Scientists in Arkansas have developed a machine-learning approach that can identify potentially disease-causing strains of a poultry bacterium by analyzing not only which genes are present, but also how those genes are arranged across the genome. The method focuses on the “genetic neighborhoods” surrounding genes, offering a new way to distinguish harmful strains of Enterococcus cecorum from closely related strains that do not cause disease.
E. cecorum is commonly found in poultry environments, and many of its strains are harmless. However, pathogenic strains can cause arthritis, bone infections and lameness, creating serious animal-welfare problems and economic losses for poultry producers. Because pathogenic and nonpathogenic strains can share many of the same genes, identifying the genetic features associated with disease has been challenging.
The research team, led by Aranyak Goswami of the Arkansas Agricultural Experiment Station’s Center for Agricultural Data Analytics, examined the organization of genes within genomic islands. These are segments of DNA that bacteria often acquire from other microorganisms through horizontal gene transfer. Genomic islands can carry genes involved in antibiotic resistance, bacterial survival, movement of DNA and virulence, making them important regions for understanding how pathogens emerge.
Rather than treating the bacterial genome as a simple list of genetic components, the researchers analyzed it as a structured map. They investigated which genes occurred near one another, the order in which they appeared and the way groups of neighboring genes formed recurring units known as genomic-island cassettes. This architecture provided information that could be missed when genes are examined individually.
“The machine-learning model recognizes patterns in gene order much like it recognizes patterns in language,” Goswami said. In the same way that a language model can learn that certain words frequently appear together, the computational system learned that particular combinations and arrangements of bacterial genes were associated with pathogenic strains. The approach therefore captures relationships among genes rather than relying only on the presence or absence of individual DNA sequences.
For the proof-of-concept study, the researchers analyzed the genomes of 145 E. cecorum strains isolated from poultry. The dataset included 95 nonpathogenic strains and 50 pathogenic strains capable of causing illness. The analysis found that disease-associated strains were more likely to contain genomic islands enriched in genes linked to antimicrobial resistance and the transfer of genetic material between bacteria.
Those findings do not mean that every bacterium carrying such genes will necessarily cause disease. Instead, the researchers describe the system as an exploratory classification and research tool. It identifies patterns that may help scientists investigate why some bacterial lineages become harmful, while also providing clues about how resistance and virulence traits move through bacterial populations.
Current monitoring methods for E. cecorum often depend on culturing the bacterium or screening for specific genes. Such techniques remain valuable, but they may overlook broader genomic relationships. The new pipeline could complement these approaches by evaluating the wider context in which genes occur. Additional testing with larger and more geographically diverse datasets will be necessary before the method can be used for routine flock surveillance or diagnostic decision-making.
The researchers believe the strategy could eventually be adapted to other bacterial species affecting animals, humans, wildlife and plants. Goswami’s team is beginning to examine Enterococcus faecalis, a close relative of E. cecorum and a frequent cause of hospital-acquired infections in humans. They also plan to apply the pipeline to Escherichia coli and other bacteria to study how nonpathogenic lineages acquire the genomic configurations associated with disease. The study, published in Frontiers in Microbiology, demonstrates how machine learning and comparative genomics can reveal hidden signals in bacterial DNA and may help researchers track the evolution of emerging pathogens.
Subject of Research: Animals
Article Title: Genomic-island cassette architecture provides interpretable signal for exploratory classification of poultry-associated Enterococcus cecorum lineages
News Publication Date: 7-Jul-2026
Web References: https://doi.org/10.3389/fmicb.2026.1882753
References: Frontiers in Microbiology, DOI: 10.3389/fmicb.2026.1882753
Image Credits: UA University Relations photo by Chieko Hara
Keywords: artificial intelligence, machine learning, deep learning, computational biology, bacterial pathogens, Enterococcus cecorum, genomic islands, genomic architecture, antibiotic resistance, poultry disease, pathogen surveillance, comparative genomics
