{
  "abstract": "Predicting how cells, tissues, and patients will respond to a drug, cytokine, or genetic perturbation is central to biological and clinical reasoning. The practical goal is to estimate the analysis-ready readouts that support this reasoning: which cellular responses are context-dependent, which perturbations reveal shared or divergent mechanisms, and which observations should become the basis for the next experiment. Here we introduce Rhaister, a perturbation-response predictor that operates directly on screen-level summary statistics. By measuring just a few perturbations in a new biological context, Rhaister predicts the unmeasured perturbations by learning how response patterns vary across reference contexts. This formulation applies to both fine-grained molecular readouts, such as transcriptional responses from Tahoe-100M or other large perturbation screen, or on phenotypic endpoints. To train and apply Rhaister on pheno-typic endpoints we created Emerald Bay, a purpose-built Tahoe dataset that unifies multi-day cancer drug perturbation, pooled Mosaic tumor contexts, and paired transcriptomic response measurements * . Across these settings, Rhaister matches or exceeds substantially more expensive virtual-cell models, often achieving the highest values possible in evaluation metrics, while training in seconds and running predictions in milliseconds. On Emerald Bay, Rhaister predicts context-specific drug phenotypes from sensitivity measurements alone and improves further when including transcriptomic information. We also introduce Rhaister-O, predicting drug responses in new contexts from baseline expression alone and, to our knowledge, provides the first zero-shot model for this task. Rhaister establishes summary-statistic perturbation modeling as a fast, interpretable framework for predicting biological response across new contexts.",
  "abstract_shown": true,
  "affiliations": [
    "Tahoe Therapeutics, South San Francisco, CA, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Valentine Svensson",
      "orcid": "0000-0002-9217-2330"
    },
    {
      "affs": [
        0
      ],
      "name": "Umair Khan",
      "orcid": "0000-0002-6361-4996"
    },
    {
      "affs": [
        0
      ],
      "name": "Hamed Heydari",
      "orcid": "0000-0001-6708-9116"
    },
    {
      "affs": [
        0
      ],
      "name": "Airol A. Ubas"
    },
    {
      "affs": [
        0
      ],
      "name": "Nicole Thomas"
    },
    {
      "affs": [
        0
      ],
      "name": "Daniele Merico",
      "orcid": "0000-0002-3728-4401"
    },
    {
      "affs": [
        0
      ],
      "name": "Hani Goodarzi",
      "orcid": "0000-0002-9648-8949"
    },
    {
      "affs": [
        0
      ],
      "name": "Johnny X. Yu",
      "orcid": "0000-0002-9857-4349"
    },
    {
      "affs": [
        0
      ],
      "name": "Nima Alidoust"
    },
    {
      "affs": [
        0
      ],
      "name": "Shreshth Gandhi",
      "orcid": "0009-0004-2625-4575"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a1qbrfjqgf4dw.bib",
  "cited_by": 7,
  "doi": "10.64898/2026.06.09.731197",
  "fulltext_url": null,
  "id": "a1qbrfjqgf4dw",
  "issns": [],
  "landing_url": "https://doi.org/10.64898/2026.06.09.731197",
  "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",
      "3002|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7164497504",
  "pdf_url": "https://www.biorxiv.org/content/biorxiv/early/2026/06/12/2026.06.09.731197.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-12",
  "publisher": "Cold Spring Harbor Laboratory",
  "ris": "https://research.draconitic.com/paper/a1qbrfjqgf4dw.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:00Z",
      "native_id": "W7164497504",
      "source": "openalex",
      "url": "https://doi.org/10.64898/2026.06.09.731197"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:3002|Computational Drug Discovery Methods",
      "subfield": "medicinal"
    }
  ],
  "title": "Back to basics: Observed statistics are sufficient to predict drug responses",
  "title_text": "Back to basics: Observed statistics are sufficient to predict drug responses",
  "type": "preprint",
  "updated_at": "2026-11-09T13:21:17Z",
  "url": "https://research.draconitic.com/paper/a1qbrfjqgf4dw",
  "venue": "bioRxiv (Cold Spring Harbor Laboratory)",
  "versions": []
}