{ "bcoid": "GLY_000142", "title": "Human Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)", "description": "The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by ...", "filename": "human_proteoform_glycosylation_sites_harvard.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Proteoform", "tags": "Glycosylation sites (Harvard)", "status": "Reviewed", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "Q6ZSR9-1...", "150..." ], [ "Q6ZSR9-1...", "150..." ] ], "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": "composition" }, { "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" } ], [ "Q6ZSR9-1", "150", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "150", "150", "Ser", "Ser", "S" ], [ "Q6ZSR9-1", "150", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "150", "150", "Ser", "Ser", "S" ], [ "Q6ZSR9-1", "221", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "221", "221", "Ser", "Ser", "S" ], [ "Q6ZSR9-1", "221", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "221", "221", "Ser", "Ser", "S" ], [ "Q2M2I8-1", "448", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "448", "448", "Thr", "Thr", "T" ], [ "Q2M2I8-1", "448", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "448", "448", "Thr", "Thr", "T" ], [ "O14639-1", "452", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "452", "452", "Ser", "Ser", "S" ], [ "O14639-1", "452", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "452", "452", "Ser", "Ser", "S" ], [ "Q15027-1", "258", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "258", "258", "Ser", "Ser", "S" ], [ "Q15027-1", "258", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "258", "258", "Ser", "Ser", "S" ], [ "Q15027-1", "306", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "306", "306", "Thr", "Thr", "T" ], [ "Q15027-1", "306", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "306", "306", "Thr", "Thr", "T" ], [ "P62736-1", "370", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "370", "370", "Ser", "Ser", "S" ], [ "P62736-1", "370", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "370", "370", "Ser", "Ser", "S" ], [ "P60709-1", "271", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "271", "271", "Ser", "Ser", "S" ], [ "P60709-1", "271", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "271", "271", "Ser", "Ser", "S" ], [ "P12814-1", "293", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "293", "293", "Thr", "Thr", "T" ], [ "P12814-1", "293", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "293", "293", "Thr", "Thr", "T" ], [ "P55265-1", "397", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "397", "397", "Ser", "Ser", "S" ], [ "P55265-1", "397", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "397", "397", "Ser", "Ser", "S" ], [ "P35611-1", "558", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "558", "558", "Thr", "Thr", "T" ], [ "P35611-1", "558", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "558", "558", "Thr", "Thr", "T" ], [ "Q9H2P0-1", "763", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "763", "763", "Ser", "Ser", "S" ], [ "Q9H2P0-1", "763", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "763", "763", "Ser", "Ser", "S" ], [ "Q16186-1", "221", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "221", "221", "Thr", "Thr", "T" ], [ "Q16186-1", "221", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "221", "221", "Thr", "Thr", "T" ], [ "Q16186-1", "213", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "213", "213", "Ser", "Ser", "S" ], [ "Q16186-1", "213", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "213", "213", "Ser", "Ser", "S" ], [ "Q16186-1", "211", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "211", "211", "Ser", "Ser", "S" ], [ "Q16186-1", "211", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "211", "211", "Ser", "Ser", "S" ], [ "Q08117-1", "161", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "161", "161", "Thr", "Thr", "T" ], [ "Q08117-1", "161", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "161", "161", "Thr", "Thr", "T" ], [ "Q08117-1", "158", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "158", "158", "Ser", "Ser", "S" ], [ "Q08117-1", "158", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "158", "158", "Ser", "Ser", "S" ], [ "P52594-1", "367", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "367", "367", "Ser", "Ser", "S" ], [ "P52594-1", "367", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "367", "367", "Ser", "Ser", "S" ], [ "P52594-1", "302", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "302", "302", "Ser", "Ser", "S" ], [ "P52594-1", "302", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "302", "302", "Ser", "Ser", "S" ], [ "P52594-1", "142", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "142", "142", "Ser", "Ser", "S" ], [ "P52594-1", "142", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "142", "142", "Ser", "Ser", "S" ], [ "P52594-1", "362", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "362", "362", "Ser", "Ser", "S" ], [ "P52594-1", "362", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "362", "362", "Ser", "Ser", "S" ], [ "O95081-1", "191", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "191", "191", "Ser", "Ser", "S" ], [ "O95081-1", "191", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "191", "191", "Ser", "Ser", "S" ], [ "O95081-1", "193", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "193", "193", "Ser", "Ser", "S" ], [ "O95081-1", "193", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "193", "193", "Ser", "Ser", "S" ], [ "O95081-1", "192", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "192", "192", "Thr", "Thr", "T" ], [ "O95081-1", "192", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "192", "192", "Thr", "Thr", "T" ], [ "O95081-1", "193", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "193", "193", "Ser", "Ser", "S" ], [ "O95081-1", "193", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "193", "193", "Ser", "Ser", "S" ], [ "O95081-1", "194", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "194", "194", "Ser", "Ser", "S" ], [ "O95081-1", "194", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "194", "194", "Ser", "Ser", "S" ], [ "O95081-1", "192", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", " HexNAc(1)", "", "", "192", "192", "Thr", "Thr", "T" ], [ "O95081-1", "192", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", " HexNAc(1)", "", "", "192", "192", "Thr", "Thr", "T" ], [ "Q09666-1", "5603", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "5603", "5603", "Ser", "Ser", "S" ], [ "Q09666-1", "5603", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "5603", "5603", "Ser", "Ser", "S" ], [ "Q09666-1", "5552", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "5552", "5552", "Ser", "Ser", "S" ], [ "Q09666-1", "5552", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "5552", "5552", "Ser", "Ser", "S" ], [ "Q09666-1", "5555", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "5555", "5555", "Ser", "Ser", "S" ], [ "Q09666-1", "5555", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", " HexNAz2Si(1)", "", "", "5555", "5555", "Ser", "Ser", "S" ], [ "Q9UKA4-1", "1255", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAc(1)", "", "", "1255", "1255", "Thr", "Thr", "T" ], [ "Q9UKA4-1", "1255", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAc(1)", "", "", "1255", "1255", "Thr", "Thr", "T" ], [ "Q9UKA4-1", "1059", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1059", "1059", "Ser", "Ser", "S" ], [ "Q9UKA4-1", "1059", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1059", "1059", "Ser", "Ser", "S" ], [ "O43823-1", "217", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "217", "217", "Ser", "Ser", "S" ], [ "O43823-1", "217", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "217", "217", "Ser", "Ser", "S" ], [ "Q01433-1", "168", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAc(1)", "", "", "168", "168", "Ser", "Ser", "S" ], [ "Q01433-1", "168", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAc(1)", "", "", "168", "168", "Ser", "Ser", "S" ], [ "Q8IWZ3-1", "1817", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1817", "1817", "Ser", "Ser", "S" ], [ "Q8IWZ3-1", "1817", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1817", "1817", "Ser", "Ser", "S" ], [ "Q8IWZ3-1", "1813", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1813", "1813", "Thr", "Thr", "T" ], [ "Q8IWZ3-1", "1813", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1813", "1813", "Thr", "Thr", "T" ], [ "Q8IWZ3-1", "1799", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1799", "1799", "Thr", "Thr", "T" ], [ "Q8IWZ3-1", "1799", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1799", "1799", "Thr", "Thr", "T" ], [ "Q8IWZ3-1", "1846", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1846", "1846", "Ser", "Ser", "S" ], [ "Q8IWZ3-1", "1846", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "1846", "1846", "Ser", "Ser", "S" ], [ "O75179-1", "2382", "Ser", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "2382", "2382", "Ser", "Ser", "S" ], [ "O75179-1", "2382", "Ser", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "2382", "2382", "Ser", "Ser", "S" ], [ "O75179-1", "2379", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "2379", "2379", "Thr", "Thr", "T" ], [ "O75179-1", "2379", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "2379", "2379", "Thr", "Thr", "T" ], [ "O75179-1", "2001", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "2001", "2001", "Thr", "Thr", "T" ], [ "O75179-1", "2001", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "2001", "2001", "Thr", "Thr", "T" ], [ "P07355-1", "153", "Thr", "G70994MS", "O-linked", "protein_xref_glygen_ds", "GLYDS000142", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "153", "153", "Thr", "Thr", "T" ], [ "P07355-1", "153", "Thr", "G70994MS", "O-linked", "protein_xref_pubmed", "29351928", "protein_xref_glygen_ds", "GLYDS000142", "HexNAz2Si(1)", "", "", "153", "153", "Thr", "Thr", "T" ] ] }, "readme": "Name\n - Human Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-06-06T17:51:22.706056\n\nModified on\n - 2020-05-01T15:22:27.881080\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@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 - Christina Woo [cwoo@chemistry.harvard.edu], Christina Woo [cwoo@chemistry.harvard.edu]\n\nChecksum\n - \n\nUsability Domain\n - The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by Dr.Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. The GlyTouCan accession (G70994MS)is annotated to the glycan composition based on author's recommendation. Author's note: \"For the glycan assignment, it would be most technically correct to use a HexNAc molecule, although by and large, these are O-GlcNAc modifications, we cannot be 100% certain for every single one\". The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). The source publication:Woo CM, Lund PJ, Huang AC, Davis MM, Bertozzi CR, Pitteri SJ. Mapping and Quantification of Over 2000 O-linked Glycopeptides in Activated Human T Cells with Isotope-Targeted Glycoproteomics (Isotag). Mol Cell Proteomics. 2018;17(4):764-75. doi: 10.1074/mcp.RA117.000261. PubMed PMID: 29351928; PubMed Central PMCID: PMCPMC5880114).\n\nDescription Domain\n Keywords\n - Glycan\n - Publications\n - Proteoform\n\n Pipeline Steps\n - Step-1: The input file was submitted by the author. An additional column \"Evidence\" with value \"GLYDS000142\" was added in the input file. A python script was used to process data to 1. map UniprotKB accessions to UniProtKB canonical accessions 2. Split the \"GlycoSite(s) (protein)\" column to amino acid and glycosylation site. 3.Split the \"GlycoSite(s) (protein)\" column into single value row. 4. Add two new columns: glycosylation_type=o-linked and evidence=29351928 (based on author's recommendation). A quality check is done to match the position + amino acid with the canonical fasta sequence (https://data.glygen.org/GLYDS000002). The rows which fail the QC are eliminated from the final output file.\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: T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv\n URI: https:/data.glygen.org/ln2downloads/harvard/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_harvard.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/human_proteoform_glycosylation_sites_harvard.csv\n Name: human_proteoform_glycosylation_sites_harvard.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/human_proteoform_glycosylation_sites_harvard.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"374\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"640\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"2\"\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: \"1\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"2\"\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: \"1\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"2\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"640\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"640\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"2\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"2\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.12.3/reviewed/human_proteoform_glycosylation_sites_harvard.csv" }