{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "InstaDeep"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "M. Gelard"
    },
    {
      "name": "H. Benkirane"
    },
    {
      "name": "T. Pierrot"
    },
    {
      "name": "P.-H. Cournede"
    },
    {
      "name": "B. P. de Almeida"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2haa0ysnj7jhb.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.07.757352",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757352v1.full",
  "id": "2haa0ysnj7jhb",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757352v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7222121285",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757352v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2haa0ysnj7jhb.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:54Z",
      "native_id": "10.64898/2026.10.07.757352",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757352v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling",
  "title_text": "From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:54Z",
  "url": "https://research.draconitic.com/paper/2haa0ysnj7jhb",
  "venue": "bioRxiv",
  "versions": []
}