Gene signature discovery and systematic validation across diverse clinical cohorts for TB prognosis and response to treatment

While blood gene signatures have shown promise in tuberculosis (TB) diagnosis and treatment monitoring, most signatures derived from a single cohort may be insufficient to capture TB heterogeneity in populations and individuals. Here we report a new generalized approach combining a network-based meta-analysis with machine-learning modeling to leverage the power of heterogeneity among studies. The transcriptome datasets from 57 studies (37 TB and 20 viral infections) across demographics and TB disease states were used for gene signature discovery and model training and validation. The network-based meta-analysis identified a common 45-gene signature specific to active TB disease across studies. Two optimized random forest regression models, using the full or partial 45-gene signature, were then established to model the continuum from Mycobacterium tuberculosis infection to disease and treatment response. In model validation, using pooled multi-cohort datasets to mimic the real-world setting, the model provides robust predictive performance for incipient to active TB risk over a 2.5-year period with an AUROC of 0.85, 74.2% sensitivity, and 78.3% specificity, which approximates the minimum criteria (>75% sensitivity and >75% specificity) within the WHO target product profile for prediction of progression to TB. Moreover, the model strongly discriminates active TB from viral infection (AUROC 0.93, 95% CI 0.91–0.94). For treatment monitoring, the TB scores generated by the model statistically correlate with treatment responses over time and were predictive, even before treatment initiation, of standard treatment clinical outcomes. We demonstrate an end-to-end gene signature model development scheme that considers heterogeneity for TB risk estimation and treatment monitoring.Author summary: Developing new diagnostic tools is one of the key areas to accelerate progress towards TB eradication. Having an accurate and rapid molecular test for TB detection in early stage has been highlighted in the recent updates of WHO guidelines and that facilitates faster treatment and reduces the risk of disease transmission. Blood gene signatures have shown promise in TB diagnosis, however, early detection and robust diagnosis against diverse populations are still the challenges to be overcome. Here we present a new computational approach leveraging the power of diverse clinical cohorts that not only defines a common gene signature specific to active TB disease but establishes a generalized predictive model. Importantly, we demonstrate robust performance of the model in both short-term and long-term TB risk estimation that provides a complementary approach to the current models, most of which offer good performance in active TB diagnosis and/or short-term TB risk estimation. In addition, we also demonstrate the utility of the model to monitor treatment responses along with Mycobacterium tuberculosis elimination, which provides additional information for evaluation before the end of treatment.