{
  "abstract": "Motivation: Single-cell cell-type classifiers are often evaluated using random cell-level splits, although cells from the same donor are not independent. We asked how evaluation design affects estimates of cross-donor generalization. Results: Across PBMC and lung datasets, random cell-level splitting consistently yielded higher macro F1 than donor-held-out evaluation across multiple expression representations. This gap persisted after batch covariate adjustment and donor-level mixed-effects modeling. In contrast, evaluation gaps were minimal in near-ceiling kidney, pancreas, and blood benchmarks and in a randomized-label floor control. These results show that evaluation bias depends on the underlying classification regime and that donor-held-out evaluation is necessary when claims concern generalization to unseen individuals. Availability and Implementation: Code and analyses are available on GitHub at https://github.com/danielchen05/scRNA-cross-donor-generalization/ and archived at Zenodo at 10.5281/zenodo.23669184. All data are publicly available and cited.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "Xingyi Chen",
      "orcid": "0009-0008-7226-2022"
    },
    {
      "name": "Jiabei Li",
      "orcid": "0009-0006-8707-8506"
    },
    {
      "name": "Alexis Battle",
      "orcid": "0000-0002-5287-627X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fzs625v2y4h3h.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.26.761949",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761949v1.full",
  "id": "fzs625v2y4h3h",
  "issns": [
    "2692-8205"
  ],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761949v1",
  "language": "en",
  "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"
    ],
    [
      "heading",
      "Article"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7223956409",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761949v1.full.pdf",
  "pmcid": "PMC13734011",
  "pmid": "42990534",
  "published": "2026-10-26",
  "publisher": "Cold Spring Harbor Laboratory Preprints",
  "ris": "https://research.draconitic.com/paper/fzs625v2y4h3h.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:51Z",
      "native_id": "10.64898/2026.10.26.761949",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761949v1"
    },
    {
      "first_seen": "2026-11-08T12:23:40Z",
      "native_id": "PMC13734011",
      "source": "pmc",
      "url": "https://doi.org/10.64898/2026.10.26.761949"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Evaluation design shapes estimates of cross-donor generalization in single-cell classification of cell-type",
  "title_text": "Evaluation design shapes estimates of cross-donor generalization in single-cell classification of cell-type",
  "type": "preprint",
  "updated_at": "2026-11-08T12:23:40Z",
  "url": "https://research.draconitic.com/paper/fzs625v2y4h3h",
  "venue": "bioRxiv",
  "versions": []
}