Metagenomic detection of phage-encoded platelet-binding factors in the human oral cavity

Abstract

The human oropharynx is a reservoir for many potential pathogens, including streptococcal species that cause endocarditis. Although oropharyngeal microbes have been well described, viral communities are essentially uncharacterized. We conducted a metagenomic study to determine the composition of oropharyngeal DNA viral communities (both phage and eukaryotic viruses) in healthy individuals and to evaluate oropharyngeal swabs as a rapid method for viral detection. Viral DNA was extracted from 19 pooled oropharyngeal swabs and sequenced. Viral communities consisted almost exclusively of phage, and complete genomes of several phage were recovered, including Escherichia coli phage T3, Propionibacterium acnes phage PA6, and Streptococcus mitis phage SM1. Phage relative abundances changed dramatically depending on whether samples were chloroform treated or filtered to remove microbial contamination. pblA and pblB genes of phage SM1 were detected in the metagenomes. pblA and pblB mediate the attachment of S. mitis to platelets and play a significant role in S. mitis virulence in the endocardium, but have never previously been detected in the oral cavity. These genes were also identified in salivary metagenomes from three individuals at three time points and in individual saliva samples by PCR. Additionally, we demonstrate that phage SM1 can be induced by commonly ingested substances. Our results indicate that the oral cavity is a reservoir for pblA and pblB genes and for phage SM1 itself. Further studies will determine the association between pblA and pblB genes in the oral cavity and the risk of endocarditis.

Fig. 1.

Coverage of viral genomes by oropharyngeal metagenomic sequences: Epstein-Barr virus (A), E. coli phage T3 (B), P. acnes phage PA6 (C), and S. mitis phage SM1 (D). Similarities obtained from the chloroformed metagenome are shown in blue, and those from the filtered metagenome are shown in red. Nucleotide-level coverage (A, B, C, and top of D) was determined by alignment of metagenomic sequences to complete viral genome sequences obtained from the National Center for Biotechnology Information using BLAT. Amino acid level coverage (D, bottom) was plotted using significant tBLASTx (e-value <10⁻⁵) similarities to each genome. Contigs were assembled using the 454 gsAssembler and aligned to genomes using BLAT.

Fig. 2.

Taxonomic composition and diversity of the oropharyngeal metagenomes. (A) Composition of complete metagenomes as determined by best tBLASTx similarities to the nonredundant database (e-value <10⁻⁵). (B) Composition of viral communities. Viral relative abundances were determined by GAAS on the basis of tBLASTx similarities (e-value <10⁻⁵, percentage identity >30%, query coverage >80%) to a database containing all complete viral genomes currently available at the National Center for Biotechnology Information. (C) Monte Carlo analysis of cross-contig spectra for oropharyngeal metagenomes. The area of maximum likelihood is indicated by an arrow. The metagenomes were predicted to share more than 95% of genotypes with 30% of their relative abundances permuted.

Fig. 3.

Phylogenetic relationships between pblA sequences from saliva samples and reference genomes. The Bayes values show the proportion of sampled trees in which the sequences to the right of the branch point clustered together.

Fig. 4.

Phage induction assay. Data are presented as induction treatment on the x axis versus the mean number of phage events counted using flow cytometry (±SEM) on the y axis (n = 3). White wine, nicotine, soda, and soy sauce treatments were diluted 1:10, and the red wine treatment was diluted 1:100. Asterisks indicate that nicotine, soy sauce, and mitomycin C caused a statistically significant increase in phage count (P < 0.05).