In a research study, published in the January 2019 issue of Emerging Infectious Diseases a team of scientists at the University of Georgia Center for Food Safety used more than a thousand genomes to develop a machine-learning approach that could lead to quicker identification of the animal source of certain Salmonella outbreaks. The study used an algorithm (Random Forest), and data from <1,300 S. Typhimurium genomes from known sources (CDC’s PulseNet network, the FDA’s GenomeTrakr database of sources in the United States, Europe, South America, Asia, and Africa and retail meat isolates from the FDA arm of the National Antimicrobial Resistance Monitoring System). The system predicted the animal source of the S. Typhimurium with 83% accuracy. The algorithm performed best in predicting poultry and swine sources, followed by bovine and wild bird sources. The machine also detects whether its prediction is precise or imprecise. When the prediction was precise, the machine was accurate about 92 percent of the time. Frank Yiannas, deputy commissioner of the FDA, called the machine learning of whole genome sequences project “a new era of smarter food safety and epidemiology.”@ https://www.technologynetworks.com/informatics/news/machine-learning-helps-id-the-source-of-salmonella-315287 Reference: Al, S. Z. et. (n.d.). Zoonotic Source Attribution of Salmonella enterica Serotype Typhimurium Using Genomic Surveillance Data, United States - Volume 25, Number 1—January 2019 - Emerging Infectious Diseases journal - CDC. https://doi.org/10.3201/eid2501.180835
Identifying the Source of Salmonella enterica Serotype Typhimurium with the aid of Machine Learning
A team of scientists led by researchers at the University of Georgia Center for Food Safety in Griffin, Georgia, has developed a machine-learning approach that could lead to quicker identification of the animal source of certain Salmonella outbreaks.