{
    "bcoid": "GLY_000033",
    "title": "Human Protein Information (UniProtKB)",
    "description": "The Human Protein Information dataset contains human [taxid:9606] UniProtKB canonical accessions with ...",
    "filename": "human_protein_info_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": "Homo sapiens",
        "molecule": "Protein",
        "tags": "Protein Information",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q8TBF5-1...",
                "PIGX_HUMAN..."
            ],
            [
                "Q8TBF4-1...",
                "ZCRB1_HUMAN..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "uniprotkb_id..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "uniprotkb_id"
                },
                {
                    "type": "string",
                    "label": "uniprotkb_protein_mass"
                },
                {
                    "type": "string",
                    "label": "uniprotkb_protein_length"
                }
            ],
            [
                "Q8TBF5-1",
                "PIGX_HUMAN",
                "28788",
                "258"
            ],
            [
                "Q8TBF4-1",
                "ZCRB1_HUMAN",
                "24592",
                "217"
            ],
            [
                "Q9NRJ4-1",
                "TULP4_HUMAN",
                "169000",
                "1543"
            ],
            [
                "Q9NQ79-1",
                "CRAC1_HUMAN",
                "71421",
                "661"
            ],
            [
                "Q9NVL8-1",
                "CC198_HUMAN",
                "34690",
                "296"
            ],
            [
                "Q9NRQ5-1",
                "SMCO4_HUMAN",
                "6738",
                "59"
            ],
            [
                "Q8IZF5-1",
                "AGRF3_HUMAN",
                "116341",
                "1079"
            ],
            [
                "P30613-1",
                "KPYR_HUMAN",
                "61830",
                "574"
            ],
            [
                "Q5H9L4-1",
                "TAF7L_HUMAN",
                "52588",
                "462"
            ],
            [
                "Q9BZL4-1",
                "PP12C_HUMAN",
                "84881",
                "782"
            ],
            [
                "Q9NVL1-1",
                "FA86C_HUMAN",
                "18454",
                "165"
            ],
            [
                "Q5QJ38-1",
                "TCHL1_HUMAN",
                "99275",
                "904"
            ],
            [
                "Q9NQ75-1",
                "CASS4_HUMAN",
                "87144",
                "786"
            ],
            [
                "P20930-1",
                "FILA_HUMAN",
                "435170",
                "4061"
            ],
            [
                "P20933-1",
                "ASPG_HUMAN",
                "37208",
                "346"
            ],
            [
                "P20936-1",
                "RASA1_HUMAN",
                "116403",
                "1047"
            ],
            [
                "A0A1W2PQ27-1",
                "A0A1W2PQ27_HUMAN",
                "22511",
                "194"
            ],
            [
                "Q8NFX7-1",
                "STXB6_HUMAN",
                "23554",
                "210"
            ],
            [
                "Q9UM21-1",
                "MGT4A_HUMAN",
                "61544",
                "535"
            ],
            [
                "Q496A3-1",
                "SPAS1_HUMAN",
                "33705",
                "300"
            ],
            [
                "P83859-1",
                "OX26_HUMAN",
                "14941",
                "136"
            ],
            [
                "P40617-1",
                "ARL4A_HUMAN",
                "22615",
                "200"
            ],
            [
                "Q70EL4-1",
                "UBP43_HUMAN",
                "122809",
                "1123"
            ],
            [
                "Q8TBF2-1",
                "PXL2B_HUMAN",
                "21223",
                "198"
            ],
            [
                "Q15573-1",
                "TAF1A_HUMAN",
                "52676",
                "450"
            ],
            [
                "Q15572-1",
                "TAF1C_HUMAN",
                "95213",
                "869"
            ],
            [
                "Q9BQP9-1",
                "BPIA3_HUMAN",
                "28436",
                "254"
            ],
            [
                "Q9H999-1",
                "PANK3_HUMAN",
                "41094",
                "370"
            ],
            [
                "P23919-1",
                "KTHY_HUMAN",
                "23819",
                "212"
            ],
            [
                "Q8NHX4-1",
                "SPTA3_HUMAN",
                "20901",
                "192"
            ],
            [
                "Q8NHX9-1",
                "TPC2_HUMAN",
                "85243",
                "752"
            ],
            [
                "A8MU46-1",
                "SMTL1_HUMAN",
                "52987",
                "494"
            ],
            [
                "Q6ZNW5-1",
                "GDPP1_HUMAN",
                "42362",
                "385"
            ],
            [
                "Q9NXR8-1",
                "ING3_HUMAN",
                "46743",
                "418"
            ],
            [
                "Q9C0H2-1",
                "TTYH3_HUMAN",
                "57545",
                "523"
            ],
            [
                "Q9C0H5-1",
                "RHG39_HUMAN",
                "121286",
                "1083"
            ],
            [
                "A0A494C0I6-1",
                "A0A494C0I6_HUMAN",
                "8392",
                "67"
            ],
            [
                "Q4VXU2-1",
                "PAP1L_HUMAN",
                "68392",
                "614"
            ],
            [
                "Q9C0H6-1",
                "KLHL4_HUMAN",
                "80245",
                "718"
            ],
            [
                "Q9C0H9-5",
                "SRCN1_HUMAN",
                "127105",
                "1183"
            ],
            [
                "Q9NXR1-2",
                "NDE1_HUMAN",
                "37721",
                "335"
            ],
            [
                "Q00537-1",
                "CDK17_HUMAN",
                "59582",
                "523"
            ],
            [
                "Q00536-1",
                "CDK16_HUMAN",
                "55716",
                "496"
            ],
            [
                "Q9NXR5-1",
                "ANR10_HUMAN",
                "44768",
                "420"
            ],
            [
                "Q00532-1",
                "CDKL1_HUMAN",
                "41803",
                "358"
            ],
            [
                "Q96J66-1",
                "ABCCB_HUMAN",
                "154301",
                "1382"
            ],
            [
                "O00244-1",
                "ATOX1_HUMAN",
                "7402",
                "68"
            ],
            [
                "Q9UBM8-1",
                "MGT4C_HUMAN",
                "56061",
                "478"
            ],
            [
                "Q9H2V7-1",
                "SPNS1_HUMAN",
                "56630",
                "528"
            ],
            [
                "O00241-1",
                "SIRB1_HUMAN",
                "43211",
                "398"
            ],
            [
                "O00716-1",
                "E2F3_HUMAN",
                "49162",
                "465"
            ],
            [
                "Q8IX01-1",
                "SUGP2_HUMAN",
                "120207",
                "1082"
            ],
            [
                "G5EA27-1",
                "G5EA27_HUMAN",
                "11630",
                "106"
            ],
            [
                "Q9UBM1-1",
                "PEMT_HUMAN",
                "22134",
                "199"
            ],
            [
                "A8MTA8-1",
                "F166B_HUMAN",
                "30575",
                "275"
            ],
            [
                "Q9UBM4-1",
                "OPT_HUMAN",
                "37261",
                "332"
            ],
            [
                "P24522-1",
                "GA45A_HUMAN",
                "18336",
                "165"
            ],
            [
                "Q13835-1",
                "PKP1_HUMAN",
                "82861",
                "747"
            ],
            [
                "Q7Z3T1-1",
                "OR2W3_HUMAN",
                "34789",
                "314"
            ],
            [
                "A0AVF1-1",
                "IFT56_HUMAN",
                "64178",
                "554"
            ],
            [
                "P40424-1",
                "PBX1_HUMAN",
                "46626",
                "430"
            ],
            [
                "P40425-1",
                "PBX2_HUMAN",
                "45881",
                "430"
            ],
            [
                "P09001-1",
                "RM03_HUMAN",
                "38633",
                "348"
            ],
            [
                "Q8IZK6-1",
                "MCLN2_HUMAN",
                "65942",
                "566"
            ],
            [
                "P40429-1",
                "RL13A_HUMAN",
                "23577",
                "203"
            ],
            [
                "P51991-1",
                "ROA3_HUMAN",
                "39595",
                "378"
            ],
            [
                "Q13838-1",
                "DX39B_HUMAN",
                "48991",
                "428"
            ],
            [
                "O00337-1",
                "S28A1_HUMAN",
                "71584",
                "649"
            ],
            [
                "Q8TDW7-3",
                "FAT3_HUMAN",
                "501978",
                "4557"
            ],
            [
                "Q5M775-1",
                "CYTSB_HUMAN",
                "118585",
                "1068"
            ],
            [
                "Q8WTV0-1",
                "SCRB1_HUMAN",
                "60878",
                "552"
            ],
            [
                "Q9H2I8-1",
                "LRMDA_HUMAN",
                "22568",
                "198"
            ],
            [
                "A0A075B6S2-1",
                "KVD29_HUMAN",
                "13143",
                "120"
            ],
            [
                "P08842-1",
                "STS_HUMAN",
                "65492",
                "583"
            ],
            [
                "P03891-1",
                "NU2M_HUMAN",
                "38961",
                "347"
            ],
            [
                "Q5VUR7-1",
                "A20A3_HUMAN",
                "94108",
                "823"
            ],
            [
                "P48960-1",
                "CD97_HUMAN",
                "91869",
                "835"
            ],
            [
                "P03897-1",
                "NU3M_HUMAN",
                "13186",
                "115"
            ],
            [
                "P02768-1",
                "ALBU_HUMAN",
                "69367",
                "609"
            ],
            [
                "A0A075B7E8-1",
                "A0A075B7E8_HUMAN",
                "12904",
                "117"
            ],
            [
                "P20645-1",
                "MPRD_HUMAN",
                "30993",
                "277"
            ],
            [
                "P05386-1",
                "RLA1_HUMAN",
                "11514",
                "114"
            ],
            [
                "P05387-1",
                "RLA2_HUMAN",
                "11665",
                "115"
            ],
            [
                "P24863-1",
                "CCNC_HUMAN",
                "33243",
                "283"
            ]
        ]
    },
    "readme": "Name\n   - Human Protein Information (UniProtKB)\n\nVersion\n   - 1.5.23\n\nCreated on\n  - 2019-01-23T17:21:05.900608\n\nModified on\n   - 2020-04-10T11:27:03.338813\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.gwu.edu]\n\nAuthors\n   - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n   - \n\nUsability Domain\n   - The Human Protein Information dataset contains human [taxid:9606] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n   Keywords\n   - UniProtKB entry id\n   - UniProtKB mnemonic name\n   - protein length\n   - protein mass\n\n   Pipeline Steps\n   - Step-1: The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format\n\nExecution Domain\n   Scripts   - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-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: uniprot-proteome-homo-sapiens.nt\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.5.23/source/uniprot-proteome-homo-sapiens.nt\n      Name: human_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.5.23/reviewed/human_protein_masterlist.csv\n   Output Subdomain\n      Name: human_protein_info_uniprotkb.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.5.23/reviewed/human_protein_info_uniprotkb.csv\n      Name: human_protein_info_uniprotkb.stat.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.5.23/reviewed/human_protein_info_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_protein_length\"\n     Description: \"Length of the protein sequence\"\n      Unique Values: \"2163\"\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n      Unique Values: \"20656\"\n      Name: \"uniprotkb_protein_mass\"\n     Description: \"Molecular Mass of the protein in Daltons (Da)\"\n      Unique Values: \"18761\"\n      Name: \"uniprotkb_id\"\n     Description: \"The entry name or mnemonic identifier assigned to the protein accession that consists of up to 11 uppercase alphanumeric characters for UniProtKB/Swiss-Prot entry and up to 16 uppercase alphanumeric characters for UniProtKB/TrEMBL entry with a defined naming convention\"\n      Unique Values: \"20656\"",
    "downloadurl": "/ln2data/releases/data/v-1.5.23/reviewed/human_protein_info_uniprotkb.csv"
}
