Abstract
MotivationResistance co-occurrence within first-line anti-tuberculosis (TB) drugs is a common phenomenon. Existing methods based on genetic data analysis of Mycobacterium tuberculosis (MTB) have been able to predict resistance of MTB to individual drugs, but have not considered the resistance co-occurrence and cannot capture latent structure of genomic data that corresponds to lineages.ResultsWe used a large cohort of TB patients from 16 countries across six continents where whole-genome sequences for each isolate and associated phenotype to anti-TB drugs were obtained using drug susceptibility testing recommended by the World Health Organization. We then proposed an end-to-end multi-task model with deep denoising auto-encoder (DeepAMR) for multiple drug classification and developed DeepAMR_cluster, a clustering variant based on DeepAMR, for learning clusters in latent space of the data. The results showed that DeepAMR outperformed baseline model and four machine learning models with mean AUROC from 94.4% to 98.7% for predicting resistance to four first-line drugs [i.e. isoniazid (INH), ethambutol (EMB), rifampicin (RIF), pyrazinamide (PZA)], multi-drug resistant TB (MDR-TB) and pan-susceptible TB (PANS-TB: MTB that is susceptible to all four first-line anti-TB drugs). In the case of INH, EMB, PZA and MDR-TB, DeepAMR achieved its best mean sensitivity of 94.3%, 91.5%, 87.3% and 96.3%, respectively. While in the case of RIF and PANS-TB, it generated 94.2% and 92.2% sensitivity, which were lower than baseline model by 0.7% and 1.9%, respectively. t-SNE visualization shows that DeepAMR_cluster captures lineage-related clusters in the latent space.Availability and implementationThe details of source code are provided at http://www.robots.ox.ac.uk/∼davidc/code.php.Supplementary information Supplementary data are available at Bioinformatics online.
Highlights
Tuberculosis (TB) is one of the top 10 causes of death worldwide (WHO, 2018); and cases that are resistant to the main antibiotics that are normally used to treat the disease are increasing
Two types of resistant Mycobacterium tuberculosis (MTB) are monitored by the World Health Organization (WHO): () multi-drug resistant TB (MDR-TB), defined as MTB that is resistant to at least INH and RIF and (ii) extensively drug-resistant tuberculosis (XDR-TB) involves resistance to the two most powerful anti-TB drugs, INH and RIF, in addition to resistance to any of the fluoroquinolones and to at least one of the three injectable second-line drugs
The baseline method considered in this study aims to classify drug resistance based on the presence of any resistance determinant from a library of such determinants that has been assembled from the literature; we term this method ‘direct association’ (DA) using the resistance single nucleotide polymorphisms (SNPs) catalog described in an existing study (Walker et al, 2015), we note that the method formally evaluated in this study exploited ‘susceptible’ SNPs and had a third prediction class for novel mutations where the method classified samples as not being predictable
Summary
Tuberculosis (TB) is one of the top 10 causes of death worldwide (WHO, 2018); and cases that are resistant to the main antibiotics that are normally used to treat the disease are increasing. The SNP variants previously identified for single drugs are often jointly used for detecting M/XDR-TB. The evolution of poly-resistant MTB strains (isolates that are resistant to two or more drugs but do not meet the definition of MDR-TB) is a complex dynamic process that will have been influenced by interactions between genes and drug-resistant phenotype. Hazbon et al (2006) studied 608 INH-susceptible and 403 INH-resistant MTB, and found the mutations in katG315 were more common in the MDR isolates, while the mutations in the inhA promoter were more common in INH mono-resistant isolates. Sintchenko et al (1999) studied 36 MTB isolates in Australia and concluded that amino acid substitutions at Asp516 and Ser522 in the rpoB gene in RIF-resistant MTB predicted rifabutin susceptibility for MDR-TB. Walker et al (2015) studied 23 candidate genes of 2099 MTB isolates, where 120 mutations were characterized as resistance determining and 772 as benign
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
