Global patterns of 16S rRNA diversity at a depth of millions of sequences per sample

Abstract

The ongoing revolution in high-throughput sequencing continues to democratize the ability of small groups of investigators to map the microbial component of the biosphere. In particular, the coevolution of new sequencing platforms and new software tools allows data acquisition and analysis on an unprecedented scale. Here we report the next stage in this coevolutionary arms race, using the Illumina GAIIx platform to sequence a diverse array of 25 environmental samples and three known "mock communities" at a depth averaging 3.1 million reads per sample. We demonstrate excellent consistency in taxonomic recovery and recapture diversity patterns that were previously reported on the basis of metaanalysis of many studies from the literature (notably, the saline/nonsaline split in environmental samples and the split between host-associated and free-living communities). We also demonstrate that 2,000 Illumina single-end reads are sufficient to recapture the same relationships among samples that we observe with the full dataset. The results thus open up the possibility of conducting large-scale studies analyzing thousands of samples simultaneously to survey microbial communities at an unprecedented spatial and temporal resolution.

Fig. 1.

Protocol for barcoded Illumina pyrosequencing. First, conserved regions within the target gene (in this case, 16S rRNA) are identified (blue), together with an amplicon that clipping studies along the lines of ref. indicate are especially good for community sequence analysis (green). Second, PCR amplifications are performed, using primers that include a linker sequence not homologous to any 16S rRNA sequence at the corresponding positions, the barcode, and the Illumina adaptor. Thus, the match between the primer and the template sequence ends at the end of the black region of the primer, and the linker and adaptors (shown in color) do not match the template. This procedure yields a library of amplification products that contain the barcode and Illumina adaptors. Finally, three separate primers are used to yield the 5′ read, the 3′ read, and the index read (that yields the barcode sequence).

Fig. 2.

Reproducibility of taxon assignment at the order level and the genus level. Reproducibility of taxon assignment at the order level (A) is excellent; reproducibility at the genus level (B) is extremely consistent within a region, although the 5′ and 3′ regions lead to somewhat different assignments.

Fig. 3.

Comparison of α diversity measures in the mock community. (A) PD, or phylogenetic diversity, a measure showing the branch length on a phylogenetic tree that is covered by a given sample. (B) Number of observed species-level OTUs (at the 97% level) in each community. (C) Number of estimated species using the Chao1 estimator of species richness. The three replicates are shown in red, blue, and green; the true value for the mock community is shown as a dashed black line (note that the expected line shown in C is the true number of species, not the Chao1 estimate of this number, because Chao1 has no meaning when applied to a community that consists solely of singletons). Note the log scales on both axes. As with other sequencing platforms, aggressive quality filtering is required to correctly interpret diversity results from the Illumina platform.

Fig. 4.

UPGMA UniFrac clustering of the 5′ and 3′ reads from each environmental sample show that samples from a given environment type cluster together well. Samples are feces (blue), freshwater creek (bright green), freshwater lake (red), ocean (cyan), sediment (pink), skin (yellow), soil (dark green), and tongue (dark red). Jackknife-supported clusters showing >80% support are shown on the tree.

Fig. 5.

PCoA of the samples using sequences from each region. Samples are feces (blue), freshwater creek (bright green), freshwater lake (red), ocean (cyan), sediment (pink), skin (yellow), soil (dark green), and tongue (dark red). In the Procrustes analysis, using all reads, the samples derived from the 5′ end and the 3′ end are linked with a bar: in every case, the distance between the 5′ and 3′ reads of the same samples is much smaller than the distance between samples, highlighting the robustness of UniFrac analysis relative to the taxonomic analysis shown in Fig. 2. The smaller panels, using only 2,000 randomly chosen sequences per sample, show the weighted and unweighted UniFrac results from the 5′ and 3′ reads individually: the pattern of samples is highly reproducible (note that the direction of each axis is arbitrary, only the relative position of the points matters rather than whether a particular sample appears to the left or the right of the plot). As seen in ref , axis 1 is host associated/free living and axis 3 is saline/nonsaline environment.