Delayed gut microbiota maturation in the first year of life is a hallmark of pediatric allergic disease

Abstract

Allergic diseases affect millions of people worldwide. An increase in their prevalence has been associated with alterations in the gut microbiome, i.e., the microorganisms and their genes within the gastrointestinal tract. Maturation of the infant immune system and gut microbiota occur in parallel; thus, the conformation of the microbiome may determine if tolerant immune programming arises within the infant. Here we show, using deeply phenotyped participants in the CHILD birth cohort (n = 1115), that there are early-life influences and microbiome features which are uniformly associated with four distinct allergic diagnoses at 5 years: atopic dermatitis (AD, n = 367), asthma (As, n = 165), food allergy (FA, n = 136), and allergic rhinitis (AR, n = 187). In a subset with shotgun metagenomic and metabolomic profiling (n = 589), we discover that impaired 1-year microbiota maturation may be universal to pediatric allergies (AD p = 0.000014; As p = 0.0073; FA p = 0.00083; and AR p = 0.0021). Extending this, we find a core set of functional and metabolic imbalances characterized by compromised mucous integrity, elevated oxidative activity, decreased secondary fermentation, and elevated trace amines, to be a significant mediator between microbiota maturation at age 1 year and allergic diagnoses at age 5 years (β_indirect = -2.28; p = 0.0020). Microbiota maturation thus provides a focal point to identify deviations from normative development to predict and prevent allergic disease.

Fig. 1. Clinical evaluation of CHILD participants and data collection from biological samples.

a Timeline of CHILD enrollment and clinical evaluations from gestation through 5-year evaluations. b Consort diagram of CHILD participants and samples included in this study, including the composition of participant allergic diseases and their interrelated diagnoses. Created with Biorender.com.

Fig. 2. Individual allergic disease progression and influences.

Multivariable conditional logistic regression, using the data collection site as a stratum, evaluating the odds ratio of developing a one or more atopic or allergic diagnoses (n = 592) and b one or more atopic or allergic diagnoses (1+, n = 592), two or more diagnoses of (2+, n = 107), and each of atopic dermatitis (AD, n = 282), food allergy (FA, n = 100), asthma (As, n = 127), or allergic rhinitis (AR, n = 141) when accounting for early-life and familial exposures. (*) p < 0.05, (.) p < 0.1. For forest plot, data were presented as adjusted odds ratios (95% confidence intervals) and exact p values: male p = 6.8e-05, antibiotic usage p = 2.0e-05, and ethnicity p = 5.1e-07.

Fig. 3. Diversity and microbiome-derived age of the infant’s gut.

Shannon diversity index of a 3-month samples for one or more atopic or allergic diagnoses (1+, n = 344), two or more allergic diagnoses (2+, n = 130), and individual clinical diagnoses at 5 years, i.e., atopic dermatitis (AD, n = 211), food allergy (FA, n = 73), asthma (As, n = 100), or allergic rhinitis (AR, n = 108), at 5 years, and healthy control (HC, n = 244) participants, as well as b 1-year samples for 1+ (n = 353, p = 0.039), 2+ (n = 82), and individual clinical diagnoses at 5 years, i.e., AD (n = 212, p = 0.021), FA (n = 75, p = 0.043), As (An = 103, p = 0.0097), or AR (n = 113), at 5 years, and HC (n = 236) participants, c Scatterplot between chronological age and microbiome-derived age with linear regression line of best fit (Pearson R = 0.89, p < 2.2e-16). d Predicted age and chronological age for aggregate and individual clinical diagnoses as compared to no diagnoses at 5 years. e Predicted age of 1-year samples for 1+ (n = 353, p = 0.000036), 2+ (n = 82, p = 0.0023), and individual clinical diagnoses at 5 years, i.e., AD (n = 212, p = 0.000014), FA (n = 75, p = 0.00083), As (n = 103, p = 0.0073), or AR (n = 113, p = 0.0021), at 5 years, and HC (n = 236) participants. P values are from Wilcoxon tests between HC and each allergic diagnosis (b, c, e). For box plots, data are presented as box plots (center line at the median, upper bound at 75th percentile, lower bound at 25th percentile) with whiskers at minimum and maximum values. (*) p < 0.05.

Fig. 4. Important underlying microbiota of early-life microbiome age.

a Top 25 most important species in predicted age determination, shaded according to the MaAsLin2 regression coefficient with predicted age, adjusting chronological age and with a random effect of the sample collection site. The size of the points represents logarithmic relative abundance. b Venn diagram of the top 25 important species in predicted age and differential within atopic disease  as compared to healthy controls. c The nine commonly identified species within one or more atopic or allergic diagnoses (1+, n = 353), two or more allergic diagnoses (2+, n = 82), and individual clinical diagnoses at 5 years, i.e., atopic dermatitis (AD, n = 212), food allergy (FA, n = 75), asthma (As, n = 103), or allergic rhinitis (AR, n = 113), at 5 years, as compared to healthy control (HC, n = 236) participants, adjusting for chronological age at the time of collection and with a random effect of the sample collection site. Data were presented as MaAslin2 coefficients ± standard error.

Fig. 5. Functional differences within the early-life gut microbiome of infants later diagnosed with atopic diseases.

a MaAslin2 volcano plot of Metacyc-annotated gene pathways using predicted age as the outcome, adjusting for chronological age and a random effect of the sample collection site. b 11 pathways associated with predicted age and differential within four or more atopic disease differential analyses (individual or aggregate; FDR < 0.1). c Heatmap of spearman correlation analysis between 11 pathways of interest and nine species identified in Fig. 4.

Fig. 6. Relating significant microbiome features with metabolic profiles in the gut.

a Principal component analysis (PCA) plot of variance within the 1-year gut metabolome and colored by predicted age distribution. b Weighted gene coexpression analysis (WGCNA)-determined modules and interactions of metabolites in the 1-year gut, mapped using Cytoscape. c Spearman correlation heatmap of the relationship between metabolites, WGCNA clusters, and microbiome features of interest identified in Figs. 3, 4. (*) q < 0.05.

Fig. 7. Linking predicted age and allergic disease using specific microbial and metabolomic features.

Structural equation modeling (SEM) diagram showing the direct and indirect effects of predicted age upon atopic and allergic disease, as mediated by the 1-year microbiome and metabolome features.