{ "bcoid": "GLY_000757", "title": "Yeast Gene Ontology (GO)", "description": "The Yeast Gene Ontology (GO) dataset contains yeast [taxid:559292] Gene Ontology Id and name, categories ...", "filename": "yeast_protein_go_annotation.csv", "filetype": "csv", "categories": { "species": [ "Saccharomyces cerevisiae S288C" ], "molecule": [ "Protein" ], "tag": [ "Gene Ontology (Go)" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P30619-1...", "SEC1..." ], [ "P30619-1...", "SEC1..." ] ], "headers": [ "uniprotkb_ca...", "gene_symbol..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_symbol" }, { "type": "string", "label": "go_term_id" }, { "type": "string", "label": "go_term_label" }, { "type": "string", "label": "go_term_category" }, { "type": "string", "label": "eco_id" }, { "type": "string", "label": "pmid" } ], [ "P30619-1", "SEC1", "GO_0005886", "plasma membrane", "cellular_component", "", "" ], [ "P30619-1", "SEC1", "GO_0006886", "intracellular protein transport", "biological_process", "", "" ], [ "P30619-1", "SEC1", "GO_0019905", "syntaxin binding", "molecular_function", "", "" ], [ "P30619-1", "SEC1", "GO_0071944", "cell periphery", "cellular_component", "", "" ], [ "P30619-1", "SEC1", "GO_0016192", "vesicle-mediated transport", "biological_process", "", "" ], [ "P30619-1", "SEC1", "GO_0031340", "positive regulation of vesicle fusion", "biological_process", "", "" ], [ "P30619-1", "SEC1", "GO_0000149", "SNARE binding", "molecular_function", "", "" ], [ "P30619-1", "SEC1", "GO_0006887", "exocytosis", "biological_process", "", "" ], [ "P30619-1", "SEC1", "GO_0006904", "vesicle docking involved in exocytosis", "biological_process", "", "" ], [ "P30619-1", "SEC1", "GO_0005934", "cellular bud tip", "cellular_component", "", "" ], [ "P30619-1", "SEC1", "GO_0005935", "cellular bud neck", "cellular_component", "", "" ], [ "P39970-1", "ACA1", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "P39970-1", "ACA1", "GO_0006357", "regulation of transcription by RNA polymerase II", "biological_process", "", "" ], [ "P39970-1", "ACA1", "GO_0045944", "positive regulation of transcription by RNA polymerase II", "biological_process", "", "" ], [ "P39970-1", "ACA1", "GO_0000978", "RNA polymerase II cis-regulatory region sequence-specific DNA binding", "molecular_function", "", "" ], [ "P39970-1", "ACA1", "GO_0000981", "DNA-binding transcription factor activity, RNA polymerase II-specific", "molecular_function", "", "" ], [ "P39970-1", "ACA1", "GO_0043565", "sequence-specific DNA binding", "molecular_function", "", "" ], [ "P39970-1", "ACA1", "GO_0001228", "DNA-binding transcription activator activity, RNA polymerase II-specific", "molecular_function", "", "" ], [ "P39976-1", "DLD3", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "P39976-1", "DLD3", "GO_0005739", "mitochondrion", "cellular_component", "", "" ], [ "P39976-1", "DLD3", "GO_0071949", "FAD binding", "molecular_function", "", "" ], [ "P39976-1", "DLD3", "GO_0004458", "D-lactate dehydrogenase (cytochrome) activity", "molecular_function", "", "" ], [ "P39976-1", "DLD3", "GO_0019249", "lactate biosynthetic process", "biological_process", "", "" ], [ "P39976-1", "DLD3", "GO_0030447", "filamentous growth", "biological_process", "", "" ], [ "P39976-1", "DLD3", "GO_0099615", "(D)-2-hydroxyglutarate-pyruvate transhydrogenase activity", "molecular_function", "", "" ], [ "P39977-1", "", "GO_0005783", "endoplasmic reticulum", "cellular_component", "", "" ], [ "P39975-1", "RMD6", "GO_0005777", "peroxisome", "cellular_component", "", "" ], [ "P39975-1", "RMD6", "GO_0051321", "meiotic cell cycle", "biological_process", "", "" ], [ "P39975-1", "RMD6", "GO_0030435", "sporulation resulting in formation of a cellular spore", "biological_process", "", "" ], [ "P39978-1", "", "GO_0005739", "mitochondrion", "cellular_component", "", "" ], [ "P39979-1", "HPA3", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "P39979-1", "HPA3", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "P39979-1", "HPA3", "GO_0004402", "histone acetyltransferase activity", "molecular_function", "", "" ], [ "P39979-1", "HPA3", "GO_0006473", "protein acetylation", "biological_process", "", "" ], [ "P39979-1", "HPA3", "GO_0046416", "D-amino acid metabolic process", "biological_process", "", "" ], [ "P39979-1", "HPA3", "GO_0008080", "N-acetyltransferase activity", "molecular_function", "", "" ], [ "P39979-1", "HPA3", "GO_0070458", "cellular detoxification of nitrogen compound", "biological_process", "", "" ], [ "P39979-1", "HPA3", "GO_0047812", "D-amino-acid N-acetyltransferase activity", "molecular_function", "", "" ], [ "Q07959-1", "IZH3", "GO_0005783", "endoplasmic reticulum", "cellular_component", "", "" ], [ "Q07959-1", "IZH3", "GO_0005789", "endoplasmic reticulum membrane", "cellular_component", "", "" ], [ "Q07959-1", "IZH3", "GO_0006882", "intracellular zinc ion homeostasis", "biological_process", "", "" ], [ "Q07959-1", "IZH3", "GO_0038023", "signaling receptor activity", "molecular_function", "", "" ], [ "P0CX69-1", "TY1A-MR2", "GO_0032197", "retrotransposition", "biological_process", "", "" ], [ "P0CX69-1", "TY1A-MR2", "GO_0003723", "RNA binding", "molecular_function", "", "" ], [ "P0CX69-1", "TY1A-MR2", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "P0CX69-1", "TY1A-MR2", "GO_0000943", "retrotransposon nucleocapsid", "cellular_component", "", "" ], [ "P25379-1", "CHA1", "GO_0005739", "mitochondrion", "cellular_component", "", "" ], [ "P25379-1", "CHA1", "GO_0030170", "pyridoxal phosphate binding", "molecular_function", "", "" ], [ "P25379-1", "CHA1", "GO_0042645", "mitochondrial nucleoid", "cellular_component", "", "" ], [ "P25379-1", "CHA1", "GO_0003941", "L-serine ammonia-lyase activity", "molecular_function", "", "" ], [ "P25379-1", "CHA1", "GO_0004794", "L-threonine ammonia-lyase activity", "molecular_function", "", "" ], [ "P25379-1", "CHA1", "GO_0006567", "threonine catabolic process", "biological_process", "", "" ], [ "P25379-1", "CHA1", "GO_0006565", "L-serine catabolic process", "biological_process", "", "" ], [ "P25379-1", "CHA1", "GO_0009097", "isoleucine biosynthetic process", "biological_process", "", "" ], [ "P25378-1", "RHB1", "GO_0003924", "GTPase activity", "molecular_function", "", "" ], [ "P25378-1", "RHB1", "GO_0005525", "GTP binding", "molecular_function", "", "" ], [ "P25378-1", "RHB1", "GO_0005829", "cytosol", "cellular_component", "", "" ], [ "P25378-1", "RHB1", "GO_0005886", "plasma membrane", "cellular_component", "", "" ], [ "P25378-1", "RHB1", "GO_0007264", "small GTPase mediated signal transduction", "biological_process", "", "" ], [ "P25378-1", "RHB1", "GO_0042147", "retrograde transport, endosome to Golgi", "biological_process", "", "" ], [ "P25378-1", "RHB1", "GO_0019003", "GDP binding", "molecular_function", "", "" ], [ "P17121-1", "SAC7", "GO_0005096", "GTPase activator activity", "molecular_function", "", "" ], [ "P17121-1", "SAC7", "GO_0005856", "cytoskeleton", "cellular_component", "", "" ], [ "P17121-1", "SAC7", "GO_0005938", "cell cortex", "cellular_component", "", "" ], [ "P17121-1", "SAC7", "GO_0007165", "signal transduction", "biological_process", "", "" ], [ "P17121-1", "SAC7", "GO_0032956", "regulation of actin cytoskeleton organization", "biological_process", "", "" ], [ "P17121-1", "SAC7", "GO_0035024", "negative regulation of Rho protein signal transduction", "biological_process", "", "" ], [ "P17121-1", "SAC7", "GO_0090038", "negative regulation of protein kinase C signaling", "biological_process", "", "" ], [ "P17121-1", "SAC7", "GO_0060237", "regulation of fungal-type cell wall organization", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0016226", "iron-sulfur cluster assembly", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0034227", "tRNA thio-modification", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "P25374-1", "NFS1", "GO_0005739", "mitochondrion", "cellular_component", "", "" ], [ "P25374-1", "NFS1", "GO_0005829", "cytosol", "cellular_component", "", "" ], [ "P25374-1", "NFS1", "GO_0030170", "pyridoxal phosphate binding", "molecular_function", "", "" ], [ "P25374-1", "NFS1", "GO_0046872", "metal ion binding", "molecular_function", "", "" ], [ "P25374-1", "NFS1", "GO_0006879", "intracellular iron ion homeostasis", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0002098", "tRNA wobble uridine modification", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0044571", "[2Fe-2S] cluster assembly", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0070903", "mitochondrial tRNA thio-modification", "biological_process", "", "" ], [ "P25374-1", "NFS1", "GO_0051536", "iron-sulfur cluster binding", "molecular_function", "", "" ], [ "P25374-1", "NFS1", "GO_0031071", "cysteine desulfurase activity", "molecular_function", "", "" ], [ "P25374-1", "NFS1", "GO_1990221", "L-cysteine desulfurase complex", "cellular_component", "", "" ], [ "P25374-1", "NFS1", "GO_1990229", "iron-sulfur cluster assembly complex", "cellular_component", "", "" ] ] }, "readme": "Name\n - Yeast Gene Ontology (GO)\n\nVersion\n - v-2.4.1\n\nCreated on\n - 2022-08-30T16:13:56.875825\n\nModified on\n - 2023-09-11T19:07:37\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], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@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 Gene Ontology (GO) dataset contains yeast [taxid:559292] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. \n\nDescription Domain\n Keywords\n - go id\n - go name\n - molecular function\n - biological process\n - cellular component\n - Gene Ontology (GO)\n\n Pipeline Steps\n - Step-1: The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. \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/2024_02_13/uniprot-proteome-saccharomyces-cerevisiae.nt\n Output Subdomain\n Name: yeast_protein_go_annotation.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/yeast_protein_go_annotation.csv\n Name: yeast_protein_go_annotation.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/yeast_protein_go_annotation.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"5731\"\n Name: \"gene_symbol\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene names/symbols are approved by the HUGO Gene Nomenclature Committee (HGNC)\"\n Unique Values: \"5178\"\n Name: \"go_term_id\"\n Description: \"The Gene Ontology (GO) term unique alphanumeric identifier\"\n Unique Values: \"5733\"\n Name: \"go_term_label\"\n Description: \"The Gene Ontology (GO) name that is a word or string of words\"\n Unique Values: \"5733\"\n Name: \"go_term_category\"\n Description: \"\"The Gene Ontology (GO) domain to which the term belongs. There are three ontology domain in GO - cellular component\"\n Unique Values: \"3\"\n Name: \"eco_id\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"1\"\n Name: \"pmid\"\n Description: \"NCBI PubMed database Identifier\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/yeast_protein_go_annotation.csv" }