The human nasal microbiota and Staphylococcus aureus carriage

Abstract

Background: Colonization of humans with Staphylococcus aureus is a critical prerequisite of subsequent clinical infection of the skin, blood, lung, heart and other deep tissues. S. aureus persistently or intermittently colonizes the nares of approximately 50% of healthy adults, whereas approximately 50% of the general population is rarely or never colonized by this pathogen. Because microbial consortia within the nasal cavity may be an important determinant of S. aureus colonization we determined the composition and dynamics of the nasal microbiota and correlated specific microorganisms with S. aureus colonization.

Methodology/principal findings: Nasal specimens were collected longitudinally from five healthy adults and a cross-section of hospitalized patients (26 S. aureus carriers and 16 non-carriers). Culture-independent analysis of 16S rRNA sequences revealed that the nasal microbiota of healthy subjects consists primarily of members of the phylum Actinobacteria (e.g., Propionibacterium spp. and Corynebacterium spp.), with proportionally less representation of other phyla, including Firmicutes (e.g., Staphylococcus spp.) and Proteobacteria (e.g. Enterobacter spp). In contrast, inpatient nasal microbiotas were enriched in S. aureus or Staphylococcus epidermidis and diminished in several actinobacterial groups, most notably Propionibacterium acnes. Moreover, within the inpatient population S. aureus colonization was negatively correlated with the abundances of several microbial groups, including S. epidermidis (p = 0.004).

Conclusions/significance: The nares environment is colonized by a temporally stable microbiota that is distinct from other regions of the integument. Negative association between S. aureus, S. epidermidis, and other groups suggests microbial competition during colonization of the nares, a finding that could be exploited to limit S. aureus colonization.

Figure 1. Relative abundance of predominant bacterial taxa followed longitudinally in healthy adults.

Shading indicates the proportion of each rDNA library represented by a particular rDNA sequence type. Rows represent species or genus-level taxonomic groups and columns represent individual specimens. Data are presented only for the 25 most abundant taxa, which account for 90% of rDNA sequences analyzed.

Figure 2. Similarities between microbiotas determined longitudinally for healthy adults.

Morisita-Horn Community Similarity Indices (C_MH) were calculated for each pairwise combination of samples and plotted as a heatmap that compares all values. Color gradient denotes C_MH values, which range from 0.0 (no similarity between communities) to 1.0 (identical communities). Ax: Axilla samples. Grn: Groin samples. Nar: Nares samples.

Figure 3. Comparison of community similarity (C_MH) between specimen types.

The similarity of microbiota in all pairwise combinations of specimens obtained from healthy adults was assessed using the abundance-based Morisita-Horn similarity index (C_MH). Boxplots indicate the spread of C_MH values calculated for the indicated comparison. Each chart summarizes data for a study participant. For instance, the first boxplot (“A Nar vs. A Nar”) summarizes data for C_MH scores for pairs of Subject A nares samples over time. Statistical significances are reported in Table 2.

Figure 4. Similarity of microbiotas determined longitudinally for healthy adults.

Panel A. Principal Components Analysis of Microbiotas. Colors indicate the subject and anatomical location from which longitudinal specimens were obtained. No sampling time-dependent trends were observed in the data, so datapoints are not labeled with respect to time of collection. Panel B. Hierarchical Clustering. Colors indicate the subject and anatomical location from which longitudinal specimens were obtained. Leafs are labeled by subject and day of collection. See Materials and Methods for details.

Figure 5. Temporal variation in nares microbiotas of healthy individuals.

Each line plots the similarity of a baseline nares specimen to subsequently collected nares specimens from the same individual. Similarity is based on the Morisita-Horn community similarity index.

Figure 6. Inter-subject variability in nares microbiota.

Panel A. Comparison of S. aureus and S. epidermidis proportions in rDNA libraries. Column heights represent relative abundances of particular microbial groups in hospitalized patients and healthy adults. Hospitalized patients are labeled “D” or “V”, based on the hospital ICU at which they were admitted. The dashed lines denote the mean abundances of S. aureus and S. epidermidis -- 4.8% and 9.3% respectively -- in all nares specimens from healthy adults. rDNA sequences were determined by pyrosequencing. Panel B. All other bacteria, grouped at taxonomic-order level. Dashed line represents the mean abundance of Actinomycetales in all nares specimens from healthy adults.

Figure 7. Impact of S. aureus sequences on distributions of other nares bacteria.

Panel A. Percent abundance of top twelve genera. Panel B. Percent abundance of top twelve genera adjusted by removal of S. aureus from total sequence counts.

Figure 8. Ecological richness and diversity of nares microbiotas.

The top panel presents the distributions of species richness indices (S_obs) calculated for nares specimens obtained from hospitalized or healthy adults. The middle panel summarizes sample biodiversity (Shannon diversity index H_o) and the lower panel presents species evenness (H_o/H_max. H_o = Shannon index; H_max = maximum value of H_o for a specimen). Significance levels are indicated by * p<0.05; *** p<0.001.

Figure 9. Accuracy of rDNA sequence-based classification of S. aureus and S. epidermidis.

Each nares sequence classified as S. aureus or S. epidermidis by BLAST query of a highly-curated database (SILVA LTP_S95) was aligned and its pairwise sequence similarity determined in relation to each sequence in a dataset consisting of all LTP_S95 staphylococcal sequences along with other staphylococcal genomic sequences. Maximum percent identity scores were identified both to the predicted species (S. aureus or S. epidermidis) and to all other staphylococci in the dataset. These two scores were plotted for each nares sequence. Points falling above the diagonal line therefore represent nares sequences that were most closely related to the species predicted by BLAST, whereas points falling below the diagonal suggest mis-classification. The majority of sequences were at least 97% identical to the predicted species, which justifies species-level identification of rRNA sequences. We interpret the low maximum percent identity values obtained for some sequences (i.e.,<97% identity to any staphylococcal species, yet a top BLAST hit of S. aureus or S. epidermidis) as arising from base-calling or alignment errors inherent in analysis of pyrosequencing reads. Panel A. Nares sequences classified as S. aureus. Panel B. Nares sequences classified as S. epidermidis.

Figure 10. Distinct microbial populations in healthy and hospitalized adults.

Pie charts depict average frequencies of dominant microorganisms in the anterior nares of healthy adults and inpatients, classified by S. aureus carriage status. Arrows outline possible pathways by which microbial populations develop in hospitalized patients. “Other” represents less abundant taxa, such as Proteobacteria and Firmicutes other than S. aureus and S. epidermidis.