Rapid and accurate detection of Shiga toxin-producing Escherichia coli (STEC) serotype O157 : H7 by mass spectrometry directly from the isolate, using 10 potential biomarker peaks and machine learning predictive models.
Eduardo Manfredi, María Florencia Rocca, Jonathan Zintgraff, Lucía Irazu, Elizabeth Miliwebsky, Carolina Carbonari, Natalia Deza, Monica Prieto, Isabel Chinen
{"title":"Rapid and accurate detection of Shiga toxin-producing <i>Escherichia coli</i> (STEC) serotype O157 : H7 by mass spectrometry directly from the isolate, using 10 potential biomarker peaks and machine learning predictive models.","authors":"Eduardo Manfredi, María Florencia Rocca, Jonathan Zintgraff, Lucía Irazu, Elizabeth Miliwebsky, Carolina Carbonari, Natalia Deza, Monica Prieto, Isabel Chinen","doi":"10.1099/jmm.0.001675","DOIUrl":null,"url":null,"abstract":"<p><p><b>Introduction.</b> The different pathotypes of <i>Escherichia coli</i> can produce a large number of human diseases. Surveillance is complex since their differentiation is not easy. In particular, the detection of Shiga toxin-producing <i>Escherichia coli</i> (STEC) serotype O157 : H7 consists of stool culture of a diarrhoeal sample on enriched and/or selective media and identification of presumptive colonies and confirmation, which require a certain level of training and are time-consuming and expensive.<b>Hypothesis.</b> Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a quick and easy way to obtain the protein spectrum of a microorganism, identify the genus and species, and detect potential biomarker peaks of certain characteristics.<b>Aim.</b> To verify the usefulness of MALDI-TOF MS to rapidly identify and differentiate STEC O157 : H7 from other <i>E. coli</i> pathotypes.<b>Methodology.</b> The direct method was employed, and the information obtained using Microflex LT platform-based analysis from 60 clinical isolates (training set) was used to detect differences between the peptide fingerprints of STEC O157 : H7 and other <i>E. coli</i> strains. The protein profiles detected laid the foundations for the development and evaluation of machine learning predictive models in this study.<b>Results.</b> The detection of potential biomarkers in combination with machine learning predictive models in a new set of 142 samples, called 'test set', achieved 99.3 % (141/142) correct classification, allowing us to distinguish between the isolates of STEC O157 : H7 and the other <i>E. coli</i> group. Great similarity was also observed with respect to this last group and the <i>Shigella</i> species when applying the potential biomarkers algorithm, allowing differentiation from STEC O157 : H7<b>Conclusion.</b> Given that STEC O157 : H7 is the main causal agent of haemolytic uremic syndrome, and based on the performance values obtained in the present study (sensitivity=98.5 % and specificity=100.0 %), the implementation of this technique provides a proof of principle for MALDI-TOF MS and machine learning to identify biomarkers to rapidly screen or confirm STEC O157 : H7 versus other diarrhoeagenic <i>E. coli</i> in the future.</p>","PeriodicalId":16343,"journal":{"name":"Journal of medical microbiology","volume":"72 5","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of medical microbiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1099/jmm.0.001675","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Introduction. The different pathotypes of Escherichia coli can produce a large number of human diseases. Surveillance is complex since their differentiation is not easy. In particular, the detection of Shiga toxin-producing Escherichia coli (STEC) serotype O157 : H7 consists of stool culture of a diarrhoeal sample on enriched and/or selective media and identification of presumptive colonies and confirmation, which require a certain level of training and are time-consuming and expensive.Hypothesis. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a quick and easy way to obtain the protein spectrum of a microorganism, identify the genus and species, and detect potential biomarker peaks of certain characteristics.Aim. To verify the usefulness of MALDI-TOF MS to rapidly identify and differentiate STEC O157 : H7 from other E. coli pathotypes.Methodology. The direct method was employed, and the information obtained using Microflex LT platform-based analysis from 60 clinical isolates (training set) was used to detect differences between the peptide fingerprints of STEC O157 : H7 and other E. coli strains. The protein profiles detected laid the foundations for the development and evaluation of machine learning predictive models in this study.Results. The detection of potential biomarkers in combination with machine learning predictive models in a new set of 142 samples, called 'test set', achieved 99.3 % (141/142) correct classification, allowing us to distinguish between the isolates of STEC O157 : H7 and the other E. coli group. Great similarity was also observed with respect to this last group and the Shigella species when applying the potential biomarkers algorithm, allowing differentiation from STEC O157 : H7Conclusion. Given that STEC O157 : H7 is the main causal agent of haemolytic uremic syndrome, and based on the performance values obtained in the present study (sensitivity=98.5 % and specificity=100.0 %), the implementation of this technique provides a proof of principle for MALDI-TOF MS and machine learning to identify biomarkers to rapidly screen or confirm STEC O157 : H7 versus other diarrhoeagenic E. coli in the future.
期刊介绍:
Journal of Medical Microbiology provides comprehensive coverage of medical, dental and veterinary microbiology, and infectious diseases. We welcome everything from laboratory research to clinical trials, including bacteriology, virology, mycology and parasitology. We publish articles under the following subject categories: Antimicrobial resistance; Clinical microbiology; Disease, diagnosis and diagnostics; Medical mycology; Molecular and microbial epidemiology; Microbiome and microbial ecology in health; One Health; Pathogenesis, virulence and host response; Prevention, therapy and therapeutics