Type I interferons and microbial metabolites of tryptophan modulate astrocyte activity and central nervous system inflammation via the aryl hydrocarbon receptor

Abstract

Astrocytes have important roles in the central nervous system (CNS) during health and disease. Through genome-wide analyses we detected a transcriptional response to type I interferons (IFN-Is) in astrocytes during experimental CNS autoimmunity and also in CNS lesions from patients with multiple sclerosis (MS). IFN-I signaling in astrocytes reduces inflammation and experimental autoimmune encephalomyelitis (EAE) disease scores via the ligand-activated transcription factor aryl hydrocarbon receptor (AHR) and the suppressor of cytokine signaling 2 (SOCS2). The anti-inflammatory effects of nasally administered interferon (IFN)-β are partly mediated by AHR. Dietary tryptophan is metabolized by the gut microbiota into AHR agonists that have an effect on astrocytes to limit CNS inflammation. EAE scores were increased following ampicillin treatment during the recovery phase, and CNS inflammation was reduced in antibiotic-treated mice by supplementation with the tryptophan metabolites indole, indoxyl-3-sulfate, indole-3-propionic acid and indole-3-aldehyde, or the bacterial enzyme tryptophanase. In individuals with MS, the circulating levels of AHR agonists were decreased. These findings suggest that IFN-Is produced in the CNS function in combination with metabolites derived from dietary tryptophan by the gut flora to activate AHR signaling in astrocytes and suppress CNS inflammation.

Figure 1. CNS inflammation induces a type I IFN signature in astrocytes

(a) Heatmap of all 17,964 expressed genes (detected at level 0.1 in at least half of the samples) sorted by their differential expression (signal to noise ratio) between naive and EAE (peak disease) astrocytes; representatives out of two independent experiments (n = 2 per group). Gene expression levels are row centered and log₂ transformed and saturated at − 0.5 and + 0.5 for visualization. (b) Heatmap of 1,869 differentially expressed genes sorted by their differential expression (signal to noise ratio) between naive and EAE (peak disease) astrocytes; representatives out of two independent experiments (n = 2 per group). Gene expression levels are row centered and log₂ transformed and saturated at − 0.5 and + 0.5 for visualization. (c) qPCR analysis of transcription factors and relevant genes involved in type I IFN signaling from FACS-sorted naive and EAE astrocytes (n = 3; mean + SEM, Student’s t-test; normalized to Naive Stat1). Significance levels: *P < 0.05, **P < 0.01, ***P < 0.001, n.s.: not statistically significant.

Figure 2. Type I IFN signaling in astrocytes limits CNS inflammation

EAE was induced by active immunization with MOG_35-55 in C57Bl/6 WT mice, which were injected intracerebroventricularly at days 7 and 15 after disease induction with Ifnar1 targeting (shIfnar1) or control (shControl) lentiviruses. (a) Top: Schematic of the astrocyte-specific shRNA targeting lentiviral vector. cPPT, central polypurine tract termination; WPRE, woodchuck hepatitis virus post-transcriptional regulatory element; mir30, micro-RNA30. Bottom: Clinical scores of shControl or shIfnar1-injected mice (mean ± s.e.m., representative out of two independent experiments with n = 10 mice per group; Two-way ANOVA). (b) Astrocytes infected with shControl or shIfnar1 were identified by GFP expression at the peak of EAE and isolated by FACS-sorting. qPCR analysis of indicated genes from GFP⁺ astrocytes (upper row) and the entire CD11b⁺CD45^lo microglia population (lower row); n = 4 mice per group, representative of two independent experiments; Student’s t-test; normalized to shControl Microglia Irf9). (c) Fold change in mRNA expression of the indicated genes from sorted astrocytes of shIfnar1 and shControl mice during peak disease as determined by Nanostring analysis (fold change in relative expression as determined by log₂(shIfnar1/shControl)). Representative out of two independent experiments of pooled astrocytes of n = 3 mice per group. (d) qPCR analysis of Ahr and Cyp1b1 expression in astrocytes and microglia sorted as in (b); n = 4 mice per group, representative of two independent experiments; Student’s t-test; normalized to astrocytes shIfnar1 Cyp1b1. (e,f) Nanostring analysis of pro-inflammatory gene clusters (Supplementary Table 3) from sorted microglia (e) and Ly-6C^hi pro-inflammatory monocytes (f); ratio of count numbers of shIfnar1 to shControl; representative out of two independent experiments of pooled microglia and macrophages with n = 3 mice per group. Significance levels: *P < 0.05, **P < 0.01, ***P < 0.001), n.s.: not statistically significant.

Figure 3. Interferon-β induces AhR expression in astrocytes

(a) qPCR analysis of Ahr and Cyp1b1 expression in astrocytes sorted from naive mice and mice with peak EAE scores (mean+s.e.m., n = 3, Student’s t-test; normalized to Naive Ahr). (b) mRNA expression of the indicated genes in in vitro cultured astrocytes transduced with shControl or shIfnar1 lentivirus and treated with IFN-β or vehicle (n = 3, representative of three independent experiments; one-way ANOVA followed by Tukey’s multiple comparisons test; normalized to Vehicle – IFN-β Ifnar1). (c) Schematic of type I interferon signaling pathway. (d) FACS analysis of pStat1 expression in WT astrocytes stimulated with IFN-β or vehicle; left in histograms: red line: isotype, grey line: unstimulated; blue line: anti-pStat1; right in bar graph: quantification of GFP⁺; representative of two independent experiments; one-way ANOVA followed by Tukey’s multiple comparisons test; (e) mRNA expression of interferon response gene (ISG) Mx1 and Ahr as determined by qPCR in astrocytes activated with IFN-β and inhibitors of the type I IFN pathway (n = 3, representative of two independent experiments,; one-way ANOVA followed by Tukey’s multiple comparisons test; normalized to Control Mx1). (f) Schematic of predicted Stat1 and ISRE binding sites in AhR promoter as determined by bioinformatics analysis. (g) ChIP from WT astrocytes incubated with IFN-β or control in vitro using anti-STAT1 or non-specific antibodies to determine binding of Stat1 to its binding sites in the AhR promoter (n = 3, representative of two independent experiments, one-way ANOVA followed by Tukey’s multiple comparisons test; g and h normalized to Vehicle non-specific stat1(1,2)). (h) EAE was induced in WT and Ifnar1 KO animals, astrocytes were purified at peak of disease by FACS sorting and ChIP analysis for STAT1 binding in the AhR promoter was performed as in (g). (i) HEK293 cells were transfected with an AhR-responsive reporter (pGud-Luc) and treated as indicated with IFN-β or AhR Inhibitor CH-223191 (n = 3, representative of three independent experiments, one-way ANOVA followed by Tukey’s multiple comparisons test; normalized to Vehicle). Significance levels: * P<0.05, ** P<0.01, *** P<0.001.

Figure 4. AhR in astrocytes limits CNS inflammation

EAE in GFAP-AhR-deficient or control mice. (a) Top: Clinical scores (mean ± s.e.m.; representative out of five independent experiments with n = 10 mice per group; Two-way ANOVA). Bottom: Ratio of RNA abundances in pro-inflammatory cluster from sorted GFAP-AhR-deficient and control astrocytes at the peak of disease (fold change in relative expression as determined by log₂(GFAP-AhR/Control). Representative of two independent experiments of pooled astrocytes of n = 3 mice per group. (b) Absolute number of CNS infiltrating CD11b⁺Ly-6C^hi monocytes as assessed by FACS analysis. n = 5 per group, representative of five independent experiments, Student’s t-test. (c) Left two figures: Nanostring analysis of pro-inflammatory gene clusters (Supplementary Table 3) from sorted CD11b⁺CD45^lo microglia (left) and CD11b⁺Ly-6C^hi monocytes (right); numbers of GFAP-AhR divided by Control; representative out of two independent experiments of pooled microglia and macrophages of n = 3 mice per group; Student’s t-test. Right three figures: RNA expression of indicated genes in astrocytes sorted from WT and GFAP-AhR mice at peak of disease. (n = 3, Student’s t-test; normalized to Control Ccl2) (d) Left: Supernatants of LPS or vehicle stimulated WT or GFAP-AhR-deficient astrocytes were investigated in migration assays using CD11b⁺Ly6C^hi WT monocytes as migrating cells (absolute cell numbers; n = 3; representative of three independent experiments; one-way ANOVA, Tukey’s multiple comparisons test). Right: Migration assay using blocking antibodies as indicated or IL-27R KO macrophages (fold cell numbers; n = 3; representative of three independent experiments; one-way ANOVA within treatment groups, Turkey’s multiple comparisons test). (e) Left panel: Sorted CD11b⁺Ly6C^hi monocytes were co-cultured with activated control or GFAP-AhR-deficient astrocytes, re-isolated and gene-expression analyzed by qPCR (n = 3, representative of two independent experiments; Student’s t-test; normalized to Control Ccl2 in c). Right graph: Neurotoxicity assay with supernatants from control or GFAP-AhR-deficient astrocytes after activation with LPS or vehicle n = 3, representative of two independent experiments, one-way ANOVA, Tukey’s multiple comparisons test). (f) ChIP analysis of binding of NF-kB (p65) to the promoters of Ccl2, Csf2 and Nos2 in Control or GFAP-AhR-deficient astrocytes after activation with LPS. (n = 3, representative of two independent experiments, one-way ANOVA, Tukey’s multiple comparisons test). (g) Schematic of predicted AhR binding sites (XREs) in the SOCS2 promoter (upper graph) and ChIP analysis of AhR binding to the promoter of SOCS2 in astrocytes after stimulation with indicated conditions (lower bar graphs). (n = 3, representative of two independent experiments, one-way ANOVA, Tukey’s multiple comparisons test; f, g normalized to pCcl2 Control rIgG). (h) Relative expression of Socs2 in WT or GFAP-AhR astrocytes after stimulation with LPS (representative out of two independent experiments; one-way ANOVA, Tukey’s multiple comparisons test; normalized to Control Vehicle). (i) Western blot detecting NF-kB (p65; left) and quantification (right) of the ratio of nuclear to cytoplasmatic fraction of WT, GFAP-AhR, and SOCS2^−/− astrocytes stimulated with indicated conditions (representative out of three independent experiments, one-way ANOVA, Tukey’s multiple comparisons test). (j) qPCR of expression levels of Ccl2, Csf2, and Nos2 in Control and SOCS2^−/− astrocytes after stimulation with LPS (representative out of two independent experiments; Student’s t-test; normalized to Control Ccl2). Significance levels: * P<0.05, ** P<0.01, *** P<0.001.

Figure 5. Microbial metabolites of tryptophan and IFN-β suppress CNS inflammation via AhR in astrocytes

(a) qPCR from sorted astrocytes and splenic DCs, macrophages or T cells from naive WT mice treated intranasally with 5.000 IU hIFN-β or PBS daily for 2 days (n = 3, Student’s t-test; normalized to Astrocytes Ahr). (b) EAE in control or GFAP-AhR mice under intranasal IFN-β treatment. Clinical scores of control (left) or GFAP-AhR-deficient (right) mice (mean ± s.e.m. in left graph; representative out of three independent experiments with n = 10 mice per group; Two-way ANOVA). (c) Left panel: RNA abundances from Control and GFAP-AhR astrocytes of indicated genes (n = 3, representative of two independent experiments, one-way ANOVA, Tukey’s multiple comparison test; normalized to Control Veh Vim). Middle graph: Quantification of CNS infiltrating CD11b⁺Ly6C^hi inflammatory monocytes; representative out of three independent experiments with n = 10 mice per group; one-way ANOVA, Tukey’s multiple comparison test. Right graph: RNA analysis of pro-inflammatory gene cluster from sorted monocytes; ratio of count numbers of specific treatment group to Control veh; representative out of two independent experiments of pooled monocytes of n = 3 mice per group; one-way ANOVA, Tukey’s multiple comparison test. (d) GFAP-AhR-deficient and control animals under indicated treatment starting from day 22 after EAE induction (TDD: Tryptophan depleted diet; Trp: Tryptophan; Clinical scores, mean ± s.e.m.; representative out of two independent experiments with n = 10 mice per group; Two-way ANOVA; Tukey’s multiple comparison test). (e) qPCR of Ccl2 and Nos2 in indicated treatment conditions as in (c; normalized to Control TDD+Trp Ccl2, one-way ANOVA, Tukey’s multiple comparison test) (f, g, i) Clinical scores of WT mice treated with indicated conditions starting from day 22 after EAE induction (mean ± s.e.m.; representative out of two independent experiments with n = 5 mice per group; Two-way ANOVA; Tukey’s multiple comparisons test) (h) Left: qPCR of relative mRNA abundances for Ccl2 and Nos2 from astrocytes sorted at day 36 from experimental groups as in f, g, and i; (n = 3, representative of two independent experiments; one-way ANOVA followed by Tukey’s multiple comparisons test normalized to Vehicle Ccl2). Right: Measurement of I3S in urine samples collected at day 36 of experimental groups as in f, g, i (n = 3; representative of two independent experiments; one-way ANOVA followed by Tukey’s multiple comparison test). (j) SYBR Green qPCR of Lactobacillus reuteri bacterial DNA isolated from fecal samples of indicated groups at day 36 after EAE induction (n = 4 per group, representative of two independent experiments; one-way ANOVA followed by Tukey’s multiple comparisons test normalized to TDD+Trp). Significance levels: * P<0.05, ** P<0.01, *** P<0.001.

Figure 6. Human astrocyte activation is controlled by IFN-β and AhR signaling

(a,b) qPCR analysis of indicated mRNA expression in samples from lesions and normal appearing white matter (NAWM) from individuals with MS, or healthy controls relative to GAPDH (n = 4 Controls, n = 5 MS NAWM, n = 10 MS Lesion; one-way ANOVA, Tukey’s multiple comparison test; normalized to Control STAT2). (c) qPCR of RNA levels from human fetal astrocytes treated with IFN-β or vehicle in vitro (n = 3, representative of two independent experiments, Student’s t-test; normalized to Vehicle AHR). (d) qPCR of pro-inflammatory genes from human fetal astrocytes activated with Poly(I:C) and treated with 3-Indoxylsulfate (I3S) or vehicle. (n = 3, representative of two independent experiments; Student’s t-test; normalized to Poly(I:C)+I3S NOS2). (e) Immunofluorescence staining of human white matter brain tissue of active MS lesions for AhR (red), CCL2 (green, left), iNOS (green, right) and GFAP (blue) (Data shown are representative of n = 12 fields from three distinct MS brains) and co-expression of AhR and CCL2, AhR and iNOS, and AhR and GFAP. Scatter graphs (right panel) show the distribution of pixels and extent of colocalization in percentage. Scale bar: 20 μm. (f) qPCR analysis of CYP1B1 expression as in a,b. (g) Luciferase assay for the determination of absolute amount of AhR ligands in human serum (representative of two independent experiments with 11 Healthy controls, 49 MS; student’s t-test) (h) Schematic of tryptophan metabolism (left), and heatmap of median abundances of tryptophan metabolites in serum of healthy controls (HC) and multiple sclerosis patients (right, n = 11 HC, n = 49 MS; Hotelling’s T²-test). Significance levels: * P<0.05, ** P<0.01, *** P<0.001, **** P<0.0001, n.s. not statistically significant.