USDA Grants $611,000 to UAlbany Scientists to Develop Rapid Salmonella Detection Kit

253

The U.S. Department of Agriculture’s National Institute of Food and Agriculture (USDA’s NIFA) has awarded $611,000 to University at Albany researchers to develop a rapid, portable, colorimetric Salmonella detection kit for food products. If successfully created, the test will reduce the time it takes to detect Salmonella in food from several days to as little as six hours.

The project will focus on detecting S. Enteritidis and S. Typhimurium, the two serotypes that are jointly responsible for half of all human Salmonella infections in the U.S. The team’s nano-diagnostic system will also serve as a template for foodborne bacterial detection beyond Salmonella.

The detection kit is based on a novel approach that relies on nanotechnology and artificial intelligence (AI), rather than leveraging reliable, yet time-consuming techniques used in conventional detection, like microbial culturing or whole genome sequencing (WGS).

The proposed diagnostic kit will include pre-filled vials, allowing the user to easily add a sample and induce the chemical reaction necessary to determine the presence or absence of Salmonella. When the processing is complete, color-coded results (purple for positive or red for negative) will be visible in a test tube solution or on a paper test strip.

The team is further exploring the development of an image analysis system, integrating machine learning techniques to interpret the color patterns exhibited on the nanoarray test strip. The innovative approach aims to empower users by providing automated assistance in result interpretation, enhancing the overall usability and accessibility of the Salmonella detection process. The feature is reminiscent to certain COVID-19 tests that allow a photo to be taken of a test strip for results interpretation, using a mobile phone. The AI in Complex Systems Lab at UAlbany will lead the development of a smartphone application specifically designed for image analysis, incorporating image recognition and machine learning techniques.

Source: Food Safety Magazine