EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Whole-genome sequencing and bioinformatic tools powered by machine learning to identify antibiotic-resistant genes and virulence factors in Escherichia coli from sepsis

Nishitha R Kumar, Tejashree A Balraj, Kerry K Cooper, Akila Prashant

Microbial Genomics · 11.08.2025 · 11 (8)

DOI: 10.1099/mgen.0.001465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Microbial Genomics, erschienen am 11.08.2025. Verfasst von Nishitha R Kumar und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry, JSS Medical College and Hospital, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India. Hauptthemen laut MEDLINE: Escherichia coli, Virulence Factors, Whole Genome Sequencing, Sepsis. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSS Academy of Higher Education and Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extended-spectrum β -lactamase-producing Escherichia coli poses a global public health threat. Here, we performed a hospital-based study that reinforced the necessity for rapid antimicrobial resistance (AMR) and virulence gene mapping of clinical E. coli isolates. Whole-genome sequencing of 18 sepsis-causing E. coli strains was performed to identify multidrug resistance (MDR) and virulence factor genes and to correlate these with antibiotic use in patients with sepsis. We identified various global and emerging MDR sequence types, utilizing a supervised machine learning approach to elucidate the relationship between genome content and AMR profiles across 17 antimicrobial classes, ensuring unbiased analysis. Known AMR genes were correlated with resistance phenotypes, and several crucial and novel AMR genes were identified. The feature selection methodology involved processing the genome into overlapping 13 bp k-mer features using a two-step selection process. Logistic regression with nested cross-validation and synthetic minority oversampling technique confirmed the robustness of the model. The combination of Machine Learning (ML) algorithms facilitates the discovery of nonlinear interactions and complex patterns within genomic data, which may not be readily apparent using conventional genomic analysis alone. This will enable the identification of novel biomarkers and genetic determinants of AMR profiles. The integration of genomic data with ML models can be used to quickly predict AMR, allowing for more targeted and personalized treatment strategies that are not typically achieved by traditional AMR surveillance methods. Our findings tailor the research approaches for patients with sepsis, particularly with AMR E. coli , highlighting the importance of prompt surveillance, robust infection control, optimized antibiotic stewardship and integrated genomic and epidemiological analysis to control MDR bacteria transmission, ultimately improving patient outcomes and safeguarding public health.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Escherichia coliVirulence FactorsWhole Genome SequencingSepsisMachine LearningEscherichia coli InfectionsComputational BiologyDrug Resistance, Multiple, BacterialHumansAnti-Bacterial AgentsGenome, Bacterial

Stichwörter der Autor:innen

Escherichia colicommunity acquired infectionshospital acquired infectionsmultidrug resistancemultilocus sequence typingphylogentic analysissepsissupervised machine learningvirulence factorswhole-genome sequencing

Substanzen

Virulence FactorsAnti-Bacterial Agents

Autor:innen und Institutionen

  • Department of Biochemistry, JSS Medical College and Hospital, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India.
  • Department of Microbiology, JSS Medical College and Hospital, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India.
  • School of Animal and Comparative Biomedical Sciences, University of Arizona, Tucson, AZ, USA.
  • BIO5 Institute, University of Arizona, Tucson, AZ, USA.
  • Department of Medical Genetics, JSS Medical College and Hospital, JSS Academy of Higher Education and Research, Mysuru, Karnataka, India.

Förderung

  • JSS Academy of Higher Education and Research

Zitieren

APA

Kumar, N. R., Balraj, T. A., Cooper, K. K., & Prashant, A. (2025). Whole-genome sequencing and bioinformatic tools powered by machine learning to identify antibiotic-resistant genes and virulence factors in Escherichia coli from sepsis. Microbial Genomics, 11(8). https://doi.org/10.1099/mgen.0.001465

Vancouver

Kumar NR, Balraj TA, Cooper KK, Prashant A. Whole-genome sequencing and bioinformatic tools powered by machine learning to identify antibiotic-resistant genes and virulence factors in Escherichia coli from sepsis. Microbial Genomics. 2025;11(8). doi:10.1099/mgen.0.001465

BibTeX
@article{Kumar2025,
  author = {Kumar, Nishitha R and Balraj, Tejashree A and Cooper, Kerry K and Prashant, Akila},
  title = {Whole-genome sequencing and bioinformatic tools powered by machine learning to identify antibiotic-resistant genes and virulence factors in Escherichia coli from sepsis},
  journal = {Microbial Genomics},
  year = {2025},
  volume = {11},
  number = {8},
  doi = {10.1099/mgen.0.001465}
}
Kostenlos starten →