Bacterial biogeography of the human digestive tract

Abstract

We present bacterial biogeography as sampled from the human gastrointestinal tract of four healthy subjects. This study generated >32 million paired-end sequences of bacterial 16S rRNA genes (V3 region) representing >95,000 unique operational taxonomic units (OTUs; 97% similarity clusters), with >99% Good's coverage for all samples. The highest OTU richness and phylogenetic diversity was found in the mouth samples. The microbial communities of multiple biopsy sites within the colon were highly similar within individuals and largely distinct from those in stool. Within an individual, OTU overlap among broad site definitions (mouth, stomach/duodenum, colon and stool) ranged from 32-110 OTUs, 25 of which were common to all individuals and included OTUs affiliated with Faecalibacterium prasnitzii and the TM7 phylum. This first comprehensive characterization of the abundant and rare microflora found along the healthy human digestive tract represents essential groundwork to investigate further how the human microbiome relates to health and disease.

Figure 1. Alpha diversity of each sample.

(a) Shannon diversity and (b) phylogenetic diversity (PD) at each body site for all four subjects, where points represent a sample. Five iterations of rarefied subsets of 200,000 sequences from each sample were used to calculate the values for both metrics and the average was plotted. Asterisks indicate statistical significance (Kruskal-Wallis test, p < 0.05).

Figure 2. Genera represented in the digestive tracts of four subjects (S1–S4).

Bars delineate unique genera and are coloured with the phylum level assignment for each group. A complete list of sequence counts for each phylum and generus grouped by sample are presented in Supplemental tables 3 and 4, respectively. Low abundance phyla comprising the “Other” category include Acidobacteria, Chloroflexi, Deinococcus-Thermus, Euryarchaeota, Lentisphaerae, Planctomycetes, Synergistetes and Tenericutes.

Figure 3. Contribution of different taxonomic groups to separation of samples based on phylogenetic information.

The contribution of each group is represented by the size of the circles (grey) overlayed onto a PCoA of unweighted UniFrac distances for all samples within the oral and digestive tract. Panels (a–d) represent variations in sample colouration to highlight potential relationships between sample clustering and metadata.

Figure 4. Venn diagrams demonstrating 97% OTU cluster overlap within broad sampling regions.

Numbers correspond to unique OTU clusters within a subset. To highlight shared OTUs, singleton clusters were removed before analysis.

Figure 5. Rank abundance plots and proportional taxonomic bar plots for sequences from Subject 1 pooled within various body sites and assigned to order.

To demonstrate taxonomic distribution at decreasing ranks, the data were split according to different logarithmic abundance ranges as appropriate. The low abundance orders comprising the “Other” category included Synergistales, Halanaerobiales, Mycoplasmatales, Xanthomonadales, Sphingobacteriales, Caulobacterales, Desulfobacterales, Legionellales, Oceanospirillales, Deinococcales, Methanobacteriales, Myxococcales, Anaerolineales, Methylophilales, Chromatiales, Thermales, Bdellovibrionales, Desulfuromonadales, Solirubrobacterales, Methanomicrobiales, Planctomycetales, Methylococcales, Anaeroplasmatales, Coriobacteriales, Desulfovibrionales, Rhizobiales, Rhodocyclales, Sphingomonadales, Victivallales. Plots for subjects 2–4 are available in Figures S5.

Figure 6. Abundance of V3 regions of 16S rRNA genes of targeted organisms within all samples.

The entire sequence dataset was queried for type strains of Streptococcus mutans, Treponema denticola, Clostridium difficile and Faecalibacterium prausnitzii. For results from additional target organisms, see Table S6.