{ "bcoid": "GLY_000224", "title": "Rat Glycosylation Sites (UniProtKB)", "description": "", "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Rattus Norvegicus", "molecule": "Protein", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "D4A806-1...", "N-linked..." ], [ "Q66H49-1...", "N-linked..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "data_source" }, { "type": "string", "label": "evidence" }, { "type": "string", "label": "eco_id" }, { "type": "string", "label": "uniprotkb_ftid" } ], [ "D4A806-1", "N-linked", "GlcNAc...", "Asn", "83", "pirsr", "PIRSR038061-1", "ECO_0000256", "" ], [ "Q66H49-1", "N-linked", "GlcNAc...", "Asn", "357", "pirsr", "PIRSR038193-2", "ECO_0000256", "" ], [ "B2GUY2-1", "N-linked", "GlcNAc...", "Asn", "235", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "141", "", "", "", "" ], [ "O35757-1", "N-linked", "GlcNAc...", "Asn", "201", "", "", "", "" ], [ "P01830-1", "N-linked", "GlcNAc...", "Asn", "93", "PubMed", "6118137", "ECO_0000269", "" ], [ "P01830-1", "N-linked", "GlcNAc...", "Asn", "93", "PubMed", "24090084", "ECO_0000244", "" ], [ "P04774-1", "N-linked", "GlcNAc...", "Asn", "301", "", "", "", "" ], [ "P08932-1", "N-linked", "GlcNAc...", "Asn", "168", "", "", "", "" ], [ "P09875-1", "N-linked", "GlcNAc...", "Asn", "134", "", "", "", "" ], [ "P0CC10-1", "N-linked", "GlcNAc...", "Asn", "402", "PubMed", "24090084", "ECO_0000244", "" ], [ "P14562-1", "N-linked", "GlcNAc...", "Asn", "312", "", "", "", "" ], [ "P18292-1", "N-linked", "GlcNAc...", "Asn", "412", "", "", "", "" ], [ "P18331-1", "N-linked", "GlcNAc...", "Asn", "165", "", "", "", "" ], [ "P22831-1", "N-linked", "GlcNAc...", "Asn", "33", "", "", "", "" ], [ "P26260-1", "O-linked", "Xyl...", "Ser", "47", "", "", "", "" ], [ "P30680-1", "N-linked", "GlcNAc...", "Asn", "32", "", "", "", "" ], [ "P30836-1", "N-linked", "GlcNAc...", "Asn", "60", "", "", "", "" ], [ "P30937-1", "N-linked", "GlcNAc...", "Asn", "21", "", "", "", "" ], [ "P55146-1", "N-linked", "GlcNAc...", "Asn", "181", "", "", "", "" ], [ "P55205-1", "N-linked", "GlcNAc...", "Asn", "85", "", "", "", "" ], [ "P61943-1", "N-linked", "GlcNAc...", "Asn", "129", "", "", "", "" ], [ "P70628-1", "N-linked", "GlcNAc...", "Asn", "316", "", "", "", "" ], [ "P81828-1", "N-linked", "GlcNAc...", "Asn", "74", "", "", "", "" ], [ "P82450-1", "N-linked", "GlcNAc...", "Asn", "138", "", "", "", "" ], [ "P84903-1", "N-linked", "GlcNAc...", "Asn", "171", "", "", "", "" ], [ "P97708-1", "N-linked", "GlcNAc...", "Asn", "330", "PubMed", "16342937", "ECO_0000269", "" ], [ "Q05695-1", "N-linked", "GlcNAc...", "Asn", "489", "", "", "", "" ], [ "Q07977-1", "N-linked", "GlcNAc...", "Asn", "234", "", "", "", "" ], [ "Q5J3G9-1", "N-linked", "GlcNAc...", "Asn", "266", "", "", "", "" ], [ "Q5ZQU0-1", "N-linked", "GlcNAc...", "Asn", "408", "", "", "", "" ], [ "Q62666-1", "N-linked", "GlcNAc...", "Asn", "89", "", "", "", "" ], [ "Q62668-1", "N-linked", "GlcNAc...", "Asn", "742", "", "", "", "" ], [ "Q63548-1", "N-linked", "GlcNAc...", "Asn", "125", "", "", "", "" ], [ "Q641X3-1", "N-linked", "GlcNAc...", "Asn", "157", "", "", "", "" ], [ "Q642G2-1", "N-linked", "GlcNAc...", "Asn", "47", "", "", "", "" ], [ "Q64319-1", "N-linked", "GlcNAc...", "Asn", "329", "", "", "", "" ], [ "Q6IE46-1", "N-linked", "GlcNAc...", "Asn", "52", "", "", "", "" ], [ "Q6TXF5-1", "N-linked", "GlcNAc...", "Asn", "42", "", "", "", "" ], [ "Q6X782-1", "N-linked", "GlcNAc...", "Asn", "220", "", "", "", "" ], [ "Q700K0-1", "N-linked", "GlcNAc...", "Asn", "2035", "", "", "", "" ], [ "Q7TPF1-1", "O-linked", "GalNAc...", "Thr", "15", "", "", "", "" ], [ "Q8CH34-1", "N-linked", "GlcNAc...", "Asn", "50", "", "", "", "" ], [ "Q920H8-1", "N-linked", "GlcNAc...", "Asn", "236", "", "", "", "" ], [ "Q924A5-1", "N-linked", "GlcNAc...", "Asn", "173", "", "", "", "" ], [ "Q924V4-1", "N-linked", "GlcNAc...", "Asn", "223", "", "", "", "" ], [ "Q99P67-1", "N-linked", "GlcNAc...", "Asn", "53", "", "", "", "" ], [ "Q9ES58-1", "N-linked", "GlcNAc...", "Asn", "96", "", "", "", "" ], [ "Q9JHE5-1", "N-linked", "GlcNAc...", "Asn", "254", "", "", "", "" ], [ "Q9JLS4-1", "N-linked", "GlcNAc...", "Asn", "116", "", "", "", "" ], [ "Q9QYE2-1", "N-linked", "GlcNAc...", "Asn", "52", "", "", "", "" ], [ "Q9R103-1", "N-linked", "GlcNAc...", "Asn", "35", "", "", "", "" ], [ "Q9R1N3-1", "N-linked", "GlcNAc...", "Asn", "790", "", "", "", "" ], [ "Q9WUK5-1", "N-linked", "GlcNAc...", "Asn", "110", "", "", "", "" ], [ "Q9Z0M4-1", "N-linked", "GlcNAc...", "Asn", "179", "", "", "", "" ], [ "Q9Z2I6-1", "N-linked", "GlcNAc...", "Asn", "484", "", "", "", "" ], [ "A2VCW5-1", "N-linked", "GlcNAc...", "Asn", "236", "", "", "", "" ], [ "B0BMY1-1", "N-linked", "GlcNAc...", "Asn", "10", "", "", "", "" ], [ "B0BNK7-1", "N-linked", "GlcNAc...", "Asn", "348", "", "", "", "" ], [ "B0BNK7-1", "N-linked", "GlcNAc...", "Asn", "393", "", "", "", "" ], [ "B0BNK7-1", "N-linked", "GlcNAc...", "Asn", "339", "", "", "", "" ], [ "B2GUY2-1", "N-linked", "GlcNAc...", "Asn", "334", "", "", "", "" ], [ "B2GUY2-1", "N-linked", "GlcNAc...", "Asn", "535", "", "", "", "" ], [ "B3EY83-1", "N-linked", "GlcNAc...", "Asn", "172", "", "", "", "" ], [ "B3EY83-1", "N-linked", "GlcNAc...", "Asn", "143", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "54", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "123", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "27", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "496", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "476", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "60", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "165", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "603", "", "", "", "" ], [ "D3ZEH5-1", "N-linked", "GlcNAc...", "Asn", "572", "", "", "", "" ], [ "D4A1J9-1", "N-linked", "GlcNAc...", "Asn", "452", "", "", "", "" ], [ "D4A1J9-1", "N-linked", "GlcNAc...", "Asn", "339", "", "", "", "" ], [ "D4A6L0-1", "N-linked", "GlcNAc...", "Asn", "143", "", "", "", "" ], [ "D4A6L0-1", "N-linked", "GlcNAc...", "Asn", "333", "", "", "", "" ], [ "D4A6L0-1", "N-linked", "GlcNAc...", "Asn", "274", "", "", "", "" ], [ "D4A6L0-1", "N-linked", "GlcNAc...", "Asn", "98", "", "", "", "" ], [ "D4A6L0-1", "N-linked", "GlcNAc...", "Asn", "215", "", "", "", "" ], [ "D4A7K7-1", "N-linked", "GlcNAc...", "Asn", "4", "", "", "", "" ], [ "D4ABX8-1", "N-linked", "GlcNAc...", "Asn", "333", "", "", "", "" ], [ "D4ABX8-1", "N-linked", "GlcNAc...", "Asn", "25", "", "", "", "" ] ] }, "readme": "Name\n - Rat Glycosylation Sites (UniProtKB)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-09-06T14:06:38.952590\n\nModified on\n - 2019-09-11T17:24:53.636544\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\nDescription Domain\n\n Pipeline Steps\n - Step-1: The script loads the glycosylation 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-10116-rattus-norvegicus-2019-05.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt\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_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv\n Name: rat_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_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: \"2067\"\n Name: \"data_source\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1392\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"3\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"6\"\n Name: \"uniprotkb_ftid\"\n Description: \"\"\n Unique Values: \"6\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"151\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"14\"\n Name: \"eco_id\"\n Description: \"\"\n Unique Values: \"9\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv" }