Antimicrobial resistance dataset for pattern recognition in machine learning application.

Area of Science:

• Microbiology
• Environmental Science
• Public Health

Background:

• The environment is a significant factor in the development and dissemination of antimicrobial resistance (AMR).
• AMR poses a substantial and escalating threat to global public health.
• Challenges exist in selecting appropriate antibiotics for treating bacterial infections due to evolving resistance patterns.

Purpose of the Study:

• To present a novel dataset of bacterial isolates sourced from abattoir environments in Osun State, Nigeria.
• To facilitate research aimed at understanding and mitigating the spread of antimicrobial resistance.
• To support the development of predictive models for effective antibiotic selection in clinical settings.

Main Methods:

• Collection of bacterial isolates from various sources within abattoirs in Osun State, Nigeria.
• Characterization of isolates to identify bacterial species and assess their resistance profiles (details to be elaborated in the full study).
• Dataset curation for accessibility and usability in antimicrobial resistance research.

Main Results:

• A comprehensive dataset of bacterial isolates from a specific environmental niche (abattoirs) has been established.
• The dataset provides a foundation for further research into AMR determinants and epidemiology.
• Potential for identifying novel resistance mechanisms or prevalent resistant strains in the region.

Conclusions:

• The generated dataset is a valuable resource for the scientific community studying antimicrobial resistance.
• Understanding environmental AMR reservoirs, such as abattoirs, is critical for public health interventions.
• This resource can advance the prediction of effective antimicrobial therapies and combat the global AMR crisis.