Examining the Evidence for an Adult Healthy Middle Ear Microbiome

Abstract

Otitis media (OM) is a cluster of diseases of the middle ear that commonly result from bacterial infection. OM subtypes in which the tympanic membrane is intact (acute otitis media and otitis media with effusion) are presumed to result from pathogen translocation through the eustachian tube. Recent molecular-based studies have suggested that a diverse middle ear microbiome exists in the absence of disease. These have been largely unsupported by culture and feature species that commonly contaminate low-biomass sequencing data. Combining culture-based and molecular techniques, we undertook a detailed investigation of the evidence for bacterial colonization of the healthy middle ear. Middle ear (ME), nasopharynx (NP), and external ear canal (EC) swabs were collected from a total of 25 adult patients undergoing cochlear implant, stapedotomy, or translabyrinthine vestibular schwannoma resection. Diagnostic culture, microscopy, quantitative PCR, and 16S rRNA gene amplicon sequencing were used to assess sample bacterial content. EC and NP microbiota were consistent with previous reports. In contrast, bacterial levels in ME samples were not significantly above those in unused control swabs. Commonly detected taxa were among recognized sequencing contaminants (Methylobacterium, Pseudomonas, and Acinetobacter). Linear regression of dominant ME taxa confirmed a negative relationship between relative abundance and bacterial load, consistent with contamination. No bacteria were detected by microscopy or diagnostic culture in any middle ear sample. Our findings cast substantial doubt on previous reports identifying a healthy middle ear microbiome using 16S amplicon sequencing.IMPORTANCE Recent molecular-based studies have suggested that a diverse middle ear microbiome in adults and children can exist in the absence of disease. These studies have been largely unsupported by culture and feature species that commonly contaminate low-biomass sequencing data. While 16S rRNA gene amplicon sequencing has proven to be a highly informative technique in many clinical contexts, it is susceptible to spurious signal arising from sequencing reagent contaminants where sample biomass is low. Combining culture-based and molecular techniques, we undertook a detailed investigation of the evidence for bacterial colonization of the healthy middle ear. In finding no evidence of viable bacterial cells in middle ear samples, our study further underlines the importance of careful consideration of amplicon sequence data derived from very-low-biomass contexts and the value of analytical approaches that combine culture and molecular techniques.

Keywords: microbiome; middle ear; otitis media.

FIG 1

Tukey’s box plot showing sample bacterial loads, as determined by quantitative PCR. Middle ear samples had a median of 0.9 log10 cells/μl and interquartile range (IQR) of 0.6 to 1.1, ear canal samples had a median of 3.3 and IQR of 0.9 to 195.8, while nasopharyngeal samples had a median of 47.5 and IQR of 10.5 to 502.0. Swab controls had a median of 0.5 log10 cells/μl with an IQR of 0.4 to 0.6. Ringer’s buffer had a median of 0.6 log10 cells/μl with an IQR of 0.5 to 0.7.

FIG 2

NMDS plot based on Bray Curtis dissimilarity differences for subjects where middle ear (○), ear canal (●), and nasopharyngeal samples (▲) were all available (n = 13).

FIG 3

Canonical correspondence biplots for microbiota. ○, middle ear; ●, ear canal; ▲, nasopharynx. Biplot lines for bacterial taxa show the direction of increase, with the length of each line indicating the degree of correlation with ordination axes.

FIG 4

Tukey’s box plots showing relative abundances of taxa strongly associated with middle ear microbiota, as defined by 16S rRNA gene amplicon sequencing. ME, middle ear; EC, ear canal; NP, nasopharynx.