{
  "release": {
    "date": "2026-04-05",
    "id": "234",
    "name": "VOGDB release 234",
    "data_source": "NCBI Refseq release 234",
    "url": "https://fileshare.csb.univie.ac.at/vog/vog234",
    "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": 715490,
    "number_genomes": 15375
  },
  "groups": [
    {
      "name": "vfam",
      "description": "Virus protein families (built from vogs by HMM-HMM clustering)",
      "number": 39776,
      "summary": "Number of VFAM: 39776 (Virus protein families)"
    },
    {
      "name": "vog",
      "description": "Virus orthologous groups (built from bidirectional sequence similarities)",
      "number": 48605,
      "summary": "Number of VOG: 48605 (Virus orthologous groups)"
    },
    {
      "name": "vfold",
      "description": "Virus protein structural folds (built from vfams by clustering of predicted 3D structures of representative proteins)",
      "number": 33135,
      "summary": "Number of VFOLD: 33135 (Virus protein structural folds)"
    }
  ],
  "files": [
    {
      "name": "vog.raw_algs.alistat.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "2b1b0489580596b81dd7e7ef08bb0165",
      "bytes": 3268283,
      "url_label": "vog.raw_algs.alistat.txt (Statistics of multiple alignments): 3,268,283 bytes, MD5 checksum 2b1b0489580596b81dd7e7ef08bb0165"
    },
    {
      "name": "vog.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "f565c2a22efce43e34736cacd002d502",
      "bytes": 370631,
      "url_label": "vog.annotations.tsv.gz (Funcational annotations of groups): 370,631 bytes, MD5 checksum f565c2a22efce43e34736cacd002d502"
    },
    {
      "name": "vfam.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "b7713e33155ccfe728f7ba92839803b4",
      "bytes": 4528104,
      "url_label": "vfam.members.tsv.gz (Member protein ids of groups): 4,528,104 bytes, MD5 checksum b7713e33155ccfe728f7ba92839803b4"
    },
    {
      "name": "vfam.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "84fd9b10595fbcb3bfa74156c7fcb477",
      "bytes": 104819,
      "url_label": "vfam.virusonly.tsv.gz (Specificity if groups to Viruses): 104,819 bytes, MD5 checksum 84fd9b10595fbcb3bfa74156c7fcb477"
    },
    {
      "name": "vfam.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "10307a214a66c2b4ed092f4ca806378b",
      "bytes": 497240,
      "url_label": "vfam.lca.tsv.gz (Last common aencestors of groups): 497,240 bytes, MD5 checksum 10307a214a66c2b4ed092f4ca806378b"
    },
    {
      "name": "vog.hmm.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "223d72ed8cd8e5f966b23c16c5f25641",
      "bytes": 455121855,
      "url_label": "vog.hmm.tar.gz (Hidden Markov Models of groups): 455,121,855 bytes, MD5 checksum 223d72ed8cd8e5f966b23c16c5f25641"
    },
    {
      "name": "vfam.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "b090bf532b771ab225242a404827af16",
      "bytes": 294527,
      "url_label": "vfam.annotations.tsv.gz (Funcational annotations of groups): 294,527 bytes, MD5 checksum b090bf532b771ab225242a404827af16"
    },
    {
      "name": "vog.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vog.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "07af77d916f7d0ad85902418b69bc3e0",
      "bytes": 61850606,
      "url_label": "vog.faa.tar.gz (Protein sequences of groups): 61,850,606 bytes, MD5 checksum 07af77d916f7d0ad85902418b69bc3e0"
    },
    {
      "name": "vogdb.host.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "db3fe76efd019b4980ffe1da31b590b5",
      "bytes": 474175,
      "url_label": "vogdb.host.txt (Host information and classification for genomes): 474,175 bytes, MD5 checksum db3fe76efd019b4980ffe1da31b590b5"
    },
    {
      "name": "vfold.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vfold.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "ee11501baead71126e0632f2d9481b09",
      "bytes": 60231702,
      "url_label": "vfold.faa.tar.gz (Protein sequences of groups): 60,231,702 bytes, MD5 checksum ee11501baead71126e0632f2d9481b09"
    },
    {
      "name": "vfam.raw_algs.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vfam.raw_algs.tar.gz",
      "description": "Compressed archive of multiple sequence alignments for each VOGDB group.",
      "md5sum": "13fe0af64b19d7ec9a472301e317c685",
      "bytes": 53614182,
      "url_label": "vfam.raw_algs.tar.gz (Multiple sequence alignments of groups): 53,614,182 bytes, MD5 checksum 13fe0af64b19d7ec9a472301e317c685"
    },
    {
      "name": "vog.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "ade0ee66d81818431d09e4e6b47efbb3",
      "bytes": 4600511,
      "url_label": "vog.members.tsv.gz (Member protein ids of groups): 4,600,511 bytes, MD5 checksum ade0ee66d81818431d09e4e6b47efbb3"
    },
    {
      "name": "vfold.members.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "35bf0abad8598081e18867dc4d69a78b",
      "bytes": 4486189,
      "url_label": "vfold.members.tsv.gz (Member protein ids of groups): 4,486,189 bytes, MD5 checksum 35bf0abad8598081e18867dc4d69a78b"
    },
    {
      "name": "vfam.hmm.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "957278e2919e99df7a30f01701b9d454",
      "bytes": 369989880,
      "url_label": "vfam.hmm.tar.gz (Hidden Markov Models of groups): 369,989,880 bytes, MD5 checksum 957278e2919e99df7a30f01701b9d454"
    },
    {
      "name": "vfold.annotations.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "903415806333d3b88ebfe08c1fadc38b",
      "bytes": 243163,
      "url_label": "vfold.annotations.tsv.gz (Funcational annotations of groups): 243,163 bytes, MD5 checksum 903415806333d3b88ebfe08c1fadc38b"
    },
    {
      "name": "vfam.representatives.colabfold_predictions.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vfam.representatives.colabfold_predictions.tar.gz",
      "description": "Colabfold predictions of protein structures, represented by best ranked PDB and score files.",
      "md5sum": "4a0e33d499e4afe20ebd87aa23ba56e0",
      "bytes": 5039012334,
      "url_label": "vfam.representatives.colabfold_predictions.tar.gz (Protein structure predictions): 5,039,012,334 bytes, MD5 checksum 4a0e33d499e4afe20ebd87aa23ba56e0"
    },
    {
      "name": "vogdb.proteins.all.fa.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "18e59f8c11c3051f3523a01fc183575e",
      "bytes": 105862961,
      "url_label": "vogdb.proteins.all.fa.gz (Protein sequences of all genomes): 105,862,961 bytes, MD5 checksum 18e59f8c11c3051f3523a01fc183575e"
    },
    {
      "name": "vogdb.genes.all.fa.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "323a1bb2649925aa4e396f26b7da7a3f",
      "bytes": 170331744,
      "url_label": "vogdb.genes.all.fa.gz (Gene sequences of all genomes): 170,331,744 bytes, MD5 checksum 323a1bb2649925aa4e396f26b7da7a3f"
    },
    {
      "name": "vfam.raw_algs.alistat.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "a75ac83a979d7c43fdbfe2313184e07e",
      "bytes": 2718578,
      "url_label": "vfam.raw_algs.alistat.txt (Statistics of multiple alignments): 2,718,578 bytes, MD5 checksum a75ac83a979d7c43fdbfe2313184e07e"
    },
    {
      "name": "vfam.representatives.colabfold_mean_plddt.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vfam.representatives.colabfold_mean_plddt.txt",
      "description": "Mean pLDDT values for colabfold predictions of protein structures.",
      "md5sum": "85eebde06ddaff3f1378ade092c496e4",
      "bytes": 635376,
      "url_label": "vfam.representatives.colabfold_mean_plddt.txt (Mean pLDDT values of protein structure predictions): 635,376 bytes, MD5 checksum 85eebde06ddaff3f1378ade092c496e4"
    },
    {
      "name": "vog.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "76a8cd85eca073dcb25ff871036b5eb8",
      "bytes": 126157,
      "url_label": "vog.virusonly.tsv.gz (Specificity if groups to Viruses): 126,157 bytes, MD5 checksum 76a8cd85eca073dcb25ff871036b5eb8"
    },
    {
      "name": "vog.raw_algs.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vog.raw_algs.tar.gz",
      "description": "Compressed archive of multiple sequence alignments for each VOGDB group.",
      "md5sum": "62821e83b7597611354dcd74fcf205e3",
      "bytes": 53412286,
      "url_label": "vog.raw_algs.tar.gz (Multiple sequence alignments of groups): 53,412,286 bytes, MD5 checksum 62821e83b7597611354dcd74fcf205e3"
    },
    {
      "name": "vfold.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "1c5ffe6944d34f415c67474a84881f71",
      "bytes": 412291,
      "url_label": "vfold.lca.tsv.gz (Last common aencestors of groups): 412,291 bytes, MD5 checksum 1c5ffe6944d34f415c67474a84881f71"
    },
    {
      "name": "vogdb.functional_categories.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "6b816cc49c17d0095da91bad4e7552fa",
      "bytes": 308,
      "url_label": "vogdb.functional_categories.txt (Lettercodes of functional categories): 308 bytes, MD5 checksum 6b816cc49c17d0095da91bad4e7552fa"
    },
    {
      "name": "vfold.virusonly.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "14fc309cf96eea8b0c8b89dedcee23ba",
      "bytes": 86788,
      "url_label": "vfold.virusonly.tsv.gz (Specificity if groups to Viruses): 86,788 bytes, MD5 checksum 14fc309cf96eea8b0c8b89dedcee23ba"
    },
    {
      "name": "vog.lca.tsv.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/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": "c514540736876d48652130c795db2858",
      "bytes": 614139,
      "url_label": "vog.lca.tsv.gz (Last common aencestors of groups): 614,139 bytes, MD5 checksum c514540736876d48652130c795db2858"
    },
    {
      "name": "vogdb.species.txt",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vogdb.species.txt",
      "description": "Tab separated file of virus genomes used for VOG construction. Columns: species name|taxon id|source|source version",
      "md5sum": "5159318ce8353b41fa8c28a20a5e52d5",
      "bytes": 799590,
      "url_label": "vogdb.species.txt (Virus genomes used for VOG construction): 799,590 bytes, MD5 checksum 5159318ce8353b41fa8c28a20a5e52d5"
    },
    {
      "name": "vogdb.taxonomy.krona.html",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vogdb.taxonomy.krona.html",
      "description": "Interactive chart of virus genome taxonomies.",
      "md5sum": "a94e77047774ca55f4e36cc7cf5b46bf",
      "bytes": 6827733,
      "url_label": "vogdb.taxonomy.krona.html (Distribution of virus genome taxonomies): 6,827,733 bytes, MD5 checksum a94e77047774ca55f4e36cc7cf5b46bf"
    },
    {
      "name": "vfam.faa.tar.gz",
      "url": "https://fileshare.csb.univie.ac.at/vog/vog234/vfam.faa.tar.gz",
      "description": "Compressed archive of FASTA formatted files of the proteins per vogdb group.",
      "md5sum": "08e557885dad321d5f45054c9af0779d",
      "bytes": 61338977,
      "url_label": "vfam.faa.tar.gz (Protein sequences of groups): 61,338,977 bytes, MD5 checksum 08e557885dad321d5f45054c9af0779d"
    }
  ]
}