{
  "abstract": "The growing availability of single-cell resources creates new opportunities to extract cell-type-resolved information from the vast body of existing bulk omics data through cell-type deconvolution. Conventional deconvolution methods often rely on linear mixture models or specific probabilistic assumptions and can be sensitive to batch effects, whereas many deep-learning approaches are modality-specific or lack a unified end-to-end learning framework. Here, we developed DECIPHER, an end-to-end representation-learning framework for cell-type deconvolution that can be applied across multiple molecular modalities. DECIPHER learns a domain-constant representation (Zc) for deconvolution and a domain-specific representation (Zs) to model domain-associated variation. By integrating nonlinear representation learning with differentiable non-negative least-squares optimization, DECIPHER estimates cell-type proportions from Zc. Across simulated datasets, experimentally generated bulk-cell mixtures, real-world datasets, and multiple molecular modalities, DECIPHER showed robust and competitive cell-type deconvolution performance. Beyond cell-type proportion estimation, the learned Zc supported chronological age prediction across independent cohorts and prognostic stratification in lung adenocarcinoma, demonstrating that DECIPHER can transform high-dimensional bulk omics data into low-dimensional, biologically informative representations. DECIPHER thus broadens the utility of existing bulk omics resources for biological discovery and clinical research.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Systems Biomedical Sciences, School of Medicine, Jinan University, Guangzhou 510632, China"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "W. Lai"
    },
    {
      "name": "C. Li"
    },
    {
      "name": "Q. Deng"
    },
    {
      "name": "Y. Zhu"
    },
    {
      "name": "C. Liu"
    },
    {
      "name": "Z. Li"
    },
    {
      "affs": [
        0
      ],
      "name": "O. J. Luo"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4wbzkw56fcm0c.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.24.753940",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.753940v1.full",
  "id": "4wbzkw56fcm0c",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.753940v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7214719236",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.753940v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4wbzkw56fcm0c.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:15Z",
      "native_id": "10.64898/2026.09.24.753940",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.24.753940v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "DECIPHER integrates disentangled representation learning and prototype-based cell-type deconvolution across molecular modalities",
  "title_text": "DECIPHER integrates disentangled representation learning and prototype-based cell-type deconvolution across molecular modalities",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:26Z",
  "url": "https://research.draconitic.com/paper/4wbzkw56fcm0c",
  "venue": "bioRxiv",
  "versions": []
}