{ "bcoid": "GLY_000945", "title": "Pig Protein Submitted Names (UniProtKB)", "description": "The Pig Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Pig [taxid:9823] ...", "filename": "pig_protein_submittednames.csv", "filetype": "csv", "categories": { "species": [ "Sus scrofa" ], "molecule": [ "Protein" ], "tag": [ "Protein Submitted Names" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "A0A8W4F999-1...", "Uncharacteri..." ], [ "A0A287BN22-1...", "BTB domain c..." ] ], "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" } ], [ "A0A8W4F999-1", "Uncharacterized protein", "", "" ], [ "A0A287BN22-1", "BTB domain containing 10", "", "" ], [ "A0A287BN22-1", "BTB/POZ domain-containing protein 10 isoform 1", "", "" ], [ "A0A287BN27-1", "PABIR family member 2", "", "" ], [ "A0A5G2QDB0-1", "Uncharacterized protein", "", "" ], [ "A0A8W4FDQ3-1", "Uncharacterized protein", "", "" ], [ "I3LFU4-1", "Coiled-coil domain containing 14", "", "" ], [ "I3LFU3-1", "Uncharacterized protein", "", "" ], [ "A0A5G2QDB9-1", "Phospholipid phosphatase 5", "", "" ], [ "I3LQS2-1", "5', 3'-nucleotidase, cytosolic", "", "" ], [ "F1RTM0-1", "Complement C1q and tumor necrosis factor-related protein 9A", "", "" ], [ "I3L7Y8-1", "Zinc finger protein 76", "", "" ], [ "F1SUD0-1", "Neuropeptide FF receptor 1", "", "" ], [ "F1SUD5-1", "PHD finger protein 2", "", "" ], [ "F1SUD6-1", "Family with sequence similarity 120A", "", "" ], [ "I3LHP8-1", "Energy homeostasis associated", "", "" ], [ "A0A287BFE7-1", "Solute carrier family 35 member D2", "", "" ], [ "A0A286ZNE3-1", "Solute carrier family 30 member 10", "", "" ], [ "A0A286ZNE5-1", "Transmembrane protein 268", "", "" ], [ "A0A286ZNE4-1", "Sushi domain containing 5", "", "" ], [ "F1SKE6-1", "U2 snRNP-associated SURP motif-containing protein isoform X2", "", "" ], [ "F1SKE6-1", "U2 snRNP associated SURP domain containing", "", "" ], [ "F1SKE6-1", "U2 snRNP-associated SURP motif-containing protein isoform 1", "", "" ], [ "F1SKE7-1", "Procollagen C-endopeptidase enhancer 2", "", "" ], [ "A0A4X1UGW7-1", "B-cell linker protein", "", "" ], [ "A0A4X1UGW7-1", "B cell linker", "", "" ], [ "A0A8D1DGD3-1", "Small G protein signaling modulator 2", "", "" ], [ "C1JEX7-1", "Sperm associated antigen 6", "", "" ], [ "A0A5G2RGX7-1", "von Willebrand factor A domain containing 3A", "", "" ], [ "I3LGF1-1", "CD72 molecule", "", "" ], [ "A0A287BF73-1", "Potassium channel tetramerization domain containing 16", "", "" ], [ "A0A287BF73-1", "BTB/POZ domain-containing protein KCTD16 isoform X1", "", "" ], [ "A0A287BF71-1", "Tight junction protein 1", "", "" ], [ "A0A287BF79-1", "Phospholipid phosphatase related 3", "", "" ], [ "A0A287BF79-1", "Phospholipid phosphatase-related protein type 3 isoform 2", "", "" ], [ "F1SBQ0-1", "Protein phosphatase, Mg2+/Mn2+ dependent 1J", "", "" ], [ "A0A8W4FL22-1", "Uncharacterized protein", "", "" ], [ "A0A5G2QU61-1", "Transmembrane protein 262", "", "" ], [ "F1RU47-1", "Uncharacterized protein", "", "" ], [ "F1RU42-1", "Transmembrane protein 151A", "", "" ], [ "F6Q7B0-1", "Adaptor protein, phosphotyrosine interacting with PH domain and leucine zipper 2", "", "" ], [ "A0A5G2QTF4-1", "Uncharacterized protein", "", "" ], [ "A0A5G2QTF9-1", "Uncharacterized protein", "", "" ], [ "A0A5G2QTF8-1", "Uncharacterized protein", "", "" ], [ "A0A8W4FD47-1", "Exosome component 10", "", "" ], [ "A0A287A669-1", "Interferon regulatory factor 4", "", "" ], [ "A0A287A663-1", "Zinc finger AN1-type containing 3", "", "" ], [ "A0A286ZL52-1", "Purinergic receptor P2Y12", "", "" ], [ "A0A286ZL51-1", "Ribosomal protein L23a", "", "" ], [ "A0A286ZL58-1", "Monocyte to macrophage differentiation associated", "", "" ], [ "F1SEX4-1", "Telomerase RNA component interacting RNase", "", "" ], [ "F1SEX6-1", "F-box/WD repeat-containing protein 9", "", "" ], [ "F1SEX6-1", "F-box and WD repeat domain containing 9", "", "" ], [ "A0A5G2QNX5-1", "Desmocollin 3", "", "" ], [ "A0A8W4FFG9-1", "Uncharacterized protein", "", "" ], [ "A0A8W4FFG2-1", "PHD finger protein 20", "", "" ], [ "A0A8W4FFG3-1", "Uncharacterized protein", "", "" ], [ "A0A8W4FFG0-1", "Uncharacterized protein", "", "" ], [ "A0A287BMC4-1", "Phosphofurin acidic cluster sorting protein 1", "", "" ], [ "A0A287BMC7-1", "C1q and TNF related 1", "", "" ], [ "A0A8W4F8J9-1", "Tectonin beta-propeller repeat containing 2", "", "" ], [ "A0A287AUE2-1", "Crystallin beta-gamma domain containing 2", "", "" ], [ "A0A287AUE4-1", "Ubiquitin conjugating enzyme E2 K", "", "" ], [ "A0A480QFR5-1", "L3MBTL histone methyl-lysine binding protein 3", "", "" ], [ "A0A480QFR5-1", "Lethal(3)malignant brain tumor-like protein 3 isoform X2", "", "" ], [ "A0A287ATT0-1", "LEM domain nuclear envelope protein 2", "", "" ], [ "I3LMN2-1", "Methylcrotonyl-CoA carboxylase subunit 1", "", "" ], [ "A0A287BSN5-1", "Zinc finger protein 446", "", "" ], [ "A0A287BH18-1", "Zinc finger protein 649", "", "" ], [ "A0A287ALQ9-1", "Pleckstrin homology like domain family B member 3", "", "" ], [ "F1RQT0-1", "SAC3 domain containing 1", "", "" ], [ "F1S0J5-1", "Uncharacterized protein", "", "" ], [ "F1SJI0-1", "Espin like", "", "" ], [ "I3LTA5-1", "Glycoprotein VI platelet", "", "" ], [ "F1RUQ4-1", "Uncharacterized protein", "", "" ], [ "F1RUQ7-1", "Coiled-coil domain containing 3", "", "" ], [ "A0A480SN06-1", "Hes related family bHLH transcription factor with YRPW motif like", "", "" ], [ "A0A480SN06-1", "Hairy/enhancer-of-split related with YRPW motif-like protein", "", "" ], [ "A0A8D0VWI0-1", "Uncharacterized protein", "", "" ], [ "A0A5G2R463-1", "Uncharacterized protein", "", "" ], [ "F1S890-1", "Serine/threonine kinase 35", "", "" ], [ "F1S890-1", "Serine/threonine-protein kinase 35", "", "" ], [ "A0A8W4F819-1", "Uncharacterized protein", "", "" ], [ "A0A287A7A5-1", "Polycomb group ring finger 2", "", "" ] ] }, "readme": "Name\n - Pig Protein Submitted Names (UniProtKB)\n\nVersion\n - v-2.4.1\n\nCreated on\n - \n\nModified on\n - 2024-02-28T18:21:15\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu], Luke Johnson [luke.johnson@email.gwu.edu], Jingyue Wu [jingyue.wu@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 Pig Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for Pig [taxid:9823] 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-sus_scrofa.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-sus_scrofa.nt\n Output Subdomain\n Name: pig_protein_submittednames.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_submittednames.csv\n Name: pig_protein_submittednames.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_submittednames.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"11188\"\n Name: \"submitted_name_full\"\n Description: \"The full submitted protein name in UniProtKB\"\n Unique Values: \"12223\"\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: \"6\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/pig_protein_submittednames.csv" }