{
  "abstract": "Oxford Nanopore direct-cDNA sequencing enables full-length transcriptome profiling without PCR amplification, but recurrent chimeric artifacts introduced during reverse transcription and library preparation can compromise isoform reconstruction and gene-fusion analysis. These include foldback inversions, aberrant primer configurations, internal adapter concatemers, and homopolymer-mediated template-switching events. Existing preprocessing strategies primarily address primer-based orientation and adapter detection, leaving several direct-cDNA-specific artifact classes unresolved and often discarding reads that still contain usable transcript sequence. We developed DirectClean, an artifact-aware preprocessing and read-rescue framework integrating strand orientation, artifact removal, and junction-level splitting of recoverable chimeric reads. Benchmarking across four direct-cDNA datasets showed consistently higher read and base retention with DirectClean than with Pychopper. In VCaP, DirectClean retained 65.2% of reads compared with 57.6% for Pychopper, supported additional transcripts, and reduced the chimeric read rate from 30.9% in raw data to 16.9%. Semi-synthetic validation demonstrated accurate rescue of adapter-associated and A/T-rich chimeric reads, and matched real-data analyses showed no enrichment of novel transcript models in split-derived reads relative to matched untouched reads. DirectClean provides a reproducible, openly available framework for artifact-aware preprocessing of direct-cDNA transcriptomes and improves the reliability of downstream isoform and fusion analyses.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Urology, Northwestern University Feinberg School of Medicine , 303 E Superior St, Chicago, IL 60611 ,",
    "Robert H. Lurie Comprehensive Cancer Center, Northwestern University Feinberg School of Medicine , 303 E Superior St, Chicago, IL 60611 ,"
  ],
  "article_type": "brief report",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Qingxiang Guo",
      "orcid": "0000-0002-3694-3428"
    },
    {
      "affs": [
        0
      ],
      "name": "Yangyang Li",
      "orcid": "0000-0001-8224-1067"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Rendong Yang",
      "orcid": "0000-0002-9512-2240"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/60ekch1j8gs80.bib",
  "cited_by": 0,
  "doi": "10.1093/nargab/lqag132",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13722937/?tool=EBI",
  "id": "60ekch1j8gs80",
  "issns": [
    "2631-9268"
  ],
  "landing_url": "https://academic.oup.com/nargab/article/doi/10.1093/nargab/lqag132/9005802",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "AcademicSubjects/SCI00030"
    ],
    [
      "heading",
      "AcademicSubjects/SCI00980"
    ],
    [
      "heading",
      "AcademicSubjects/SCI01060"
    ],
    [
      "heading",
      "AcademicSubjects/SCI01140"
    ],
    [
      "heading",
      "AcademicSubjects/SCI01180"
    ],
    [
      "heading",
      "Editor's Choice"
    ],
    [
      "heading",
      "High Throughput Sequencing Methods"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://academic.oup.com/nargab/article-pdf/8/4/lqag132/72647515/lqag132.pdf",
  "pmcid": "PMC13722937",
  "pmid": "42966957",
  "published": "2026-10-31",
  "publisher": "Oxford University Press (OUP)",
  "ris": "https://research.draconitic.com/paper/60ekch1j8gs80.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:21:27Z",
      "native_id": "10.1093/nargab/lqag132",
      "source": "crossref",
      "url": "https://academic.oup.com/nargab/article/doi/10.1093/nargab/lqag132/9005802"
    },
    {
      "first_seen": "2026-11-02T03:21:51Z",
      "native_id": "PMC:PMC13722937",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13722937"
    },
    {
      "first_seen": "2026-11-04T12:21:38Z",
      "native_id": "PMC13722937",
      "source": "pmc",
      "url": "https://doi.org/10.1093/nargab/lqag132"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "issn:2631-9268",
      "subfield": "bioinformatics"
    }
  ],
  "title": "DirectClean: artifact-aware preprocessing and read rescue for Oxford Nanopore direct-cDNA transcriptome sequencing",
  "title_text": "DirectClean: artifact-aware preprocessing and read rescue for Oxford Nanopore direct-cDNA transcriptome sequencing",
  "type": "peer-reviewed",
  "updated_at": "2026-11-04T12:21:38Z",
  "url": "https://research.draconitic.com/paper/60ekch1j8gs80",
  "venue": "NAR Genomics and Bioinformatics",
  "versions": []
}