{
    "bcoid": "GLY_000106",
    "title": "Human UniProtKB Xref InterPro",
    "description": "The Human UniProtKB Xref InterPro contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...",
    "filename": "human_protein_xref_interpro.csv",
    "filetype": "csv",
    "categories": {
        "species": "Homo sapiens",
        "molecule": "Protein",
        "tags": "Interpro cross-references",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "O75818-1...",
                "protein_xref..."
            ],
            [
                "P30613-1...",
                "protein_xref..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "xref_key..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                },
                {
                    "type": "string",
                    "label": "xref_label"
                }
            ],
            [
                "O75818-1",
                "protein_xref_interpro",
                "IPR013893",
                "RNase_P_Rpp40"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR011037",
                "Pyrv_Knase-like_insert_dom_sf"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR015813",
                "Pyrv/PenolPyrv_Kinase-like_dom"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR001697",
                "Pyr_Knase"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR015793",
                "Pyrv_Knase_brl"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR015795",
                "Pyrv_Knase_C"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR018209",
                "Pyrv_Knase_AS"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR036918",
                "Pyrv_Knase_C_sf"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR015806",
                "Pyrv_Knase_insert_dom_sf"
            ],
            [
                "P30613-1",
                "protein_xref_interpro",
                "IPR040442",
                "Pyrv_Kinase-like_dom_sf"
            ],
            [
                "P05093-1",
                "protein_xref_interpro",
                "IPR001128",
                "Cyt_P450"
            ],
            [
                "P05093-1",
                "protein_xref_interpro",
                "IPR002401",
                "Cyt_P450_E_grp-I"
            ],
            [
                "P05093-1",
                "protein_xref_interpro",
                "IPR017972",
                "Cyt_P450_CS"
            ],
            [
                "P05093-1",
                "protein_xref_interpro",
                "IPR036396",
                "Cyt_P450_sf"
            ],
            [
                "A0A1W2PQ27-1",
                "protein_xref_interpro",
                "IPR006811",
                "RNA_pol_II_suA"
            ],
            [
                "A0A1W2PQ27-1",
                "protein_xref_interpro",
                "IPR036196",
                "Ptyr_pPase_sf"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR000651",
                "Ras-like_Gua-exchang_fac_N"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR000159",
                "RA_dom"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR014710",
                "RmlC-like_jellyroll"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR001478",
                "PDZ"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR036034",
                "PDZ_sf"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR008937",
                "Ras-like_GEF"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR001895",
                "RASGEF_cat_dom"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR023578",
                "Ras_GEF_dom_sf"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR000595",
                "cNMP-bd_dom"
            ],
            [
                "Q8TEU7-1",
                "protein_xref_interpro",
                "IPR018490",
                "cNMP-bd-like"
            ],
            [
                "P09471-1",
                "protein_xref_interpro",
                "IPR027417",
                "P-loop_NTPase"
            ],
            [
                "P09471-1",
                "protein_xref_interpro",
                "IPR001019",
                "Gprotein_alpha_su"
            ],
            [
                "Q92994-1",
                "protein_xref_interpro",
                "IPR013150",
                "TFIIB_cyclin"
            ],
            [
                "Q92994-1",
                "protein_xref_interpro",
                "IPR013763",
                "Cyclin-like"
            ],
            [
                "Q92994-1",
                "protein_xref_interpro",
                "IPR036915",
                "Cyclin-like_sf"
            ],
            [
                "Q92994-1",
                "protein_xref_interpro",
                "IPR000812",
                "TFIIB"
            ],
            [
                "P23769-1",
                "protein_xref_interpro",
                "IPR029522",
                "GATA-2"
            ],
            [
                "P23769-1",
                "protein_xref_interpro",
                "IPR039355",
                "Transcription_factor_GATA"
            ],
            [
                "Q7RTN6-1",
                "protein_xref_interpro",
                "IPR000719",
                "Prot_kinase_dom"
            ],
            [
                "Q7RTN6-1",
                "protein_xref_interpro",
                "IPR011009",
                "Kinase-like_dom_sf"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR001452",
                "SH3_domain"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR001849",
                "PH_domain"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR003598",
                "Ig_sub2"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR003599",
                "Ig_sub"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR007110",
                "Ig-like_dom"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR011993",
                "PH-like_dom_sf"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR013783",
                "Ig-like_fold"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR036028",
                "SH3-like_dom_sf"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR036179",
                "Ig-like_dom_sf"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR000219",
                "DH-domain"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR035899",
                "DBL_dom_sf"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR002017",
                "Spectrin_repeat"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR018159",
                "Spectrin/alpha-actinin"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR013098",
                "Ig_I-set"
            ],
            [
                "O75962-1",
                "protein_xref_interpro",
                "IPR028570",
                "TRIO"
            ],
            [
                "P23919-1",
                "protein_xref_interpro",
                "IPR027417",
                "P-loop_NTPase"
            ],
            [
                "P23919-1",
                "protein_xref_interpro",
                "IPR018094",
                "Thymidylate_kinase"
            ],
            [
                "P23919-1",
                "protein_xref_interpro",
                "IPR039430",
                "Thymidylate_kin-like_dom"
            ],
            [
                "P23919-1",
                "protein_xref_interpro",
                "IPR018095",
                "Thymidylate_kin_CS"
            ],
            [
                "Q8NHX4-1",
                "protein_xref_interpro",
                "IPR026717",
                "SPATA3"
            ],
            [
                "Q8NHX9-1",
                "protein_xref_interpro",
                "IPR028798",
                "TPC2"
            ],
            [
                "Q8NHX9-1",
                "protein_xref_interpro",
                "IPR005821",
                "Ion_trans_dom"
            ],
            [
                "Q8NHX9-1",
                "protein_xref_interpro",
                "IPR027359",
                "Volt_channel_dom_sf"
            ],
            [
                "H3BTG2-1",
                "protein_xref_interpro",
                "IPR038788",
                "TEX46-like"
            ],
            [
                "P10242-1",
                "protein_xref_interpro",
                "IPR009057",
                "Homeobox-like_sf"
            ],
            [
                "P10242-1",
                "protein_xref_interpro",
                "IPR001005",
                "SANT/Myb"
            ],
            [
                "P10242-1",
                "protein_xref_interpro",
                "IPR017930",
                "Myb_dom"
            ],
            [
                "P10242-1",
                "protein_xref_interpro",
                "IPR012642",
                "Tscrpt_reg_Wos2-domain"
            ],
            [
                "Q9GZW8-1",
                "protein_xref_interpro",
                "IPR007237",
                "CD20-like"
            ],
            [
                "Q9GZW8-1",
                "protein_xref_interpro",
                "IPR030417",
                "MS4A"
            ],
            [
                "Q9GZW8-1",
                "protein_xref_interpro",
                "IPR030423",
                "MS4A7"
            ],
            [
                "Q9C0H2-1",
                "protein_xref_interpro",
                "IPR006990",
                "Tweety"
            ],
            [
                "Q9C0H5-1",
                "protein_xref_interpro",
                "IPR000198",
                "RhoGAP_dom"
            ],
            [
                "Q9C0H5-1",
                "protein_xref_interpro",
                "IPR008936",
                "Rho_GTPase_activation_prot"
            ],
            [
                "Q9C0H5-1",
                "protein_xref_interpro",
                "IPR001202",
                "WW_dom"
            ],
            [
                "Q9C0H5-1",
                "protein_xref_interpro",
                "IPR036020",
                "WW_dom_sf"
            ],
            [
                "Q9C0H5-1",
                "protein_xref_interpro",
                "IPR000857",
                "MyTH4_dom"
            ],
            [
                "Q9C0H5-1",
                "protein_xref_interpro",
                "IPR038185",
                "MyTH4_dom_sf"
            ],
            [
                "Q9C0H6-1",
                "protein_xref_interpro",
                "IPR000210",
                "BTB/POZ_dom"
            ],
            [
                "Q9C0H6-1",
                "protein_xref_interpro",
                "IPR011333",
                "SKP1/BTB/POZ_sf"
            ],
            [
                "Q9C0H6-1",
                "protein_xref_interpro",
                "IPR006652",
                "Kelch_1"
            ],
            [
                "Q9C0H6-1",
                "protein_xref_interpro",
                "IPR015915",
                "Kelch-typ_b-propeller"
            ],
            [
                "Q9C0H6-1",
                "protein_xref_interpro",
                "IPR011705",
                "BACK"
            ],
            [
                "Q9C0H9-5",
                "protein_xref_interpro",
                "IPR026727",
                "Srcin1"
            ],
            [
                "Q9C0H9-5",
                "protein_xref_interpro",
                "IPR022782",
                "AIP3-like_C"
            ],
            [
                "Q86VV8-1",
                "protein_xref_interpro",
                "IPR011989",
                "ARM-like"
            ],
            [
                "Q86VV8-1",
                "protein_xref_interpro",
                "IPR016024",
                "ARM-type_fold"
            ],
            [
                "Q86VV8-1",
                "protein_xref_interpro",
                "IPR030791",
                "Rotatin"
            ]
        ]
    },
    "readme": "Name\n   - Human UniProtKB Xref InterPro\n\nVersion\n   - 1.9.9\n\nCreated on\n  - 2019-03-15T12:05:44.324142\n\nModified on\n   - 2020-04-10T11:35:29.829977\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 UniProtKB Xref InterPro contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. 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   - InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them.\n\nDescription Domain\n   Keywords\n   - protein family\n   - protein domain\n   - protein functional site\n   - InterPro\n   - cross-reference\n\n   Pipeline Steps\n   - Step-1: The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset\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/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt\n      Name: human_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n   Output Subdomain\n      Name: human_protein_xref_interpro.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_interpro.csv\n      Name: human_protein_xref_interpro.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_interpro.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"1\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"1\"\n      Name: \"title\"\n     Description: \"Title of the published article in the journal\"\n      Unique Values: \"1\"\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: \"journal_name\"\n     Description: \"The name of the journal in which the article is published\"\n      Unique Values: \"1\"\n      Name: \"authors\"\n     Description: \"NA\"\n      Unique Values: \"1\"\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: \"1\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"1\"",
    "downloadurl": "/ln2data/releases/data/v-1.9.9/reviewed/human_protein_xref_interpro.csv"
}
