Tracking down cellular gene functions with AI and microscopy

Sadie Harley

Scientific Editor

Robert Egan

Senior Editor

Cell(2026). DOI: 10.1016/j.cell.2026.09.021

A new technology promises to enable more comprehensive investigations into how individual genes determine the appearance and behavior of cells. Researchers led by professor Veit Hornung at LMU's Gene Center and professor Matthias Mann at the Max Planck Institute of Biochemistry in Martinsried, together with professor Fabian Theis at Helmholtz Munich, have developed SPARCS, a technology that combines artificial intelligence with microscopy and genetic screening.

It enables researchers to screen millions of genetically modified cells for complex visual features and then selectively isolate individual cells of interest. Using SPARCS, cellular effects can thus be linked to the genetic changes that cause them. The findings have now been published in the journal Cell.

Genes involved in cellular recycling and the immune system

In their study, the scientists used artificial intelligence to analyze microscopy images of a total of 70 million cells for changes caused by genetic alterations. In an initial genome-wide proof-of-concept experiment, the researchers investigated autophagy—an important cellular recycling process.

"SPARCS identified a large proportion of the genes already known to regulate autophagosome formation, while also uncovering additional genes involved in the process," says first author Dr. Niklas Schmacke (LMU).

The researchers also examined STING, a key sensor of the innate immune system. They found that the acidity of the Golgi apparatus is important for the early transport of STING within the cell. The protein GPHR influences this pH level and, consequently, the subsequent activation of the immune sensor.

Because the selected cells are isolated intact, the researchers were then able to analyze their protein composition using mass spectrometry. This allowed them to precisely characterize the effects of genetic changes at the molecular level.

Overall, the study demonstrated how artificial intelligence, combined with scalable image-based genetic screening, opens up new opportunities to systematically investigate genes and advance biological discovery, the researchers say.

Publication details

Niklas A. Schmacke et al, SPARCS enables scalable recovery of complex image-based phenotypes for genetic screening, Cell (2026). DOI: 10.1016/j.cell.2026.09.021

Journal information:

Cell

Provided by Ludwig Maximilian University of Munich

Citation: Tracking down cellular gene functions with AI and microscopy (2026, October 8) retrieved 8 October 2026 from https://phys.org/news/2026-10-tracking-cellular-gene-functions-ai.html