Truace
Subscribe

Discovery of dietary polyphenols targeting the autoinducer-2 quorum sensing system of pathogenic bacteria

Targeting autoinducer-2 (AI-2) quorum sensing (QS) systems with dietary compounds represents a promising strategy to combat pathogens, yet mechanisms remain elusive. Here, we develop a machine learning-driven framework combining computational screening with multi-level experimental analysis to identify AI-2 quorum sensing interference molecules (QSIMs). A graph neural network (GNN)-based classifier (AI2IMpred) screens over 7000 phytochemicals and identifies dietary polyphenols as potent QSIMs. Using Salmonella T…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-1348· cite & verify
Discovery of dietary polyphenols targeting the autoinducer-2 quorum sensing system of pathogenic bacteria
Cdc stab culture by Todd Parker, Ph.D., Assoc Director for Laboratory Science, Div of Preparedness and Emerging Infections at CDC. Public domain

In brief

Researchers built a machine learning framework around a graph neural network classifier called AI2IMpred and used it to screen more than 7000 plant-derived compounds for the ability to interfere with the AI-2 quorum sensing system that bacteria use to coordinate behavior. Dietary polyphenols emerged as strong candidates.

Using Salmonella Typhimurium LT2 as a model, the team confirmed that 17 polyphenols bind key quorum sensing proteins and altered gene expression, bacterial traits and infection-related behavior in cell tests. The work matters because it suggests a route to diet-based approaches against drug-resistant pathogens, though the abstract describes only potential development, not clinical use.

Main points

  1. The AI2IMpred graph neural network classifier screened more than 7000 phytochemicals for quorum sensing interference.
  2. Seventeen polyphenols, including pterostilbene and pyrogallol, were confirmed by SPR assays to target LuxS and LsrB in Salmonella.
  3. Molecular docking predicted possible interactions with TqsA and LsrR, which were not confirmed by SPR in the abstract.
  4. Para-substituted hydrocarbyl groups were found to enhance binding to LsrB.

The gain

A machine learning classifier screening over 7000 phytochemicals identified 17 polyphenols that bind quorum sensing proteins in Salmonella, pointing toward diet-based options against drug-resistant infections.

The rundown

The framework pairs computational screening with multi-level experimental analysis. The machine learning model prioritized candidates, and surface plasmon resonance assays tested whether the compounds physically bind the target proteins LuxS and LsrB.

Beyond binding, the effects of polyphenols were checked through gene expression changes, bacterial phenotypes, and adhesion and invasion assays using NCM460 cells. Structural analysis identified para-substituted hydrocarbyl groups as enhancing LsrB binding.

The researchers also performed cross-pathogen analysis with Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa, indicating the approach may extend beyond the Salmonella model.

Sources

  1. Peer-reviewedGut Microbes2026-10-03

The debate