COIOSDeep risk insights through multi-disciplinary research across the globe
stainless steel spoon and fork on brown wooden tray
Item new Peer-reviewed Added

Machine learning screen finds 17 dietary polyphenols that bind Salmonella proteins

A graph neural network screened over 7,000 plant compounds, and laboratory binding assays confirmed that 17 dietary polyphenols attach to two proteins Salmonella uses to coordinate its virulence.

A graph neural network classifier screened over 7,000 plant compounds for molecules that interfere with the chemical signalling bacteria use to coordinate infection. Binding assays confirmed that 17 polyphenols, including pterostilbene and pyrogallol, attach to two of these signalling proteins in Salmonella Typhimurium. The compounds also changed the activity of those signalling genes and the bacteria's attachment to human gut cells grown in culture.

Why it is interesting: Machine learning used to find compounds rather than to predict outcomes, with the evidence stopping at laboratory work.

Source
Gut Microbes, 3 October 2026
Paper
Discovery of dietary polyphenols targeting the autoinducer-2 quorum sensing system of pathogenic bacteria
Authors
Wu S, Zhang P, Wang M, Xiao X, Jin H, Zhang H et al.
DOI
10.1080/19490976.2026.2726629
Type
Peer-reviewed article
Design
In-silico screen of >7,000 phytochemicals with a graph neural network classifier, followed by SPR binding, docking, gene expression and cell-adhesion assays in Salmonella Typhimurium LT2 and three other pathogens
Verdict
New finding
Driver
AI in medicine
Free full text
Free to read at the publisher

Other drivers in Data, models and systems