{ "bcoid": "GLY_000330", "title": "Mouse Glycosylation Sites (GlyConnect) ", "description": "The Mouse Glycosylation Sites (GlyConnect) dataset contains mouse [taxid:10090] UniProtKB canonical accessions ...", "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q09163-1...", "N-Linked..." ], [ "Q09163-1...", "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": "evidence" }, { "type": "string", "label": "composition" }, { "type": "string", "label": "glyconnect_id" }, { "type": "string", "label": "is_composition_only" }, { "type": "string", "label": "glycan_core" }, { "type": "string", "label": "glyconnect_protein_id" }, { "type": "string", "label": "glytoucan_ac_composition" } ], [ "Q09163-1", "N-Linked", "G10995NB", "Asn", "100", "9118998", "Hex:5 HexNAc:4 dHex:1", "2352", "", "Complex", "153", "G23863VK" ], [ "Q09163-1", "N-Linked", "G17205DU", "Asn", "100", "9118998", "Hex:5 HexNAc:5 dHex:1", "971", "", "Complex", "153", "G91636VS" ], [ "Q09163-1", "N-Linked", "G03584KV", "Asn", "100", "9118998", "Hex:5 HexNAc:4 dHex:1 NeuAc:1", "1003", "", "Complex", "153", "G84452RH" ], [ "Q09163-1", "N-Linked", "G86503RS", "Asn", "100", "9118998", "Hex:6 HexNAc:5 dHex:1", "2712", "", "Complex", "153", "G72797UR" ], [ "Q09163-1", "N-Linked", "G58063ME", "Asn", "100", "9118998", "Hex:5 HexNAc:5 dHex:1 NeuAc:1", "816", "", "Complex", "153", "G02030ZB" ], [ "Q09163-1", "N-Linked", "G37626XQ", "Asn", "100", "9118998", "Hex:5 HexNAc:4 dHex:1 NeuAc:2", "3612", "", "Complex", "153", "G22310AV" ], [ "Q09163-1", "N-Linked", "G54422SY", "Asn", "100", "9118998", "Hex:6 HexNAc:5 dHex:1 NeuAc:1", "2071", "", "Complex", "153", "G81263BG" ], [ "Q09163-1", "N-Linked", "G58229BR", "Asn", "100", "9118998", "Hex:5 HexNAc:5 dHex:1 NeuAc:2", "630", "", "Complex", "153", "G91473PK" ], [ "Q09163-1", "N-Linked", "G64076LG", "Asn", "100", "9118998", "Hex:6 HexNAc:5 dHex:1 NeuAc:2", "3680", "", "Complex", "153", "G11629QQ" ], [ "Q09163-1", "O-Linked", "G96881BQ", "Thr", "224", "9118998", "dHex:1", "1898", "", "No-core", "153", "" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "248", "G49874UX" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "248", "G46687AB" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "248", "G46687AB" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "248", "G23863VK" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "251", "G49874UX" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "251", "G49874UX" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "251", "G49874UX" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "251", "G46687AB" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "251", "G46687AB" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "251", "G46687AB" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "251", "G46687AB" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "251", "G46687AB" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "251", "G46687AB" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "251", "G23863VK" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "251", "G23863VK" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "251", "G23863VK" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "252", "G49874UX" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "252", "G49874UX" ], [ "P01869-1", "N-Linked", "G80858MF", "Asn", "174", "2108149", "Hex:3 HexNAc:4 dHex:1", "2967", "", "Complex", "252", "G49874UX" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "252", "G46687AB" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "252", "G46687AB" ], [ "P01869-1", "N-Linked", "G58667NI", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "1819", "", "Complex", "252", "G46687AB" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "252", "G46687AB" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "252", "G46687AB" ], [ "P01869-1", "N-Linked", "G27919IH", "Asn", "174", "2108149", "Hex:4 HexNAc:4 dHex:1", "2198", "", "Complex", "252", "G46687AB" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "252", "G23863VK" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "252", "G23863VK" ], [ "P01869-1", "N-Linked", "G78059CC", "Asn", "174", "2108149", "Hex:5 HexNAc:4 dHex:1", "1860", "", "Complex", "252", "G23863VK" ], [ "Q05769-1", "N-Linked", "G21001NA", "Asn", "130", "11258925", "Hex:6 HexNAc:2", "474", "", "High-Mannose", "514", "G39188ZX" ], [ "Q05769-1", "N-Linked", "G74910CR", "Asn", "130", "11258925", "Hex:7 HexNAc:2", "263", "", "High-Mannose", "514", "G05724UK" ], [ "Q05769-1", "N-Linked", "G26335RK", "Asn", "130", "11258925", "Hex:8 HexNAc:2", "3114", "", "High-Mannose", "514", "G64527OM" ], [ "Q05769-1", "N-Linked", "G48712ZJ", "Asn", "130", "11258925", "Hex:9 HexNAc:2", "1539", "", "High-Mannose", "514", "G70101JE" ], [ "Q05769-1", "N-Linked", "G62768NK", "Asn", "130", "11258925", "Hex:10 HexNAc:2", "376", "", "High-Mannose", "514", "" ], [ "Q05769-1", "N-Linked", "G45841FE", "Asn", "396", "11258925", "Hex:5 HexNAc:2", "279", "", "High-Mannose", "514", "G06110VR" ], [ "Q05769-1", "N-Linked", "G21001NA", "Asn", "396", "11258925", "Hex:6 HexNAc:2", "474", "", "High-Mannose", "514", "G39188ZX" ], [ "Q05769-1", "N-Linked", "G74910CR", "Asn", "396", "11258925", "Hex:7 HexNAc:2", "263", "", "High-Mannose", "514", "G05724UK" ], [ "Q05769-1", "N-Linked", "G74910CR", "Asn", "53", "11258925", "Hex:7 HexNAc:2", "263", "", "High-Mannose", "514", "G05724UK" ], [ "Q05769-1", "N-Linked", "G74910CR", "Asn", "580", "11258925", "Hex:7 HexNAc:2", "263", "", "High-Mannose", "514", "G05724UK" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:5 HexNAc:2", "3115", "", "Undefined core", "556", "G06110VR" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:5 HexNAc:2", "3115", "", "Undefined core", "556", "G06110VR" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:8 HexNAc:2", "3206", "", "Undefined core", "556", "G64527OM" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:8 HexNAc:2", "3206", "", "Undefined core", "556", "G64527OM" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:3 HexNAc:6", "1218", "", "Undefined core", "556", "G14260UH" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:3 HexNAc:6", "1218", "", "Undefined core", "556", "G14260UH" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:5 HexNAc:4 dHex:1", "2287", "", "Undefined core", "556", "G23863VK" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:5 HexNAc:4 dHex:1", "2287", "", "Undefined core", "556", "G23863VK" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:9 HexNAc:2", "1710", "", "Undefined core", "556", "G70101JE" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:9 HexNAc:2", "1710", "", "Undefined core", "556", "G70101JE" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:4 HexNAc:6", "3379", "", "Undefined core", "556", "G48584BU" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "30899004", "Hex:4 HexNAc:6", "3379", "", "Undefined core", "556", "G48584BU" ], [ "Q921I1-1", "N-Linked", "G40608DF", "Asn", "513", "20571061", "Hex:5 HexNAc:4 NeuGc:2", "3649", "", "Complex", "556", "G15569GG" ], [ "Q921I1-1", "N-Linked", "G39397SW", "Asn", "513", "20571061", "Hex:5 HexNAc:4 dHex:1 NeuGc:2", "430", "", "Complex", "556", "G15488CF" ], [ "Q921I1-1", "N-Linked", "", "Asn", "513", "20571061", "Hex:5 HexNAc:4 NeuGc:3", "90", "", "Complex", "556", "G80269JV" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "1261", "30899004", "Hex:3 HexNAc:2 dHex:1", "1061", "", "Undefined core", "590", "G74724QE" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "1261", "30899004", "Hex:5 HexNAc:2", "3115", "", "Undefined core", "590", "G06110VR" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "1261", "30899004", "Hex:3 HexNAc:3 dHex:1", "836", "", "Undefined core", "590", "G94854LT" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "1261", "30899004", "Hex:6 HexNAc:2", "1530", "", "Undefined core", "590", "G39188ZX" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "1261", "30899004", "Hex:6 HexNAc:2 Ph:1", "8840", "", "Undefined core", "590", "G93180LE" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "1261", "30899004", "Hex:5 HexNAc:3 dHex:1", "1466", "", "Undefined core", "590", "G82119TF" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "278", "30899004", "Hex:3 HexNAc:2 dHex:1", "1061", "", "Undefined core", "590", "G74724QE" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "470", "30899004", "Hex:3 HexNAc:2 dHex:1", "1061", "", "Undefined core", "590", "G74724QE" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "470", "30899004", "Hex:3 HexNAc:3 dHex:1", "836", "", "Undefined core", "590", "G94854LT" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "470", "30899004", "Hex:3 HexNAc:6", "1218", "", "Undefined core", "590", "G14260UH" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "55", "30899004", "Hex:3 HexNAc:2 dHex:1", "1061", "", "Undefined core", "590", "G74724QE" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "55", "30899004", "Hex:8 HexNAc:2", "3206", "", "Undefined core", "590", "G64527OM" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "581", "30899004", "Hex:3 HexNAc:2 dHex:1", "1061", "", "Undefined core", "590", "G74724QE" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "581", "30899004", "Hex:4 HexNAc:2", "8630", "", "Undefined core", "590", "G66538GV" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "581", "30899004", "Hex:5 HexNAc:2", "3115", "", "Undefined core", "590", "G06110VR" ], [ "Q8BYI9-1", "N-Linked", "", "Asn", "581", "30899004", "Hex:5 HexNAc:3 dHex:1", "1466", "", "Undefined core", "590", "G82119TF" ], [ "Q01339-1", "N-Linked", "G39397SW", "Asn", "162", "20571061", "Hex:5 HexNAc:4 dHex:1 NeuGc:2", "430", "", "Complex", "652", "G15488CF" ], [ "P35441-1", "N-Linked", "G07508HQ", "Asn", "1067", "20571061", "Hex:5 HexNAc:4 dHex:2 NeuGc:2", "1793", "", "Complex", "667", "G36591UL" ], [ "Q61838-1", "N-Linked", "", "Asn", "1003", "20571061", "Hex:5 HexNAc:4 NeuAc:1 NeuGc:1", "3269", "", "Complex", "675", "G12579WK" ], [ "Q61838-1", "N-Linked", "G40608DF", "Asn", "1003", "20571061", "Hex:5 HexNAc:4 NeuGc:2", "3649", "", "Complex", "675", "G15569GG" ], [ "Q61838-1", "N-Linked", "G39397SW", "Asn", "1003", "20571061", "Hex:5 HexNAc:4 dHex:1 NeuGc:2", "430", "", "Complex", "675", "G15488CF" ] ] }, "readme": "Name\n - Mouse Glycosylation Sites (GlyConnect) \n\nVersion\n - 1.5.18\n\nCreated on\n - 2020-02-10T12:16:18.548585\n\nModified on\n - 2020-04-10T12:48:54.154665\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - Frederique Lisacek [frederique.lisacek@sib.swiss], Julien Mariethoz [julien.mariethoz@sib.swiss]\n\nChecksum\n - \n\nUsability Domain\n - The Mouse Glycosylation Sites (GlyConnect) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived directly from authors ( Frederique Lisacek; Julien Mariethoz) on 10/09/2019. If you use this dataset please provide proper attribution to GlyConnect and GlyGen.\n\nDescription Domain\n Keywords\n - glycosylation\n - reported glycosylation\n\n Pipeline Steps\n - Step-1: The script loads the glycosylation information from the input JSON file and extracts the data associated with Mouse [TaxID:10090] UniProtKB accessions. The QC checks filter out any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000007) and/or if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein.\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: glygen_2019_10_09_56_06.json\n URI: https://data.glygen.org/ln2wwwdata/source/glygen_2019_10_09_56_06.json\n Name: mouse_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv\n Name: mouse_protein_canonicalsequences.fasta\n URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta\n Output Subdomain\n Name: mouse_proteoform_glycosylation_sites_glyconnect.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv\n Name: mouse_proteoform_glycosylation_sites_glyconnect.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.stat.csv\n\nFields\n Name: \"glyconnect_id\"\n Description: \"entity Id from GlyConnect database\"\n Unique Values: \"153\"\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: \"712\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"801\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"2\"\n Name: \"glycan_core\"\n Description: \"Core of the associated glycan\"\n Unique Values: \"4\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"5\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"31\"\n Name: \"glyconnect_protein_id\"\n Description: \"Protein id from GlyConnect database\"\n Unique Values: \"718\"\n Name: \"is_composition_only\"\n Description: \"Yes when the associated GlytouCan accession is a composition accession only.\"\n Unique Values: \"1\"\n Name: \"glytoucan_ac_composition\"\n Description: \"Composition of the associated glycan from GlyConnect database\"\n Unique Values: \"127\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"135\"", "downloadurl": "/ln2data/releases/data/v-1.5.18/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv" }