Altered Epithelial Gene Expression in Peripheral Airways of Severe Asthma

Abstract

Management of severe asthma remains a challenge despite treatment with glucocorticosteroid therapy. The majority of studies investigating disease mechanisms in treatment-resistant severe asthma have previously focused on the large central airways, with very few utilizing transcriptomic approaches. The small peripheral airways, which comprise the majority of the airway surface area, remain an unexplored area in severe asthma and were targeted for global epithelial gene expression profiling in this study. Differences between central and peripheral airways were evaluated using transcriptomic analysis (Affymetrix HG U133 plus 2.0 GeneChips) of epithelial brushings obtained from severe asthma patients (N = 17) and healthy volunteers (N = 23). Results were validated in an independent cohort (N = 10) by real-time quantitative PCR. The IL-13 disease signature that is associated with an asthmatic phenotype was upregulated in severe asthmatics compared to healthy controls but was predominantly evident within the peripheral airways, as were genes related to mast cell presence. The gene expression response associated with glucocorticosteroid therapy (i.e. FKBP5) was also upregulated in severe asthmatics compared to healthy controls but, in contrast, was more pronounced in central airways. Moreover, an altered epithelial repair response (e.g. FGFBP1) was evident across both airway sites reflecting a significant aspect of disease in severe asthma unadressed by current therapies. A transcriptomic approach to understand epithelial activation in severe asthma has thus highlighted the need for better-targeted therapy to the peripheral airways in severe asthma, where the IL-13 disease signature persists despite treatment with currently available therapy.

Fig 1. Peripheral airways versus central airways, in healthy volunteers and in severe asthmatics.

A. Greater expression, genes with a greater expression in peripheral airways compared to central airways; Lesser expression, genes with a lesser expression in peripheral airways compared to central airways. B. Heatmap depicting unsupervised hierarchical clustering (Pearson complete) of modules identified using SSIM. Expression values of genes within each module were averaged and scaled to indicate the number of standard deviations above (red) or below (blue) the mean, denoted as row Z-score. PA, peripheral airways; SA, severe asthmatics; ns, not significant. C. Fold changes for mast cell proteases obtained by differential gene expression analysis. D. RT-qPCR validation of differential gene expression analysis of mast cell proteases. Changes in gene expression (mean and standard error of mean) are shown relative to GAPDH. HC, central airways in health; HP, peripheral airways in health; SC, central airways in severe asthma; SP, peripheral airways in severe asthma; *, p-value < 0.05.

Fig 2. Severe asthma versus health, in central airways and in peripheral airways.

A. Greater expression, genes with a greater expression in severe asthmatics when compared to healthy volunteers; Lesser expression, genes with a lesser expression in severe asthmatics when compared to healthy controls. B. Fold changes for IL-13 disease signature and steroid response obtained by differential gene expression analysis. C. RT-qPCR validation of microarray findings. Changes in gene expression (mean and standard error of mean) are shown relative to GAPDH. HC, central airways in health; HP, peripheral airways in health; SC, central airways in severe asthma; SP, peripheral airways in severe asthma; *, p-value < 0.05.

Fig 3. Interaction analysis to evaluate the effects of disease and lung airway region on gene expression.

Log₂ intensities are plotted and significance of interaction is depicted by: DR, interaction between disease and lung airway region; D, main effect of disease; R, main effect of region; p-values * < 0.05, ** < 0.01, *** <0.001, **** <0.0001; ns, not significant.

Fig 4. Heatmap depicting heterogeneity in severe asthma samples.

Unsupervised hierarchical clustering (Euclidean complete) was performed on log₂ fold change values for severe asthmatics with paired samples from both central and peripheral airways (N = 11 pairs). Red and blue represent greater and lower expression in the peripheral airways compared to the central airways, respectively. Severe asthma patients have been assigned a letter from A through K, arbitrarily.

Fig 5. Schematic depicting the conclusions from the study.

The main findings along with the numbers of differentially expressed genes are listed for each comparison. PA, peripheral airways; ns, not significant.