{
  "abstract": "Background: The synthesis of anonymized data derived from real-world cohorts offers a promising strategy for regulatory-compliant and privacy-preserving biological data sharing, potentially facilitating model development that can improve predictive performance. However, the extent to which generative models can preserve biological signals while remaining resilient to adversarial privacy attacks in high-dimensional omics contexts remains underexplored. To address this gap, the CAMDA 2025 Health Privacy Challenge launched a community-driven effort to evaluate synthetic and privacy-preserving data generation for bulk RNA-seq cohorts.\n\nResults: Building on this initiative, we systematically benchmark 11 generative methods across two cancer cohorts (~ 1,000 and ~ 5,000 patients) over 978 landmark genes. Methods are evaluated across distributional fidelity, downstream utility, biological plausibility and empirical privacy risk, with emphasis on trade-offs between vulnerability to membership inference attacks and other evaluation dimensions. Expressive deep generative models achieve strong predictive utility and differential expression recovery, but are often more vulnerable to membership inference risk under the evaluated threat model. Differentially private methods improve resistance to attacks at the cost of reduced utility, while simpler statistical approaches offer competitive utility with moderate privacy risk and fast training.\n\nConclusions: Synthetic bulk RNA-seq quality is inherently multi-dimensional and shaped by trade-offs between utility, biological preservation and privacy. Our results indicate that model architecture drives distinct trade-offs across these axes, suggesting that model choice should align with dataset characteristics, intended downstream use and privacy requirements. Privacy risk should also be assessed using multiple complementary attack methods and, where possible, mitigated through formal differential privacy protection.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 22,
  "authors": [
    {
      "name": "Hakime Öztürk"
    },
    {
      "name": "Tejumade Afonja"
    },
    {
      "name": "Joonas Jälkö"
    },
    {
      "name": "Ruta Binkyte"
    },
    {
      "name": "Pablo Rodriguez-Mier"
    },
    {
      "name": "Sebastian Lobentanzer"
    },
    {
      "name": "Andrew Wicks"
    },
    {
      "name": "Jules Kreuer"
    },
    {
      "name": "Sofiane Ouaari"
    },
    {
      "name": "Nico Pfeifer"
    },
    {
      "name": "Shane Menzies"
    },
    {
      "name": "Sikha Pentyala"
    },
    {
      "name": "Daniil Filienko"
    },
    {
      "name": "Steven Golob"
    },
    {
      "name": "Patrick McKeever"
    },
    {
      "name": "Jineta Banerjee"
    },
    {
      "name": "Luca Foschini"
    },
    {
      "name": "Martine De Cock"
    },
    {
      "name": "Julio Saez-Rodriguez"
    },
    {
      "name": "Mario Fritz"
    },
    {
      "name": "Oliver Stegle"
    },
    {
      "name": "Antti Honkela"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/670pnxcbfjgjx.bib",
  "cited_by": 0,
  "doi": "10.1186/s13059-026-04326-1",
  "fulltext_url": null,
  "id": "670pnxcbfjgjx",
  "issns": [
    "1474-760X"
  ],
  "landing_url": "https://link.springer.com/article/10.1186/s13059-026-04326-1",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-09",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/670pnxcbfjgjx.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T12:22:48Z",
      "native_id": "10.1186/s13059-026-04326-1",
      "source": "crossref",
      "url": "https://link.springer.com/article/10.1186/s13059-026-04326-1"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "journal-openalex:1312|Genomics and Phylogenetic Studies",
      "subfield": "molecular-biology"
    },
    {
      "field": "biology",
      "origin": "issn:1474-760X",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Community benchmarking of generative models for privacy-preserving synthetic bulk RNA-seq data generation",
  "title_text": "Community benchmarking of generative models for privacy-preserving synthetic bulk RNA-seq data generation",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T12:22:48Z",
  "url": "https://research.draconitic.com/paper/670pnxcbfjgjx",
  "venue": "Genome Biology",
  "versions": []
}