Plant-Derived Exosomal MicroRNAs Shape the Gut Microbiota

Abstract

The gut microbiota can be altered by dietary interventions to prevent and treat various diseases. However, the mechanisms by which food products modulate commensals remain largely unknown. We demonstrate that plant-derived exosome-like nanoparticles (ELNs) are taken up by the gut microbiota and contain RNAs that alter microbiome composition and host physiology. Ginger ELNs (GELNs) are preferentially taken up by Lactobacillaceae in a GELN lipid-dependent manner and contain microRNAs that target various genes in Lactobacillus rhamnosus (LGG). Among these, GELN mdo-miR7267-3p-mediated targeting of the LGG monooxygenase ycnE yields increased indole-3-carboxaldehyde (I3A). GELN-RNAs or I3A, a ligand for aryl hydrocarbon receptor, are sufficient to induce production of IL-22, which is linked to barrier function improvement. These functions of GELN-RNAs can ameliorate mouse colitis via IL-22-dependent mechanisms. These findings reveal how plant products and their effects on the microbiome may be used to target specific host processes to alleviate disease.

Keywords: IL-22; LexA; and LGG adherence; ginger exosome-like nanoparticle; gut microbiota composition; lipid targeting; miRNA/mRNA interaction; small RNA; tryptophan metabolites.

Figure 1.. GELNs shape gut microbiota and uptake by gut bacteria

(A) GELNs or PBS were fed to C57BL/6 mice every other day for a total of 3 times. Bacterial DNA from feces evaluated using 16S rRNA gene sequencing (n=5). The bar graph shows the percentage of each bacteria sequences in all sequence reads at the level of family. (B) Selected bacteria identified by qPCR in feces of mice. Sequencing results (left); qPCR results (right); GELNs vs PBS, *P<0.05. (C) Heat map depicting the mouse gut microbiota using a qPCR array; red and blue represent high and low levels of bacteria, respectively. (D) Healthy subjects treated with GELNs (n=28) or 0.9% NaCl (n=30). Bacteria in feces were evaluated via 16S rRNA gene sequencing after being randomly pooled into three groups. The bar graph shows the percentage of each bacteria sequence in all sequence reads (bottom left). The level of selected bacteria verified with qPCR (bottom right). (E) A representative confocal microscopy image of a fecal sample from mice fed PKH26-labeled GELNs (left, scale bar: 10 μm) and quantitative FACS analysis (right). (F) Schematic representation of the treatment schedule for PKH2-labeled GELN uptake by gut bacteria in mice (n=5 mice per group). (G) The bar graph shows the results of 16S rRNA sequencing at the level of family for bacteria with a preference for taking up GELNs. The data are representative of three independent experiments (error bars, SD). See also Figure S1-2 and Table S2-3.

Figure 2.. PA-enriched GELNs are preferentially taken up by LGG and regulate the expression of LGG mRNA and protein

(A) Lipid extracted from ELNs from ginger, turmeric, garlic and grapefruit. Lipid composition was determined using a triple quadrupole mass spectrometer. The bar graph shows the percentage of each lipid in all the lipids. (B) GELN- and grapefruit ELN-derived lipids were separated by thin-layer chromatography (TLC). PA and PC loaded was as a standard marker. (C) GNVs generated with whole lipids, PA-depleted lipids from GELNs and grapefruit ELNs, and supplementary PA with depleted lipids. PKH26-labeled GNVs exposed to LGG. PKH26-positive bacteria were quantitatively analyzed vis FACS. (D) FACS analysis of LGG incubated with PKH26-labeled GNVs from whole grapefruit ELN lipids with or without PC depletion and supplementary PC with depleted lipids. (E) A representative image of the duodenum, colon and liver from mice (n=5) receiving a gavage of DiR dye-labeled GNVs with or without PA or PC lipid (left); quantification of fluorescence intensity (right). Ginger GNVs vs ginger GNVs/PC⁺, *P<0.05; grapefruit GNVs vs grapefruit GNVs/PC⁻, # P<0.05 (F) PKH26-labeled GELNs were incubated with 1×10⁷ colony-forming units (CFU) of LGG, and uptake of PKH26-labeled GELNs was visualized using confocal microscopy. (G) Frequency of PKH67-labeled LGG and PKH26-labeled GELNs assessed using flow cytometry. Numbers in quadrants indicate the percentage of LGG in each. (H) A heat map showing the effect of GELNs on LGG mRNA expression determined by next-generation sequencing. (I) Venn diagram of all mRNAs detected in LGG. The numbers in brackets indicate the in vitro results. (J) A heat map based on LC-MS data showing the effect of GELNs on LGG proteins. (K) Venn diagram of all the proteins detected in LGG. (L) qPCR of LexA expression in LGG treated with gma-miR396e. *P<0.05 (two-tailed t-test). (M) Analysis of LGG proliferation after treatment with gma-miR396e. *P<0.05 (two-tailed t-test). The data are representative of three independent experiments (error bars, SD). See also Figure S2-3 and Table S4-6.

Figure 3.. GELN RNAs enhance LGG-mediated protection against mouse colitis

(A) GELN RNAs (1 μg) were packed in 100 nM ginger-derived lipid to form nanovectors (GNVs/GELN-RNAs) and were incubated with 1×10⁷ CFU of LGG. Uptake of PKH26-labeled GNVs/GELN-RNAs was visualized using confocal microscopy; 200x magnification; scale bar: 10 μm. (B) Proliferation of LGG treated with GNVs/GELN-RNAs over time. *P<0.05. (C) Schematic representation of the treatment schedule for DSS-induced colitis. (D) Body weight. GELN-RNAs vs scrambled RNAs, *P<0.05 and **P<0.01. (E) Survival of mice after administration of 2.5% DSS in drinking water. (F) Representative colons from mice treated as labeled in the figure (left); quantification of colon length (right). *P<0.05. (G) H&E-stained sections of colon (400x magnification) from mice treated as indicated in the figure. (H-J) Representative colons (H) from germ-free mice (n=5) treated as labeled in the figure (left); quantification of colon length (right). (I) Body weight. (J) H&E-stained sections of colon (400x magnification). *P<0.05; **P<0.01. (K) Wild-type (WT) and AHR knockout (KO) mice (n=5) supplied with 2.5% DSS after gavage with GELN RNAs or scrambled RNAs. ELISA analysis of IL-22, IL-1β and TNFα levels in colon mucus. The data are representative of three independent experiments (n=5; error bars, SD). *P<0.05; ** P<0.01 (two-tailed t-test); NS, not significant; (error bars, SD). Related to Figure S4.

Figure 4.. GELN RNAs mediate induction of IL-22 via inhibition of I3AM production

(A-B) The C57BL/6 mouse (n=5) treatment schedule was the same as that described in Figure 3C. Representative HPLC analysis of (A) indole-3-carboxaldehyde (I3A) and indole-3-acetaldehyde (IAAld) via detection of UV absorbance at 300 nm and (B) tryptophan and indole-3-acetamide (I3AM) using a fluorescence detector. Arrows point to the peak of the standard. *P<0.05; **P<0.01. (C-D) LGG grown in MRS medium with I3AM and GNV/scrambled RNAs or GNV/GELN-RNAs for 6 h. HPLC analysis of IAAld and I3A in the MRS medium. The concentrations of the metabolites listed in the figure were quantified (D). *P<0.05. (E) HPLC analysis of I3A in LGG cultures in the presence of I3AM at the time indicated in the figure. GNV/GELN-RNAs vs GNV; GNV/I3AM vs GNV; *P<0.05. (F) HPLC analysis of IAAld and I3A in MRS medium from LGG treated with I3AM at the different concentrations indicated in the figure without or with IAAld. *P<0.05; **P<0.01. (G) ELISA analysis of IL-22 in colon mucus of mice (WT, left; AHR KO, right) gavaged with MRS medium from LGG treated with I3AM. The data are representative of three independent experiments (error bars, SD). * P<0.05; ** P<0.01. Related to Figure 5.

Figure 5.. GELN RNAs protect mice from colitis by initiating regulation of monooxygenase ycnE expression in LGG.

(A) LC-MS spectra of monooxygenase ycnE from LGG. (B) Schematic diagram of the putative binding sites of mdo-miR7267-3p in the monooxygenase ycnE. (C) qPCR analysis of ycnE expression in LGG treated with mdo-miR7267-3p or scrambled miRNA. (D) HPLC analysis of I3AM and I3A in LGG cultures treated with mdo-miR7267-3p. (E) Hypothetical model of GELN RNA regulation of LGG I3A induction. I3AM inhibits the production of IAAId, which is a precursor of I3A synthesis. GELN-RNA pretreatment leads to a reduction in I3AM production. (F) Mice were treated with antibiotics in drinking water for one week followed by an oral gavage treatment, as indicated in the figure (n=5). HPLC analysis of I3A in feces. (G) Representative Western blot of AHR, phosphorylated AHR (pAHR) at Ser36, CYP1A1 and GAPDH (loading control) in colon lymphocytes. (H) Representative FACS analysis of IL-22, CD3 and RORγt expression in colon lymphocytes. The numbers in quadrants indicate the percentage of cells in each. (I) Colon lymphocytes isolated from WT and AHR KO mice (n=5) and incubated with I3A or supernatant from LGG treated with the agents listed in the figure. ELISA analysis of IL-22 in cell supernatants. (J) Representative colons from WT or IL-22 KO mice treated as listed in the figure (left); quantification of colon length (right). (K) H&E-stained sections of colon (400x magnification) from WT and IL-22 KO mice treated as indicated in the figure. The data (C, D, F, I, J) are representative of three independent experiments (error bars, SD). * P<0.05 and ** P<0.01 (two-tailed t-test); NS, not significant. Related to Figure 4 and Figure S4.

Figure 6.. GELN RNA treatment reduces bloodstream infections in DSS-induced colitis

(A) C57BL/6 mice supplemented with 2.5% DSS following gavage with 10⁹ CFU LGG treated with GNV/GELN-RNA or GNV/scrambled RNA. Representative numbers of bacteria colonies in the blood and liver cultured on MRS agar plates (uppers) and quantified (bottoms) as bacteria CFU; each symbol represents an individual mouse (n=5). *P<0.05 and **P<0.01 (two-tailed t-test). (B) Representative imaging of location of PKH26-labeled LGG (red) treated with PKH67-labeled GNVs (green) in the colon using confocal microscopy; 200x magnification; scale bar: 10 μm. (C) Blood cultured on MRS agar plates at different time points after gavage, as indicated in the figure, quantified (right) as CFU. *P<0.05. (D) Germ-free mice treated using the same procedure described in (A). *P<0.05. (E) Germ-free mice treated using the same procedure described in (B) and visualized with confocal microscopy; 200x magnification; scale bar: 25 μm. (F) MC38 cells and (G) Caco-2 cells were inoculated with LGG treated with GNVs/GELN-RNAs, and the frequency of PKH26-labeled LGG and PKH67-labeled GNVs/GELN-RNAs was assessed using flow cytometry. The numbers in quadrants indicate the percentage of LGG in each. (H, I) The number of intracellular bacteria was determined by plating on MRS plates. Quantification of CFU in H and I (right). *P<0.05. (J) Visualization via confocal microscopy of MC38 cells presented with LGG and LGG/GELN-RNAs. Arrows in red indicate LGG/PKH26; arrows in green indicate GNVs/GELN-RNAs/PKH67. Scale bars, 10 μm. 3D images showing colocalization of LGG/PKH26 and GNVs/GELN-RNAs/PKH67 in MC38 cells. The data are representative of three independent experiments (error bars, SD). Related to Figure S5.

Figure 7.. GELN miR-167a targets and down-regulates SpaC in LGG

(A) MC38 cells were inoculated with 10⁷ LGG prior to being presented with selected ginger ELN miRNAs. The number of intracellular LGG was determined by FACS (top) and the CFU number on MRS plates (bottom). (B) Quantification of CFU in A. *P<0.05. (C) Schematic diagram of the putative binding sites of ath-miR167a-5p in the WT SpaC gene. The ath-miR167a-5p seed matches in the SpaC gene are mutated at the positions indicated. (D) LGG were treated with ath-miR167a and administered via oral gavage to mice supplemented with 2.5% DSS. Representative numbers of bacterial colonies in the diluted aliquots of blood cultured on MRS agar. (E) qPCR quantification of LGG on mucus. *P<0.05. (F) ath-miR167a mimic knock-down of SpaC in LGG evaluated by qPCR. *P<0.05. (G) ath-miR167a mimic reduced SpaC protein in LGG, determined by Western blotting. (H) Immunogold labeling and electron microscopy of LGG using SpaC antiserum with protein A-10-nm gold particles. The location of gold particles (black arrow) on the pilus structure is indicated. (I) A portion of the sequence of the SpaC gene containing the potential miR-167a binding site was constructed into a GFP reporter vector to obtain pSpaC. A binding site mutant construct (pSpaCm-GFP) served as the control. *P<0.05 (two-tailed t-test). The data are representative of three independent experiments (error bars, SD). Related to Figure S7 and Figure 2.