{
    "bcoid": "GLY_000290",
    "title": "Glycan Sequences IUPAC Extended",
    "description": "The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan ...",
    "filename": "glycan_sequences_iupac_extended.csv",
    "filetype": "csv",
    "categories": {
        "molecule": "Glycan",
        "tags": "IUPAC Extended format",
        "status": "Reviewed",
        "file_type": "csv",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "G00002CF...",
                "?-D-NeupGc-(..."
            ],
            [
                "G00009BX...",
                "alpha-L-Fucp..."
            ]
        ],
        "headers": [
            "glytoucan_ac...",
            "sequence_iup..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "glytoucan_ac"
                },
                {
                    "type": "string",
                    "label": "sequence_iupac_extended"
                }
            ],
            [
                "G00002CF",
                "?-D-NeupGc-(2->?)-?-D-NeupGc-(2->?)-?-D-Galp-(1->?)-?-D-Glcp-(1->"
            ],
            [
                "G00009BX",
                "alpha-L-Fucp-(1->2)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-?-D-GlcNAc-(?->"
            ],
            [
                "G00012MO",
                "beta-D-GalpNAc-(1->3)-alpha-D-Galp-(1->3)-beta-D-Galp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00013MO",
                "beta-D-Galp-(1->3)-beta-D-Galp-(1->4)-beta-D-Galp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00014MO",
                "beta-D-GalpNAc-(1->4)-beta-D-GlcpNAc-(1->3)-beta-D-Manp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00015MO",
                "beta-D-GlcpNAc-(1->2)-alpha-D-Manp-(1->3)-beta-D-Manp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00016MO",
                "alpha-D-Galp-(1->4)-?-D-Gal-(?->"
            ],
            [
                "G00017MO",
                "beta-D-GlcpA-(1->3)-beta-D-GlcpNAc-(1->4)-beta-D-GlcpA-(1->3)-?-D-GlcNAc-(?->"
            ],
            [
                "G00018MO",
                "beta-D-GlcpA-(1->3)-beta-D-GalpNAc4S-(1->4)-beta-D-GlcpA-(1->3)-?-D-GalNAc4S-(?->"
            ],
            [
                "G00019MO",
                "beta-D-IdopA-(1->3)-beta-D-GalpNAc4S-(1->4)-beta-D-IdopA-(1->3)-?-D-GalNAc4S-(?->"
            ],
            [
                "G00020MO",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc6S-(1->3)-beta-D-Galp-(1->4)-?-D-GlcNAc6S-(?->"
            ],
            [
                "G00023MO",
                "beta-D-GlcpNAc3lRLac-(1->4)-beta-D-GlcpNAc-(1->4)-beta-D-GlcpNAc3lRLac-(1->4)-?-D-GlcpNAc-(1->"
            ],
            [
                "G00024MO",
                "beta-D-Glcp-(1->3)-beta-D-Glcp-(1->3)-beta-D-Glcp-(1->"
            ],
            [
                "G00025AJ",
                "beta-D-Galp-(1->4)[alpha-L-Fucp-(1->3)]-?-D-Glc-(?->"
            ],
            [
                "G00025MO",
                "beta-D-Glcp-(1->4)-beta-D-Glcp-(1->4)-beta-D-Glcp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00026MO",
                "alpha-D-Manp-(1->3)[alpha-D-Manp-(1->6)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)-?-D-GlcNAc-(?->"
            ],
            [
                "G00027JG",
                "alpha-L-Fucp-(1->2)-beta-D-Galp-(1->3)[alpha-L-Fucp-(1->2)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->6)]-beta-D-Gal?NAc-(1->"
            ],
            [
                "G00027MO",
                "alpha-D-Manp-(1->3)[alpha-D-Manp-(1->6)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00028MO",
                "alpha-D-Manp-(1->3)[alpha-D-Manp-(1->3)[alpha-D-Manp-(1->6)]-alpha-D-Manp-(1->6)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)-?-D-GlcNAc-(?->"
            ],
            [
                "G00029MO",
                "beta-D-GlcpNAc-(1->2/4)-alpha-D-Manp-(1->3)[alpha-D-Manp-(1->3/6)-alpha-D-Manp-(1->6)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)-?-D-GlcpNAc-(1->"
            ],
            [
                "G00030MO",
                "beta-D-GlcpNAc-(1->2/4)-alpha-D-Manp-(1->3)[beta-D-GlcpNAc-(1->2/4)-alpha-D-Manp-(1->6)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)-?-D-GlcNAc-(?->"
            ],
            [
                "G00031MO",
                "beta-D-Galp-(1->3)-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00032MO",
                "beta-D-Galp-(1->3)-?-D-GalNAc-(?->"
            ],
            [
                "G00033MO",
                "beta-D-Galp-(1->3)[beta-D-GlcpNAc-(1->6)]-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00034MO",
                "beta-D-Galp-(1->3)[beta-D-GlcpNAc-(1->6)]-?-D-GalNAc-(?->"
            ],
            [
                "G00034WH",
                "alpha-D-Glcp-(1->6)-alpha-D-Glcp-(1->6)-alpha-D-Glcp-(1->6)-alpha-D-Glcp-(1->4)-alpha-D-Glcp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00035MO",
                "beta-D-GlcpNAc-(1->3)-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00036MO",
                "beta-D-GlcpNAc-(1->3)-?-D-GalNAc-(?->"
            ],
            [
                "G00037MO",
                "beta-D-GlcpNAc-(1->3)[beta-D-GlcpNAc-(1->6)]-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00038MO",
                "beta-D-GlcpNAc-(1->3)[beta-D-GlcpNAc-(1->6)]-?-D-GalNAc-(?->"
            ],
            [
                "G00039MO",
                "alpha-D-GalpNAc-(1->3)-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00040MO",
                "alpha-D-GalpNAc-(1->3)-?-D-GalNAc-(?->"
            ],
            [
                "G00041IL",
                "beta-D-Galp-(1->3)-?-D-GlcpNAc-(1->3)[alpha-D-NeupAc-(2->6)]-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00041MO",
                "beta-D-GlcpNAc-(1->6)-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00042MO",
                "beta-D-GlcpNAc-(1->6)-?-D-GalNAc-(?->"
            ],
            [
                "G00043MO",
                "alpha-D-GalpNAc-(1->6)-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00044MO",
                "alpha-D-GalpNAc-(1->6)-?-D-GalNAc-(?->"
            ],
            [
                "G00045MO",
                "alpha-D-Manp-(1->2)-alpha-D-Manp-(1->6)-alpha-D-Manp-(1->4)-?-D-GlcN-(?->"
            ],
            [
                "G00046MO",
                "alpha-D-Galp-(1->3)-?-D-Gal-(?->"
            ],
            [
                "G00047MO",
                "beta-D-Galp-(1->3)[alpha-L-Fucp-(1->4)]-?-D-GlcpNAc-(1->"
            ],
            [
                "G00048MO",
                "alpha-L-Fucp-(1->2)-beta-D-Galp-(1->3)[alpha-L-Fucp-(1->4)]-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00049MO",
                "beta-D-Galp-(1->3)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00050MO",
                "alpha-L-Fucp-(1->2)-beta-D-Galp-(1->3)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00051MO",
                "beta-D-Galp-(1->4)[alpha-L-Fucp-(1->3)]-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00052MO",
                "alpha-L-Fucp-(1->2)-beta-D-Galp-(1->4)[alpha-L-Fucp-(1->3)]-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00053MO",
                "alpha-D-NeupAc-(2->3)-beta-D-Galp-(1->3)[alpha-L-Fucp-(1->4)]-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00054MO",
                "alpha-D-NeupAc-(2->3)-beta-D-Galp-(1->4)[alpha-L-Fucp-(1->3)]-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00055MO",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00056HH",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2)[beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->6)]-alpha-D-Manp-(1->?)[beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2)-alpha-D-Manp-(1->?)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)[?-L-Fucp-(1->?)]-?-D-GlcpNAc-(1->"
            ],
            [
                "G00056MO",
                "beta-D-Galp-(1->3)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00057MO",
                "beta-D-GalpNAc-(1->4)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00058MO",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00059MO",
                "alpha-D-Galp-(1->4)-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00060BT",
                "alpha-D-Manp-(1->3)[alpha-D-Manp-(1->3)-beta-D-Manp-(1->6)]-beta-D-Manp-(1->4)-?-D-GlcNAc-(?->"
            ],
            [
                "G00060MO",
                "alpha-D-Galp-(1->4)-beta-D-Galp-(1->4)-beta-D-GalpNAc-(1->3)-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00061MO",
                "beta-D-GalpNAc-(1->3)-alpha-D-Galp-(1->4)-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00062MO",
                "alpha-D-NeupAc-(2->3)[beta-D-GalpNAc-(1->4)]-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->"
            ],
            [
                "G00063MO",
                "alpha-D-NeupAc-(2->3)[beta-D-GalpNAc-(1->4)]-beta-D-Galp-(1->3)[alpha-D-NeupAc-(2->6)]-beta-D-GalpNAc-(1->"
            ],
            [
                "G00064MO",
                "alpha-D-GlcpNAc-(1->3)-beta-D-GalpNAc-(1->3)-alpha-D-Galp-(1->4)-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00065MO",
                "alpha-D-NeupAc-(2->3)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00066MO",
                "alpha-D-GalpNAc-(1->3)[alpha-L-Fucp-(1->2)]-beta-D-Galp-(1->"
            ],
            [
                "G00067MO",
                "beta-D-Galp-(1->3)[alpha-L-Fucp-(1->2)]-beta-D-Galp-(1->"
            ],
            [
                "G00068MO",
                "alpha-L-Fucp-(1->2)-beta-D-Galp-(1->"
            ],
            [
                "G00069MO",
                "beta-D-Galp-(1->3)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00070MO",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00071MO",
                "beta-D-Galp-(1->3)-beta-D-GalpNAc-(1->4)-beta-D-Galp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00072MO",
                "beta-D-GalpNAc-(1->3)-beta-D-Galp-(1->4)-beta-D-Galp-(1->4)-?-D-Glc-(?->"
            ],
            [
                "G00076PK",
                "alpha-D-Galp-(1->4)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->"
            ],
            [
                "G00089VH",
                "alpha-D-NeupAc-(2->6)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2)-beta-D-Manp-(1->3)[alpha-D-NeupAc-(2->6)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2)-beta-D-Manp-(1->6)]-alpha-D-Manp-(1->4)-?-D-GlcNAc-(?->"
            ],
            [
                "G00090SL",
                "alpha-D-Manp-(1->6)-?-D-Man-(?->"
            ],
            [
                "G00091RT",
                "alpha-D-Manp-(1->2)-alpha-D-Manp-(1->3)[alpha-D-Manp-(1->2)-alpha-D-Manp-(1->6)]-alpha-D-Manp-(1->"
            ],
            [
                "G00094SE",
                "alpha-D-Galp-(1->3)-alpha-D-GalpNAc-(1->3)[alpha-L-Fucp-(1->2)]-beta-D-Galp-(1->3)[beta-D-GlcpNAc-(1->3)-beta-D-GlcpNAc-(1->6)]-alpha-D-GalpNAc-(1->"
            ],
            [
                "G00106LE",
                "?-D-NeupAc-(2->?)-?-D-Galp6S-(1->?)[?-L-Fucp-(1->?)]-?-D-GlcNAc-(?->"
            ],
            [
                "G00112IO",
                "alpha-D-GalpNAc-(1->3)-beta-D-Galp-(1->3)-beta-D-GlcpNAc-(1->3)[beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->6)]-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->3)-?-D-GalNAc-(?->"
            ],
            [
                "G00120QS",
                "alpha-D-Manp-(1->6)-?-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)-?-D-GlcpNAc-(1->"
            ],
            [
                "G00123JF",
                "beta-D-Xylf-(1->"
            ],
            [
                "G00133UK",
                "alpha-D-NeupGc-(2->3)[beta-D-Galp-(1->4)]-alpha-D-Galp-(1->"
            ],
            [
                "G00140XB",
                "alpha-D-Galp-(1->3)-?-D-Manp-(1->"
            ],
            [
                "G00140YZ",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->3/6)[alpha-L-Fucp-(1->2)-beta-D-Galp-(1->3/6)]-?-D-GalNAc-(?->"
            ],
            [
                "G00141ZD",
                "alpha-D-Glcp-(1->4)[alpha-D-Galp-(1->6)]-?-D-Glc-(?->"
            ],
            [
                "G00152LK",
                "beta-D-Glcp-(1->3)-beta-D-Glcp-(1->3)-beta-D-Glcp-(1->3)-alpha-D-Glcp-(1->3)-beta-D-Glcp-(1->3)-beta-D-Glcp-(1->"
            ],
            [
                "G00153LJ",
                "beta-D-Galp-(1->2)-beta-D-Galp-(1->2)-beta-D-Galp-(1->"
            ],
            [
                "G00157WT",
                "alpha-D-NeupAc-(2->3)-beta-D-Galp-(1->3)[alpha-L-Fucp-(1->4)]-beta-D-GlcpNAc-(1->3)[beta-D-Galp-(1->3)[alpha-L-Fucp-(1->4)]-beta-D-GlcpNAc-(1->3)-beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->6)]-beta-D-Galp-(1->4)-beta-D-Glcp-(1->"
            ],
            [
                "G00167VE",
                "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2)[beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->6)]-alpha-D-Manp-(1->3/6)[beta-D-GalpNAc-(1->4)-beta-D-GlcpNAc-(1->2)-alpha-D-Manp-(1->3/6)]-beta-D-Manp-(1->4)-beta-D-GlcpNAc-(1->4)[alpha-L-Fucp-(1->6)]-?-D-GlcpNAc-(1->"
            ]
        ]
    },
    "readme": "Name\n   - Glycan Sequences IUPAC Extended\n\nVersion\n   - 1.8.25\n\nCreated on\n  - 2019-11-13T16:31:31.525156\n\nModified on\n   - 2020-05-01T15:05:00.162142\n\nCreated by\n   - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n   - Nathan Edwards [nje5@georgetown.edu]\n\nChecksum\n   - \n\nUsability Domain\n   - The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/\n\nDescription Domain\n   Keywords\n   - Glycan\n   - GlyTouCan Accession\n   - IUPAC Extended\n\n   Pipeline Steps\n   - Step-1: The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list.\n\nExecution Domain\n   Scripts   - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-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: iupac_extended.zip\n      URI: https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip\n   Output Subdomain\n      Name: glycan_sequences_iupac_extended.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_iupac_extended.csv\n      Name: glycan_sequences_iupac_extended.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_iupac_extended.stat.csv\n\nFields\n      Name: \"src_xref_key\"\n     Description: \"Source Xref  key\"\n      Unique Values: \"1\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"119\"\n      Name: \"title\"\n     Description: \"Title of the published article in the journal\"\n      Unique Values: \"119\"\n      Name: \"src_xref_id\"\n     Description: \"Source X-ref ID\"\n      Unique Values: \"120\"\n      Name: \"journal_name\"\n     Description: \"The name of the journal in which the article is published\"\n      Unique Values: \"49\"\n      Name: \"authors\"\n     Description: \"NA\"\n      Unique Values: \"118\"\n      Name: \"publication_date\"\n     Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n      Unique Values: \"117\"\n      Name: \"glytoucan_ac\"\n     Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n      Unique Values: \"115\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"1\"",
    "downloadurl": "/ln2data/releases/data/v-1.8.25/reviewed/glycan_sequences_iupac_extended.csv"
}
