{ "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": [ [ "A0A0J9YW22-1...", "Immunoglobul..." ], [ "A0A6Q8PFQ6-1...", "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" } ], [ "A0A0J9YW22-1", "Immunoglobulin heavy diversity 3-9", "", "" ], [ "A0A6Q8PFQ6-1", "Uncharacterized protein", "", "" ], [ "A0A8V8TPP0-1", "Uncharacterized protein", "", "" ], [ "A0A494C071-1", "PWWP domain-containing 4", "", "" ], [ "A0A494BZU2-1", "BLACAT1 overlapping LEMD1 locus", "", "" ], [ "A0A1W2PQU2-1", "KANTR integral membrane protein", "", "" ], [ "A0A075B6U9-1", "T cell receptor alpha joining 2 (non-functional)", "", "" ], [ "A0A075B6U8-1", "T cell receptor alpha joining 12", "", "" ], [ "A0A075B6U7-1", "T cell receptor alpha joining 23", "", "" ], [ "A0A075B6U6-1", "T cell receptor alpha variable 8-7 (pseudogene)", "", "" ], [ "A0A8V8TPE2-1", "Family with sequence similarity 90 member A3, pseudogene", "", "" ], [ "A0A0U1RQB9-1", "Immunoglobulin heavy diversity 5-12", "", "" ], [ "B7Z3J9-1", "HCG2040265, isoform CRA_a", "", "" ], [ "B7Z3J9-1", "cDNA FLJ50015", "", "" ], [ "A0A804HJP8-1", "Uncharacterized protein", "", "" ], [ "A0A075B6Z8-1", "T cell receptor alpha joining 25 (non-functional)", "", "" ], [ "A0A075B6Z9-1", "T cell receptor alpha joining 24", "", "" ], [ "A0A075B6Z4-1", "T cell receptor delta joining 4", "", "" ], [ "A0A075B6Z5-1", "T cell receptor alpha joining 4", "", "" ], [ "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", "", "" ], [ "A0A5K1VDZ0-1", "KIR2DL1 protein", "", "" ], [ "A0A1B0GTJ6-1", "HCG1796489", "", "" ], [ "A0N4Z3-1", "HCG2039775", "", "" ], [ "A0N4Z3-1", "Possible J 14 gene", "", "" ], [ "A0N4Z3-1", "T cell receptor alpha joining 14", "", "" ], [ "A0A0J9YVP9-1", "Immunoglobulin heavy joining 5", "", "" ], [ "A0A7I2V4U8-1", "Uncharacterized protein", "", "" ], [ "A0A075B7B6-1", "Immunoglobulin heavy variable 4/OR15-8 (non-functional)", "", "" ], [ "A0A075B7B9-1", "Protein IGHD2OR15-2B", "", "" ], [ "A0A075B7B9-1", "Protein IGHD2OR15-2A", "", "" ], [ "A0A2R8YD15-1", "Uncharacterized protein", "", "" ], [ "A0A075B6W1-1", "T cell receptor delta joining 3", "", "" ], [ "A0A1B0GWH6-1", "Long intergenic non-protein coding RNA 672", "", "" ], [ "Q6JHZ5-1", "NS5ATP13TP1", "", "" ], [ "A0A6Q8PGZ7-1", "Uncharacterized protein", "", "" ], [ "A0A075B6Y8-1", "T cell receptor alpha joining 11", "", "" ], [ "A0A075B6Y1-1", "T cell receptor alpha joining 30", "", "" ], [ "A0A075B6Y2-1", "T cell receptor alpha joining 35 (non-functional)", "", "" ], [ "A0A075B6Y5-1", "T cell receptor alpha joining 47", "", "" ], [ "A0A075B6Y4-1", "T cell receptor alpha joining 19 (non-functional)", "", "" ], [ "A0A1B0GTE1-1", "Contactin-associated protein family member 3C", "", "" ], [ "A0A804HI29-1", "Uncharacterized protein", "", "" ], [ "A0A3B3IU46-1", "RNA guanine-7 methyltransferase-activating subunit-like (pseudogene)", "", "" ], [ "A0A0J9YVP2-1", "Immunoglobulin heavy joining 6", "", "" ], [ "A0A8V8TLD8-1", "Uncharacterized protein", "", "" ], [ "A0A0J9YWD0-1", "Immunoglobulin heavy diversity 3-3", "", "" ], [ "A0A096LPG2-1", "Uncharacterized protein", "", "" ], [ "A0A075B6X8-1", "T cell receptor alpha joining 44", "", "" ], [ "A0A075B6X9-1", "T cell receptor alpha joining 18", "", "" ], [ "A0A075B6X3-1", "T cell receptor alpha joining 32", "", "" ], [ "A0A075B6X0-1", "T cell receptor alpha joining 45", "", "" ], [ "A0A075B6X4-1", "T cell receptor alpha joining 28", "", "" ], [ "A0A8I5KY86-1", "Notch 2 N-terminal-like R (pseudogene)", "", "" ], [ "Q68DW6-1", "Uncharacterized protein DKFZp781C0719", "", "" ], [ "A0A140TA67-1", "Keratin-associated protein 9-6", "", "" ], [ "A0A0J9YVS3-1", "Immunoglobulin heavy joining 4", "", "" ], [ "A0A0J9YW14-1", "Immunoglobulin heavy joining 3", "", "" ], [ "A0A075B709-1", "T cell receptor alpha joining 13", "", "" ], [ "A0A0G2JNF4-1", "Killer cell immunoglobulin-like receptor, two Ig domains pseudogene 1", "", "" ], [ "A0A8V8TND5-1", "Uncharacterized protein", "", "" ], [ "Q9H3A6-1", "PRO2179", "", "" ], [ "A0A1Y8EI39-1", "Immunoglobulin heavy diversity 6-13", "", "" ], [ "A0A0J9YWN2-1", "Immunoglobulin heavy joining 2", "", "" ], [ "A0A0G2JN01-1", "Killer cell immunoglobulin-like receptor, three Ig domains pseudogene 1", "", "" ], [ "A0A6Q8PHS2-1", "Uncharacterized protein", "", "" ], [ "A0A5H1ZRR4-1", "T cell receptor gamma joining 2", "", "" ], [ "A0A669KAW2-1", "Uncharacterized protein", "", "" ], [ "A0A8I5QKY2-1", "Uncharacterized protein", "", "" ], [ "A0A087WZ39-1", "T cell receptor beta variable 15", "", "" ], [ "A0A024RCN7-1", "Chromosome 6 open reading frame 48, isoform CRA_a", "", "" ], [ "A0A024RCN7-1", "Small nucleolar RNA host gene 32", "", "" ], [ "V9GZ13-1", "Molecular chaperone MKKS", "", "" ], [ "A0A8V8TII8-1", "Uncharacterized protein", "", "" ], [ "A0A590UK10-1", "Rho guanine nucleotide exchange factor 18", "", "" ], [ "A0A0B4J1T7-1", "Lymphocyte antigen 6 family member G6E", "", "" ], [ "A0A8V8TLL3-1", "Uncharacterized protein", "", "" ], [ "A0A8I5QJV6-1", "Uncharacterized protein", "", "" ], [ "A2JGV3-1", "TCR gamma alternate reading frame protein", "", "" ], [ "A2JGV3-1", "TCRgamma alternate reading frame protein", "", "" ], [ "A0A8V8TLY5-1", "Uncharacterized protein", "", "" ], [ "A0A8V8TNB9-1", "Uncharacterized protein", "", "" ] ] }, "readme": "Name\n - Human Protein Submitted Names (UniProtKB)\n\nVersion\n - v-2.0.3\n\nCreated on\n - 2020-03-15T13:38:29.540245\n\nModified on\n - 2022-09-26T09:05:27.626904\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 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/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-homo-sapiens.nt\n URI: /data/shared/glyds/downloads/ebi/2022_05/uniprot-proteome-homo-sapiens.nt\n Output Subdomain\n Name: human_protein_submittednames.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_submittednames.csv\n Name: human_protein_submittednames.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_submittednames.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"181\"\n Name: \"submitted_name_full\"\n Description: \"The full submitted protein name in UniProtKB\"\n Unique Values: \"167\"\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: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.0.3/reviewed/human_protein_submittednames.csv" }