{
  "abstract": "Formalin-fixed paraffin-embedded (FFPE) tumor tissues often suffer from RNA degradation, posing a long-standing challenge for reliable transcriptomic profiling. Here, we propose FFPERescuer, a deep learning framework employing unsupervised domain adaptation, to rectify distorted gene expression data. FFPERescuer comprises a partial encoder that maps a small subset of genes to high-level representations and a decoder to reconstruct full gene expression profiles. On simulated data with varying noise levels, FFPERescuer faithfully recovered gene expression profiles, achieving high Pearson correlation coefficients (PCCs > 0.85) with the ground truth. In FF-FFPE-matched cohorts, FFPERescuer significantly enhanced expression profile concordance, with average PCCs increased by 23% (P < 0.05). Applying to cancer subtyping, FFPERescuer improved classification accuracy from 67% to 92%, recapitulated subtype-specific biological properties lost in the FFPE-derived data, and enhanced survival associations. Our studies provide a powerful framework for reliable transcriptomic profiling from FFPE-archived tumor samples that are widely available in the clinic.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Surgery, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 21,
  "authors": [
    {
      "name": "l. He"
    },
    {
      "name": "K. Song"
    },
    {
      "name": "Y. Li"
    },
    {
      "name": "Y. Dong"
    },
    {
      "name": "C. Y. N. Wong"
    },
    {
      "name": "L. Qi"
    },
    {
      "name": "X. Zhang"
    },
    {
      "name": "K. Lenos"
    },
    {
      "name": "T. d. Back"
    },
    {
      "name": "C. Elbers"
    },
    {
      "name": "C. Xu"
    },
    {
      "name": "R. M. H. Leung"
    },
    {
      "name": "R. Deng"
    },
    {
      "name": "Y. Zhang"
    },
    {
      "name": "S. Qiao"
    },
    {
      "name": "F. Gao"
    },
    {
      "name": "Y. Chen"
    },
    {
      "name": "S. S.-M. Ng"
    },
    {
      "name": "S. Zhou"
    },
    {
      "name": "L. Vermeulen"
    },
    {
      "affs": [
        0
      ],
      "name": "X. Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/39wk7m0zdrw8d.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.02.748790",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748790v1.full",
  "id": "39wk7m0zdrw8d",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748790v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Gene expression and cancer classification"
    ]
  ],
  "openalex": "W7211949325",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748790v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/39wk7m0zdrw8d.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:11Z",
      "native_id": "10.64898/2026.09.02.748790",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748790v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "FFPERescuer: deep unsupervised domain adaptation for the reconstruction of gene expression profiles derived from formalin-fixed paraffin-embedded samples",
  "title_text": "FFPERescuer: deep unsupervised domain adaptation for the reconstruction of gene expression profiles derived from formalin-fixed paraffin-embedded samples",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:11Z",
  "url": "https://research.draconitic.com/paper/39wk7m0zdrw8d",
  "venue": "bioRxiv",
  "versions": []
}