{
  "abstract": "Single-cell screens of immune cells from many donors are used to study why individuals respond differently and to benchmark response models. Each donor-perturbation combination typically occupies one well, controls are grouped, and donors share one layout, so technical effects can look biological. Using a 90-cytokine screen, two compound screens, four cohorts and simulations, we show that well effects explain most replicate-control variation in abundant cell types, controls carry a shared offset, and identical control wells differ by hundreds of differentially expressed genes at a standard threshold, about as many as two receptor-negative proteins do. Negative controls, design-aware estimators and perturbation-specific evaluation change the interpretation of four recent analyses. A deep-learning model that scores below a perturbation-agnostic predictor under standard evaluation outperforms a simple baseline on perturbation-specific differences in two of three cell types (significantly in one with stricter controls), but predicts less well the component shared with inert wells.",
  "abstract_shown": true,
  "affiliations": [
    "Wright State University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "G. Ghajari"
    },
    {
      "name": "K. Thirunarayan"
    },
    {
      "name": "F. Amsaad"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9grh80sccvj57.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.04.764088",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.04.764088v1.full",
  "id": "9grh80sccvj57",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.04.764088v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.04.764088v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9grh80sccvj57.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T12:21:02Z",
      "native_id": "10.64898/2026.11.04.764088",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.04.764088v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Plate design confounds donor variation and model evaluation in single-cell perturbation screens",
  "title_text": "Plate design confounds donor variation and model evaluation in single-cell perturbation screens",
  "type": "preprint",
  "updated_at": "2026-11-07T12:20:29Z",
  "url": "https://research.draconitic.com/paper/9grh80sccvj57",
  "venue": "bioRxiv",
  "versions": []
}