{ "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": [ [ "P30613-1...", "PKLR..." ], [ "P30613-1...", "PKLR..." ] ], "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" } ], [ "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_0007584", "response to nutrient", "biological_process", "", "" ], [ "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_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", "", "" ], [ "P30613-1", "PKLR", "GO_0048029", "monosaccharide binding", "molecular_function", "", "" ], [ "Q92994-1", "BRF1", "GO_0017025", "TBP-class protein binding", "molecular_function", "", "" ], [ "Q92994-1", "BRF1", "GO_0000126", "transcription factor TFIIIB complex", "cellular_component", "", "" ], [ "Q92994-1", "BRF1", "GO_0070897", "transcription preinitiation complex assembly", "biological_process", "", "" ], [ "Q92994-1", "BRF1", "GO_0000995", "RNA polymerase III general transcription initiation factor activity", "molecular_function", "", "" ], [ "P10242-1", "MYB", "GO_0003677", "DNA binding", "molecular_function", "", "" ], [ "P10242-1", "MYB", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "P10242-1", "MYB", "GO_0006355", "regulation of DNA-templated transcription", "biological_process", "", "" ], [ "Q9GZW8-1", "MS4A7", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "O14817-1", "TSPAN4", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "A2RU30-1", "TESPA1", "GO_0005102", "signaling receptor binding", "molecular_function", "", "" ], [ "A2RU30-1", "TESPA1", "GO_0050862", "positive regulation of T cell receptor signaling pathway", "biological_process", "", "" ], [ "A2RU30-1", "TESPA1", "GO_0010387", "COP9 signalosome assembly", "biological_process", "", "" ], [ "Q8N6H7-1", "ARFGAP2", "GO_0005096", "GTPase activator activity", "molecular_function", "", "" ], [ "Q8N6H7-1", "ARFGAP2", "GO_0005794", "Golgi apparatus", "cellular_component", "", "" ], [ "Q8N6H7-1", "ARFGAP2", "GO_0005829", "cytosol", "cellular_component", "", "" ], [ "Q8N6H7-1", "ARFGAP2", "GO_0005886", "plasma membrane", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0005524", "ATP binding", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0005886", "plasma membrane", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0042626", "ATPase-coupled transmembrane transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0055085", "transmembrane transport", "biological_process", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0070062", "extracellular exosome", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0008559", "ABC-type xenobiotic transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0015432", "ABC-type bile acid transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0015721", "bile acid and bile salt transport", "biological_process", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0016324", "apical plasma membrane", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0030659", "cytoplasmic vesicle membrane", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0005774", "vacuolar membrane", "cellular_component", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0008514", "organic anion transmembrane transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0015216", "purine nucleotide transmembrane transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0015711", "organic anion transport", "biological_process", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0015865", "purine nucleotide transport", "biological_process", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0043225", "ATPase-coupled inorganic anion transmembrane transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0015431", "ABC-type glutathione S-conjugate transporter activity", "molecular_function", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0042908", "xenobiotic transport", "biological_process", "", "" ], [ "Q96J66-1", "ABCC11", "GO_0071716", "leukotriene transport", "biological_process", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0005524", "ATP binding", "molecular_function", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0005783", "endoplasmic reticulum", "cellular_component", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0042626", "ATPase-coupled transmembrane transporter activity", "molecular_function", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0055085", "transmembrane transport", "biological_process", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0005789", "endoplasmic reticulum membrane", "cellular_component", "", "" ], [ "Q96J65-1", "ABCC12", "GO_0140359", "ABC-type transporter activity", "molecular_function", "", "" ], [ "Q9BUZ4-1", "TRAF4", "GO_0046872", "metal ion binding", "molecular_function", "", "" ], [ "Q8NC06-1", "ACBD4", "GO_0000062", "fatty-acyl-CoA binding", "molecular_function", "", "" ], [ "Q8IYT4-1", "KATNAL2", "GO_0005524", "ATP binding", "molecular_function", "", "" ], [ "Q8IYT4-1", "KATNAL2", "GO_0016887", "ATP hydrolysis activity", "molecular_function", "", "" ], [ "Q53F39-1", "MPPE1", "GO_0005794", "Golgi apparatus", "cellular_component", "", "" ], [ "Q53F39-1", "MPPE1", "GO_0016787", "hydrolase activity", "molecular_function", "", "" ], [ "Q53F39-1", "MPPE1", "GO_0033116", "endoplasmic reticulum-Golgi intermediate compartment membrane", "cellular_component", "", "" ], [ "Q53F39-1", "MPPE1", "GO_0006506", "GPI anchor biosynthetic process", "biological_process", "", "" ], [ "A6NC51-1", "TMEM150B", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q8NBW4-1", "SLC38A9", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "Q14766-1", "LTBP1", "GO_0031012", "extracellular matrix", "cellular_component", "", "" ], [ "Q14766-1", "LTBP1", "GO_0005509", "calcium ion binding", "molecular_function", "", "" ], [ "P40424-1", "PBX1", "GO_0001779", "natural killer cell differentiation", "biological_process", "", "" ], [ "P40424-1", "PBX1", "GO_2000648", "positive regulation of stem cell proliferation", "biological_process", "", "" ], [ "P40424-1", "PBX1", "GO_0035162", "embryonic hemopoiesis", "biological_process", "", "" ], [ "P40424-1", "PBX1", "GO_0003677", "DNA binding", "molecular_function", "", "" ], [ "P40424-1", "PBX1", "GO_0003700", "DNA-binding transcription factor activity", "molecular_function", "", "" ], [ "P40424-1", "PBX1", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "P40424-1", "PBX1", "GO_0005654", "nucleoplasm", "cellular_component", "", "" ], [ "P40424-1", "PBX1", "GO_0005737", "cytoplasm", "cellular_component", "", "" ] ] }, "readme": "Name\n - Human Gene Ontology (GO)\n\nVersion\n - v-2.0.3\n\nCreated on\n - 2019-09-06T14:06:38.951602\n\nModified on\n - 2022-09-26T09:04:47.947013\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], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@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 2019-09 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 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-homo-sapiens.nt\n URI: /data/shared/glyds/downloads/ebi/2022_05/uniprot-proteome-homo-sapiens.nt\n Output Subdomain\n Name: human_protein_go_annotation.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_go_annotation.csv\n Name: human_protein_go_annotation.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_go_annotation.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"19363\"\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: \"19321\"\n Name: \"go_term_id\"\n Description: \"The Gene Ontology (GO) term unique alphanumeric identifier\"\n Unique Values: \"18946\"\n Name: \"go_term_label\"\n Description: \"The Gene Ontology (GO) name that is a word or string of words\"\n Unique Values: \"18946\"\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-2.0.3/reviewed/human_protein_go_annotation.csv" }