Patterns in the skin microbiota differ in children and teenagers between rural and urban environments

Abstract

The composition of human microbiota is affected by a multitude of factors. Understanding the dynamics of our microbial communities is important for promoting human health because microbiota has a crucial role in the development of inflammatory diseases, such as allergies. We have studied the skin microbiota of both arms in 275 Finnish children of few months old to teenagers living in contrasting environments. We show that while age is a major factor affecting skin microbial composition, the living environment also discriminates the skin microbiota of rural and urban children. The effect of environment is age-specific; it is most prominent in toddlers but weaker for newborns and non-existent for teenagers. Within-individual variation is also related to age and environment. Surprisingly, variation between arms is smaller in rural subjects in all age groups, except in teenagers. We also collected serum samples from children for characterization of allergic sensitization and found a weak, but significant association between allergic sensitization and microbial composition. We suggest that physiological and behavioral changes, related to age and the amount of contact with environmental microbiota, jointly influence the dynamics of the skin microbiota, and explain why the association between the living environment skin microbiota is lost in teenager.

Figure 1. The diversity of skin microbiota in different age groups.

(a) Diversity in skin microbiota tends to increases with age. Diversity was calculated with q = 1, which corresponds to Shannon’s index. Box colour indicates the living-environment and the purple line indicates the mean diversity for each age group. In the oldest age group, children living in rural area (n = 26) have significantly lower diversity than those living in Helsinki (Urban, n = 8): P = 0.018. (b) The increase in diversity during the first eight years of life is associated with a reduced dominance of the Order Lactobacillales (namely Streptococcus) and a relatively even increase in other taxa, whereas the reduction in diversity in puberty is due to Actinobacteria (such as Propionibacterium acnes) becoming dominant. Means (±SE) are given for each age group.

Figure 2. The composition of skin microbiota differs between urban and rural children.

(Main panel) Predictions from random forest (RF) analyses plotted as an ordination. The x-axis shows the predicted age and the y-axis shows the predicted land-use around the current home. The variances explained indicate how well skin microbiota independently predicts either age or land-use. Symbol size indicates true age in months, symbol shape indicates the living environment of the current home (Urban, Rural, or Semi-urban), and the lines give spline fits to the respective groups. In the case a child had moved from the home at birth, the color of the symbol indicates the environment of the subject at birth. RF analyses were based on sqrt-transformed, CSS-normalised counts. RF analysis gives the OTUs which are the most important discriminators between subjects: The upper panel shows the relative proportion of OTU 12 (Streptococcus) across predicted age. The right panel shows the sum of proportions of several OTUs across the predicted land-use gradient. The segregation between living environments is not due to different variances along the land-use gradient for children of different age (Levene’s test: F = 0.45, P = 0.81), nor differences in sample size (X² = 3.39, P = 0.64).

Figure 3. The between- and within-individual variation in the skin microbiota.

The x-axis in figures shows the Bray-Curtis dissimilarity between compared samples, and grey vertical lines are the average values of given groups. In figures (a) and (b) samples from the dominant and non-dominant arms have been compared, while in figure (c) the dominant arms of different individuals have been compared. Figure (a) shows that the intra-individual dissimilarity between arms is significantly smaller than inter-individual dissimilarity. Figure (b) shows that the intra-individual dissimilarity between arms is significantly smaller in rural than in urban children. Figure (c) shows that the inter-individual dissimilarities are significantly smaller between sibling-pairs than in other pairs meaning that children share more of their microbiota with their children than with other children. Our data included one dizygotic twin-pair (teenagers of different sex), who shared more of their microbiota than sibling pairs on average, providing interesting example about the effect of shared microbiota.