{
  "release": {
    "date": "2023-08-22",
    "id": "85",
    "name": "VOGDB release 85",
    "data_source": "NCBI Refseq release 85",
    "url": "https://fileshare.csb.univie.ac.at/vog/vog85",
    "license": "All data published are licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)",
    "authors": "Lovro Trgovec-Greif, Hans-Joerg Hellinger, Jean Mainguy, Alexander Pfundner, Dmitrij Frishman, Michael Kiening, Nicole Webster, Patrick Laffy, Thomas Rattei",
    "contact": "Thomas Rattei, Centre for Microbiology and Environmental Systems Science, University of Vienna, Austria, thomas.rattei@univie.ac.at",
    "number_proteins": 301035,
    "number_genomes": 6462
  },
  "groups": [
    {
      "name": "vog",
      "description": "Virus orthologous groups (built from bidirectional sequence similarities)",
      "number": 22426,
      "summary": "Number of VOG: 22426 (Virus orthologous groups)"
    }
  ],
  "files": [
    {
      "name": "vog.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.annotations.tsv.gz",
      "description": "Tab separated file of groups and their consensus functional annotations (preferrably from Swissprot annotations, if not available then the annotations from RefSeq were used). Columns: GroupName|ProteinCount|SpeciesCount|FunctionalCategory|ConsensusFunctionalDescription",
      "md5sum": "39e68abf7d3d846a65edef1292dab540",
      "bytes": 160483,
      "url_label": "vog.annotations.tsv.gz (Funcational annotations of groups): 160,483 bytes, MD5 checksum 39e68abf7d3d846a65edef1292dab540"
    },
    {
      "name": "vog.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "10a31f94c99e217808abab4e4a458b2a",
      "bytes": 31674180,
      "url_label": "vog.faa.tar.gz (Protein sequences of groups): 31,674,180 bytes, MD5 checksum 10a31f94c99e217808abab4e4a458b2a"
    },
    {
      "name": "vog.genes.all.fa.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.genes.all.fa.gz",
      "description": "FASTA formatted file of all gene sequences from the genomes in vog.species.list. Same IDs as in the protein file are used. For polyprotein genes the partial gene sequences of the peptides as well as the complete gene sequences of the polyprotein are contained.",
      "md5sum": "a207f964fc13bfbf764face71ee7ae69",
      "bytes": 69056687,
      "url_label": "vog.genes.all.fa.gz (Gene sequences of all genomes): 69,056,687 bytes, MD5 checksum a207f964fc13bfbf764face71ee7ae69"
    },
    {
      "name": "vog.hmm.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.hmm.tar.gz",
      "description": "Compressed archive of the HMMER3 compatible Hidden Markov Models obtained from the multiple sequence alignments for each vogdb group.",
      "md5sum": "1c9ec63791a59cb7e8fb1c49e1af2777",
      "bytes": 302520139,
      "url_label": "vog.hmm.tar.gz (Hidden Markov Models of groups): 302,520,139 bytes, MD5 checksum 1c9ec63791a59cb7e8fb1c49e1af2777"
    },
    {
      "name": "vog.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.lca.tsv.gz",
      "description": "Tab separated file of VOGs and the taxonomic lineage of the last common aencestor (LCA) of member genomes. Genomes with unclassified taxonomic lineages have not been used for LCA determination, which can result in VOG without lca (if all proteins of a VOG are from unclassified lineages). The numbers of genomes per VOG and LCA, as well as the total numbers of genomes in the LCA are given. Columns: GroupName|GenomesInGroupAndLCA|GenomesTotalInLCA|LastCommonAncestor_TaxonName|LastCommonAncestor_TaxonID",
      "md5sum": "dd9b4f02e1ec2272fda15396f3706442",
      "bytes": 100712,
      "url_label": "vog.lca.tsv.gz (Last common aencestors of groups): 100,712 bytes, MD5 checksum dd9b4f02e1ec2272fda15396f3706442"
    },
    {
      "name": "vog.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.members.tsv.gz",
      "description": "Tab separated file of VOGs and the comma separated lists of their member protein ids. Columns: GroupName|ProteinCount|SpeciesCount|FunctionalCategory|ProteinIDs",
      "md5sum": "0ebf9ceaf1a8d3ae40c87d9e9799f6d2",
      "bytes": 1454219,
      "url_label": "vog.members.tsv.gz (Member protein ids of groups): 1,454,219 bytes, MD5 checksum 0ebf9ceaf1a8d3ae40c87d9e9799f6d2"
    },
    {
      "name": "vog.proteins.all.fa.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.proteins.all.fa.gz",
      "description": "FASTA formatted file of all proteins from the genomes in vog.species.list. Protein IDs encode the taxonomy id of the genome and the RefSeq protein id. For peptides from polyproteins also the corresponding protein id of the polyprotein (CDS) is given.",
      "md5sum": "adac4fc7eb888a5210bad67998f4d09c",
      "bytes": 43641461,
      "url_label": "vog.proteins.all.fa.gz (Protein sequences of all genomes): 43,641,461 bytes, MD5 checksum adac4fc7eb888a5210bad67998f4d09c"
    },
    {
      "name": "vog.raw_algs.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.raw_algs.tar.gz",
      "description": "Compressed archive of multiple sequence alignments for each VOGDB group.",
      "md5sum": "e2a1c909b315fe46052d0a52ca5a46f4",
      "bytes": 32560783,
      "url_label": "vog.raw_algs.tar.gz (Multiple sequence alignments of groups): 32,560,783 bytes, MD5 checksum e2a1c909b315fe46052d0a52ca5a46f4"
    },
    {
      "name": "vog.species.list",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.species.list",
      "description": "Tab separated file of virus genomes used for VOG construction. Columns: species name|taxon id|phage/nonphage|source|source version",
      "md5sum": "cde84b0d6464008711e401070d0e0587",
      "bytes": 381766,
      "url_label": "vog.species.list (Virus genomes used for VOG construction): 381,766 bytes, MD5 checksum cde84b0d6464008711e401070d0e0587"
    },
    {
      "name": "vog.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog.virusonly.tsv.gz",
      "description": "Tab separated file of VOGs and their specificic occurrence in virus genomes. For this purpose the homology of all member proteins to cellular genomes from eggNOG 4.5 have been determined with three different stringencies: High stringency: blastp e-Value <=1e-04 and hits in maximal 2 cellular genomes; Medium stringency: blastp e-Value <=1e-10 and hits in maximal 3 cellular genomes; Low stringency: blastp e-Value <=1e-15 and hits in maximal 4 cellular genomes; The column Only_in_viruses has been set true if members matched not more than the maximal number of genomes at the e-Value threshold for each stringency level. Columns: GroupName|Only in viruses (high stringency)|Only in viruses (medium stringency)|Only in viruses (low stringency) 1=True; 0=False. This file is useful to extract virus-specific markers from all VOGs, based on your preferred level of stringency.",
      "md5sum": "51bbc4f99e9ae01f3a6eb29ed30eb033",
      "bytes": 56295,
      "url_label": "vog.virusonly.tsv.gz (Specificity if groups to Viruses): 56,295 bytes, MD5 checksum 51bbc4f99e9ae01f3a6eb29ed30eb033"
    },
    {
      "name": "vog_functional_categories.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog85/vog_functional_categories.txt",
      "description": "Text file listing the lettercodes of functional categories. These consist of X (unused in NCBI COG functional categories), followed by a lower case character indicating the functional category.",
      "md5sum": "91da9fb2ea00ce7ffb3248a072847a62",
      "bytes": 264,
      "url_label": "vog_functional_categories.txt (Lettercodes of functional categories): 264 bytes, MD5 checksum 91da9fb2ea00ce7ffb3248a072847a62"
    }
  ]
}