{
  "release": {
    "date": "2025-08-02",
    "id": "231",
    "name": "VOGDB release 231",
    "data_source": "NCBI Refseq release 231",
    "url": "https://fileshare.csb.univie.ac.at/vog/vog231",
    "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": 692869,
    "number_genomes": 15019
  },
  "groups": [
    {
      "name": "vfam",
      "description": "Virus protein families (built from vogs by HMM-HMM clustering)",
      "number": 39624,
      "summary": "Number of VFAM: 39624 (Virus protein families)"
    },
    {
      "name": "vfold",
      "description": "Virus protein structural folds (built from vfams by clustering of predicted 3D structures of representative proteins)",
      "number": 33073,
      "summary": "Number of VFOLD: 33073 (Virus protein structural folds)"
    },
    {
      "name": "vog",
      "description": "Virus orthologous groups (built from bidirectional sequence similarities)",
      "number": 48445,
      "summary": "Number of VOG: 48445 (Virus orthologous groups)"
    }
  ],
  "files": [
    {
      "name": "vfam.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.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": "14b86f1fdecf0020d4fe3e58e642729c",
      "bytes": 285209,
      "url_label": "vfam.annotations.tsv.gz (Funcational annotations of groups): 285,209 bytes, MD5 checksum 14b86f1fdecf0020d4fe3e58e642729c"
    },
    {
      "name": "vfam.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "bb87fdc7336fd25394cdf5f8ae48569b",
      "bytes": 62814659,
      "url_label": "vfam.faa.tar.gz (Protein sequences of groups): 62,814,659 bytes, MD5 checksum bb87fdc7336fd25394cdf5f8ae48569b"
    },
    {
      "name": "vfam.hmm.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.hmm.tar.gz",
      "description": "Compressed archive of the HMMER3 compatible Hidden Markov Models obtained from the multiple sequence alignments for each vogdb group.",
      "md5sum": "20a0b53e33705ee99b1880c5d8bfa8c9",
      "bytes": 458770010,
      "url_label": "vfam.hmm.tar.gz (Hidden Markov Models of groups): 458,770,010 bytes, MD5 checksum 20a0b53e33705ee99b1880c5d8bfa8c9"
    },
    {
      "name": "vfam.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.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": "bb9637cb855483ae5e2f72fa0e431060",
      "bytes": 440289,
      "url_label": "vfam.lca.tsv.gz (Last common aencestors of groups): 440,289 bytes, MD5 checksum bb9637cb855483ae5e2f72fa0e431060"
    },
    {
      "name": "vfam.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.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": "d12112fc08e1e825b8dc8e3905aa932f",
      "bytes": 4274455,
      "url_label": "vfam.members.tsv.gz (Member protein ids of groups): 4,274,455 bytes, MD5 checksum d12112fc08e1e825b8dc8e3905aa932f"
    },
    {
      "name": "vfam.raw_algs.alistat.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.raw_algs.alistat.txt",
      "description": "Statistics of multiple alignments according to minimum reporting standard for multiple sequence alignments (https://doi.org/10.1093/nargab/lqaa024).",
      "md5sum": "fd6affa47fe288eabf8960b8b89e8315",
      "bytes": 3019766,
      "url_label": "vfam.raw_algs.alistat.txt (Statistics of multiple alignments): 3,019,766 bytes, MD5 checksum fd6affa47fe288eabf8960b8b89e8315"
    },
    {
      "name": "vfam.raw_algs.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.raw_algs.tar.gz",
      "description": "Compressed archive of multiple sequence alignments for each VOGDB group.",
      "md5sum": "35c3686b5039509dd389ea341b7c900b",
      "bytes": 60363345,
      "url_label": "vfam.raw_algs.tar.gz (Multiple sequence alignments of groups): 60,363,345 bytes, MD5 checksum 35c3686b5039509dd389ea341b7c900b"
    },
    {
      "name": "vfam.representatives.colabfold_mean_plddt.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.representatives.colabfold_mean_plddt.txt",
      "description": "Mean pLDDT values for colabfold predictions of protein structures.",
      "md5sum": "19180ee0e246dca42c19925c9056187b",
      "bytes": 4464,
      "url_label": "vfam.representatives.colabfold_mean_plddt.txt (Mean pLDDT values of protein structure predictions): 4,464 bytes, MD5 checksum 19180ee0e246dca42c19925c9056187b"
    },
    {
      "name": "vfam.representatives.colabfold_predictions.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.representatives.colabfold_predictions.tar.gz",
      "description": "Colabfold predictions of protein structures, represented by best ranked PDB and score files.",
      "md5sum": "146ccdd206866702611b2c5cd2935425",
      "bytes": 2126108097,
      "url_label": "vfam.representatives.colabfold_predictions.tar.gz (Protein structure predictions): 2,126,108,097 bytes, MD5 checksum 146ccdd206866702611b2c5cd2935425"
    },
    {
      "name": "vfam.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfam.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": "ce489c1e37ac2b5d2d73935a57aae2cd",
      "bytes": 104371,
      "url_label": "vfam.virusonly.tsv.gz (Specificity if groups to Viruses): 104,371 bytes, MD5 checksum ce489c1e37ac2b5d2d73935a57aae2cd"
    },
    {
      "name": "vfold.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfold.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": "bc27d40a32da74afb2f9b04567075e06",
      "bytes": 238815,
      "url_label": "vfold.annotations.tsv.gz (Funcational annotations of groups): 238,815 bytes, MD5 checksum bc27d40a32da74afb2f9b04567075e06"
    },
    {
      "name": "vfold.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfold.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "61e92f71f2c43f7a82a7a6ea5b9f9e7f",
      "bytes": 61610425,
      "url_label": "vfold.faa.tar.gz (Protein sequences of groups): 61,610,425 bytes, MD5 checksum 61e92f71f2c43f7a82a7a6ea5b9f9e7f"
    },
    {
      "name": "vfold.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfold.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": "6e80c7eea702ba0de480386ddd730e12",
      "bytes": 366579,
      "url_label": "vfold.lca.tsv.gz (Last common aencestors of groups): 366,579 bytes, MD5 checksum 6e80c7eea702ba0de480386ddd730e12"
    },
    {
      "name": "vfold.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfold.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": "4088a8a5b5bf51dab9e9d6021f956cd5",
      "bytes": 4257052,
      "url_label": "vfold.members.tsv.gz (Member protein ids of groups): 4,257,052 bytes, MD5 checksum 4088a8a5b5bf51dab9e9d6021f956cd5"
    },
    {
      "name": "vfold.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vfold.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": "d663f282013dd7c6cf033ce3a88d2ca2",
      "bytes": 86217,
      "url_label": "vfold.virusonly.tsv.gz (Specificity if groups to Viruses): 86,217 bytes, MD5 checksum d663f282013dd7c6cf033ce3a88d2ca2"
    },
    {
      "name": "vog.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/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": "59906fd4a9a762fa61ae38630c594179",
      "bytes": 365718,
      "url_label": "vog.annotations.tsv.gz (Funcational annotations of groups): 365,718 bytes, MD5 checksum 59906fd4a9a762fa61ae38630c594179"
    },
    {
      "name": "vogdb.functional_categories.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vogdb.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": "vogdb.functional_categories.txt (Lettercodes of functional categories): 264 bytes, MD5 checksum 91da9fb2ea00ce7ffb3248a072847a62"
    },
    {
      "name": "vogdb.genes.all.fa.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vogdb.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": "02a38eb461966ca9a4759a8998a467ef",
      "bytes": 165819829,
      "url_label": "vogdb.genes.all.fa.gz (Gene sequences of all genomes): 165,819,829 bytes, MD5 checksum 02a38eb461966ca9a4759a8998a467ef"
    },
    {
      "name": "vogdb.host.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vogdb.host.txt",
      "description": "Tab separated file of host information and classification for virus taxa. Columns: taxon id|phage/nonphage|host|superkingdom of host.",
      "md5sum": "404ad698f4b06b1363eedec16632a42c",
      "bytes": 477720,
      "url_label": "vogdb.host.txt (Host information and classification for genomes): 477,720 bytes, MD5 checksum 404ad698f4b06b1363eedec16632a42c"
    },
    {
      "name": "vogdb.proteins.all.fa.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vogdb.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": "cb2c7184a79f996f14291fb54da07154",
      "bytes": 103020524,
      "url_label": "vogdb.proteins.all.fa.gz (Protein sequences of all genomes): 103,020,524 bytes, MD5 checksum cb2c7184a79f996f14291fb54da07154"
    },
    {
      "name": "vogdb.species.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vogdb.species.txt",
      "description": "Tab separated file of virus genomes used for VOG construction. Columns: species name|taxon id|source|source version",
      "md5sum": "790a3d899d775b1bbd1a5ff480f4266d",
      "bytes": 780590,
      "url_label": "vogdb.species.txt (Virus genomes used for VOG construction): 780,590 bytes, MD5 checksum 790a3d899d775b1bbd1a5ff480f4266d"
    },
    {
      "name": "vogdb.taxonomy.krona.html",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vogdb.taxonomy.krona.html",
      "description": "Interactive chart of virus genome taxonomies.",
      "md5sum": "3b1f0d95e96e61f21d86b08d5f9d9003",
      "bytes": 5856617,
      "url_label": "vogdb.taxonomy.krona.html (Distribution of virus genome taxonomies): 5,856,617 bytes, MD5 checksum 3b1f0d95e96e61f21d86b08d5f9d9003"
    },
    {
      "name": "vog.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vog.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "e3d224c48e7af5997f80106113f265e4",
      "bytes": 63725685,
      "url_label": "vog.faa.tar.gz (Protein sequences of groups): 63,725,685 bytes, MD5 checksum e3d224c48e7af5997f80106113f265e4"
    },
    {
      "name": "vog.hmm.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/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": "a640847eaf39cd36d5a2174cf9f2dfd2",
      "bytes": 563596609,
      "url_label": "vog.hmm.tar.gz (Hidden Markov Models of groups): 563,596,609 bytes, MD5 checksum a640847eaf39cd36d5a2174cf9f2dfd2"
    },
    {
      "name": "vog.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/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": "6d2e0c950d1d8038adda324994fac6e0",
      "bytes": 561634,
      "url_label": "vog.lca.tsv.gz (Last common aencestors of groups): 561,634 bytes, MD5 checksum 6d2e0c950d1d8038adda324994fac6e0"
    },
    {
      "name": "vog.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/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": "4db8bc0d55c2f996d57179a0c0f55ff7",
      "bytes": 4422329,
      "url_label": "vog.members.tsv.gz (Member protein ids of groups): 4,422,329 bytes, MD5 checksum 4db8bc0d55c2f996d57179a0c0f55ff7"
    },
    {
      "name": "vog.raw_algs.alistat.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vog.raw_algs.alistat.txt",
      "description": "Statistics of multiple alignments according to minimum reporting standard for multiple sequence alignments (https://doi.org/10.1093/nargab/lqaa024).",
      "md5sum": "b994638ee8d53176011c1024fd97a441",
      "bytes": 3633840,
      "url_label": "vog.raw_algs.alistat.txt (Statistics of multiple alignments): 3,633,840 bytes, MD5 checksum b994638ee8d53176011c1024fd97a441"
    },
    {
      "name": "vog.raw_algs.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/vog.raw_algs.tar.gz",
      "description": "Compressed archive of multiple sequence alignments for each VOGDB group.",
      "md5sum": "d6a1a6a336cd4c4c9f1214e71973a12e",
      "bytes": 59432260,
      "url_label": "vog.raw_algs.tar.gz (Multiple sequence alignments of groups): 59,432,260 bytes, MD5 checksum d6a1a6a336cd4c4c9f1214e71973a12e"
    },
    {
      "name": "vog.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog231/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": "1b694b5226968840310e1ddcd1310dc0",
      "bytes": 126249,
      "url_label": "vog.virusonly.tsv.gz (Specificity if groups to Viruses): 126,249 bytes, MD5 checksum 1b694b5226968840310e1ddcd1310dc0"
    }
  ]
}
