{ "bcoid": "GLY_000827", "title": "Dictyostelium Glycosylation Sites (UniProtKB)", "description": "The Dictyostelium Glycosylation Sites (UniProtKB) dataset contains dictyostelium [taxid:44689] UniProtKB ...", "filename": "dicty_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": [ "Dictyostelium discoideum" ], "molecule": [ "Proteoform" ], "tag": [ "Glycosylation Sites" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q54YF7-1...", "503..." ], [ "Q54YF7-1...", "30..." ] ], "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" } ], [ "Q54YF7-1", "503", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54YF7", "protein_xref_uniprotkb_gly", "Q54YF7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "503", "503", "Asn", "Asn", "N" ], [ "Q54YF7-1", "30", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54YF7", "protein_xref_uniprotkb_gly", "Q54YF7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "30", "30", "Asn", "Asn", "N" ], [ "Q54RE1-1", "352", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54RE1", "protein_xref_uniprotkb_gly", "Q54RE1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "352", "352", "Asn", "Asn", "N" ], [ "Q55GI8-1", "32", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55GI8", "protein_xref_uniprotkb_gly", "Q55GI8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "32", "32", "Asn", "Asn", "N" ], [ "Q54K56-1", "551", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54K56", "protein_xref_uniprotkb_gly", "Q54K56", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "551", "551", "Asn", "Asn", "N" ], [ "Q54SB5-1", "299", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54SB5", "protein_xref_uniprotkb_gly", "Q54SB5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "299", "299", "Asn", "Asn", "N" ], [ "P12019-1", "141", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P12019", "protein_xref_uniprotkb_gly", "P12019", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "141", "141", "Asn", "Asn", "N" ], [ "Q54C16-1", "523", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54C16", "protein_xref_uniprotkb_gly", "Q54C16", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "523", "523", "Asn", "Asn", "N" ], [ "Q54C16-1", "523", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00415", "protein_xref_uniprotkb_gly", "Q54C16", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "523", "523", "Asn", "Asn", "N" ], [ "Q54P69-1", "537", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54P69", "protein_xref_uniprotkb_gly", "Q54P69", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "537", "537", "Asn", "Asn", "N" ], [ "Q06885-1", "410", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q06885", "protein_xref_uniprotkb_gly", "Q06885", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTT", "NXT", "410", "410", "Asn", "Asn", "N" ], [ "Q86H13-1", "119", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q86H13", "protein_xref_uniprotkb_gly", "Q86H13", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "119", "119", "Asn", "Asn", "N" ], [ "Q54QG7-1", "363", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54QG7", "protein_xref_uniprotkb_gly", "Q54QG7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDT", "NXT", "363", "363", "Asn", "Asn", "N" ], [ "Q54K71-1", "119", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54K71", "protein_xref_uniprotkb_gly", "Q54K71", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NCS", "NXS", "119", "119", "Asn", "Asn", "N" ], [ "Q54YF7-1", "63", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54YF7", "protein_xref_uniprotkb_gly", "Q54YF7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "63", "63", "Asn", "Asn", "N" ], [ "Q54T74-1", "771", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54T74", "protein_xref_uniprotkb_gly", "Q54T74", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NQS", "NXS", "771", "771", "Asn", "Asn", "N" ], [ "Q556N7-1", "57", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q556N7", "protein_xref_uniprotkb_gly", "Q556N7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAT", "NXT", "57", "57", "Asn", "Asn", "N" ], [ "Q557E9-1", "429", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q557E9", "protein_xref_uniprotkb_gly", "Q557E9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "429", "429", "Asn", "Asn", "N" ], [ "Q54JA3-1", "1620", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54JA3", "protein_xref_uniprotkb_gly", "Q54JA3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTT", "NXT", "1620", "1620", "Asn", "Asn", "N" ], [ "Q54MV6-1", "385", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54MV6", "protein_xref_uniprotkb_gly", "Q54MV6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLS", "NXS", "385", "385", "Asn", "Asn", "N" ], [ "Q55FQ5-1", "47", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55FQ5", "protein_xref_uniprotkb_gly", "Q55FQ5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "47", "47", "Asn", "Asn", "N" ], [ "Q54MV6-1", "39", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54MV6", "protein_xref_uniprotkb_gly", "Q54MV6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "39", "39", "Asn", "Asn", "N" ], [ "Q55FL1-1", "31", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55FL1", "protein_xref_uniprotkb_gly", "Q55FL1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "31", "31", "Asn", "Asn", "N" ], [ "Q8T869-1", "611", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8T869", "protein_xref_uniprotkb_gly", "Q8T869", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "611", "611", "Asn", "Asn", "N" ], [ "Q55FE6-1", "288", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55FE6", "protein_xref_uniprotkb_gly", "Q55FE6", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007829", "", "GlcNAc...", "", "NTS", "NXS", "288", "288", "Asn", "Asn", "N" ], [ "Q55FE6-1", "288", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "4ZZQ", "protein_xref_uniprotkb_gly", "Q55FE6", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007829", "", "GlcNAc...", "", "NTS", "NXS", "288", "288", "Asn", "Asn", "N" ], [ "Q23911-1", "129", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q23911", "protein_xref_uniprotkb_gly", "Q23911", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "129", "129", "Asn", "Asn", "N" ], [ "Q9BKJ9-1", "28", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9BKJ9", "protein_xref_uniprotkb_gly", "Q9BKJ9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRT", "NXT", "28", "28", "Asn", "Asn", "N" ], [ "Q54PF8-1", "4", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54PF8", "protein_xref_uniprotkb_gly", "Q54PF8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NKS", "NXS", "4", "4", "Asn", "Asn", "N" ], [ "Q54RJ4-1", "161", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54RJ4", "protein_xref_uniprotkb_gly", "Q54RJ4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNT", "NXT", "161", "161", "Asn", "Asn", "N" ], [ "Q54NU3-1", "47", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54NU3", "protein_xref_uniprotkb_gly", "Q54NU3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "47", "47", "Asn", "Asn", "N" ], [ "Q554H5-1", "107", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q554H5", "protein_xref_uniprotkb_gly", "Q554H5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYS", "NXS", "107", "107", "Asn", "Asn", "N" ], [ "Q55AP8-1", "64", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55AP8", "protein_xref_uniprotkb_gly", "Q55AP8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "64", "64", "Asn", "Asn", "N" ], [ "Q94503-1", "305", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q94503", "protein_xref_uniprotkb_gly", "Q94503", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NWS", "NXS", "305", "305", "Asn", "Asn", "N" ], [ "Q54MI3-1", "994", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54MI3", "protein_xref_uniprotkb_gly", "Q54MI3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFS", "NXS", "994", "994", "Asn", "Asn", "N" ], [ "P13723-1", "79", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P13723", "protein_xref_uniprotkb_gly", "P13723", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "79", "79", "Asn", "Asn", "N" ], [ "Q54K56-1", "303", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54K56", "protein_xref_uniprotkb_gly", "Q54K56", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFS", "NXS", "303", "303", "Asn", "Asn", "N" ], [ "Q54CU4-1", "10379", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54CU4", "protein_xref_uniprotkb_gly", "Q54CU4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "10379", "10379", "Asn", "Asn", "N" ], [ "Q54L75-1", "356", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54L75", "protein_xref_uniprotkb_gly", "Q54L75", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVS", "NXS", "356", "356", "Asn", "Asn", "N" ], [ "Q54L75-1", "781", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54L75", "protein_xref_uniprotkb_gly", "Q54L75", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "781", "781", "Asn", "Asn", "N" ], [ "Q557E9-1", "212", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q557E9", "protein_xref_uniprotkb_gly", "Q557E9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NKT", "NXT", "212", "212", "Asn", "Asn", "N" ], [ "Q554K2-1", "209", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q554K2", "protein_xref_uniprotkb_gly", "Q554K2", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "209", "209", "Asn", "Asn", "N" ], [ "Q554K2-1", "209", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00415", "protein_xref_uniprotkb_gly", "Q554K2", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NTT", "NXT", "209", "209", "Asn", "Asn", "N" ], [ "Q54CU4-1", "9839", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54CU4", "protein_xref_uniprotkb_gly", "Q54CU4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNT", "NXT", "9839", "9839", "Asn", "Asn", "N" ], [ "Q54PF8-1", "184", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54PF8", "protein_xref_uniprotkb_gly", "Q54PF8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDS", "NXS", "184", "184", "Asn", "Asn", "N" ], [ "Q9NA13-1", "2392", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9NA13", "protein_xref_uniprotkb_gly", "Q9NA13", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "2392", "2392", "Asn", "Asn", "N" ], [ "P34115-1", "392", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P34115", "protein_xref_uniprotkb_gly", "P34115", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "392", "392", "Asn", "Asn", "N" ], [ "Q55AP8-1", "397", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55AP8", "protein_xref_uniprotkb_gly", "Q55AP8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "397", "397", "Asn", "Asn", "N" ], [ "Q54CM0-1", "195", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54CM0", "protein_xref_uniprotkb_gly", "Q54CM0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "195", "195", "Asn", "Asn", "N" ], [ "Q1ZXE4-1", "144", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q1ZXE4", "protein_xref_uniprotkb_gly", "Q1ZXE4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q54K55-1", "69", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54K55", "protein_xref_uniprotkb_gly", "Q54K55", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFT", "NXT", "69", "69", "Asn", "Asn", "N" ], [ "Q8T2Q0-1", "565", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8T2Q0", "protein_xref_uniprotkb_gly", "Q8T2Q0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "565", "565", "Asn", "Asn", "N" ], [ "Q54CU4-1", "3339", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54CU4", "protein_xref_uniprotkb_gly", "Q54CU4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "3339", "3339", "Asn", "Asn", "N" ], [ "Q54RJ4-1", "870", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54RJ4", "protein_xref_uniprotkb_gly", "Q54RJ4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "870", "870", "Asn", "Asn", "N" ], [ "Q54K11-1", "837", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54K11", "protein_xref_uniprotkb_gly", "Q54K11", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "837", "837", "Asn", "Asn", "N" ], [ "Q54VS4-1", "554", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54VS4", "protein_xref_uniprotkb_gly", "Q54VS4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "554", "554", "Asn", "Asn", "N" ], [ "Q54HW8-1", "212", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54HW8", "protein_xref_uniprotkb_gly", "Q54HW8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "212", "212", "Asn", "Asn", "N" ], [ "Q54T74-1", "59", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54T74", "protein_xref_uniprotkb_gly", "Q54T74", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "59", "59", "Asn", "Asn", "N" ], [ "Q54L75-1", "706", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54L75", "protein_xref_uniprotkb_gly", "Q54L75", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "706", "706", "Asn", "Asn", "N" ], [ "Q55CY2-1", "140", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55CY2", "protein_xref_uniprotkb_gly", "Q55CY2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDT", "NXT", "140", "140", "Asn", "Asn", "N" ], [ "Q557B8-1", "512", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q557B8", "protein_xref_uniprotkb_gly", "Q557B8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "512", "512", "Asn", "Asn", "N" ], [ "Q54QD9-1", "91", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54QD9", "protein_xref_uniprotkb_gly", "Q54QD9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NCT", "NXT", "91", "91", "Asn", "Asn", "N" ], [ "Q54V07-1", "706", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54V07", "protein_xref_uniprotkb_gly", "Q54V07", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTS", "NXS", "706", "706", "Asn", "Asn", "N" ], [ "Q06885-1", "478", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q06885", "protein_xref_uniprotkb_gly", "Q06885", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "478", "478", "Asn", "Asn", "N" ], [ "Q54K56-1", "347", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54K56", "protein_xref_uniprotkb_gly", "Q54K56", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "347", "347", "Asn", "Asn", "N" ], [ "Q54KN4-1", "932", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54KN4", "protein_xref_uniprotkb_gly", "Q54KN4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLS", "NXS", "932", "932", "Asn", "Asn", "N" ], [ "Q869R1-1", "174", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q869R1", "protein_xref_uniprotkb_gly", "Q869R1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTS", "NXS", "174", "174", "Asn", "Asn", "N" ], [ "Q54MI3-1", "1049", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54MI3", "protein_xref_uniprotkb_gly", "Q54MI3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "1049", "1049", "Asn", "Asn", "N" ], [ "Q550R7-1", "346", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q550R7", "protein_xref_uniprotkb_gly", "Q550R7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "346", "346", "Asn", "Asn", "N" ], [ "Q54CU4-1", "10802", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54CU4", "protein_xref_uniprotkb_gly", "Q54CU4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "10802", "10802", "Asn", "Asn", "N" ], [ "Q54GU3-1", "143", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54GU3", "protein_xref_uniprotkb_gly", "Q54GU3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "143", "143", "Asn", "Asn", "N" ], [ "Q54S52-1", "2762", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54S52", "protein_xref_uniprotkb_gly", "Q54S52", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "2762", "2762", "Asn", "Asn", "N" ], [ "Q54JA5-1", "1860", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54JA5", "protein_xref_uniprotkb_gly", "Q54JA5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAT", "NXT", "1860", "1860", "Asn", "Asn", "N" ], [ "P34115-1", "498", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P34115", "protein_xref_uniprotkb_gly", "P34115", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYS", "NXS", "498", "498", "Asn", "Asn", "N" ], [ "Q54SH2-1", "393", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54SH2", "protein_xref_uniprotkb_gly", "Q54SH2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "393", "393", "Asn", "Asn", "N" ], [ "Q86JG6-1", "220", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q86JG6", "protein_xref_uniprotkb_gly", "Q86JG6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "220", "220", "Asn", "Asn", "N" ], [ "Q54LR6-1", "127", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54LR6", "protein_xref_uniprotkb_gly", "Q54LR6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "127", "127", "Asn", "Asn", "N" ], [ "Q54F54-1", "544", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54F54", "protein_xref_uniprotkb_gly", "Q54F54", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "544", "544", "Asn", "Asn", "N" ], [ "Q54SB6-1", "393", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q54SB6", "protein_xref_uniprotkb_gly", "Q54SB6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "393", "393", "Asn", "Asn", "N" ], [ "P54683-1", "747", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P54683", "protein_xref_uniprotkb_gly", "P54683", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "747", "747", "Asn", "Asn", "N" ], [ "Q55GI8-1", "588", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q55GI8", "protein_xref_uniprotkb_gly", "Q55GI8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "588", "588", "Asn", "Asn", "N" ], [ "Q86H13-1", "769", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q86H13", "protein_xref_uniprotkb_gly", "Q86H13", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "769", "769", "Asn", "Asn", "N" ], [ "P22549-1", "65", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P22549", "protein_xref_uniprotkb_gly", "P22549", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "65", "65", "Asn", "Asn", "N" ], [ "P34098-1", "520", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P34098", "protein_xref_uniprotkb_gly", "P34098", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "520", "520", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Dictyostelium Glycosylation Sites (UniProtKB)\n\nVersion\n - v-2.4.1\n\nCreated on\n - \n\nModified on\n - \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], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@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 Dictyostelium Glycosylation Sites (UniProtKB) dataset contains dictyostelium [taxid:44689] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Dictyostelium discoideum proteome release.\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-2.4.1/misc/glycosylation_subtype.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/n_sequon_info.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt\n Name: uniprot-proteome-dictyostelium-discoideum.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_19/uniprot-proteome-dictyostelium-discoideum.nt\n Output Subdomain\n Name: dicty_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.csv\n Name: dicty_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"383\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1086\"\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: \"4\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"387\"\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: \"383\"\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: \"5\"\n Name: \"data_source\"\n Description: \"The source database for the data\"\n Unique Values: \"5\"\n Name: \"eco_id\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"5\"\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: \"3\"\n Name: \"glycosylation_subtype\"\n Description: \"\"\n Unique Values: \"4\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"39\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"1086\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"1086\"\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-2.4.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.csv" }