{ "bcoid": "GLY_000143", "title": "Human Protein Glycosylation (Literature)", "description": "The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed ...", "filename": "human_proteoform_glycosylation_sites_literature.csv", "filetype": "csv", "categories": { "species": [ "Homo sapiens" ], "molecule": [ "Proteoform" ], "tag": [ "UniCarbKB publications" ], "status": [ "Reviewed" ], "file_type": [ "csv" ], "scope": [ "external" ] }, "minitable": { "content": [ [ "Q13443-1...", "144..." ], [ "Q13443-1...", "144..." ] ], "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_ac" }, { "type": "string", "label": "evidence" }, { "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" } ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q13443", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q13443", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A0AVL1", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A0AVL1", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q13443-2", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q13443-2", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "F8WC54", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "144", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "F8WC54", "24190977", "NAS", "NXS", "144", "144", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q13443", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q13443", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A0AVL1", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A0AVL1", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q13443-2", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q13443-2", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "F8WC54", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "Q13443-1", "154", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "F8WC54", "24190977", "NSS", "NXS", "154", "154", "Asn", "Asn", "N" ], [ "A1A5B4-1", "641", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A1A5B4", "24190977", "NST", "NXT", "641", "641", "Asn", "Asn", "N" ], [ "A1A5B4-1", "641", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A1A5B4", "24190977", "NST", "NXT", "641", "641", "Asn", "Asn", "N" ], [ "A1A5B4-1", "652", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A1A5B4", "24190977", "NHS", "NXS", "652", "652", "Asn", "Asn", "N" ], [ "A1A5B4-1", "652", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A1A5B4", "24190977", "NHS", "NXS", "652", "652", "Asn", "Asn", "N" ], [ "Q9NTN9-1", "55", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q9NTN9-2", "24190977", "NYS", "NXS", "55", "55", "Asn", "Asn", "N" ], [ "Q9NTN9-1", "55", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q9NTN9-2", "24190977", "NYS", "NXS", "55", "55", "Asn", "Asn", "N" ], [ "Q9NTN9-1", "55", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q9NTN9", "24190977", "NYS", "NXS", "55", "55", "Asn", "Asn", "N" ], [ "Q9NTN9-1", "55", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q9NTN9", "24190977", "NYS", "NXS", "55", "55", "Asn", "Asn", "N" ], [ "Q9NTN9-1", "55", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "E5RGX4", "24190977", "NYS", "NXS", "55", "55", "Asn", "Asn", "N" ], [ "Q9NTN9-1", "55", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "E5RGX4", "24190977", "NYS", "NXS", "55", "55", "Asn", "Asn", "N" ], [ "P28068-1", "110", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P28068", "24190977", "NRT", "NXT", "110", "110", "Asn", "Asn", "N" ], [ "P28068-1", "110", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P28068", "24190977", "NRT", "NXT", "110", "110", "Asn", "Asn", "N" ], [ "P10321-1", "110", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "O19617", "24190977", "NQS", "NXS", "110", "110", "Asn", "Asn", "N" ], [ "P10321-1", "110", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "O19617", "24190977", "NQS", "NXS", "110", "110", "Asn", "Asn", "N" ], [ "P10321-1", "110", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A2AEA2", "24190977", "NQS", "NXS", "110", "110", "Asn", "Asn", "N" ], [ "P10321-1", "110", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A2AEA2", "24190977", "NQS", "NXS", "110", "110", "Asn", "Asn", "N" ], [ "P10321-1", "110", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P10321", "24190977", "NQS", "NXS", "110", "110", "Asn", "Asn", "N" ], [ "P10321-1", "110", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P10321", "24190977", "NQS", "NXS", "110", "110", "Asn", "Asn", "N" ], [ "P04440-1", "48", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P04440", "24190977", "NGT", "NXT", "48", "48", "Asn", "Asn", "N" ], [ "P04440-1", "48", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P04440", "24190977", "NGT", "NXT", "48", "48", "Asn", "Asn", "N" ], [ "P04440-1", "48", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q5EP54", "24190977", "NGT", "NXT", "48", "48", "Asn", "Asn", "N" ], [ "P04440-1", "48", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q5EP54", "24190977", "NGT", "NXT", "48", "48", "Asn", "Asn", "N" ], [ "P0C0L4-1", "226", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P0C0L4", "24190977", "NSS", "NXS", "226", "226", "Asn", "Asn", "N" ], [ "P0C0L4-1", "226", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P0C0L4", "24190977", "NSS", "NXS", "226", "226", "Asn", "Asn", "N" ], [ "P0C0L5-1", "226", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P0C0L5", "24190977", "NSS", "NXS", "226", "226", "Asn", "Asn", "N" ], [ "P0C0L5-1", "226", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P0C0L5", "24190977", "NSS", "NXS", "226", "226", "Asn", "Asn", "N" ], [ "P0C0L5-1", "226", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "F5GXS0", "24190977", "NSS", "NXS", "226", "226", "Asn", "Asn", "N" ], [ "P0C0L5-1", "226", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "F5GXS0", "24190977", "NSS", "NXS", "226", "226", "Asn", "Asn", "N" ], [ "P0C0L4-1", "1328", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P0C0L4", "24190977", "NVT", "NXT", "1328", "1328", "Asn", "Asn", "N" ], [ "P0C0L4-1", "1328", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P0C0L4", "24190977", "NVT", "NXT", "1328", "1328", "Asn", "Asn", "N" ], [ "P0C0L5-1", "1328", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "P0C0L5", "24190977", "NVT", "NXT", "1328", "1328", "Asn", "Asn", "N" ], [ "P0C0L5-1", "1328", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "P0C0L5", "24190977", "NVT", "NXT", "1328", "1328", "Asn", "Asn", "N" ], [ "P0C0L5-1", "1328", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "F5GXS0", "24190977", "NVT", "NXT", "1328", "1328", "Asn", "Asn", "N" ], [ "P0C0L5-1", "1328", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "F5GXS0", "24190977", "NVT", "NXT", "1328", "1328", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-3", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-3", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-2", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-2", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A8MVE2", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "302", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A8MVE2", "24190977", "NLS", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-3", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-3", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-2", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6-2", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q8NHL6", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A8MVE2", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "Q8NHL6-1", "281", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A8MVE2", "24190977", "NFT", "NXT", "281", "281", "Asn", "Asn", "N" ], [ "O76082-1", "91", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "O76082", "24190977", "NFS", "NXS", "91", "91", "Asn", "Asn", "N" ], [ "O76082-1", "91", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "O76082", "24190977", "NFS", "NXS", "91", "91", "Asn", "Asn", "N" ], [ "Q9H015-1", "91", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q9H015", "24190977", "NFS", "NXS", "91", "91", "Asn", "Asn", "N" ], [ "Q9H015-1", "91", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q9H015", "24190977", "NFS", "NXS", "91", "91", "Asn", "Asn", "N" ], [ "O76082-1", "91", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "F8WCC9", "24190977", "NFS", "NXS", "91", "91", "Asn", "Asn", "N" ], [ "O76082-1", "91", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "F8WCC9", "24190977", "NFS", "NXS", "91", "91", "Asn", "Asn", "N" ], [ "A2RU67-1", "396", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A2RU67", "24190977", "NCS", "NXS", "396", "396", "Asn", "Asn", "N" ], [ "A2RU67-1", "396", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A2RU67", "24190977", "NCS", "NXS", "396", "396", "Asn", "Asn", "N" ], [ "A2RU67-1", "399", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A2RU67", "24190977", "NLL", "other", "399", "399", "Asn", "Asn", "N" ], [ "A2RU67-1", "399", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A2RU67", "24190977", "NLL", "other", "399", "399", "Asn", "Asn", "N" ], [ "A2RU67-1", "237", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A2RU67", "24190977", "NAT", "NXT", "237", "237", "Asn", "Asn", "N" ], [ "A2RU67-1", "237", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A2RU67", "24190977", "NAT", "NXT", "237", "237", "Asn", "Asn", "N" ], [ "Q01973-1", "315", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "Q01973", "24190977", "NST", "NXT", "315", "315", "Asn", "Asn", "N" ], [ "Q01973-1", "315", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "Q01973", "24190977", "NST", "NXT", "315", "315", "Asn", "Asn", "N" ], [ "A2VDJ0-1", "343", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A2VDJ0-5", "24190977", "NFT", "NXT", "343", "343", "Asn", "Asn", "N" ], [ "A2VDJ0-1", "343", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A2VDJ0-5", "24190977", "NFT", "NXT", "343", "343", "Asn", "Asn", "N" ], [ "A2VDJ0-1", "343", "Asn", "", "N-linked", "protein_xref_pubmed", "24190977", "protein_xref_glygen_ds", "GLY_000143", "A2VDJ0", "24190977", "NFT", "NXT", "343", "343", "Asn", "Asn", "N" ], [ "A2VDJ0-1", "343", "Asn", "", "N-linked", "protein_xref_glygen_ds", "GLY_000143", "protein_xref_glygen_ds", "GLY_000143", "A2VDJ0", "24190977", "NFT", "NXT", "343", "343", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Human Protein Glycosylation (Literature)\n\nVersion\n - v-2.4.1\n\nCreated on\n - 2019-06-14T14:54:26.195339\n\nModified on\n - 2022-09-26T08:56:48.520442\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@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 - Not Applicable []\n\nChecksum\n - \n\nUsability Domain\n - The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Winiewski, J. R., & Mann, M. (2012). Quantification of the N-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\"). The listed proteins (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\n - literature\n - publications\n\n Pipeline Steps\n - Step-1: The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLYDS000002)to generate the output files.\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_sites_lit_23090970_s2.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/glycosylation_sites_lit_23090970_s2.csv\n Name: glycosylation_sites_lit_23090970_s5.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/glycosylation_sites_lit_23090970_s5.csv\n Name: glycosylation_sites_lit_24190977_s5.cs\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/glycosylation_sites_lit_24190977_s5.cs\n Name: glycosylation_sites_lit_x_sx.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/glycosylation_sites_lit_x_sx.csv\n Name: hcv1a_proteoform_glycosylation_sites_literature.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv\n Name: sarscov1_proteoform_glycosylation_sites_literature.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/compiled/sarscov1_proteoform_glycosylation_sites_literature.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 Output Subdomain\n Name: human_proteoform_glycosylation_sites_literature.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_literature.csv\n Name: human_proteoform_glycosylation_sites_literature.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_literature.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1330\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"1049\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"1\"\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: \"3\"\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: \"uniprotkb_ac\"\n Description: \"Accession assigned to the protein in the UniProtKB database\"\n Unique Values: \"4806\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) or DOI (Digital Object Identifier) as evidence for the entry/annotation\"\n Unique Values: \"2\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"248\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"6\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"1049\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"1049\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_literature.csv" }