{
  "abstract": "We present RabbitCD-HIT, a scalable distributed high-sensitivity greedy incremental clustering tool for ultra-large protein sequence datasets. It fully exploits cluster resources to enable efficient billion-scale clustering. RabbitCD-HIT clustered the March 10, 2026 NCBI nr snapshot (1.02 billion sequences; 487 GB FASTA) at 90\\% identity within 5 hours on 64 nodes; the resulting representatives and cluster assignments are released as a public database resource. On a 256-core server, RabbitCD-HIT achieved a 2.1$\\times$--6.6$\\times$ speedup over CD-HIT with identical results under matched settings. Our approach addresses performance bottlenecks of traditional greedy incremental algorithms and provides an effective solution for large-scale protein sequence clustering.",
  "abstract_shown": true,
  "affiliations": [
    "Shandong University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "name": "Y. Gao"
    },
    {
      "name": "G. Ma"
    },
    {
      "name": "Z. Yin"
    },
    {
      "name": "L. Yan"
    },
    {
      "name": "Y. Yang"
    },
    {
      "name": "T. Zhang"
    },
    {
      "name": "T. Zhao"
    },
    {
      "affs": [
        0
      ],
      "name": "Z. Liu"
    },
    {
      "name": "X. Duan"
    },
    {
      "name": "B. Niu"
    },
    {
      "name": "B. Schmibt"
    },
    {
      "affs": [
        0
      ],
      "name": "W. Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/51evdt6f9qwq2.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.05.764756",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764756v1.full",
  "id": "51evdt6f9qwq2",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764756v1",
  "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/10.64898/2026.11.05.764756v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/51evdt6f9qwq2.ris",
  "sources": [
    {
      "first_seen": "2026-11-10T00:23:31Z",
      "native_id": "10.64898/2026.11.05.764756",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764756v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "RabbitCD-HIT: Distributed High-Sensitivity Greedy Incremental Clustering for Billion-Scale Protein Sequences in Hours",
  "title_text": "RabbitCD-HIT: Distributed High-Sensitivity Greedy Incremental Clustering for Billion-Scale Protein Sequences in Hours",
  "type": "preprint",
  "updated_at": "2026-11-10T00:23:31Z",
  "url": "https://research.draconitic.com/paper/51evdt6f9qwq2",
  "venue": "bioRxiv",
  "versions": []
}