{ "bcoid": "GLY_000252", "title": "Mouse Gene Ontology (GO)", "description": "The Mouse Gene Ontology (GO) dataset contains mouse [taxid:10090] Gene Ontology Id and name, categories ...", "filename": "mouse_protein_go_annotation.csv", "filetype": "csv", "categories": { "species": [ "Mus musculus" ], "molecule": [ "Protein" ], "tag": [ "Gene Ontology (Go)" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q8BH24-1...", "Tm9sf4..." ], [ "Q8BH24-1...", "Tm9sf4..." ] ], "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" } ], [ "Q8BH24-1", "Tm9sf4", "GO_0005769", "early endosome", "cellular_component", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0005794", "Golgi apparatus", "cellular_component", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0007155", "cell adhesion", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_2000010", "positive regulation of protein localization to cell surface", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0001666", "response to hypoxia", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0006909", "phagocytosis", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0072657", "protein localization to membrane", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0070072", "vacuolar proton-transporting V-type ATPase complex assembly", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0051453", "regulation of intracellular pH", "biological_process", "", "" ], [ "Q8BH24-1", "Tm9sf4", "GO_0070863", "positive regulation of protein exit from endoplasmic reticulum", "biological_process", "", "" ], [ "Q8BH27-1", "Megf9", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q8BH27-1", "Megf9", "GO_0005604", "basement membrane", "cellular_component", "", "" ], [ "Q8BH27-1", "Megf9", "GO_0007411", "axon guidance", "biological_process", "", "" ], [ "Q8BH27-1", "Megf9", "GO_0005201", "extracellular matrix structural constituent", "molecular_function", "", "" ], [ "Q8BH26-1", "Lyset", "GO_0000139", "Golgi membrane", "cellular_component", "", "" ], [ "Q8BH26-1", "Lyset", "GO_0005794", "Golgi apparatus", "cellular_component", "", "" ], [ "Q8BH26-1", "Lyset", "GO_0007040", "lysosome organization", "biological_process", "", "" ], [ "Q8BH26-1", "Lyset", "GO_0060627", "regulation of vesicle-mediated transport", "biological_process", "", "" ], [ "Q8BH26-1", "Lyset", "GO_0007041", "lysosomal transport", "biological_process", "", "" ], [ "Q8BH26-1", "Lyset", "GO_0031985", "Golgi cisterna", "cellular_component", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0001701", "in utero embryonic development", "biological_process", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0004175", "endopeptidase activity", "molecular_function", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0004222", "metalloendopeptidase activity", "molecular_function", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0005615", "extracellular space", "cellular_component", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0016485", "protein processing", "biological_process", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0030198", "extracellular matrix organization", "biological_process", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0031012", "extracellular matrix", "cellular_component", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0008233", "peptidase activity", "molecular_function", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0010573", "vascular endothelial growth factor production", "biological_process", "", "" ], [ "E9Q287-1", "Adamts3", "GO_0032964", "collagen biosynthetic process", "biological_process", "", "" ], [ "E9Q287-1", "Adamts3", "GO_1900748", "positive regulation of vascular endothelial growth factor signaling pathway", "biological_process", "", "" ], [ "Q922G0-1", "Slc25a36", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0005654", "nucleoplasm", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0005794", "Golgi apparatus", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0005829", "cytosol", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0015031", "protein transport", "biological_process", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0032588", "trans-Golgi network membrane", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0043231", "intracellular membrane-bounded organelle", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0048471", "perinuclear region of cytoplasm", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0030276", "clathrin binding", "molecular_function", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0030121", "AP-1 adaptor complex", "cellular_component", "", "" ], [ "Q80WT5-1", "Aftph", "GO_0046907", "intracellular transport", "biological_process", "", "" ], [ "Q80T32-1", "Adgrd1", "GO_0004930", "G protein-coupled receptor activity", "molecular_function", "", "" ], [ "Q80T32-1", "Adgrd1", "GO_0007166", "cell surface receptor signaling pathway", "biological_process", "", "" ], [ "Q80T32-1", "Adgrd1", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q80T32-1", "Adgrd1", "GO_0022008", "neurogenesis", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0060323", "head morphogenesis", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0043249", "erythrocyte maturation", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0001701", "in utero embryonic development", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0005739", "mitochondrion", "cellular_component", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0005886", "plasma membrane", "cellular_component", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0006839", "mitochondrial transport", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0031966", "mitochondrial membrane", "cellular_component", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0015232", "heme transmembrane transporter activity", "molecular_function", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0030218", "erythrocyte differentiation", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0035264", "multicellular organism growth", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0001568", "blood vessel development", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0048536", "spleen development", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0015886", "heme transport", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0020037", "heme binding", "molecular_function", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0042733", "embryonic digit morphogenesis", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0048704", "embryonic skeletal system morphogenesis", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0035108", "limb morphogenesis", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0046620", "regulation of organ growth", "biological_process", "", "" ], [ "B2RXV4-1", "Flvcr1", "GO_0097037", "heme export", "biological_process", "", "" ], [ "P62492-1", "Rab11a", "GO_0003924", "GTPase activity", "molecular_function", "", "" ], [ "P62492-1", "Rab11a", "GO_0005525", "GTP binding", "molecular_function", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0016202", "regulation of striated muscle tissue development", "biological_process", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0051310", "metaphase plate congression", "biological_process", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0000278", "mitotic cell cycle", "biological_process", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0000922", "spindle pole", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005635", "nuclear envelope", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005654", "nucleoplasm", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005813", "centrosome", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005819", "spindle", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0005829", "cytosol", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0007059", "chromosome segregation", "biological_process", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0008017", "microtubule binding", "molecular_function", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0015031", "protein transport", "biological_process", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0031965", "nuclear membrane", "cellular_component", "", "" ], [ "E9Q3P4-1", "Cenpf", "GO_0042803", "protein homodimerization activity", "molecular_function", "", "" ] ] }, "readme": "Name\n - Mouse Gene Ontology (GO)\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2019-09-06T14:06:38.979310\n\nModified on\n - 2022-09-26T09:04:47.900986\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]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Mouse Gene Ontology (GO) dataset contains mouse [taxid:10090] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. 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-mus-musculus.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-mus-musculus.nt\n Output Subdomain\n Name: mouse_protein_go_annotation.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_go_annotation.csv\n Name: mouse_protein_go_annotation.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/mouse_protein_go_annotation.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"20612\"\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: \"20682\"\n Name: \"go_term_id\"\n Description: \"The Gene Ontology (GO) term unique alphanumeric identifier\"\n Unique Values: \"19332\"\n Name: \"go_term_label\"\n Description: \"The Gene Ontology (GO) name that is a word or string of words\"\n Unique Values: \"19332\"\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-2.2.1/reviewed/mouse_protein_go_annotation.csv" }