{ "bcoid": "GLY_000097", "title": "Human UniProtKB Xref CDD", "description": "The Human UniProtKB Xref CDD contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_cdd.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Cdd cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8TBF4-1...", "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" } ], [ "Q8TBF4-1", "protein_xref_cdd", "cd12393", "RRM_ZCRB1" ], [ "P30613-1", "protein_xref_cdd", "cd00288", "Pyruvate_Kinase" ], [ "Q5H9L4-1", "protein_xref_cdd", "cd08047", "TAF7" ], [ "Q5QJ38-1", "protein_xref_cdd", "cd00213", "S-100" ], [ "Q9NQ75-1", "protein_xref_cdd", "cd12000", "SH3_CASS4" ], [ "P20930-1", "protein_xref_cdd", "cd00213", "S-100" ], [ "P20936-1", "protein_xref_cdd", "cd10353", "SH2_Nterm_RasGAP" ], [ "P20936-1", "protein_xref_cdd", "cd10354", "SH2_Cterm_RasGAP" ], [ "P20936-1", "protein_xref_cdd", "cd11788", "SH3_RasGAP" ], [ "Q8NFX7-1", "protein_xref_cdd", "cd14681", "PH-STXBP6" ], [ "Q8NFX7-1", "protein_xref_cdd", "cd15892", "R-SNARE_STXBP6" ], [ "A8MU46-1", "protein_xref_cdd", "cd00014", "CH" ], [ "Q9NXR8-1", "protein_xref_cdd", "cd15585", "PHD_ING3" ], [ "Q9C0H2-1", "protein_xref_cdd", "cd07912", "Tweety_N" ], [ "O00244-1", "protein_xref_cdd", "cd00371", "HMA" ], [ "O00716-1", "protein_xref_cdd", "cd14660", "E2F_DD" ], [ "P40424-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "P40425-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "P40426-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "P40429-1", "protein_xref_cdd", "cd00392", "Ribosomal_L13" ], [ "P51991-1", "protein_xref_cdd", "cd12582", "RRM2_hnRNPA3" ], [ "P51991-1", "protein_xref_cdd", "cd12763", "RRM1_hnRNPA3" ], [ "Q5M775-1", "protein_xref_cdd", "cd00014", "CH" ], [ "P02768-1", "protein_xref_cdd", "cd00015", "ALBUMIN" ], [ "P05387-1", "protein_xref_cdd", "cd05833", "Ribosomal_P2" ], [ "P24863-1", "protein_xref_cdd", "cd00043", "CYCLIN" ], [ "P02760-1", "protein_xref_cdd", "cd00109", "KU" ], [ "P02765-1", "protein_xref_cdd", "cd00042", "CY" ], [ "Q7L266-1", "protein_xref_cdd", "cd04702", "ASRGL1_like" ], [ "Q9UQ05-1", "protein_xref_cdd", "cd00130", "PAS" ], [ "Q9UQ05-1", "protein_xref_cdd", "cd00038", "CAP_ED" ], [ "Q9UJ71-1", "protein_xref_cdd", "cd03590", "CLECT_DC-SIGN_like" ], [ "O15254-1", "protein_xref_cdd", "cd01150", "AXO" ], [ "O15259-1", "protein_xref_cdd", "cd11770", "SH3_Nephrocystin" ], [ "P29401-1", "protein_xref_cdd", "cd02012", "TPP_TK" ], [ "P41181-1", "protein_xref_cdd", "cd00333", "MIP" ], [ "O14776-1", "protein_xref_cdd", "cd00201", "WW" ], [ "P12074-1", "protein_xref_cdd", "cd00925", "Cyt_c_Oxidase_VIa" ], [ "Q9H9Z2-1", "protein_xref_cdd", "cd04458", "CSP_CDS" ], [ "Q9P218-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "Q5W111-1", "protein_xref_cdd", "cd12880", "SPRYD7" ], [ "Q9UK13-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "Q9UK11-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "Q9Y6E2-1", "protein_xref_cdd", "cd11560", "W2_eIF5C_like" ], [ "Q9BZG2-1", "protein_xref_cdd", "cd07061", "HP_HAP_like" ], [ "Q9HC73-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "P16402-1", "protein_xref_cdd", "cd00073", "H15" ], [ "Q6NX49-1", "protein_xref_cdd", "cd07765", "KRAB_A-box" ], [ "Q9UKZ9-1", "protein_xref_cdd", "cd03576", "NTR_PCOLCE" ], [ "Q9UKZ9-1", "protein_xref_cdd", "cd00041", "CUB" ], [ "P04035-1", "protein_xref_cdd", "cd00643", "HMG-CoA_reductase_classI" ], [ "Q14563-1", "protein_xref_cdd", "cd11249", "Sema_3A" ], [ "Q14565-1", "protein_xref_cdd", "cd01123", "Rad51_DMC1_radA" ], [ "Q9NWM3-1", "protein_xref_cdd", "cd14366", "CUE_CUED1" ], [ "O60741-1", "protein_xref_cdd", "cd00038", "CAP_ED" ], [ "Q9UHF7-1", "protein_xref_cdd", "cd00202", "ZnF_GATA" ], [ "P41214-1", "protein_xref_cdd", "cd11608", "eIF2D_C" ], [ "Q9UHC6-1", "protein_xref_cdd", "cd00057", "FA58C" ], [ "Q7Z5L0-1", "protein_xref_cdd", "cd00220", "VMO-I" ], [ "Q92526-1", "protein_xref_cdd", "cd03342", "TCP1_zeta" ], [ "Q92520-1", "protein_xref_cdd", "cd13940", "ILEI_FAM3C" ], [ "Q92522-1", "protein_xref_cdd", "cd00073", "H15" ], [ "Q02878-1", "protein_xref_cdd", "cd13156", "KOW_RPL6" ], [ "Q9HAP2-1", "protein_xref_cdd", "cd00083", "HLH" ], [ "P07202-1", "protein_xref_cdd", "cd00033", "CCP" ], [ "Q6PII5-1", "protein_xref_cdd", "cd07723", "hydroxyacylglutathione_hydrolase_MBL-fold" ], [ "Q96G23-1", "protein_xref_cdd", "cd00086", "homeodomain" ], [ "Q9BWU0-1", "protein_xref_cdd", "cd00060", "FHA" ], [ "Q13239-1", "protein_xref_cdd", "cd10344", "SH2_SLAP" ], [ "Q13239-1", "protein_xref_cdd", "cd12010", "SH3_SLAP" ], [ "Q68DE3-1", "protein_xref_cdd", "cd00083", "HLH" ], [ "Q13237-1", "protein_xref_cdd", "cd05572", "STKc_cGK" ], [ "Q13237-1", "protein_xref_cdd", "cd00038", "CAP_ED" ], [ "Q9NRH3-1", "protein_xref_cdd", "cd02188", "gamma_tubulin" ], [ "Q00534-1", "protein_xref_cdd", "cd07862", "STKc_CDK6" ], [ "A0A1W2PRP0-1", "protein_xref_cdd", "cd00059", "FH" ], [ "P10914-1", "protein_xref_cdd", "cd00103", "IRF" ], [ "Q07960-1", "protein_xref_cdd", "cd00170", "SEC14" ], [ "P10911-1", "protein_xref_cdd", "cd00160", "RhoGEF" ], [ "P10912-1", "protein_xref_cdd", "cd00063", "FN3" ], [ "P23743-1", "protein_xref_cdd", "cd00051", "EFh" ], [ "P23743-1", "protein_xref_cdd", "cd00029", "C1" ], [ "P59910-1", "protein_xref_cdd", "cd06257", "DnaJ" ], [ "Q96MU8-1", "protein_xref_cdd", "cd00041", "CUB" ] ] }, "readme": "Name\n - Human UniProtKB Xref CDD\n\nVersion\n - 1.8.24\n\nCreated on\n - 2019-03-15T12:09:02.680538\n\nModified on\n - 2020-04-10T11:33:22.447768\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 CDD contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CDD 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 - The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins.\n\nDescription Domain\n Keywords\n - protein domains\n - CDD\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file 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/ln2data/releases/data/v-1.8.24/source/uuniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_xref_cdd.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_xref_cdd.csv\n Name: human_protein_xref_cdd.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_xref_cdd.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-1.8.24/reviewed/human_protein_xref_cdd.csv" }