Quantitative drug susceptibility testing for M. tuberculosis using unassembled sequencing data and machine learning
The CRyPTIC consortium, A. S. Lachapelle
This paper develops a machine learning system to predict minimum inhibitory concentrations from unassembled whole-genome sequencing data for 13 anti-tuberculosis drugs, achieving high accuracy for most drugs.
bioRxiv · Sep 14, 2021 · PreprintMicrobiology