{
  "abstract": "Synthetic single-cell RNA-seq data generation offers a promising route for privacy-aware biomedical data sharing, but donor-linked datasets require careful balancing of biological utility and privacy risk. In this work, we benchmark synthetic generation methods for the CAMDA 2026 ELSA Health Privacy Challenge using the donor-split OneK1K dataset, comparing scGFT, scLDM, and Cell2Sentence across statistical fidelity, downstream biological preservation, and membership inference vulnerability. Because full-transcriptome generation is computationally demanding, we focus generative modeling on highly variable genes and evaluate alternative strategies for reconstructing non-HVG expression. Our results show that non-HVG handling is a central determinant of privacy: directly copying non-HVG values leads to severe leakage, whereas Poisson-based reconstruction substantially reduces membership inference risk. We further find that scGFT and scLDM better preserve biological structure than an independent Poisson baseline, while maintaining near-random privacy profiles under appropriate configurations. These findings highlight the importance of evaluating synthetic single-cell data beyond marginal similarity alone, emphasizing robustness, interpretability, and privacy-conscious design choices throughout preprocessing, generation, and post-processing.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.31454",
  "author_total": 3,
  "authors": [
    {
      "name": "Buse Giledereli"
    },
    {
      "name": "Basar Temiz"
    },
    {
      "name": "Amirreza Sattarzadeh Khanehbargh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3a98r7x4fe68n.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.31454",
  "fulltext_url": null,
  "id": "3a98r7x4fe68n",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.31454",
  "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",
      "q-bio.GN"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7223357350",
  "pdf_url": "https://arxiv.org/pdf/2610.31454",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3a98r7x4fe68n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:38Z",
      "native_id": "2610.31454",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.31454"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Benchmarking Recent Single-Cell Synthetic Data Generation Methods on the OneK1K Dataset",
  "title_text": "Benchmarking Recent Single-Cell Synthetic Data Generation Methods on the OneK1K Dataset",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:38Z",
  "url": "https://research.draconitic.com/paper/3a98r7x4fe68n",
  "venue": "arXiv",
  "versions": []
}