Pyrosequencing Unveils Cystic Fibrosis Lung Microbiome Differences Associated with a Severe Lung Function Decline

Abstract

Chronic airway infection is a hallmark feature of cystic fibrosis (CF) disease. In the present study, sputum samples from CF patients were collected and characterized by 16S rRNA gene-targeted approach, to assess how lung microbiota composition changes following a severe decline in lung function. In particular, we compared the airway microbiota of two groups of patients with CF, i.e. patients with a substantial decline in their lung function (SD) and patients with a stable lung function (S). The two groups showed a different bacterial composition, with SD patients reporting a more heterogeneous community than the S ones. Pseudomonas was the dominant genus in both S and SD patients followed by Staphylococcus and Prevotella. Other than the classical CF pathogens and the most commonly identified non-classical genera in CF, we found the presence of the unusual anaerobic genus Sneathia. Moreover, the oligotyping analysis revealed the presence of other minor genera described in CF, highlighting the polymicrobial nature of CF infection. Finally, the analysis of correlation and anti-correlation networks showed the presence of antagonism and ecological independence between members of Pseudomonas genus and the rest of CF airways microbiota, with S patients showing a more interconnected community in S patients than in SD ones. This population structure suggests a higher resilience of S microbiota with respect to SD, which in turn may hinder the potential adverse impact of aggressive pathogens (e.g. Pseudomonas). In conclusion, our findings shed a new light on CF airway microbiota ecology, improving current knowledge about its composition and polymicrobial interactions in patients with CF.

Fig 1. Relative abundance of sputum microbiota among patients.

Relative OTUs abundance was computed dividing the number of 16S sequences assigned to each OTU by the total number of sequences obtained for each sample. Boxes denote the interquartile range (IQR) between the 25^th and the 75^th percentile (first and third quartiles), whereas the inner line represents the median. Whiskers represent the lowest and highest values within 1.5 times IQR from the first and third quartiles Outliers were reported using white circles. CP: common CF pathogens; NC: non-classical but commonly identified genera in CF; OG: other genera in CF; NDG: not yet described genera in CF; S: stable patients; SD: severe decliner patients; [un] unclassified; [unc] uncultured.

Fig 2. Canonical Correlation analysis based on the log-transformed abundance of 44 OTUs.

Patient conditions were used as constraining variable. Two first components (CCA1 and CA1) were plotted accounting for 15.6% of overall inertia of the data set. Individuals (represented by points) were clustered, and centroids were computed for each group. Ellipses were drawn using the standard deviation of points belonging to the same cluster with a confidence limit of 95%.

Fig 3. Differences in microbial community distribution between stable and severe decliner groups.

Bacterial taxonomic profiling revealed differences between stable and severe decliner communities. a) Standardized abundances of two OTUs (OTU 2 and 36) showing a different distribution between patient groups. b) Differences between the two most represented oligotypes identified for OTU 2. Standardize abundances were calculated as: [x - mean(x)]/sd(x), where "sd" is the standard deviation and “mean” is the mean value. As a result, all OTUs have equal means and standard deviations (0 and 1, respectively) but different ranges. Reported p values were obtained with a Wilcoxon signed-rank test.

Fig 4. OTU Networks based on correlation analysis.

Networks report positive and negative correlations between OTUs found in the airway microbiota of S and SD patients. Node color corresponds to taxonomic assignments, whereas node size reflects the log-transformed abundance. Edge thickness is proportional to the modulus of Spearman's rank correlation coefficient. Average degree values are reported in the upper-right corner of each network.