Metagenomic microbial community profiling using unique clade-specific marker genes

Abstract

Metagenomic shotgun sequencing data can identify microbes populating a microbial community and their proportions, but existing taxonomic profiling methods are inefficient for increasingly large data sets. We present an approach that uses clade-specific marker genes to unambiguously assign reads to microbial clades more accurately and >50× faster than current approaches. We validated our metagenomic phylogenetic analysis tool, MetaPhlAn, on terabases of short reads and provide the largest metagenomic profiling to date of the human gut. It can be accessed at http://huttenhower.sph.harvard.edu/metaphlan/.

Fig. 1. Comparison of MetaPhlAn to existing methods

We used 10 total synthetic metagenomes to compare MetaPhlAn to PhymmBL, BLAST, theRITA pipeline, and NBC. a–b) Absolute and root mean squared (rms) errors with respect to 100 total organisms in one synthetic metagenome at the species (a) and class (b) level c) Correlations of inferred and true species abundances on 8 non-evenly distributed synthetic metagenomes;. d) Reads-per-second rates for the tested methods on single CPUs.

Fig. 2. Composition of healthy vaginal microbiota

MetaPhlAn species and genus abundances and 16S phylotype abundances for 51 healthy vaginal microbiomes from the Human Microbiome Project. Samples were naively grouped by assigning each based on its dominant (>50%) Lactobacillus species or by the absence (<2%) of any Lactobacillus. For each cluster (named from I to V) we report averages across samples for all genera and species as inferred by MetaPhlAn and, for genera, as estimated by the combination of mothur and the RDP classifier (see Methods) applied to 16S rRNA gene sequences from the same specimen.

Fig. 3. The gut microbiota in asymptomatic Western populations as inferred by MetaPhlAn on 224 samples combining the HMP and MetaHIT cohorts

a) A taxonomic cladogram reporting all clades present in one or both cohorts (≥0.5% abundance in ≥1 sample). Circle size is proportional to the log of average abundance; color represents relative enrichment of the most abundant taxa (≥1% average in ≥1 cohort) between the HMP (139) and MetaHIT (85, healthy only) populations. b–c) Genus- (b) and species-level (c) taxonomic profiles of the most abundant clades hierarchically clustered (average linkage) with the Bray-Curtis similarity reveal sets of samples with similar microbial community compositions. With the exception of the cluster dominated by genus Bacteroides (B. vulgatus and B. ovatus in particular), samples from both studies are present in all groups, confirming substantial consistency of the gut microbiota characterized by independent and geographically distant western-diet asymptomatic cohorts. Only species and genera with at least 7.5% abundances at the 95^th percentile of their distribution are reported.