Activation of the unfolded protein response is required for defenses against bacterial pore-forming toxin in vivo

Abstract

Pore-forming toxins (PFTs) constitute the single largest class of proteinaceous bacterial virulence factors and are made by many of the most important bacterial pathogens. Host responses to these toxins are complex and poorly understood. We find that the endoplasmic reticulum unfolded protein response (UPR) is activated upon exposure to PFTs both in Caenorhabditis elegans and in mammalian cells. Activation of the UPR is protective in vivo against PFTs since animals that lack either the ire-1-xbp-1 or the atf-6 arms of the UPR are more sensitive to PFT than wild-type animals. The UPR acts directly in the cells targeted by the PFT. Loss of the UPR leads to a normal response against unrelated toxins or a pathogenic bacterium, indicating its PFT-protective role is specific. The p38 mitogen-activated protein (MAPK) kinase pathway has been previously shown to be important for cellular defenses against PFTs. We find here that the UPR is one of the key downstream targets of the p38 MAPK pathway in response to PFT since loss of a functional p38 MAPK pathway leads to a failure of PFT to properly activate the ire-1-xbp-1 arm of the UPR. The UPR-mediated activation and response to PFTs is distinct from the canonical UPR-mediated response to unfolded proteins both in terms of its activation and functional sensitivities. These data demonstrate that the UPR, a fundamental intracellular pathway, can operate in intrinsic cellular defenses against bacterial attack.

Figure 1. The IRE-1 UPR is activated in response to PFTs.

(A) xbp-1 mRNA splicing is induced in wild-type C. elegans fed E. coli expressing Cry5B compared to control E. coli not expressing Cry5B. The time the worms were allowed to feed on the E. coli before total RNA was prepared for RT-PCR is indicated at the top, and the positions of the nucleotide size markers are indicated at the left. (B) Compared to worms fed control non-Cry5B expressing E. coli, in vivo activation of hsp-4::GFP occurs specifically in the intestines of worms fed Cry5B expressing E. coli at 20°C for 8 hours. As a comparison for GFP induction, separate worms on control bacteria were heat shocked at 30°C for 8 hours to induce the ER stress response by causing unfolded proteins. The heat shock worms have a strong increase in GFP throughout the body including the head, intestine and hypodermis. Thus, although the entire worm is capable of activating the ire-1-xbp-1 pathway as judged by hsp-4 induction, activation in Cry5B-fed animals is occurring only in those cells targeted by the PFT. Images taken by light microscopy are compared to images with fluorescence microscopy. Scale bar is 0.2 mm. The experiment was performed three times, and representative worms are shown. (C) Aerolysin induces activation of IRE1 in mammalians cells. Exposure of HeLa cells to proaerolysin (2 ng/mL) leads to increased production of spliced XBP1 protein as shown on this immunoblot (upper) and quantitated relative to no toxin control (lower). DTT (10 µg/mL for 2 h) was used as a positive control. Positions of molecular weight markers (kDa) are indicated on right side of the figure. A nonspecific antibody-reacting band was used as a loading control and normalization of the XBP1 signal in each lane.

Figure 2. Loss of specific UPR pathways cause hypersensitivity to PFT but not other toxins or a pathogenic bacteria.

(A) Comparison of ER stress response mutants to wild-type N2 on 25% Cry5B-expressing E. coli plates indicate ire-1(v33) and xbp-1(zc12) are hypersensitive to Cry5B intoxication. Two representative worms are shown for each strain 48 hours after feeding either on E. coli without Cry5B or on E. coli of which 25% expressed Cry5B. Scale bar is 0.2 mm. (B) A lethal concentration assay was performed using purified Cry5B toxin to quantitatively compare sensitivities of wild-type N2 and the ER stress mutants. Lethality was determined after 8 days. This semi-log graph represents three independent experiments, and each data point is the mean and standard deviations of the experiments. (C) A Cry5B developmental inhibition assay was performed beginning with synchronized worms at the first larval stage. Worms were grown on plates containing different percentages of Cry5B-expressing E. coli (% Cry5B as indicated under the figure), and the percent of worms reaching the L4 stage or adulthood 72 hours later is indicated. ire-1(v33) was included only on the plates with 0% Cry5B. Data are presented as mean and standard deviation. (D) A lethal concentration assay comparing sensitivity to CuSO₄ revealed xbp-1(zc12) is not hypersensitive compared to wild-type N2. Lethality was determined after 8 days of CuSO₄ exposure, the same time frame as the Cry5B lethality assay. Data, plotted semi-log, are the mean and standard deviation of three independent experiments. (E) A lethal concentration assay comparing sensitivity to H₂O₂ revealed xbp-1(zc12) is not hypersensitive compared to wild-type N2. Lethality was determined after 4 hours of H₂O₂ exposure. Data, plotted semi-log, are the mean and standard deviation of three independent experiments. (F) A lifespan assay was used to compare the ER stress mutants to slow killing by P. aeruginosa PA14. This graph represents combined data from three experiments.

Figure 3. Intestinal specific expression of xbp-1 is sufficient to rescue sensitivity to the PFT.

Sensitivity to Cry5B was compared among wild-type N2, xbp-1(zc12), xbp-1(zc12) transformed with app-1::GFP, and xbp-1(zc12) transformed with app-1::xbp-1 animals using a plate feeding assay. (A) The health of the worms (details in Materials and Methods) was evaluated after 72 hours on 25% Cry5B-expressing E. coli. Three and six independent lines of app-1::GFP and app-1::xbp-1 were used, respectively. Data are mean and standard deviation of three experiments. (B) Images comparing the health of wild-type N2, xbp-1(zc12), xbp-1(zc-12) app-1::GFP, and xbp-1(zc-12) app-1::xbp-1 animals on 25% Cry5B plates for 72 h. Scale bar is 0.2 mm.

Figure 4. The ER stress response mutants differ in their sensitivities to tunicamycin.

A lethality assay was used to compare sensitivities of the ER stress mutants and wild-type N2 to tunicamycin. The percent of worms alive after 8 days of exposure to each concentration of tunicamycin was determined. Data are the mean and standard deviation of three independent experiments.

Figure 5. Relationship of the p38 MAPK and UPR pathways in response to PFT and unfolded proteins.

(A) The xbp-1 pathway is not required for phosphorylation of p38 MAPK by Cry5B. Wild-type N2 and xbp-1(zc12) were exposed to either control buffer or purified Cry5B toxin for one hour. Worm lysates were analyzed by immunoblotting for phospho P38 MAPK along with α-tubulin as a loading comparison. Positions of molecular weight markers in kilodaltons are shown on left side of gel. Data are representative of three independent experiments. (B) Cry5B induced splicing of xbp-1 requires sek-1 (MAPKK). Splicing of xbp-1 mRNA was compared in glp-4(bn2) and glp-4(bn2);sek-1(km4) after 3 hours of exposure to either control E. coli or E. coli expressing Cry5B. Size markers in nucleotides are indicated on the left. This is a representative experiment of three independent experiments. (C) Tunicamycin induced splicing of xbp-1 does not require sek-1 (MAPKK). Splicing of xbp-1 mRNA was compared in glp-4(bn2) and glp-4(bn2);sek-1(km4) after 3 hours of exposure to either control (DMSO) or tunicamycin (2 µg/mL). This is a representative experiment of three independent experiments. (D) In vivo induction of hsp-4::GFP by Cry5B requires pmk-1 (p38 MAPK). The strains hsp-4::GFP and hsp-4::GFP;pmk-1(km25) were fed either control E. coli or E. coli expressing Cry5B for 8 hours and the expression of GFP was then analyzed. Cry5B induces GFP within the intestinal cells of the strain hsp-4::GFP but not in the strain containing the pmk-1(km25) mutant. The experiment was performed three times and representative worms are shown. Scale bar is 0.2 mm. (E) In vivo induction of hsp-4::GFP by tunicamycin does not require pmk-1 (p38 MAPK). The strains hsp-4::GFP and hsp-4::GFP;pmk-1(km25) were exposed to either control (DMSO) or tunicamycin (2 µg/mL) for 8 hours and the expression of GFP was then analyzed. Tunicamycin induces GFP throughout both the strains hsp-4::GFP and hsp-4::GFP;pmk-1(km25), including within the intestinal cells. The experiment was performed three times and representative worms are shown. Scale bar is 0.2 mm. (F) Downstream targets of the UPR require the p38 MAPK pathway for induction by PFT but not unfolded proteins. The fold change in the levels of hsp-4 and Y41C4A.11 mRNA transcripts by Cry5B and tunicamycin were determined for glp-4(bn2), glp-4(bn2);xbp-1(zc12) and glp-4(bn2);sek-1(km4) using real-time PCR. In addition, the fold change in ttm-2 transcripts was determined in response to Cry5B. Data are mean and standard deviation of three independent experiments. (G) Animals lacking sek-1 MAPKK are more sensitive to Cry5B than animals lacking xbp-1. Wild-type N2, sek-1(km4), and xbp-1(zc12) animals were placed on plates spread with E. coli transformed with empty vector (0%) or spread with empty vector E. coli diluted 9∶1 (10%) or 3∶1 (25%) with Cry5B-expressing E. coli (% thus gives toxin dose on a plate relative to undiluted Cry5B-expressing E. coli). The assay was initiated with L4 stage worms and photographs were taken 48 hours later. In the absence of Cry5B, the worms developed into dark, gravid, active, healthy adults. On 10% Cry5B-expressing E. coli, xbp-1(zc12) were slightly smaller than N2 but healthier than sek-1(km4), which were as small, pale, inactive, and severely intoxicated. On 25% Cry5B-expressing E. coli, xbp-1(zc12) was more intoxicated than N2 but not as intoxicated as sek-1(km4) animals. Scale bar is 0.2 mm.

Figure 6. Schematic illustrating relationship between p38 MAPK, ire-1-xbp-1, and PFT defense pathways.

PFTs at the cell surface of epithelial cells activate p38 MAPK that activates IRE-1 that induces splicing of xbp-1, which then turns on defense against PFTs. Residual activation of xbp-1 targets in the absence of the p38 MAPK pathway suggests there might be p38-independent activation of the ire-1-xbp-1 pathway in response to PFT as well (not shown). Independent of IRE-1 activation, p38 MAPK can also activate TTM-2 and other PFT defenses. Tunicamycin, which causes the accumulation of unfolded proteins in the ER, activates IRE-1 via a mechanism independent of the PFT and p38 MAPK.