database:
  name: RVDB_PROT
  version: '32.0'
  release_date: 2026-07
  description: Protein-derived clustered and annotated viral database from U-RVDB
  website: https://rvdb-prot.pasteur.fr
  author: Thomas Bigot / Bioinformatics Hub @ Institut Pasteur
  contact: thomas.bigot@pasteur.fr
upstream:
  name: U-RVDB
  version: '32.0'
  website: https://rvdb.dbi.udel.edu
  fasta_url: https://rvdb.dbi.udel.edu/download/U-RVDBvCurrent.fasta.gz
tools:
  cd-hit: CD-HIT 4.8.1
  hmmer: HMMER 3.3.1
  blast: BLAST+ 2.10.0
  mafft: MAFFT 7.526
  silix: SILIX 1.2.11
  golden: GOLDEN unknown
  python: Python 3.11.11
files:
  protein_sequences:
    filename: U-RVDBv32.0-prot.fasta
    description: Unclustered protein sequences (translated from nucleotide RVDB)
    format: FASTA
    compression: xz
    sequence_count: 41321264
    residue_count: 42914089778
    size_compressed: 399153264
    size_uncompressed: 47233505889
    md5_checksum_uncompressed: aaf70d0b8b960aaf3ed6f7dd3efee881
    md5_checksum_compressed: 44ff19b8b58e02bf6b4093a65e549260
  clustered_protein_sequences:
    filename: U-RVDBv32.0-prot_unique.fasta
    description: Clustered protein sequences (100% identity threshold)
    format: FASTA
    compression: xz
    sequence_count: 783103
    residue_count: 291573049
    size_compressed: 72961192
    size_uncompressed: 361459904
    md5_checksum_uncompressed: 75bebc137ad9658d350312d656c1edbb
    md5_checksum_compressed: 5bb367c39dc71776cc5a91637f9d7a68
  hmm_profiles:
    filename: U-RVDBv32.0-prot.hmm
    description: HMM profiles built from clustered protein families
    format: HMMER3
    compression: xz
    profile_count: 13679
    size_compressed: 266598820
    size_uncompressed: 2715363745
    md5_checksum_uncompressed: 7e6d213a9a55739af1cf1d498e58647c
    md5_checksum_compressed: d21c42648369ccaf30188633536d08e9
  annotations_sqlite:
    filename: U-RVDBv32.0-prot-hmm.sqlite
    description: Annotations linked to HMM models (taxonomy, function, keywords)
    format: SQLite
    compression: xz
    record_count: 13679
    size_compressed: 6283684
    size_uncompressed: 24489984
    md5_checksum_uncompressed: a95a0d3ab084f7a49e15170d777ed262
    md5_checksum_compressed: 4179c579c38fb2d2c5c0af967bcface7
  annotations_text:
    filename: U-RVDBv32.0-prot-hmm-txt.tar
    description: Text-based annotations extracted from SQLite DB
    format: Tarball
    compression: xz
    file_count_in_tar: 13681
    size_compressed: 5027616
    md5_checksum_compressed: c093ba5da41cc4cc7c0451563e595ffe
disclaimer: This database is distributed for academic and research use only.It should
  NOT be considered a regulatory standard or official reference.All users must validate
  data quality before any application.
build_info:
  prefix: U-RVDBv32.0
  build_timestamp: '2026-07-03T15:05:55.756060'
  build_date: '2026-07-03 15:05:55'