Dataset Information

Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis.

ABSTRACT: While Raman spectroscopy can provide label-free discrimination between highly similar biological species, the discrimination is often marginal, and optimal use of spectral information is imperative. Here, we compare two machine learning models, an artificial neural network and a support vector machine, for discriminating between Raman spectra of 11 bacterial mutants of Escherichia coli MDS42. While we find that both models discriminate the 11 bacterial strains with similarly high accuracy, sensitivity and specificity, it is clear that the models form different class boundaries. By extracting strain-specific (and function-specific) spectral features utilized by the models, we find that both models utilize a small subset of high intensity peaks while separate subsets of lower intensity peaks are utilized by only one method or the other. This analysis highlights the need for methods to use the complete spectral information more effectively, beginning with a better understanding of the distinct information gained from each model.

SUBMITTER: Zahn J

PROVIDER: S-EPMC9262779 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis.

Zahn Jessica J Germond Arno A Lundgren Alice Y AY Cicerone Marcus T MT

Journal of biophotonics 20220406 7

While Raman spectroscopy can provide label-free discrimination between highly similar biological species, the discrimination is often marginal, and optimal use of spectral information is imperative. Here, we compare two machine learning models, an artificial neural network and a support vector machine, for discriminating between Raman spectra of 11 bacterial mutants of Escherichia coli MDS42. While we find that both models discriminate the 11 bacterial strains with similarly high accuracy, sensi ...[more]

PMID: 35238159

Similar Datasets

Project description:Antibiotic therapy is the standard of care for urinary tract infections (UTIs) caused by uropathogenic Escherichia coli (UPEC). However, previous antibiotic therapy may impart a selective pressure that influences the population structure and pathogenic potential of infecting UPEC strains. Here, we conducted a 3-year study using whole-genome-sequencing analysis and retrospective medical record review to characterize how antibiotic exposure influenced the phenotypic antibiotic resistance, acquired resistome, virulome, and population structure of 88 UTI-causing E. coli strains from dogs. A majority of UTI-associated E. coli strains were from phylogroup B2 and clustered within sequence type 372. Previous antibiotic exposure was associated with a population shift toward UPEC from phylogroups other than the typical urovirulent phylogroup B2. The specific virulence profiles within the accessory virulome that were associated with antibiotic use were elicited by the effect of antibiotics on UPEC phylogenetic structure. Among phylogroup B2, antibiotic exposure increased the quantity of genes within the resistome and the odds of developing reduced susceptibility to at least one antibiotic. Non-B2 UPEC strains harbored a more diverse and greater resistome that conferred reduced susceptibility to multiple antibiotic classes following antibiotic exposure. Collectively, these data suggest that previous antibiotic exposure establishes an environment that provides a selective edge to non-B2 UPEC strains through their diverse and abundant antibiotic resistance genes, despite their lack of urovirulence genes. Our findings highlight the necessity for judicious use of antibiotics as we uncover another mechanism by which antibiotic exposure and resistance can influence the dynamics of bacterial infectious disease. IMPORTANCE Urinary tract infections (UTIs) are one of the most common infections of dogs and humans. While antibiotic therapy is the standard of care for UTIs and other infections, antibiotic exposure may influence the pathogenic profile of subsequent infections. We used whole-genome sequencing and retrospective medical record review to characterize the effect of systemic antibiotic therapy on the resistance, virulence, and population structure of 88 UTI-causing UPEC strains isolated from dogs. Our results indicate that antibiotic exposure alters the population structure of infecting UPEC strains, providing a selective edge for non-B2 phylogroups that harbor diverse and abundant resistance gene catalogues but fewer urovirulence genes. These findings highlight how antibiotic resistance can influence pathogen infection dynamics and have clinical implications for the judicious use of antibiotics for bacterial infections.

Dataset Information

Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis.

Publications

Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets