TUM – Technical University of Munich Menu
Durch die Einzelzell-RNA-Sequenzierung lässt sich herausfinden, welche DNA-Abschnitte für die Bildung einer Zelle aktiv werden. (Bild: iStockphoto.com / D-Keine)
Durch die Einzelzell-Analyse lässt sich herausfinden, welche DNA-Abschnitte für die Bildung einer Zelle aktiv werden. (Bild: iStockphoto.com / D-Keine)
  • Research news

New algorithms identify measuring errors in single-cell sequencing

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 been prone to errors. A team from the Technical University of Munich (TUM), the Helmholtz Center Munich, and the English Wellcome Sanger Institute has developed new algorithms which predict and correct such sources of error with the use of artificial intelligence (AI).

Being able to map all the cells in the human body and thereby improve the diagnosis, monitoring, and treatment of diseases — this is the vision behind the international Human Cell Atlas project. Such a reference database for the development of personalized medicine aims to allow healthy cells to be distinguished from diseased ones. This is made possible by single-cell RNA sequencing. With this method, it can be determined which genes play a role for the production of a cell. When a protein for cell assembly is generated, only certain segments of a person's DNA are read and translated into RNA which serves as a basis for protein biosynthesis.

Extremely fine measurements are necessary for single-cell RNA sequencing. These are frequently distorted by the devices used, the environment, or the cell biology itself. Discrepancies in the measurements occur, for example, when the temperature of the measuring instrument has deviated even slightly or the processing time of the cells changes. Although several models exist for the correction of this so called batch effect, those methods are highly dependent on the actual magnitude of the effect. Fabian Theis is a professor for Mathematical Modelling of Biological Systems at the TUM and the director of the Institute of Computational Biology at the Helmholtz Zentrum. His team has developed a new measure called kBET which quantifies differences between experiments and therefore facilitates the comparison of different correction results. The findings were presented in a publication in Nature Methods.

An algorithm that detects dropout events

One other challenge for single-cell sequencing are dropout events. "Let’s say we sequence a cell and observe that a particular gene in the cell does not emit any signal at all. The underlying cause of this can be biological or technical in nature: either the gene is not being read by the sequencer because it’s simply not expressed, or it could not be detected for technical reasons", says Fabian Theis.

Whether a dropout event occurred due to a biological or technical failure can now be determined by an algorithm which Theis' group has developed. The software presented in Nature Communications is based on a new probability model and compares the original with the reconstructed data. "We're not developing software to smooth out results", says Theis. "Our chief goal is to identify and correct errors. We’re able to share these data, which are as accurate as possible, with our colleagues worldwide and compare our results with theirs." The reliability and comparability of the data are of paramount importance if they are to be integrated to major projects like the Human Cell Atlas. "Our new algorithm is one of the first in the area of single-cell genomics to be based on neural networks and is the fastest in this field so far", says Theis.


Büttner, M.; Theis F. et al. (2019): A test metric for assessing single-cell RNA-seq batch correction. Nature Methods, DOI: 10.1038/s41592-018-0254-1

Eraslan, G.; Simon, L.M.; Theis F. et al. (2019): Single cell RNA-seq denoising using a deep count autoencoder. Nature Communications, DOI: 10.1038/s41467-018-07931-2


Prof. Dr. Fabian Theis
Technichal University of Munich
Department of Mathematics
Chair of Mathematical Modelling of Biological Systems
Tel.: +49 (0)89 3187 2211

Corporate Communications Center

Technical University of Munich

Article at tum.de

Computer biology can be used to calculate cell changes.

AI extrapolates from mice to humans

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...

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...

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...