TUM – Technical University of Munich Menu
Computer biology can be used to calculate cell changes.
Computer biology can be used to calculate cell changes.
Image: iStock / nicolas_
  • Research news
  • Reading time: 2 MIN

Machine learning-based software scGen predicts cell behaviorAI predicts treatment success for diseases

The scGen computer model, developed by scientists at the Technical University of Munich (TUM) and Helmholtz Zentrum München, predicts how cells will behave. The software uses artificial intelligence to model the response of a cell to a disease or treatment – with no need for experimental data from pertubed human cells.

Cells can be altered by diseases or genetic mutations. However, the possibilities for finding out how cells are affected by various influences through laboratory experiments are limited. Due to the sheer number of possible combinations of treatment and disease conditions, expanding these data to characterize disease and disease treatment in traditional life science laboratories is labor intensive and costly and, hence, not scalable.

First machine learning model for predicting cell behavior

It is therefore a central goal of computational biology to use mathematical models to describe cellular responses to perturbations to make them accessible to numerical methods. Previous models were based on statistical and mechanistic approaches. With scGen, Fabian Theis, a professor of Mathematical Modelling of Biological Systems at TUM and the director of the Institute of Computational Biology at the Helmholtz Zentrum München, and his team have developed the first machine learning-based software tool in this area. The tool can be used to study high-dimensional phenomena for which no observations exist. It utilizes ideas from image, sequence and language processing to create a computer model of a cell's behavior.

Applying data from mice to human cells

Consequently, if scGen is trained with data capturing the effect of perturbations on a given system, the model can generate reliable predictions for another system of interest. The tool therefore harbors the potential for new approaches to the study and treatment of diseases. "For the first time, we have the opportunity to use data generated in one model system such as mouse and use the data to predict disease or therapy response in human patients," says Mohammad Lotfollahi, a PhD candidate at the TUM School of Life Sciences Weihenstephan.

scGen software to be expanded to address more complex problems

The participating researchers plan to improve the predictive power of scGen through further development work. This will also make it possible to compute combinations of factors affecting cells. "We can now start optimizing scGen to answer more and more complex questions about diseases," says Prof. Theis.


Theis, F.; Lotfollahi, M.; Wolf A.: scGen predicts single-cell perturbation responses. In: Nature Methods 16; 715-721 (2019). DOI 10.1038/s41592-019-0494-8

Corporate Communications Center

Technical University of Munich

Contacts to this article:

Prof. Fabian Theis
Technical University of Munich
Chair of Mathematical Modeling of Biological Systems
Tel: +49 (89) 289 18386

Article at tum.de

Das Bild zeigt Prof. Fabian Theis, beim Schreiben von Formeln an eine Tafel.

Germany-wide AI network headquartered in Munich

Informatics, robotics and machine intelligence are central fields of research at the Technical University of Munich (TUM). Now TUM is networking as a part of the new Helmholtz Artificial Intelligence Cooperation Unit...

Durch die Einzelzell-RNA-Sequenzierung lässt sich herausfinden, welche DNA-Abschnitte für die Bildung einer Zelle aktiv werden. (Bild: iStockphoto.com / D-Keine)

AI finds errors in RNA analysis

Why is it that some cells in the human body do not behave as they should and form cancerous tumors, for example? Researchers hope to find answers through what they call single-cell analysis. However, so far this method has...

In der Munich School of Data Science finden Doktorandinnen und Doktoranden ein auf sie zugeschnittenes Kursangebot. (Foto: iStockphoto/gorodenkoff)

New Graduate School for Data Science

Digitized research produces enormous amounts of data these days. This increasingly complex flood of data contains great potential, for example for biomedicine. However, big data needs to be controlled and interpreted in...

Mit der Software BaSiC verbessertes Mosaikbild eines Maushirn-Schnitts. (Bild: Tingying Peng / TUM/HMGU)

Clear view on stem cell development

Today, tracking the development of individual cells and spotting the associated factors under the microscope is nothing unusual. However, impairments like shadows or changes in the background complicate the interpretation...

Mehr als 40% aller Gene im Experiment korrelierten mit einem kleinen Satz bekannter Zellzyklus-Marker (orange) - Grafik: Florian Büttner

Mathematics improve single-cell analysis

A new computational approach allows to account for confounding factors and hidden biological processes in the analysis of single-cell RNA sequence data. Using this method, individual subpopulations and cell types can be...

Fluoreszenz-in-situ-Hybridisierung zeigt mRNA-Aktivität. Blau: niedrige, rot: hohe Aktivität Bild: S. S. Bajikar / University of Virginia, Charlottesville (USA)

Tracing unique cells with mathematics

Stem cells can turn into heart cells, skin cells can mutate to cancer cells; even cells of the same tissue type exhibit small heterogeneities. Scientists use single-cell analysis to investigate these heterogeneities. But...