Here the authors train multivariate logistic regression models on over 52,000 MTBC isolates to associate binary resistance phenotypes for 15 antitubercular drugs with variants extracted from candidate resistance genes, and generate a regression-based catalogue of resistance-associated mutations that achieves higher sensitivity on average than the gold standard with smaller average decreases in specificity and positive predictive value.
- Sanjana G. Kulkarni
- Sacha Laurent
- Maha R. Farhat
