Enteric viruses evoke broad host immune responses resembling those elicited by the bacterial microbiome

Abstract

The contributions of the viral component of the microbiome-the virome-to the development of innate and adaptive immunity are largely unknown. Here, we systematically defined the host response in mice to a panel of eukaryotic enteric viruses representing six different families. Infections with most of these viruses were asymptomatic in the mice, the magnitude and duration of which was dependent on the microbiota. Flow cytometric and transcriptional profiling of mice mono-associated with these viruses unveiled general adaptations by the host, such as lymphocyte differentiation and IL-22 signatures in the intestine, as well as numerous viral-strain-specific responses that persisted. Comparison with a dataset derived from analogous bacterial mono-association in mice identified bacterial species that evoke an immune response comparable with the viruses we examined. These results expand an understanding of the immune space occupied by the enteric virome and underscore the importance of viral exposure events.

Keywords: enteric virome; host-virome relationship; regulation of the enteric immune system; virome; virus.

Figure 1.. Colonization and Bacterial Dependence of Enteric Viruses Following the Natural Route of Infection

(A-B) Stool (A) and blood (B) collected over time from conventional (black) and GF mice (colored) inoculated with indicated viruses. Viral titers were quantified by plaque assay or qPCR. Symbols indicate individual samples. Lines pass through the mean at each timepoint. Shadowed areas indicate SEM. Gray areas indicate limit of detection. N = 4–8 mice per condition, combined from two independent experiments. (C) Neutralizing antibodies in sera of mice 28 days post-inoculation (dpi) with RRV quantified by a plaque-reduction neutralization assay. Reduction in plaque-forming units (PFU) shown as percent relative to control sera from naïve conventional mice. Results are from 3–9 mice from three independent experiments. n.d.: not determined. See also Figure S1 and Table S1.

Figure 2.. Enteric Viruses Promote Changes in Immune Cell Populations

(A) Heatmap showing average fold-change for cLP and siLP immune populations identified by flow cytometry (gating strategy in Fig. S2) for mice inoculated with individual viruses or MDF relative to GF controls with an FDR<0.1. Gray: FDR>0.1. Bar graph on top represents the proportion of immune populations with an FDR<0.1 and a fold change>1.5. (B-E) Fold changes of CD62L⁺CD44⁻ (B), CD62L⁻CD44⁺ (C), T-bet⁺ (D), and pDCs (E) in the cLP CD4⁺ (B-D), CD8⁺ (B-C), or CD45⁺ (E) populations. Each dot represents a single sample. (F-G) Percentage of Foxp3⁺ cells in the cLP (F) or siLP (G) CD4⁺ populations. Each dot represents a single sample. (H-I) Hierarchical clustering based on cLP (H) and siLP (I) population frequencies. (J-K) Effect size determined by db-RDA of viral characteristics: identity, genome, persistence, and viremia as explanatory variables of the cLP (J) and siLP (K) population frequency variance. Pie charts represent combined effect size of genome, persistence, and viremia. Statistical significance was calculated by one-way ANOVA followed by Dunn’s post-hoc analysis and corrected for multiple testing by the Benjamini-Hochberg procedure (A-E) or by non-parametric Mann-Whitney test (F-G). See also Figures S2–3 and Table S2.

Figure 3.. Enteric Viruses Increase Cytokine Production by Immune Cells

(A) Heatmaps showing average fold-change for cytokine-producing immune cells in cLP and siLP identified by flow cytometry for mice inoculated with the viruses shown or MDF relative to GF controls with an FDR<0.1. Gray: FDR>0.1. (B-D) Fold-changes of IFN-γ+ (B) and IL-22⁺ (C-D) cells in the cLP CD4+ and CD8⁺ (B), cLP CD45⁺ (C), and siLP CD45⁺ (D). (E-F) Representative dot plot (E) and percentage of IFN-γ⁺IL-10⁺ cells in the cLP CD4⁺ T cell population (F). (G-H) Hierarchical clustering of the different microbial associations based on the cLP (G) and siLP (H) cytokine production frequencies. (I-J) Effect size determined by db-RDA of viral characteristics: identity, genome, persistence, and viremia as explanatory variables of the cLP (I) and siLP (J) cytokine-producing immune cell frequency variance. Pie charts represent the combined effect size of genome, persistence, and viremia. Statistical significance was calculated by one-way ANOVA followed by Dunn’s post-hoc analysis and corrected for multiple testing by the Benjamini-Hochberg procedure (A-B), by Kruskal-Wallis test followed by Dunn’s post-hoc analysis (C-D), or by non-parametric Mann-Whitney test (F). See also Figure S4 and Table S2.

Figure 4.. Intestinal Transcriptome of Virus-Infected Mice

(A-B) Heatmaps showing DE genes (|average fold-change over GF|≥2 and unadjusted p- value≤0.01) in the colon (A) and small intestine (B) of virus-infected mice compared with GF mice. C: colon; SI: small intestine. (C) Number of DE genes in colon and small intestine for each condition compared with GF mice. (D-E) Venn diagrams depicting the number and overlap of DE genes in all virus-infected and MDF-associated mice in colon (D) and small intestine (E). (F-G) Top 15 most highly enriched biological process GO terms for DE genes in the colon (F) and small intestine (G) of virus-infected and MDF-associated mice. (H-I) Heatmaps showing Euclidean distances between group centroids of DE genes in colon (H) and small intestine (I) comparing each condition. Boxes outlined in black indicate significant differences (PERMANOVA<0.05). (J-K) Effect size determined by db-RDA of virus characteristics as explanatory variables of the DE gene variance in the colon (J) and small intestine (K). Pie charts represent the combined effect size of genome, persistence, and viremia. (L) Effect size determined by db-RDA of immune population frequencies from Figure 2 on DE gene variance in colon and small intestine. Boxes outlined in black indicate p-value<0.05. See also Figure S5 and Table S3.

Figure 5.. Intestinal Gene Expression Common and Specific to Individual Viruses

(A-B) Heatmaps displaying normalized expression values of DE genes (average fold-change over GF≥2 and unadjusted p-value≤0.01) modulated by at least five viruses in colon (A) and small intestine (B). (C-D) Heatmaps displaying normalized expression values of DE genes (average fold-change over GF≥1.5 and unadjusted p-value≤0.01) annotated in GO:0050829, GO:0050830, and GO:0061844 in colon (C) and small intestine (D). (E-F) DE genes from colonic transcriptomes of virus-infected mice analyzed by Ingenuity Pathway Analysis. Results from Canonical Pathway Analysis (E) and Upstream Regulator Analysis (F) relating to IFN signaling are shown. (G-H) Colonic (G) and small intestinal (H) DE genes analyzed by IPA for upstream regulators. Top 10 upstream regulators for each virus with an activation score>1 are depicted. See also Figure S6.

Figure 6.. Intestinal Transcriptomes of Virus-Infected Mice Are Enriched for Bacterial Microbiome Gene Signatures

(A-D) Colonic (A-B) and small intestinal (C-D) transcriptomes from virus-infected mice compared with gene expression signatures of bacterially colonized mice by GSEA. Gene sets upregulated following colonization by bacteria are depicted in A and C; downregulated gene sets are depicted in B and D. (E) GSEA plot showing enrichment of the E. faecalis upregulated gene set in the colonic transcriptome of mice infected with MNV CR6. (F-G) Hierarchical clustering of immune population frequencies described in Table S5. Purple: viruses; dark purple: MDF and GF from this study; orange: bacteria; pink: conventional SPF and GF from Geva-Zatorsky et al. See also Figure S6 and Table S4–5.