{ "bcoid": "GLY_000793", "title": "Yeast UniProtKB Xref Pfam", "description": "The Yeast UniProtKB Xref Pfam contains yeast [taxid:559292] UniProtKB canonical accessions cross-referenced ...", "filename": "yeast_protein_xref_pfam.csv", "filetype": "csv", "categories": { "species": [ "Saccharomyces cerevisiae S288C" ], "molecule": [ "Protein" ], "tag": [ "Pfam cross-references" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P30619-1...", "protein_xref..." ], [ "P39972-1...", "protein_xref..." ] ], "headers": [ "uniprotkb_ca...", "xref_key..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_label" } ], [ "P30619-1", "protein_xref_pfam", "PF00995", "Sec1" ], [ "P39972-1", "protein_xref_pfam", "PF11603", "Sir1" ], [ "P39970-1", "protein_xref_pfam", "PF00170", "bZIP_1" ], [ "P39976-1", "protein_xref_pfam", "PF01565", "FAD_binding_4" ], [ "P39976-1", "protein_xref_pfam", "PF02913", "FAD-oxidase_C" ], [ "P39979-1", "protein_xref_pfam", "PF00583", "Acetyltransf_1" ], [ "Q07959-1", "protein_xref_pfam", "PF03006", "HlyIII" ], [ "P0CX69-1", "protein_xref_pfam", "PF01021", "TYA" ], [ "P25379-1", "protein_xref_pfam", "PF00291", "PALP" ], [ "P25378-1", "protein_xref_pfam", "PF00071", "Ras" ], [ "P17121-1", "protein_xref_pfam", "PF00620", "RhoGAP" ], [ "P25374-1", "protein_xref_pfam", "PF00266", "Aminotran_5" ], [ "P17123-1", "protein_xref_pfam", "PF05032", "Spo12" ], [ "P17122-1", "protein_xref_pfam", "PF19225", "Spo16" ], [ "P25371-1", "protein_xref_pfam", "PF00005", "ABC_tran" ], [ "P25371-1", "protein_xref_pfam", "PF01061", "ABC2_membrane" ], [ "P25371-1", "protein_xref_pfam", "PF19055", "ABC2_membrane_7" ], [ "P25373-1", "protein_xref_pfam", "PF00462", "Glutaredoxin" ], [ "P25372-1", "protein_xref_pfam", "PF00085", "Thioredoxin" ], [ "Q03049-1", "protein_xref_pfam", "PF01370", "Epimerase" ], [ "Q06567-1", "protein_xref_pfam", "PF03109", "ABC1" ], [ "Q06563-1", "protein_xref_pfam", "PF04117", "Mpv17_PMP22" ], [ "Q00539-1", "protein_xref_pfam", "PF00076", "RRM_1" ], [ "Q07748-1", "protein_xref_pfam", "PF09084", "NMT1" ], [ "Q07963-1", "protein_xref_pfam", "PF02207", "zf-UBR" ], [ "Q07963-1", "protein_xref_pfam", "PF18995", "PRT6_C" ], [ "Q00246-1", "protein_xref_pfam", "PF00071", "Ras" ], [ "Q00245-1", "protein_xref_pfam", "PF00071", "Ras" ], [ "P0CX61-1", "protein_xref_pfam", "PF01021", "TYA" ], [ "P40422-1", "protein_xref_pfam", "PF03604", "DNA_RNApol_7kD" ], [ "P0CX62-1", "protein_xref_pfam", "PF01021", "TYA" ], [ "P0CX64-1", "protein_xref_pfam", "PF00665", "rve" ], [ "P0CX64-1", "protein_xref_pfam", "PF01021", "TYA" ], [ "P0CX64-1", "protein_xref_pfam", "PF07727", "RVT_2" ], [ "P0CX67-1", "protein_xref_pfam", "PF01021", "TYA" ], [ "P18494-1", "protein_xref_pfam", "PF00320", "GATA" ], [ "P18496-1", "protein_xref_pfam", "PF05176", "ATP-synt_10" ], [ "Q03441-1", "protein_xref_pfam", "PF02582", "DUF155" ], [ "Q08748-1", "protein_xref_pfam", "PF00168", "C2" ], [ "Q08749-1", "protein_xref_pfam", "PF05328", "CybS" ], [ "Q08746-1", "protein_xref_pfam", "PF04939", "RRS1" ], [ "Q08747-1", "protein_xref_pfam", "PF08766", "DEK_C" ], [ "Q08747-1", "protein_xref_pfam", "PF02201", "SWIB" ], [ "Q08745-1", "protein_xref_pfam", "PF03501", "S10_plectin" ], [ "Q08742-1", "protein_xref_pfam", "PF00581", "Rhodanese" ], [ "Q08743-1", "protein_xref_pfam", "PF04117", "Mpv17_PMP22" ], [ "P32915-1", "protein_xref_pfam", "PF00344", "SecY" ], [ "P32915-1", "protein_xref_pfam", "PF10559", "Plug_translocon" ], [ "P32914-1", "protein_xref_pfam", "PF06093", "Spt4" ], [ "P32917-1", "protein_xref_pfam", "PF11610", "Ste5" ], [ "P32917-1", "protein_xref_pfam", "PF12194", "Ste5_C" ], [ "P32916-1", "protein_xref_pfam", "PF00448", "SRP54" ], [ "P32916-1", "protein_xref_pfam", "PF02881", "SRP54_N" ], [ "P32916-1", "protein_xref_pfam", "PF09201", "SRX" ], [ "P32911-1", "protein_xref_pfam", "PF01253", "SUI1" ], [ "P32910-1", "protein_xref_pfam", "PF05158", "RNA_pol_Rpc34" ], [ "P32913-1", "protein_xref_pfam", "PF00787", "PX" ], [ "P32912-1", "protein_xref_pfam", "PF00787", "PX" ], [ "Q04438-1", "protein_xref_pfam", "PF17325", "SPG4" ], [ "Q04439-1", "protein_xref_pfam", "PF00018", "SH3_1" ], [ "Q04439-1", "protein_xref_pfam", "PF06017", "Myosin_TH1" ], [ "Q04439-1", "protein_xref_pfam", "PF00063", "Myosin_head" ], [ "Q04430-1", "protein_xref_pfam", "PF03630", "Fumble" ], [ "Q04431-1", "protein_xref_pfam", "PF17097", "Kre28" ], [ "Q04432-1", "protein_xref_pfam", "PF01965", "DJ-1_PfpI" ], [ "Q04433-1", "protein_xref_pfam", "PF17357", "FIT1_2" ], [ "Q04437-1", "protein_xref_pfam", "PF02735", "Ku" ], [ "Q04437-1", "protein_xref_pfam", "PF03730", "Ku_C" ], [ "Q04437-1", "protein_xref_pfam", "PF03731", "Ku_N" ], [ "P00546-1", "protein_xref_pfam", "PF00069", "Pkinase" ], [ "P04385-1", "protein_xref_pfam", "PF08544", "GHMP_kinases_C" ], [ "P04385-1", "protein_xref_pfam", "PF00288", "GHMP_kinases_N" ], [ "P04385-1", "protein_xref_pfam", "PF10509", "GalKase_gal_bdg" ], [ "P04387-1", "protein_xref_pfam", "PF01408", "GFO_IDH_MocA" ], [ "P04386-1", "protein_xref_pfam", "PF00172", "Zn_clus" ], [ "P04386-1", "protein_xref_pfam", "PF03902", "Gal4_dimer" ], [ "P04386-1", "protein_xref_pfam", "PF04082", "Fungal_trans" ], [ "Q08299-1", "protein_xref_pfam", "PF07690", "MFS_1" ], [ "Q08562-1", "protein_xref_pfam", "PF00176", "SNF2-rel_dom" ], [ "Q08562-1", "protein_xref_pfam", "PF00271", "Helicase_C" ], [ "P25377-1", "protein_xref_pfam", "PF00107", "ADH_zinc_N" ], [ "P25377-1", "protein_xref_pfam", "PF08240", "ADH_N" ], [ "P25376-1", "protein_xref_pfam", "PF00324", "AA_permease" ], [ "P32474-1", "protein_xref_pfam", "PF00085", "Thioredoxin" ] ] }, "readme": "Name\n - Yeast UniProtKB Xref Pfam\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2022-08-31T13:42:50.669379\n\nModified on\n - 2023-09-11T20:30:18\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Yeast UniProtKB Xref Pfam contains yeast [taxid:559292] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. \n - Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. \n\nDescription Domain\n Keywords\n - protein family\n - Pfam\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. \n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: uniprot-proteome-saccharomyces-cerevisiae.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-saccharomyces-cerevisiae.nt\n Output Subdomain\n Name: yeast_protein_xref_pfam.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_pfam.csv\n Name: yeast_protein_xref_pfam.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_pfam.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"4951\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"3294\"\n Name: \"xref_label\"\n Description: \"Label/Name associated with x-ref\"\n Unique Values: \"3294\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/yeast_protein_xref_pfam.csv" }