{ "bcoid": "GLY_000040", "title": "Glycosylation Sites - UniCarbKB [Human proteins]", "description": "List of human [taxid:9606] proteins with information on glycosylation sites and associated glycans (if ...", "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv", "filetype": "csv", "categories": { "status": "Reviewed", "molecule": "Proteoform", "species": "Homo sapiens", "tags": "UniCarbKB glycosylation sites", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "P07498-1...", "143..." ], [ "P07498-1...", "143..." ] ], "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": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "site_seq" }, { "type": "string", "label": "site_type" }, { "type": "string", "label": "src_file_name" }, { "type": "string", "label": "uckb_id" }, { "type": "string", "label": "composition" }, { "type": "string", "label": "curation_notes" }, { "type": "string", "label": "additional_notes" }, { "type": "string", "label": "pdb" }, { "type": "string", "label": "swiss_model" }, { "type": "string", "label": "abundance" }, { "type": "string", "label": "n_sequon" }, { "type": "string", "label": "n_sequon_type" } ], [ "P07498-1", "143", "thr", "G29231AT", "Thr", "protein_xref_unicarbkb", "P07498", "protein_xref_unicarbkb", "P07498", "143", "143", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "352", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: T-133, T-143, T-148, T-151, T-157, S-162, T-167, T-169, T-178, T-181", "", "", "", "", "", "" ], [ "P07498-1", "143", "thr", "G29231AT", "Thr", "protein_xref_pubmed", "3342257", "protein_xref_unicarbkb", "P07498", "143", "143", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "352", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: T-133, T-143, T-148, T-151, T-157, S-162, T-167, T-169, T-178, T-181", "", "", "", "", "", "" ], [ "Q8WWV6-1", "423", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "Q8WWV6", "protein_xref_unicarbkb", "Q8WWV6", "423", "423", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q8WWV6-1", "423", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "Q8WWV6", "423", "423", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q9NQ40-1", "182", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "Q9NQ40", "protein_xref_unicarbkb", "Q9NQ40", "182", "182", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q9NQ40-1", "182", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "Q9NQ40", "182", "182", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P00747-1", "308", "asn", "G11041DA", "Asn", "protein_xref_unicarbkb", "P00747", "protein_xref_unicarbkb", "P00747", "308", "308", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1119", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: ASN-308 ; ASN-308", "", "", "", "", "", "" ], [ "P00747-1", "308", "asn", "G11041DA", "Asn", "protein_xref_pubmed", "2065054", "protein_xref_unicarbkb", "P00747", "308", "308", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1119", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: ASN-308 ; ASN-308", "", "", "", "", "", "" ], [ "P07911-1", "76", "asn", "G71906BW", "Asn", "protein_xref_unicarbkb", "P07911", "protein_xref_unicarbkb", "P07911", "76", "76", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "5172", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-76, N-80, N-232, N-275, N-322, N-396, N-513", "", "", "", "", "", "" ], [ "P07911-1", "76", "asn", "G71906BW", "Asn", "protein_xref_pubmed", "9884403", "protein_xref_unicarbkb", "P07911", "76", "76", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "5172", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-76, N-80, N-232, N-275, N-322, N-396, N-513", "", "", "", "", "", "" ], [ "Q6UXB8-1", "214", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "Q6UXB8", "protein_xref_unicarbkb", "Q6UXB8", "214", "214", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q6UXB8-1", "214", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "Q6UXB8", "214", "214", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P01861-1", "177", "asn", "G68318VE", "Asn", "protein_xref_unicarbkb", "P01861", "protein_xref_unicarbkb", "P01861", "177", "177", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P01861-1", "177", "asn", "G68318VE", "Asn", "protein_xref_pubmed", "24841998", "protein_xref_unicarbkb", "P01861", "177", "177", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P25311-1", "128", "asn", "", "Asn", "protein_xref_unicarbkb", "P25311", "protein_xref_unicarbkb", "P25311", "128", "128", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc2Hex9dHex0NeuAc0Gc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P25311-1", "128", "asn", "", "Asn", "protein_xref_pubmed", "29741879", "protein_xref_unicarbkb", "P25311", "128", "128", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc2Hex9dHex0NeuAc0Gc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P16112-1", "1599", "ser", "G43417UB", "Ser", "protein_xref_unicarbkb", "P16112", "protein_xref_unicarbkb", "P16112", "1599", "1599", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P16112-1", "1599", "ser", "G43417UB", "Ser", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "P16112", "1599", "1599", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P02724-1", "36", "thr", "G47180UC", "Thr", "protein_xref_unicarbkb", "P02724", "protein_xref_unicarbkb", "P02724", "36", "36", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "385", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-21, T-22, T-23, T-29, S-30, T-31, S-32, T-36, S-38, S-41, T-44, N-45, T-52, T-56, S-63, S-66, T-69", "", "", "", "", "", "" ], [ "P02724-1", "36", "thr", "G47180UC", "Thr", "protein_xref_pubmed", "4091823", "protein_xref_unicarbkb", "P02724", "36", "36", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "385", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-21, T-22, T-23, T-29, S-30, T-31, S-32, T-36, S-38, S-41, T-44, N-45, T-52, T-56, S-63, S-66, T-69", "", "", "", "", "", "" ], [ "P04278-1", "36", "thr", "G56682BC", "Thr", "protein_xref_unicarbkb", "P04278", "protein_xref_unicarbkb", "P04278", "36", "36", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "8", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: T-36, N-380, N-396", "", "", "", "", "", "" ], [ "P04278-1", "36", "thr", "G56682BC", "Thr", "protein_xref_pubmed", "6684483", "protein_xref_unicarbkb", "P04278", "36", "36", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "8", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: T-36, N-380, N-396", "", "", "", "", "", "" ], [ "P07911-1", "396", "asn", "G31532GK", "Asn", "protein_xref_unicarbkb", "P07911", "protein_xref_unicarbkb", "P07911", "396", "396", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "5161", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-76, N-80, N-232, N-275, N-322, N-396, N-513", "", "", "", "", "", "" ], [ "P07911-1", "396", "asn", "G31532GK", "Asn", "protein_xref_pubmed", "9884403", "protein_xref_unicarbkb", "P07911", "396", "396", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "5161", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-76, N-80, N-232, N-275, N-322, N-396, N-513", "", "", "", "", "", "" ], [ "P00747-1", "308", "asn", "G56749GV", "Asn", "protein_xref_unicarbkb", "P00747", "protein_xref_unicarbkb", "P00747", "308", "308", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1137", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: ASN-308 ; ASN-308", "", "", "", "", "", "" ], [ "P00747-1", "308", "asn", "G56749GV", "Asn", "protein_xref_pubmed", "1899031", "protein_xref_unicarbkb", "P00747", "308", "308", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1137", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: ASN-308 ; ASN-308", "", "", "", "", "", "" ], [ "P78509-1", "184", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "P78509", "protein_xref_unicarbkb", "P78509", "184", "184", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P78509-1", "184", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "P78509", "184", "184", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q92673-1", "1413", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "Q92673", "protein_xref_unicarbkb", "Q92673", "1413", "1413", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q92673-1", "1413", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "Q92673", "1413", "1413", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P00742-1", "188", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "P00742", "protein_xref_unicarbkb", "P00742", "188", "188", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "Experimentally indistinguishable attachment sites T183, S188, S189, S190, S197, T199, Y203", "", "", "", "", "" ], [ "P00742-1", "188", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "22171320", "protein_xref_unicarbkb", "P00742", "188", "188", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "Experimentally indistinguishable attachment sites T183, S188, S189, S190, S197, T199, Y203", "", "", "", "", "" ], [ "P08603-1", "822", "asn", "G08146BT", "Asn", "protein_xref_unicarbkb", "P08603", "protein_xref_unicarbkb", "P08603", "822", "822", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "8102", "", "", "", "", "", "", "", "" ], [ "P08603-1", "822", "asn", "G08146BT", "Asn", "protein_xref_pubmed", "17591618", "protein_xref_unicarbkb", "P08603", "822", "822", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "8102", "", "", "", "", "", "", "", "" ], [ "P01588-1", "51", "asn", "G17155VX", "Asn", "protein_xref_unicarbkb", "P01588", "protein_xref_unicarbkb", "P01588", "51", "51", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1983", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01588-1", "51", "asn", "G17155VX", "Asn", "protein_xref_pubmed", "8477709", "protein_xref_unicarbkb", "P01588", "51", "51", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1983", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01730-1", "296", "asn", "G45560HM", "Asn", "protein_xref_unicarbkb", "P01730", "protein_xref_unicarbkb", "P01730", "296", "296", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1185", "", "ASN-296 AND ASN-325 ; ASN-296 AND ASN-325", "", "", "", "", "", "" ], [ "P01730-1", "296", "asn", "G45560HM", "Asn", "protein_xref_pubmed", "2592374", "protein_xref_unicarbkb", "P01730", "296", "296", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1185", "", "ASN-296 AND ASN-325 ; ASN-296 AND ASN-325", "", "", "", "", "", "" ], [ "P08861-1", "114", "asn", "G82348BZ", "Asn", "protein_xref_unicarbkb", "P08861", "protein_xref_unicarbkb", "P08861", "114", "114", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1477", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-114", "", "", "", "", "", "" ], [ "P08861-1", "114", "asn", "G82348BZ", "Asn", "protein_xref_pubmed", "1898343", "protein_xref_unicarbkb", "P08861", "114", "114", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1477", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-114", "", "", "", "", "", "" ], [ "P08519-1", "16", "ser", "G27391WQ", "Ser", "protein_xref_unicarbkb", "P08519", "protein_xref_unicarbkb", "P08519", "16", "16", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc2Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P08519-1", "16", "ser", "G27391WQ", "Ser", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "P08519", "16", "16", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc2Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P02724-1", "41", "ser", "G65562ZE", "Ser", "protein_xref_unicarbkb", "P02724", "protein_xref_unicarbkb", "P02724", "41", "41", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "7", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-21, T-22, T-23, T-29, S-30, T-31, S-32, T-36, S-38, S-41, T-44, N-45, T-52, T-56, S-63, S-66, T-69", "", "", "", "", "", "" ], [ "P02724-1", "41", "ser", "G65562ZE", "Ser", "protein_xref_pubmed", "4091823", "protein_xref_unicarbkb", "P02724", "41", "41", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "7", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-21, T-22, T-23, T-29, S-30, T-31, S-32, T-36, S-38, S-41, T-44, N-45, T-52, T-56, S-63, S-66, T-69", "", "", "", "", "", "" ], [ "P01588-1", "110", "asn", "G68892PJ", "Asn", "protein_xref_unicarbkb", "P01588", "protein_xref_unicarbkb", "P01588", "110", "110", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1991", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01588-1", "110", "asn", "G68892PJ", "Asn", "protein_xref_pubmed", "3179269", "protein_xref_unicarbkb", "P01588", "110", "110", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1991", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01588-1", "65", "asn", "G30460NZ", "Asn", "protein_xref_unicarbkb", "P01588", "protein_xref_unicarbkb", "P01588", "65", "65", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1973", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01588-1", "65", "asn", "G30460NZ", "Asn", "protein_xref_pubmed", "11805077", "protein_xref_unicarbkb", "P01588", "65", "65", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1973", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "Q05707-1", "731", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "Q05707", "protein_xref_unicarbkb", "Q05707", "731", "731", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q05707-1", "731", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "Q05707", "731", "731", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q4LDE5-1", "894", "ser", "G43417UB", "Ser", "protein_xref_unicarbkb", "Q4LDE5", "protein_xref_unicarbkb", "Q4LDE5", "894", "894", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "Experimentally indistinguishable attachment sites T887, T891, T893 , S894", "", "", "", "", "" ], [ "Q4LDE5-1", "894", "ser", "G43417UB", "Ser", "protein_xref_pubmed", "22171320", "protein_xref_unicarbkb", "Q4LDE5", "894", "894", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "Experimentally indistinguishable attachment sites T887, T891, T893 , S894", "", "", "", "", "" ], [ "P07911-1", "322", "asn", "G90987JA", "Asn", "protein_xref_unicarbkb", "P07911", "protein_xref_unicarbkb", "P07911", "322", "322", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "5145", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-76, N-80, N-232, N-275, N-322, N-396, N-513", "", "", "", "", "", "" ], [ "P07911-1", "322", "asn", "G90987JA", "Asn", "protein_xref_pubmed", "9884403", "protein_xref_unicarbkb", "P07911", "322", "322", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "5145", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-76, N-80, N-232, N-275, N-322, N-396, N-513", "", "", "", "", "", "" ], [ "P08709-1", "382", "asn", "G50739NP", "Asn", "protein_xref_unicarbkb", "P08709", "protein_xref_unicarbkb", "P08709", "382", "382", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7510", "", "", "", "", "", "", "", "" ], [ "P08709-1", "382", "asn", "G50739NP", "Asn", "protein_xref_pubmed", "18642129", "protein_xref_unicarbkb", "P08709", "382", "382", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7510", "", "", "", "", "", "", "", "" ], [ "P01730-1", "296", "asn", "G78059CC", "Asn", "protein_xref_unicarbkb", "P01730", "protein_xref_unicarbkb", "P01730", "296", "296", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1603", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-296, N-325", "", "", "", "", "", "" ], [ "P01730-1", "296", "asn", "G78059CC", "Asn", "protein_xref_pubmed", "2592374", "protein_xref_unicarbkb", "P01730", "296", "296", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1603", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-296, N-325", "", "", "", "", "", "" ], [ "P00734-1", "416", "asn", "G91365ZQ", "Asn", "protein_xref_unicarbkb", "P00734", "protein_xref_unicarbkb", "P00734", "416", "416", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1107", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-121, N-143, N-416", "", "", "", "", "", "" ], [ "P00734-1", "416", "asn", "G91365ZQ", "Asn", "protein_xref_pubmed", "7309709", "protein_xref_unicarbkb", "P00734", "416", "416", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1107", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-121, N-143, N-416", "", "", "", "", "", "" ], [ "P01215-1", "76", "asn", "G24413UY", "Asn", "protein_xref_unicarbkb", "P01215", "protein_xref_unicarbkb", "P01215", "76", "76", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1307", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: ASN-76", "", "", "", "", "", "" ], [ "P01215-1", "76", "asn", "G24413UY", "Asn", "protein_xref_pubmed", "9449027", "protein_xref_unicarbkb", "P01215", "76", "76", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1307", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: ASN-76", "", "", "", "", "", "" ], [ "P16150-1", "109", "thr", "G65562ZE", "Thr", "protein_xref_unicarbkb", "P16150", "protein_xref_unicarbkb", "P16150", "109", "109", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "7", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: T-21, T-22, T-26, T-28, S-29, S-35, T-36, S-37, S-41, S-42, T-46, T-47, S-48, T-50, T-58, T-69, S-99, S-103, T-109, T-113, S-114, T-136, T-137, T-173, T-178, N-239", "", "", "", "", "", "" ], [ "P16150-1", "109", "thr", "G65562ZE", "Thr", "protein_xref_pubmed", "2943741", "protein_xref_unicarbkb", "P16150", "109", "109", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "7", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: T-21, T-22, T-26, T-28, S-29, S-35, T-36, S-37, S-41, S-42, T-46, T-47, S-48, T-50, T-58, T-69, S-99, S-103, T-109, T-113, S-114, T-136, T-137, T-173, T-178, N-239", "", "", "", "", "", "" ], [ "P02771-1", "251", "asn", "G66937TJ", "Asn", "protein_xref_unicarbkb", "P02771", "protein_xref_unicarbkb", "P02771", "251", "251", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1489", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-251", "", "", "", "", "", "" ], [ "P02771-1", "251", "asn", "G66937TJ", "Asn", "protein_xref_pubmed", "1694115", "protein_xref_unicarbkb", "P02771", "251", "251", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1489", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-251", "", "", "", "", "", "" ], [ "Q14766-1", "461", "thr", "G43417UB", "Thr", "protein_xref_unicarbkb", "Q14766", "protein_xref_unicarbkb", "Q14766", "461", "461", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "Q14766-1", "461", "thr", "G43417UB", "Thr", "protein_xref_pubmed", "30459171", "protein_xref_unicarbkb", "Q14766", "461", "461", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P01588-1", "110", "asn", "G47279LF", "Asn", "protein_xref_unicarbkb", "P01588", "protein_xref_unicarbkb", "P01588", "110", "110", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1995", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01588-1", "110", "asn", "G47279LF", "Asn", "protein_xref_pubmed", "8460945", "protein_xref_unicarbkb", "P01588", "110", "110", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1995", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: N-51, N-65, N-110, S-153", "", "", "", "", "", "" ], [ "P01215-1", "76", "asn", "G25835MT", "Asn", "protein_xref_unicarbkb", "P01215", "protein_xref_unicarbkb", "P01215", "76", "76", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1113", "", "ASN-76 ; ASN-76", "", "", "", "", "", "" ], [ "P01215-1", "76", "asn", "G25835MT", "Asn", "protein_xref_pubmed", "1820200", "protein_xref_unicarbkb", "P01215", "76", "76", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "1113", "", "ASN-76 ; ASN-76", "", "", "", "", "", "" ], [ "P08709-1", "382", "asn", "G71527NE", "Asn", "protein_xref_unicarbkb", "P08709", "protein_xref_unicarbkb", "P08709", "382", "382", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7464", "", "", "", "", "", "", "", "" ], [ "P08709-1", "382", "asn", "G71527NE", "Asn", "protein_xref_pubmed", "18642129", "protein_xref_unicarbkb", "P08709", "382", "382", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7464", "", "", "", "", "", "", "", "" ], [ "Q14624-1", "577", "asn", "", "Asn", "protein_xref_unicarbkb", "Q14624", "protein_xref_unicarbkb", "Q14624", "577", "577", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "988076971", "", "", "", "", "", "", "", "" ], [ "Q14624-1", "577", "asn", "", "Asn", "protein_xref_pubmed", "24884609", "protein_xref_unicarbkb", "Q14624", "577", "577", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "988076971", "", "", "", "", "", "", "", "" ], [ "P02724-1", "56", "thr", "G33350UC", "Thr", "protein_xref_unicarbkb", "P02724", "protein_xref_unicarbkb", "P02724", "56", "56", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "517", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-21, T-22, T-23, T-29, S-30, T-31, S-32, T-36, S-38, S-41, T-44, N-45, T-52, T-56, S-63, S-66, T-69", "", "", "", "", "", "" ], [ "P02724-1", "56", "thr", "G33350UC", "Thr", "protein_xref_pubmed", "7430095", "protein_xref_unicarbkb", "P02724", "56", "56", "T", "known_site", "known_legacy_human_mouse_rat_glygen", "517", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-21, T-22, T-23, T-29, S-30, T-31, S-32, T-36, S-38, S-41, T-44, N-45, T-52, T-56, S-63, S-66, T-69", "", "", "", "", "", "" ], [ "P04275-1", "1515", "asn", "G16175ZV", "Asn", "protein_xref_unicarbkb", "P04275", "protein_xref_unicarbkb", "P04275", "1515", "1515", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc4Hex6dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P04275-1", "1515", "asn", "G16175ZV", "Asn", "protein_xref_pubmed", "29671580", "protein_xref_unicarbkb", "P04275", "1515", "1515", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc4Hex6dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "P02786-1", "727", "asn", "G74910CR", "Asn", "protein_xref_unicarbkb", "P02786", "protein_xref_unicarbkb", "P02786", "727", "727", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "4039", "", "ASN-727", "", "", "", "", "", "" ], [ "P02786-1", "727", "asn", "G74910CR", "Asn", "protein_xref_pubmed", "2403553", "protein_xref_unicarbkb", "P02786", "727", "727", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "4039", "", "ASN-727", "", "", "", "", "", "" ], [ "O94905-1", "106", "asn", "G01650EU", "Asn", "protein_xref_unicarbkb", "O94905", "protein_xref_unicarbkb", "O94905", "106", "106", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc3Hex6dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ], [ "O94905-1", "106", "asn", "G01650EU", "Asn", "protein_xref_pubmed", "29741879", "protein_xref_unicarbkb", "O94905", "106", "106", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "", "comp_HexNAc3Hex6dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "", "" ] ] }, "readme": "Name\n - Glycosylation Sites - UniCarbKB [Human proteins]\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-01-23T17:21:05.907769\n\nModified on\n - 2020-05-01T15:20:46.152020\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@email.gwu.edu]\n\nAuthors\n - Matthew Campbell [m.campbell2@griffith.edu.au], Robel Kahsay [rykahsay@email.gwu.edu], Nathan Edwards [Georgetown University]\n\nChecksum\n - \n\nUsability Domain\n - List of human [taxid:9606] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001).\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation sites\n - glycan\n - UniCarbKB\n - GlyTouCan\n\n Pipeline Steps\n - Step-1: The input file ;for script:human_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid.\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: merge_human_rat_mouse_gps_06022020_130220.csv\n URI: https://data.glygen.org//ln2downloads/unicarbkb/06_24_2021/merge_human_rat_mouse_gps_06022020_130220.csv\n Name: glycan_properties.tsv\n URI: https://data.glygen.org//ln2downloads/glytoucan/gtc_06_30_2021/export/glycan_properties.tsv\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_masterlist.csv\n Name: glycan_xref_unicarbkb.csv\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/glycan_xref_unicarbkb.csv\n Name: aadict.csv\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/misc/aadict.csv\n Name: classification.tsv\n URI: https://data.glygen.org//ln2downloads/glytoucan/gtc_06_30_2021/export/classification.tsv\n Name: human_protein_allsequences.fasta\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_allsequences.fasta\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_unicarbkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n Name: human_proteoform_glycosylation_sites_unicarbkb.1.log\n URI: http://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb.1.log\n Name: human_proteoform_glycosylation_sites_unicarbkb.2.log\n URI: http://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb.2.log\n Name: human_proteoform_glycosylation_sites_unicarbkb.stats.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n Name: human_proteoform_glycosylation_sites_unicarbkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.stat.csv", "downloadurl": "/ln2data/releases/data/v-1.12.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv" }