Deep learning predicts hematopoietic stem cell development

February 21, 2017, Helmholtz Association of German Research Centres
What are they going to be? Hematopoietic stem cells under the microscope: New methods are helping the Helmholtz scientists to predict how they will develop. Credit: Helmholtz Zentrum München

Autonomous driving, automatic speech recognition, and the game Go: Deep Learning is generating more and more public awareness. Scientists at the Helmholtz Zentrum München and their partners at ETH Zurich and the Technical University of Munich (TUM) have now used it to determine the development of hematopoietic stem cells in advance. In 'Nature Methods' they describe how their software predicts the future cell type based on microscopy images.

Today, cell biology is no longer limited to static states but also attempts to understand the dynamic development of cell populations. One example is the generation of different types of from their precursors, the hematopoietic stem cells. "A 's decision to become a certain cell type cannot be observed. At this time, it is only possible to verify the decision retrospectively with ," explains Dr. Carsten Marr, head of the Quantitative Single Cell Dynamics Research Group at the Helmholtz Zentrum München's Institute of Computational Biology (ICB).

He and his team have now developed an algorithm that can predict the decision in advance. So-called Deep Learning is the key. "Deep Neural Networks play a major role in our method," says Marr. "Our algorithm classifies light microscopic images and videos of by comparing these data with past experience from the development of such cells. In this way, the algorithm 'learns' how certain cells behave."

Three generations earlier than standard methods

Specifically, the researchers examined hematopoietic stem cells that were filmed under the microscope in the lab of Timm Schroeder at ETH Zurich. Using the information on appearance and speed, the software was able to 'memorize' the corresponding behaviour patterns and then make its prediction. "Compared to conventional methods, such as fluorescent antibodies against certain surface proteins, we know how the cells will decide three cell generations earlier," reports ICB scientist Dr. Felix Buggenthin, joint first author of the study together with Dr. Florian Büttner.

But what is the benefit of this look into the future? As study leader Marr explains, "Since we now know which cells will develop in which way, we can isolate them earlier than before and examine how they differ at a molecular level. We want to use this information to understand how the choices are made for particular developmental traits."

In the future, the focus will expand beyond hematopoietic . "We are using Deep Learning for very different problems with sufficiently large data records," explains Prof. Dr. Dr. Fabian Theis, ICB director and holder of the Mathematical Modelling of Biological Systems Chair at the TUM, who led the study together with Carsten Marr. "For example, we use very similar algorithms to analyse disease-associated patterns in the genome and identify biomarkers in clinical cell screens."

Explore further: Enough is enough—stem cell factor Nanog knows when to slow down

More information: Buggenthin, F. et al. (2017): Prospective identification of hematopoietic lineage choice by deep learning. Nature Methods, DOI: 10.1038/nmeth.4182

Related Stories

A new tracking and quantification tool for single cells

July 19, 2016

Working with colleagues from the ETH Zürich, scientists at the Helmholtz Zentrum München and the Technical University of Munich have developed software that allows observing cells for weeks while also measuring molecular ...

Algorithms offer insight into cellular development

August 31, 2016

Through RNA sequencing, researchers can measure which genes are expressed in each individual cell of a sample. A new statistical method allows researchers to infer different developmental processes from a cell mixture consisting ...

Optimizing cell cycle analysis with the right algorithms

January 7, 2016

Scientists of the the Helmholtz Zentrum München have found a new approach improving the identification of cell cycle phases using imaging flow cytometry data. They could avoid the use of stains by applying algorithms from ...

Recommended for you

Genome duplication drives evolution of species

September 25, 2018

Many wild and cultivated plants arise through the combination of two species. The genome of these so-called polyploid species often consists of a quadruple set of chromosomes—a double set for each parental species—and ...

Some female termites can reproduce without males

September 24, 2018

Populations of the termite species Glyptotermes nakajimai can form successful, reproducing colonies in absence of males, according to a study published in the open access journal BMC Biology.

Photosynthesis discovery could help next-gen biotechnologies

September 24, 2018

Researchers from The University of Queensland (UQ) and the University of Münster (WWU) have purified and visualized the 'Cyclic Electron Flow' (CEF) supercomplex, a critical part of the photosynthetic machinery in all plants, ...

How fruits got their eye-catching colors

September 24, 2018

Red plums. Green melons. Purple figs. Ripe fruits come in an array of greens, yellows, oranges, browns, reds and purples. Scientists say they have new evidence that plants owe their rainbow of fruit colors to the different ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.