Host blood RNA signatures predict the outcome of tuberculosis treatment

Abstract

Biomarkers for tuberculosis treatment outcome will assist in guiding individualized treatment and evaluation of new therapies. To identify candidate biomarkers, RNA sequencing of whole blood from a well-characterized TB treatment cohort was performed. Application of a validated transcriptional correlate of risk for TB revealed symmetry in host gene expression during progression from latent TB infection to active TB disease and resolution of disease during treatment, including return to control levels after drug therapy. The symmetry was also seen in a TB disease signature, constructed from the TB treatment cohort, that also functioned as a strong correlate of risk. Both signatures identified patients at risk of treatment failure 1-4 weeks after start of therapy. Further mining of the transcriptomes revealed an association between treatment failure and suppressed expression of mitochondrial genes before treatment initiation, leading to development of a novel baseline (pre-treatment) signature of treatment failure. These novel host responses to TB treatment were integrated into a five-gene real-time PCR-based signature that captures the clinically relevant responses to TB treatment and provides a convenient platform for stratifying patients according to their risk of treatment failure. Furthermore, this 5-gene signature is shown to correlate with the pulmonary inflammatory state (as measured by PET-CT) and can complement sputum-based Gene Xpert for patient stratification, providing a rapid and accurate alternative to current methods.

Keywords: Biomarkers; Host response; Mitochondria; Transcriptome; Tuberculosis treatment.

Fig. 1

Symmetry between progression and treatment response. A. The expression of each junction in the ACS COR at each time point and in controls. For each group, the middle column is the mean and the right/left columns are the mean ± SEM. Multiple junctions from the same gene are indicated by multiple rows. B. ACS COR scores on samples from the ACS (left) and CTRC (right) datasets. After treatment initiation, scores significantly decrease from baseline by week 1 (Wilcoxon p < 10⁻⁵) and remain significantly higher at the end of treatment compared to controls (Wilcoxon p = 0.001). C. Average expression of ACS COR genes as measured by qRT-PCR. Expression is significantly higher in cures at the end of treatment than in controls (Wilcoxon p = 0.003) but is no longer significantly higher one year after the end of treatment (Wilcoxon p = 0.31). D. The expression of each junction in the DISEASE signature at each time point and in controls. For each group, the middle column is the mean and the right/left columns are the mean ± SEM. Multiple junctions from the same gene are indicated by multiple rows. E. ROC curve for the DISEASE signature predicting TB progression on the ACS dataset. AUC = 0.78, p < 10⁻¹³. F. DISEASE scores on samples from the ACS (left) and CTRC (right) datasets. For the heatmaps in Figs. 1A and 1D, the junction-level mean ± standard error of the mean is plotted for each group of samples. Values are shifted such that the mean expression in controls is set to zero, and scaled such that the values lie between −1 and 1. The junctions plotted and reference junctions used for standardization are given in Tables S7 and S8.

Fig. 2

Prediction of treatment failures. A. DISEASE score ROCs for predicting treatment failure using gene expression profiles at week 24 (solid; AUC = 0.99, p = 0.000003), week 4 (dashed; AUC = 0.70, p = 0.03) and week 1 (dotted; AUC = 0.72, p = 0.04). B. Pre-treatment expression of mitochondria genes in treatment failures, cures and controls. For each group, the middle column is the mean and the right/left columns are the mean ± SEM. C. Leave-one-out cross-validation ROC curve for FAILURE signature (AUC = 0.87, p = 0.0006), demonstrating the ability to predict treatment failure using pre-treatment expression profiles. D. Pre-treatment expression of the junctions in the FAILURE signature in treatment failures, cures and controls. For each group, the middle column is the mean and the right/left columns are the mean ± SEM. Multiple junctions from the same gene are indicated by multiple rows. E. ROC curve of the FAILURE signature predicting progression on the ACS dataset (AUC = 0.63, p = 0.0001). For the heatmaps in Figs. 2B and D, junction (2B) or gene (2D) -level mean ± standard error of the mean is plotted for each group of samples. Values are shifted such that the mean expression in controls is set to zero, and scaled such that the values lie between −1 and 1. The junctions plotted and reference junctions used for standardization are given in Table S9.

Fig. 3

The RESPONSE5 signature. A. The RESPONSE5 signature involves six ratios of assays, each involving one assay from the DISEASE signature and one from the FAILURE signature. Ratios of expression for the pairs of assays in the RESPONSE5 signature are plotted for treatment failures and cures, at baseline and week 24, and for controls. For each group, the middle column is the mean and the right/left columns are the mean ± SEM. B. Pre-treatment Cts of SMARCD3 and UCP2 discriminate treatment failures (blue diamonds) from cures (orange circles). Negative Cts are plotted throughout, such that increasing values correspond to increasing expression. C. Week 24 Cts of SMARCD3 and UCP2 discriminate treatment failures (blue diamonds) from cures (orange circles). D. Week 24 RESPONSE5 scores and Gene Xpert Cts perfectly discriminate treatment failures (blue diamonds) from cures (orange circles). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Fig. 4

The RESPONSE5 signature and PET-CT stratification. A. RESPONSE5 scores plotted versus TGAI for all available samples in the CTRC (Spearman ρ = 0.68, p < 10⁻³⁷). The solid line is the linear regression fit to the data. B. Pre-treatment RESPONSE5 scores stratify patients according to ultimate treatment outcome. Treatment failures vs cures: AUC = 0.92, p = 0.00015. Non-resolved vs resolved cures: AUC = 0.74, p = 0.0074. C. Week 4 RESPONSE5 scores and Gene Xpert Cts discriminate PET-CT resolved cures (blue diamonds) from PET-CT unresolved cures (orange circles). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)