Hungarian researchers develop machine learning method to track bacterial cell damage

Researchers from the HUN-REN Szeged Biological Research Centre and the Hungarian Center for Molecular Medicine Excellence (HCEMM) have developed a new machine learning-based method to track how bacteria interact with human cells. The system, named MALVINA (Machine Learning-Based Virulence Interaction Analysis), uses fluorescent labeling to identify bacteria within human cells and employs machine learning to analyze microscopic images.

Unlike traditional averaging methods that only measure total bacterial quantity, MALVINA provides cell-by-cell data. This allows scientists to distinguish between different infection patterns, such as whether a small number of bacteria are spreading across many cells or if a large quantity is accumulating within just a few cells. The method can simultaneously measure bacterial presence, accumulation levels, and the resulting DNA damage to the host cell.

This high-throughput approach is expected to assist in identifying dangerous bacterial strains, testing drug candidates, and developing new probiotic approaches. It can also reveal how different bacteria influence one another when they interact with human cells simultaneously.