Yersinia outer protein YopE affects the actin cytoskeleton in Dictyostelium discoideum through targeting of multiple Rho family GTPases

Abstract

Background: All human pathogenic Yersinia species share a virulence-associated type III secretion system that translocates Yersinia effector proteins into host cells to counteract infection-induced signaling responses and prevent phagocytosis. Dictyostelium discoideum has been recently used to study the effects of bacterial virulence factors produced by internalized pathogens. In this study we explored the potential of Dictyostelium as model organism for analyzing the effects of ectopically expressed Yersinia outer proteins (Yops).

Results: The Yersinia pseudotuberculosis virulence factors YopE, YopH, YopM and YopJ were expressed de novo within Dictyostelium and their effects on growth in axenic medium and on bacterial lawns were analyzed. No severe effect was observed for YopH, YopJ and YopM, but expression of YopE, which is a GTPase activating protein for Rho GTPases, was found to be highly detrimental. GFP-tagged YopE expressing cells had less conspicuous cortical actin accumulation and decreased amounts of F-actin. The actin polymerization response upon cAMP stimulation was impaired, although chemotaxis was unaffected. YopE also caused reduced uptake of yeast particles. These alterations are probably due to impaired Rac1 activation. We also found that YopE predominantly associates with intracellular membranes including the Golgi apparatus and inhibits the function of moderately overexpressed RacH.

Conclusion: The phenotype elicited by YopE in Dictyostelium can be explained, at least in part, by inactivation of one or more Rho family GTPases. It further demonstrates that the social amoeba Dictyostelium discoideum can be used as an efficient and easy-to-handle model organism in order to analyze the function of a translocated GAP protein of a human pathogen.

Figure 1

Kinetics of Yop expression in D. discoideum. (A) Expression of yopE was induced by removal of tetracycline (-Tet). At indicated time points (in hours), total RNA of 10⁷ cells was separated on 1.2% agarose/6.6% formaldehyde gels, transferred onto a nylon membrane, and probed with DIG-labeled yopE. (B) Expression of GFP-Yop fusion proteins. Expression was induced by removal of tetracycline (-Tet). At indicated time points (in hours), total cell protein from 5 × 10⁵ vegetative cells was separated on 15%polyacrylamide/0.1% SDS gels and blotted onto nitrocellulose. Blots were probed with a GFP-specific antibody.

Figure 2

YopE inhibits amoebial growth. Vegetative growth was measured in liquid cultures of cell lines with non-induced and induced expression of YopE, GFP-YopE, YopH, GFP-YopH, GFP-YopJ and GFP-YopM. Black squares: non-induced cell lines; grey circles: induced cell lines. For each growth curve, two independent cultures, each run in duplicate, were analyzed and averaged. Standard error bars are mostly smaller than symbol sizes.

Figure 3

YopE associates with intracellular membrane compartments. (A) YopE colocalizes with markers of intracellular membrane compartments. Cells expressing GFP-YopE were fixed in cold methanol and were incubated with monoclonal antibodies that recognize the Golgi marker comitin and the ER marker protein disulfide isomerase (PDI) followed by incubation with Cy3-labeled anti-mouse IgG. GFP is visualized directly. Images are confocal sections. Scale bar, 10 μm. (B) Fractionation of Dictyostelium cells expressing GFP-YopE. Cells were lysed by sonication and cytosolic and membrane fractions were separated by ultracentrifugation. Samples were resolved in 12% polyacrylamide gels, blotted onto nitrocellulose membranes and probed with antibodies against GFP, PDI (marker for the membrane fraction) and RhoGDI (marker for the cytososlic fraction). (C) Sucrose gradient fractionation of cells expressing GFP-YopE. Fractions were collected from the top and analyzed in Western blots using antibodies for the indicated proteins or in enzymatic reactions. Interaptin is a protein of the nuclear envelope and ER. RhoGDI is a predominantly cytosolic protein but a small amount appears associated to membrane compartments. Alkaline phosphatase is a marker for plasma membrane and the contractile vacuole and acid phosphatase is a marker for lysosomes.

Figure 4

Impaired phagocytosis in GFP-YopE expressing cells. (A) Cells were allowed to phagocytose TRITC-labeled yeast particles on coverslips for 30 minutes before fixation. Arrows indicate yeast particles internalized by Dictyostelium cells. Note that cells expressing large amounts of the GFP fusion have no internalized particles. Scale bar, 25 μm. (B) Cells were treated as in A and scored for the presence of internalized particles. Control cells are cells of the parental strain MB35 expressing GFP. The intensity of GFP expression was quantitated with Image J. The diagrams display the distribution of the corresponding cell population according to the GFP levels. The populations were divided in 10 equally large classes and the proportion of phagocytosing cells was calculated. 259 control and 271 GFP-YopE cells from 4 coverslips were scored. *P < 0.05 relative to the average proportion of phagocytosing cells in the control population.

Figure 5

Altered actin distribution in GFP-YopE expressing cells. (A) Induced GFP-YopE expressing cells were allowed to sit on glass coverslips, fixed and stained with actin-specific mAb Act 1–7 followed by Cy3-labeled anti-mouse IgG. Images are confocal sections. Note that cells expressing large amounts of the GFP fusion have visibly less cortical actin. Examples of intensity profiles across cells that express large amounts GFP-YopE (1, 2) or no visible GFP-YopE (3, 4) are shown. Scale bar, 10 μm. (B) Intensity profiles across cells stained with actin-specific antibody. Control cells are induced cells that do not express GFP-YopE. The fluorescence intensity was determined for 30 cells from two independent preparations and the distance between the maxima at the cell cortex normalized. Shown is the average ± standard deviation. For simplicity, error bars are depicted in one direction only. *P < 0.05, Student's t-test. (C) Relative F-actin content of vegetative cells as determined by TRITC-phalloidin staining. Values were normalized to the total protein content of the sample. Unaltered total actin amounts were verified by Western blotting of total cell lysates. (5 μg of total protein) probed with mAb Act1-7. Control cells are non-induced cells carrying the GFP-YopE plasmid. Data are average ± standard deviation of 6 independent determinations. *P < 0.05, Student's t-test.

Figure 6

Reduced actin polymerization response and Rac1 activation upon cAMP stimulation in YopE expressing cells. (A) Relative F-actin content as determined by TRITC-phalloidin staining of aggregation competent cells fixed at the indicated time points after stimulation with 1 μM cAMP. Control cells are non-induced cells carrying the GFP-YopE plasmid. The amount of F-actin was normalized relative to the F-actin level of unstimulated cells. Data are average ± standard deviation of 5 independent experiments. For simplicity, error bars are depicted only in one direction. *P < 0.05, Student's t-test. (B) Activation of Rac1 upon cAMP stimulation in cells expressing GFP-YopE. Rac1-GTP was separated using a pulldown assay. A representative blot of each strain is shown. Data are average ± standard deviation of four independent pull down experiments. *P < 0.05, Student's t-test.

Figure 7

YopE blocks the effects of RacH on growth and endocytosis. (A) Growth in nutrient medium. Cultures were inoculated at a density of 0.5 × 10⁶ cells/ml. The graph is representative of two independent experiments, each run in duplicate. * P < 0.05 of GFP-RacH relative to AX2, † P < 0.05 of GFP-RacH/myc-YopE relative to AX2; ANOVA. (B) Fluid-phase endocytosis of FITC-dextran. Cells were resuspended in fresh axenic medium at 5 × 10⁶ cells/ml in the presence of 2 mg/ml FITC-dextran. Fluorescence from the internalized marker was measured at selected time points. Data are presented as relative fluorescence, AX2 being considered 100%. Four independent experiments are averaged. For clarity, error bars are depicted only in one direction. * P < 0.05 relative to AX2, ANOVA.