{
  "abstract": "Bisulfite sequencing (BS-seq) measures cytosine methylation on the DNA at single-base resolution, but converts unmethylated cytosines to thymines, disrupting conventional strand complementarity and reducing sequence complexity. These pose a fundamental challenge to efficient sequence comparison and indexing tasks. Although k-mer hashing is foundational to bioinformatics for enabling such high-throughput operations, generic algorithms for string hashing are poorly equipped to handle the reduced-complexity alphabet and sequence ambiguity created by this conversion. We therefore require fast k-mer hashing that directly recognizes bisulfite-compatible sequence states. Here, we present biHash, a rolling hash algorithm tailored for bisulfite-sequenced data. Using context-specific dinucleotide encodings, biHash maps designated bisulfite-compatible sequence variants to the same hash value while retaining context-specific specificity. When hashing adjacent k-mers, biHash performs ~13 times faster than generic string hashing algorithms.",
  "abstract_shown": true,
  "affiliations": [
    "The University of British Columbia"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "j. wong"
    },
    {
      "name": "I. Birol"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3pm405ayxvr32.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.19.760264",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.19.760264v1.full",
  "id": "3pm405ayxvr32",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.19.760264v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1702|Algorithms and Data Compression"
    ]
  ],
  "openalex": "W7223448080",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.19.760264v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3pm405ayxvr32.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:32Z",
      "native_id": "10.64898/2026.10.19.760264",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.19.760264v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "biHash: bisulfite-aware recursive nucleotide hashing",
  "title_text": "biHash: bisulfite-aware recursive nucleotide hashing",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:32Z",
  "url": "https://research.draconitic.com/paper/3pm405ayxvr32",
  "venue": "bioRxiv",
  "versions": []
}