Adding layers of information to scRNA-seq data using pre-trained language models
Pre-trained language models promise to enrich single-cell analyses with contextual information from large biomedical text corpora, but it remains unclear how to optimally align this knowledge with quantitative single-cell RNA sequencing (scRNA-seq) data. To address this, we construct text-based training datasets from both scRNA-seq data and biomedical literature targeted to the experimental setting at hand. We then fine-tune lightweight encoder-only biomedical language models to learn a shared, literature-enriched representation. Controlled evaluations across immune and developmental datasets show that this representation preserves cell identity while adding robust and interpretable contextual layers of functional, disease-associated, and developmental information to single-cell analysis workflows.
Authors
- Jasper Menger (ORCID: https://orcid.org/0009-0000-9521-2281)
- Harald Binder (ORCID: https://orcid.org/0000-0002-5666-8662)
- Tanja Vogel (ORCID: https://orcid.org/0000-0002-0602-9133)
- Maren Hackenberg (ORCID: https://orcid.org/0000-0003-4403-634X)
- Johan Rollin (ORCID: https://orcid.org/0000-0002-9564-7872)
- Sonia Maria Krissmer (ORCID: https://orcid.org/0009-0004-8158-7305)
Institutions
- University of Freiburg (DE)
- University Medical Center Freiburg (DE)
- European Molecular Biology Laboratory (DE)
- European Molecular Biology Laboratory (DE)
Publication Details
- Journal
- Genome biology
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1186/s13059-026-04353-y
- Citations
- 1
- Primary Topic
- Single-cell and spatial transcriptomics
- Type
- article
- Field-Weighted Citation Impact
- 1.12
Funders
- Deutsche Forschungsgemeinschaft