Baseline microbiota composition modulates antibiotic-mediated effects on the gut microbiota and host

Abstract

Background: Normal mammalian development and homeostasis are dependent upon the gut microbiota. Antibiotics, essential for the treatment and prophylaxis of bacterial infections, can have collateral effects on the gut microbiota composition, which can in turn have far-reaching and potentially deleterious consequences for the host. However, the magnitude and duration of such collateral effects appear to vary between individuals. Furthermore, the degree to which such perturbations affect the host response is currently unclear. We aimed to test the hypothesis that different human microbiomes have different responses to a commonly prescribed antibiotic and that these differences may impact the host response.

Methods: Germ-free mice (n = 30) humanized with the microbiota of two unrelated donors (A and B) were subjected to a 7-day antibiotic challenge with amoxicillin-clavulanate ("co-amoxiclav"). Microbiome and colonic transcriptome analysis was performed, pre (day 0) and post antibiotics (day 8) and subsequently into recovery (days 11 and 18).

Results: Unique community profiles were evident depending upon the donor, with donor A recipient mice being dominated by Prevotella and Faecalibacterium and donor B recipient mice dominated by Bacteroides and Parabacteroides. Donor A mice underwent a marked destabilization of their microbiota following antibiotic treatment, while donor B mice maintained a more stable profile. Dramatic and overlapping alterations in the host transcriptome were apparent following antibiotic challenge in both groups. Despite this overlap, donor A mice experienced a more significant alteration in gene expression and uniquely showed correlations between host pathways and key microbial genera.

Conclusions: Germ-free mice humanized by different donor microbiotas maintain distinct microbiome profiles, which respond in distinct ways to antibiotic challenge and evince host responses that parallel microbiome disequilibrium. These results suggest that inter-individual variation in the gut microbiota may contribute to personalized host responses following microbiota perturbation.

Keywords: Antibiotics; Gut; Microbiome; Transcriptome.

Fig. 1

a Schematic of study design, including donor groups, antibiotic treatment, and recovery period as well as sampling points. b Barplots of relative genus-level abundance of the 50 most abundant OTUs in each sample. c Differentially abundant genera by DESeq2 between donor groups, including all time points. d Simpson diversity stratified by donor and time point

Fig. 2

a Genera differentially abundant (adjusted P value < 0.01) in donor A mice by DESeq2. b Similar to a but for donor B mice. c Weighted unifrac distance with per group. Results of the corresponding two-way PERMANOVA are presented in Table 1. d PCoA of weighted unifrac distances for donor A alone, with genera that correlate significantly with PCoA axes (Spearman’s correlation, P value after correction 0.1) and PERMANOVA R² and P value for univariate comparison. e PCoA for donor B as in d with weighted unifrac distances. No significant correlations were present. PERMANOVA R² and P value for univariate comparison

Fig. 3

a PCA plots of gene expression data following antibiotic treatments for all mice combined, clustered by day with respect to antibiotic treatment. b Heatmap of differentially expressed genes at the D18 vs D0 contrast. c GO enrichment analysis, followed by submission to REVIGO, stratified by contrast

Fig. 4

Gene expression analysis for both donor groups individually. a PCA as in Fig. 3a, isolating donor A gene expression. b PCA for donor B expression alone. c Contrasts with differential genes and the relative contribution from donor A and donor B. Red represents donor A, blue donor B, and white overlap. d D11 vs D8 heatmap of differential gene expression. e D18 vs D8 heatmap of differential gene expression. f GO enrichment analysis following submission to REVIGO, stratified by contrast for donor A. g As in f but for donor B

Fig. 5

Network plot of significant correlations between GO pathways drawn from GSVA and genera abundance for donor A mice determined by the HAllA method. Corresponding GO pathways are provided in Additional file 6