No abstract

During 1994–2005, we isolated Mycobacterium microti from 5 animals and 4 humans. Only 1 person was immunocompromised. Spoligotyping showed 3 patterns: vole type, llama type, and a new variant llama type.

Motivation Resistance 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. Results We 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 implementation The 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.

The Mycobacterium abscessus complex is an emerging cause of chronic pulmonary infection in patients with underlying lung disease. The M. abscessus complex is regarded as an environmental pathogen but its molecular adaptation to the human lung during long-term infection is poorly understood. Here we carried out a longitudinal molecular epidemiological analysis of 178 M. abscessus spp. isolates obtained from 10 cystic fibrosis (CF) and 2 non CF patients over a 13 year period. Multi-locus sequence and molecular typing analysis revealed that 11 of 12 patients were persistently colonized with the same genotype during the course of the infection while replacement of a M. abscessus sensu stricto strain with a Mycobacterium massiliense strain was observed for a single patient. Of note, several patients including a pair of siblings were colonized with closely-related strains consistent with intra-familial transmission or a common infection reservoir. In general, a switch from smooth to rough colony morphology was observed during the course of long-term infection, which in some cases correlated with an increasing severity of clinical symptoms. To examine evolution during long-term infection of the CF lung we compared the genome sequences of 6 sequential isolates of Mycobacterium bolletii obtained from a single patient over an 11 year period, revealing a heterogeneous clonal infecting population with mutations in regulators controlling the expression of virulence factors and complex lipids. Taken together, these data provide new insights into the epidemiology of M. abscessus spp. during long-term infection of the CF lung, and the molecular transition from saprophytic organism to human pathogen.

No abstract