Differentiating commensal and disease-associated Enterococcus cecorum isolates in poultry using protein sequences

Area of Science:

• Veterinary Microbiology
• Computational Biology
• Avian Pathology

Background:

• *Enterococcus cecorum* (EC) transitioned from avian commensal to a significant pathogen causing bacterial chondronecrosis with osteomyelitis (BCO) in broilers and sepsis (SS) in young birds.
• Distinguishing pathogenic EC from commensal strains is crucial for effective surveillance and control in poultry production.
• Previous methods lacked the precision to differentiate EC pathotypes effectively.

Purpose of the Study:

• To develop a method for differentiating pathogenic *Enterococcus cecorum* from commensal strains using amino acid k-mer profiling.
• To identify specific oligopeptide signatures associated with EC pathogenicity, including BCO and SS.
• To explore the utility of supervised learning in analyzing proteomic differences for poultry health management.

Main Methods:

• Amino acid k-mer profiling with k=5 was employed to analyze *Enterococcus cecorum* isolates.
• Supervised learning algorithms, specifically Random Forest and Multilayer Perceptron, were utilized.
• Minimal sets of discriminatory k-mers were identified to classify isolates based on pathogenicity and disease type.

Main Results:

• A five k-mer set achieved 86% accuracy in distinguishing commensal EC from pathogenic BCO and SS isolates.
• Eight k-mers differentiated BCO from SS isolates with 90% accuracy.
• Discriminatory k-mers were linked to proteins involved in carbohydrate transport, stress response, mobile elements, and metabolic adaptation, indicating distinct pathogenic strategies.

Conclusions:

• Amino acid k-mer profiling combined with machine learning offers a powerful tool for differentiating *Enterococcus cecorum* pathotypes.
• Distinct proteomic signatures correlate with the specific pathogenicity of BCO and SS, offering insights into disease mechanisms.
• This approach has significant implications for enhancing surveillance, diagnosis, and targeted interventions in poultry production to control EC-related diseases.