{ "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": [ [ "A0A494C0I6-1...", "Uncharacteri..." ], [ "A0A075B7E8-1...", "Immunoglobul..." ] ], "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" } ], [ "A0A494C0I6-1", "Uncharacterized protein", "", "" ], [ "A0A075B7E8-1", "Immunoglobulin heavy variable 3/OR16-13 (non-functional)", "", "" ], [ "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", "", "" ], [ "A0A0A0MTA3-1", "Immunoglobulin kappa joining 5", "", "" ], [ "A0A0A0MTA2-1", "T cell receptor beta joining 2-2P (non-functional)", "", "" ], [ "A0A2R8Y7D0-1", "TINCR ubiquitin domain-containing", "", "" ], [ "A0A6Q8PHS2-1", "Uncharacterized protein", "", "" ], [ "A0A0G2JP03-1", "Uncharacterized protein", "", "" ], [ "A0A1B0GTB2-1", "TCL1 upstream neural differentiation-associated RNA", "", "" ], [ "A0A1B0GTB2-1", "HCG2038094, isoform CRA_a", "", "" ], [ "A0A075B6Z4-1", "T cell receptor delta joining 4", "", "" ], [ "A0A0G2JNQ3-1", "Heterogeneous nuclear ribonucleoprotein C-like 2", "", "" ], [ "A0A1Y8EKQ5-1", "Immunoglobulin heavy diversity 6-19", "", "" ], [ "A0A096LPH7-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PQL4-1", "Zinc finger protein 722, pseudogene", "", "" ], [ "A0A6I8PU40-1", "Taurine up-regulated 1", "", "" ], [ "A0A0G2JKD1-1", "Mucin-21", "", "" ], [ "A0A6Q8PFC9-1", "Uncharacterized protein", "", "" ], [ "A0A075B6V6-1", "T cell receptor delta joining 2", "", "" ], [ "A0A087WWU0-1", "Uncharacterized protein", "", "" ], [ "A0A087WUV0-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PPD8-1", "Lysine demethylase 4F", "", "" ], [ "A0A0G2JMM0-1", "Uncharacterized protein", "", "" ], [ "A0A0J9YW14-1", "Immunoglobulin heavy joining 3", "", "" ], [ "A0A2R8YCY7-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PR64-1", "TATA-box-binding protein-associated factor 11-like 9", "", "" ], [ "A0A1W2PRN6-1", "HCG1807616", "", "" ], [ "A0A1W2PRN6-1", "Long intergenic non-protein coding RNA 2218", "", "" ], [ "A0A075B6W7-1", "T cell receptor alpha joining 38", "", "" ], [ "A0A075B714-1", "T cell receptor alpha joining 7", "", "" ], [ "A0A2R8Y747-1", "Uncharacterized protein", "", "" ], [ "A0A1W2PPH5-1", "TATA-box-binding protein-associated factor 11-like 13", "", "" ], [ "A0A2R8Y4M2-1", "Diablo homolog, mitochondrial", "", "" ], [ "S4R460-1", "Immunoglobulin heavy variable 3/OR16-9 (non-functional)", "", "" ], [ "A0A1B0GTJ6-1", "HCG1796489", "", "" ], [ "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", "", "" ], [ "A0A191URJ7-1", "KIR2DL protein", "", "" ], [ "A0A191URJ7-1", "Killer cell immunoglobulin-like receptor two domains long cytoplasmic tail 1", "", "" ], [ "A0A5F9Z9Y6-1", "Killer cell immunoglobulin-like receptor 2DL2", "", "" ], [ "A0A075B6W6-1", "T cell receptor alpha joining 27", "", "" ], [ "A0A590UJ96-1", "Uncharacterized protein", "", "" ], [ "A0A2R8YE69-1", "Uncharacterized protein", "", "" ], [ "A0A286YF18-1", "Uncharacterized protein", "", "" ], [ "A0A1B0GTH9-1", "Uncharacterized protein", "", "" ], [ "A0N4Z8-1", "T cell receptor alpha joining 9", "", "" ], [ "A0N4Z8-1", "HCG2039779", "", "" ], [ "A0N4Z8-1", "Possible J 9 gene", "", "" ], [ "A0N4Z3-1", "HCG2039775", "", "" ], [ "A0N4Z3-1", "Possible J 14 gene", "", "" ], [ "A0N4Z3-1", "T cell receptor alpha joining 14", "", "" ], [ "A0A140T8X8-1", "Mucin-21", "", "" ], [ "A0A1W2PPE2-1", "TATA-box-binding protein-associated factor 11-like 4", "", "" ], [ "A0A075B6Z5-1", "T cell receptor alpha joining 4", "", "" ], [ "A0A5F9ZHS0-1", "Uncharacterized protein", "", "" ], [ "A0A075B6V3-1", "T cell receptor alpha joining 48", "", "" ], [ "A0A075B6V8-1", "T cell receptor alpha joining 5", "", "" ], [ "A0A075B6V9-1", "T cell receptor alpha joining 59 (non-functional)", "", "" ], [ "A0A075B734-1", "Uncharacterized protein", "", "" ], [ "A0A0B4J2B6-1", "Immunoglobulin heavy variable 2/OR16-5 (non-functional)", "", "" ], [ "A0A0B4J2B8-1", "Immunoglobulin heavy variable 1/OR15-9 (non-functional)", "", "" ], [ "A0A494C162-1", "Uncharacterized protein", "", "" ], [ "A0A0C4DH63-1", "T cell receptor gamma joining P", "", "" ], [ "A0A376A8Z9-1", "KIR2DS5 protein", "", "" ], [ "A0A0M3HER8-1", "Golgin subfamily A member 6-like protein 10", "", "" ], [ "A0A075B6X8-1", "T cell receptor alpha joining 44", "", "" ], [ "Q68DW6-1", "Uncharacterized protein DKFZp781C0719", "", "" ], [ "A0A075B7E0-1", "Protein IGHD3OR15-3A", "", "" ], [ "A0A075B7E0-1", "Protein IGHD3OR15-3B", "", "" ], [ "A0A075B6X4-1", "T cell receptor alpha joining 28", "", "" ], [ "A0A075B710-1", "T cell receptor alpha joining 39", "", "" ], [ "A0A075B711-1", "T cell receptor alpha joining 29", "", "" ], [ "A0A075B712-1", "T cell receptor alpha joining 54", "", "" ], [ "A0A6Q8PHR7-1", "Uncharacterized protein", "", "" ], [ "A0A075B6Z9-1", "T cell receptor alpha joining 24", "", "" ], [ "A0A6Q8PGL7-1", "Uncharacterized protein", "", "" ], [ "A0A0G2JN01-1", "Killer cell immunoglobulin-like receptor, three Ig domains pseudogene 1", "", "" ] ] }, "readme": "Name\n - Human Protein Submitted Names (UniProtKB)\n\nVersion\n - 1.8.24\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-1.8.24/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_submittednames.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_submittednames.csv\n Name: human_protein_submittednames.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_submittednames.stat.csv\n\nFields\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"119\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"119\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"120\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"49\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"118\"\n Name: \"publication_date\"\n Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n Unique Values: \"117\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"115\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.8.24/reviewed/human_protein_submittednames.csv" }