A microbiome case-control study of recurrent acute otitis media identified potentially protective bacterial genera

Abstract

Background: Recurrent acute otitis media (rAOM, recurrent ear infection) is a common childhood disease caused by bacteria termed otopathogens, for which current treatments have limited effectiveness. Generic probiotic therapies have shown promise, but seem to lack specificity. We hypothesised that healthy children with no history of AOM carry protective commensal bacteria that could be translated into a specific probiotic therapy to break the cycle of re-infection. We characterised the nasopharyngeal microbiome of these children (controls) in comparison to children with rAOM (cases) to identify potentially protective bacteria. As some children with rAOM do not appear to carry any of the known otopathogens, we also hypothesised that characterisation of the middle ear microbiome could identify novel otopathogens, which may also guide the development of more effective therapies.

Results: Middle ear fluids, middle ear rinses and ear canal swabs from the cases and nasopharyngeal swabs from both groups underwent 16S rRNA gene sequencing. The nasopharyngeal microbiomes of cases and controls were distinct. We observed a significantly higher abundance of Corynebacterium and Dolosigranulum in the nasopharynx of controls. Alloiococcus, Staphylococcus and Turicella were abundant in the middle ear and ear canal of cases, but were uncommon in the nasopharynx of both groups. Gemella and Neisseria were characteristic of the case nasopharynx, but were not prevalent in the middle ear.

Conclusions: Corynebacterium and Dolosigranulum are characteristic of a healthy nasopharyngeal microbiome. Alloiococcus, Staphylococcus and Turicella are possible novel otopathogens, though their rarity in the nasopharynx and prevalence in the ear canal means that their role as normal aural flora cannot be ruled out. Gemella and Neisseria are unlikely to be novel otopathogens as they do not appear to colonise the middle ear in children with rAOM.

Keywords: 16S rRNA; Alloiococcus; Corynebacterium; Dolosigranulum; Microbiome; Middle ear; Nasopharynx; Otitis media; Turicella.

Fig. 1

Alpha diversity measured by a) Faith’s Phylogenetic Diversity and b) Inverse Simpson metrics grouped by sample type. Alpha diversity values were calculated on CSS normalised and logged read counts. The p-values represent the difference between groups determined by Wilcoxon rank sum (case/control NPS) or Wilcoxon signed rank (MEF/MER and MEF/NPS) test where paired samples were from the same child

Fig. 2

Principal coordinates analysis (PCoA) on nasopharyngeal samples from cases and controls. Distances between samples were calculated using the weighted UniFrac metric [56]

Fig. 3

Log CSS normalised counts of differentially abundant OTUs between rAOM-prone and rAOM-resistant children. OTUs shown are significantly differentially abundant between the nasopharyngeal samples of the cases and controls and are additionally found above the threshold of ≥0.35% mean or median relative abundance in at least one group. Differential abundance analysis controlled for recent antibiotic usage, length of breastfeeding and sex; children with missing data for any of these covariates were excluded (n = 4). log₂FC refers to the log fold change of OTU abundance from cases to controls

Fig. 4

Principal coordinates analysis (PCoA) on samples from children with rAOM. Distances between samples were calculated using the weighted UniFrac metric [56]

Fig. 5

Log CSS normalised counts of differentially abundant OTUs amongst sample types within the cases. OTUs plotted are significantly differentially abundant between paired (within-child) a) MEF and MER samples; b) MEF and NPS samples; c) MER and NPS samples; d) MEF and ECS samples. Only OTUs with an adjusted p ≤ 0.05 and above the threshold of ≥0.35% mean or median relative abundance in at least one of the groups in each comparison are shown. log₂FC refers to the log fold change between the two groups, with the value representing the change from a) fluids to rinses; b) fluids to NPS; c) NPS to rinses; d) ear canals to fluids

Fig. 6

Correlations between OTUs. Correlation coefficients between OTUs were calculated by SparCC [58] within the a) Case NPS; b) Control NPS; c) MEF and d) MER. One sample per child was included in each set. Non-significant correlations (one-sided p > 0.05) are coloured white. N refers to the number of samples included in each correlation analysis, which tested for correlations between all OTUs observed in those samples