{
  "abstract": "Proteomics is strengthening research in biology and the diversification of the model organisms studied is very promising for fully understanding the complexity of biological principles. However, the lack of protein sequence databases for many species is a major bottleneck. Existing computational solutions are usually incomplete and/or only usable by bioinformaticians. We have built an open-source, user-friendly pipeline, called Brownotate, which allows anyone to generate protein sequence databases for any species as long as sequencing information is available. The pipeline can extract already existing protein sequences, but also automatically annotate any genome assembly or assemble and annotate any DNA sequence dataset. By testing the pipeline with numerous sequencing and assembly datasets covering a large part of the phylogenetic tree, we show that Brownotate generates fragmented but good quality assemblies and good quality annotations when compared to reference data. By comparing the use of protein databases generated by Brownotate or downloaded from NCBI to interpret proteomic data, we show very comparable results. The Brownotate pipeline is, therefore, an important new addition to the proteomics toolbox.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Adrien Brown"
    },
    {
      "name": "Alexandre Burel"
    },
    {
      "name": "Sarah Cianférani"
    },
    {
      "name": "Christine Carapito"
    },
    {
      "name": "Fabrice Bertile"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0yv9ceac7gc1j.bib",
  "cited_by": 0,
  "doi": "10.1002/pmic.70094",
  "fulltext_url": null,
  "id": "0yv9ceac7gc1j",
  "issns": [
    "1615-9853",
    "1615-9861"
  ],
  "landing_url": "https://hal.science/hal-05771454v1",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.sdv"
    ],
    [
      "hal",
      "1.sdv.bbm"
    ],
    [
      "hal",
      "1.sdv.bibs"
    ],
    [
      "hal",
      "2.sdv.bbm.gtp"
    ],
    [
      "openalex",
      "1312|Genomics and Phylogenetic Studies"
    ]
  ],
  "openalex": "W7118872641",
  "pdf_url": "https://hal.science/hal-05771454/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": "Wiley-VCH Verlag",
  "ris": "https://research.draconitic.com/paper/0yv9ceac7gc1j.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:44Z",
      "native_id": "hal-05771454",
      "source": "hal",
      "url": "https://hal.science/hal-05771454v1"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "hal:2.sdv.bbm.gtp",
      "subfield": "proteomics-metabolomics"
    },
    {
      "field": "biology",
      "origin": "hal:1.sdv.bibs",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Brownotate, a Comprehensive Solution to Generate Protein Sequence Databases for Any Species",
  "title_text": "Brownotate, a Comprehensive Solution to Generate Protein Sequence Databases for Any Species",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:44Z",
  "url": "https://research.draconitic.com/paper/0yv9ceac7gc1j",
  "venue": "Proteomics",
  "versions": []
}