Comparison of storage conditions for human vaginal microbiome studies

Abstract

Background: The effect of storage conditions on the microbiome and metabolite composition of human biological samples has not been thoroughly investigated as a potential source of bias. We evaluated the effect of two common storage conditions used in clinical trials on the bacterial and metabolite composition of the vaginal microbiota using pyrosequencing of barcoded 16S rRNA gene sequencing and (1)H-NMR analyses.

Methodology/principal findings: Eight women were enrolled and four mid-vaginal swabs were collected by a physician from each woman. The samples were either processed immediately, stored at -80°C for 4 weeks or at -20°C for 1 week followed by transfer to -80°C for another 4 weeks prior to analysis. Statistical methods, including Kolmogorovo-Smirnov and Wilcoxon tests, were performed to evaluate the differences in vaginal bacterial community composition and metabolites between samples stored under different conditions. The results showed that there were no significant differences between samples processed immediately after collection or stored for varying durations. (1)H-NMR analysis of the small molecule metabolites in vaginal secretions indicated that high levels of lactic acid were associated with Lactobacillus-dominated communities. Relative abundance of lactic acid did not appear to correlate with relative abundance of individual Lactobacillus sp. in this limited sample, although lower levels of lactic acid were observed when L. gasseri was dominant, indicating differences in metabolic output of seemingly similar communities.

Conclusions/significance: These findings benefit large-scale, field-based microbiome and metabolomic studies of the vaginal microbiota.

Figure 1. Heatmap of the relative abundance of microbial taxa characterized by 16S rRNA gene sequencing (left) and metabolic content featured by NMR (right) in samples from 8 participants (S01-S08) stored under three different conditions (C1-C3).

The community state types, the relative content of lactic acid and Nugent score are also shown. The unassigned NMR integration regions were labeled by chemical shift.

Figure 2. Distribution of 16S rRNA sequence data in UniFrac principal coordinates analysis (PCoA).

The symbols represent the 23 samples from 8 subjects summarized in Table 1 and 2. Symbols are colored by subject (shown in legend). The scatterplot is of principal coordinate 1 (PC1) plotted against principal coordinate 2 (PC2). The percentage of the variation in the samples described by the plotted principal coordinates in indicated on the axes.

Figure 3. ¹H NMR spectrum for subject #S08 at condition 1.

Enlarged spectral region of δ = 0.85–1.10 ppm from S08 in inset A and S03 in inset B. The major metabolites are labeled: 1) lactate; 2) alanine; 3) acetate; 4) succinate; 5) glutamate; 6) glutamine; 7) citrate; 8) creatine; 9) choline; 10) glucose; 11) maltose; residual lubricant ingredient 12) PEG; 13) n-butyrate; 14) iso-valerate; 15) Isoleucine; 16) leucine; 17) valine and 18) propionate.

Figure 4. One-dimensional ¹H NMR spectra of 24 aqueous vaginal samples from 8 participants (S01-S08) stored under three different conditions (C1 in black, C2 in red, and C3 in blue).

The Ward hierarchical clustering of samples was based on the normalized spectral integrals representing the relative proton abundance of the metabolites.