Metagenomic analysis of mother-infant gut microbiome reveals global distinct and shared microbial signatures

Abstract

Emerging evidence indicates maternal microbiota as one major reservoir for pioneering microbes in infants. However, the global distinct and identical features of mother-infant gut microbiota at various taxonomic resolutions and metabolic functions across cohorts and potential of infant microbial prediction based on their paired mother's gut microbiota remain unclear. Here, we analyzed 376 mother-infant dyads (468 mother and 1024 infant samples) of eight studies from six countries and observed higher diversity at species and strain levels in maternal gut microbiota but not their metabolic functions. A number of 290 species were shared in at least one mother-infant dyad, with 26 species (five at strain level) observed across cohorts. The profile of mother-infant shared species and strains was further influenced by delivery mode and feeding regimen. The mother-sourced species in infants exhibited similar strain heterogeneity but more metabolic functions compared to other-sourced species, suggesting the comparable stability and fitness of shared and non-shared species and the potential role of shared species in the early gut microbial community, respectively. Predictive models showed moderate performance accuracy for shared species and strains occurrences in infants. These generalized mother-infant shared species and strains may be considered as the primary targets for future work toward infant microbiome development and probiotics exploration.

Keywords: Mother; gut; infant; metagenomics; microbiome; neonate; prediction; vertical transmission.

Figure 1.

Distinct diversity and composition of gut microbiota from mother–infant dyads. (a) Species alpha diversity (Shannon diversity index) of mothers (n=468) and infants (n=1024). The p-value was computed using a blocked (by “study”) Wilcoxon test from R package “coin”. (b) Species alpha diversity (Shannon diversity index) of stools from mothers and infants stratified by “sampling time points” into three categories for mothers and six categories for infants. The p-values were computed using Wilcoxon test. The overall p-value in (b) (on top) was calculated with a blocked (by “study”) Kruskal–Wallis test from R package “coin”. (c) Principal coordinate analysis (PCoA) of samples of mothers and infants from all the eight included studies based on Bray–Curtis dissimilarity of species. The boxplots on the right side and below show samples of mothers and infants projected onto the first two principal coordinates, respectively. The p-values were calculated by the adonis (permutations=1000) function from the R package “vegan” for the PCoA plot, and by a blocked (by “study”) Wilcoxon test from R package “coin” for the boxplots. (d, e) Comparisons of the mean relative abundance of gut genera from mothers and infants (d), and stratified by “sampling time points” (e). Only the genera that differed (FDR < 0.05, Wilcoxon test blocked by “study”) between mothers and infants, with > 0.3% mean relative abundance and at least 5% prevalence among maternal and infant samples across all “sampling time points”, respectively, are plotted. The mean relative abundance of genera with blue are higher in stools of infants, and genera with red are higher in mothers

Figure 2.

Feature of microbiota shared by mother–infant dyads. (a) Similarity of species-level composition profiles between related and unrelated mother–infant dyads as measured by Bray–Curtis dissimilarity. (b) Number of mother–infant shared species increased as infants aged, with regression line (red). (c) Longitudinal changes in the relative abundance of mother–infant shared species, with > 0.1% mean relative abundance and at least 5% prevalence of infant samples across all “sampling time points”. (d) Horizontal bars indicated the proportion of variance (R) explained by clinical covariates stratified by “sampling time points” that are associated with mother–infant shared species in the model as determined by PERMANOVA. Asterisk denotes the significance (FDR < 0.05) of each covariate as determined by PERMANOVA. (e) Abundance of a core set of 26 mother–infant shared species across six studies investigated, with average relative abundance > 0.1% and at least 5% prevalence among all the infant samples. The column annotations on the top indicate the study, mode of delivery and the total relative abundance of 26 shared species for each sample. Bar plot on right side indicated the prevalence of each core shared species among all mother–infant dyads (n = 342, including four twin births)

Figure 3.

Strain-level analysis of the mother-to-infant gut transmitted species. (a) SNP haplotype similarity of each species based on all pairwise comparisons (dominant strain per species) of the marker genes, and stratified to intra-mother and intra-infant comparisons. Species containing at least 10 comparisons in both strata are shown. The significance (p-values adjusted by Benjamini–Hochberg FDR method on the right of the bars) of the difference in similarity between mothers and infants was determined by Wilcoxon test. The solid black point indicates the mean of SNP haplotype similarity. (b) Number of shared strains increased as infants aged indicating by the regression line (red). (c) Dynamic prevalence of mother–infant shared strains stratified by “sampling time points”. Only the frequently mother–infant shared strains present in at least 10% of samples (indicated in the bracket) in at least one period are shown

Figure 4.

Gut microbiota functional capacity shared by infants with their mothers. (a) Dynamic changes of microbial metabolic functions that differed (FDR < 0.05, Wilcoxon test blocked by “study”) between mothers and infants, with > 1% mean relative abundance and at least 5% prevalence among maternal and infant samples across all “sampling time points”, respectively. The mean relative abundances of metabolic functions in blue are higher in infants, and metabolic functions in red are higher in mothers. (b) Infants and mothers shared, on average, four times of number of metabolic pathways (76.6%) than species (16.8%) (Wilcoxon test blocked by “study, p < .001). The curves show quadratic fit for the percentage of shared features with infants age, and shaded area shows 95% confidence interval for each fit. (c) Shared metabolic pathways by mothers and infants stratified by “sampling time points”, with significant difference (Wilcoxon test blocked by “study”, FDR < 0.05, bar with asterisk) between mothers and infants at least one time point. Metabolic pathways (> 0.5% mean relative abundance and at least 5% prevalence in infant samples across all “sampling time points”) are colored based on the metabolic functions

Figure 5.

Influence of mode of delivery and feeding regimen on the mother–infant shared gut species and strains. (a) Longitudinal changes in the mean relative abundance of genera of microbiota in infants stratified by “sampling point times” and mode of delivery (Cesarean section vs. vaginal), for genera with > 1% mean relative abundance from infant samples across all “sampling point times”. (b) Longitudinal changes in the number of species and strains shared by mothers and infants stratified by mode of delivery (p < .001 for shared species, and p < .001 for shared strains, Wilcoxon test blocked by “sampling time points”). (c) Dynamic prevalence (%) of shared strains by mothers and infants stratified by “sampling time points” and mode of delivery. Only the frequently shared strains present in at least 10% of samples (indicated in the bracket) in at least one period of either vaginally- or Cesarean section-born infants are shown. (d) Forest plot illustrated the coefficients of shared genera (MaAsLin, FDR < 0.25 for delivery or feeding regimen) influenced by mode of delivery and feeding regimen (exclusive vs. non-exclusive breastfeeding). (e) Comparisons of metabolic functions between vaginally and Cesarean section-born infants, with > 1% mean relative abundance across all infant samples (MaAsLin, FDR < 0.25). The mean relative abundance of genera of infant samples across all “sampling point times” (a) and metabolic functions (e) with blue are higher (MaAsLin, FDR < 0.25) in vaginally born infants; genera/metabolic functions with red are higher (MaAsLin, FDR < 0.25) in infants via Cesarean section; and no differences (MaAsLin, FDR > 0.25) for genera/metabolic functions with yellow

Figure 6.

Assessment of prediction performance of shared species occurrences in infants gut based on maternal gut microbiota. (a) The area under the curve (AUC) matrix obtained from random forest model with leave-one-study-out (LOSO) approach for the core set of 26 shared species across six studies. Each column refers to the performance of machine learning by taking all but the data set of the corresponding column and applying it to the data set of the corresponding column. (b) The AUC matrix obtained from random forest model with LOSO approach for the five strains across six studies. (c) Changes in the prediction performance with AUC when stratified the samples by mode of delivery. (d) The importance of predictive features reflected by the mean decrease in GINI with LOSO approach for the model of Bifidobacterium longum. Only features appearing in the 10 top-ranking features in at least one study are reported. (e) Prediction performances with increasing number of microbial species obtained by retraining the random forest classifier on the top-ranking features identified from the first random forest model training with LOSO approach. The data show the mean of AUC values of the set of 26 species