{
  "abstract": "A central goal of biology is to predict the dynamics of multicellular systems. Lineage context (the states of a cell's sisters, cousins, etc.) could inform these predictions, but how best to leverage it remains unclear. Here we introduce lineage inpainting, a generative modeling approach that uses lineage context with tree-structured transformers and stochastic interpolants to model cell state dynamics across lineage trees. Applied to a lineage-traced transcriptional atlas of mouse embryogenesis, it recovers dynamics not resolved by gene expression alone, including multiple transcriptional convergence events where distinct lineages are drawn to a common state. Despite being fit on unperturbed development, lineage inpainting can generate hypotheses about perturbation responses by simulating counterfactuals. These simulations agree in many cases with observed developmental phenotypes, including a single-cell measurement of the Tbx5 knockout response. Our results show that lineage information provides a rich source of context for learning multicellular dynamics.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "research article",
  "arxiv": "2610.40447",
  "author_total": 13,
  "authors": [
    {
      "name": "Gokul Gowri"
    },
    {
      "name": "Nic Fishman"
    },
    {
      "name": "William N. Colgan"
    },
    {
      "name": "Minming Wang"
    },
    {
      "name": "Yusuke Kijima"
    },
    {
      "name": "Sachin A. Kumar"
    },
    {
      "name": "Aleksandr Zimin"
    },
    {
      "name": "Luke W. Koblan"
    },
    {
      "name": "Marinka Zitnik"
    },
    {
      "name": "Zachary D. Smith"
    },
    {
      "name": "Stephen Bates"
    },
    {
      "name": "Philippe Rigollet"
    },
    {
      "name": "Jonathan S. Weissman"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0p7vcjzmv1gvr.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.40447",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13735029/",
  "id": "0p7vcjzmv1gvr",
  "issns": [
    "2331-8422"
  ],
  "landing_url": "https://arxiv.org/abs/2610.40447",
  "language": "en",
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "heading",
      "Article"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.40447",
  "pmcid": "PMC13735029",
  "pmid": "42995749",
  "published": "2026-10-29",
  "publisher": "arXiv",
  "ris": "https://research.draconitic.com/paper/0p7vcjzmv1gvr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:36:36Z",
      "native_id": "2610.40447",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.40447"
    },
    {
      "first_seen": "2026-11-09T12:20:48Z",
      "native_id": "PMC13735029",
      "source": "pmc",
      "url": null
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Learning developmental dynamics from lineage context",
  "title_text": "Learning developmental dynamics from lineage context",
  "type": "preprint",
  "updated_at": "2026-11-09T12:20:48Z",
  "url": "https://research.draconitic.com/paper/0p7vcjzmv1gvr",
  "venue": "arXiv",
  "versions": []
}