Quantitative analysis of cell organelles with artificial intelligence
The images show part of a frozen mammalian cell. On the left is a section of the 3D X-ray tomogram (scale: 2 μm). The right image shows the reconstructed cell volume after applying the new AI-supported algorithm. © HZB /FU Berlin
X-ray microscopy (cryo-SXT) enables high-resolution insights into cells and cell organelles - in three dimensions. Until now, the 3D data sets have been analysed manually, which is very time-consuming. A team from Freie Universität Berlin has now developed a self-learning algorithm based on a convolutional neural network. In collaboration with experts in cell biology (FU Berlin) and X-ray microscopy at the Helmholtz Zentrum Berlin, this algorithm has now been used for the first time to analyse cell components in cryo-SXT data sets. It identified cell organelles and produced highly detailed, complex 3D images within a few minutes.
BESSY II’s high-brilliance X-rays can be used to produce microscopic images with spatial resolution down to a few tens of nanometres. Whole cell volumes can be examined without the need for complex sample preparation as in electron microscopy. Under the X-ray microscope, the tiny cell organelles with their fine structures and boundary membranes appear clear and detailed, even in three dimensions. This makes cryo x-ray tomography ideal for studying changes in cell structures caused, for example, by external triggers. Until now, however, the evaluation of 3D tomograms has required largely manual and labour-intensive data analysis.
To overcome this problem, teams led by computer scientist Prof. Dr. Frank Noé and cell biologist Prof. Dr. Helge Ewers (both from FU Berlin) have now collaborated with the X-ray microscopy department at HZB. The computer science team has developed a novel, self-learning algorithm. This AI-based analysis method is based on the automated detection of subcellular structures. It accelerates the quantitative analysis of 3D X-ray data sets. The 3D images of the interior of biological samples were acquired at the U41 beamline at BESSY II.
“In this study, we have now shown how well the AI-based analysis of cell volumes works. Using mammalian cells from cell cultures that have so-called filopodia,” says Dr Stephan Werner. Werner is an expert in X-ray microscopy at HZB. Mammalian cells have a complex structure with many different cell organelles, each of which has to fulfil different cellular functions. Filopodia are protrusions of the cell membrane and serve in particular for cell migration. “For cryo X-ray microscopy, the cell samples are first shock-frozen, so quickly that no ice crystals form inside the cell. This leaves the cells in an almost natural state and allows us to study the structural influence of external factors inside the cell,” Werner explains.
AI-based analysis method faster and and more reliable
“Our work has already aroused considerable interest among experts,” says first author Michael Dyhr from Freie Universität Berlin. The neural network correctly recognises about 70% of the existing cell features within a very short time, thus enabling a very fast evaluation of the data set. “In the future, we could use this new analysis method to investigate how cells react to environmental influences such as nanoparticles, viruses or carcinogens much faster and more reliably than before,” says Dyhr.
- AI agents deliver results – but do they reason scientifically?A research team co-led by Kevin Maik Jablonka from the Helmholtz Institute for Polymers in Energy Applications Jena (HIPOLE Jena) and N. M. Anoop Krishnan from the Indian Institute of Technology Delhi has developed Corral, a new benchmark for AI agents in science. The preprint “AI scientists produce results without reasoning scientifically” has been published on arXiv (https://doi.org/10.48550/arXiv.2604.18805). The analysis shows that current systems can execute scientific workflows and deliver results; however, they often do not follow the basic principles of scientific testing and reasoning.
- Magnetic field during catalyst synthesis triples ammonia yieldApplying an external magnetic field during the synthesis of CoFe₂O₄ electrocatalysts triples the ammonia yield during electrocatalytic conversion. The magnetic field alters the surface states of the spinel oxide thin films, making catalytically active sites more accessible. In the journal 'Advanced Functional Materials', a team led by Marcel Risch at HZB and Sanjay Mathur at University of Cologne demonstrates a scalable strategy for developing next-generation electrocatalysts for efficient and sustainable chemical production.
- Materials chemistry shapes the future of catalysisThe synthesis of materials can serve as a tool for developing smart, adaptive electrocatalysts. This rapidly evolving field of research involves in-situ analytics, data-driven discoveries and autonomous robotics. These new approaches could accelerate the discovery of long-lasting and efficient catalysts for future energy conversion and the decarbonisation of the chemical industry. A recent article by Dr Prashanth Menezes and his team in the renowned journal Angewandte Chemie provides an overview of this research.