Maturation of the gut microbiome and risk of asthma in childhood

Abstract

The composition of the human gut microbiome matures within the first years of life. It has been hypothesized that microbial compositions in this period can cause immune dysregulations and potentially cause asthma. Here we show, by associating gut microbial composition from 16S rRNA gene amplicon sequencing during the first year of life with subsequent risk of asthma in 690 participants, that 1-year-old children with an immature microbial composition have an increased risk of asthma at age 5 years. This association is only apparent among children born to asthmatic mothers, suggesting that lacking microbial stimulation during the first year of life can trigger their inherited asthma risk. Conversely, adequate maturation of the gut microbiome in this period may protect these pre-disposed children.

Fig. 1

Microbial compositions change in the gut over the first year of life. PCoA plots of weighted UniFrac distances. a Separation of the composition by sampling time point. b Separation of the bacterial populations by Partitioning around medoids (PAM) clusters (optimal number of clusters is 2; silhouette width = 0.30). The five most distinctive indicator OTUs for each of the two clusters were: PAM cluster 1 (N = 1019): Enterobacteriaceae, Staphylococcus, Streptococcus, Bifidobacterium and Enterococcus, and PAM cluster 2 (N = 677): Faecalibacterium, Bacteroides(x3), and Anaerostipes. Ellipses demonstrate the mean ± 2 SD in a and b. c Relationship between sampling time point and PAM cluster

Fig. 2

β-diversity in the 1-year fecal samples associates with later asthma. PCoA plots of weighted UniFrac distances. Microbial compositions are assessed in relation to a child’s asthma status at age 5 years, and stratified by maternal asthma. P-values correspond to Adonis PERMANOVA tests. Ellipses demonstrate the mean ± 1 SD of children, who at age 5 years were asthmatic (orange) (N = 58) or non-asthmatic (green) (N = 531). Subsets include: asthmatic mother, asthmatic (orange) (N = 25), and non-asthmatic (green) (N = 122); non-asthmatic mother, asthmatic (orange) (N = 33), and non-asthmatic (green) (N = 409)

Fig. 3

Relative abundances in the 1-year fecal samples associate with later asthma. Comparison among the 20 most abundant bacterial genera. Relative abundance of each genus is shown with respect to asthma at age 5 years in all children, and stratified by maternal asthma. P-values correspond to Wilcoxon rank-sum tests of the relative abundances, with significant values (P < 0.05) bolded. FDR limits were calculated for the comparisons: Bonferroni (all: P < 0.0025), Benjamini & Hochberg (all children: P < 0.0024, asthmatic mother: P < 0.0102, non-asthmatic mother: P < 0.05). A pseudocount (+1e−06) was added to all abundances for the log-scale presentation. The black dots indicate median values and the abundances are colored according to the asthmatic (orange) (N = 58) or non-asthmatic (green) (N = 531) status of the child at age 5 years

Fig. 4

Kaplan–Meier plots illustrate risk of asthma in the first 5 years of life according to Partitioning Around Medoids (PAM) cluster at 1 year. Comparisons shown of all children and stratified by maternal asthma, demonstrating interaction between PAM cluster and maternal asthma (P = 0.01). Associations are quantified by Cox proportional hazards regression, adjusted for presence of older children in the home (aHR, adjusted Hazard Ratio). Children with a transient asthmatic phenotype (remission before age 5 years) are excluded. Curves are colored according to cluster; All: PAM cluster 1 (red) (N = 28), PAM cluster 2 (blue) (N = 490). Subsets include: asthmatic mother, PAM cluster 1 (red) (N = 7), PAM cluster 2 (blue) (N = 113); non-asthmatic mother: PAM cluster 1 (red) (N = 21), PAM cluster 2 (blue) (N = 377)

Fig. 5

β-diversity at 1 year associates with asthma and allergic sensitization. PCoA plots of weighted UniFrac distances. Microbial compositions are assessed in relation to a child’s asthma status at age 5 years and allergic sensitization before age 18 months, and stratified by maternal asthma. P-values correspond to Adonis PERMANOVA tests. Ellipses demonstrate the mean ± 1 SD of children, who at age 5 years were: asthmatic and sensitized (red) (N = 12), asthmatic and not sensitized (purple) (N = 45), non-asthmatic and sensitized (blue) (N = 59), or non-asthmatic and not sensitized (green) (N = 465). Subsets include: asthmatic mother, asthmatic and sensitized (red) (N = 5), asthmatic and not sensitized (purple) (N = 19), non-asthmatic and sensitized (blue) (N = 15), and non-asthmatic and not sensitized (green) (N = 103); non-asthmatic mother: asthmatic and sensitized (red) (N = 7), asthmatic and not sensitized (purple) (N = 26), non-asthmatic and sensitized (blue) (N = 44), and non-asthmatic and not sensitized (green) (N = 362)