{
  "abstract": "Tissue graph counterfactuals ask what a cell would express if its spatial neighborhood were altered, a question central to predicting cell behavior in tissues. Existing methods, however, present only specific instances of such queries. In this work, we first formalize tissue graph counterfactuals as a class of spatial interventions that either rewire connections between cells (edge perturbation) or modify the expression of their neighbors (node perturbation). We then introduce Cellina (https://cellina.readthedocs.io), a framework that uses supervised disentanglement to decompose a cell's intrinsic state from its spatial context, using the latter as a conditioning input for in-silico perturbation predictions. Across benchmarks spanning over 2.5 million spatially-resolved cells in observational and interventional screens, Cellina outperforms both spatially-informed and non-spatial competitors in in-silico perturbations, while training as fast as non-spatial methods. Moreover, we show that Cellina reveals cancer subdomains with distinct signaling programs in an unsupervised manner and enables targeted neighbor perturbation simulations.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.08493",
  "author_total": 7,
  "authors": [
    {
      "name": "Abdul Moeed"
    },
    {
      "name": "Stefan Schrod"
    },
    {
      "name": "Martin Rohbeck"
    },
    {
      "name": "Marc Jan Bonder"
    },
    {
      "name": "Pavlo Lutsik"
    },
    {
      "name": "Oliver Stegle"
    },
    {
      "name": "Daniel Dimitrov"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0zqs24h2zgde0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.08493",
  "fulltext_url": null,
  "id": "0zqs24h2zgde0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.08493",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7163991750",
  "pdf_url": "https://arxiv.org/pdf/2606.08493",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0zqs24h2zgde0.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:21:15Z",
      "native_id": "2606.08493",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.08493"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement",
  "title_text": "Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:50Z",
  "url": "https://research.draconitic.com/paper/0zqs24h2zgde0",
  "venue": "arXiv",
  "versions": []
}