A metagenomic approach to characterization of the vaginal microbiome signature in pregnancy

Abstract

While current major national research efforts (i.e., the NIH Human Microbiome Project) will enable comprehensive metagenomic characterization of the adult human microbiota, how and when these diverse microbial communities take up residence in the host and during reproductive life are unexplored at a population level. Because microbial abundance and diversity might differ in pregnancy, we sought to generate comparative metagenomic signatures across gestational age strata. DNA was isolated from the vagina (introitus, posterior fornix, midvagina) and the V5V3 region of bacterial 16S rRNA genes were sequenced (454FLX Titanium platform). Sixty-eight samples from 24 healthy gravidae (18 to 40 confirmed weeks) were compared with 301 non-pregnant controls (60 subjects). Generated sequence data were quality filtered, taxonomically binned, normalized, and organized by phylogeny and into operational taxonomic units (OTU); principal coordinates analysis (PCoA) of the resultant beta diversity measures were used for visualization and analysis in association with sample clinical metadata. Altogether, 1.4 gigabytes of data containing >2.5 million reads (averaging 6,837 sequences/sample of 493 nt in length) were generated for computational analyses. Although gravidae were not excluded by virtue of a posterior fornix pH >4.5 at the time of screening, unique vaginal microbiome signature encompassing several specific OTUs and higher-level clades was nevertheless observed and confirmed using a combination of phylogenetic, non-phylogenetic, supervised, and unsupervised approaches. Both overall diversity and richness were reduced in pregnancy, with dominance of Lactobacillus species (L. iners crispatus, jensenii and johnsonii, and the orders Lactobacillales (and Lactobacillaceae family), Clostridiales, Bacteroidales, and Actinomycetales. This intergroup comparison using rigorous standardized sampling protocols and analytical methodologies provides robust initial evidence that the vaginal microbial 16S rRNA gene catalogue uniquely differs in pregnancy, with variance of taxa across vaginal subsite and gestational age.

Figure 1. Beta diversity metrics of bacterial 16S rRNA genes reveal distinctly clustered vaginal microbiome communities structured by pregnancy.

Datasets were minimally filtered for removal of singletons (left panels) or filtered for chimeras (right panels; QIIME ChimeraSlayer). Beta diversity microbiome community clustering is observed for non-phylogenetic methods ((A) normalized Canberra), binary non-phylogenetic methods ((B) binary Chord, (C) binary Ochiai), and phylogenetic beta diversity metrics ((D) unweighted UniFrac). In each panel, each point corresponds to a vaginal sample from either a pregnant (green) or non-pregnant (blue) subject. The percentage of variation explained by the plotted principal coordinates is indicated on the axes.

Figure 2. Subclassification of microbial community structure by vaginal subsite and week of gestation.

(A) Pregnancy clusters vaginal microbial communities, while site of vaginal sampling minimally contributes to within cluster formation. Canberra beta diversity metric with PCoA plot clustering. Each dots represents one sample from the distinct vaginal subsites (mid vagina, posterior fornix, and vaginal introitus) of individual subjects from pregnant (green shades) and non-pregnant (blue and purple shades). (B) Among gravid subjects, microbial community richness and diversity (Shannon indices) vary by week of gestation and proximity to the uterus. Community richness and Shannon diversity indices by gestational age and vaginal sampling site against normalized abundance values from both OTU and phylogeny based analysis charted by vaginal site (posterior fornix, mid vagina, introitus) and gestational age. Richness - Black; Diversity – Dark Red; Left panel designates OTU based; Right panel designates Phylogeny based. Gestational age interval shown in weeks, or designated as non-pregnant (NP). Error bars denote variance (standard error of the mean, s.e.m.). In each of the gestational age intervals, an equivalent number of gravidae were sampled and compared (n = 6 per strata).

Figure 3. Measures of within community diversity (alpha diversity) at two levels of data filtering.

Black lines indicate pregnant cohort, with red lines indicating non-pregnant cohort. Data sets were subjected AbundantOTU (left panels), or denoising and chimera slaying with removal of singletons and chimeras (right panels). (A) Rarefaction alpha diversity metrics note significantly lower richness in the pregnant data set, while (B) Renyi alpha diversity metrics indicates significantly less diversity among pregnant vaginal communities following denoising. Significance is denoted by the absence of curves crossing over at any point following denoising and chimera slaying (right panels).

Figure 4. Global phylogenetic trees after AbundantOTU and QIIME denoising.

Global phylogenetic trees show the distribution of taxonomy among all the pregnant and non-pregnant subject samples. The internal cluster dendrograms are colored by taxa Family level projections (annotated in figure legend), while the mid-circle is colored by the majority origins of OTUs from pregnant or non-pregnant subject samples (pregnant-magenta; non-pregnant-brown). Outermost circle using text to indicates OTU projection to Order level (Bacteroidales-red, Actinomycetales-yellow, Lactobacillales-green, Clostridiales-blue). OTU tables and representative sequences generated from AbundantOTU ( Figure 4A ) and QIIME denoised ( Figure 4B ) datasets were employed in generating these global phylogenetic trees.

Figure 5. Metagenomics-based discovery of bacterial taxa contributing to differentiation of vaginal communities in pregnancy.

Bacterial taxa were selected as significantly differentially abundant between pregnant and non-pregnant communities (regardless of sampling site) by the LDA Effect Size (LEfSe) algorithm, (left panel) sorted by degree of difference (listing only taxonomic leaves) and (right panel) overlayed on a complete taxonomy. Taxa are again reduced in diversity during pregnancy, with several specific Lactobacillus OTUs detected uniquely among pregnant individuals. OTU tables and representative sequences generated from AbundantOTU ( Figure 5A ) and QIIME denoised ( Figure 5B ) datasets were employed in LEfSe analyses.