Genomic signatures associated with epidemiologically defined high-risk pathogenic Escherichia coli isolates identified by interpretable machine learning
Journal of Microbiology · 2026
DOI: 10.71150/jm.2604011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Microbiology, 2026. Verfasst von Yoojung Hwang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Sciences, Graduate School of The Catholic University of Korea, Seoul 06591, Republic of Korea. Hauptthemen laut MEDLINE: Escherichia coli, Machine Learning, Genome, Bacterial, Escherichia coli Infections. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Ministry of Food and Drug Safety, Catholic Education Foundation, Korea Research Environment Open NETwork.
Abstract (Originalsprache)
Pathogenic Escherichia coli is a major cause of foodborne illness worldwide and includes strains capable of causing severe disease. To establish a genome-informed framework for foodborne outbreak surveillance, we analyzed 1,029 E. coli isolates from clinical, food, livestock, and environmental sources using whole-genome sequencing. Pathogenic isolates obtained from human clinical cases or linked to documented outbreaks were classified as epidemiologically defined high-risk (EpiHR), whereas the remaining pathogenic isolates were classified as non-EpiHR. Virulence-associated genomic features were extracted using a bioinformatics pipeline, and four machine learning (ML) algorithms, including gradient boosting machine, random forest (RF), and support vector machines with linear and radial basis function kernels, were evaluated. Among them, the RF model showed the best performance, achieving an area under the curve (AUC) of 0.98 and accuracy of 0.93 in 10-fold cross-validation. Additional leave-one-group-out validation showed retained discrimination across held-out sequence types and serotypes, although performance was reduced when isolates were grouped by isolation source. Evaluation using an independent test dataset of 1,908 publicly available pathogenic E. coli genomes showed an AUC of 0.97 and a sensitivity of 0.98. Feature importance analysis using Shapley additive explanations identified influential predictive features, including traT, etpB, and enterotoxin-associated genes. A reduced 10-feature model achieved an AUC of 0.79 in the independent test dataset, supporting its exploratory use for future simplified screening approaches. These results indicate that genome-based ML provides a sensitive framework for surveillance-oriented prioritization of EpiHR pathogenic E. coli isolates, with model predictions interpreted together with epidemiological information.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Medical Sciences, Graduate School of The Catholic University of Korea, Seoul 06591, Republic of Korea.
- Catholic Research Institute for Human Genome Polymorphism, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea.
- ConnectaGen, Hanam 12918, Republic of Korea.
- Division of Food Microbiology, National Institute of Food and Drug Safety Evaluation, Ministry of Food and Drug Safety, Cheongju 28159, Republic of Korea.
- Department of Microbiology, Sungkyunkwan University School of Medicine, Suwon 16419, Republic of Korea.
- Department of Biological Sciences, Inje University, Gimhae 50834, Republic of Korea.
Förderung
- Ministry of Food and Drug Safety
- Catholic Education Foundation
- Korea Research Environment Open NETwork
Zitieren
APA
Hwang, Y., Cho, W. Y., Lee, W., Joo, I., Shin, J. I., Seo, M. R., Shin, S. H., Ko, K. S., Park, K. T., Chung, Y. J., & Jung, S. H. (2026). Genomic signatures associated with epidemiologically defined high-risk pathogenic Escherichia coli isolates identified by interpretable machine learning. Journal of Microbiology. https://doi.org/10.71150/jm.2604011
Vancouver
Hwang Y, Cho WY, Lee W, Joo I, Shin JI, Seo MR, et al. Genomic signatures associated with epidemiologically defined high-risk pathogenic Escherichia coli isolates identified by interpretable machine learning. Journal of Microbiology. 2026. doi:10.71150/jm.2604011
BibTeX
@article{Hwang2026,
author = {Hwang, Yoojung and Cho, Woo Young and Lee, Woojung and Joo, Insun and Shin, Jeong-Ih and Seo, Mi-Ran and Shin, Seung-Hun and Ko, Kwan Soo and Park, Kun Taek and Chung, Yeun-Jun and Jung, Seung-Hyun},
title = {Genomic signatures associated with epidemiologically defined high-risk pathogenic Escherichia coli isolates identified by interpretable machine learning},
journal = {Journal of Microbiology},
year = {2026},
doi = {10.71150/jm.2604011}
}
EUVIMED