{ "bcoid": "GLY_000223", "title": "Human Gene Ontology (GO)", "description": "The Human Gene Ontology (GO) dataset contains human [taxid:9606] Gene Ontology Id and name, categories ...", "filename": "human_protein_go_annotation.csv", "filetype": "csv", "categories": { "species": "Homo Sapiens", "molecule": "Protein", "tags": "Gene Ontology (Go)", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8TBF5-1...", "PIGX..." ], [ "Q8TBF5-1...", "PIGX..." ] ], "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" } ], [ "Q8TBF5-1", "PIGX", "GO_0016254", "preassembly of GPI anchor in ER membrane", "biological_process" ], [ "Q8TBF5-1", "PIGX", "GO_0016021", "integral component of membrane", "cellular_component" ], [ "Q8TBF5-1", "PIGX", "GO_0005789", "endoplasmic reticulum membrane", "cellular_component" ], [ "Q8TBF4-1", "ZCRB1", "GO_0003723", "RNA binding", "molecular_function" ], [ "Q8TBF4-1", "ZCRB1", "GO_0005654", "nucleoplasm", "cellular_component" ], [ "Q8TBF4-1", "ZCRB1", "GO_0008270", "zinc ion binding", "molecular_function" ], [ "Q8TBF4-1", "ZCRB1", "GO_0008380", "RNA splicing", "biological_process" ], [ "Q8TBF4-1", "ZCRB1", "GO_0000398", "mRNA splicing, via spliceosome", "biological_process" ], [ "Q8TBF4-1", "ZCRB1", "GO_0005689", "U12-type spliceosomal complex", "cellular_component" ], [ "O60507-1", "TPST1", "GO_0000139", "Golgi membrane", "cellular_component" ], [ "O60507-1", "TPST1", "GO_0005794", "Golgi apparatus", "cellular_component" ], [ "O60507-1", "TPST1", "GO_0006954", "inflammatory response", "biological_process" ], [ "O60507-1", "TPST1", "GO_0016020", "membrane", "cellular_component" ], [ "O60507-1", "TPST1", "GO_0030173", "integral component of Golgi membrane", "cellular_component" ], [ "O60507-1", "TPST1", "GO_0042803", "protein homodimerization activity", "molecular_function" ], [ "O60507-1", "TPST1", "GO_0050427", "3'-phosphoadenosine 5'-phosphosulfate metabolic process", "biological_process" ], [ "O60507-1", "TPST1", "GO_0006478", "peptidyl-tyrosine sulfation", "biological_process" ], [ "O60507-1", "TPST1", "GO_0008476", "protein-tyrosine sulfotransferase activity", "molecular_function" ], [ "Q9NQ79-1", "CRTAC1", "GO_0030426", "growth cone", "cellular_component" ], [ "Q9NQ79-1", "CRTAC1", "GO_0070062", "extracellular exosome", "cellular_component" ], [ "Q9NQ79-1", "CRTAC1", "GO_0005509", "calcium ion binding", "molecular_function" ], [ "Q9NQ79-1", "CRTAC1", "GO_0007413", "axonal fasciculation", "biological_process" ], [ "Q9NQ79-1", "CRTAC1", "GO_1900121", "negative regulation of receptor binding", "biological_process" ], [ "Q9NQ79-1", "CRTAC1", "GO_0021772", "olfactory bulb development", "biological_process" ], [ "Q9NRQ5-1", "SMCO4", "GO_0016021", "integral component of membrane", "cellular_component" ], [ "Q8IZF5-1", "ADGRF3", "GO_0004930", "G protein-coupled receptor activity", "molecular_function" ], [ "Q8IZF5-1", "ADGRF3", "GO_0007166", "cell surface receptor signaling pathway", "biological_process" ], [ "Q8IZF5-1", "ADGRF3", "GO_0007186", "G protein-coupled receptor signaling pathway", "biological_process" ], [ "Q8IZF5-1", "ADGRF3", "GO_0016021", "integral component of membrane", "cellular_component" ], [ "P30613-1", "PKLR", "GO_0042866", "pyruvate biosynthetic process", "biological_process" ], [ "P30613-1", "PKLR", "GO_0000287", "magnesium ion binding", "molecular_function" ], [ "P30613-1", "PKLR", "GO_0005524", "ATP binding", "molecular_function" ], [ "P30613-1", "PKLR", "GO_0005737", "cytoplasm", "cellular_component" ], [ "P30613-1", "PKLR", "GO_0005829", "cytosol", "cellular_component" ], [ "P30613-1", "PKLR", "GO_0032869", "cellular response to insulin stimulus", "biological_process" ], [ "P30613-1", "PKLR", "GO_0070062", "extracellular exosome", "cellular_component" ], [ "P30613-1", "PKLR", "GO_0001666", "response to hypoxia", "biological_process" ], [ "P30613-1", "PKLR", "GO_0006754", "ATP biosynthetic process", "biological_process" ], [ "P30613-1", "PKLR", "GO_0010226", "response to lithium ion", "biological_process" ], [ "P30613-1", "PKLR", "GO_0009749", "response to glucose", "biological_process" ], [ "P30613-1", "PKLR", "GO_0006096", "glycolytic process", "biological_process" ], [ "P30613-1", "PKLR", "GO_0051591", "response to cAMP", "biological_process" ], [ "P30613-1", "PKLR", "GO_0061621", "canonical glycolysis", "biological_process" ], [ "P30613-1", "PKLR", "GO_0071872", "cellular response to epinephrine stimulus", "biological_process" ], [ "P30613-1", "PKLR", "GO_0009408", "response to heat", "biological_process" ], [ "P30613-1", "PKLR", "GO_0016301", "kinase activity", "molecular_function" ], [ "P30613-1", "PKLR", "GO_0030955", "potassium ion binding", "molecular_function" ], [ "P30613-1", "PKLR", "GO_0033198", "response to ATP", "biological_process" ], [ "P30613-1", "PKLR", "GO_0004743", "pyruvate kinase activity", "molecular_function" ], [ "Q5H9L4-1", "TAF7L", "GO_0007275", "multicellular organism development", "biological_process" ], [ "Q5H9L4-1", "TAF7L", "GO_0003713", "transcription coactivator activity", "molecular_function" ], [ "Q5H9L4-1", "TAF7L", "GO_0005737", "cytoplasm", "cellular_component" ], [ "Q5H9L4-1", "TAF7L", "GO_0006357", "regulation of transcription by RNA polymerase II", "biological_process" ], [ "Q5H9L4-1", "TAF7L", "GO_0007283", "spermatogenesis", "biological_process" ], [ "Q5H9L4-1", "TAF7L", "GO_0030154", "cell differentiation", "biological_process" ], [ "Q5H9L4-1", "TAF7L", "GO_0008134", "transcription factor binding", "molecular_function" ], [ "Q5H9L4-1", "TAF7L", "GO_0044212", "transcription regulatory region DNA binding", "molecular_function" ], [ "Q5H9L4-1", "TAF7L", "GO_0005669", "transcription factor TFIID complex", "cellular_component" ], [ "Q5H9L4-1", "TAF7L", "GO_0035035", "histone acetyltransferase binding", "molecular_function" ], [ "Q5H9L4-1", "TAF7L", "GO_0051123", "RNA polymerase II preinitiation complex assembly", "biological_process" ], [ "Q9BZL4-1", "PPP1R12C", "GO_0004857", "enzyme inhibitor activity", "molecular_function" ], [ "Q9BZL4-1", "PPP1R12C", "GO_0005737", "cytoplasm", "cellular_component" ], [ "Q9BZL4-1", "PPP1R12C", "GO_0005856", "cytoskeleton", "cellular_component" ], [ "Q9BZL4-1", "PPP1R12C", "GO_0007165", "signal transduction", "biological_process" ], [ "Q9BZL4-1", "PPP1R12C", "GO_0019901", "protein kinase binding", "molecular_function" ], [ "Q9BZL4-1", "PPP1R12C", "GO_0019208", "phosphatase regulator activity", "molecular_function" ], [ "Q9NVL1-1", "FAM86C1", "GO_0008168", "methyltransferase activity", "molecular_function" ], [ "Q9NVL1-1", "FAM86C1", "GO_0032991", "protein-containing complex", "cellular_component" ], [ "Q5QJ38-1", "TCHHL1", "GO_0046914", "transition metal ion binding", "molecular_function" ], [ "Q9NQ75-1", "CASS4", "GO_0005737", "cytoplasm", "cellular_component" ], [ "Q9NQ75-1", "CASS4", "GO_0005856", "cytoskeleton", "cellular_component" ], [ "Q9NQ75-1", "CASS4", "GO_0005925", "focal adhesion", "cellular_component" ], [ "Q9NQ75-1", "CASS4", "GO_0007155", "cell adhesion", "biological_process" ], [ "Q9NQ75-1", "CASS4", "GO_0016477", "cell migration", "biological_process" ], [ "Q9NQ75-1", "CASS4", "GO_0030335", "positive regulation of cell migration", "biological_process" ], [ "Q9NQ75-1", "CASS4", "GO_0061098", "positive regulation of protein tyrosine kinase activity", "biological_process" ], [ "Q9NQ75-1", "CASS4", "GO_1900026", "positive regulation of substrate adhesion-dependent cell spreading", "biological_process" ], [ "Q9NQ75-1", "CASS4", "GO_1990782", "protein tyrosine kinase binding", "molecular_function" ], [ "Q9NQ75-1", "CASS4", "GO_0090527", "actin filament reorganization", "biological_process" ], [ "P20930-1", "FLG", "GO_0007275", "multicellular organism development", "biological_process" ], [ "P20930-1", "FLG", "GO_0005634", "nucleus", "cellular_component" ], [ "P20930-1", "FLG", "GO_0005829", "cytosol", "cellular_component" ], [ "P20930-1", "FLG", "GO_0043231", "intracellular membrane-bounded organelle", "cellular_component" ], [ "P20930-1", "FLG", "GO_0046914", "transition metal ion binding", "molecular_function" ] ] }, "readme": "Name\n - Human Gene Ontology (GO)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-09-06T14:06:38.951602\n\nModified on\n - \n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@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 Human Gene Ontology (GO) dataset contains human [taxid:9606] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-05 UniProt release. The dataset is derived from 2019-05 UniProt 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 sequnces\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/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-9606-homo-sapiens-2019-05.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/uniprot-proteome-9606-homo-sapiens-2019-05.nt\n Name: human_protein_idmapping.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_protein_idmapping.csv\n Output Subdomain\n Name: human_protein_go_annotation.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_protein_go_annotation.csv\n Name: human_protein_go_annotation.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_protein_go_annotation.stat.csv\n\nFields\n Name: \"gene_symbol\"\n Description: \"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\n Unique Values: \"19014\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"19349\"\n Name: \"go_term_label\"\n Description: \"\"\n Unique Values: \"18048\"\n Name: \"go_term_category\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"go_term_id\"\n Description: \"\"\n Unique Values: \"18048\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/human_protein_go_annotation.csv" }