Dr. Moritz Schaefer
MedUni Wien RESEARCHER OF THE MONTH July 2026
Single-cell RNA sequencing (scRNA-seq) has become an indispensable tool in biomedical research. However, data analysis typically requires specialized software and programming skills. “CellWhisperer” is a new method that enables language-based analysis of single-cell data through a web interface: A simple command like “Show me structural cells with immune functions” suffices, and the corresponding cells are highlighted in color. The method is based on modern language models and allows analyzing cell data through a “chat” with arbitrary questions.
Comparative studies showed that users reached the same conclusions four times faster with CellWhisperer than with conventional methods. The software has already helped to temporally map organ formation in a human development atlas and uncover new developmental markers for the heart and other organs.
The CellWhisperer AI model is trained on over one million gene expression profiles, connecting biological data and language in a shared mathematical space to handle diverse user queries. CellWhisperer is available as open-source software
(https://cellwhisperer.bocklab.org) and demonstrates how AI assistants can make complex datasets accessible and promote hypothesis generation.
Selected Literature
- Schaefer, M.*, Peneder, P.*, Malzl, D., Lombardo, S. D., Peycheva, M., Burton, J., Hakobyan, A., Sharma, V., Krausgruber, T., Sin, C., Menche, J., Tomazou, E. M., & Bock, C. (2025). Multimodal learning enables chat-based exploration of single-cell data. Nature Biotechnology. https://doi.org/10.1038/s41587-025-02857-9
- Schaefer, M.*, Nonchev, K.*, Awasthi, A.*, Burton, J.*, Koelzer, V. H., Rätsch, G., & Bock, C. (2025). Molecularly informed analysis of histopathology images using natural language. bioRxiv. https://doi.org/10.1101/2025.07.14.664402
(* geteilte Erstautoren)