{ "bcoid": "GLY_000224", "title": "Rat Glycosylation Sites (UniProtKB)", "description": "The Rat Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions ...", "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": [ [ "P07174-1...", "N-linked..." ], [ "P31652-1...", "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": "uniprotkb_glycosylation_annotation_comment" }, { "type": "string", "label": "data_source" }, { "type": "string", "label": "evidence" }, { "type": "string", "label": "eco_id" }, { "type": "string", "label": "uniprotkb_ftid" } ], [ "P07174-1", "N-linked", "GlcNAc...", "Asn", "61", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P31652-1", "N-linked", "GlcNAc...", "Asn", "217", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P31652-1", "N-linked", "GlcNAc...", "Asn", "208", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P08921-1", "N-linked", "GlcNAc...", "Asn", "134", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P10252-1", "N-linked", "GlcNAc...", "Asn", "38", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P10252-1", "N-linked", "GlcNAc...", "Asn", "186", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P10252-1", "N-linked", "GlcNAc...", "Asn", "203", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P10252-1", "N-linked", "GlcNAc...", "Asn", "97", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P19490-1", "N-linked", "GlcNAc...", "Asn", "363", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P19490-1", "N-linked", "GlcNAc...", "Asn", "257", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P19490-1", "N-linked", "GlcNAc...", "Asn", "249", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "546", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "432", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "82", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "53", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "299", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "690", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "601", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "90", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5EGZ1-1", "N-linked", "GlcNAc...", "Asn", "660", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q62962-1", "N-linked", "GlcNAc...", "Asn", "392", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q62962-1", "N-linked", "GlcNAc...", "Asn", "365", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q80W57-1", "N-linked", "GlcNAc...", "Asn", "596", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q80W57-1", "N-linked", "GlcNAc...", "Asn", "600", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P47866-1", "N-linked", "GlcNAc...", "Asn", "13", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "254", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "325", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "280", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "411", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "350", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "121", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "178", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "67", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "338", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q63604-1", "N-linked", "GlcNAc...", "Asn", "205", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q02563-1", "N-linked", "GlcNAc...", "Asn", "498", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q02563-1", "N-linked", "GlcNAc...", "Asn", "548", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q02563-1", "N-linked", "GlcNAc...", "Asn", "573", "N-linked (GlcNAc...) asparagine; alternate", "", "", "", "" ], [ "O35303-1", "O-linked", "GlcNAc", "Thr", "605", "O-linked (GlcNAc) threonine", "", "", "", "" ], [ "O35303-1", "O-linked", "GlcNAc", "Thr", "604", "O-linked (GlcNAc) threonine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "382", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "158", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "292", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "362", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "101", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "389", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "329", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P84039-1", "N-linked", "GlcNAc...", "Asn", "369", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P17438-1", "N-linked", "GlcNAc...", "Asn", "229", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P35053-1", "N-linked", "GlcNAc...", "Asn", "116", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P35053-1", "N-linked", "GlcNAc...", "Asn", "79", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q66H49-1", "N-linked", "GlcNAc...", "Asn", "357", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P37199-1", "O-linked", "GlcNAc", "Ser", "525", "O-linked (GlcNAc) serine", "", "", "", "" ], [ "Q5BJT4-1", "N-linked", "GlcNAc...", "Asn", "276", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5BJT4-1", "N-linked", "GlcNAc...", "Asn", "177", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5BJT4-1", "N-linked", "GlcNAc...", "Asn", "189", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q5BJT4-1", "N-linked", "GlcNAc...", "Asn", "170", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q64232-1", "N-linked", "GlcNAc...", "Asn", "247", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q64232-1", "N-linked", "GlcNAc...", "Asn", "164", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q80ZA5-1", "N-linked", "GlcNAc...", "Asn", "696", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q80ZA5-1", "N-linked", "GlcNAc...", "Asn", "686", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q80ZA5-1", "N-linked", "GlcNAc...", "Asn", "676", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q62674-1", "N-linked", "GlcNAc...", "Asn", "643", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q62674-1", "N-linked", "GlcNAc...", "Asn", "605", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q8R2H2-1", "N-linked", "GlcNAc...", "Asn", "477", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q8R2H2-1", "N-linked", "GlcNAc...", "Asn", "345", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q8R2H2-1", "N-linked", "GlcNAc...", "Asn", "584", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q8R2H2-1", "N-linked", "GlcNAc...", "Asn", "396", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q8R2H2-1", "N-linked", "GlcNAc...", "Asn", "679", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70352-1", "N-linked", "GlcNAc...", "Asn", "197", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70352-1", "N-linked", "GlcNAc...", "Asn", "166", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70352-1", "N-linked", "GlcNAc...", "Asn", "131", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70352-1", "N-linked", "GlcNAc...", "Asn", "127", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P07725-1", "O-linked", "GalNAc...", "Thr", "144", "O-linked (GalNAc...) threonine; partial", "", "", "", "" ], [ "P07725-1", "N-linked", "GlcNAc...", "Asn", "63", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P07725-1", "O-linked", "GalNAc...", "Thr", "148", "O-linked (GalNAc...) threonine", "", "", "", "" ], [ "P07725-1", "O-linked", "GalNAc...", "Thr", "158", "O-linked (GalNAc...) threonine", "", "", "", "" ], [ "P07725-1", "O-linked", "GalNAc...", "Thr", "152", "O-linked (GalNAc...) threonine", "", "", "", "" ], [ "P07725-1", "O-linked", "GalNAc...", "Thr", "160", "O-linked (GalNAc...) threonine", "", "", "", "" ], [ "Q4V7F2-1", "N-linked", "GlcNAc...", "Asn", "205", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70244-1", "N-linked", "GlcNAc...", "Asn", "711", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70244-1", "N-linked", "GlcNAc...", "Asn", "781", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70244-1", "N-linked", "GlcNAc...", "Asn", "857", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O70244-1", "N-linked", "GlcNAc...", "Asn", "749", "N-linked (GlcNAc...) asparagine", "", "", "", "" ] ] }, "readme": "Name\n - Rat Glycosylation Sites (UniProtKB)\n\nVersion\n - 1.5.12\n\nCreated on\n - 2019-09-06T14:06:38.952590\n\nModified on\n - 2019-12-04T17:09:19.549493\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 Rat Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites 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\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-rattus-norvegicus.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.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: \"2085\"\n Name: \"data_source\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1424\"\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: \"1\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"1\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"13\"\n Name: \"uniprotkb_glycosylation_annotation_comment\"\n Description: \"\"\n Unique Values: \"47\"\n Name: \"eco_id\"\n Description: \"\"\n Unique Values: \"7\"", "downloadurl": "/ln2data/releases/data/v-1.5.12/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv" }