Bacterial Topography of the Healthy Human Lower Respiratory Tract

Abstract

Although culture-independent techniques have refuted lung sterility in health, controversy about contamination during bronchoscope passage through the upper respiratory tract (URT) has impeded research progress. We sought to establish whether bronchoscopic sampling accurately reflects the lung microbiome in health and to distinguish between two proposed routes of authentic microbial immigration, (i) dispersion along contiguous respiratory mucosa and (ii) subclinical microaspiration. During bronchoscopy of eight adult volunteers without lung disease, we performed seven protected specimen brushings (PSB) and bilateral bronchoalveolar lavages (BALs) per subject. We amplified, sequenced, and analyzed the bacterial 16S rRNA gene V4 regions by using the Illumina MiSeq platform. Rigorous attention was paid to eliminate potential sources of error or contamination, including a randomized processing order and the inclusion and analysis of exhaustive procedural and sequencing control specimens. Indices of mouth-lung immigration (mouth-lung community similarity, bacterial burden, and community richness) were all significantly greater in airway and alveolar specimens than in bronchoscope contamination control specimens, indicating minimal evidence of pharyngeal contamination. Ecological indices of mouth-lung immigration peaked at or near the carina, as predicted for a primary immigration route of microaspiration. Bacterial burden, diversity, and mouth-lung similarity were greater in BAL than PSB samples, reflecting differences in the sampled surface areas. (This study has been registered at ClinicalTrials.gov under registration no. NCT02392182.)IMPORTANCE This study defines the bacterial topography of the healthy human respiratory tract and provides ecological evidence that bacteria enter the lungs in health primarily by microaspiration, with potential contribution in some subjects by direct dispersal along contiguous mucosa. By demonstrating that contamination contributes negligibly to microbial communities in bronchoscopically acquired specimens, we validate the use of bronchoscopy to investigate the lung microbiome.

FIG 1

Experimental design and conceptual models. Eight subjects without respiratory disease underwent serial sampling of the LRT by bronchoscopy. (A) Sampling methods and locations. Numbers refer to the sampling order. (B) Schematic diagram of method: avoiding contact with airway mucosa for BCC (left), brushing a discrete area of airway mucosa with PSBs (middle), and sampling airways distal to the wedged bronchoscope by BAL (right). (C) Predicted bacterial topographic patterns for three possible routes of microbial immigration: bronchoscope contamination (indices of mouth-lung immigration peak with the BCC and decrease with serial sampling), dispersion along the bronchial mucosa (indices are low in BCC and high in proximal samples and decrease with distance from the pharyngeal source community), and microaspiration (indices are also low in BCC, peak at the main carina, and decrease with subsequent bronchial distance in upright subjects).

FIG 2

Bacterial taxa detected in airway, alveolar, and procedural control specimens. Taxa are listed in decreasing order of mean relative abundance in oral specimens. Red squares represent higher relative abundance (see color key at bottom right). On the right are plots of the kernel density estimates (bandwidth = 0.1) of Bray-Curtis similarity measurements comparing oral-to-specimen similarity (0, entirely different; 1, identical). The oral rinse plot reflects intragroup Bray-Curtis similarity. Plot heights are scaled to the relative density maximum.

FIG 3

Bacterial topography of the healthy human LRT. Mouth-lung bacterial immigration along the LRT was quantified by mouth-lung community similarity (Bray-Curtis similarity) (A), bacterial DNA (log₁₀ number of 16S copies per reaction determined by real-time qPCR) (B), and community richness (number of OTUs per 2,000 sequences) (C). Symbols are as in Fig. 1; Prox, proximal; BI, bronchus intermedius. By all indices, BCCs (triangle) exhibited less evidence of mouth-lung immigration than airway wall PSB specimens (squares) (P ≤ 0.001, paired Student t test) or BAL specimens (circles) (P ≤ 0.01, paired Student t test). Indices of mouth-lung immigration in airway PSB samples are nonlinear, consistent with the topographic pattern predicted in Fig. 1 for microaspiration in upright subjects. Data are mean values ± SEM (n = 8).

FIG 4

Bacterial community membership along the healthy human LRT. The relative abundances of the two most abundant bacterial community members in oral rinse specimens, Prevotella sp. (OTU002) (A) and Veillonella sp. (OTU004) (B), among LRT communities at various locations are graphed. Symbols are as in Fig. 1. Note that the leftmost sample is oral rinse rather than BCC as in Fig. 1C and 2. The relative abundances of both OTUs in LRT PSB samples are nonlinear, peaking at the carina and proximal (Prox.) bronchus intermedius (BI), consistent with the predicted pattern of microaspiration in upright subjects. Data are mean values ± SEM (n = 8).