Sunday, 15 October 2023 13:45

Predicting the effect of drugs on single cells with the help of computers Featured

Physicians and bioinformaticians at the Swiss Federal Institute of Technology Zurich, the University of Zurich and University Hospital Zurich report using machine learning to develop a method for predicting how individual cells will respond to specific treatments. This should enable more accurate diagnoses and therapies.


The researchers have developed a new prediction method called "CellOT." This can not only evaluate existing measurement data from patient cells and thus expand knowledge of cellular disruptive responses. It can also predict how individual cells from a patient will respond to a perturbation whose responses have not yet been measured in the laboratory.

This, researchers hope, will lead to more accurate and personalized therapies.

Original publications:
Bunne, C, Stark, SG, Gut, G, Sarabia del Castillo, J, Lehmann, K-V, Pelkmans, L, Krause, A, Rätsch, G. Learning single-cell perturbation responses using neural optimal transport. Nature Methods (2023). 28 September 2023. DOI: external page10.1038/s41592-023-01969-xcall_made.

Research Briefing. Neural optimal transport predicts perturbation responses at the single-cell level. Nature Methods (2023). 28 September 2023. DOI: external page10.1038/s41592-023-01968-ycall_made.

Read more here:
https://ethz.ch/en/news-and-events/eth-news/news/2023/10/predictions-of-the-effect-of-drugs-on-individual-cells-are-now-possible.html