{
  "abstract": "Automated protein function annotation remains challenging as sequence databases outpace curated labels and homology-based transfer fails for proteins lacking close relatives. We present GOlien, a scalable, composition-based method that annotates protein sequences using a Shannon-entropy k-mer model. Built from the CAFA3-based training split and evaluated on the held-out validation split, GOlien achieves micro-averaged of 0.7317 (Biological Process), 0.7610 (Cellular Component) and 0.8295 (Molecular Function). Our tool offers a practical, complementary alternative to existing pipelines and extending annotation coverage for proteins. Availability and Implementation: The command line tool to submit FASTA files and retrieve predicted GO term annotations with the corresponding documentation is available at: https://github.com/probalytiq/golien-tool",
  "abstract_shown": true,
  "affiliations": [
    "University of Debrecen, Faculty of Health Sciences, One Health Institute, Department of Bioinformatics"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "L. Laczko"
    },
    {
      "name": "D. Pek"
    },
    {
      "name": "B. L. Kovacs"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0erbx0ezss5h2.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.04.749510",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749510v1.full",
  "id": "0erbx0ezss5h2",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749510v1",
  "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|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7212224180",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749510v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0erbx0ezss5h2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:17Z",
      "native_id": "10.64898/2026.09.04.749510",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749510v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "GOlien tool: fast and scalable GO term annotation of proteins using a Shannon-entropy k-mer model",
  "title_text": "GOlien tool: fast and scalable GO term annotation of proteins using a Shannon-entropy k-mer model",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:17Z",
  "url": "https://research.draconitic.com/paper/0erbx0ezss5h2",
  "venue": "bioRxiv",
  "versions": []
}