{ "bcoid": "GLY_000242", "title": "Rat Gene Ontology (GO)", "description": "The Rat Gene Ontology (GO) dataset contains rat [taxid:10116] Gene Ontology Id and name, categories and ...", "filename": "rat_protein_go_annotation.csv", "filetype": "csv", "categories": { "species": "Rattus Norvegicus", "molecule": "Protein", "tags": "Gene Ontology (Go)", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q5RJK9-1...", "Polr1c..." ], [ "Q5RJK9-1...", "Polr1c..." ] ], "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" } ], [ "Q5RJK9-1", "Polr1c", "GO_0006360", "transcription by RNA polymerase I", "biological_process" ], [ "Q5RJK9-1", "Polr1c", "GO_0003677", "DNA binding", "molecular_function" ], [ "Q5RJK9-1", "Polr1c", "GO_0046983", "protein dimerization activity", "molecular_function" ], [ "Q5RJK9-1", "Polr1c", "GO_0006383", "transcription by RNA polymerase III", "biological_process" ], [ "Q5RJK9-1", "Polr1c", "GO_0005736", "RNA polymerase I complex", "cellular_component" ], [ "Q5RJK9-1", "Polr1c", "GO_0005666", "RNA polymerase III complex", "cellular_component" ], [ "Q5RJK9-1", "Polr1c", "GO_0003899", "DNA-directed 5'-3' RNA polymerase activity", "molecular_function" ], [ "Q5RJK8-1", "Acbd6", "GO_0005737", "cytoplasm", "cellular_component" ], [ "Q5RJK8-1", "Acbd6", "GO_0008289", "lipid binding", "molecular_function" ], [ "Q5RJK8-1", "Acbd6", "GO_0000062", "fatty-acyl-CoA binding", "molecular_function" ], [ "D3ZZY8-1", "Olfr225", "GO_0004930", "G protein-coupled receptor activity", "molecular_function" ], [ "D3ZZY8-1", "Olfr225", "GO_0005886", "plasma membrane", "cellular_component" ], [ "D3ZZY8-1", "Olfr225", "GO_0016021", "integral component of membrane", "cellular_component" ], [ "D3ZZY8-1", "Olfr225", "GO_0004984", "olfactory receptor activity", "molecular_function" ], [ "D3ZG10-1", "Grap2", "GO_0005634", "nucleus", "cellular_component" ], [ "D3ZG10-1", "Grap2", "GO_0005768", "endosome", "cellular_component" ], [ "D3ZB44-1", "Zfp324", "GO_0046872", "metal ion binding", "molecular_function" ], [ "D3ZB44-1", "Zfp324", "GO_0006355", "regulation of transcription, DNA-templated", "biological_process" ], [ "D3ZB44-1", "Zfp324", "GO_0003676", "nucleic acid binding", "molecular_function" ], [ "D3ZZY2-1", "Utp14a", "GO_0005730", "nucleolus", "cellular_component" ], [ "D3ZZY2-1", "Utp14a", "GO_0006364", "rRNA processing", "biological_process" ], [ "D3ZZY2-1", "Utp14a", "GO_0032040", "small-subunit processome", "cellular_component" ], [ "Q5RJK0-1", "Tmem106c", "GO_0016021", "integral component of membrane", "cellular_component" ], [ "Q5RJK0-1", "Tmem106c", "GO_0005789", "endoplasmic reticulum membrane", "cellular_component" ], [ "Q5RJK3-1", "Trmt10b", "GO_0009019", "tRNA (guanine-N1-)-methyltransferase activity", "molecular_function" ], [ "Q5RJK3-1", "Trmt10b", "GO_0005634", "nucleus", "cellular_component" ], [ "Q5RJK3-1", "Trmt10b", "GO_0005654", "nucleoplasm", "cellular_component" ], [ "Q5RJK3-1", "Trmt10b", "GO_0005739", "mitochondrion", "cellular_component" ], [ "Q5RJK3-1", "Trmt10b", "GO_0005829", "cytosol", "cellular_component" ], [ "Q5RJK3-1", "Trmt10b", "GO_0000049", "tRNA binding", "molecular_function" ], [ "Q5RJK3-1", "Trmt10b", "GO_0090646", "mitochondrial tRNA processing", "biological_process" ], [ "Q5RJK3-1", "Trmt10b", "GO_0052905", "tRNA (guanine(9)-N(1))-methyltransferase activity", "molecular_function" ], [ "P30349-1", "Lta4h", "GO_0005634", "nucleus", "cellular_component" ], [ "P30349-1", "Lta4h", "GO_0005737", "cytoplasm", "cellular_component" ], [ "P30349-1", "Lta4h", "GO_0008237", "metallopeptidase activity", "molecular_function" ], [ "P30349-1", "Lta4h", "GO_0008270", "zinc ion binding", "molecular_function" ], [ "P30349-1", "Lta4h", "GO_0010043", "response to zinc ion", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0044255", "cellular lipid metabolic process", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0043171", "peptide catabolic process", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0004177", "aminopeptidase activity", "molecular_function" ], [ "P30349-1", "Lta4h", "GO_0004301", "epoxide hydrolase activity", "molecular_function" ], [ "P30349-1", "Lta4h", "GO_0006691", "leukotriene metabolic process", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0019370", "leukotriene biosynthetic process", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0043434", "response to peptide hormone", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0060509", "type I pneumocyte differentiation", "biological_process" ], [ "P30349-1", "Lta4h", "GO_0004463", "leukotriene-A4 hydrolase activity", "molecular_function" ], [ "Q5RJK5-1", "Cbx3", "GO_0005634", "nucleus", "cellular_component" ], [ "Q5RJK5-1", "Cbx3", "GO_0005819", "spindle", "cellular_component" ], [ "Q5RJK5-1", "Cbx3", "GO_0019904", "protein domain specific binding", "molecular_function" ], [ "Q5RJK5-1", "Cbx3", "GO_0042802", "identical protein binding", "molecular_function" ], [ "Q5RJK5-1", "Cbx3", "GO_0045892", "negative regulation of transcription, DNA-templated", "biological_process" ], [ "Q5RJK5-1", "Cbx3", "GO_0000775", "chromosome, centromeric region", "cellular_component" ], [ "Q5RJK5-1", "Cbx3", "GO_0006974", "cellular response to DNA damage stimulus", "biological_process" ], [ "Q5RJK5-1", "Cbx3", "GO_0071549", "cellular response to dexamethasone stimulus", "biological_process" ], [ "Q5RJK5-1", "Cbx3", "GO_0005719", "nuclear euchromatin", "cellular_component" ], [ "Q5RJK5-1", "Cbx3", "GO_0005720", "nuclear heterochromatin", "cellular_component" ], [ "Q5RJK5-1", "Cbx3", "GO_1990226", "histone methyltransferase binding", "molecular_function" ], [ "Q5RJK5-1", "Cbx3", "GO_0035985", "senescence-associated heterochromatin focus", "cellular_component" ], [ "Q5RJK5-1", "Cbx3", "GO_0090734", "site of DNA damage", "cellular_component" ], [ "D3ZB48-1", "Hook1", "GO_0030897", "HOPS complex", "cellular_component" ], [ "D3ZB48-1", "Hook1", "GO_0003779", "actin binding", "molecular_function" ], [ "D3ZB48-1", "Hook1", "GO_0005737", "cytoplasm", "cellular_component" ], [ "D3ZB48-1", "Hook1", "GO_0005813", "centrosome", "cellular_component" ], [ "D3ZB48-1", "Hook1", "GO_0005829", "cytosol", "cellular_component" ], [ "D3ZB48-1", "Hook1", "GO_0008017", "microtubule binding", "molecular_function" ], [ "D3ZB48-1", "Hook1", "GO_0042802", "identical protein binding", "molecular_function" ], [ "D3ZB48-1", "Hook1", "GO_0007032", "endosome organization", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_0007040", "lysosome organization", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_0008333", "endosome to lysosome transport", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_0045022", "early endosome to late endosome transport", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_0070695", "FHF complex", "cellular_component" ], [ "D3ZB48-1", "Hook1", "GO_0007030", "Golgi organization", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_0030705", "cytoskeleton-dependent intracellular transport", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_0051959", "dynein light intermediate chain binding", "molecular_function" ], [ "D3ZB48-1", "Hook1", "GO_0031122", "cytoplasmic microtubule organization", "biological_process" ], [ "D3ZB48-1", "Hook1", "GO_1905198", "manchette assembly", "biological_process" ], [ "Q5RJK6-1", "Inpp1", "GO_0004441", "inositol-1,4-bisphosphate 1-phosphatase activity", "molecular_function" ], [ "Q5RJK6-1", "Inpp1", "GO_0046855", "inositol phosphate dephosphorylation", "biological_process" ], [ "Q5RJK6-1", "Inpp1", "GO_0046854", "phosphatidylinositol phosphorylation", "biological_process" ], [ "A0A096MKC6-1", "", "GO_0036094", "small molecule binding", "molecular_function" ], [ "Q6MG55-1", "Abhd16a", "GO_0016021", "integral component of membrane", "cellular_component" ], [ "Q6MG55-1", "Abhd16a", "GO_0004620", "phospholipase activity", "molecular_function" ], [ "Q6MG55-1", "Abhd16a", "GO_0047372", "acylglycerol lipase activity", "molecular_function" ], [ "Q6MG55-1", "Abhd16a", "GO_0052651", "monoacylglycerol catabolic process", "biological_process" ] ] }, "readme": "Name\n - Rat Gene Ontology (GO)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-09-06T14:06:38.969307\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 Rat Gene Ontology (GO) dataset contains rat [taxid:10116] 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-10116-rattus-norvegicus-2019-05.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt\n Name: rat_protein_idmapping.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/rat_protein_idmapping.csv\n Output Subdomain\n Name: rat_protein_go_annotation.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/rat_protein_go_annotation.csv\n Name: rat_protein_go_annotation.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/rat_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: \"18306\"\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: \"19736\"\n Name: \"go_term_label\"\n Description: \"\"\n Unique Values: \"16651\"\n Name: \"go_term_category\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"go_term_id\"\n Description: \"\"\n Unique Values: \"16651\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/rat_protein_go_annotation.csv" }