Cdc42 regulates microtubule-dependent Golgi positioning

Abstract

The molecular mechanisms underlying cytoskeleton-dependent Golgi positioning are poorly understood. In mammalian cells, the Golgi apparatus is localized near the juxtanuclear centrosome via dynein-mediated motility along microtubules. Previous studies implicate Cdc42 in regulating dynein-dependent motility. Here we show that reduced expression of the Cdc42-specific GTPase-activating protein, ARHGAP21, inhibits the ability of dispersed Golgi membranes to reposition at the centrosome following nocodazole treatment and washout. Cdc42 regulation of Golgi positioning appears to involve ARF1 and a binding interaction with the vesicle-coat protein coatomer. We tested whether Cdc42 directly affects motility, as opposed to the formation of a trafficking intermediate, using a Golgi capture and motility assay in permeabilized cells. Disrupting Cdc42 activation or the coatomer/Cdc42 binding interaction stimulated Golgi motility. The coatomer/Cdc42-sensitive motility was blocked by the addition of an inhibitory dynein antibody. Together, our results reveal that dynein and microtubule-dependent Golgi positioning is regulated by ARF1-, coatomer-, and ARHGAP21-dependent Cdc42 signaling.

Figure 1. Dynein-dependent Golgi positioning involves ARHGAP21

(A) Hela cells were transfected with siRNA against ARHGAP21 or a control siRNA against luciferase as indicated. The cells were treated with nocodazole (20 μM) for 5 hours to disperse the Golgi apparatus, and the nocodazole was washed away for the indicated time. At each time point, cells were fixed and Golgi membranes were labeled with GM130 antibody. Shown are confocal micrographs. (B) Hela cells were transfected with siRNA as in (A). After 24 hours the cells were transferred to new plates and transfected with plasmids encoding GFP-ARFBD/GAP domain of ARHGAP21 or GFP alone as indicated. The cells were fixed after 24 additional hours and decorated with antibodies against the Golgi marker, GM130. The size bar equals 5 μm. (C) The fraction of cells containing a compact Golgi apparatus at 1 hour after nocodazole washout was determined for ARHGAP21 and luciferase siRNA expressing HelA cells. The GM130-labeled Golgi complex was defined as compact if it could fit inside a circle with a diameter of 10 μm. Shown is the average from 3 experiments; the bars indicate standard error. (D) The number of Golgi particles per cell was determined using a particle counter plugin for ImageJ. Shown is the average from 3 experiments of 10 cells each; the bars indicate standard error. There was no significant change in the average number of particles/cell before nocodazole washout (p=0.3245). After the one hour nocodazole washout, cells treated with ARHGAP21 siRNA had significantly more particles than cells treated with luciferase siRNAs (p<0.006).

Figure 2. Microtubule-dependent Golgi positioning requires Rho GTPases

(A) NRK cells were treated with nocodazole for 2 hours. 100 ng/ml Toxin B was added as the nocodazole was washed out. Shown are confocal micrographs of cells that were fixed at the indicated time points and decorated with anti-GM130 antibody. The size bars represent 5 μm. (B–C) Golgi motility in living NRK cells was quantified by incubation with NBD-C6 ceramide prior to nocodazole addition. 100 ng/ml Toxin B (B) or 2 μg/ml C3 transferase (C) was added during the nocodazole wash out. A peripheral region of interest was defined for each cell and the change in peripheral fluorescence was recorded for 25 minutes at 37°C. The mean fluorescence intensity within the region of interest is plotted as a function of time; n=3 experiments for (B,C). The standard error in each case is indicated by bars.

Figure 3. Golgi positioning depends on ARF1 activity and coatomer

(A) NRK cells were treated with nocodazole for 2 hours. 10 μM brefeldin A (BFA) was added as the nocodazole was washed out. Shown are confocal micrographs of cells that were fixed at the indicated time points and decorated with anti-GM130 antibody. The size bars represent 20 μm. (B–C) Golgi motility in living NRK cells was quantified by incubation with NBD-C6 ceramide prior to nocodazole addition. 10 μM brefeldin A (B), or 50 μM BAPTA-AM (C) was added during the nocodazole wash out. A peripheral region of interest was defined for each cell and the change in peripheral NBD fluorescence was recorded for 25 minutes at 37°C. The mean fluorescence intensity within the region of interest is plotted as a function of time. The number of experiments is n=3 for (B and C). The standard error in each case is indicated by bars. (D) Shown are confocal micrographs of NRK cells transfected with pEGFP-C1, pEGFP-p23 (199–212), and pEGFP-p23(199–212, KK-AA). Cells expressing the GFP constructs are marked with an asterisk. The cells were pretreated for 2 hours with 20 μM nocodazole. Nocodazole was washed off, and the cells were incubated for 20 minutes before fixation and decoration with a mouse polyclonal antibody against the Golgi marker, GM130. The bar represents 10 μm. (E) The percentage of cells with juxtanuclear Golgi membranes at the 20-minute time point was determined after cells were scored in a blind manner. The average of 4 experiments is plotted. The bars indicate standard error. The percentage of cells displaying juxtanuclear Golgi is significantly increased in the presence of GFP-p23 (p<0.05).

Figure 4. Exogenous Golgi membranes bind permeabilized cells

(A) NRK cells were mock treated or permeabilized by a freeze/thaw cycle as indicated. Rat-liver Golgi particles were incubated with cytosol, GTPγS, and an ATP-regenerating system then labeled with bodipy-C5-ceramide (red), and added to the permeabilized cells at 37°C. The nuclei were labeled using DRAQ5 (blue). In two independent experiments, no exogenous membranes were found bound to intact cells (n=20 cells) while an average of 0.6 membrane particles was observed per permeabilized cell (n=19 cells). The bar represents 10 μm. (B) Permeabilized Vero cells were incubated with rat-liver Golgi membranes (red). The cells were fixed and the endogenous Golgi membranes were decorated with a primate-specific antibody against giantin (green). The nuclei were labeled using DRAQ5 (blue).

Figure 5. Exogenous Golgi membranes undergo microtubule-dependent entry into permeabilized cells

(A) Shown are confocal micrographs of NRK cells that were fixed at the indicated time points relative to permeabilization and incubation. The cells were decorated with antibodies against the Golgi marker GM130 (green) and microtubules (red). The nuclei were labeled using DRAQ5 (blue). (B) Shown are confocal micrographs indicating actin distribution at the indicated time points relative to the permeabilization and incubation. (C) NRK cells were either mock treated (control) or incubated with 20 μM nocodazole before and after permeabilization. Rat-liver Golgi membranes (red) and cytosol were added to the cells, and cell-associated membranes were visualized by confocal microscopy. The bar represents 20 μm. (D) NRK cells were treated as in (C) and the average number of Golgi particles per cell was determined from four independent experiments by blind counting with (n=85 cells) or without (n=111 cells) nocodazole treatment. The standard error is indicated by bars.

Figure 6. p23 peptide, recombinant PBD, and cytochalasin D stimulate dynein-dependent Golgi motility

(A) Shown are merged images of confocal micrographs taken at an initial time point (0 seconds; red), 2.5 seconds (yellow), and 5 seconds (green) after incubating rat-liver Golgi membranes with permeabilized NRK cells. Prior to their addition to the NRK cells, the membranes were incubated with p23 peptide or cytochalasin D as indicated. Nuclei were labeled with 10 μM DRAQ5. The bar represents 10 μm. (B) Golgi membranes were treated with or without the p23 peptide and incubated with permeabilized cells. The velocities of Golgi particles was calculated and plotted as a histogram representing the average from 3 independent experiments. A total of 109 particles associated with 53 cells (minus peptide) and 65 particles associated with 54 cells (plus peptide) were analyzed. The standard error is indicated by bars. (C) The fraction of motile Golgi particles during a five second interval was determined for recombinant PBD (5 μg/ml) or mock-treated membranes. Over three independent experiments, 56 Golgi particles associated with 45 cells (minus PBD) and 54 particles associated with 48 cells (plus PBD) were analyzed. PBD treatment significantly increased the fraction of motile membrane particles (p<0.04). (D) The fraction of motile Golgi membranes was determined following mock or cytochalasin D (CytoD) treatment. Over three independent experiments, 226 Golgi particles associated with 77 cells (minus CytoD), and 273 particles associated with 59 cells were analyzed. The standard error is indicated by bars. Cytochalasin D significantly increases the fraction of motile particles (p<0.05). (E) Rat-liver Golgi membranes were incubated using reaction conditions identical to those used for the motility assay shown in panels A-D. Following the incubation, the Golgi membranes were reisolated by centrifugation and processed for SDS-PAGE. Western blot analysis was used to determine the levels of β-COP, dynein, and Cdc42 as indicated. (F) The fraction of motile Golgi membrane particles was determined after mock treatment (176 particles associated with 100 cells), treatment with the inhibitory dynein antibody 70.1 (199 particles; 114 cells), treatment with the p23 peptide (235 particles; 123 cells), or treatment with both (206 particles; 130 cells). Plotted are the averages from three independent experiments. The standard error is indicated by bars. The anti-dynein antibody significantly inhibits p23-stimulated motility (p<0.05).