Metagenomic Shotgun Sequencing of Endocervical, Vaginal, and Rectal Samples among Fijian Women with and without Chlamydia trachomatis Reveals Disparate Microbial Populations and Function across Anatomic Sites: a Pilot Study

Abstract

Chlamydia trachomatis is a sexually transmitted pathogen and a global public health concern. Little is known about the microbial composition and function across endocervical, vaginal, and rectal microbiomes in the context of C. trachomatis infection. We evaluated the microbiomes of 10 age-matched high-risk Fijian women with and without C. trachomatis using metagenomic shotgun sequencing (MSS). Lactobacillus iners and Lactobacillus crispatus dominated the vagina and endocervix of uninfected women. Species often found in higher relative abundance in bacterial vaginosis (BV)-Mageeibacillus indolicus, Prevotella spp., Sneathia spp., Gardnerella vaginalis, and Veillonellaceae spp.-were dominant in C. trachomatis-infected women. This combination of BV pathogens was unique to Pacific Islanders compared to previously studied groups. The C. trachomatis-infected endocervix had a higher diversity of microbiota and microbial profiles that were somewhat different from those of the vagina. However, community state type III (CST-III) and CST-IV predominated, reflecting pathogenic microbiota regardless of C. trachomatis infection status. Rectal microbiomes were dominated by Prevotella and Bacteroides, although four women had unique microbiomes with Gardnerella, Akkermansia, Bifidobacterium, and Brachyspira. A high level of microbial similarity across microbiomes in two C. trachomatis-infected women suggested intragenitorectal transmission. A number of metabolic pathways in the endocervix, driven by BV pathogens and C. trachomatis to meet nutritional requirements for survival/growth, 5-fold higher than that in the vagina indicated that endocervical microbial functions are likely more diverse and complex than those in the vagina. Our novel findings provide the impetus for larger prospective studies to interrogate microbial/microbiome interactions that promote C. trachomatis infection and better define the unique genitorectal microbiomes of Pacific Islanders. IMPORTANCE Chlamydia trachomatis is the primary cause of bacterial sexually transmitted infections worldwide, with a disturbing increase in annual rates. While there is a plethora of data on healthy and pathogenic vaginal microbiomes-defining microbial profiles and associations with sexually transmitted infections (STIs)-far fewer studies have similarly examined the endocervix or rectum. Further, vulnerable populations, such as Pacific Islanders, remain underrepresented in research. We investigated the microbial composition, structure, and function of these anatomic microbiomes using metagenomic shotgun sequencing among a Fijian cohort. We found, primarily among C. trachomatis-infected women, unique microbial profiles in endocervical, vaginal, and rectal microbiomes with an increased diversity and more complex microbial pathways in endocervical than vaginal microbiomes. Similarities in microbiome composition across sites for some women suggested intragenitorectal transmission. These novel insights into genitorectal microbiomes and their purported function require prospective studies to better define Pacific Islander microbiomes and microbial/microbiome interactions that promote C. trachomatis infection.

Keywords: Chlamydia trachomatis; endocervical microbiome; metabolomics; metagenomic shotgun sequencing; pathogenesis; rectal microbiome; sexually transmitted infections; vaginal microbiome.

FIG 1

Pipeline for clinical sample data generation, processing, and integration for the characterization of the endocervical, vaginal, and rectal microbiomes.

FIG 2

Taxonomic composition of the endocervical, vaginal, and rectal microbiota. (A) The relative abundance bar plots represent the top 28 species within the microbial community structure of the C. trachomatis-positive and -negative women. The colored boxes below indicate the Shannon index. The grid below the Shannon index indicates the presence or absence of bacterial vaginosis (BV), human papillomavirus (HPV), Neisseria gonorrhoeae (Ng), Candida albicans (CA), and/or Mycoplasma genitalium (Mg). (B) Anatomic site-specific microbial Shannon diversity for the endocervix, vagina, and rectum. Rectal samples had a statistically significant difference in Shannon diversity compared with endocervical (*, P < 0.05) and vaginal (***, P < 0.0005) samples. The difference for endocervix versus vagina was not significant (ns) as measured by Kruskal-Wallis test and Dunn’s multiple comparisons. The top 28 species in the vaginal (C) and endocervical (D) microbiomes with the most unique abundant gene content in VIRGO are plotted. Density curves for each species compare the distribution of the relative abundance of reads for the C. trachomatis-positive (in red) and -negative women (in green), and the vertical bars represent the individual data points. Significant differences in relative abundance of species between positive and negative women are shown (*, P < 0.05; **, P < 0.01). Statistical significance was determined using two-sample Wilcox test between the C. trachomatis-positive and -negative samples. The x axis represents the log₂ of the ratio of the unique gene content of a species divided by the gene content of the entire community.

FIG 3

Bray-Curtis hierarchical clustering of endocervical, vaginal, and rectal samples and principal coordinates analysis (PCoA) plot of samples from all three anatomic sites. (A) Clustering is based on species composition and percent abundance of microbial communities. Color key of percent abundance is indicated on the top: scale toward black (0) and yellow (100) indicates lower and higher percent abundance, respectively. Rows represent taxa, and columns represent samples. Grid below heatmap indicates the presence or absence of C. trachomatis (Ct), bacterial vaginosis (BV), human papillomavirus (HPV), Neisseria gonorrhoeae (Ng), Candida (CA), and Mycoplasma genitalium (Mg). (B) Principal coordinates analysis (PCoA) plot of samples from all three anatomic sites. C. trachomatis-positive and -negative samples from vaginal (C) and endocervical (D) sites based on Bray-Curtis distance (beta diversity). The first and second principal coordinates are represented.

FIG 4

Pie chart representation of community state types (CSTs) for patient sample 35V identified by the CST classifier VALENCIA based on the taxonomic outputs generated by four different databases. Represented databases: VIRGO (A), One Codex (B), Kraken (D), and Metaphlan (E). The reference bacterial compositions for CST-III-B (C) and IV-B (F) are shown for comparison.

FIG 5

Enterotypes of rectal microbiota based on taxonomic relative abundances at the genus level for C. trachomatis-positive and -negative women. Only genera with relative abundance of >1% on average are reported. Remaining taxa are grouped as “Other.” Enterotypes are indicated at the top of each relative abundance bar: enterotype 1 (ET-B), Bacteroides as the best indicator; enterotype 2, Prevotella as the driver, a genus whose abundance is inversely correlated with Bacteroides (ET-P); enterotype 3, distinguished by an overrepresentation of Firmicutes, most prominently Ruminococcus (ET-F, not present); N, indicates that an enterotype could not be predicted based on current enterotype compositions.

FIG 6

Spectral clustering of the top 50 predicted functional pathways in endocervical, vaginal, and rectal metagenomes. The clustering was based on the average abundance matrix of the predicted functional pathways with the greatest variance across the three anatomic sites. Rows represent the predicted functional categories of the bacterial communities, whereas the columns represent the sample identities. The color key of the average abundance is indicated above the heatmap. C. trachomatis infection status is indicated below the heatmap matrix. Key functional categories are indicated on the right above the functional pathway designations.

FIG 7

Functional profiling of the vaginal metagenomes for C. trachomatis-positive and -negative women. Functional categories were annotated using EggNOG v4.5 (see Materials and Methods). Functional profiles were stratified by species using the taxonomic profiling provided by VIRGO. y axis, functional categories; x axis, log 2 transformed gene counts for individual species.