TLR-dependent control of Francisella tularensis infection and host inflammatory responses

Abstract

Background: Francisella tularensis is the causative agent of tularemia and is classified as a Category A select agent. Recent studies have implicated TLR2 as a critical element in the host protective response to F. tularensis infection, but questions remain about whether TLR2 signaling dominates the response in all circumstances and with all species of Francisella and whether F. tularensis PAMPs are predominantly recognized by TLR2/TLR1 or TLR2/TLR6. To address these questions, we have explored the role of Toll-like receptors (TLRs) in the host response to infections with F. tularensis Live Vaccine Strain (LVS) and F. tularensis subspecies (subsp.) novicida in vivo.

Methodology/principal findings: C57BL/6 (B6) control mice and TLR- or MyD88-deficient mice were infected intranasally (i.n.) or intradermally (i.d.) with F. tularensis LVS or with F. tularensis subsp. novicida. B6 mice survived >21 days following infection with LVS by both routes and survival of TLR1(-/-), TLR4(-/-), and TLR6(-/-) mice infected i.n. with LVS was equivalent to controls. Survival of TLR2(-/-) and MyD88(-/-) mice, however, was significantly reduced compared to B6 mice, regardless of the route of infection or the subspecies of F. tularensis. TLR2(-/-) and MyD88(-/-) mice also showed increased bacterial burdens in lungs, liver, and spleen compared to controls following i.n. infection. Primary macrophages from MyD88(-/-) and TLR2(-/-) mice were significantly impaired in the ability to secrete TNF and other pro-inflammatory cytokines upon ex vivo infection with LVS. TNF expression was also impaired in vivo as demonstrated by analysis of bronchoalveolar lavage fluid and by in situ immunofluorescent staining.

Conclusions/significance: We conclude from these studies that TLR2 and MyD88, but not TLR4, play critical roles in the innate immune response to F. tularensis infection regardless of the route of infection or the subspecies. Moreover, signaling through TLR2 does not depend exclusively on TLR1 or TLR6 during F. tularensis LVS infection.

Figure 1. Survival of TLR^−/− and MyD88^−/− mice inoculated intranasally or intradermally with F. tularensis.

Groups of mice (•, B6; ○, B6129PF2/J; ♦, TLR2^−/−; □, TLR4^−/−; ▾,MyD88^−/−) were inoculated i.n. or i.d. with the indicated strains. The mice were monitored daily for 21 days for survival and signs of illness. Kaplan-Meier survival analyses were performed and survival was plotted as a function of time with each point representing the cumulative probability of survival for the indicated group. Error bars represent the standard error for the cumulative probability of survival. Significant differences among groups were determined by Log Rank analysis and individual p values were calculated by the Holm-Sidek method as described in Materials and Methods; p values of <0.05 were considered significant. (A) The i.n. inoculum for B6 and TLR2^−/− mice was 4,330 CFU of LVS; i.n. inoculum for B6129PF2/J mice was 6,183 CFU; n = 10. One representative experiment is shown of two independent experiments performed. *p = 0.001. (B) The i.n. inoculum was 5,360 CFU of LVS, n = 6. One representative experiment is shown of 2–4 independent experiments performed. *p = 0.001. (C) The i.d. inoculum was 38,680 CFU of LVS, n = 10. *p = 0.029. (D) The i.d. inoculum was 45,600 CFU, n = 6. *p = 0.055; **p = 0.001. (E) The i.n. inoculum was 4 CFU of F. tularensis subsp. novicida, n = 6. *p = 0.004; **p = 0.004.

Figure 2. Bacterial burdens in organs of mice following intranasal infection with F. tularensis LVS.

Groups of mice (•, B6; ♦, TLR2^−/−; ▾, MyD88^−/−) were inoculated intranasally with 5000 CFU of LVS and viable bacterial counts were determined in the lungs, livers, and spleens at days 3, 5, and 7 post-infection as described in Materials and Methods. Each data point represents the total CFUs recovered per mg of tissue from the indicated organs from an individual mouse. The median detectable CFU/mg of organ tissue in each group is indicated to the right of the symbols by a horizontal tick mark and the 75^th (upper) and 25^th (lower) percentiles are also indicated. The data are representative of four independent experiments. Significant differences among groups were determined by Kruskal-Wallis ANOVA on ranks as described in Materials and Methods; n = 5 mice per time-point, *p<0.05 compared to B6 controls.

Figure 3. Cytokine and chemokine expression by primary macrophages in response to F. tularensis LVS infection.

(A) Proteose peptone-elicited peritoneal macrophages from B6, TLR2^−/−, TLR4^−/−, and MyD88^−/− mice were infected with LVS (MOI of 120) or stimulated with E. coli LPS (10 µg/ml) as indicated. Culture supernatants were collected after 4 h, and cytokines were quantified by BD™ Cytometric Bead Array (CBA) Mouse Inflammation Kit (BD Biosciences Pharmingen, San Diego, CA). The data are expressed as the average cytokine level (pg/ml) (+SEM) in duplicate culture supernatants and are representative of 2–3 independent experiments. Significant differences among groups were determined by one-way ANOVA followed by Holm-Sidek post-hoc analysis; ^* p<0.01 compared to B6 macrophages infected with LVS, ^# p<0.01 compared to B6 macrophages stimulated with E. coli LPS. Cytokine and chemokine levels in supernatants from mock-infected cells were <20 pg/ml (data not shown). (B) Alveolar macrophages harvested by bronchoalveolar lavage were infected with LVS (MOI of 80) and culture supernatants were collected at 4 h. TNF expression was analyzed by ELISA as described in Materials and Methods. The data are expressed as the average TNF level (pg/ml) (+SEM) in duplicate culture supernatants, ^* p<0.01. TNF levels in supernatants from mock-infected cells were <20 pg/ml (data not shown).

Figure 4. TNF expression in the lungs of mice infected i.n. with F. tularensis LVS.

(A) Groups of 3–4 mice from the indicated strains were infected intranasally with 6,000 CFU of LVS. At day 5 post-infection, BALF was recovered from each mouse and cytokine levels quantified by BD™ Cytometric Bead Array (BD Biosciences, San Diego, CA). The data are expressed as the average cytokine level (+ SEM) from 3–4 individual mice. Significant differences among groups were determined by Kruskal-Wallis ANOVA on ranks followed by Dunn's post-hoc analysis; ^* p<0.05. (B) Groups of 2–3 B6, MyD88^−/− and TLR2^−/− mice were infected i.n. with 3,600 CFU of LVS or mock-infected and sacrificed after 1, 3, and 5 days post-infection. Lung tissue cryosections were prepared at the indicated time points and stained with purified goat anti-TNF (red) followed by Rhodamine Red-X-conjugated anti-goat Ig and analyzed by in situ immunofluorescence microscopy. Nuclei of cells (blue) were visualized via staining with 4′6′diamidino-2-phenylindole-dilactate (DAPI). The same sections were also stained for bacteria (green) with Alexa488-conjugated mouse anti-LVS LPS. Representative images from 2–3 mice are shown. Magnification for all images is 400×.

Figure 5. Survival rates and cytokine expression of TLR1^−/− and TLR6^−/− mice infected with F. tularensis LVS.

(A) Survival curves are shown for intranasal infections with LVS. The data shown were pooled from two independent experiments with the i.n. inocula and group sizes as indicated: B6 (6,200 CFU, n = 10), TLR1^−/− (6,200 CFU, n = 10), TLR6^−/− (9,700 CFU, n = 10). (B) Proteose peptone-elicited peritoneal macrophages from B6, TLR1^−/−, and TLR6^−/− mice were infected with LVS (MOI of 120), supernatants were collected from cultures at 4 h, and cytokines were quantified by BD™ Cytometric Bead Array (CBA) Mouse Inflammation Kit (BD Biosciences Pharmingen, San Diego, CA). The data are expressed as the average cytokine level (pg/ml) (+ SEM) in triplicate culture supernatants and are representative of 2–3 independent experiments. Significant differences among groups were determined by one-way ANOVA followed by Holm-Sidek post-hoc analysis; ^*p<0.01. Cytokine and chemokine levels in supernatants from mock-infected cells were <20 pg/ml (data not shown).