24.01.2025

Teaser image to How to analyze millions of individual cells

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


Subscribe to RSS News feed

Related

Link to Gitta Kutyniok Appears on ARD Audiothek

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.

Link to Björn Ommer featured on IT-BUSINESS podcast

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.

Link to MCML PI Björn Schuller Featured in ARD Documentary on AI and Depression Therapy

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?”

Link to Stephan Günnemann featured in BR24

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.

Link to AI research by Daniel Rückert improves medical imaging and data privacy

29.07.2025

AI Research by Daniel Rückert Improves Medical Imaging and Data Privacy

Daniel Rückert develops AI for faster medical imaging and secure data use through federated learning and privacy-preserving methods.