Environmental microbiome diversity and stability is a barrier to antimicrobial resistance gene accumulation

Abstract

When antimicrobial resistant bacteria (ARB) and genes (ARGs) reach novel habitats, they can become part of the habitat's microbiome in the long term if they are able to overcome the habitat's biotic resilience towards immigration. This process should become more difficult with increasing biodiversity, as exploitable niches in a given habitat are reduced for immigrants when more diverse competitors are present. Consequently, microbial diversity could provide a natural barrier towards antimicrobial resistance by reducing the persistence time of immigrating ARB and ARG. To test this hypothesis, a pan-European sampling campaign was performed for structured forest soil and dynamic riverbed environments of low anthropogenic impact. In soils, higher diversity, evenness and richness were significantly negatively correlated with relative abundance of >85% of ARGs. Furthermore, the number of detected ARGs per sample were inversely correlated with diversity. However, no such effects were present in the more dynamic riverbeds. Hence, microbiome diversity can serve as a barrier towards antimicrobial resistance dissemination in stationary, structured environments, where long-term, diversity-based resilience against immigration can evolve.

Fig. 1. Diversity of the river and soil datasets.

(a) PCoA of the beta diversity based on Bray Curtis distance of ASV relative abundance data from riverbed materials (sediments: triangles & biofilms: circles) and soil (squares). Colors code for the country of origin. Ellipses were drawn based on a 95% confidence interval to represent samples from each of the substrates. (b) Alpha-diversity indices (Chao1 richness, Shannon diversity and Pielou evenness) from riverbed materials and soil collected from the seven countries.

Fig. 2. Heatmap of relative ARG abundances.

(a) in the river dataset, (b) in the soil dataset. Values are displayed after transformation to log10 scale. The list of ARGs is presented based on similarity in abundance patterns and displayed from high abundance (red) to below the detection limit (blue). Color coding on the right displays the class of antibiotics they confer resistance to. Samples are ordered according to similarity in ARG profiles represented by the dendrogram on top based on default Euclidian clustering from the ComplexHeatmap R package and color coded based on country of origin.

Fig. 3. Correlation analysis of the number of ARGs detected per sample with diversity metrics.

Linear Pearson correlation with Bonferroni correction for multiple testing from river environmental samples with Pielou Evenness (a), Shannon Diversity (b) and Chao1 Richness (c). Linear correlations from soil environmental samples with Pielou Evenness (d), Shannon Diversity (e) and Chao1 Richness (f). Colors depict the country of sample origin and the symbols depict the sample type.

Fig. 4. Correlation analysis of relative ARG abundance with observed diversity metrics.

Spearman rank correlation with Bonferroni correction for multiple testing from river environmental samples with Pielou Evenness (a), Shannon Diversity (b) and Chao1 Richness (c). Correlations from soil environmental samples with Pielou Evenness (d), Shannon Diversity (e) and Chao1 Richness (f). Filled bars represent significant, while hatched bars represent non-significant correlations. Colors depict the class of antibiotic the ARG confers resistance to. Only ARGs that were detected in at least 25% of samples of a dataset were tested.

Fig. 5. Correlation analysis of relative MGE abundance with observed diversity metrics.

Spearman rank correlation with Bonferroni correction for multiple testing from river environmental samples with Pielou Evenness (a), Shannon Diversity (b) and Chao1 Richness (c). Correlations from soil environmental samples with Pielou Evenness (d), Shannon Diversity (e) and Chao1 Richness (f). Filled bars represent significant, while hatched bars represent non-significant correlations.

Fig. 6. Distribution of pairwise Bray-Curtis dissimilarities.

Distribution of pairwise Bray-Curtis dissimilarities for river (a) and soil (b) dataset is displayed across all samples within the dataset as well as across those subsets of samples with the 20% lowest (Bottom 20%) and the 20% highest (Top 20%) total ARG abundance. Significance testing between pairwise dissimilarity distributions is performed through one-way ANOVA with post-hoc Tukey HSD.