24.01.2025

©Astrid Eckert / TUM
How to Analyze Millions of Individual Cells
TUM News Article
Researchers from the Technical University of Munich (TUM) and Helmholtz Munich have tested self-supervised learning as a promising approach for analysing over 20 million individual cells. MCML PI Fabian Theis holds the Chair of Mathematical Modelling of Biological Systems at TUM. Together with his team, he has investigated whether self-supervised learning is better suited to analysing large amounts of data than other methods.
Given the enormous amounts of data generated by advances in single-cell technology, it is important to interpret them efficiently in order to recognise differences between healthy cells and those with diseases such as lung cancer or COVID-19. Self-supervised learning does not require pre-classified data and enables the robust processing of large amounts of data.
The study shows that this method improves performance, especially on transfer tasks and zero-shot predictions. The researchers compare masked learning and contrastive learning and find that masked learning is better suited for large datasets. The results could lead to the development of virtual cells that map the diversity of cells in different datasets and are useful for analysing cell changes in diseases.
24.01.2025
Related

01.09.2025
Gitta Kutyniok Appears on ARD Audiothek
MCML PI Gitta Kutyniok featured on ARD Audiothek, discussing climate-neutral AI and sustainable data centers.

21.08.2025
Björn Ommer Featured on IT-BUSINESS Podcast
MCML PI Björn Ommer discussed the state and opportunities of generative AI in Germany on the IT-BUSINESS podcast.

05.08.2025
MCML PI Björn Schuller Featured in ARD Documentary on AI and Depression Therapy
MCML PI Björn Schuller discusses the use of AI as a digital therapist in ARD’s documentary “Depression - How to Get Out of It?”

01.08.2025
Stephan Günnemann Featured in BR24
MCML PI Stephan Günnemann was featured in BR24 on the future of AI agents and their role in software, law, and corporate decision-making.