Whole-genome sequencing-driven source tracing of foodborne diseases: from cgMLST/SNP typing toward an integrated framework of pan-genomics and machine learning
- 1Health Monitoring Testing and Protection Institute, Hubei Provincial Center for Disease Control and Prevention
Abstract
Core-genome multilocus sequence typing (cgMLST) and core-genome single-nucleotide polymorphism (cgSNP) analysis have made whole-genome sequencing (WGS) the standard tool for foodborne disease surveillance. Fixed-threshold clustering is increasingly unreliable for highly clonal lineages such as Salmonella Enteritidis ST11 and Escherichia coli ST131, whose core genomes differ by only a handful of alleles even between unrelated strains. The central question is whether surveillance should keep simple, easy-to-interpret allele thresholds or move to probabilistic machine-learning models that also use accessory-genome variation. Accessory genes and mobile genetic elements, including prophages, plasmids, and genomic islands, change on timescales that match outbreak transmission and carry niche-adaptation signal absent from the core genome. Gradient-boosting and deep-learning models can combine genomic, epidemiological, and spatiotemporal data to report source probabilities instead of binary cluster assignments. A U.S. CDC random forest trained on 18,661 Salmonella isolates achieved 81% out-of-bag accuracy when every prediction was counted and 91% when limited to high-confidence isolates whose largest predicted source probability was above 0.50. Feature-attribution analysis ranked plasmid-borne and cell-surface genes among the strongest predictors, raising host-adaptation hypotheses that still require experimental testing. The review ends with the threshold-vs.-probability debate, barriers to data sharing and federated-learning alternatives, and the gap between retrospective accuracy and prospective validation in routine surveillance.
Related
- Evaluations of Climate-Informed Early Warning Systems for Foodborne, Waterborne, and Vector-Borne Diseases: A Scoping Review
- Comparative analysis of Illumina and Ultima-Genomics sequencing for plasma cell-free small RNA profiling in pancreatic cancer
- Genomics-Guided Risk Stratification in Myeloma Precursor Conditions: Converging Frameworks From Whole-Genome Sequencing
- A national ecosystem for long-read genome sequencing: Integrating population genomics and rare disease diagnostics in Sweden
- Pheno+: An Electronic Health Record-Integrated, Clinician-in-the-Loop Application for Efficient Phenotyping in Clinical Genomics
BibTeX
@article{song2026wholegenome,
title = {{Whole-genome sequencing-driven source tracing of foodborne diseases: from cgMLST/SNP typing toward an integrated framework of pan-genomics and machine learning}},
author = {Yong Song and Chi Zhang and Jing-jing Li and Shi-yu Dai and Qin Zhang and Zhen-zhen Yao and Ying-Ying Ouyang and Chen-rui Gong},
journal = {Frontiers in Public Health},
year = {2026},
month = oct,
doi = {10.3389/fpubh.2026.1968969},
url = {https://www.frontiersin.org/articles/10.3389/fpubh.2026.1968969/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Whole-genome sequencing-driven source tracing of foodborne diseases: from cgMLST/SNP typing toward an integrated framework of pan-genomics and machine learning
AU - Yong Song
AU - Chi Zhang
AU - Jing-jing Li
AU - Shi-yu Dai
AU - Qin Zhang
AU - Zhen-zhen Yao
AU - Ying-Ying Ouyang
AU - Chen-rui Gong
PY - 2026
DA - 2026/10/20
JO - Frontiers in Public Health
DO - 10.3389/fpubh.2026.1968969
UR - https://www.frontiersin.org/articles/10.3389/fpubh.2026.1968969/full
AB - Core-genome multilocus sequence typing (cgMLST) and core-genome single-nucleotide polymorphism (cgSNP) analysis have made whole-genome sequencing (WGS) the standard tool for foodborne disease surveillance. Fixed-threshold clustering is increasingly unreliable for highly clonal lineages such as Salmonella Enteritidis ST11 and Escherichia coli ST131, whose core genomes differ by only a handful of alleles even between unrelated strains. The central question is whether surveillance should keep simple, easy-to-interpret allele thresholds or move to probabilistic machine-learning models that also use accessory-genome variation. Accessory genes and mobile genetic elements, including prophages, plasmids, and genomic islands, change on timescales that match outbreak transmission and carry niche-adaptation signal absent from the core genome. Gradient-boosting and deep-learning models can combine genomic, epidemiological, and spatiotemporal data to report source probabilities instead of binary cluster assignments. A U.S. CDC random forest trained on 18,661 Salmonella isolates achieved 81% out-of-bag accuracy when every prediction was counted and 91% when limited to high-confidence isolates whose largest predicted source probability was above 0.50. Feature-attribution analysis ranked plasmid-borne and cell-surface genes among the strongest predictors, raising host-adaptation hypotheses that still require experimental testing. The review ends with the threshold-vs.-probability debate, barriers to data sharing and federated-learning alternatives, and the gap between retrospective accuracy and prospective validation in routine surveillance.
SN - 2296-2565
ER -