{ "bcoid": "GLY_000780", "title": "Yeast UniProtKB Xref CDD", "description": "The Yeast UniProtKB Xref CDD contains yeast [taxid:559292] UniProtKB canonical accessions cross-referenced ...", "filename": "yeast_protein_xref_cdd.csv", "filetype": "csv", "categories": { "species": [ "Saccharomyces cerevisiae S288C" ], "molecule": [ "Protein" ], "tag": [ "Cdd cross-references" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P39970-1...", "protein_xref..." ], [ "P39979-1...", "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" } ], [ "P39970-1", "protein_xref_cdd", "cd14687", "bZIP_ATF2" ], [ "P39979-1", "protein_xref_cdd", "cd04301", "NAT_SF" ], [ "P25379-1", "protein_xref_cdd", "cd06448", "L-Ser-dehyd" ], [ "P25378-1", "protein_xref_cdd", "cd04137", "RheB" ], [ "P17121-1", "protein_xref_cdd", "cd04396", "RhoGAP_fSAC7_BAG7" ], [ "P25371-1", "protein_xref_cdd", "cd00055", "EGF_Lam" ], [ "P25371-1", "protein_xref_cdd", "cd03213", "ABCG_EPDR" ], [ "P25373-1", "protein_xref_cdd", "cd03419", "GRX_GRXh_1_2_like" ], [ "P25372-1", "protein_xref_cdd", "cd02947", "TRX_family" ], [ "Q03049-1", "protein_xref_cdd", "cd05227", "AR_SDR_e" ], [ "Q06567-1", "protein_xref_cdd", "cd13969", "ADCK1-like" ], [ "Q00539-1", "protein_xref_cdd", "cd12345", "RRM2_SECp43_like" ], [ "Q00539-1", "protein_xref_cdd", "cd12346", "RRM3_NGR1_NAM8_like" ], [ "Q00539-1", "protein_xref_cdd", "cd12611", "RRM1_NGR1_NAM8_like" ], [ "Q07748-1", "protein_xref_cdd", "cd13650", "PBP2_THI5" ], [ "Q07963-1", "protein_xref_cdd", "cd19670", "UBR-box_UBR1_2_3" ], [ "Q00246-1", "protein_xref_cdd", "cd04132", "Rho4_like" ], [ "Q00245-1", "protein_xref_cdd", "cd04134", "Rho3" ], [ "P0CX64-1", "protein_xref_cdd", "cd09272", "RNase_HI_RT_Ty1" ], [ "P18494-1", "protein_xref_cdd", "cd00202", "ZnF_GATA" ], [ "Q08748-1", "protein_xref_cdd", "cd04043", "C2_Munc13_fungal" ], [ "Q08749-1", "protein_xref_cdd", "cd03496", "SQR_TypeC_CybS" ], [ "Q08747-1", "protein_xref_cdd", "cd10567", "SWIB-MDM2_like" ], [ "Q08742-1", "protein_xref_cdd", "cd01519", "RHOD_HSP67B2" ], [ "P32914-1", "protein_xref_cdd", "cd07973", "Spt4" ], [ "P32916-1", "protein_xref_cdd", "cd17876", "SRalpha_C" ], [ "P32916-1", "protein_xref_cdd", "cd14818", "longin-like" ], [ "P32911-1", "protein_xref_cdd", "cd11566", "eIF1_SUI1" ], [ "P32913-1", "protein_xref_cdd", "cd06891", "PX_Vps17p" ], [ "P32913-1", "protein_xref_cdd", "cd07625", "BAR_Vps17p" ], [ "P32912-1", "protein_xref_cdd", "cd06897", "PX_SNARE" ], [ "P32912-1", "protein_xref_cdd", "cd15858", "SNARE_VAM7" ], [ "Q04439-1", "protein_xref_cdd", "cd01378", "MYSc_Myo1" ], [ "Q04439-1", "protein_xref_cdd", "cd11858", "SH3_Myosin-I_fungi" ], [ "Q04432-1", "protein_xref_cdd", "cd03147", "GATase1_Ydr533c_like" ], [ "Q04437-1", "protein_xref_cdd", "cd00873", "KU80" ], [ "Q04437-1", "protein_xref_cdd", "cd01458", "vWA_ku" ], [ "P00546-1", "protein_xref_cdd", "cd07835", "STKc_CDK1_CdkB_like" ], [ "P04386-1", "protein_xref_cdd", "cd00067", "GAL4" ], [ "P04386-1", "protein_xref_cdd", "cd14654", "ZIP_Gal4" ], [ "P04386-1", "protein_xref_cdd", "cd12148", "fungal_TF_MHR" ], [ "Q08299-1", "protein_xref_cdd", "cd17322", "MFS_ARN_like" ], [ "Q08562-1", "protein_xref_cdd", "cd18008", "DEXDc_SHPRH-like" ], [ "Q08562-1", "protein_xref_cdd", "cd23136", "RING-HC_ULS1-like" ], [ "Q08562-1", "protein_xref_cdd", "cd18793", "SF2_C_SNF" ], [ "P25377-1", "protein_xref_cdd", "cd05283", "CAD1" ], [ "P32474-1", "protein_xref_cdd", "cd02961", "PDI_a_family" ], [ "P32474-1", "protein_xref_cdd", "cd02981", "PDI_b_family" ], [ "P32474-1", "protein_xref_cdd", "cd02982", "PDI_b'_family" ], [ "P32474-1", "protein_xref_cdd", "cd02995", "PDI_a_PDI_a'_C" ], [ "P04037-1", "protein_xref_cdd", "cd00924", "Cyt_c_Oxidase_Vb" ], [ "P04039-1", "protein_xref_cdd", "cd00929", "Cyt_c_Oxidase_VIIc" ], [ "P00724-1", "protein_xref_cdd", "cd18622", "GH32_Inu-like" ], [ "Q03048-1", "protein_xref_cdd", "cd11286", "ADF_cofilin_like" ], [ "Q02875-1", "protein_xref_cdd", "cd00072", "GYF" ], [ "P36096-1", "protein_xref_cdd", "cd23117", "RING-H2_TUL1-like" ], [ "Q10740-1", "protein_xref_cdd", "cd09599", "M1_LTA4H" ], [ "Q05473-1", "protein_xref_cdd", "cd01876", "YihA_EngB" ], [ "Q05471-1", "protein_xref_cdd", "cd18793", "SF2_C_SNF" ], [ "Q05471-1", "protein_xref_cdd", "cd18003", "DEXQc_SRCAP" ], [ "Q03220-1", "protein_xref_cdd", "cd07470", "CYTH-like_mRNA_RTPase" ], [ "Q07747-1", "protein_xref_cdd", "cd19147", "AKR_AKR9A3_9B1-4" ], [ "P19073-1", "protein_xref_cdd", "cd01874", "Cdc42" ], [ "P53040-1", "protein_xref_cdd", "cd08050", "TAF6C" ], [ "P23748-1", "protein_xref_cdd", "cd01530", "Cdc25" ], [ "P40161-1", "protein_xref_cdd", "cd11604", "RTT106_N" ], [ "P40161-1", "protein_xref_cdd", "cd13303", "PH1-like_Rtt106" ], [ "P40161-1", "protein_xref_cdd", "cd13304", "PH2-like_Rtt106" ], [ "P40160-1", "protein_xref_cdd", "cd05144", "RIO2_C" ], [ "P40308-1", "protein_xref_cdd", "cd07229", "Pat_TGL3_like" ], [ "P33734-1", "protein_xref_cdd", "cd01748", "GATase1_IGP_Synthase" ], [ "P33734-1", "protein_xref_cdd", "cd04731", "HisF" ], [ "P38966-1", "protein_xref_cdd", "cd14474", "SPX_YDR089W" ], [ "P38961-1", "protein_xref_cdd", "cd02440", "AdoMet_MTases" ], [ "P15180-1", "protein_xref_cdd", "cd00775", "LysRS_core" ], [ "P15180-1", "protein_xref_cdd", "cd04322", "LysRS_N" ], [ "P48558-1", "protein_xref_cdd", "cd10429", "GAAP_like" ], [ "P48559-1", "protein_xref_cdd", "cd00154", "Rab" ], [ "P16521-1", "protein_xref_cdd", "cd03221", "ABCF_EF-3" ], [ "P16521-1", "protein_xref_cdd", "cd18626", "CD_eEF3" ], [ "Q12511-1", "protein_xref_cdd", "cd00143", "PP2Cc" ], [ "Q12512-1", "protein_xref_cdd", "cd11307", "M35_Asp_f2_like" ], [ "P30283-1", "protein_xref_cdd", "cd20512", "CYCLIN_CLBs_yeast_rpt2" ], [ "Q12517-1", "protein_xref_cdd", "cd09804", "Dcp1" ] ] }, "readme": "Name\n - Yeast UniProtKB Xref CDD\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2022-08-31T12:47:56.887721\n\nModified on\n - 2023-09-11T20:20:29\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu], Jingyue Wu [jingyue.wu@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 Yeast UniProtKB Xref CDD contains yeast [taxid:559292] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. 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/glygener/glygen-backend-integration/blob/master/dataset-maker/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-saccharomyces-cerevisiae.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-saccharomyces-cerevisiae.nt\n Output Subdomain\n Name: yeast_protein_xref_cdd.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_cdd.csv\n Name: yeast_protein_xref_cdd.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_cdd.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"2500\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"2063\"\n Name: \"xref_label\"\n Description: \"Label/Name associated with x-ref\"\n Unique Values: \"2061\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/yeast_protein_xref_cdd.csv" }