{ "bcoid": "GLY_000681", "title": "Fruitfly Glycosylation Sites (UniProtKB)", "description": "The Fruitfly Glycosylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical ...", "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": [ "Drosophila melanogaster" ], "molecule": [ "Proteoform" ], "tag": [ "Glycosylation Sites" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q9VN14-1...", "604..." ], [ "Q0E961-1...", "627..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "src_xref_key" }, { "type": "string", "label": "src_xref_id" }, { "type": "string", "label": "uniprotkb_glycosylation_annotation_comment" }, { "type": "string", "label": "data_source" }, { "type": "string", "label": "eco_id" }, { "type": "string", "label": "uniprotkb_ftid" }, { "type": "string", "label": "carb_name" }, { "type": "string", "label": "glycosylation_subtype" }, { "type": "string", "label": "n_sequon" }, { "type": "string", "label": "n_sequon_type" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "start_aa" }, { "type": "string", "label": "end_aa" }, { "type": "string", "label": "site_seq" } ], [ "Q9VN14-1", "604", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VN14", "protein_xref_uniprotkb_gly", "Q9VN14", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NWT", "NXT", "604", "604", "Asn", "Asn", "N" ], [ "Q0E961-1", "627", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q0E961", "protein_xref_uniprotkb_gly", "Q0E961", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NAT", "NXT", "627", "627", "Asn", "Asn", "N" ], [ "Q0E961-1", "627", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q0E961", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NAT", "NXT", "627", "627", "Asn", "Asn", "N" ], [ "P25123-2", "58", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P25123", "protein_xref_uniprotkb_gly", "P25123", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "58", "58", "Asn", "Asn", "N" ], [ "Q9V3L1-1", "892", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9V3L1", "protein_xref_uniprotkb_gly", "Q9V3L1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYS", "NXS", "892", "892", "Asn", "Asn", "N" ], [ "Q7JQ32-1", "416", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7JQ32", "protein_xref_uniprotkb_gly", "Q7JQ32", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS", "416", "416", "Asn", "Asn", "N" ], [ "Q7JQ32-1", "416", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q7JQ32", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS", "416", "416", "Asn", "Asn", "N" ], [ "Q9VER6-1", "621", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VER6", "protein_xref_uniprotkb_gly", "Q9VER6", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NRS", "NXS", "621", "621", "Asn", "Asn", "N" ], [ "Q9VER6-1", "621", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9VER6", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NRS", "NXS", "621", "621", "Asn", "Asn", "N" ], [ "Q9W0R6-1", "165", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9W0R6", "protein_xref_uniprotkb_gly", "Q9W0R6", "N-linked (GlcNAc...) asparagine", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "", "NGT", "NXT", "165", "165", "Asn", "Asn", "N" ], [ "Q5BI42-1", "668", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q5BI42", "protein_xref_uniprotkb_gly", "Q5BI42", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "668", "668", "Asn", "Asn", "N" ], [ "Q8MUJ1-1", "226", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8MUJ1", "protein_xref_uniprotkb_gly", "Q8MUJ1", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NHT", "NXT", "226", "226", "Asn", "Asn", "N" ], [ "Q8MUJ1-1", "226", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q8MUJ1", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NHT", "NXT", "226", "226", "Asn", "Asn", "N" ], [ "Q9VEU1-1", "822", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VEU1", "protein_xref_uniprotkb_gly", "Q9VEU1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "822", "822", "Asn", "Asn", "N" ], [ "Q9NFP1-1", "120", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9NFP1", "protein_xref_uniprotkb_gly", "Q9NFP1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "120", "120", "Asn", "Asn", "N" ], [ "Q9VYZ1-1", "178", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VYZ1", "protein_xref_uniprotkb_gly", "Q9VYZ1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NMT", "NXT", "178", "178", "Asn", "Asn", "N" ], [ "B7TB45-1", "317", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "B7TB45", "protein_xref_uniprotkb_gly", "B7TB45", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "317", "317", "Asn", "Asn", "N" ], [ "B7TB45-1", "317", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "B7TB45", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "317", "317", "Asn", "Asn", "N" ], [ "O97394-1", "628", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O97394", "protein_xref_uniprotkb_gly", "O97394", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "628", "628", "Asn", "Asn", "N" ], [ "Q9VUN0-1", "111", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VUN0", "protein_xref_uniprotkb_gly", "Q9VUN0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS", "111", "111", "Asn", "Asn", "N" ], [ "Q9VUN0-1", "111", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9VUN0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS", "111", "111", "Asn", "Asn", "N" ], [ "Q7JQ32-1", "394", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7JQ32", "protein_xref_uniprotkb_gly", "Q7JQ32", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NRT", "NXT", "394", "394", "Asn", "Asn", "N" ], [ "Q7JQ32-1", "394", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q7JQ32", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NRT", "NXT", "394", "394", "Asn", "Asn", "N" ], [ "P54360-1", "379", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P54360", "protein_xref_uniprotkb_gly", "P54360", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "379", "379", "Asn", "Asn", "N" ], [ "P11584-1", "72", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P11584", "protein_xref_uniprotkb_gly", "P11584", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTS", "NXS", "72", "72", "Asn", "Asn", "N" ], [ "Q9VW60-1", "941", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VW60", "protein_xref_uniprotkb_gly", "Q9VW60", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFS", "NXS", "941", "941", "Asn", "Asn", "N" ], [ "Q9W192-1", "321", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9W192", "protein_xref_uniprotkb_gly", "Q9W192", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NLT", "NXT", "321", "321", "Asn", "Asn", "N" ], [ "Q9W192-1", "321", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9W192", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NLT", "NXT", "321", "321", "Asn", "Asn", "N" ], [ "Q9U4H5-1", "206", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9U4H5", "protein_xref_uniprotkb_gly", "Q9U4H5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "206", "206", "Asn", "Asn", "N" ], [ "Q9VJB6-1", "283", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VJB6", "protein_xref_uniprotkb_gly", "Q9VJB6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "283", "283", "Asn", "Asn", "N" ], [ "Q9VUN0-1", "174", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VUN0", "protein_xref_uniprotkb_gly", "Q9VUN0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NLT", "NXT", "174", "174", "Asn", "Asn", "N" ], [ "Q9VUN0-1", "174", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9VUN0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NLT", "NXT", "174", "174", "Asn", "Asn", "N" ], [ "B6VQA1-1", "133", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "B6VQA1", "protein_xref_uniprotkb_gly", "B6VQA1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "133", "133", "Asn", "Asn", "N" ], [ "O97394-1", "942", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O97394", "protein_xref_uniprotkb_gly", "O97394", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "942", "942", "Asn", "Asn", "N" ], [ "P16620-1", "85", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P16620", "protein_xref_uniprotkb_gly", "P16620", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDS", "NXS", "85", "85", "Asn", "Asn", "N" ], [ "Q0KHY3-3", "386", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q0KHY3", "protein_xref_uniprotkb_gly", "Q0KHY3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "386", "386", "Asn", "Asn", "N" ], [ "P24014-1", "1199", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P24014", "protein_xref_uniprotkb_gly", "P24014", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "1199", "1199", "Asn", "Asn", "N" ], [ "P10040-1", "1361", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P10040", "protein_xref_uniprotkb_gly", "P10040", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "1361", "1361", "Asn", "Asn", "N" ], [ "Q09147-1", "444", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q09147", "protein_xref_uniprotkb_gly", "Q09147", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NWT", "NXT", "444", "444", "Asn", "Asn", "N" ], [ "Q9VGG5-1", "1349", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VGG5", "protein_xref_uniprotkb_gly", "Q9VGG5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDT", "NXT", "1349", "1349", "Asn", "Asn", "N" ], [ "P18168-1", "1000", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P18168", "protein_xref_uniprotkb_gly", "P18168", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "1000", "1000", "Asn", "Asn", "N" ], [ "Q9VUY0-1", "221", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VUY0", "protein_xref_uniprotkb_gly", "Q9VUY0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "221", "221", "Asn", "Asn", "N" ], [ "P18168-1", "408", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P18168", "protein_xref_uniprotkb_gly", "P18168", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRT", "NXT", "408", "408", "Asn", "Asn", "N" ], [ "Q8T062-1", "916", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8T062", "protein_xref_uniprotkb_gly", "Q8T062", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NYT", "NXT", "916", "916", "Asn", "Asn", "N" ], [ "Q8T062-1", "916", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q8T062", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NYT", "NXT", "916", "916", "Asn", "Asn", "N" ], [ "Q9V4A7-1", "1307", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9V4A7", "protein_xref_uniprotkb_gly", "Q9V4A7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "1307", "1307", "Asn", "Asn", "N" ], [ "P08953-1", "508", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P08953", "protein_xref_uniprotkb_gly", "P08953", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NIS", "NXS", "508", "508", "Asn", "Asn", "N" ], [ "P08953-1", "508", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "4LXS", "protein_xref_uniprotkb_gly", "P08953", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NIS", "NXS", "508", "508", "Asn", "Asn", "N" ], [ "P08953-1", "508", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P08953", "protein_xref_uniprotkb_gly", "P08953", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NIS", "NXS", "508", "508", "Asn", "Asn", "N" ], [ "P08953-1", "508", "Asn", "", "N-linked", "protein_xref_pubmed", "24733933", "protein_xref_uniprotkb_gly", "P08953", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NIS", "NXS", "508", "508", "Asn", "Asn", "N" ], [ "P08953-1", "508", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "4LXR", "protein_xref_uniprotkb_gly", "P08953", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NIS", "NXS", "508", "508", "Asn", "Asn", "N" ], [ "M9NDE3-1", "2139", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "M9NDE3", "protein_xref_uniprotkb_gly", "M9NDE3", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "2139", "2139", "Asn", "Asn", "N" ], [ "M9NDE3-1", "2139", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "M9NDE3", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "2139", "2139", "Asn", "Asn", "N" ], [ "A6MHQ4-1", "449", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A6MHQ4", "protein_xref_uniprotkb_gly", "A6MHQ4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "449", "449", "Asn", "Asn", "N" ], [ "P09478-1", "233", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P09478", "protein_xref_uniprotkb_gly", "P09478", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "233", "233", "Asn", "Asn", "N" ], [ "Q7K4Y6-1", "188", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7K4Y6", "protein_xref_uniprotkb_gly", "Q7K4Y6", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NET", "NXT", "188", "188", "Asn", "Asn", "N" ], [ "Q7K4Y6-1", "188", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q7K4Y6", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NET", "NXT", "188", "188", "Asn", "Asn", "N" ], [ "P40795-1", "252", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P40795", "protein_xref_uniprotkb_gly", "P40795", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTT", "NXT", "252", "252", "Asn", "Asn", "N" ], [ "Q9W332-1", "2889", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9W332", "protein_xref_uniprotkb_gly", "Q9W332", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NVS", "NXS", "2889", "2889", "Asn", "Asn", "N" ], [ "Q9W332-1", "2889", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9W332", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NVS", "NXS", "2889", "2889", "Asn", "Asn", "N" ], [ "Q9VCR3-1", "244", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VCR3", "protein_xref_uniprotkb_gly", "Q9VCR3", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NRT", "NXT", "244", "244", "Asn", "Asn", "N" ], [ "Q9VCR3-1", "244", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9VCR3", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NRT", "NXT", "244", "244", "Asn", "Asn", "N" ], [ "P12024-1", "267", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P12024", "protein_xref_uniprotkb_gly", "P12024", "N-linked (GlcNAc...) (complex) asparagine; alternate", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NET", "NXT", "267", "267", "Asn", "Asn", "N" ], [ "P12024-1", "267", "Asn", "", "N-linked", "protein_xref_pubmed", "19415110", "protein_xref_uniprotkb_gly", "P12024", "N-linked (GlcNAc...) (complex) asparagine; alternate", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NET", "NXT", "267", "267", "Asn", "Asn", "N" ], [ "Q59DY6-1", "47", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q59DY6", "protein_xref_uniprotkb_gly", "Q59DY6", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NES", "NXS", "47", "47", "Asn", "Asn", "N" ], [ "Q59DY6-1", "47", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q59DY6", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NES", "NXS", "47", "47", "Asn", "Asn", "N" ], [ "Q9VB68-1", "270", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VB68", "protein_xref_uniprotkb_gly", "Q9VB68", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NGS", "NXS", "270", "270", "Asn", "Asn", "N" ], [ "Q9VB68-1", "270", "Asn", "", "N-linked", "protein_xref_pubmed", "21310954", "protein_xref_uniprotkb_gly", "Q9VB68", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NGS", "NXS", "270", "270", "Asn", "Asn", "N" ], [ "Q9VB68-1", "270", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VB68", "protein_xref_uniprotkb_gly", "Q9VB68", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NGS", "NXS", "270", "270", "Asn", "Asn", "N" ], [ "Q9VB68-1", "270", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "2XXL", "protein_xref_uniprotkb_gly", "Q9VB68", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NGS", "NXS", "270", "270", "Asn", "Asn", "N" ], [ "P16620-1", "162", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P16620", "protein_xref_uniprotkb_gly", "P16620", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "162", "162", "Asn", "Asn", "N" ], [ "Q9W4Y2-1", "137", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9W4Y2", "protein_xref_uniprotkb_gly", "Q9W4Y2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "137", "137", "Asn", "Asn", "N" ], [ "Q24292-1", "2967", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q24292", "protein_xref_uniprotkb_gly", "Q24292", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "2967", "2967", "Asn", "Asn", "N" ], [ "Q9V969-1", "290", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9V969", "protein_xref_uniprotkb_gly", "Q9V969", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "290", "290", "Asn", "Asn", "N" ], [ "Q9VTH0-1", "680", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VTH0", "protein_xref_uniprotkb_gly", "Q9VTH0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NCS", "NXS", "680", "680", "Asn", "Asn", "N" ], [ "Q9VTH0-1", "680", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9VTH0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NCS", "NXS", "680", "680", "Asn", "Asn", "N" ], [ "P25931-1", "49", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P25931", "protein_xref_uniprotkb_gly", "P25931", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTT", "NXT", "49", "49", "Asn", "Asn", "N" ], [ "P16620-1", "442", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P16620", "protein_xref_uniprotkb_gly", "P16620", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLS", "NXS", "442", "442", "Asn", "Asn", "N" ], [ "A0A0B4K6Z6-1", "53", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q0E9K4", "protein_xref_uniprotkb_gly", "Q0E9K4", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007829", "", "GlcNAc...", "", "NST", "NXT", "53", "53", "Asn", "Asn", "N" ], [ "A0A0B4K6Z6-1", "53", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "4X9F", "protein_xref_uniprotkb_gly", "Q0E9K4", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007829", "", "GlcNAc...", "", "NST", "NXT", "53", "53", "Asn", "Asn", "N" ], [ "Q9VTH0-1", "504", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9VTH0", "protein_xref_uniprotkb_gly", "Q9VTH0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "504", "504", "Asn", "Asn", "N" ], [ "Q9VTH0-1", "504", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q9VTH0", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "504", "504", "Asn", "Asn", "N" ], [ "P22270-1", "57", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P22270", "protein_xref_uniprotkb_gly", "P22270", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "57", "57", "Asn", "Asn", "N" ], [ "P28466-1", "528", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P28466", "protein_xref_uniprotkb_gly", "P28466", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDT", "NXT", "528", "528", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Fruitfly Glycosylation Sites (UniProtKB)\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2022-09-06T09:50:57.220135\n\nModified on\n - 2022-09-26T09:08:12.457590\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@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 Fruitfly Glycosylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. 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/glygener/glygen-backend-integration/blob/master/dataset-maker/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: glycosylation_subtype.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/misc/glycosylation_subtype.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/misc/n_sequon_info.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2023_07_13/cellosaurus.txt\n Name: uniprot-proteome-drosophila-melanogaster.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt\n Output Subdomain\n Name: fruitfly_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv\n Name: fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"524\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1151\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"3\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"1\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"5\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"606\"\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"545\"\n Name: \"uniprotkb_glycosylation_annotation_comment\"\n Description: \"The glycosylation annotation in UniProtKB that provides more context and description about the glycosylation event on a proein\"\n Unique Values: \"17\"\n Name: \"data_source\"\n Description: \"The source database for the data\"\n Unique Values: \"6\"\n Name: \"eco_id\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"9\"\n Name: \"uniprotkb_ftid\"\n Description: \"A stable feature identifier that allows to construct links directly from position-specific annotation to specialized protein-related databases. (In the dataset the FTID is for glycosylation for residues attached to an oligosaccharide structure annotated in the UniCarbKB database)\"\n Unique Values: \"1\"\n Name: \"carb_name\"\n Description: \"carbohydrate name\"\n Unique Values: \"6\"\n Name: \"glycosylation_subtype\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"41\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"5\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"1151\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"1151\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"3\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv" }