{
  "abstract": "Standard short-read RNA-seq analysis pipelines quantify expression over annotated exons and disregard signals mapped to introns, thereby missing independently transcribed intronic RNAs. Existing strategies depend on annotation, biologically crude whole-intron quantification, or subjective, low-throughput manual genome-browser inspection. We present MOCHI (Mapping of Cryptic Hidden Intronic Transcripts), a framework that couples reference-independent, k-mer-based signal discovery with reference-guided genomic interpretation and a custom multi-step filtering module to systematically curate potential independent intronic transcription units from strand-specific short-read RNA-seq data. On two simulated datasets, MOCHI recovered annotated sense-intronic long non-coding RNAs removed from the reference and distinguished them from intronic signal confounders. Across paired ribosomal RNA-depleted and poly(A)-selected libraries from ten cancer cell lines, MOCHI curated candidates whose host introns are strongly enriched for a transcription-initiation signal. Candidate expression is largely uncoupled from host-gene exons, and their genomic features resemble those of annotated long non-coding RNAs. In ten matched cohorts from The Cancer Genome Atlas, candidates were detected in tumor samples, and a subset was associated with overall survival after adjustment for age and host-gene expression. Consequently, MOCHI extends the transcriptomic landscape that can be mined from existing short-read RNA-seq data and provides a curated resource of candidate intronic transcripts for downstream analyses.",
  "abstract_shown": true,
  "affiliations": [
    "Izmir Institute of Technology"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "D. C. Gurer-Er"
    },
    {
      "name": "G. Karakulah"
    },
    {
      "name": "D. Gautheret"
    },
    {
      "affs": [
        0
      ],
      "name": "B. Akgul"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/amgjjndrdax2p.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.05.764473",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764473v1.full",
  "id": "amgjjndrdax2p",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764473v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764473v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/amgjjndrdax2p.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T00:21:26Z",
      "native_id": "10.64898/2026.11.05.764473",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764473v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "MOCHI enables systematic identification of candidate independent intronic transcriptional signals from short-read RNA-seq data",
  "title_text": "MOCHI enables systematic identification of candidate independent intronic transcriptional signals from short-read RNA-seq data",
  "type": "preprint",
  "updated_at": "2026-11-08T00:21:10Z",
  "url": "https://research.draconitic.com/paper/amgjjndrdax2p",
  "venue": "bioRxiv",
  "versions": []
}