{
  "abstract": "Somatic variant discovery in tumors is crucial for clinical analysis, yet most existing methods are designed for short-read sequencing, with few developed specifically for long reads. Here we present Clair-Somatic (ClairS), a deep-learning-based somatic small-variant caller designed for long-read tumor-normal pairs. Trained on synthetic somatic variants with diverse coverages and variant allele fractions, ClairS accurately detects a wide range of somatic variants. Using the Nanopore Q20+ HCC1395-HCC1395BL dataset at 50/25× tumor/normal coverage, ClairS achieved F1 scores of 89.83% for single-nucleotide variations and 73.38% for indels; augmenting training with real cancer cell lines improved performance to 96.19% and 79.67%, respectively. Our findings indicate that improved read phasing enabled by long-read sequencing is key to accurate single-nucleotide variation detection, especially at low variant allele fractions. Through experiments across varied coverage, purity, contamination levels, multiple platforms and real cancer cell lines, we demonstrate that ClairS is a robust and reliable caller. ClairS is open source and available at https://github.com/HKU-BAL/ClairS .",
  "abstract_shown": true,
  "affiliations": [
    "School of Computing and Data Science, The University of Hong Kong, Hong Kong, China",
    "School of Computing and Data Science, The University of Hong Kong, Hong Kong, China. rbluo@cs.hku.hk"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Zhenxian Zheng",
      "orcid": "0000-0002-6546-2324"
    },
    {
      "affs": [
        0
      ],
      "name": "Lei Chen",
      "orcid": "0000-0002-9727-0714"
    },
    {
      "affs": [
        0
      ],
      "name": "Junhao Su",
      "orcid": "0000-0002-8560-3999"
    },
    {
      "affs": [
        0
      ],
      "name": "Xian Yu",
      "orcid": "0009-0004-1917-143X"
    },
    {
      "affs": [
        0
      ],
      "name": "Minggao He",
      "orcid": "0009-0008-0367-8534"
    },
    {
      "affs": [
        0
      ],
      "name": "Yan-Lam Lee",
      "orcid": "0000-0002-4518-9789"
    },
    {
      "affs": [
        0
      ],
      "name": "Tak‐Wah Lam",
      "orcid": "0000-0003-4676-8587"
    },
    {
      "affs": [
        1
      ],
      "name": "Ruibang Luo",
      "orcid": "0000-0001-9711-6533"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6sww43j39v9ee.bib",
  "cited_by": 31,
  "doi": "10.1038/s41592-026-03152-4",
  "fulltext_url": null,
  "id": "6sww43j39v9ee",
  "issns": [
    "1548-7091",
    "1548-7105"
  ],
  "landing_url": "https://doi.org/10.1038/s41592-026-03152-4",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Genomics and Phylogenetic Studies"
    ]
  ],
  "openalex": "W7166882478",
  "pdf_url": null,
  "pmcid": "PMC13441973",
  "pmid": "42387002",
  "published": "2026-07-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/6sww43j39v9ee.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T13:20:30Z",
      "native_id": "W7166882478",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41592-026-03152-4"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Genomics and Phylogenetic Studies",
      "subfield": "molecular-biology"
    }
  ],
  "title": "ClairS: a deep-learning method for long-read tumor–normal pair somatic small variant calling",
  "title_text": "ClairS: a deep-learning method for long-read tumor–normal pair somatic small variant calling",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:41Z",
  "url": "https://research.draconitic.com/paper/6sww43j39v9ee",
  "venue": "Nature Methods",
  "versions": []
}