Viruses in the faecal microbiota of monozygotic twins and their mothers

Abstract

Viral diversity and life cycles are poorly understood in the human gut and other body habitats. Phages and their encoded functions may provide informative signatures of a human microbiota and of microbial community responses to various disturbances, and may indicate whether community health or dysfunction is manifest after apparent recovery from a disease or therapeutic intervention. Here we report sequencing of the viromes (metagenomes) of virus-like particles isolated from faecal samples collected from healthy adult female monozygotic twins and their mothers at three time points over a one-year period. We compared these data sets with data sets of sequenced bacterial 16S ribosomal RNA genes and total-faecal-community DNA. Co-twins and their mothers share a significantly greater degree of similarity in their faecal bacterial communities than do unrelated individuals. In contrast, viromes are unique to individuals regardless of their degree of genetic relatedness. Despite remarkable interpersonal variations in viromes and their encoded functions, intrapersonal diversity is very low, with >95% of virotypes retained over the period surveyed, and with viromes dominated by a few temperate phages that exhibit remarkable genetic stability. These results indicate that a predatory viral-microbial dynamic, manifest in a number of other characterized environmental ecosystems, is notably absent in the very distal intestine.

Fig. 1. Classification of viruses present in VLP preparations generated from fecal samples collected from four families of MZ twins and their mothers

Prophages are classified based on their bacterial host taxonomy. Prominent bacterial phyla are represented by different colors (Proteobacteria, blue; Firmicutes green; Bacteroidetes, red; Actinobacteria, black). Class-level taxa within these phyla are indicated. Phage and eukaryotic viruses are sorted according to taxonomy. Nomenclature used for VLP preparations from fecal biospecimens: F, family; T1, co-twin 1; T2, co-twin 2; M, mother of co-twins. Time points (1–3), and technical replicates (R) produced from a given sample are noted. The color bar at the bottom of the figure provides a reference key for the percent coverage of a viral genome in the NR_Viral_DB by reads from given VLP virome dataset (data normalized using 14,000 randomly selected reads/dataset).

Fig. 2. A sample-by-sample view of the proportional representation of KEGG second level pathways in sequenced VLP-associated viromes and gut microbiomes

Known or predicted proteins encoded by viruses in the NR_Viral_DB, fecal VLP-derived viromes, 121 sequenced reference human gut-associated microbial genomes, and fecal microbiomes are shown. See Fig. 1 for sample nomenclature.

Fig. 3. Gnotobiotic mice reveal in vivo activation of the transcriptome of a Marvinbryantia formatexigens prophage

Shown are the three predicted prophages present in M. formatexigens and the levels of expression of their ORFs in cecal and fecal micobial communities harvested from gnotobiotic mice co-colonized with Bacteroides thetaiotaomicron. Expression levels for genes in each prophage genome are from normalized RNA-Seq read count data (see color key; normalization based on sequencing effort and length of each predicted ORF). Active expression is defined as a normalized read count >100. R, technical replicate shows the reproducibility of the method for performing RNA-Seq analysis. RNA-Seq data are also presented for each prophage genome in M. formatexigens during mid-log phase growth in defined medium containing different carbon sources (NAG, N-acetylglucosamine). Red arrows indicate the position of toxin/anti-toxin gene pairs. Green arrows denote genes with hypothetical functions that are expressed in more than 50% of the conditions tested. ORF designations for the first and last genes in the predicted genomes of each prophage are provided.