{ "bcoid": "GLY_000952", "title": "Pig Gene Ontology (GO)", "description": "The Pig Gene Ontology (GO) dataset contains pig [taxid:9823] Gene Ontology Id and name, categories and ...", "filename": "pig_protein_go_annotation.csv", "filetype": "csv", "categories": { "species": [ "Sus scrofa" ], "molecule": [ "Protein" ], "tag": [ "Gene Ontology (Go)" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "A0A8W4F999-1...", "..." ], [ "A0A8W4F999-1...", "..." ] ], "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" } ], [ "A0A8W4F999-1", "", "GO_0003677", "DNA binding", "molecular_function", "", "" ], [ "A0A8W4F999-1", "", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "A0A8W4F999-1", "", "GO_0046872", "metal ion binding", "molecular_function", "", "" ], [ "A0A4X1U3C8-1", "CTSC", "GO_0006508", "proteolysis", "biological_process", "", "" ], [ "A0A4X1U3C8-1", "CTSC", "GO_0005764", "lysosome", "cellular_component", "", "" ], [ "A0A4X1U3C8-1", "CTSC", "GO_0008234", "cysteine-type peptidase activity", "molecular_function", "", "" ], [ "A0A287BSN5-1", "ZNF446", "GO_0005634", "nucleus", "cellular_component", "", "" ], [ "F1RV90-1", "MAK", "GO_0004672", "protein kinase activity", "molecular_function", "", "" ], [ "F1RV90-1", "MAK", "GO_0005524", "ATP binding", "molecular_function", "", "" ], [ "F1S708-1", "TNN", "GO_0005576", "extracellular region", "cellular_component", "", "" ], [ "F1S708-1", "TNN", "GO_0030154", "cell differentiation", "biological_process", "", "" ], [ "F1S708-1", "TNN", "GO_0048856", "anatomical structure development", "biological_process", "", "" ], [ "A0A8W4FMS3-1", "ARHGAP26", "GO_0005096", "GTPase activator activity", "molecular_function", "", "" ], [ "A0A8W4FMS3-1", "ARHGAP26", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "A0A8W4FMS3-1", "ARHGAP26", "GO_0005856", "cytoskeleton", "cellular_component", "", "" ], [ "A0A8W4FMS3-1", "ARHGAP26", "GO_0005925", "focal adhesion", "cellular_component", "", "" ], [ "A0A8W4FMS3-1", "ARHGAP26", "GO_0007165", "signal transduction", "biological_process", "", "" ], [ "I3L6J1-1", "RTN1", "GO_0005789", "endoplasmic reticulum membrane", "cellular_component", "", "" ], [ "A0A5G2RAB5-1", "TXNRD1", "GO_0004791", "thioredoxin-disulfide reductase (NADP) activity", "molecular_function", "", "" ], [ "A0A5G2RAB5-1", "TXNRD1", "GO_0050660", "flavin adenine dinucleotide binding", "molecular_function", "", "" ], [ "A0A5G2RAB5-1", "TXNRD1", "GO_0045454", "cell redox homeostasis", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0098978", "glutamatergic synapse", "cellular_component", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0048787", "presynaptic active zone membrane", "cellular_component", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0007409", "axonogenesis", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0009887", "animal organ morphogenesis", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0050804", "modulation of chemical synaptic transmission", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0010975", "regulation of neuron projection development", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0009888", "tissue development", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0099560", "synaptic membrane adhesion", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0098632", "cell-cell adhesion mediator activity", "molecular_function", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_2001222", "regulation of neuron migration", "biological_process", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0098685", "Schaffer collateral - CA1 synapse", "cellular_component", "", "" ], [ "A0A287AGD8-1", "NTNG1", "GO_0150011", "regulation of neuron projection arborization", "biological_process", "", "" ], [ "A0A287BN22-1", "BTBD10", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "A0A287AE97-1", "PIGK", "GO_0003923", "GPI-anchor transamidase activity", "molecular_function", "", "" ], [ "A0A287AE97-1", "PIGK", "GO_0006508", "proteolysis", "biological_process", "", "" ], [ "A0A287AE97-1", "PIGK", "GO_0016255", "attachment of GPI anchor to protein", "biological_process", "", "" ], [ "A0A287AE97-1", "PIGK", "GO_0042765", "GPI-anchor transamidase complex", "cellular_component", "", "" ], [ "A0A287BN27-1", "PABIR2", "GO_0004865", "protein serine/threonine phosphatase inhibitor activity", "molecular_function", "", "" ], [ "A0A286ZXT3-1", "PI4KA", "GO_0016310", "phosphorylation", "biological_process", "", "" ], [ "A0A286ZXT3-1", "PI4KA", "GO_0048015", "phosphatidylinositol-mediated signaling", "biological_process", "", "" ], [ "A0A286ZXT3-1", "PI4KA", "GO_0016301", "kinase activity", "molecular_function", "", "" ], [ "A0A286ZXT3-1", "PI4KA", "GO_0046854", "phosphatidylinositol phosphate biosynthetic process", "biological_process", "", "" ], [ "A0A5G2QDB0-1", "", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "A0A4X1VDU3-1", "ATG5", "GO_0016236", "macroautophagy", "biological_process", "", "" ], [ "A0A4X1VDU3-1", "ATG5", "GO_0034045", "phagophore assembly site membrane", "cellular_component", "", "" ], [ "A0A8D0PQ51-1", "FAM162A", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "I3L942-1", "RPTOR", "GO_0031929", "TOR signaling", "biological_process", "", "" ], [ "I3L942-1", "RPTOR", "GO_0031931", "TORC1 complex", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_1903232", "melanosome assembly", "biological_process", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0035651", "AP-3 adaptor complex binding", "molecular_function", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0036461", "BLOC-2 complex binding", "molecular_function", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0090383", "phagosome acidification", "biological_process", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0003924", "GTPase activity", "molecular_function", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0005525", "GTP binding", "molecular_function", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0005739", "mitochondrion", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0005769", "early endosome", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0005764", "lysosome", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0044233", "mitochondria-associated endoplasmic reticulum membrane", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0045335", "phagocytic vesicle", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0016192", "vesicle-mediated transport", "biological_process", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0005802", "trans-Golgi network", "cellular_component", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0035646", "endosome to melanosome transport", "biological_process", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0072657", "protein localization to membrane", "biological_process", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0007005", "mitochondrion organization", "biological_process", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0030742", "GTP-dependent protein binding", "molecular_function", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0035650", "AP-1 adaptor complex binding", "molecular_function", "", "" ], [ "A0A4X1U326-1", "RAB38", "GO_0033162", "melanosome membrane", "cellular_component", "", "" ], [ "A0A5G2Q7W2-1", "CLIC5", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "A0A5G2Q7W2-1", "CLIC5", "GO_0005254", "chloride channel activity", "molecular_function", "", "" ], [ "A0A5G2Q7W2-1", "CLIC5", "GO_0034707", "chloride channel complex", "cellular_component", "", "" ], [ "A0A287AZX1-1", "KLK11", "GO_0004252", "serine-type endopeptidase activity", "molecular_function", "", "" ], [ "A0A287AZX1-1", "KLK11", "GO_0006508", "proteolysis", "biological_process", "", "" ], [ "A0A287BPN5-1", "UROC1", "GO_0016153", "urocanate hydratase activity", "molecular_function", "", "" ], [ "A0A287BPN5-1", "UROC1", "GO_0019556", "histidine catabolic process to glutamate and formamide", "biological_process", "", "" ], [ "A0A287BPN5-1", "UROC1", "GO_0019557", "histidine catabolic process to glutamate and formate", "biological_process", "", "" ], [ "A0A287BAF3-1", "ADSS1", "GO_0000287", "magnesium ion binding", "molecular_function", "", "" ], [ "A0A287BAF3-1", "ADSS1", "GO_0005525", "GTP binding", "molecular_function", "", "" ], [ "A0A287BAF3-1", "ADSS1", "GO_0005737", "cytoplasm", "cellular_component", "", "" ], [ "A0A287BAF3-1", "ADSS1", "GO_0004019", "adenylosuccinate synthase activity", "molecular_function", "", "" ], [ "A0A287BAF3-1", "ADSS1", "GO_0044208", "'de novo' AMP biosynthetic process", "biological_process", "", "" ], [ "F1SRD2-1", "ANO10", "GO_0016020", "membrane", "cellular_component", "", "" ], [ "A0A287AM68-1", "TLK2", "GO_0004672", "protein kinase activity", "molecular_function", "", "" ], [ "A0A287AM68-1", "TLK2", "GO_0005524", "ATP binding", "molecular_function", "", "" ] ] }, "readme": "Name\n - Pig Gene Ontology (GO)\n\nVersion\n - v-2.4.1\n\nCreated on\n - \n\nModified on\n - 2024-02-28T19:07:30\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], 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 Pig Gene Ontology (GO) dataset contains pig [taxid:9823] 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-sus_scrofa.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-sus_scrofa.nt\n Output Subdomain\n Name: pig_protein_go_annotation.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_go_annotation.csv\n Name: pig_protein_go_annotation.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_go_annotation.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"20630\"\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: \"17197\"\n Name: \"go_term_id\"\n Description: \"The Gene Ontology (GO) term unique alphanumeric identifier\"\n Unique Values: \"15976\"\n Name: \"go_term_label\"\n Description: \"The Gene Ontology (GO) name that is a word or string of words\"\n Unique Values: \"15976\"\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/pig_protein_go_annotation.csv" }