Protective mucosal immunity mediated by epithelial CD1d and IL-10

Abstract

The mechanisms by which mucosal homeostasis is maintained are of central importance to inflammatory bowel disease. Critical to these processes is the intestinal epithelial cell (IEC), which regulates immune responses at the interface between the commensal microbiota and the host. CD1d presents self and microbial lipid antigens to natural killer T (NKT) cells, which are involved in the pathogenesis of colitis in animal models and human inflammatory bowel disease. As CD1d crosslinking on model IECs results in the production of the important regulatory cytokine interleukin (IL)-10 (ref. 9), decreased epithelial CD1d expression--as observed in inflammatory bowel disease--may contribute substantially to intestinal inflammation. Here we show in mice that whereas bone-marrow-derived CD1d signals contribute to NKT-cell-mediated intestinal inflammation, engagement of epithelial CD1d elicits protective effects through the activation of STAT3 and STAT3-dependent transcription of IL-10, heat shock protein 110 (HSP110; also known as HSP105), and CD1d itself. All of these epithelial elements are critically involved in controlling CD1d-mediated intestinal inflammation. This is demonstrated by severe NKT-cell-mediated colitis upon IEC-specific deletion of IL-10, CD1d, and its critical regulator microsomal triglyceride transfer protein (MTP), as well as deletion of HSP110 in the radioresistant compartment. Our studies thus uncover a novel pathway of IEC-dependent regulation of mucosal homeostasis and highlight a critical role of IL-10 in the intestinal epithelium, with broad implications for diseases such as inflammatory bowel disease.

Extended Data Figure 1. Proposed model of CD1d signalling in polarized intestinal epithelia and overview of experimental procedures

a, The proposed model of protective (blue) and pathogenic (red) effects of lipid antigen presentation in intestinal inflammation. Bone-marrow-derived antigen-presenting cells (APCs) contribute to oxazolone colitis in a CD1d- and iNKT-cell-dependent manner. By contrast, engagement of intestinal epithelial CD1d elicits protective functions through cytoplasmic CD1d tail-dependent activation of STAT3, and STAT3-dependent transcription of Cd1d1, Il10 and Hsph1. Epithelial IL-10 and HSP110 support this protective self-reinforcing pathway through STAT3-dependent signalling. Interference with any of the elements involved in this regulatory pathway (MTP, CD1d, IL-10 or HSP110) is associated with uncontrolled intestinal inflammation, thus highlighting a critical role of this pathway in the control of intestinal inflammation. Conv., conventional. b, Overview of experimental procedures.

Extended Data Figure 2. Absence of enterocyte lipid accumulation and ER stress in Mttp^ΔIEC mice

a, Absence of lipid accumulation in Mttp^ΔIEC mice as shown in representative haematoxylin and eosin and rare osmium tetroxide (arrows) staining in the caecum, proximal, and distal colon. Scale bar, 25 μm. b, Xbp1 splicing in small intestinal (SI) and colonic IECs of the indicated mice before (left) (n = 5 mice per group) and 6 h after rectal challenge with oxazolone (Ox., right) (n =5 mice per group). MODE-K cells were treated with either thapsigargin (Tg) or vehicle (DMSO) as positive and negative controls, respectively. Results representative of three independent experiments are shown.

Extended Data Figure 3. Impaired CD1d- but not MHC-class I-restricted antigen presentation in Mttp^ΔIEC mice

a, CD1d-mediated presentation of the exogenous lipid antigen α-GalCer to the invariant NKT-cell hybridomas 24.7 and DN32.D3 and of endogenous lipid antigens (autoreactivity) to the non-invariant NKT-cell hybridoma 14S.6 by IECs from CD1d-knockout (CD1d-KO) mice, Mttp^ΔIEC mice and wild-type littermates (Mttp^+/+) (n = 5 mice per group). b, Presentation of H2-K^b-restricted SIINFEKL by the indicated IECs (see a) to the SIINFEKL-responsive hybridoma RF33.70. c, Representative histograms of CD1d cell surface expression as determined by flow cytometry of colonic IECs of the indicated mouse strains before (left, n = 5 mice per group) and 6 h after (right, n = 5 mice per group) rectal oxazolone challenge. d, Representative haematoxylin and eosin stainings of the indicated mouse strains upon rectal challenge with oxazolone (Ox.) or vehicle (ethanol (EtOH)). Scale bar, 40 μm. Results representative of three independent experiments are shown. Mean ±s.e.m. of triplicate cultures are shown. Student’s t-test was applied.

Extended Data Figure 4. Increased morbidity and mortality in oxazolone-challenged Mttp^ΔIEC mice is due to CD1d-restricted components of the adaptive immune system

a, Intestinal permeability as determined by FD-4 before and 18 h after rectal challenge with oxazolone (ox.) in the indicated mouse strains. Each symbol represents a single mouse. b, IL-1β secretion by CD11b⁺ cells from colonic lamina propria of the indicated bone marrow chimaeras. CD11b⁺cells were isolated using magnetic microbeads 24 h after rectal challenge with oxazolone or ethanol and cultured for 24 h before measurement of IL-1β in culture supernatants by ELISA. Mean ±s.e.m. of triplicate cultures are shown. c, d, Survival and body weight of the indicated mouse strains at the indicated days after rectal oxazolone challenge. Results representative of three independent experiments are shown. Mean ±s.e.m. of the indicated number of mice are shown. Student’s t-test was applied.

Extended Data Figure 5. Development and characterization of mice with IEC-specific Cd1d1 deletion

a, Schematic map of the targeting strategy for generation of Cd1d1^fl/fl mice. A LoxP (L83) site was inserted at 10310 and a FNFL (Frt-Neo-Frt-LoxP) cassette at 12190 to flank exons 2, 3, and 4 (about 1.9 kb) of the Cd1d1 gene to generate the ‘floxed/neo’ Cd1d1 allele. A gene-targeting vector was constructed by retrieving one 5 kb long homology arm (5′ to L83), one 1.9 kb sequence containing exon 2/3/4, FNFL cassette, and one 2 kb short homology arm (end of FNFL to 3′). The FNFL cassette conferred G418 resistance during gene targeting in PTL1 (129B6 hybrid) embryonic stem (ES) cells. The targeted Cd1d1 allele was PCR amplified and sequenced to confirm the targeted C57BL/6 allele based on the C57BL/6-specific mutation in the Cd1d2 allele. Three targeted ES cells with targeted C57BL/6 allele were injected into C57BL/6 blastocysts to generate chimaeric mice. Male chimaeras were bred to bACTFlpe females or EIIa-Cre females to transmit the floxed Cd1d1 allele (Cd1d1^L/+) (with neo cassette removed by Fple recombinase) through the germ line. Mice carrying the floxed Cd1d1 allele were crossed to tissue-specific VillinCre-ER^T2 and exons 2, 3 and 4 and Frt-LoxP were removed by Cre recombinase in intestinal epithelial cells. b–e, Impaired CD1d- but not MHC-class I-restricted antigen presentation in Cd1d1^ΔIEC mice. b, Cd1d1^ΔIEC mice exhibit normal numbers of invariant NKT cells in liver, spleen and colonic lamina propria as determined by flow cytometry using α-GalCer/CD1d tetramers (n = 4 mice per group). c, Representative histograms of CD1d cell surface expression on colonic IECs of the indicated mouse strains before (left, n =5 mice per group) and 6 h after (right, n =5 mice per group) rectal oxazolone challenge. d, CD1d-mediated antigen presentation by colonic IECs of the indicated mouse strains (n = 5 mice per group). Presentation of the model glycolipid antigen α-GalCer to invariant NKT-cell hybridomas 24.7 and DN32.D3 and of endogenous antigens (autoreactivity) to the non-invariant NKT-cell hybridoma 14S.6 is shown. e, Presentation of H2-K^b-restricted SIINFEKL presentation by the indicated IECs (n = 5 mice per group) to the SIINFEKL-responsive hybridoma RF33.70. Results representative of three independent experiments are shown b–e, Mean ±s.e.m. of triplicate cultures are shown. Student’s t-test was applied. f, Intestinal epithelial CD1d is protective in oxazolone colitis. Representative macroscopic colon images of Cd1d1^ΔIEC and wild-type littermates upon rectal challenge with oxazolone (Ox., n =5 mice per group) or vehicle (ethanol (EtOH), n =4 mice per group).

Extended Data Figure 6. Epithelial HSP110 expression is decreased in Mttp^ΔIEC mice and in human ulcerative colitis

a, HSP110 immunohistochemistry in mice with IEC Mttp deletion (bottom) as compared with wild-type littermates (top) 6 h after rectal oxazolone challenge. b, HSP110 immunohistochemistry in the colonic intestinal epithelium and the lamina propria of healthy controls and patients with active and inactive ulcerative colitis. Signal intensity was scored on a scale from 0 to 3 in a blinded fashion. Each symbol represents a single patient. The median and significance level as determined by the Mann–Whitney U-test are shown. c, Mortality in conventional HSP110-knockout mice in the oxazolone colitis model. Results representative of three independent experiments are shown. Mean ±s.e.m. of the indicated number of mice is shown. Student’s t-test and the log-rank test (survival) were applied. NS, not significant.

Extended Data Figure 7. Purity of isolated IECs

After isolation of colonic IECs, potential contamination with haematopoetic cells was investigated by flow cytometry. The major population of cells was gated (upper left), was shown to contain viable cells (upper middle), and to contain largely EpCAM-positive epithelial cells that do not stain with leukocyte markers (middle and bottom). The upper right panel shows isotype control staining. Results representative of three independent experiments (n = 5 mice per experiment) are shown.

Extended Data Figure 8. CD1d-dependent STAT3 phosphorylation upon co-culture of IECs and iNKT cells

a, STAT3 phosphorylation in IECs upon co-culture with iNKT cells is CD1d-dependent. Expression of pSTAT3, STAT3 and β-actin as determined by western blotting of MODE-K cells at the indicated time after addition of the iNKT-cell hybridoma 24.7. Where indicated, MODE-K cells were pre-incubated with a monoclonal blocking antibody directed against CD1d (19G11; +) or an isotype control (−). b, siRNA-mediated knockdown of Stat3 in MODE-K cells as determined 68 h after siRNA transfection. Results representative of three independent experiments are shown. Means ±s.e.m. of triplicates are shown. Student’s t-test was applied.

Extended Data Figure 9. CD1d-mediated cytokine production is dependent on the APC and expression of co-stimulatory molecules

a–f, IL-10 (a, c–f) and IL-12p70 (b) secretion of co-cultures of the IEC line MODE-K or splenic dendritic cells (DCs) together with the iNKT-cell hybridoma 24.7. APCs were loaded with α-GalCer (αGC; 100 ng ml⁻¹) before washing and co-culture with iNKT cells. c, MODE-K cells (IEC) were transfected with control siRNA or siRNA directed against Il10 before co-culture with iNKT cells. d, f, MODE-K cells were transfected with CD40 (d) and CD1d (f) as indicated. Histograms demonstrated increased expression of CD40 (d) and CD1d (f) after transfection. e, Stimulatory anti-CD28 antibody was added during co-culture of MODE-K and iNKT cells. Means ±s.e.m. of quadruplicate cultures are shown. Student’s t-test was applied. Results are representative of two independent experiments.

Figure 1. Intestinal epithelial MTP and CD1d protect from oxazolone colitis

a–k, Survival (a, left, c, left, f, left, h, left), body weight (a, right, c, right, f, right, h, right), histopathology (b, d, g, i), cytokine secretion (enzyme-linked immunosorbent assay (ELISA)) in colon explant cultures (e, j), and cytokine expression (quantitative polymerase chain reaction (qPCR)) of sorted colonic iNKT cells combined from intraepithelial and lamina propria compartments (k) of the indicated mice upon rectal challenge with oxazolone (ox., a–k) or vehicle (ethanol (EtOH, a–e, h–j)). c–e, Wild-type (WT) and CD1d-knockout (CD1d-KO) mice were reconstituted with wild-type bone marrow. f, g, 19G11 (anti-CD1d) or isotype control antibody (IgG2b) were administered. Results representative of three independent experiments are shown. Mean ± standard error of the mean (s.e.m.) of the indicated number of mice is shown. j, Right, Mann–Whitney U-test was applied. In all other panels, Student’s t-test or log-rank test (survival) were applied.

Figure 2. HSP110 elicits protective effects downstream of intestinal epithelial CD1d

a, b, Hsph1 expression (qPCR) in purified IECs of the indicated mouse strains at baseline (a) or on day 5 after rectal oxazolone (Ox.) or ethanol (EtOH) (b). c, HSP110 immunohistochemistry in colon of human ulcerative colitis and controls. d–i, Survival (d, bottom, h, left), body weight (d, top, h, right), histopathology (e, i), and cytokine secretion in colon explants (ELISA) (f) in the oxazolone model. d, f, Wild-type (WT) and HSP110-KO recipients of wild-type bone marrow received 19G11 anti-CD1d or isotype control antibody. g–i, Mice received adenoviruses expressing HSP110 (AdHSP110) or β-galactosidase (AdLacZ). g, Immunofluorescence of colonic GFP after AdHSP110-IRES2-eGFP administration. DAPI, 4′,6-diamidino-2-phenylindole. j–l, MODE-K Hsph1 and Il10 (qPCR) after antibody-mediated CD1d crosslinking (1B1) (j–k) or α-GalCer presentation to iNKT cells (24.7 hybridoma) in the presence/ absence of neutralizing CD1d antibodies (19G11) (l). mAb, monoclonal antibody. m, Hsph1 and Il10 (qPCR) in purified small intestinal IECs from wild-type and TD-CD1d recipients of wild-type bone marrow after injection with vehicle or α-GalCer (6 mice per group). c, g, Scale bars, 50 μm. Results representative of two or three independent experiments are shown. Means ±s.e.m. of the indicated number of mice or triplicate cultures (l) are indicated. Student’s t-test or log-rank test (survival) were applied.

Figure 3. Epithelial CD1d induces STAT3-dependent expression of IL-10 and HSP110

a, MODE-K pSTAT3 after CD1d-crosslinking (1B1 monoclonal antibody clone) or iNKT (24.7 hybridoma) co-culture. b, Colonic pSTAT3 immunohistochemistry 5 days after rectal oxazolone (Ox.) or ethanol (EtOH). Scale bar, 50 μm. c, pSTAT3 in purified small intestinal IECs from the indicated bone marrow chimaeras (IECs from one mouse per lane). d–f, Cd1d1, Hsph1 and Il10 (qPCR) in MODE-K cells after treatment with recombinant HSP110 (e) or Stat3/ control siRNA knockdown (d, f) followed by viral transduction at a multiplicity of infection (MOI) of 5 (f). g, Il10, Hsph1 and Tgfb in purified IECs (qPCR) 6 h after rectal oxazolone in the presence or absence of viral infection. The fold change compared to oxazolone-treated Cd1d1^+/+ mice without virus is indicated. h, Western blot of IECs 24 h after rectal oxazolone. i, Western blot of purified CD11b⁺ lamina propria cells 5 days after rectal oxazolone. j–l, Survival (j, left), body weight (j, right), histopathology (k) and cytokine secretion by colon explants (ELISA; l) of the indicated oxazolone-challenged mice with or without viral infection and antibody treatment as indicated. Results representative of three independent experiments are shown. Means ±s.e.m. of the indicated number of mice or triplicate cultures (d–f) are indicated. Student’s t-test or log-rank test (survival) were applied. NS, not significant.

Figure 4. Epithelial IL-10 is critical for control of intestinal inflammation

a–f, Survival (a, c), IL-13 production in colon explants on day 1 after rectal oxazolone (Ox.) or ethanol (EtOH) (b), body weight (d), histopathology (e), and Il10 (left), Hsph1 (middle) and Cd1d1 (right) expression (qPCR; f) in colonic IECs 5 days after rectal oxazolone challenge in the indicated mouse strains. Results representative of three (a, b) or two (c–f) independent experiments are shown. Means ±s.e.m. of the indicated number of mice are shown. Student’s t-test or log-rank test (survival) were applied.