Longitudinal comparison of the developing gut virome in infants and their mothers

Abstract

The human gut virome and its early life development are poorly understood. Prior studies have captured single-point assessments with the evolution of the infant virome remaining largely unexplored. We performed viral metagenomic sequencing on stool samples collected longitudinally from a cohort of 53 infants from age 2 weeks to 3 years (80.7 billion reads), and from their mothers (9.8 billion reads) to examine and compare viromes. The asymptomatic infant virome consisted of bacteriophages, nonhuman dietary/environmental viruses, and human-host viruses, predominantly picornaviruses. In contrast, human-host viruses were largely absent from the maternal virome. Previously undescribed, sequence-divergent vertebrate viruses were detected in the maternal but not infant virome. As infants aged, the phage component evolved to resemble the maternal virome, but by age 3, the human-host component remained dissimilar from the maternal virome. Thus, early life virome development is determined predominantly by dietary, infectious, and environmental factors rather than direct maternal acquisition.

Keywords: SURPI; alpha diversity; bacteriophages; beta diversity; infant gut virome; maternal virome; metagenomic sequencing; microbiome; microviruses; parechovirus; picornaviruses; principal component analysis.

Graphical abstract

Figure 1

Overview of STORK sample and data collection and virome composition in infants and mothers over time (A) Stool samples for mothers and infants were collected at each household visit. Time points are shown by visit, including visits to the mother during the second trimester (Mtrim2), third trimester (Mtrim3), and in year 1 of infant life (M1–M3) and visits to the infant in year 1 (B1–B3), year 2 (B4–B6) and year 3 (B7–B9) of infant life. Medical records for the infants were reviewed and clinical metadata extracted at the time points indicated by “Chart Review.” (B) Distribution of the most abundant phage/viral families in infants based on mean relative abundance. P indicates prokaryotic host range, while E indicates eukaryotic host range. (C) Distribution of the most abundant viral families in mothers based on mean relative abundance. P indicates prokaryotic host range, while E indicates eukaryotic host range. (D and E) Fractional abundance of eukaryotic (human pathogenic), diet/environmental, and prokaryotic viruses in infants and mothers.

Figure 2

Abundance (log₁₀), alpha diversity, and beta diversity over the first 3 years of life (A–D) Box and whiskers plot, by DNA or RNA genome, of (A) phage abundance, (B) phage Shannon diversity, (C) human-host virus abundance, and (D) human-host virus Shannon diversity. (E) Principal coordinate analysis (PCoA) plot showing infants clustered by Jaccard distances from bacteriophage. (F) PCoA plot of infants clustered by Jaccard distances of human-host viruses. Samples are colorized with an age gradient (light to dark orange representing the visits of B1–B9, see Table 1 for age ranges). The top 5 taxa driving clustering are shown as a biplot. Abbreviations: AN, Anelloviridae sp.; EA, Enterovirus A; GO: human gut gokushovirus; GW, gokushovirus WZ-2015a; LP, Lactococcus phage 936 sensu lato; PA, parechovirus A; PO, Poophage MBI-2016a; TT, torque teno virus-like mini virus; TV, Torque teno virus; VI, Vibrio phage JSF5. ^∗p < 0.01, ^∗∗p < 0.001, NS, no significance. Wald test (see Table S5).

Figure 3

Distribution of viral families in infants Heatmap distribution of the log₁₀ abundance of the top 14 viral and phage families in infants for visits B1–B9. Black indicates zero counts.

Figure 4

Comparison of viral abundance, alpha diversity, and beta diversity between infants and mothers (A–D) Box and whiskers plot of (A) prokaryotic phage abundance, (B) prokaryotic phage Shannon diversity, (C) human-host-virus abundance, and (D) human-host-virus Shannon diversity. (E) PCoA plot of infant and mother samples, clustered by Jaccard distances of bacteriophage and archaeal viral counts. (F) PCoA plot of infant and mother samples using human virus counts clustered with Jaccard distances. Samples are colorized with an age gradient, with a light to dark orange representing the visit ID of the infants, and a range of light to dark blue representing samples from the mothers (infants B1–B9, mothers MTrim2–MTrim3 and M1–M3, see Table 1 for age ranges). The top 5 taxa driving clustering are shown as a biplot. Abbreviations: CR, circular rep-encoding single-stranded (CRESS) virus sp.; GW, gokushovirus WZ-2015a; GO, human gut gokushovirus; HP, human picobirnavirus; LP, Lactococcus phage 936 sensu lato; MI, Microviridae sp.; PA, parechovirus A; PI, picobirnavirus sp.; PO, Poophage MBI-2016a; TT, torque teno virus-like mini virus. D, DNA virus/phage; R, RNAvirus/phage, ^∗p < 0.005, ^∗∗p < 0.0001, NS, no significance. Wald test (see Table S5).

Figure 5

Comparison of mothers (M3) and infants (B9) sampled at the last time point Box and whiskers plot of (A) phage DNA abundance, (B) phage RNA abundance, (C) phage DNA Shannon diversity, (D) phage RNA Shannon diversity, (E) DNA human virus abundance, (F) RNA human virus abundance, (G) DNA human virus Shannon diversity, (H) RNA human virus Shannon diversity, (I) heatmap of phage/viral family abundances at B9 for infants and M3 for mothers (see Table 1 for visit ID details). Black indicates zero counts. Significance is via Kruskal-Wallis tests. ^∗p < 0.05, ^∗∗p < 0.005.

Figure 6

Identification of sequence-divergent vertebrate viruses in infant and maternal viromes (A) De novo assembly of viral and unmatched reads into contiguous sequences (contigs) using de Bruijn graphs was performed, followed by contig alignment to the GenBank protein database. After filtering out spurious hits to non-viral organisms, contigs were classified as derived from canonical or sequence-divergent viruses based on degree of sequence homology. (B) Canonical vertebrate viruses. (C) Sequence-divergent vertebrate viruses. Note that the 13 individual viruses identified from babies (left) exhibit 52%–90% nucleotide sequence identity to reference viruses in GenBank, while the 3 viruses from mothers (right, highlighted in red boldfaced text) only exhibit sequence identity at the amino acid level (30%–70%).