The Legionella pneumophila effector protein, LegC7, alters yeast endosomal trafficking

Abstract

The intracellular pathogen, Legionella pneumophila, relies on numerous secreted effector proteins to manipulate host endomembrane trafficking events during pathogenesis, thereby preventing fusion of the bacteria-laden phagosome with host endolysosomal compartments, and thus escaping degradation. Upon expression in the surrogate eukaryotic model Saccharomyces cerevisiae, we find that the L. pneumophila LegC7/YlfA effector protein disrupts the delivery of both biosynthetic and endocytic cargo to the yeast vacuole. We demonstrate that the effects of LegC7 are specific to the endosome:vacuole delivery pathways; LegC7 expression does not disrupt other known vacuole-directed pathways. Deletions of the ESCRT-0 complex member, VPS27, provide resistance to the LegC7 toxicity, providing a possible target for LegC7 function in vivo. Furthermore, a single amino acid substitution in LegC7 abrogates both its toxicity and ability to alter endosomal traffic in vivo, thereby identifying a critical functional domain. LegC7 likely inhibits endosomal trafficking during L. pneumophila pathogenesis to prevent entry of the phagosome into the endosomal maturation pathway and eventual fusion with the lysosome.

Figure 1. Residue N242 is required for LegC7 toxicity in yeast.

(A) BY4742 yeast strains harboring the galactose-inducible control plasmid pYES2/NT C, pVJS52 (LEGC7 ⁺), or pVJS54 (LEGC7 ^N242I) were spotted onto CSM-uracil medium supplemented with either 2% glucose or 2% galactose with 10-fold serial dilutions from a starting culture of OD₆₀₀ = 1.0. Plates were incubated for 72 h at 30°C. (B) Strains from (A) were grown in for 24 h in CSM-uracil supplemented with 2% glucose at 30°C, washed in ddH₂O, suspended in fresh CSM-uracil/2% galactose, and incubated at 30°C for 16 h. Equal fractions of each strain were harvested, total protein was extracted [55], and 30μl from each sample was separated by SDS-PAGE. Samples were immunoblotted for LegC7 (rabbit 1:5000) or Sec17p (Rabbit, 1:1000) [56] (loading control). (C) The LEGC7 ⁺ plasmid, pVJS52, was mutagenized via site-directed mutagenesis (Materials and Methods), transformed into BY4742, and spotted onto CSM-Ura medium containing either 2% glucose or 2% galactose in 10-fold serial dilutions. (D) Diagram of the predicted LegC7 protein structure indicating transmembrane domain (TM, red) and three predicted coiled coil domains (CC, blue). Transmembrane prediction was calculated with TMHMM Server v.2.0 (http://www.cbs.dtu.dk/services/TMHMM/,) and coiled coil predictions were calculated with COILS (http://toolkit.tuebingen.mpg.de/pcoils) with a window size of 21, weighting, and an iterated matrix. (E) Coiled coil probability prediction of LegC7 containing either N, I, or D at position 242 were run as in (D). Probabilities at each position were plotted and the predicted disordered region between predicted coiled coil regions 1 and 2 is marked (red arrow).

Figure 2. LegC7 induces endosome:vacuole trafficking defects.

(A) BY4742 yeast strains harboring GFP-CPS and either the vector control, LEGC7 ⁺, or LEGC7 ^N242I plasmids were grown in selective media supplemented with 2% glucose at 30°C, washed in ddH₂O, suspended in fresh CSM-uracil/2% galactose, incubated at 30°C for 16 h, then visualized. (B) Equal portions of total proteins were extracted from strains in (A), then immunoblotted for GFP and Sec17p (loading control). (C) BY4742 yeast strains containing GFP-Sna3 and either the vector control, LEGC7 ⁺, or LEGC7 ^N242I plasmids were grown as in (A), then visualized. (D) Cells containing the vector control, LEGC7 ⁺, or LEGC7 ^N242I plasmids were incubated with Lucifer Yellow (Materials and Methods), and then visualized. (E) Strains from (D) were grown in selective media supplemented with 2% glucose at 30°C, washed in ddH₂O, suspended in fresh CSM-uracil/2% galactose, incubated at 30°C for 16 h, then stained with the yeast vacuolar marker FM4–64 [57] and visualized. (F) Wild type SEY6210 or ∆4+ENTH (Table 1) strains harboring Ste3-GFP and either the vector control or LEGC7 ⁺ plasmids were grown as in (A) and then visualized.

Figure 3. LegC7 does not delay non-endosomal vacuolar traffic.

(A) Wild type yeast strains expressing GFP-Vam3 [58] and expressing either LEGC7 ⁺ or LEGC7 ^N242I were grown in selective media supplemented with 2% glucose at 30°C, washed in ddH₂O, suspended in fresh CSM-uracil-lysine/2% galactose, incubated at 30°C for 16 h, then visualized. (B) Wild type or atg19∆ cells expressing either LEGC7 ⁺ or LEGC7 ^N242I were grown in selective media containing 2% glucose at 30°C, washed in ddH₂O, suspended in fresh CSM-uracil/2% galactose, incubated at 30°C for 16 h, and total proteins were extracted from equal fractions. Proteins were separated and immunoblotted for Ape1p (Rabbit 1:2000) [39] and LegC7.

Figure 4. Deletion of VPS27 reduces LegC7 toxicity.

(A) BY4742 or vps27∆ strains harboring either the control or LEGC7 ⁺ plasmids were spotted onto CSM-Ura plates containing 2% glucose or 2% galactose in 10-fold serial dilutions (starting OD₆₀₀ = 1.0) and grown at 30°C for 96h. (B) BY4742 or vps27∆ strains expressing GFP or GFP-LegC7 were grown in selective media supplemented with 2% glucose at 30°C, stained with FM4–64, and visualized for GFP and FM4–64 fluorescence. (C) Yeast vps27∆ strains expressing either GFP-CPS or Sna3-GFP harboring the LEGC7 ⁺ expression plasmid or vector control were grown in selective media supplemented with 2% glucose at 30°C, washed in ddH₂O, suspended in fresh CSM-uracil-lysine/2% galactose, incubated at 30°C for 16 h, then visualized. (D) Cells expressing GFP-Vps27 and LegC7 were grown as in (C), and localization of GFP-Vps27 was determined.