Dataset Information

Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data.

ABSTRACT: 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 0.79 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.

SUBMITTER: Moradigaravand D

PROVIDER: S-EPMC6310291 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data.

Moradigaravand Danesh D Palm Martin M Farewell Anne A Mustonen Ville V Warringer Jonas J Parts Leopold L

PLoS computational biology 20181214 12

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 m ...[more]

PMID: 30550564

Similar Datasets

Project description:Biofilms are considered to be highly resistant to antimicrobial agents. Several mechanisms have been proposed to explain this high resistance of biofilms, including restricted penetration of antimicrobial agents into biofilms, slow growth owing to nutrient limitation, expression of genes involved in the general stress response, and emergence of a biofilm-specific phenotype. However, since combinations of these factors are involved in most biofilm studies, it is still difficult to fully understand the mechanisms of biofilm resistance to antibiotics. In this study, the antibiotic susceptibility of Escherichia coli cells in biofilms was investigated with exclusion of the effects of the restricted penetration of antimicrobial agents into biofilms and the slow growth owing to nutrient limitation. Three different antibiotics, ampicillin (100 microg/ml), kanamycin (25 microg/ml), and ofloxacin (10 microg/ml), were applied directly to cells in the deeper layers of mature biofilms that developed in flow cells after removal of the surface layers of the biofilms. The results of the antibiotic treatment analyses revealed that ofloxacin and kanamycin were effective against biofilm cells, whereas ampicillin did not kill the cells, resulting in regrowth of the biofilm after the ampicillin treatment was discontinued. LIVE/DEAD staining revealed that a small fraction of resistant cells emerged in the deeper layers of the mature biofilms and that these cells were still alive even after 24 h of ampicillin treatment. Furthermore, to determine which genes in the biofilm cells are induced, allowing increased resistance to ampicillin, global gene expression was analyzed at different stages of biofilm formation, the attachment, colony formation, and maturation stages. The results showed that significant changes in gene expression occurred during biofilm formation, which were partly induced by rpoS expression. Based on the experimental data, it is likely that the observed resistance of biofilms can be attributed to formation of ampicillin-resistant subpopulations in the deeper layers of mature biofilms but not in young colony biofilms and that the production and resistance of the subpopulations were aided by biofilm-specific phenotypes, like slow growth and induction of rpoS-mediated stress responses.

Dataset Information

Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data.

Publications

Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets