{ "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": [ [ "A0A0G2JVG5-1...", "Trichohyalin..." ], [ "A0A0G2JVG6-1...", "Zinc finger ..." ] ], "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" } ], [ "A0A0G2JVG5-1", "Trichohyalin-like", "", "" ], [ "A0A0G2JVG6-1", "Zinc finger protein 59", "", "" ], [ "F7FI04-1", "Sorting nexin 10", "", "" ], [ "D4A4W8-1", "T-box transcription factor T", "", "" ], [ "D4A4W1-1", "Uncharacterized 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", "", "" ], [ "D4A4W7-1", "Mitochondria-localized glutamic acid-rich protein", "", "" ], [ "A0A8I6AEL7-1", "Similar to MGC79482 protein", "", "" ], [ "F1MAA4-1", "ATPase cation-transporting 13A2", "", "" ], [ "A0A8I5Y6V4-1", "Myb/SANT DNA-binding domain-containing 1", "", "" ], [ "A0A8I5Y6V4-1", "Similar to RIKEN cDNA A930005I04 gene (Predicted), isoform CRA_a", "", "" ], [ "A0A8I6AER0-1", "Tau tubulin kinase 2", "", "" ], [ "A0A8I6AVR1-1", "Spermine synthase, pseudogene 1", "", "" ], [ "A0A8I6AVR1-1", "RCG63119", "", "" ], [ "D3ZIY3-1", "YTH N(6)-methyladenosine RNA-binding protein 3", "", "" ], [ "D3ZIY3-1", "YTH domain family 3 (Predicted), isoform CRA_a", "", "" ], [ "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", "", "" ], [ "D3ZFP1-1", "G protein-coupled receptor 137C", "", "" ], [ "D4A131-1", "Mitochondrial ribosomal protein L4", "", "" ], [ "D4A131-1", "Mitochondrial ribosomal protein L4 (Predicted), isoform CRA_b", "", "" ], [ "D4A138-1", "Nanos C2HC-type zinc finger 3", "", "" ], [ "D4A138-1", "Nanos homolog 3 (Drosophila) (Predicted)", "", "" ], [ "D3ZCS5-1", "Essential meiotic structure-specific endonuclease 1", "", "" ], [ "D3ZCS4-1", "IQ motif-containing GTPase-activating protein 3", "", "" ], [ "D3ZCS6-1", "Otopetrin 2 (Predicted)", "", "" ], [ "D3ZCS6-1", "Otopetrin 2", "", "" ], [ "D3ZCS1-1", "Regulator of G-protein-signaling 13", "", "" ], [ "D3ZCS1-1", "Similar to RGS13 (Predicted)", "", "" ], [ "D3ZCS3-1", "Poly(rC)-binding protein 4", "", "" ], [ "D3ZUF0-1", "Myosin XVB", "", "" ], [ "D3ZUF1-1", "Similar to RIKEN cDNA 2310010M24 (Predicted)", "", "" ], [ "D3ZUF1-1", "LY6/PLAUR domain-containing 6B", "", "" ], [ "Q6P5P4-1", "F-box protein 16", "", "" ], [ "D3ZXJ0-1", "Matrix metallopeptidase 17 (Predicted)", "", "" ], [ "D3ZXJ0-1", "Matrix metallopeptidase 17", "", "" ], [ "D3ZXJ5-1", "RCG24931", "", "" ], [ "D3ZXJ5-1", "Elongation factor-like GTPase 1", "", "" ], [ "A0A8I6ACH9-1", "Zinc finger protein 526", "", "" ], [ "A0A0G2JVZ3-1", "Spetex-2G protein", "", "" ], [ "A0A0G2JVZ2-1", "T-cell leukemia homeobox 2", "", "" ], [ "A0A0G2JVZ7-1", "Crystallin beta-gamma domain-containing 2", "", "" ], [ "A0A8I6A180-1", "Teneurin transmembrane protein 4", "", "" ], [ "A0A8I6A182-1", "Phosphatidylinositol transfer protein, cytoplasmic 1", "", "" ], [ "A0A8I6A4S8-1", "Exocyst complex component 3-like 2", "", "" ], [ "D3ZT68-1", "Early B-cell factor 2 (Predicted)", "", "" ], [ "D3ZT68-1", "EBF transcription factor 2", "", "" ], [ "D4AE81-1", "Pleckstrin homology and RhoGEF domain-containing G1", "", "" ], [ "D4AE82-1", "Transcription elongation regulator 1-like", "", "" ], [ "D4AE85-1", "Vasohibin 1", "", "" ], [ "D3ZPI2-1", "Proline-rich 27", "", "" ], [ "M0R657-1", "Spindlin-2-like", "", "" ], [ "D3ZH36-1", "Extracellular leucine-rich repeat and fibronectin type III domain-containing 2", "", "" ], [ "F1M348-1", "Transmembrane serine protease 12", "", "" ], [ "F1M344-1", "WD repeat domain 49", "", "" ], [ "A0A8I6ADY1-1", "Cystatin F", "", "" ], [ "A0A0G2JV12-1", "Collagen type XV alpha 1 chain", "", "" ], [ "A0A0G2JV12-1", "Procollagen, type XV, isoform CRA_a", "", "" ], [ "A0A0G2JV16-1", "Dedicator of cytokinesis 11", "", "" ], [ "A0A8I5ZSG2-1", "Metal response element-binding transcription factor 2", "", "" ], [ "A0A8I6ASL4-1", "Leucine rich repeat containing 28 (Predicted), isoform CRA_d", "", "" ], [ "A0A8I6ASL4-1", "Leucine-rich repeat-containing 28", "", "" ], [ "A0A8I6ASL2-1", "Similar to protein tyrosine phosphatase 4a2", "", "" ], [ "D3ZEJ9-1", "Similar to Protein Njmu-R1", "", "" ], [ "D3ZEJ2-1", "Mitochondrial calcium uniporter regulator 1", "", "" ], [ "D3ZEJ5-1", "Dual oxidase maturation factor 2", "", "" ], [ "D3ZEJ6-1", "Ankyrin repeat and SOCS box-containing 13 (Predicted), isoform CRA_b", "", "" ], [ "D3ZEJ6-1", "Ankyrin repeat and SOCS box-containing 13", "", "" ], [ "Q9R005-1", "Proliferin-related protein", "", "" ], [ "Q9R005-1", "Prolactin family 7, subfamily D, member 1", "", "" ], [ "D3ZN99-1", "Adhesion G protein-coupled receptor B2", "", "" ], [ "D3ZN99-1", "Brain-specific angiogenesis inhibitor 2 (Predicted)", "", "" ], [ "D3ZN93-1", "Nescient helix loop helix 1 (Predicted), isoform CRA_a", "", "" ], [ "D3ZN93-1", "Nescient helix loop helix 1", "", "" ], [ "A0A8I6AT34-1", "Family with sequence similarity 9, member B", "", "" ], [ "D4A2S8-1", "Sentrin-specific protease 5", "", "" ], [ "D4A2S9-1", "Claudin 34E", "", "" ], [ "D4A2S9-1", "RCG36285", "", "" ] ] }, "readme": "Name\n - Rat Protein Submitted Names (UniProtKB)\n\nVersion\n - v-2.0.3\n\nCreated on\n - 2020-03-15T13:43:53.106298\n\nModified on\n - 2022-09-26T09:05:27.753646\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/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-rattus-norvegicus.nt\n URI: /data/shared/glyds/downloads/ebi/2022_05/uniprot-proteome-rattus-norvegicus.nt\n Output Subdomain\n Name: rat_protein_submittednames.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_submittednames.csv\n Name: rat_protein_submittednames.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_submittednames.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"9007\"\n Name: \"submitted_name_full\"\n Description: \"The full submitted protein name in UniProtKB\"\n Unique Values: \"11929\"\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-2.0.3/reviewed/rat_protein_submittednames.csv" }