Host responses to intestinal microbial antigens in gluten-sensitive mice

Abstract

Background and aims: Excessive uptake of commensal bacterial antigens through a permeable intestinal barrier may influence host responses to specific antigen in a genetically predisposed host. The aim of this study was to investigate whether intestinal barrier dysfunction induced by indomethacin treatment affects the host response to intestinal microbiota in gluten-sensitized HLA-DQ8/HCD4 mice.

Methodology/principal findings: HLA-DQ8/HCD4 mice were sensitized with gluten, and gavaged with indomethacin plus gluten. Intestinal permeability was assessed by Ussing chamber; epithelial cell (EC) ultra-structure by electron microscopy; RNA expression of genes coding for junctional proteins by Q-real-time PCR; immune response by in-vitro antigen-specific T-cell proliferation and cytokine analysis by cytometric bead array; intestinal microbiota by fluorescence in situ hybridization and analysis of systemic antibodies against intestinal microbiota by surface staining of live bacteria with serum followed by FACS analysis. Indomethacin led to a more pronounced increase in intestinal permeability in gluten-sensitized mice. These changes were accompanied by severe EC damage, decreased E-cadherin RNA level, elevated IFN-gamma in splenocyte culture supernatant, and production of significant IgM antibody against intestinal microbiota.

Conclusion: Indomethacin potentiates barrier dysfunction and EC injury induced by gluten, affects systemic IFN-gamma production and the host response to intestinal microbiota antigens in HLA-DQ8/HCD4 mice. The results suggest that environmental factors that alter the intestinal barrier may predispose individuals to an increased susceptibility to gluten through a bystander immune activation to intestinal microbiota.

Figure 1. Intestinal barrier measurements.

Ussing-chamber experiments were performed on jejunum from all four groups 24 hours after the last gluten challenge. (A) Gluten-sensitized mice treated with indomethacin showed a significant increase in tissue conductance. (B) HRP flux (transcellular permeability) increased significantly in all treatment groups compared to non-sensitized controls, however the highest values were observed in gluten plus indomethacin treated mice. Data represent the means±SEM of 10 mice/group.

Figure 2. Evaluation of mitochondrial disruption.

Mitochondrial ultra-structure was assessed by electron microscopy. Indomethacin increased the fraction of disrupted mitochondria. Gluten sensitization plus indomethacin treatment further increased the proportion of altered mitochondria. Data represent the means±SEM of 6 mice/group. Reperesentative pictures from (A) Control mouse, arrow: normal mitochondria; (B) Gluten-sensitized mouse; (C) Indomethacin-treated mouse, arrowhead: mitochondria with disrupted cristae; (D) Indomethacin-treated plus gluten-sensitized mouse, arrowhead: mitochondria with disrupted cristae.

Figure 3. Apical epithelial cell structural abnormalities.

Epithelial ultra-structure was assessed by electron microscopy. A significant proportion of altered TJ was observed in gluten-sensitized plus indomethacin-treated mice. Indomethacin alone also increased the proportion of altered TJ but to a lesser extent than indomethacin plus gluten. Gluten sensitization alone tended to increase the proportion of altered TJ but this did not achieve statistical significance (p = 0.09 vs non-sensitized controls). Data represent the means±SEM of 5 mice/group. Representative pictures of (A–B) a control mouse, arrow: tight junction (TJ) with preserved structure; (C) Gluten-sensitized mouse, arrow: TJ with preserved structure; (D) Indomethacin-treated mouse showing one altered TJ (arrowhead) and 2 junctions with normal struture (arrows); (E–G) Gluten plus indometacin treated mouse; (E) arrowhead: microvilli (mv) height reduction, arrow: apical epithelial cell destruction; (F) Altered TJ, arrow: mitochondria (m) with disrupted cristae; (G) Several altered TJs.

Figure 4. RNA level of E-cadherin relative to control (non-sensitized).

Real-time QPCR experiments were performed on jejunum collected from all groups 24 hours after the last gluten challenge. Gluten-sensitized and indomethacin alone-treated mice showed a trend for decreased expression of E-cadherin relative to non-sensitized controls. Gluten-sensitized plus indomethacin-treated mice showed marked down-regulation of E-cadherin RNA level relative to non-sensitized controls. Data represent the means±SEM of 6 mice/group.

Figure 5. Splenocyte proliferation after incubation with PT gliadin.

Proliferation was measured by ³H-thymidine incorporation and expressed as stimulation index. Splenocytes from gluten-sensitized mice treated with or without indomethacin exhibited increased proliferation compared to non-sensitized controls. Data represent the means±SEM of 6 mice/group.

Figure 6. Cytokines in supernatant of splenocyte cultures after incubation with PT-gliadin (black) or medium (white).

Expressions of (A) IL-12p70, (B) IFN-γ, (C) IL-10 were determined by CBA analysis. Culture supernatants from gluten-sensitized plus indomethacin (Indo) treated mice showed increased IFN- γ (*p<0.01 vs all groups). Cultured splenocytes from gluten-sensitized mice, with or without indomethacin showed a trend for increased IL-10 release after PT-gliadin stimulation (p = 0.09). Data represent the means±SEM of 6 mice/group.

Figure 7. Microbiota composition.

Using 9 different oligonucleotide probes and fluorescent in situ hybridization (FISH), microbial profile was investigated in the distal jejunum of sensitized mice with and without indomethacin. The results indicate a significant perturbation in the proportions of microbiota investigated in all 3 treatment-groups when compared to non-sensitized controls, and remarkably in the gluten-sensitized plus indomethacin group. These differences achieve statistical significance in Bifidobacteria (*p = 0.04 vs controls, +p = 0.03 vs gluten) and Clostridium Leptum cluster (both *p = 0.02 vs controls and gluten sensitized, **p = 0.04 vs indomethacin) compared to gluten-sensitized alone. Data represent the means±SEM of 6 mice/group.

Figure 8. Systemic antibodies against commensals.

Serum from indomethacin and gluten treated mice showed significant positive serum antibodies against their aerobic and anaerobic intestinal microbiota. (A) Representative FACS histogram from each treatment gated on IgM⁺ cells; (B) Proportion of IgM⁺ aerobic bacterial cells for each treatment groups; (C) Proportion of IgM⁺ anaerobic bacterial cells for each treatment groups. Data represent the means±SEM of 6 mice/group.