Guanylate binding proteins promote caspase-11-dependent pyroptosis in response to cytoplasmic LPS

Abstract

IFN receptor signaling induces cell-autonomous immunity to infections with intracellular bacterial pathogens. Here, we demonstrate that IFN-inducible guanylate binding protein (Gbp) proteins stimulate caspase-11-dependent, cell-autonomous immunity in response to cytoplasmic LPS. Caspase-11-dependent pyroptosis is triggered in IFN-activated macrophages infected with the Gram-negative bacterial pathogen Legionella pneumophila. The rapid induction of pyroptosis in IFN-activated macrophages required a cluster of IFN-inducible Gbp proteins encoded on mouse chromosome 3 (Gbp(chr3)). Induction of pyroptosis in naive macrophages by infections with the cytosol-invading ΔsdhA L. pneumophila mutant was similarly dependent on Gbp(chr3), suggesting that these Gbp proteins play a role in the detection of bacteria accessing the cytosol. Cytoplasmic LPS derived from Salmonella ssp. or Escherichia coli has recently been shown to trigger caspase-11 activation and pyroptosis, but the cytoplasmic sensor for LPS and components of the caspase-11 inflammasome are not yet defined. We found that the induction of caspase-11-dependent pyroptosis by cytoplasmic L. pneumophila-derived LPS required Gbp(chr3) proteins. Similarly, pyroptosis induced by cytoplasmic LPS isolated from Salmonella was diminished in Gbp(chr3)-deficient macrophages. These data suggest a role for Gbp(chr3) proteins in the detection of cytoplasmic LPS and the activation of the noncanonical inflammasome.

Keywords: Nos2; cell death; immunity-related GTPases; interferon.

Fig. 1.

Multiple IFN-induced responses restrict the growth of L. pneumophila in murine macrophages. (A–C) Naive and IFNγ–primed BMMs were infected with luminescent ΔflaA L. pneumophila at an MOI of 1, and bacterial growth was measured over 24 h. Data are shown as averages ± SD of three independent wells at 24 hpi. Unless otherwise indicated, cells were induced with 100 U/mL IFNγ overnight. (D) Naive and IFNγ–primed BMMs were treated with the caspase inhibitor z-Val-Ala-Asp-fluoromethylketone (zVAD) where indicated. Cells were infected with L. pneumophila at an MOI of 10, and LDH release was measured at 3 hpi. (E) L. pneumophila burden in QKO BMMs treated with zVAD compared with DMSO vehicle control at 24 hpi. (F) Bacterial burden in BMMs from the indicated mouse strains at 24 hpi. All values are averages ± SD from three independent wells. Statistical significance was calculated using the unpaired Student t test. Max, maximum; n.s., not significant; RLU, relative light units.

Fig. 2.

Pyroptosis triggered by L. pneumophila (L.p.) is dependent on Gbp^chr3. (A) BMMs from the indicated mouse strains were left untreated or activated with 100 U/mL IFNγ overnight. Cells were infected with L.p. at an MOI of 10 for 3 h, and LDH release was measured. (B) Fluorometric plots show propidium iodide (PI) uptake at 3 hpi. (C) Cell death was measured at 3 hpi in BMMs primed with IFNγ (100 U/mL) and infected with L.p. at an MOI of 10. (D) WT immortalized BMMs (iBMMs) were transduced with shRNAs against the indicated Gbp^chr3 targets and infected with L.p. at an MOI of 1, and LDH was measured at 3 hpi. shLacZ and shRFP were used as negative controls. (E) Cell death was measured in primary Gbp2^−/− BMMs infected with L.p. at MOIs of 10 and 1 at 3 hpi. (F) Cell lysates and supernatants (Sup) from WT and Gbp^chr3−/− BMMs were probed for caspase-11 by Western blot. Infections with L.p. were performed at an MOI of 10 for 3 h. (G) Growth of L.p. in naive or primed BMMs (100 U/mL IFNγ) infected at an MOI of 1 at 24 hpi. Values represent averages ± SD from three independent wells. Statistical significance was calculated using the unpaired Student t test (A–D, F, and G) and one-way ANOVA (E).

Fig. 3.

Gbp^chr3 proteins are important for recognizing cytosolic bacteria. (A) iBMMs expressing galectin-3 (Gal3)–YFP either uninduced or primed with 100 U/mL IFNγ were infected with ΔsdhAΔflaA and ΔflaA L.p. at an MOI of 2. Localization of Gal3-YFP to LCVs was quantified at 4 hpi. Values are shown as averages ± SEM from a total of 800 infected cells from two independent experiments. Significance between samples was calculated using one-way ANOVA. (B) Cell death at 3 hpi in naive or IFNγ–primed BMMs (100 U/mL) from the indicated mouse strains infected with ΔsdhAΔflaA L.p. at an MOI of 10. (C) Cell death at 3 hpi in LPS-activated BMMs (50 ng/mL) infected with ΔsifA S. Typhimurium at an MOI of 50. All values shown are averages ± SD of three independent wells. Statistical significance was calculated using one-way ANOVA (A and C) and the unpaired Student t test (B).

Fig. 4.

Gbp^chr3 promotes pyroptosis in response to the cytoplasmic delivery of Legionella LPS. Naive and activated BMMs were transfected with Legionella lysates (A), Legionella LPS (B), and LDH measured 3 h posttransfection (C). Naive and primed BMMs were infected with L. monocytogenes (MOI of 5) in the presence or absence of Legionella LPS. Data are shown as the average ± SD of three independent wells. Statistical significance between samples was measured using one-way ANOVA (A and B) and the unpaired Student t test (C).

Fig. 5.

Gbp^chr3 promotes pyroptosis in response to cytoplasmic LPS derived from E. coli and Salmonella. Naive and primed iBMMs were infected with L. monocytogenes (MOI of 5) in the presence or absence of E. coli O111:B4 for 2 h (A) or incubated with the indicated combinations of CTB (20 μg/mL) and O111:B4 (1 μg/mL) (B). Naive and primed BMMs were infected with L. monocytogenes (MOI of 5) in the presence or absence of S. minnesota LPS (C) or transfected with S. minnesota LPS (D) and assessed for cell viability at 4 h posttransfection. Data are shown as the average ± SD of three independent wells. Statistical significance between samples was measured using the unpaired Student t test (A–C) and one-way ANOVA (D).