In this paper, we present a novel machine learning-based methodology for identifying bacteria DNA sub-sequences that are associated with antimicrobial resistance. The dramatic rise in cases of antibiotic resistant bacteria has been an increasing threat across the globe as the existing treatments are rendered ineffective in treating most of these cases due to mutations of their DNA. Among the most recent bacteria to display antimicrobial resistance (AMR) is Neisseria Gonorrhea with the first global treatment failure taking place in 2016. In 2018, new cases of resistance to multiple, high levels of antibiotics were reported in the United Kingdom and Australia. Timing is of the utmost importance when treating individuals who may have antimicrobial resistant infections and slowing their spread. It also is critical in identifying whether a patient has an antimicrobial infection to avoid unnecessarily prescribing antibiotics which may decrease their effectiveness in later treatments. Using machine learning, we are able to quickly and accurately identify cases of antimicrobial resistance as well as the adaptations to antibiotics.
Lingle, Jason I. and Santerre, John
"Using Machine Learning for Antimicrobial Resistant DNA Identification,"
SMU Data Science Review: Vol. 2:
2, Article 12.
Available at: https://scholar.smu.edu/datasciencereview/vol2/iss2/12
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License