{ "bcoid": "GLY_000226", "title": "Rat Glycosylation Sites (RCSB PDB)", "description": "The Rat Glycosylation Sites (RCSB PDB) dataset contains rat [taxid:10116] UniProtKB canonical accessions ...", "filename": "rat_proteoform_glycosylation_sites_pdb.csv", "filetype": "csv", "categories": { "species": "Rattus Norvegicus", "molecule": "Protein", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q64610-1...", "5l0k..." ], [ "P97675-1...", "6f2t..." ] ], "headers": [ "uniprotkb_ca...", "pdb_id..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "pdb_id" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "amino_acid_chain" }, { "type": "string", "label": "glycosylation_site_pdb" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "amino_acid_uniprotkb" } ], [ "Q64610-1", "5l0k", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "P97675-1", "6f2t", "ASN", "N-Linked", "A", "237", "237", "Asn" ], [ "P97675-1", "6f2t", "ASN", "N-Linked", "A", "280", "280", "Asn" ], [ "P97675-1", "6f2t", "ASN", "N-Linked", "A", "289", "289", "Asn" ], [ "P97675-1", "6f2t", "ASN", "N-Linked", "A", "533", "533", "Asn" ], [ "P97675-1", "6f2t", "ASN", "N-Linked", "A", "789", "789", "Asn" ], [ "P97675-1", "6f2t", "ASN", "N-Linked", "B", "574", "574", "Asn" ], [ "Q00960-1", "6cna", "ASN", "N-Linked", "B", "74", "74", "Asn" ], [ "Q00960-1", "6cna", "ASN", "N-Linked", "B", "341", "341", "Asn" ], [ "Q00960-1", "6cna", "ASN", "N-Linked", "B", "688", "688", "Asn" ], [ "Q64610-1", "2xrg", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "P19493-1", "4gpa", "ASN", "N-Linked", "A", "35", "56", "Asn" ], [ "P19493-1", "4gpa", "ASN", "N-Linked", "A", "237", "258", "Asn" ], [ "P19493-1", "4gpa", "ASN", "N-Linked", "A", "350", "371", "Asn" ], [ "P18910-1", "1t34", "ASN", "N-Linked", "A", "13", "41", "Asn" ], [ "P18910-1", "1t34", "ASN", "N-Linked", "A", "395", "423", "Asn" ], [ "Q64610-1", "5l0b", "ASN", "N-Linked", "A", "410", "410", "Asn" ], [ "Q64610-1", "5l0b", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "Q64610-1", "5l0e", "ASN", "N-Linked", "A", "410", "410", "Asn" ], [ "Q64610-1", "5l0e", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "P35439-1", "4pe5", "ASN", "N-Linked", "A", "203", "203", "Asn" ], [ "P35439-1", "4pe5", "ASN", "N-Linked", "A", "276", "276", "Asn" ], [ "P35439-1", "4pe5", "ASN", "N-Linked", "A", "300", "300", "Asn" ], [ "P35439-1", "4pe5", "ASN", "N-Linked", "A", "368", "368", "Asn" ], [ "P35439-1", "4pe5", "ASN", "N-Linked", "A", "440", "440", "Asn" ], [ "Q00960-1", "4pe5", "ASN", "N-Linked", "B", "74", "74", "Asn" ], [ "Q00960-1", "4pe5", "ASN", "N-Linked", "B", "341", "341", "Asn" ], [ "Q00960-1", "4pe5", "ASN", "N-Linked", "B", "688", "688", "Asn" ], [ "P13599-1", "3fru", "ASN", "N-Linked", "A", "104", "126", "Asn" ], [ "P13599-1", "3fru", "ASN", "N-Linked", "A", "225", "247", "Asn" ], [ "P31422-1", "2e4y", "ASN", "N-Linked", "A", "209", "209", "Asn" ], [ "P31422-1", "2e4w", "ASN", "N-Linked", "A", "209", "209", "Asn" ], [ "P19491-1", "4u4f", "ASN", "N-Linked", "A", "355", "370", "Asn" ], [ "Q9QYP1-1", "3v64", "ASN", "N-Linked", "C", "498", "498", "Asn" ], [ "P19491-1", "3kg2", "ASN", "N-Linked", "A", "355", "370", "Asn" ], [ "P80067-1", "1jqp", "ASN", "N-Linked", "A", "5", "29", "Asn" ], [ "P80067-1", "1jqp", "ASN", "N-Linked", "A", "251", "275", "Asn" ], [ "Q00960-1", "3qel", "ASN", "N-Linked", "D", "341", "341", "Asn" ], [ "Q00960-1", "3qel", "ASN", "N-Linked", "D", "74", "74", "Asn" ], [ "Q63155-1", "5z5k", "ASN", "N-Linked", "A", "60", "60", "Asn" ], [ "Q63155-1", "5z5k", "ASN", "N-Linked", "A", "94", "94", "Asn" ], [ "Q63155-1", "5z5k", "ASN", "N-Linked", "A", "299", "299", "Asn" ], [ "Q63155-1", "5z5k", "ASN", "N-Linked", "A", "318", "318", "Asn" ], [ "P63182-1", "5kwr", "ASN", "N-Linked", "A", "79", "79", "Asn" ], [ "P08424-1", "5mlg", "ASN", "N-Linked", "A", "118", "139", "Asn" ], [ "P19490-1", "3saj", "ASN", "N-Linked", "C", "231", "249", "Asn" ], [ "P19490-1", "3saj", "ASN", "N-Linked", "D", "345", "363", "Asn" ], [ "P19490-1", "3saj", "ASN", "N-Linked", "D", "239", "257", "Asn" ], [ "P19490-1", "3saj", "ASN", "N-Linked", "A", "45", "63", "Asn" ], [ "Q64610-1", "5dlw", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "Q8CHN8-1", "5ckq", "ASN", "N-Linked", "A", "31", "54", "Asn" ], [ "Q64610-1", "5m0e", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "Q00960-1", "5tpz", "ASN", "N-Linked", "D", "341", "341", "Asn" ], [ "P24268-1", "5ux4", "ASN", "N-Linked", "A", "70", "134", "Asn" ], [ "P24268-1", "5ux4", "ASN", "N-Linked", "A", "194", "258", "Asn" ], [ "Q9JJS8-1", "5ckm", "ASN", "N-Linked", "A", "84", "103", "Asn" ], [ "Q64610-1", "5ijs", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "P19491-1", "4u2p", "ASN", "N-Linked", "A", "353", "370", "Asn" ], [ "Q07008-1", "4xl1", "SER", "O-Linked", "A", "458", "458", "Ser" ], [ "Q07008-1", "4xl1", "SER", "O-Linked", "A", "496", "496", "Ser" ], [ "Q07008-1", "4xl1", "SER", "O-Linked", "D", "435", "435", "Ser" ], [ "Q80WD1-1", "4p91", "ASN", "N-Linked", "A", "50", "50", "Asn" ], [ "Q80WD1-1", "4p91", "ASN", "N-Linked", "A", "93", "93", "Asn" ], [ "Q80WD1-1", "4p91", "ASN", "N-Linked", "A", "236", "236", "Asn" ], [ "P13635-1", "5n0k", "ASN", "N-Linked", "A", "377", "396", "Asn" ], [ "P31422-1", "2e4v", "ASN", "N-Linked", "A", "209", "209", "Asn" ], [ "P19491-1", "4u4g", "ASN", "N-Linked", "A", "355", "370", "Asn" ], [ "P29288-1", "1qhw", "ASN", "N-Linked", "A", "118", "118", "Asn" ], [ "P31422-1", "2e4x", "ASN", "N-Linked", "A", "209", "209", "Asn" ], [ "P14740-1", "2gbc", "ASN", "N-Linked", "A", "83", "83", "Asn" ], [ "P14740-1", "2gbc", "ASN", "N-Linked", "A", "90", "90", "Asn" ], [ "P14740-1", "2gbc", "ASN", "N-Linked", "A", "227", "227", "Asn" ], [ "P14740-1", "2gbc", "ASN", "N-Linked", "A", "319", "319", "Asn" ], [ "P14740-1", "2gbc", "ASN", "N-Linked", "A", "521", "521", "Asn" ], [ "Q9JJS8-1", "5cis", "ASN", "N-Linked", "A", "84", "103", "Asn" ], [ "Q07008-1", "4xlw", "SER", "O-Linked", "A", "435", "435", "Ser" ], [ "Q07008-1", "4xlw", "SER", "O-Linked", "A", "458", "458", "Ser" ], [ "Q07008-1", "4xlw", "SER", "O-Linked", "A", "496", "496", "Ser" ], [ "Q00960-1", "3jpw", "ASN", "N-Linked", "A", "74", "74", "Asn" ], [ "Q00960-1", "3jpw", "ASN", "N-Linked", "A", "341", "341", "Asn" ], [ "P97675-1", "6f33", "ASN", "N-Linked", "A", "237", "237", "Asn" ], [ "P97675-1", "6f33", "ASN", "N-Linked", "A", "280", "280", "Asn" ], [ "P97675-1", "6f33", "ASN", "N-Linked", "A", "289", "289", "Asn" ], [ "P97675-1", "6f33", "ASN", "N-Linked", "A", "533", "533", "Asn" ] ] }, "readme": "Name\n - Rat Glycosylation Sites (RCSB PDB)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-09-06T14:06:38.954510\n\nModified on\n - 2019-09-12T12:49:50.695438\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 - Jasmine Young [jasmine@rcsb.rutgers.edu], Chenghua Shao [chenghua@rcsb.rutgers.edu]\n\nChecksum\n - \n\nUsability Domain\n - The Rat Glycosylation Sites (RCSB PDB) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in RCSB PDB database. If you use this dataset please provide proper attribution to RCSB PDB and GlyGen\n\nDescription Domain\n Keywords\n - glycosylation\n - reported glycosylation\n - predicted glycosylation\n - UniProtKB\n - PubMed\n - Evidence and conclusion Ontology\n\n Pipeline Steps\n - Step-1: \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: pdblist.csv\n URI: https://data.glygen.org/ln2wwwdata/source/pdblist.csv\n Name: pdb_chain_uniprot_2018_11_8_11_44_50.csv\n URI: https://data.glygen.org/ln2wwwdata/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv\n Name: rat_protein_idmapping.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv\n Output Subdomain\n Name: rat_proteoform_glycosylation_sites_pdb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.csv\n Name: rat_proteoform_glycosylation_sites_pdb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.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: \"40\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"99\"\n Name: \"amino_acid_uniprotkb\"\n Description: \"Three letter abbreviation code of amino acid at glycosylation site on the protein sequence of UniProtKB entry\"\n Unique Values: \"2\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"2\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"glycosylation_site_pdb\"\n Description: \"\"\n Unique Values: \"106\"\n Name: \"pdb_id\"\n Description: \"4-character id assigned to each protein structure in Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB)\"\n Unique Values: \"104\"\n Name: \"amino_acid_chain\"\n Description: \"\"\n Unique Values: \"4\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/rat_proteoform_glycosylation_sites_pdb.csv" }