-US28. Internalization of biotinylated Flag-US28 (bioUS28) was monitored at the time-points indicated, before cells were stripped of surface-biotin. The total amount of biotinylated proteins before the strip is shown by 100%. The lower panels show the corresponding lysate samples immunoblotted for GASP, total receptor (totUS28) and β-actin. B) Disrupting the GASP-1/US28 interaction by shRNA does not affect receptor internalization. HEK293 cells were infected with shScr (upper left panel) or shGASP-1 virus (upper right panel) for 48 h and transiently transfected with Flag-US28. Internalization of biotinylated Flag-US28 (bioUS28) was monitored as described in A. Disrupting the GASP-1/US28 interaction delays receptor degradation. C) Overexpression of GFP-cGASP-1 delays US28 degradation. HEK293 cells stably expressing GFP-cGASP-1 (upper panel) or control cells (lower panel) were transiently transfected with Flag-US28. Biotinylated Flag-US28 (bioUS28) was allowed to constitutively internalize for 45 min (see A and B), then cells where stripped of surface-biotin (arrow). Thus, 45′ indicates the internalized US28 receptor pool at 45 min. Subsequently, the degradation of US28 was monitored for additional 120 min. D) shRNA knock-down of GASP-1 delays US28 degradation. HEK293 cells were infected with shGASP-1 (upper panel) or shScr virus (lower panel) for 48 h and transiently transfected with Flag-US28. Biotinylation assays were performed as described in C. E) Quantification of biotinylation assay corresponding to D. Biotinylated receptor bands in shScr (○) or shGASP-1 (●) cells were normalized to the total US28 receptor pool and β-actin and the 45′ value was set to 100%. Data are means of five experiments ± SD, *p < 0.05. F) Quantification of surface-biotinylated US28. Biotinylated surface receptor bands (100% lanes) were normalized to the total US28 (totUS28) receptor pool and quantified with ImageJ software. Control cells (white bars) were set to 100%. In both cGASP-1 and shGASP-1 expressing cells (black bars), surface bioUS28 was significantly higher than in control cells (white bars). Data are means of two to three experiments ± SD, *p < 0.05.

Figure 5

Constitutive recycling of US28 is not dependent on GASP-1. A,B) Recycling of US28 is not impaired in cells overexpressing GFP-cGASP-1. HEK293 cells (A) or cells stably expressing GFP-cGASP-1 (B) transiently transfected with Flag-US28 were ‘fed’ a Ca2+ –sensitive antibody to the extracellular Flag-tag for 45 min. Then the cells were stripped with PBS–EDTA (strip) and warm growth medium was added. After 15 or 30 min the cells were fixed and the recycled receptor was stained under non-permeabilizing conditions. Inserts: DAPI (A) and GFP-cGASP-1 (B). C,D) Recycling of US28 is not impaired in shScr or shGASP-1 infected cells. HEK293 cells infected with shScr virus (C) or shGASP-1 virus (D) were transiently transfected with Flag-US28. Recycling experiments were performed as in A and B. Inserts: GFP-shRNA lentivirus. Scale bars = 20 μm.

Figure 6

GASP-1 modulates US28-mediated IP accumulation. A) Overexpression of GASP-1 and cGASP-1 alters US28-mediated IP turnover. HEK293 cells were transiently transfected with Flag-US28 (75 ng/well) and 100 ng/well of either pcDNA3.1 (black bar), HA-GASP-1 (striped bar) or HA-cGASP-1 (grey bar). Controls were transfected with pcDNA3.1 (175 ng/well, white bar). IP production mediated by US28 was allowed to accumulate for 45 min. Values were normalized to the cell number, and 100% corresponds to the basal activity of US28 (black bar). Data are means of six experiments ± SD carried out in quadruplicates, ***p < 0.001. B) Expression levels of HA-GASP-1 and HA-cGASP-1 in HEK293-US28 cells. HEK293 cells were transiently transfected with Flag-US28 in combination with pcDNA3.1 and HA-GASP-1 (upper panel) or with HA-cGASP-1 (lower panel). The cells were lysed, separated by SDS/PAGE and blotted with GASP antibody after 24 h. Overexpression of HA-GASP-1 or HA-cGASP-1 does not alter GASP-2 levels. C) US28 levels in HEK293 cells overexpressing GASP-1 and cGASP-1. HEK293 cells were transfected as in A. The expression levels of US28 were assayed by ELISA against the Flag-epitope tag of US28. Values were normalized to the cell number. Data are means ± SD of one representative experiment carried out in quadruplicates. The control (white bar) was set to one and the other values were normalized accordingly. D) Reduced IP accumulation in shGASP-1 infectedcells is restored by overexpression of rGASP-1. HEK293 cells were infected with shScr (black bar) or the shGASP-1 virus (striped bar and grey bar). Then cells were transiently transfected with Flag-US28 (75 ng/well) and either 100 ng/well pcDNA3.1 (black and striped bars) or 100 ng/well HA-rGASP-1 (grey bar). Controls were transfected with pcDNA3.1 (175 ng/well, white bar). The IP accumulation assay was conducted as described in A. Values were normalized to the cell number, and 100% corresponds to the basal activity of US28 in shScr infected cells (black bar). Data are means of four experiments ± SD carried out in quadruplicates, ***p < 0.001. E) GASP-1 levels in shGASP-1 infected cells can be restored with HA-rGASP-1. ShScr infected cells were transfected with Flag-US28 and pcDNA3.1. shGASP-1 infected cells were transfected with either pcDNA3.1 or HA-rGASP-1. The cells were lysed, separated by SDS/PAGE and blotted with the GASP antibody after 24 h. Blot shows one representative of at least three independentexperiments. F) US28 levels in shScr and shGASP-1 infected cells. HEK293 cells were infected and transfected (see D) and ELISA was performed as described in C.

Figure 7

US28-mediated NF-κB and CREB transcription is modulated by GASP-1. A,B) US28-mediated transcription factor activation is altered upon overexpression of GASP-1 and cGASP-1. HEK293 cells were transiently transfected with Flag-US28 (50 ng/well) in combination with 100 ng/well pcDNA3.1 (black bar), HA-GASP-1 (striped bars) or HA-cGASP-1 (grey bars) and the respective cis-reporter luciferase plasmid for either NF-κB (50 ng/well, A) or CREB (200 ng/well, B). Controls were transfected with pcDNA3.1 (white bars). A luciferase reporter assay was conducted 24 h post-transfection. Values were normalized to the cell number, whereby 100% corresponds to the basal activity of US28 (black bar). Data are means of four experiments ± SD carried out in quadruplicates, ***p < 0.001. C, D) US28 levels in HEK293 cells overexpressing GASP-1 and cGASP-1. HEK293 cells were transiently transfected as described in A and B. The expression levels of US28 were assayed by ELISA as described before.

Figure 8

Reduced NF-κB and CREB activation can be restored by overexpression of rGASP-1. A,B) US28-mediated transcription factor activation is rescued upon overexpression of rGASP-1. ShScr infected cells (black bars) and shGASP-1 infected cells (grey and striped bars) were transfected with Flag-US28 (50 ng/well) in combination with 100 ng/well of pcDNA3.1 (black bar and grey bars) or HA-rGASP-1 (striped bars) as well as the respective cis-reporter plasmids for either NF-κB (50 ng/well, A) or CREB (200 ng/well, B). Controls were transfected with pcDNA3.1 (white bars). A luciferase reporter assay was conducted 24 h post-transfection. Values were normalized to the cell number, whereby 100% corresponds to the basal activity of US28 (black bar). Data are means of four experiments ± SD carried out in quadruplicates, ***p < 0.001. C,D) US28 levels in shGASP-1 infected and rGASP-1 transfected HEK 293 cells. HEK293 cells were infected and transiently transfected as described in A and B. The expression levels of US28 were assayed by ELISA as described before.