{
  "abstract": "While machine learning models offer potential for predicting transcriptomic effects of perturbation, they currently struggle to generalize across cellular contexts. Here, we introduce State, a machine learning model that predicts perturbation effects while accounting for cellular heterogeneity within and across experiments. State is trained using single-cell gene expression data to predict perturbation effects across sets of cells. State improved discrimination of effects on large datasets by more than 30% and identified differentially expressed genes across genetic, signaling, and chemical perturbations with significantly improved accuracy compared with baselines. Its cell embeddings trained on observational data from 167 million cells enable the identification of strong perturbations in cellular contexts where no perturbations were observed during training. We further introduce Cell-Eval, a comprehensive evaluation framework that can be used to evaluate future models. Overall, the performance and flexibility of State set the stage for scaling the development of AI models of cell state.",
  "abstract_shown": true,
  "affiliations": [
    "Arc Institute, Palo Alto, CA, USA",
    "Arc Institute, Palo Alto, CA, USA; University of California, Berkeley, Berkeley, CA, USA",
    "Arc Institute, Palo Alto, CA, USA; University of Pennsylvania, Philadelphia, PA, USA",
    "Arc Institute, Palo Alto, CA, USA; University of California, San Francisco, San Francisco, CA, USA",
    "Arc Institute, Palo Alto, CA, USA; Stanford University, Stanford, CA, USA",
    "Arc Institute, Palo Alto, CA, USA; Yale University, New Haven, CT, USA",
    "Myllia Biotechnology GmbH, Vienna, Austria",
    "Stanford University, Stanford, CA, USA",
    "Arc Institute, Palo Alto, CA, USA. Electronic address: yusuf.roohani@arcinstitute.org"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 32,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Abhinav Adduri",
      "orcid": "0000-0002-7676-8994"
    },
    {
      "affs": [
        1
      ],
      "name": "Dhruv Gautam"
    },
    {
      "affs": [
        0
      ],
      "name": "Beatrice Bevilacqua",
      "orcid": "0000-0002-9462-4599"
    },
    {
      "affs": [
        1
      ],
      "name": "Mohsen Naghipourfar",
      "orcid": "0000-0003-0465-0126"
    },
    {
      "affs": [
        1
      ],
      "name": "Alishba Imran"
    },
    {
      "affs": [
        2
      ],
      "name": "Rohan Shah"
    },
    {
      "affs": [
        0
      ],
      "name": "Noam Teyssier",
      "orcid": "0000-0003-4001-6296"
    },
    {
      "affs": [
        0
      ],
      "name": "Rishi Verma",
      "orcid": "0009-0002-9995-9475"
    },
    {
      "affs": [
        3
      ],
      "name": "Christopher Carpenter"
    },
    {
      "affs": [
        0
      ],
      "name": "Basak Eraslan",
      "orcid": "0000-0003-3698-8279"
    },
    {
      "affs": [
        0
      ],
      "name": "Francis Chalissery"
    },
    {
      "affs": [
        0
      ],
      "name": "Rajesh Ilango"
    },
    {
      "affs": [
        3
      ],
      "name": "Vishvak Subramanyam",
      "orcid": "0000-0002-6144-8322"
    },
    {
      "affs": [
        0
      ],
      "name": "Chiara Ricci-Tam",
      "orcid": "0000-0002-6549-1838"
    },
    {
      "affs": [
        4
      ],
      "name": "Sanjay Nagaraj"
    },
    {
      "affs": [
        3
      ],
      "name": "Aidan F. Winters",
      "orcid": "0000-0001-8024-6155"
    },
    {
      "affs": [
        5
      ],
      "name": "Mingze Dong",
      "orcid": "0000-0001-7367-6819"
    },
    {
      "affs": [
        6
      ],
      "name": "Stefanie Fellinger"
    },
    {
      "affs": [
        6
      ],
      "name": "Adam Krejčí"
    },
    {
      "affs": [
        6
      ],
      "name": "Tilmann Bürckstümmer",
      "orcid": "0000-0001-5681-8045"
    },
    {
      "affs": [
        0
      ],
      "name": "Sravya Tirukkovular"
    },
    {
      "affs": [
        0
      ],
      "name": "Jeremy Sullivan"
    },
    {
      "affs": [
        0
      ],
      "name": "Brian S. Plosky",
      "orcid": "0009-0000-5892-3017"
    },
    {
      "affs": [
        0
      ],
      "name": "Nicholas D. Youngblut"
    },
    {
      "affs": [
        7
      ],
      "name": "Jure Leskovec",
      "orcid": "0000-0002-5411-923X"
    },
    {
      "affs": [
        3
      ],
      "name": "Luke A. Gilbert",
      "orcid": "0000-0001-5854-0825"
    },
    {
      "affs": [
        4
      ],
      "name": "Silvana Konermann",
      "orcid": "0000-0001-7915-1685"
    },
    {
      "affs": [
        1
      ],
      "name": "Patrick D. Hsu",
      "orcid": "0000-0002-9380-2648"
    },
    {
      "affs": [
        0
      ],
      "name": "Alexander Dobin"
    },
    {
      "affs": [
        0
      ],
      "name": "Dave P. Burke"
    },
    {
      "affs": [
        3
      ],
      "name": "Hani Goodarzi",
      "orcid": "0000-0002-9648-8949"
    },
    {
      "affs": [
        8
      ],
      "name": "Yusuf Roohani",
      "orcid": "0000-0002-9577-5014"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/16zpjdf66g4xs.bib",
  "cited_by": 154,
  "doi": "10.1016/j.cell.2026.07.052",
  "fulltext_url": null,
  "id": "16zpjdf66g4xs",
  "issns": [
    "0092-8674",
    "1097-4172"
  ],
  "landing_url": "https://doi.org/10.1016/j.cell.2026.07.052",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W4411757935",
  "pdf_url": null,
  "pmcid": null,
  "pmid": "42673963",
  "published": "2026-08-31",
  "publisher": "Cell Press",
  "ris": "https://research.draconitic.com/paper/16zpjdf66g4xs.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:26:46Z",
      "native_id": "W4411757935",
      "source": "openalex",
      "url": "https://doi.org/10.1016/j.cell.2026.07.052"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Single-cell and spatial transcriptomics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Predicting cellular responses to perturbation across diverse contexts with State",
  "title_text": "Predicting cellular responses to perturbation across diverse contexts with State",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:05Z",
  "url": "https://research.draconitic.com/paper/16zpjdf66g4xs",
  "venue": "Cell",
  "versions": []
}