Subsistence strategies in traditional societies distinguish gut microbiomes

Abstract

Recent studies suggest that gut microbiomes of urban-industrialized societies are different from those of traditional peoples. Here we examine the relationship between lifeways and gut microbiota through taxonomic and functional potential characterization of faecal samples from hunter-gatherer and traditional agriculturalist communities in Peru and an urban-industrialized community from the US. We find that in addition to taxonomic and metabolic differences between urban and traditional lifestyles, hunter-gatherers form a distinct sub-group among traditional peoples. As observed in previous studies, we find that Treponema are characteristic of traditional gut microbiomes. Moreover, through genome reconstruction (2.2-2.5 MB, coverage depth × 26-513) and functional potential characterization, we discover these Treponema are diverse, fall outside of pathogenic clades and are similar to Treponema succinifaciens, a known carbohydrate metabolizer in swine. Gut Treponema are found in non-human primates and all traditional peoples studied to date, suggesting they are symbionts lost in urban-industrialized societies.

Figure 1. Alpha- and beta-diversity comparisons of the gut microbiomes of the Matses, Tunapuco and Norman populations.

Analyses were performed on 16S rRNA V4 region data, with a rarefaction depth of 10,000 reads per sample. (a) Alpha diversity comparisons based on phylogenetic and non-phylogenetic richness (Faith’s PD, observed species). The urban population has significantly lower microbial richness compared with the two rural populations. This observation is robust and observable even with <5,000 reads per sample (Supplementary Fig. 2). Whiskers in the boxplot represent the range of minimum and maximum alpha diversity values within a population, excluding outliers (b) Principal coordinates analysis of weighted UniFrac distances. Proportion of variance explained by each principal coordinate axis is denoted in the corresponding axis label. The rural and urban populations show clear separation.

Figure 2. Taxonomic profile of the gut microbiomes of the Matses, Tunapuco and Norman populations.

Analyses were performed on 16S rRNA V4 region data, rarefied to a depth of 10,000 reads per sample. (a) Relative taxa abundance plots for individuals from the three populations, summarized at the phylum level. Individuals are represented along the horizontal axis, and relative taxa frequency is denoted by the vertical axis. (b) Heatmap showing 33 genera with significant differences in abundance between populations (Kruskal–Wallis, FDR-corrected P<0.05). Individual boxplots for phyla and genera are shown in Supplementary Fig. 3. Heatmap is colour-coded based on row z-scores.

Figure 3. Comparison of the gut microbiomes of Matses, Tunapuco and Norman populations to published data from hunter-gatherer, rural agriculturalist and urban-industrial communities.

Analyses were performed on genus-level taxa tables rarefied to 4,000 reads per sample. (a) Principal coordinate analysis of Bray–Curtis distances generated from taxa tables summarized at the genus level. Proportion of variance explained by each principal coordinate axis is denoted in the corresponding axis label. Populations are colour coded by subsistence strategy. Data sets are represented by triangles (this study), circles (Yatsunenko et al.3), and squares (Schnorr et al.1). Ellipses correspond to 95% confidence boundaries for each of the three subsistence categories. (b) Results from Bayesian source-tracking analysis. Source contributions are averaged across samples within the population. (c) Results from Bayesian source tracking for individual samples.

Figure 4. Comparison of taxonomic and functional diversity of gut microbiomes between populations.

Proportion of variance explained by each principal coordinate axis is denoted in the corresponding axis label (a) Principal Coordinates Analysis of Bray–Curtis distances generated from KEGG Orthologue tables rarefied to 200,000 counts per sample. (b) Procrustes analysis between the taxonomic and the functional data sets on paired samples from the Matses, Tunapuco and Norman populations.

Figure 5. Heatmap of ECs showing significant differences between the gut microbiomes of Matses, Tunapuco and Norman populations.

Enzymes are grouped based on EC class. Comparisons between populations were performed using Kruskal–Wallis tests (FDR-corrected P<0.05). Heatmap is colour coded based on row z-scores.

Figure 6. Phylogenetic trees showing relationship of Matses Treponema strains to reference Treponema species.

(a) Maximum likelihood tree constructed using 16S rRNA sequences from de novo assemblies of shotgun data. (b) Maximum likelihood tree constructed using concatenated amino acid sequences from 35 single copy marker loci, retrieved from de novo assemblies of shotgun data. Both trees show similar topology, with the Matses Treponema strains grouping with Treponema succinifaciens, a known carbohydrate metabolizer in the swine gut microbiome.

Figure 7. Hierarchical clustering of Matses Treponema and reference bacterial strains based on KEGG functional potential data.

Open reading frames (ORFs) predicted from reconstructed Matses Treponema genomes were annotated using the MAPLE server and compared with reference bacterial genomes (including Spirochaetes). The Matses Treponema strains share functional similarities with Treponema succinifaciens, a known carbohydrate metabolizer and apathogenic member of the swine gut microbiome. *denotes the Matses Treponema strains.