{
    "bcoid": "GLY_000221",
    "title": "Glycosylation sites - UniCarbKB [Rat proteins]",
    "description": "List of Rattus norvegicus [taxid:10116] proteins with information on glycosylation sites and associated ...",
    "filename_list": "rat_proteoform_glycosylation_sites_unicarbkb.csv",
    "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv",
    "filetype": "csv",
    "categories": {
        "status": [
            "Reviewed"
        ],
        "molecule": [
            "Proteoform"
        ],
        "species": [
            "Rattus norvegicus"
        ],
        "tag": [
            "UniCarbKB glycosylation sites"
        ],
        "file_type": [
            "csv"
        ],
        "scope": [
            "internal"
        ],
        "file_category": [
            "glycosylation_sites_"
        ]
    },
    "minitable": {
        "content": [
            [
                "B2GV54-1...",
                "270..."
            ],
            [
                "Q9EQV6-1...",
                "210..."
            ]
        ],
        "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": "start_aa"
                },
                {
                    "type": "string",
                    "label": "end_aa"
                },
                {
                    "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": "source_tissue_id"
                },
                {
                    "type": "string",
                    "label": "source_tissue_name"
                },
                {
                    "type": "string",
                    "label": "source_cell_line_cellosaurus_id"
                },
                {
                    "type": "string",
                    "label": "source_cell_line_cellosaurus_name"
                },
                {
                    "type": "string",
                    "label": "n_sequon"
                },
                {
                    "type": "string",
                    "label": "n_sequon_type"
                },
                {
                    "type": "string",
                    "label": "isoform_mapping_notes"
                }
            ],
            [
                "B2GV54-1",
                "270",
                "asn",
                "G09775CH",
                "N-linked",
                "protein_xref_pubmed",
                "24090084",
                "protein_xref_unicarbkb_ds",
                "GLY_000221",
                "270",
                "270",
                "Asn",
                "Asn",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7896",
                "",
                "GlycoSuiteDB  curation notes. Reported structure can be attached to the following: ASN-270",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                "NHT",
                "NXT",
                ""
            ],
            [
                "Q9EQV6-1",
                "210",
                "asn",
                "G37135JQ",
                "N-linked",
                "protein_xref_pubmed",
                "24090084",
                "protein_xref_unicarbkb_ds",
                "GLY_000221",
                "210",
                "210",
                "Asn",
                "Asn",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "3869",
                "",
                "GlycoSuiteDB  curation notes. Reported structure can be attached to the following: ASN-210",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                "NLT",
                "NXT",
                ""
            ]
        ]
    },
    "readme": "Name\n   - Glycosylation sites - UniCarbKB [Rat proteins]\n\nVersion\n   - v-2.12.1\n\nCreated on\n  - 2019-09-05T14:34:59.005886\n\nModified on\n   - 2024-12-05T19:02:39.985Z\n\nCreated by\n   - Jeet Vora [jeetvora@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], Kate Warner [k.warner1@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 Rattus norvegicus [taxid:10116] 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/GLYDS000244).\n\nDescription Domain\n   Keywords\n   - proteins\n   - canonical\n   - glycosylation sites\n   - glycan\n   - UniCarbKB\n   - GlyTouCan\n\n   Pipeline Steps\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: n_sequon_info.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.12.1/misc/n_sequon_info.csv\n      Name: sample_mapping.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.12.1/misc/sample_mapping.csv\n      Name: cellosaurus.txt\n      URI: https:/data.glygen.org/ln2downloads/cellosaurus/2026_06_02/cellosaurus.txt\n      Name: fuzzy_legacy_cph_start_end_positions.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv\n      Name: fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n      Name: fuzzy_legacy_qin_oglanac.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv\n      Name: fuzzy_simplecell_all_glygen_qc.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv\n      Name: known_33064451_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv\n      Name: known_33167210_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv\n      Name: known_33806155_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv\n      Name: known_34004174_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv\n      Name: known_34106099_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv\n      Name: known_legacy_cph_single_positions.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv\n      Name: known_legacy_dbogap_dbogap2_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv\n      Name: known_legacy_human_mouse_rat_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv\n      Name: known_legacy_larsson_xyl.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv\n      Name: known_legacy_reis_gastric_ags.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv\n      Name: known_legacy_sarscov2_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv\n      Name: known_unicarbkb_glycomics_study.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv\n      Name: mixed_34089345_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv\n      Name: unknown_20131323_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv\n      Name: unknown_33993882_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv\n      Name: unknown_34083726_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv\n      Name: unknown_34191522_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv\n      Name: unknown_34327564_glygen.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv\n      Name: unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n      URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n   Output Subdomain\n      Name: rat_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: rat_proteoform_glycosylation_sites_unicarbkb.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\"\n     Description: \"\"\n      Unique Values: \"158\"",
    "downloadurl": "/ln2data/releases/data/v-2.12.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"
}