Search

The emergence of microbial antibiotic resistance is a global health threat. In clinical settings, the key to controlling spread of resistant strains is accurate and rapid detection. As traditional culture-based methods are time consuming, genetic approaches have recently been developed for this task. The detection of antibiotic resistance is typically made by measuring a few known determinants previously identified from genome sequencing, and thus requires the prior knowledge of its biological mechanisms. To overcome this limitation, we employed machine learning models to predict resistance to 11 compounds across four classes of antibiotics from existing and novel whole genome sequences of 1936 E. coli strains. We considered a range of methods, and examined population structure, isolation year, gene content, and polymorphism information as predictors. Gradient boosted decision trees consistently outperformed alternative models with an average accuracy of 0.91 on held-out data (range 0.81–0.97). While the best models most frequently employed gene content, an average accuracy score of 0.90 could be obtained using population structure information alone. Single nucleotide variation data were less useful, and significantly improved prediction only for two antibiotics, including ciprofloxacin. These results demonstrate that antibiotic resistance in E. coli can be accurately predicted from whole genome sequences without a priori knowledge of mechanisms, and that both genomic and epidemiological data can be informative. This paves way to integrating machine learning approaches into diagnostic tools in the clinic. [ABSTRACT FROM AUTHOR]

Background: Klebsiella pneumoniae is a gram-negative bacterial species capable of occupying a broad range of environmental and clinical habitats. Known as an opportunistic pathogen, it has recently become a major causative agent of clinical infections worldwide. Despite growing knowledge about the highly diverse population of K. pneumoniae, the evolution and clinical significance of environmental K. pneumoniae, as well as the relationship between clinical and environmental K. pneumoniae, are poorly defined. Methods: We isolated and sequenced K. pneumoniae from in-patients in a single hospital in Thailand, as well as hospital sewage, and surrounding canals and farms within a 20-km radius. Results: Phylogenetic analysis of 77 K. pneumoniae (48 clinical and 29 non-clinical isolates) demonstrated that the two groups were intermixed throughout the tree and in some cases resided in the same clade, suggesting recent divergence from a common ancestor. Phylogenetic comparison of the 77 Thai genomes with 286 K. pneumoniae from a global collection showed that Thai isolates were closely related to the clinical sub-population of the global collection, indicating that Thai clinical isolates belonged to globally circulating lineages. Dating of four Thai K. pneumoniae clades indicated that they emerged between 50 and 150 years ago. Despite their phylogenetic relatedness, virulence factors and β-lactamase resistance genes were more numerous in clinical than in environmental isolates. Our results indicate that clinical and environmental K. pneumoniae are closely related, but that hospitals may select for isolates with a more resistant and virulent genotype. Conclusions: These findings highlight the clinical relevance of environmental K. pneumoniae isolates. [ABSTRACT FROM AUTHOR]