{ "bcoid": "GLY_000274", "title": "Human Phosphorylation Sites (UniProtKB)", "description": "The Human Phosphorylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions ...", "filename": "human_proteoform_phosphorylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Homo Sapiens", "molecule": "Proteoform", "tags": "Phosphorylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P00519-1...", "ABL1..." ], [ "P00519-1...", "ABL1..." ] ], "headers": [ "uniprotkb_ca...", "gene_symbol..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_symbol" }, { "type": "string", "label": "phosphorylated_residue" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "phosphorylation_site_uniprotkb" }, { "type": "string", "label": "protein_kinase" }, { "type": "string", "label": "data_source" }, { "type": "string", "label": "evidence" }, { "type": "string", "label": "eco_id" } ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "977", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "781", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "50", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "917", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine;", "Ser", "618", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine;", "Ser", "618", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine;", "Ser", "618", "PAK2", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "229", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "735", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "814", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "559", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphotyrosine", "Tyr", "253", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphotyrosine", "Tyr", "413", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "718", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "852", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphotyrosine", "Tyr", "257", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "446", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "683", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "844", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "620", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "855", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine;", "Ser", "619", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine;", "Ser", "619", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine;", "Ser", "619", "PAK2", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "751", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphothreonine", "Thr", "823", "", "", "", "" ], [ "P00519-1", "ABL1", "Phosphoserine", "Ser", "659", "", "", "", "" ], [ "P01009-1", "SERPINA1", "Phosphoserine", "Ser", "383", "", "", "", "" ], [ "P01009-1", "SERPINA1", "Phosphoserine;", "Ser", "38", "", "", "", "" ], [ "P01009-1", "SERPINA1", "Phosphoserine;", "Ser", "38", "", "", "", "" ], [ "P01009-1", "SERPINA1", "Phosphoserine;", "Ser", "38", "FAM20C", "", "", "" ], [ "O95477-1", "ABCA1", "Phosphoserine", "Ser", "1296", "", "", "", "" ], [ "P21399-1", "ACO1", "Phosphothreonine", "Thr", "628", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2270", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2283", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1774", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1863", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1395", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2125", "", "", "", "" ], [ "P25054-1", "APC", "Phosphothreonine", "Thr", "1438", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2674", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2473", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "744", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "987", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2789", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2129", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1864", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2260", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1360", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "107", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2569", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2130", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "780", "", "", "", "" ], [ "P25054-1", "APC", "Phosphothreonine", "Thr", "2679", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1371", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1971", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1385", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2088", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2535", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2710", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "908", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "111", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1042", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2132", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2093", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1038", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1973", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "748", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2724", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1392", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "2671", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1567", "", "", "", "" ], [ "P25054-1", "APC", "Phosphothreonine", "Thr", "2151", "", "", "", "" ], [ "P25054-1", "APC", "Phosphoserine", "Ser", "1861", "", "", "", "" ], [ "O96018-1", "APBA3", "Phosphoserine", "Ser", "11", "", "", "", "" ], [ "O96018-1", "APBA3", "Phosphoserine", "Ser", "171", "", "", "", "" ], [ "O96018-1", "APBA3", "Phosphoserine", "Ser", "372", "", "", "", "" ], [ "Q9NWB6-1", "ARGLU1", "Phosphoserine", "Ser", "266", "", "", "", "" ], [ "Q9NWB6-1", "ARGLU1", "Phosphoserine", "Ser", "60", "", "", "", "" ], [ "Q9NWB6-1", "ARGLU1", "Phosphothreonine", "Thr", "61", "", "", "", "" ], [ "Q9NWB6-1", "ARGLU1", "Phosphoserine", "Ser", "58", "", "", "", "" ], [ "Q9NWB6-1", "ARGLU1", "Phosphoserine", "Ser", "77", "", "", "", "" ], [ "Q9NWB6-1", "ARGLU1", "Phosphoserine", "Ser", "76", "", "", "", "" ], [ "P46379-1", "BAG6", "Phosphoserine", "Ser", "1081", "", "", "", "" ] ] }, "readme": "Name\n - Human Phosphorylation Sites (UniProtKB)\n\nVersion\n - 1.5.12\n\nCreated on\n - 2019-09-06T14:06:39.000407\n\nModified on\n - 2019-12-01T15:05:34.350651\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@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 Phosphorylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. 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 - phosphoryation Sites\n - ptm processing\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.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-1.5.12/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.12/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_proteoform_phosphorylation_sites_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.12/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv\n Name: human_proteoform_phosphorylation_sites_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.12/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"7962\"\n Name: \"data_source\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"phosphorylation_site_uniprotkb\"\n Description: \"\"\n Unique Values: \"2930\"\n Name: \"phosphorylated_residue\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"4\"\n Name: \"protein_kinase\"\n Description: \"\"\n Unique Values: \"323\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"1\"\n Name: \"gene_symbol\"\n Description: \"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\n Unique Values: \"7957\"\n Name: \"eco_id\"\n Description: \"\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.5.12/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv" }