{
  "abstract": "Background/Objectives: Cell-free DNA (cfDNA) fragmentomics from low-coverage whole-genome sequencing (lcWGS) is a promising approach for non-invasive cancer detection. However, most existing methods summarize millions of cfDNA fragments into handcrafted sample-level features before classification, potentially discarding informative patterns carried by individual molecules. We aimed to develop and benchmark a framework that learns directly from fragment-level signals. Methods: We developed FragMIL, a fragment-token multiple-instance learning framework that represents each cfDNA molecule as a learnable token integrating end-motif, genomic-position, and fragment-length information, and aggregates thousands of fragment tokens into a patient-level cancer score. FragMIL was evaluated on 934 samples from three public lcWGS cohorts (pan-cancer, lung cancer, and hepatocellular carcinoma) using five repeated subject-level splits, a 288-configuration design-space benchmark, and comparison with four established fragmentomic approaches (coverage, DELFI, end motif, and fragment size). Results: FragMIL achieved the highest mean areas under the receiver operating characteristic curve (AUROCs) in every cohort, with 0.963 ± 0.009, 0.802 ± 0.009, and 0.910 ± 0.015 in the DELFI/Cristiano 2019, LUCAS/Mathios 2021, and Jiang 2015 cohorts, respectively. End-motif encoding provided the strongest standalone discriminative signal, whereas the optimal fragment pool was cohort-dependent, with open chromatin region fragments performing best for pan-cancer detection and tumor-enriched fragments for disease-specific cohorts. Performance was retained across cancer stages and cancer types. Conclusions: Preserving molecule-level fragmentomic information improves cancer detection, supporting fragment-token learning as a promising framework for next-generation cfDNA fragmentomics.",
  "abstract_shown": true,
  "affiliations": [
    "International Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan",
    "Department of Pathology and Laboratory Medicine, Shin Kong Wu Ho-Su Memorial Hospital, Taipei 111, Taiwan",
    "AIBioMed Lab, Taipei Medical University, Taipei 110, Taiwan",
    "Department of Internal Medicine, Taipei Medical University Hospital, Taipei Medical University, Taipei 110, Taiwan",
    "Taipei Cancer Center, Taipei Medical University Hospital, Taipei Medical University, Taipei 110, Taiwan",
    "Department of Pathology, 103 Military Hospital, Hanoi 100000, Vietnam",
    "Institute of Molecular and Genomic Medicine, National Health Research Institutes, Miaoli 350, Taiwan",
    "In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan",
    "Translational Imaging Research Center, Taipei Medical University Hospital, Taipei 110, Taiwan",
    "Graduate Institute of Clinical Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Tien-Dung Bui"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Yung-Feng Lin",
      "orcid": "0000-0002-6961-3687"
    },
    {
      "affs": [
        2,
        5
      ],
      "name": "Mai-Hanh Nguyen",
      "orcid": "0000-0002-4945-1334"
    },
    {
      "affs": [
        6
      ],
      "name": "Shih-Feng Tsai"
    },
    {
      "affs": [
        2,
        7,
        8
      ],
      "name": "Nguyen-Quoc-Khanh Le",
      "orcid": "0000-0003-4896-7926"
    },
    {
      "affs": [
        1,
        9
      ],
      "name": "Teh-Ying Chou"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/89jvbp4c345e5.bib",
  "cited_by": 0,
  "doi": "10.3390/cancers18203389",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13702332/?tool=EBI",
  "id": "89jvbp4c345e5",
  "issns": [
    "2072-6694"
  ],
  "landing_url": "https://www.mdpi.com/2072-6694/18/20/3389",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1306|Cancer Genomics and Diagnostics"
    ]
  ],
  "openalex": "W7223006095",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13702332/pdf/?tool=EBI",
  "pmcid": "PMC13702332",
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/89jvbp4c345e5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:58Z",
      "native_id": "10.3390/cancers18203389",
      "source": "crossref",
      "url": "https://www.mdpi.com/2072-6694/18/20/3389"
    },
    {
      "first_seen": "2026-10-30T12:21:47Z",
      "native_id": "PMC:PMC13702332",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13702332"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:1306|Cancer Genomics and Diagnostics",
      "subfield": "oncology"
    }
  ],
  "title": "FragMIL: A Fragment-Token Multiple-Instance Learning Framework for Cancer Detection from Cell-Free DNA Fragmentomics",
  "title_text": "FragMIL: A Fragment-Token Multiple-Instance Learning Framework for Cancer Detection from Cell-Free DNA Fragmentomics",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:21:47Z",
  "url": "https://research.draconitic.com/paper/89jvbp4c345e5",
  "venue": "Cancers",
  "versions": []
}