{ "bcoid": "GLY_000651", "title": "Fruitfly Protein Recommended Names (UniProtKB)", "description": "The Fruitfly Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for fruitfly ...", "filename": "fruitfly_protein_recnames.csv", "filetype": "csv", "categories": { "species": [ "Drosophila melanogaster" ], "molecule": [ "Protein" ], "tag": [ "Protein Recommended Names" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P40796-1...", "La protein h..." ], [ "P40797-1...", "Protein pean..." ] ], "headers": [ "uniprotkb_ca...", "recommended_..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "recommended_name_full" }, { "type": "string", "label": "recommended_name_short" }, { "type": "string", "label": "ec_name" } ], [ "P40796-1", "La protein homolog", "", "" ], [ "P40797-1", "Protein peanut", "", "" ], [ "P40794-1", "Protein bottleneck", "", "" ], [ "P40795-1", "Protein folded gastrulation", "", "" ], [ "P40792-1", "Ras-related protein Rac1", "", "" ], [ "P40793-1", "Cdc42 homolog", "", "3.6.5.2" ], [ "P40791-1", "Myocyte-specific enhancer factor 2", "D-mef2", "" ], [ "P40798-1", "Protein shuttle craft", "", "" ], [ "P40421-1", "Serine/threonine-protein phosphatase rdgC", "", "3.1.3.16" ], [ "P40423-1", "Myosin regulatory light chain sqh", "", "" ], [ "P40427-1", "Homeobox protein extradenticle", "Dpbx", "" ], [ "P08841-1", "Tubulin beta-3 chain", "", "" ], [ "Q9VE87-1", "Protein hemingway", "", "" ], [ "Q9VE86-1", "3'-5' exonuclease", "", "3.1.11.-" ], [ "P05389-1", "Large ribosomal subunit protein P2", "", "" ], [ "P04388-1", "Ras-like protein 2", "", "3.6.5.2" ], [ "A1ZB47-1", "guanylate cyclase", "", "4.6.1.2" ], [ "A1ZB42-1", "Mediator of RNA polymerase II transcription subunit 9", "", "" ], [ "Q9VYT1-1", "BLOC-1-related complex subunit 5", "", "" ], [ "Q9VLI9-1", "Trafficking protein particle complex subunit", "", "" ], [ "Q9VLI1-1", "Alpha-mannosidase", "", "3.2.1.-" ], [ "Q9VLI0-1", "Alpha-mannosidase", "", "3.2.1.-" ], [ "Q9VLI2-1", "Alpha-mannosidase", "", "3.2.1.-" ], [ "Q02870-1", "General transcription and DNA repair factor IIH helicase subunit XPB", "TFIIH subunit XPB", "3.6.4.12" ], [ "Q7JUM3-1", "phosphatidylinositol N-acetylglucosaminyltransferase", "", "2.4.1.198" ], [ "Q8SXV2-1", "Protein quiver", "", "" ], [ "Q95R35-1", "Cytosol aminopeptidase", "", "3.4.13.23" ], [ "P17336-1", "Catalase", "", "1.11.1.6" ], [ "Q9VWS8-1", "Tudor domain-containing protein", "", "" ], [ "Q9VWS4-1", "Tumor necrosis factor receptor superfamily member wengen", "", "" ], [ "Q9VWS0-1", "Inhibitor of growth protein", "", "" ], [ "Q9VWS2-1", "Nucleoporin Nup35", "", "" ], [ "P48554-1", "Ras-related protein Rac2", "", "" ], [ "P48555-1", "Ras-related protein Ral-a", "", "3.6.5.2" ], [ "Q9VUR3-1", "Probable aminoacyl tRNA synthase complex-interacting multifunctional protein 2", "", "" ], [ "Q9V969-1", "Putative gustatory receptor 57a", "", "" ], [ "Q9V968-1", "MIP18 family protein galla-1", "", "" ], [ "P21663-1", "Andropin", "", "" ], [ "P11996-1", "Larval serum protein 1 beta chain", "", "" ], [ "P11997-1", "Larval serum protein 1 gamma chain", "", "" ], [ "P11995-1", "Larval serum protein 1 alpha chain", "", "" ], [ "P03896-1", "NADH-ubiquinone oxidoreductase chain 2", "", "7.1.1.2" ], [ "A1Z8T9-1", "Dynein light chain", "", "" ], [ "A1ZAI5-1", "Putative fatty acyl-CoA reductase CG5065", "", "1.2.1.84" ], [ "A1ZAI1-1", "dolichol kinase", "", "2.7.1.108" ], [ "A1ZAI3-1", "Putative fatty acyl-CoA reductase CG8303", "", "1.2.1.84" ], [ "Q9VH70-1", "Testis-specific zinc finger protein topi", "", "" ], [ "Q01583-4", "Diacylglycerol kinase 1", "DAG kinase 1", "2.7.1.107" ], [ "Q01583-4", "Diacylglycerol kinase 1", "DGK 1", "2.7.1.107" ], [ "Q01583-4", "Diacylglycerol kinase 1", "Diglyceride kinase 1", "2.7.1.107" ], [ "M9PDV2-1", "Tetraspanin", "", "" ], [ "Q8IPP9-1", "Trichohyalin", "", "" ], [ "Q8IMP6-1", "Protein SPT2 homolog", "", "" ], [ "Q9NB04-1", "Patj homolog", "", "" ], [ "A1Z9R4-1", "Zinc finger protein 423 homolog", "", "" ], [ "Q9VTC2-1", "Biogenesis of lysosome-related organelles complex 1 subunit 4", "BLOC-1 subunit 4", "" ], [ "Q9VKQ9-1", "Protein dpy-30 homolog", "", "" ], [ "P55035-1", "26S proteasome non-ATPase regulatory subunit 4", "", "" ], [ "Q7JQ32-1", "Receptor-type guanylate cyclase Gyc76C", "", "4.6.1.2" ], [ "A1ZBY1-1", "Protein fem-1 homolog B", "", "" ], [ "Q7KUN6-1", "Transcription elongation factor 1 homolog", "", "" ], [ "Q9VFW9-1", "Aminopeptidase", "", "3.4.11.-" ], [ "A0A0B4K753-1", "Hemotin", "", "" ], [ "Q9VE04-1", "Large ribosomal subunit protein mL55", "", "" ], [ "Q9W1G0-1", "Probable transaldolase", "", "2.2.1.2" ], [ "Q9VY42-1", "Tyrosine aminotransferase", "TAT", "2.6.1.5" ], [ "Q9VY41-1", "Plasminogen receptor (KT)", "", "" ], [ "Q9VY47-1", "phosphatidylinositol-3,4-bisphosphate 4-phosphatase", "", "3.1.3.66" ], [ "Q9VY44-1", "mRNA-capping enzyme", "", "" ], [ "A4V0X6-1", "Calmodulin-lysine N-methyltransferase", "", "2.1.1.60" ], [ "Q9VE09-1", "Glutamyl-tRNA(Gln) amidotransferase subunit A, mitochondrial", "Glu-AdT subunit A", "6.3.5.7" ], [ "Q9VCT3-1", "Elongation of very long chain fatty acids protein", "", "2.3.1.199" ], [ "P06602-1", "Segmentation protein even-skipped", "", "" ], [ "P06603-1", "Tubulin alpha-1 chain", "", "3.6.5.-" ], [ "P06601-1", "Segmentation protein paired", "", "" ], [ "P06606-1", "Tubulin alpha-4 chain", "", "3.6.5.-" ], [ "P06607-1", "Vitellogenin-3", "", "" ], [ "P06604-1", "Tubulin alpha-2 chain", "", "3.6.5.-" ], [ "P06605-1", "Tubulin alpha-3 chain", "", "3.6.5.-" ], [ "Q9VWN9-1", "Zinc finger SWIM domain-containing protein 8 homolog", "", "" ], [ "Q9VWN5-1", "Ubiquitin carboxyl-terminal hydrolase MINDY-3 homolog", "", "3.4.19.12" ], [ "P18475-1", "Tyrosine-protein kinase receptor torso", "", "2.7.10.1" ], [ "Q9VWN3-1", "Succinate dehydrogenase [ubiquinone] iron-sulfur subunit, mitochondrial", "", "1.3.5.1" ], [ "P25823-1", "Maternal protein tudor", "", "" ] ] }, "readme": "Name\n - Fruitfly Protein Recommended Names (UniProtKB)\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2022-08-31T11:01:36.870249\n\nModified on\n - 2022-09-26T09:08:12.703732\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 Fruitfly Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - protein recommended name\n - protein name\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.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-drosophila-melanogaster.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-drosophila-melanogaster.nt\n Output Subdomain\n Name: fruitfly_protein_recnames.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_recnames.csv\n Name: fruitfly_protein_recnames.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_recnames.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"5882\"\n Name: \"recommended_name_full\"\n Description: \"Recommended full name of the protein in the UniProtKB database\"\n Unique Values: \"4815\"\n Name: \"recommended_name_short\"\n Description: \"Recommended short name of the protein in UniProtKB database\"\n Unique Values: \"764\"\n Name: \"ec_name\"\n Description: \"Enzyme Commision name assigned to an enzyme by the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (IUBMB)\"\n Unique Values: \"685\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/fruitfly_protein_recnames.csv" }