{
    "bcoid": "GLY_000243",
    "title": "Rat UniProtKB Xref InterPro",
    "description": "The Rat UniprotKB Xref InterPro contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced ...",
    "filename": "rat_protein_xref_interpro.csv",
    "filetype": "csv",
    "categories": {
        "species": "Rattus norvegicus",
        "molecule": "Protein",
        "tags": "Interpro cross-references",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q5RJK9-1...",
                "protein_xref..."
            ],
            [
                "Q5RJK9-1...",
                "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"
                }
            ],
            [
                "Q5RJK9-1",
                "protein_xref_interpro",
                "IPR011263",
                "DNA-dir_RNA_pol_RpoA/D/Rpb3"
            ],
            [
                "Q5RJK9-1",
                "protein_xref_interpro",
                "IPR036603",
                "RBP11-like"
            ],
            [
                "Q5RJK9-1",
                "protein_xref_interpro",
                "IPR001514",
                "DNA-dir_RNA_pol_30-40kDasu_CS"
            ],
            [
                "Q5RJK9-1",
                "protein_xref_interpro",
                "IPR011262",
                "DNA-dir_RNA_pol_insert"
            ],
            [
                "Q5RJK9-1",
                "protein_xref_interpro",
                "IPR033901",
                "RNAPI/II_AC40"
            ],
            [
                "Q5RJK9-1",
                "protein_xref_interpro",
                "IPR036643",
                "RNApol_insert_sf"
            ],
            [
                "Q5RJK8-1",
                "protein_xref_interpro",
                "IPR002110",
                "Ankyrin_rpt"
            ],
            [
                "Q5RJK8-1",
                "protein_xref_interpro",
                "IPR020683",
                "Ankyrin_rpt-contain_dom"
            ],
            [
                "Q5RJK8-1",
                "protein_xref_interpro",
                "IPR036770",
                "Ankyrin_rpt-contain_sf"
            ],
            [
                "Q5RJK8-1",
                "protein_xref_interpro",
                "IPR000582",
                "Acyl-CoA-binding_protein"
            ],
            [
                "Q5RJK8-1",
                "protein_xref_interpro",
                "IPR014352",
                "FERM/acyl-CoA-bd_prot_sf"
            ],
            [
                "Q5RJK8-1",
                "protein_xref_interpro",
                "IPR035984",
                "Acyl-CoA-binding_sf"
            ],
            [
                "D3ZZY8-1",
                "protein_xref_interpro",
                "IPR000276",
                "GPCR_Rhodpsn"
            ],
            [
                "D3ZZY8-1",
                "protein_xref_interpro",
                "IPR017452",
                "GPCR_Rhodpsn_7TM"
            ],
            [
                "D3ZZY8-1",
                "protein_xref_interpro",
                "IPR000725",
                "Olfact_rcpt"
            ],
            [
                "D3ZG10-1",
                "protein_xref_interpro",
                "IPR035646",
                "GRAP2_C_SH3"
            ],
            [
                "D3ZG10-1",
                "protein_xref_interpro",
                "IPR000980",
                "SH2"
            ],
            [
                "D3ZG10-1",
                "protein_xref_interpro",
                "IPR001452",
                "SH3_domain"
            ],
            [
                "D3ZG10-1",
                "protein_xref_interpro",
                "IPR036028",
                "SH3-like_dom_sf"
            ],
            [
                "D3ZG10-1",
                "protein_xref_interpro",
                "IPR036860",
                "SH2_dom_sf"
            ],
            [
                "D3ZG10-1",
                "protein_xref_interpro",
                "IPR043539",
                "Grb2-like"
            ],
            [
                "D3ZB44-1",
                "protein_xref_interpro",
                "IPR013087",
                "Znf_C2H2_type"
            ],
            [
                "D3ZB44-1",
                "protein_xref_interpro",
                "IPR036236",
                "Znf_C2H2_sf"
            ],
            [
                "D3ZB44-1",
                "protein_xref_interpro",
                "IPR001909",
                "KRAB"
            ],
            [
                "D3ZB44-1",
                "protein_xref_interpro",
                "IPR036051",
                "KRAB_dom_sf"
            ],
            [
                "D3ZZY2-1",
                "protein_xref_interpro",
                "IPR006709",
                "SSU_processome_Utp14"
            ],
            [
                "Q5RJK0-1",
                "protein_xref_interpro",
                "IPR009790",
                "DUF1356_TMEM106"
            ],
            [
                "Q5RJK3-1",
                "protein_xref_interpro",
                "IPR016009",
                "tRNA_MeTrfase_TRMD/TRM10"
            ],
            [
                "Q5RJK3-1",
                "protein_xref_interpro",
                "IPR028564",
                "MT_TRM10-typ"
            ],
            [
                "Q5RJK3-1",
                "protein_xref_interpro",
                "IPR007356",
                "tRNA_m1G_MeTrfase_euk"
            ],
            [
                "Q5RJK3-1",
                "protein_xref_interpro",
                "IPR038459",
                "MT_TRM10-typ_sf"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR016024",
                "ARM-type_fold"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR001930",
                "Peptidase_M1"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR014782",
                "Peptidase_M1_dom"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR015211",
                "Peptidase_M1_C"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR034015",
                "M1_LTA4H"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR012777",
                "LTA4H"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR027268",
                "Peptidase_M4/M1_CTD_sf"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR038502",
                "M1_LTA-4_hydro/amino_C_sf"
            ],
            [
                "P30349-1",
                "protein_xref_interpro",
                "IPR042097",
                "Aminopeptidase_N-like_N"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR038033",
                "CBX3"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR000953",
                "Chromo/chromo_shadow_dom"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR016197",
                "Chromo-like_dom_sf"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR008251",
                "Chromo_shadow_dom"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR017984",
                "Chromo_dom_subgr"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR023779",
                "Chromodomain_CS"
            ],
            [
                "Q5RJK5-1",
                "protein_xref_interpro",
                "IPR023780",
                "Chromo_domain"
            ],
            [
                "D3ZB48-1",
                "protein_xref_interpro",
                "IPR001715",
                "CH-domain"
            ],
            [
                "D3ZB48-1",
                "protein_xref_interpro",
                "IPR036872",
                "CH_dom_sf"
            ],
            [
                "D3ZB48-1",
                "protein_xref_interpro",
                "IPR008636",
                "Hook_C"
            ],
            [
                "D3ZB48-1",
                "protein_xref_interpro",
                "IPR043936",
                "HOOK_N"
            ],
            [
                "Q5RJK6-1",
                "protein_xref_interpro",
                "IPR000760",
                "Inositol_monophosphatase-like"
            ],
            [
                "Q5RJK6-1",
                "protein_xref_interpro",
                "IPR020550",
                "Inositol_monophosphatase_CS"
            ],
            [
                "Q5RJK6-1",
                "protein_xref_interpro",
                "IPR020583",
                "Inositol_monoP_metal-BS"
            ],
            [
                "A0A096MKC6-1",
                "protein_xref_interpro",
                "IPR000566",
                "Lipocln_cytosolic_FA-bd_dom"
            ],
            [
                "A0A096MKC6-1",
                "protein_xref_interpro",
                "IPR012674",
                "Calycin"
            ],
            [
                "A0A096MKC6-1",
                "protein_xref_interpro",
                "IPR002345",
                "Lipocalin"
            ],
            [
                "A0A096MKC6-1",
                "protein_xref_interpro",
                "IPR022272",
                "Lipocalin_CS"
            ],
            [
                "A0A096MKC6-1",
                "protein_xref_interpro",
                "IPR002971",
                "Maj_urinary"
            ],
            [
                "Q6MG55-1",
                "protein_xref_interpro",
                "IPR000073",
                "AB_hydrolase_1"
            ],
            [
                "Q6MG55-1",
                "protein_xref_interpro",
                "IPR029058",
                "AB_hydrolase"
            ],
            [
                "Q6MG55-1",
                "protein_xref_interpro",
                "IPR026604",
                "ABHD16A"
            ],
            [
                "Q6MG56-1",
                "protein_xref_interpro",
                "IPR003599",
                "Ig_sub"
            ],
            [
                "Q6MG56-1",
                "protein_xref_interpro",
                "IPR007110",
                "Ig-like_dom"
            ],
            [
                "Q6MG56-1",
                "protein_xref_interpro",
                "IPR013783",
                "Ig-like_fold"
            ],
            [
                "Q6MG56-1",
                "protein_xref_interpro",
                "IPR036179",
                "Ig-like_dom_sf"
            ],
            [
                "Q6MG56-1",
                "protein_xref_interpro",
                "IPR013106",
                "Ig_V-set"
            ],
            [
                "Q6MG56-1",
                "protein_xref_interpro",
                "IPR026524",
                "LY6G6d/LY6G6f"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR000742",
                "EGF-like_dom"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR011042",
                "6-blade_b-propeller_TolB-like"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR002172",
                "LDrepeatLR_classA_rpt"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR023415",
                "LDLR_class-A_CS"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR036055",
                "LDL_receptor-like_sf"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR000033",
                "LDLR_classB_rpt"
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_interpro",
                "IPR017049",
                "LRP5/6"
            ],
            [
                "Q5XIH0-1",
                "protein_xref_interpro",
                "IPR015257",
                "Maf1"
            ],
            [
                "Q5XIH0-1",
                "protein_xref_interpro",
                "IPR038564",
                "Maf1_sf"
            ],
            [
                "Q6MG51-1",
                "protein_xref_interpro",
                "IPR029073",
                "DUF4661"
            ],
            [
                "F1M2W7-1",
                "protein_xref_interpro",
                "IPR001283",
                "CRISP-related"
            ],
            [
                "F1M2W7-1",
                "protein_xref_interpro",
                "IPR014044",
                "CAP_domain"
            ],
            [
                "F1M2W7-1",
                "protein_xref_interpro",
                "IPR035940",
                "CAP_sf"
            ],
            [
                "F1M2W7-1",
                "protein_xref_interpro",
                "IPR018244",
                "Allrgn_V5/Tpx1_CS"
            ],
            [
                "Q6MG53-1",
                "protein_xref_interpro",
                "IPR038773",
                "LY6G5B"
            ],
            [
                "D4AAV0-1",
                "protein_xref_interpro",
                "IPR019471",
                "Interferon_reg_factor-3"
            ]
        ]
    },
    "readme": "Name\n   - Rat UniProtKB Xref InterPro\n\nVersion\n   - 1.8.25\n\nCreated on\n  - 2019-09-06T14:06:38.970158\n\nModified on\n   - 2020-04-10T11:57:30.660847\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 Rat UniprotKB Xref InterPro contains rat [taxid:10116] 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-rattus-norvegicus.nt\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/source/uniprot-proteome-rattus-norvegicus.nt\n      Name: rat_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_masterlist.csv\n   Output Subdomain\n      Name: rat_protein_xref_interpro.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_xref_interpro.csv\n      Name: rat_protein_xref_interpro.stat.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_xref_interpro.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/rat_protein_xref_interpro.csv"
}
