{
  "abstract": "Complex sequencing protocols encode technical information in read structure and require accurate, e[ff]icient preprocessing. We introduce seqproc, which compiles concise sequence-geometry descriptions into execution graphs. Across four single-cell RNA-sequencing protocols, seqproc has the lowest mean runtime at every tested thread count and uses substantially less memory than the next-fastest tool. It has the highest F1 agreement with conservative structural references on all three discriminative chemistries and ties both alternatives on the 10x length-filter control. By separating protocol description from execution, seqproc makes complex read transformations compact, reusable, and efficient.",
  "abstract_shown": true,
  "affiliations": [
    "University of Maryland"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "N. Cape"
    },
    {
      "name": "E. Fisher"
    },
    {
      "name": "D. Liu"
    },
    {
      "affs": [
        0
      ],
      "name": "R. Patro"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9pa6vf159tj0q.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.07.28.741211",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.07.28.741211v2.full",
  "id": "9pa6vf159tj0q",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.07.28.741211v2",
  "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",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7171641744",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.07.28.741211v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9pa6vf159tj0q.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:38Z",
      "native_id": "10.64898/2026.07.28.741211",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.07.28.741211v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "seqproc: An efficient, flexible, and concise tool for sequence geometry description and transformation",
  "title_text": "seqproc: An efficient, flexible, and concise tool for sequence geometry description and transformation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:38Z",
  "url": "https://research.draconitic.com/paper/9pa6vf159tj0q",
  "venue": "bioRxiv",
  "versions": []
}