{
  "abstract": "Circulating tumor DNA is often scarce in plasma, and regional methylation summaries can obscure informative differences between individual molecules. Here we present ctDNA-BERT, a Transformer that scores individual bisulfite reads without predefined differentially methylated regions by jointly encoding CpG methylation state, nucleotide context and the fragment 3' end. Xenografts provide molecule-level tumor supervision. The resulting frozen scorer supported tumor-fraction estimation in synthetic and patient-derived xenograft mixtures and enriched tumor-concordant methylation and chromatin-accessibility signals in independent hepatocellular carcinoma and stage III pan-cancer plasma without cohort-specific retraining. Features derived from selected reads discriminated stage I cancers from healthy controls in a retrospective cohort of 1,477 specimens, achieving an out-of-fold area under the receiver operating characteristic curve of 0.884. By separating molecular scoring from sample-level inference, ctDNA-BERT provides a reusable read-level scoring layer for cell-free DNA methylation analysis.",
  "abstract_shown": true,
  "affiliations": [
    "Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, 230031, P. R"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 18,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "X. Zhang"
    },
    {
      "name": "X. Sun"
    },
    {
      "name": "R. Wang"
    },
    {
      "name": "N. Zhao"
    },
    {
      "name": "F. Liu"
    },
    {
      "name": "X. Li"
    },
    {
      "name": "J. Huang"
    },
    {
      "name": "J. Sun"
    },
    {
      "name": "H. Li"
    },
    {
      "name": "S. Lou"
    },
    {
      "name": "H. Wang"
    },
    {
      "name": "H. Zhao"
    },
    {
      "name": "H. Shu"
    },
    {
      "name": "P. Zhen"
    },
    {
      "name": "H. Gu"
    },
    {
      "name": "J. Shi"
    },
    {
      "name": "T. Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "F. Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bhjsdgbhc1mgt.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.26.761533",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761533v1.full",
  "id": "bhjsdgbhc1mgt",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761533v1",
  "language": null,
  "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"
    ],
    [
      "openalex",
      "1306|Cancer Genomics and Diagnostics"
    ]
  ],
  "openalex": "W7223988885",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761533v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bhjsdgbhc1mgt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:51Z",
      "native_id": "10.64898/2026.10.26.761533",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.26.761533v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Xenograft supervision and joint methylation-fragment-end encoding define a reusable molecular scoring layer for cell-free tumor DNA",
  "title_text": "Xenograft supervision and joint methylation-fragment-end encoding define a reusable molecular scoring layer for cell-free tumor DNA",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:51Z",
  "url": "https://research.draconitic.com/paper/bhjsdgbhc1mgt",
  "venue": "bioRxiv",
  "versions": []
}