{ "bcoid": "GLY_000395", "title": "Human Protein Submitted Names (UniProtKB)", "description": "The Human Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for human [taxid:9606] ...", "filename": "human_protein_submittednames.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Protein Submitted Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "A0A1W2PQ27-1...", "SSU72 pseudo..." ], [ "A0A494C0I6-1...", "Uncharacteri..." ] ], "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" } ], [ "A0A1W2PQ27-1", "SSU72 pseudogene 7", "", "" ], [ "A0A494C0I6-1", "Uncharacterized protein", "", "" ], [ "G5EA27-1", "Transmembrane protein 223", "", "" ], [ "G5EA27-1", "HCG2039995, isoform CRA_a", "", "" ], [ "A0A075B7E8-1", "Immunoglobulin heavy variable 3/OR16-13 (non-functional)", "", "" ], [ "A0A494C086-1", "Speedy/RINGO cell cycle regulator family member E21, pseudogene", "", "" ], [ "A0A075B6Z8-1", "T cell receptor alpha joining 25 (non-functional)", "", "" ], [ "A0A075B6Z0-1", "T cell receptor alpha joining 22", "", "" ], [ "A0A075B6Z1-1", "T cell receptor alpha joining 20", "", "" ], [ "A0A075B6Z2-1", "T cell receptor alpha joining 56", "", "" ], [ "A0A075B6Z3-1", "T cell receptor alpha joining 6", "", "" ], [ "H3BQS4-1", "Cerebellar degeneration-related protein 2", "", "" ], [ "A0A0A0MTA3-1", "Immunoglobulin kappa joining 5", "", "" ], [ "A0A0A0MTA2-1", "T cell receptor beta joining 2-2P (non-functional)", "", "" ], [ "A0A2R8Y7D0-1", "TINCR ubiquitin domain-containing", "", "" ], [ "J3KRL7-1", "Period circadian protein homolog 1", "", "" ], [ "B0L653-1", "KIR2DL5", "", "" ], [ "B0L653-1", "Killer cell immunoglobulin-like receptor two domains long cytoplasmic tail 5", "", "" ], [ "B0L653-1", "KIR2DL5B", "", "" ], [ "A0A0G2JP03-1", "Uncharacterized protein", "", "" ], [ "A0A1B0GTB2-1", "TCL1 upstream neural differentiation-associated RNA", "", "" ], [ "A0A1B0GTB2-1", "HCG2038094, isoform CRA_a", "", "" ], [ "A0A1W2PQC6-1", "SSU72 pseudogene 4", "", "" ], [ "J3QLK7-1", "Oxysterol-binding protein-related protein 7", "", "" ], [ "A0A075B6Z4-1", "T cell receptor delta joining 4", "", "" ], [ "A0A0A0MTC1-1", "E3 ubiquitin-protein ligase RNF213", "", "" ], [ "A0A0A0MS68-1", "Growth arrest-specific protein 7", "", "" ], [ "A0A0G2JNQ3-1", "Heterogeneous nuclear ribonucleoprotein C-like 2", "", "" ], [ "A0A1Y8EKQ5-1", "Immunoglobulin heavy diversity 6-19", "", "" ], [ "A0A096LPH7-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PQL4-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PR75-1", "SSU72 pseudogene 8", "", "" ], [ "A0A0G2JKD1-1", "Mucin-21", "", "" ], [ "A0A075B6V6-1", "T cell receptor delta joining 2", "", "" ], [ "A0A087WWU0-1", "Uncharacterized protein", "", "" ], [ "A0A087WUV0-1", "Uncharacterized protein", "", "" ], [ "A0A0A6YYF3-1", "Protein GPR75-ASB3", "", "" ], [ "A0A0A0MS05-1", "T cell receptor beta variable 5-7 (non-functional)", "", "" ], [ "A0A0A0MS04-1", "T cell receptor beta variable 6-7 (non-functional)", "", "" ], [ "A0A0A0MS06-1", "T cell receptor beta variable 23-1 (non-functional)", "", "" ], [ "A0A0A0MS01-1", "T cell receptor gamma variable 10 (non-functional)", "", "" ], [ "A0A0A0MS00-1", "Immunoglobulin lambda variable 3-32 (non-functional)", "", "" ], [ "A0A2R9YJI8-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PPD8-1", "Lysine demethylase 4F", "", "" ], [ "A0A0G2JMM0-1", "Uncharacterized protein", "", "" ], [ "A0A140TA35-1", "Valine--tRNA ligase, mitochondrial", "", "" ], [ "A0A140TA35-1", "VARS2", "", "" ], [ "A0A087X1A0-1", "Probable palmitoyltransferase ZDHHC11B", "", "" ], [ "A0A0J9YW14-1", "Immunoglobulin heavy joining 3", "", "" ], [ "M0QYQ6-1", "F-box only protein 27", "", "" ], [ "X5D2U9-1", "HLA class II histocompatibility antigen, DR beta 4 chain", "", "" ], [ "X5D2U9-1", "MHC class II antigen", "", "" ], [ "G3V3W5-1", "Olfactory receptor 4N2", "", "" ], [ "A0A1W2PR64-1", "TATA-box-binding protein-associated factor 11-like 9", "", "" ], [ "E7EQD3-1", "Zinc finger protein 304", "", "" ], [ "A0A0A0MTG1-1", "Valine--tRNA ligase, mitochondrial", "", "" ], [ "A0A1W2PRN6-1", "HCG1807616", "", "" ], [ "A0A1W2PRN6-1", "Long intergenic non-protein coding RNA 2218", "", "" ], [ "A0A075B6W7-1", "T cell receptor alpha joining 38", "", "" ], [ "M0R134-1", "Transmembrane protein 59-like", "", "" ], [ "A0A075B714-1", "T cell receptor alpha joining 7", "", "" ], [ "K7EN02-1", "Troponin I, cardiac muscle", "", "" ], [ "G3V3Z8-1", "Protein numb homolog", "", "" ], [ "A0A2R8Y4Q1-1", "Olfactory receptor 7E24", "", "" ], [ "A0A0A0MS03-1", "T cell receptor beta variable 5-3 (non-functional)", "", "" ], [ "A0A2R8Y747-1", "Uncharacterized protein", "", "" ], [ "C9IYD2-1", "Nuclear pore complex-interacting protein family member B12", "", "" ], [ "A0A1W2PPH5-1", "TATA-box-binding protein-associated factor 11-like 13", "", "" ], [ "A0A3F2YNX1-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PQJ5-1", "SSU72 pseudogene 3", "", "" ], [ "S4R460-1", "Immunoglobulin heavy variable 3/OR16-9 (non-functional)", "", "" ], [ "A0A1B0GTJ6-1", "HCG1796489", "", "" ], [ "A0A0C4DH26-1", "Immunoglobulin kappa variable 6D-41 (non-functional)", "", "" ], [ "A0A0G2JLJ8-1", "Immunoglobulin heavy diversity 5/OR15-5A (non-functional)", "", "" ], [ "A0A0G2JLJ8-1", "Immunoglobulin heavy diversity 5/OR15-5B (non-functional)", "", "" ], [ "A0A140TA67-1", "Keratin-associated protein 9-6", "", "" ], [ "A0A2R8YD15-1", "Uncharacterized protein", "", "" ], [ "A0A0J9YXN1-1", "Immunoglobulin heavy diversity 3-10", "", "" ], [ "M0R177-1", "Delta-like protein 3", "", "" ], [ "A0A075B6W6-1", "T cell receptor alpha joining 27", "", "" ], [ "A0A2R8YE69-1", "Uncharacterized protein", "", "" ], [ "A0A494C1N4-1", "Uncharacterized protein", "", "" ], [ "A0A286YF18-1", "Uncharacterized protein", "", "" ], [ "A0A1B0GTH9-1", "Uncharacterized protein", "", "" ] ] }, "readme": "Name\n - Human Protein Submitted Names (UniProtKB)\n\nVersion\n - 1.7.13\n\nCreated on\n - 2020-03-15T13:38:29.540245\n\nModified on\n - 2020-04-10T11:49:36.985464\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@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 Human Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for human [taxid:9606] 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-homo-sapiens.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.13/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_submittednames.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_submittednames.csv\n Name: human_protein_submittednames.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_submittednames.stat.csv\n\nFields\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: \"1\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"349\"\n Name: \"submitted_name_short\"\n Description: \"The short submitted protein name in UniProtKB\"\n Unique Values: \"1\"\n Name: \"submitted_name_full\"\n Description: \"The full submitted protein name in UniProtKB\"\n Unique Values: \"284\"", "downloadurl": "/ln2data/releases/data/v-1.7.13/reviewed/human_protein_submittednames.csv" }