Oral Microbiota Profile Associates with Sugar Intake and Taste Preference Genes

Abstract

Oral microbiota ecology is influenced by environmental and host conditions, but few studies have evaluated associations between untargeted measures of the entire oral microbiome and potentially relevant environmental and host factors. This study aimed to identify salivary microbiota cluster groups using hierarchical cluster analyses (Wards method) based on 16S rRNA gene amplicon sequencing, and identify lifestyle and host factors which were associated with these groups. Group members (n = 175) were distinctly separated by microbiota profiles and differed in reported sucrose intake and allelic variation in the taste-preference-associated genes TAS1R1 (rs731024) and GNAT3 (rs2074673). Groups with higher sucrose intake were either characterized by a wide panel of species or phylotypes with fewer aciduric species, or by a narrower profile that included documented aciduric- and caries-associated species. The inferred functional profiles of the latter type were dominated by metabolic pathways associated with the carbohydrate metabolism with enrichment of glycosidase functions. In conclusion, this study supported in vivo associations between sugar intake and oral microbiota ecology, but it also found evidence for a variable microbiota response to sugar, highlighting the importance of modifying host factors and microbes beyond the commonly targeted acidogenic and acid-tolerant species. The results should be confirmed under controlled settings with comprehensive phenotypic and genotypic data.

Keywords: 16S rDNA sequencing; genes; microbiota; saliva; sugar; taste.

Figure 1

Total carbohydrate and sucrose intake in the study group. Proportions of various types of carbohydrates in the reported diet (A) and cumulative percentages for sucrose intake (B).

Figure 2

(A) Dendrogram from the unsupervised hierarchical cluster analysis with Ward’s method. The clusters in red and blue refer to the groups with the highest and lowest sucrose intake, respectively, when intake in the defined cluster groups was compared, (B) bar chart for 13 identified phyla, and (C) bar chart for the top 40 identified genera out of 127.

Figure 3

Composite figure of various aspects related to cluster groups based on dichotomous ASVs. (A) rarefaction curves showing number of observed ASVs by sequencing depth (reads); (B–D) box plots of alpha diversities by the Shannon, Evenness and Faith phylogenetic diversity (pd) indexes; (E) Jaccard Principal Coordinates Analysis (PCoA) plot illustrating separation of the cluster groups based on dichotomous measures. The red colour refers to the cluster with highest sucrose intake and blue refers to the lowest.

Figure 4

Composite figure of various aspects related to cluster groups based on eHOMD-identified taxonomic names and aggregation by species. (A,B) Bar charts showing overall relative proportions in the nine represented phyla (A) and top 30 genera; (B), as classified by the eHOMD database; (C) dendrogram from hierarchical cluster analysis with Ward´s method. The red section refers to the cluster with the highest sucrose intake and blue to the lowest; (D) PLS 3D scatter plot illustrating separation of the four cluster groups; (E) Venn diagrams showing the number of species detected in all four cluster groups.

Figure 5

LEfSe results for Cluster H1 versus H3 with highest and lowest sucrose intake, respectively. (A) Cladogram showing taxonomic representation of statistically consistent differences between the two cluster groups. The analysis was based on the abundance of the 372 species and their respective family, order, class and phylum. (B) Histogram of the linear discriminant analysis (LDA) scores in cluster groups H1 and H3. (C) Violin plots with box plots for carbohydrate metabolic pathways characteristic of all four H cluster groups, and (D) STRING database predicted enriched functions within cluster H1 (high sucrose intake) compared with cluster H3 (lowest sucrose intake). Group comparisons were done using non-parametric (Kruskal–Wallis or Mann–Whitney U test, Bonferroni corrected p values, permutation 9999). Violin labels: ***, ** and * indicate <0.001, <0.01, and <0.05, respectively.