Composition and Predicted Metabolic Capacity of Upper and Lower Airway Microbiota of Healthy Dogs in Relation to the Fecal Microbiota

Abstract

The upper and lower airways of healthy humans are reported to harbor stable and consistent bacterial populations, and the composition of these communities is altered in individuals affected with several respiratory diseases. Data regarding the presence of airway microbiota in other animals are scant and a better understanding of the composition and metabolic function of such bacterial populations is essential for the development of novel therapeutic and diagnostic modalities for use in both veterinary and human medicine. Based on targeted next-generation sequencing of feces and samples collected at multiple levels of the airways from 16 healthy female dogs, we demonstrate that canine airways harbor a topographically continuous microbiota with increasing relative abundance of proteobacterial species from the upper to lower airways. The lung-associated microbiota, as assessed via bronchoalveolar lavage fluid (BALF), was the most consistent between dogs and was dominated by three distinct taxa, two of which were resolved to the species level and one to the level of family. The gene content of the nasal, oropharyngeal, and lung-associated microbiota, predicted using the Phylogenetic Investigations into Communities by Reconstruction of Unobserved States (PICRUSt) software, provided information regarding the glyoxylate and citrate cycle metabolic pathways utilized by these bacterial populations to colonize such nutrient-poor, low-throughput environments. These data generated in healthy subjects provide context for future analysis of diseased canine airways. Moreover, as dogs have similar respiratory anatomy, physiology, and immune systems as humans, are exposed to many of the same environmental stimuli, and spontaneously develop similar respiratory diseases, these data support the use of dogs as a model species for prospective studies of the airway microbiota, with findings translatable to the human condition.

Fig 1. Phylum- and family-level composition of fecal and airway microbiota.

Bar charts showing relative abundance of all taxa detected in feces, nasal swabs, oropharyngeal swabs, or bronchoalveolar lavage fluid (BALF) collected from 16 intact adult female dogs, annotated to the taxonomic level of phylum (A) or family (B). Legend for all detected phyla is shown at upper right; identity of selected microbial families consistently detected in airway samples are shown at bottom right. Samples are shown in the same order, within each collection site, i.e., the first bar from each sample site was collected from the same dog.

Fig 2. Operational taxonomic unit-level composition of fecal and airway microbiota.

Bar charts showing relative abundance of operational taxonomic units (OTUs) in the phylum Proteobacteria (A) or all other phyla (B) detected in feces, nasal swabs, oropharyngeal swabs, or bronchoalveolar lavage fluid (BALF) collected from 16 intact adult female dogs. Predominant OTUs detected in airway samples are labeled. Samples are shown in the same order, within each collection site, i.e., the first bar from each sample site was collected from the same dog.

Fig 3. Distribution of all detected taxa between sample sites.

Venn diagrams demonstrating the number of detected operational taxonomic units (OTUs) unique to each sample site, and shared between one or more sample site in feces, upper airways (nasal and oropharyngeal swabs combined), and bronchoalveolar lavage fluid (BALF) (A), or in nasal swabs, oropharyngeal swabs, and BALF (B).

Fig 4. β-diversity as shown via principal component analysis.

Unweighted principal component analysis of samples from all four sample sites (feces, nasal swabs, oropharyngeal swabs, and bronchoalveolar lavage fluid (BALF) (A) or only airway-associated samples (B). PC1 versus PC2 and PC1 versus PC3 in left and right panels respectively; legends at right.

Fig 5. Compositional uniformity of samples from each site.

Mean ± SEM unweighted (A) and weighted (B) intra-group UniFrac distance between each sample and all other samples collected from the same sample site. Bars indicate significant differences between groups (p < 0.05, Kruskal-Wallis one way ANOVA on ranks with multiple pairwise comparisons via Tukey test).

Fig 6. Gene content predicted at differential relative abundance between sample sites and at highest levels in BALF.

Metabolic pathways identified using the Phylogenetic Investigation of Communities by Reconstruction of Unobserved States (PICRUSt) software and determined to be present at differential relative abundance between groups (based on Kruskal-Wallis ANOVA on ranks) and present at relatively greater abundance in bronchoalveolar lavage fluid (BALF) samples, ranked according to their effect size determined by linear discriminant analysis (LDA) score.

Fig 7. Relative abundance in each sample site of predicted gene content expressed at highest levels in BALF.

Bar charts showing the relative abundance in each group of select pathways predicted to be enriched in bronchoalveolar lavage fluid (BALF) samples, including branched chain amino acid transport (A), general amino acid transport (B), sorbitol mannitol transport (C), multiple sugar transport (D), Leucine degradation (E), methionine degradation (F), the glyoxylate cycle (G) the Entner-Doudoroff pathway (H), the citrate cycle (I), and the second carbon oxidation of the citrate cycle (J); solid lines denote mean values within each group, dashed lines denote median values.

Fig 8. Gene content predicted at differential relative abundance between sample sites and at highest levels in feces, nasal swabs, and oropharyngeal swabs.

Metabolic pathways identified using the Phylogenetic Investigation of Communities by Reconstruction of Unobserved States (PICRUSt) software and determined to be present at differential relative abundance between groups (based on Kruskal-Wallis ANOVA on ranks) and present at relatively greater abundance in oropharyngeal (A, purple bars), nasal (B, blue bars), and fecal (C, green bars) samples, ranked according to their effect size determined by linear discriminant analysis (LDA) score.