{ "bcoid": "GLY_000397", "title": "Rat Protein Submitted Names (UniProtKB)", "description": "The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] ...", "filename": "rat_protein_submittednames.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Protein Submitted Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "D3ZB44-1...", "Zinc finger ..." ], [ "D3ZB44-1...", "RCG27445..." ] ], "headers": [ "uniprotkb_ca...", "submitted_na..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "submitted_name_full" }, { "type": "string", "label": "submitted_name_short" }, { "type": "string", "label": "ec_name" } ], [ "D3ZB44-1", "Zinc finger protein 324", "", "" ], [ "D3ZB44-1", "RCG27445", "", "" ], [ "D3ZB49-1", "Similar to Protein C8orf1 (HT41) (Predicted), isoform CRA_b", "", "" ], [ "D3ZB49-1", "Oxidative stress-induced growth inhibitor family member 2", "", "" ], [ "D3ZB48-1", "Hook microtubule-tethering protein 1", "", "" ], [ "D3ZB48-1", "Hook homolog 1 (Drosophila) (Predicted)", "", "" ], [ "A0A0G2JVG5-1", "Trichohyalin-like", "", "" ], [ "A0A0G2JVG6-1", "Uncharacterized protein", "", "" ], [ "A0A096MJY8-1", "Acetyl-CoA acetyltransferase 2-like 1", "", "" ], [ "A0A096MJY1-1", "Similar to Gpc6 protein (Predicted)", "", "" ], [ "A0A096MJY1-1", "Glypican 6", "", "" ], [ "A0A096MJY2-1", "Stomatin-like 3", "", "" ], [ "A0A096MJY2-1", "Stomatin (Epb7.2)-like 3 (Predicted), isoform CRA_a", "", "" ], [ "Q5RJK6-1", "Inositol polyphosphate-1-phosphatase", "", "" ], [ "Q5RJK6-1", "RCG22563", "", "" ], [ "D4A4W8-1", "T, brachyury homolog (Mouse) (Predicted), isoform CRA_b", "", "" ], [ "D4A4W8-1", "T-box transcription factor T", "", "" ], [ "D4A4W1-1", "Family with sequence similarity 174, member B", "", "" ], [ "F7EN52-1", "Cyp46a1 protein", "", "" ], [ "F7EN52-1", "Cytochrome P450, family 46, subfamily a, polypeptide 1", "", "" ], [ "D4A4W4-1", "Abhydrolase domain containing 9 (Predicted)", "", "" ], [ "D4A4W4-1", "Epoxide hydrolase 3", "", "" ], [ "D4A4W6-1", "SRA stem-loop-interacting RNA-binding protein", "", "" ], [ "D4A4W6-1", "RCG20695, isoform CRA_b", "", "" ], [ "D4A4W7-1", "Mitochondria-localized glutamic acid-rich protein", "", "" ], [ "D4A4W7-1", "RCG50000, isoform CRA_c", "", "" ], [ "G3V6I3-1", "Coiled-coil domain containing 49 (Predicted)", "", "" ], [ "G3V6I3-1", "CWC25 spliceosome-associated protein homolog", "", "" ], [ "G3V6I6-1", "Adiponectin receptor 1", "", "" ], [ "G3V6I6-1", "Adiponectin receptor 1, isoform CRA_a", "", "" ], [ "G3V6I4-1", "Mitochondrial amidoxime reducing component 1", "", "" ], [ "G3V6I4-1", "RCG20363, isoform CRA_a", "", "" ], [ "A0A0G2K0T8-1", "Family with sequence similarity 25, member A", "", "" ], [ "A0A0G2K0T8-1", "RCG42313", "", "" ], [ "A0A0G2K0T4-1", "Uncharacterized protein", "", "" ], [ "A0A0G2K0T7-1", "Zinc finger protein 35", "", "" ], [ "D3ZVR6-1", "SMC5-SMC6 complex localization factor 1", "", "" ], [ "D3ZVR6-1", "RCG44470", "", "" ], [ "A0A0G2K1A3-1", "Uncharacterized protein", "", "" ], [ "A0A0G2K1A1-1", "Zinc finger protein 706", "", "" ], [ "A0A0G2K1A1-1", "Uncharacterized protein LOC500855", "", "" ], [ "M0RB72-1", "Proline-rich 15-like", "", "" ], [ "M0RB72-1", "RCG34095", "", "" ], [ "E9PU34-1", "RCG41110", "", "" ], [ "E9PU34-1", "Required for meiotic nuclear division 1 homolog", "", "" ], [ "M0R8G5-1", "IgA-inducing protein", "", "" ], [ "D3ZGR6-1", "Coiled-coil domain-containing 138", "", "" ], [ "D3ZGR7-1", "Telomerase RNA component-interacting RNase", "", "" ], [ "D3ZGR7-1", "RCG51149", "", "" ], [ "D3ZGR5-1", "Ankyrin repeat domain-containing protein 12-like", "", "" ], [ "D3ZIY3-1", "YTH N(6)-methyladenosine RNA-binding protein 3", "", "" ], [ "D3ZIY3-1", "YTH domain family 3 (Predicted), isoform CRA_b", "", "" ], [ "D3ZHU7-1", "Methyl-CpG-binding domain protein 3-like 2", "", "" ], [ "D3ZSP2-1", "NACHT, LRR and PYD domains-containing protein 4B-like", "", "" ], [ "D3ZFP5-1", "Similar to Robo-1", "", "" ], [ "D3ZFP5-1", "RCG35485", "", "" ], [ "D3ZFP7-1", "Hypothetical LOC293166 (Predicted), isoform CRA_b", "", "" ], [ "D3ZFP7-1", "INSC, spindle orientation adaptor protein", "", "" ], [ "D3ZFP6-1", "TOPBP1-interacting checkpoint and replication regulator", "", "" ], [ "D3ZYL2-1", "Kiaa0408-like", "", "" ], [ "D3ZYL2-1", "RCG42077, isoform CRA_b", "", "" ], [ "D3ZYL3-1", "Vomeronasal 2 receptor, 8", "", "" ], [ "D3ZYL0-1", "Receptor (TNFRSF)-interacting serine-threonine kinase 1 (Predicted)", "", "" ], [ "D3ZYL0-1", "Receptor-interacting serine/threonine kinase 1", "", "" ], [ "D4A131-1", "Mitochondrial ribosomal protein L4", "", "" ], [ "D4A131-1", "Mitochondrial ribosomal protein L4 (Predicted), isoform CRA_b", "", "" ], [ "D4A135-1", "GRAM domain-containing 1C", "", "" ], [ "D4A138-1", "Nanos C2HC-type zinc finger 3", "", "" ], [ "D4A138-1", "Nanos homolog 3 (Drosophila) (Predicted)", "", "" ], [ "F1LWI7-1", "Retinitis pigmentosa 1-like 1 protein-like", "", "" ], [ "F1LWI8-1", "WD repeat domain 66", "", "" ], [ "D3ZCS5-1", "Essential meiotic structure-specific endonuclease 1", "", "" ], [ "D3ZCS4-1", "IQ motif-containing GTPase-activating protein 3", "", "" ], [ "D3ZHE2-1", "Yip1 domain family, member 7", "", "" ], [ "D3ZHE2-1", "Similar to YIP1B (Predicted), isoform CRA_a", "", "" ], [ "D3ZHE3-1", "Zinc finger SWIM-type-containing 9", "", "" ], [ "D3ZCS1-1", "Regulator of G-protein-signaling 13", "", "" ], [ "D3ZCS1-1", "Similar to RGS13 (Predicted)", "", "" ], [ "D3ZHE5-1", "RCG34082", "", "" ], [ "D3ZHE5-1", "RAB11 family-interacting protein 4", "", "" ], [ "D3ZCS2-1", "C1q and TNF-related 2", "", "" ], [ "D3ZUF5-1", "Proline-rich and Gla domain 1", "", "" ], [ "D3ZUF0-1", "Uncharacterized protein", "", "" ], [ "D3ZUF1-1", "Similar to RIKEN cDNA 2310010M24 (Predicted)", "", "" ] ] }, "readme": "Name\n - Rat Protein Submitted Names (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T13:43:53.106298\n\nModified on\n - 2020-03-16T11:16:17.615859\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@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 Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot.. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - protein submitted name\n - protein name\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB submitted 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/pipeline/extractor/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-rattus-norvegicus.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2021_04/uniprot-proteome-rattus-norvegicus.nt\n Output Subdomain\n Name: rat_protein_submittednames.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/rat_protein_submittednames.csv\n Name: rat_protein_submittednames.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/rat_protein_submittednames.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"9288\"\n Name: \"submitted_name_full\"\n Description: \"The full submitted protein name in UniProtKB\"\n Unique Values: \"12868\"\n Name: \"submitted_name_short\"\n Description: \"The short submitted protein name in UniProtKB\"\n Unique Values: \"1\"\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: \"5\"", "downloadurl": "/ln2data/releases/data/v-1.12.3/reviewed/rat_protein_submittednames.csv" }