{ "bcoid": "GLY_000039", "title": "Mouse Glycosylation Sites (UniProtKB)", "description": "The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions ...", "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Mus Musculus", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P01738-1...", "N-linked..." ], [ "P01739-1...", "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" } ], [ "P01738-1", "N-linked", "GlcNAc...", "Asn", "90", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P01739-1", "N-linked", "GlcNAc...", "Asn", "42", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P36368-1", "N-linked", "GlcNAc...", "Asn", "102", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "1210", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "1041", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "699", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "1185", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "658", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "670", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P70206-1", "N-linked", "GlcNAc...", "Asn", "75", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "498", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "157", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "264", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "452", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "551", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "606", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q9Z0F8-1", "N-linked", "GlcNAc...", "Asn", "539", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P31750-1", "O-linked", "GlcNAc", "Ser", "126", "O-linked (GlcNAc) serine; alternate", "", "", "", "" ], [ "P31750-1", "O-linked", "GlcNAc", "Thr", "305", "O-linked (GlcNAc) threonine", "", "", "", "" ], [ "P31750-1", "O-linked", "GlcNAc", "Ser", "473", "O-linked (GlcNAc) serine; alternate", "", "", "", "" ], [ "P31750-1", "O-linked", "GlcNAc", "Ser", "129", "O-linked (GlcNAc) serine; alternate", "", "", "", "" ], [ "P31750-1", "O-linked", "GlcNAc", "Thr", "312", "O-linked (GlcNAc) threonine", "", "", "", "" ], [ "P07141-1", "N-linked", "GlcNAc...", "Asn", "172", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P07141-1", "N-linked", "GlcNAc...", "Asn", "107", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P07141-1", "N-linked", "GlcNAc...", "Asn", "154", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P54763-3", "N-linked", "GlcNAc...", "Asn", "428", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P54763-3", "N-linked", "GlcNAc...", "Asn", "336", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P54763-3", "N-linked", "GlcNAc...", "Asn", "265", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "623", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "444", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "175", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "528", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "603", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "568", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "352", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "196", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "413", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01279-1", "N-linked", "GlcNAc...", "Asn", "128", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q60629-1", "N-linked", "GlcNAc...", "Asn", "301", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q60629-1", "N-linked", "GlcNAc...", "Asn", "266", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P63141-1", "N-linked", "GlcNAc...", "Asn", "207", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q924X6-1", "N-linked", "GlcNAc...", "Asn", "805", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q924X6-1", "N-linked", "GlcNAc...", "Asn", "840", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q924X6-1", "N-linked", "GlcNAc...", "Asn", "551", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q924X6-1", "N-linked", "GlcNAc...", "Asn", "170", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "349", "O-linked (Fuc...) threonine", "", "", "", "" ], [ "Q01705-1", "O-linked", "GlcNAc", "Thr", "900", "O-linked (GlcNAc) threonine", "", "", "", "" ], [ "Q01705-1", "N-linked", "GlcNAc...", "Asn", "1587", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "1159", "O-linked (Fuc...) threonine", "", "", "", "" ], [ "Q01705-1", "N-linked", "GlcNAc...", "Asn", "959", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "232", "O-linked (Fuc...) threonine; alternate", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "692", "O-linked (Fuc...) threonine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc", "Ser", "921", "O-linked (Fuc) serine", "", "", "", "" ], [ "Q01705-1", "N-linked", "GlcNAc...", "Asn", "1241", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "311", "O-linked (Fuc...) threonine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "617", "O-linked (Fuc...) threonine", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "997", "O-linked (Fuc...) threonine", "", "", "", "" ], [ "Q01705-1", "N-linked", "GlcNAc...", "Asn", "888", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "GlcNAc...", "Thr", "1379", "O-linked (GlcNAc...) threonine", "", "", "", "" ], [ "Q01705-1", "N-linked", "GlcNAc...", "Asn", "1489", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "GlcNAc", "Ser", "784", "O-linked (GlcNAc) serine", "", "", "", "" ], [ "Q01705-1", "N-linked", "GlcNAc...", "Asn", "1179", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q01705-1", "O-linked", "GalNAc...", "Thr", "1402", "O-linked (GalNAc...) threonine; alternate", "", "", "", "" ], [ "Q01705-1", "O-linked", "Fuc...", "Thr", "1402", "O-linked (Fuc...) threonine; alternate", "", "", "", "" ], [ "Q6ZQE4-1", "N-linked", "GlcNAc...", "Asn", "123", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "68", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "80", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "86", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "47", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "124", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "51", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "104", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P18052-1", "N-linked", "GlcNAc...", "Asn", "21", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P83861-1", "N-linked", "GlcNAc...", "Asn", "19", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P83861-1", "N-linked", "GlcNAc...", "Asn", "5", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "O09009-1", "N-linked", "GlcNAc...", "Asn", "114", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P06281-1", "N-linked", "GlcNAc...", "Asn", "139", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P06281-1", "N-linked", "GlcNAc...", "Asn", "320", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P06281-1", "N-linked", "GlcNAc...", "Asn", "69", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q6PIX5-1", "N-linked", "GlcNAc...", "Asn", "584", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q7TQ33-1", "N-linked", "GlcNAc...", "Asn", "123", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q7TQ33-1", "N-linked", "GlcNAc...", "Asn", "386", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "Q8BUX5-1", "N-linked", "GlcNAc...", "Asn", "46", "N-linked (GlcNAc...) asparagine", "", "", "", "" ], [ "P35546-1", "N-linked", "GlcNAc...", "Asn", "556", "N-linked (GlcNAc...) asparagine", "", "", "", "" ] ] }, "readme": "Name\n - Mouse Glycosylation Sites (UniProtKB)\n\nVersion\n - 1.5.11\n\nCreated on\n - 2019-01-23T17:21:05.906744\n\nModified on\n - 2019-12-04T17:08:41.033470\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 Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] 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 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: 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-mus-musculus.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt\n Name: mouse_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv\n Output Subdomain\n Name: mouse_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv\n Name: mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_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: \"3795\"\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: \"1996\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"4\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"7\"\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: \"53\"\n Name: \"eco_id\"\n Description: \"\"\n Unique Values: \"11\"", "downloadurl": "/ln2data/releases/data/v-1.5.11/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv" }