Urgent.News

What's breaking now, across thousands of outlets.

Science

Machine learning detects bacterial invasion and DNA damage in human cells

When scientists assess how dangerous a bacterium is, the first question often seems simple: Can it be stopped or killed? In microbiology and antibiotic research, one of the classic readouts has been whether a bacterium can grow in the presence of a given treatment. The bacterium either grows or it does not. The drug either stops it or it does not.

Machine learning detects bacterial invasion and DNA damage in human cells

Scientists at the HUN-REN Biological Research Center and the Hungarian Center of Excellence for Molecular Medicine have developed MALVINA, a machine learning tool that detects bacterial invasion and DNA damage in human cells. This method allows researchers to measure how efficiently bacteria enter cells, how strongly they accumulate inside them, and what kind of DNA damage they induce.

MALVINA connects previously unlinked processes at the single-cell level, connecting genotype with virulence phenotype. This tool is particularly useful when studying the same bacterial strain in different host cells, as it can reveal cell-to-cell differences that conventional averaged measurements cannot. In experiments using various E. coli strains, MALVINA identified distinct virulence profiles, including strong invasive capacity in one strain and reduced invasion in another when colibactin production was disabled.

The study also showed that bacterial behavior can change when encountering human cell treatments, with some drugs reducing viable bacteria while increasing invasion. Furthermore, the presence of other microbial neighbors can influence bacterial virulence, with invasive strains promoting the entry of less harmful strains. The MALVINA method provides a more precise picture of the consequences of infection by showing how many bacteria have entered a cell and the damage it has suffered.

Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at phys.org →

More in Science

More from Thursday 1 October →