{
  "abstract": "Microorganisms hold great promise for urgent global needs such as increasing sustainable agricultural production while reducing chemical fertilizer and pesticide use or providing novel classes of antimicrobials/therapeutics. Moving from analyzing microbiome composition to applying synthetic communities and studying their functions requires access to isolates and complete genome sequences. By spanning the frequent repeats, long-read sequencing can resolve complex prokaryotic genomes, yet error-prone short-read assemblies dominate. We here release the GenomeCompendium, a public database and interactive analysis tool for complete prokaryotic genomes (https://genome-compendium.com/). Using NCBI RefSeq (~47,000) and GenBank (~13,000) genomes, we integrated available metadata, GTDB taxonomy and computed features including repeat classes and gene content screening, intragenomic 16S rRNA sequence identity, and biosynthetic gene cluster co-occurrences. Evaluating repeat content and assembly complexity metrics, we identify taxonomic ranks dominated by difficult-to-assemble genomes and show that complex, repeat-rich genomes are more common than previously estimated. By mining metadata, our quality control flags 6.3% of RefSeq assemblies as potentially erroneous or incomplete. As valuable reference for data mining and to track taxonomic coverage, the GenomeCompendium links ~90 features across genomes, offers downloadable reports and -as unique features- pre-computed proteogenomics databases to improve genome annotations of RefSeq strains and the ability to analyze any uploaded prokaryotic genome.",
  "abstract_shown": true,
  "affiliations": [
    "Agroscope"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "name": "T. Totu"
    },
    {
      "name": "G. Jaques"
    },
    {
      "name": "B. Heiniger"
    },
    {
      "name": "T. Segessemann"
    },
    {
      "name": "M. Schmid"
    },
    {
      "name": "M. Bourqui"
    },
    {
      "name": "A. Wicki"
    },
    {
      "name": "J. E. Frey"
    },
    {
      "affs": [
        0
      ],
      "name": "C. H. Ahrens"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/536hn21cjg0b9.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.14.744864",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.08.14.744864v2.full",
  "id": "536hn21cjg0b9",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.08.14.744864v2",
  "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",
      "genomics"
    ],
    [
      "openalex",
      "1312|Genomics and Phylogenetic Studies"
    ]
  ],
  "openalex": "W7203781144",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.08.14.744864v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/536hn21cjg0b9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:52Z",
      "native_id": "10.64898/2026.08.14.744864",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.08.14.744864v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:genomics",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "GenomeCompendium: A database for the integrated analysis of repeats, assembly quality and functional content of complete prokaryotic genomes",
  "title_text": "GenomeCompendium: A database for the integrated analysis of repeats, assembly quality and functional content of complete prokaryotic genomes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:52Z",
  "url": "https://research.draconitic.com/paper/536hn21cjg0b9",
  "venue": "bioRxiv",
  "versions": []
}