Arkansas researchers reveal bacterial gene organisation as a key to identifying harmful poultry pathogens

A study at the University of Arkansas demonstrates that analysing bacterial gene arrangements through machine learning can better distinguish pathogenic strains, potentially enhancing disease surveillance in poultry.

Researchers at the University of Arkansas have shown that the organisation of bacterial genes may be as revealing as the genes themselves when it comes to spotting harmful poultry pathogens.

In a study published in Frontiers in Microbiology, the team used machine learning to examine the “genetic neighbourhoods” of Enterococcus cecorum, a bacterium that can be harmless in some strains but cause arthritis, bone infections and lameness in poultry in others. Rather than focusing only on whether a gene was present, the method looked at how genes were arranged beside one another within genomic islands, sections of DNA often acquired from other bacteria and sometimes linked to virulence or antibiotic resistance.

The researchers analysed 145 poultry-associated strains, including 50 pathogenic and 95 non-pathogenic isolates, and found that disease-causing strains were more likely to carry genomic islands enriched in antibiotic-resistance genes and genes involved in movement between bacteria.

The approach, dubbed Cassette2Vec-EC, delivered strong classification performance and outperformed simpler genomic-burden methods, according to the paper.

Aranyak Goswami, a computational biologist at the Arkansas Agricultural Experiment Station, said the work could eventually support wider surveillance efforts, though it is not yet a diagnostic tool. The team is now adapting the pipeline to study other bacteria, including Enterococcus faecalis and E. coli.

Ref: Lagad RR, Rafi S and Goswami A (2026) Genomic-island cassette architecture provides interpretable signal for exploratory classification of poultry-associated Enterococcus cecorum lineages.
Front. Microbiol. 17:1882753.
doi: 10.3389/fmicb.2026.1882753

"This news service is powered by an AI tool that curates and enhances the content related to animal health. The articles provided are for informational purposes only and should not be considered professional or veterinary advice. The content presented does not reflect the views or opinions of Stonehaven Analytics."