From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling

Authors

Gelard, M., Benkirane, H., Pierrot, T., Cournede, P.-H., P. de Almeida, B.

Abstract

Tumour heterogeneity reflects both cellular identity (lineage) and state (active transcriptional programs), yet computational methods generally analyse these axes separately. We introduce CellScribe, a generative framework that conditions a pretrained language model on frozen single cell foundation model embeddings through AdaLN adapters, enabling one shared model to generate an ontology- grounded cell type or a quantified meta-program profile. Supervised multitask fine- tuning produces fine grained typing across hundreds of cell types and outperforms generative and retrieval baselines on meta-program identification under study-holdout evaluation. We further train the model with reinforcement learning, scoring its generations against cell ontology distance and meta-program agreement, so that they align with biological knowledge rather than token agreement. To identify new cell types not present in the supervised training data, we post-train the model to read several labelled example cells in a single context, each conditioning its own text span, and infer the type of a query cell through in-context learning. CellScribe thus unifies cell identity and state in one generative interface, grounds both in biological structure, and identifies cell types outside the supervised vocabulary.

Preprint server: bioRxiv
The authors list and abstract were imported from bioRxiv on 16 Oct 2026.

Stats

1-terrible, 9-excellent. How would you rate this preprint? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.