Bacterial metabolism of bile acids promotes generation of peripheral regulatory T cells

Abstract

Intestinal health relies on the immunosuppressive activity of CD4⁺ regulatory T (T_reg) cells¹. Expression of the transcription factor Foxp3 defines this lineage, and can be induced extrathymically by dietary or commensal-derived antigens in a process assisted by a Foxp3 enhancer known as conserved non-coding sequence 1 (CNS1)^2-4. Products of microbial fermentation including butyrate facilitate the generation of peripherally induced T_reg (pT_reg) cells^5-7, indicating that metabolites shape the composition of the colonic immune cell population. In addition to dietary components, bacteria modify host-derived molecules, generating a number of biologically active substances. This is epitomized by the bacterial transformation of bile acids, which creates a complex pool of steroids⁸ with a range of physiological functions⁹. Here we screened the major species of deconjugated bile acids for their ability to potentiate the differentiation of pT_reg cells. We found that the secondary bile acid 3β-hydroxydeoxycholic acid (isoDCA) increased Foxp3 induction by acting on dendritic cells (DCs) to diminish their immunostimulatory properties. Ablating one receptor, the farnesoid X receptor, in DCs enhanced the generation of T_reg cells and imposed a transcriptional profile similar to that induced by isoDCA, suggesting an interaction between this bile acid and nuclear receptor. To investigate isoDCA in vivo, we took a synthetic biology approach and designed minimal microbial consortia containing engineered Bacteroides strains. IsoDCA-producing consortia increased the number of colonic RORγt-expressing T_reg cells in a CNS1-dependent manner, suggesting enhanced extrathymic differentiation.

Extended Data Fig. 1|. Effects of iso- and oxo-bile acids on T cell differentiation and proliferation.

(a) Effects of Treg cell-inducing BAs on the in vitro generation of Th17 cells. Naïve CD4⁺ T cells were activated by DCs in Th17-polarizing conditions (2 ng/mL TGFβ, 1 μg/mL αCD3, and 20 ng/mL IL-6). On day 3, co-cultures were re-stimulated with PMA and ionomycin in the presence of brefeldin A and monensin for 3 hours before FACS analysis of IL-17A production. (b) The 6β-OH of ω−MCA is required for its Treg cell-inducing activity. Naïve CD4⁺ T cells were activated by DCs in suboptimal Treg-cell inducing conditions (1 ng/mL TGFβ, 1 μg/mL αCD3, 100 U/mL IL-2) and exposed to ω−MCA or 6-oxoMCA at the indicated concentrations. Foxp3 induction was assessed by FACS on day 3. (c) Assessment of cell division in the presence of isoDCA and 3-oxoDCA (100 μM). Naïve CD4⁺ T cells were labeled with Cell Trace Violet and activated with αCD3/αCD28 beads in the presence of TGFβ and IL-2 for 3 days before FACS analysis. Showing mean ± SD of replicates (a-c, n=3). Statistical significance determined by one-way (a,b) or two-way (c) ANOVA followed by a Dunnet (a) or Tukey (b, c) multiple comparison test. (*) p<0.05, (**) p<0.01, (***) p<0.001 vs vehicle; (#) p<0.05 vs ω−MCA (paired concentration); (+) p<0.05 vs isoDCA (paired concentration); (ns) not significant. Data representative of at least two independent experiments.

Extended Data Fig. 2|. Characterization of mice with FXR deficiency in the myeloid compartment.

(a-e) WT (Csf1r^WT Nr1h4^fl/fl) and DC^ΔFXR (Csf1r^CreNr1h4^fl/fl) littermate mice were analyzed between 6–8 weeks of age. Gating strategy (a) and quantification of cDC1 [Live CD45⁺ Lin⁻ (dump: CD90, CD3; CD64⁻, Ly6C⁻, Siglec-F⁻) CD11c⁺ MHC class II^hi CD11b⁻ XCR1⁺] and cDC2 [Live CD45⁺ Lin⁻ (dump: CD90, CD3; CD64⁻, Ly6C⁻, Siglec-F⁻) CD11c⁺ MHC class II^hi CD11b⁺ XCR1⁻] in the spleen (Spl), mesenteric lymph node (MLN) and large intestine lamina propria (LILP, b). (c) Gating strategy for (d-e). (d) Number of total Foxp3⁺ Treg cells in the indicated organs. (e) Quantification of RORγt⁺ Foxp3⁺ Treg cells in the LILP. Data shown as mean ± SD (n=5), representative of two independent cohorts of mice. Statistical significance determined by a two-tailed T-test. (**) p<0.01.

Extended Data Fig. 3|. Anti-inflammatory effects of isoDCA treatment on DCs.

(a) DCs (1 × 10⁵) were stimulated for 18 hours with various TLR agonists in the presence or absence of 50 μM isoDCA. Levels of the indicated cytokines were determined in the culture supernatant by ELISA. (b) DCs (1 × 10⁴) were pulsed with ovalbumin (OVA, 1 mg/mL) in the presence of various concentrations of isoDCA for 1 hour in serum-free medium and allowed to process antigen for 4 hours in complete medium before addition of an NFAT-GFP reporter cell line expressing the MHC II-restricted OT-II TCR recognizing the ISQAVHAAHAEINEAGR peptide of OVA. The frequency of GFP⁺ cells was determined by FACS analysis after 24 hours. Co-cultures treated with αCD3 antibody (1 μg/mL) served as controls for DC-dependent, antigen-processing independent effects of isoDCA on the activation of reporter cells. Activation with αCD3/αCD28 beads in the presence of isoDCA served as control for DC-independent effects on reporter gene expression. Showing mean ± SD of replicates in (a) and fold-change relative to vehicle (0 μM isoDCA) within each condition (OVA, αCD3 or αCD3/CD28 beads) in (b). Statistical significance in (a) was determined by multiple T-tests using the Holm-Sidak correction method with alpha = 0.05. (****) p<0.001 vs vehicle. Statistical significance in (b) was determined by a two-way ANOVA followed by Dunnet’s multiple comparison’s test. (*) p<0.05; (****) p<0.001 vs vehicle in each condition. Data representative of 3 independent experiments.

Extended Data Fig.4|. LC-MS-based analysis of isoDCA production by engineered B. theta strains.

Bacteria were grown to exponential phase and transferred to media containing DCA. Following incubation for 24 hours, media was extracted with methanol and supernatants were analyzed by Liquid Chromatography-Mass Spectrometry (LC-MS). (a) Traces for spike-in controls with DCA and isoDCA standards (solid and dotted black lines, respectively), and media conditioned by B. theta^WT (yellow line), B. theta^CD (blue line) or the parental, un-manipulated B. theta^VPI strain VPI-5482 (gray line). Data are representative of two independent experiments carried in triplicates.

Extended Data Fig.5|. Analyses of microbial community composition in gnotobiotic and conventionalized mice.

Germ-free (GF) mice were gavaged with WT or CD engineered consortia (C. scindens + B. theta^WT or C. scindens + B. theta^CD, respectively). Recipients of a fecal microbiota transplant (FMT) and non-colonized mice (PBS) served as references. OTU composition of the cecal microbiota on day 10 post-colonization was determined by 16S sequencing. Total read counts (a) and relative abundances (b) of bacteria in individual experimental mice. Showing data pooled from two independent experiments (n=10).

Extended Data Fig.6|. Effects of isoDCA-producing consortium on colonic lymphocytes.

Germ-free (GF) mice were gavaged with engineered consortia (C. scindens + B. theta^WT or C. scindens + B. theta^CD), PBS or a complex microbial community (FMT) as described in Fig. 4b. Immune cell composition in the LILP was analyzed by FACS on day 10 (a-e) or day 30 (f-g) post-colonization. Frequencies of total Foxp3⁺ (a) and RORγt⁺Foxp3⁺ (b) Treg cells among CD45⁺ cells. Frequency of RORγt⁺Foxp3⁺ cells in the mesenteric lymph node (MLN, c) and small intestine lamina propria (SILP, d). (e) Frequency of RORγt⁺ cells among Foxp3⁻ (e, f) and Foxp3⁺ CD4⁺ T cells (g). Showing mean ± SD (n=10). Data are pooled from two independent experiments. Statistical significance determined by a one-way ANOVA followed by Tukey’s multiple comparison’s test. (**) p<0.01; (***) p<0.001; (****) p<0.0001; (ns) not significant.

Extended Data Fig.7|. IsoDCA production by engineered Bacteroides sp. strains.

(a) Quantification of isoDCA production by engineered and reference strains in vitro. Bacteria were grown to exponential phase and transferred to media containing DCA. Following incubation for 24 hours, media was extracted with methanol and supernatants were analyzed by Liquid Chromatography-Mass Spectrometry (LC-MS). (b-c) Germ-free (GF) mice were colonized with consortia containing either the engineered strain of B. frag capable of producing isoDCA (WT) or the catalytically dead (CD) mutant in combination with C. scindens (C. scindens + B. frag^WT and C. scindens + B. frag^CD, respectively). Recipients of a fecal microbiota transplant (FMT) and non-colonized mice (PBS) served as references. Immune cell composition and isoDCA quantification were performed 10 days post-colonization. (b) FACS analysis of the frequency of RORγt⁺Foxp3⁺CD4⁺ T cells in the large intestine lamina propria (LILP). (c) Quantification of isoDCA in cecal contents. Fecal material was weighed, homogenized and extracted with methanol for LC-MS analysis. Reporting area under the curve (AUC) normalized by weight of input material. Showing mean ± SD (a, n=3; b, n=10; c, n=5). Data in (a, c) are representative of two independent experiments. Data in (b) are pooled from two independent experiments. Statistical significance determined by a one-way ANOVA followed by Tukey’s multiple comparison’s test. (*) p<0.05; (ns) not significant.

Extended Data Fig. 8|. Short-chain fatty acids (SCFAs) production by minimal, defined microbial consortia.

Germ-free (GF) mice were colonized with consortia containing either the engineered strain of B. frag capable of producing isoDCA (WT) or the catalytically dead (CD) mutant in combination with C. scindens (C. scindens + B. frag^WT and C. scindens + B. frag^CD, respectively). Recipients of a fecal microbiota transplant (FMT) and non-colonized mice (PBS) served as references. Cecal content material was weighed, homogenized and subjected to organic solvent extraction for GC-MS-based quantification of SCFAs levels. Showing mean ± SD (n=6). Data are pooled from two independent experiments. Statistical significance determined by a one-way ANOVA followed by Tukey’s multiple comparison’s test. (****) p<0.0001; (ns) not significant.

Fig. 1|. Bacterial epimerization of bile acids (BAs) generates molecules with Treg cell-inducing activity.

(a, b) Structure of BAs and summary of substitutions around the cholesterol backbone. (c) Screen setup: Naïve CD4⁺ T cells (5 × 10⁴) were co-cultured with DCs (1 × 10⁵) in suboptimal Treg-cell inducing conditions (1 ng/mL TGFβ, 1 μg/mL αCD3, 100 U/mL IL-2) and analyzed on day 3 by FACS. BAs listed in (a) were added at the indicated doses. (d) Frequencies of Foxp3⁺ CD4⁺ T cells after exposure to various concentrations of BA. (e) The 3β-OH of isoDCA is required for its Treg cell-inducing effects. Cells were co-cultured as described in (c) and incubated with 3-oxoDCA or isoDCA at the indicated concentrations. (f) Assessment of cell proliferation. Naïve CD4⁺ T cells were labeled with Cell Trace Violet (CTV) and cultured with DCs as described in (c) in the presence of isoDCA or 3-oxoDCA (100 μM). CTV dilution was assessed on day 3 by FACS. (g) Effect of BAs on Treg cell differentiation in the absence of DCs. Naïve CD4⁺ T cells were activated with αCD3/CD28 beads under suboptimal Treg cell-inducing conditions. IsoDCA and 3-oxoDCA were added at the indicated concentrations and cells were analyzed on day 3 by FACS. Showing mean ± SD of technical replicates (d, n=4; e-g, n=3). (*) p<0.05, (**) p<0.01, (****) p<0.0001 vs vehicle; (+) p<0.0001 vs isoDCA (paired concentration) by one-way (d,e,g) or two-way (f) ANOVA followed by a Dunnet (d) or Tukey (e-g) multiple comparison test. Data representative of at least three independent experiments.

Fig.2|. Potentiation of Treg cell generation by isoDCA acts requires FXR expression in DCs.

(a) Effects of FXR deficiency in T cells (T^WT and T^ΔFXR) or DCs (DC^WT and DC^ΔFXR) on Treg cell induction by isoDCA (50 μM). (b-f) RNA-seq analysis of FACS-purified DCs 24 hours after BA exposure. (b) Transcriptional profiling of WT DCs treated with isoDCA (50 μM). Differentially expressed genes in orange. (c) Fold-change (FC) vs. FC plot comparing the transcriptional changes induced by isoDCA treatment (x-axis) and FXR deficiency (y-axis). Genes reduced by isoDCA in blue; genes induced by isoDCA in orange. (d) Overlap between genes regulated by isoDCA treatment (orange) and FXR deficiency (blue). (e) FC vs. FC plot comparing the effects of isoDCA on WT (x-axis) and FXR-deficient (y-axis) DCs, color-coded as in (c). (f) Overlap between genes regulated by isoDCA in WT (orange) and FXR-deficient (blue) DCs. (g) Differential scanning fluorimetry (DSF) experiment with recombinant FXR-LBD and BAs at 1000-fold (500 μM) or 200-fold (100 μM) excess. Showing the Boltzmann melting temperature (Tm). (h-i) Luciferase reporter assays. Cells expressing a Gal4-FXR-LBD fusion protein were treated with vehicle, CDCA, GW4064 alone or combined with isoDCA (100 μM). (j) FRET-based co-activator recruitment assay. BAs were mixed with GST-tagged FXR-LBD (5 nM), FITC-SRC2–2 coactivator peptide (500 nM) and Tb α-GST antibody (5 nM). Showing ratio of fluorescence at 520/485 nm. Displaying mean ± SD of technical replicates (a, g, n=3; j, n=4), representative of three independent experiments. Data in (b-f, n=3) are from one experiment. Data in (h-i, n=3) shown as mean ± SD, pooled from three independent experiments. Statistical significance determined by a one- (g) or two-way (a, h-j) ANOVA followed by Tukey or Sidak’s test. (*) p<0.05, (***) p<0.001, (****) p<0.0001 vs vehicle; (+) p<0.05 vs paired concentration of agonist; (ns) not significant.

Fig. 3|. Engineering an isoDCA producing strain of Bacteroides thetaiotaomicron (B. theta).

(a) Genes involved in isoDCA formation from DCA. Rumgna_02133 and Rumgna_00694, two hydroxysteroid dehydrogenases (HSDHs) present in Ruminococcus gnavus, were identified by Devlin et al. as key enzymes catalyzing epimerization of the 3-OH group of DCA by this bacterium. (b) Cloning strategy to reconstitute the pathway for isoDCA generation in B. theta: Constructs for Rumgna_02133 and Rumgna_00694 were codon-optimized, put under the control of a strong, constitutive promoter in B. theta and chromosomally integrated by conjugation. (c) Rationale for the design of catalytically-dead (CD) mutant of Rumgna_00694. A conserved tyrosine (red) in the putative active site of the enzyme was identified and mutated to phenylalanine (Y165F). (d) Characterization of the biochemical activity of WT and CD engineered strains of B. theta by thin layer chromatography (TLC). Bacteria were grown to exponential phase and transferred to media containing DCA. Following incubation for 24 hours, media was extracted in ethyl acetate and analyzed by TLC. DCA and isoDCA controls are shown on the 4 rightmost lanes. The WT strain (3 leftmost lanes) converts DCA into isoDCA, while the CD mutant (3 middle lanes) shows no activity. Data are representative of two experiments.

Fig. 4|. Defined bacterial consortia containing isoDCA-producing strains promote pTreg cell generation in vivo.

(a) Generation of isoDCA by a minimal microbial consortium. Enzymatic steps performed by C. scindens and the engineered Bacteroides sp. (B. thetaiotamicron, B. fragilis and B. ovatus). (b) Experimental setup. Germ-free (GF) mice were colonized with consortia containing C. scindens + B. theta^WT or C. scindens + B. theta^CD. Recipients of a fecal microbiota transplant (FMT) and non-colonized mice (PBS) served as references. Immune cell composition in the large intestine lamina propria (LILP) was analyzed on day 10 by FACS. Frequency of Foxp3⁺ (c) and RORγt⁺ (d) Treg cells. Frequency of RORγt⁺ Treg cells in GF mice colonized with C. scindens in combination with engineered B. ova (e) or B. frag (f). (g-h) B. frag^WT or B. frag^CD were administered to GF mice the absence of a 7-α dehydroxylating bacterium (w/o C. scindens). Showing frequencies of Foxp3⁺ (g) and RORγt⁺ (h) Treg cells. (i-j) GF Foxp3^GFP and Foxp3^GFPΔCNS1 littermate mice were gavaged with C. scindens + B. theta^WT (i) or C. scindens + B. frag^WT (j) and compared to recipients of the respective CD consortia. Showing percentage of colonic RORγt⁺Foxp3⁺Treg cells. (c-j) Data combined from 2 independent experiments (except in i) and shown as mean ± SD. Statistical significance determined by two-tailed T-test (e, n=8; f, n=9; g-h, n=7), one-way (c-d, n=10) or two-way (i, n=5; j, n=7) ANOVA followed by Tukey’s multiple comparison’s test. (*) p<0.05; (**) p<0.01; (***) p<0.001; (ns) not significant.