{ "bcoid": "GLY_000248", "title": "Rat UniProtKB Xref Pfam", "description": "The Rat UniProtKB Xref Pfam contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced ...", "filename": "rat_protein_xref_pfam.csv", "filetype": "csv", "categories": { "species": [ "Rattus norvegicus" ], "molecule": [ "Protein" ], "tags": [ "Pfam cross-references" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q5RJZ1-1...", "protein_xref..." ], [ "Q5RJZ1-1...", "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" } ], [ "Q5RJZ1-1", "protein_xref_pfam", "PF06733", "DEAD_2" ], [ "Q5RJZ1-1", "protein_xref_pfam", "PF13307", "Helicase_C_2" ], [ "F1LVT6-1", "protein_xref_pfam", "PF02902", "Peptidase_C48" ], [ "Q0HA29-1", "protein_xref_pfam", "PF01467", "CTP_transf_like" ], [ "Q9WVK3-1", "protein_xref_pfam", "PF00106", "adh_short" ], [ "A0A0G2JVG5-1", "protein_xref_pfam", "PF14988", "DUF4515" ], [ "A0A0G2JVG6-1", "protein_xref_pfam", "PF01352", "KRAB" ], [ "A0A0G2JVG6-1", "protein_xref_pfam", "PF00096", "zf-C2H2" ], [ "P30938-1", "protein_xref_pfam", "PF00001", "7tm_1" ], [ "P32301-1", "protein_xref_pfam", "PF00002", "7tm_2" ], [ "P32301-1", "protein_xref_pfam", "PF02793", "HRM" ], [ "A0A8I5ZR95-1", "protein_xref_pfam", "PF01237", "Oxysterol_BP" ], [ "A0A8I5ZR95-1", "protein_xref_pfam", "PF00169", "PH" ], [ "A0A0G2K069-1", "protein_xref_pfam", "PF01391", "Collagen" ], [ "A0A0G2K069-1", "protein_xref_pfam", "PF01410", "COLFI" ], [ "A0A0G2K069-1", "protein_xref_pfam", "PF02210", "Laminin_G_2" ], [ "A0A8I6B3C5-1", "protein_xref_pfam", "PF00240", "ubiquitin" ], [ "A0A8I5Y4X4-1", "protein_xref_pfam", "PF00627", "UBA" ], [ "A0A8I5Y4X4-1", "protein_xref_pfam", "PF18037", "Ubiquitin_5" ], [ "P30937-1", "protein_xref_pfam", "PF00001", "7tm_1" ], [ "P30936-1", "protein_xref_pfam", "PF00001", "7tm_1" ], [ "O35158-1", "protein_xref_pfam", "PF07679", "I-set" ], [ "O35158-1", "protein_xref_pfam", "PF00041", "fn3" ], [ "O35158-1", "protein_xref_pfam", "PF13927", "Ig_3" ], [ "F7FI04-1", "protein_xref_pfam", "PF00787", "PX" ], [ "P02761-1", "protein_xref_pfam", "PF00061", "Lipocalin" ], [ "Q9QYH1-1", "protein_xref_pfam", "PF00595", "PDZ" ], [ "Q9QYH1-1", "protein_xref_pfam", "PF00625", "Guanylate_kin" ], [ "P02764-1", "protein_xref_pfam", "PF00061", "Lipocalin" ], [ "P02767-1", "protein_xref_pfam", "PF00576", "Transthyretin" ], [ "D4A4W8-1", "protein_xref_pfam", "PF00907", "T-box" ], [ "D4A4W9-1", "protein_xref_pfam", "PF01199", "Ribosomal_L34e" ], [ "D4A4W0-1", "protein_xref_pfam", "PF13853", "7tm_4" ], [ "D4A4W2-1", "protein_xref_pfam", "PF01554", "MatE" ], [ "F7EN52-1", "protein_xref_pfam", "PF00067", "p450" ], [ "D4A4W4-1", "protein_xref_pfam", "PF12697", "Abhydrolase_6" ], [ "D4A4W5-1", "protein_xref_pfam", "PF16209", "PhoLip_ATPase_N" ], [ "D4A4W5-1", "protein_xref_pfam", "PF16212", "PhoLip_ATPase_C" ], [ "D4A4W5-1", "protein_xref_pfam", "PF13246", "Cation_ATPase" ], [ "D4A4W6-1", "protein_xref_pfam", "PF00076", "RRM_1" ], [ "D4A4W7-1", "protein_xref_pfam", "PF14962", "AIF-MLS" ], [ "P07727-1", "protein_xref_pfam", "PF02931", "Neur_chan_LBD" ], [ "P07727-1", "protein_xref_pfam", "PF02932", "Neur_chan_memb" ], [ "D4A6Q6-1", "protein_xref_pfam", "PF00176", "SNF2-rel_dom" ], [ "D4A6Q6-1", "protein_xref_pfam", "PF00271", "Helicase_C" ], [ "D4A6Q6-1", "protein_xref_pfam", "PF13892", "DBINO" ], [ "A0A8I6ABX7-1", "protein_xref_pfam", "PF14672", "LCE" ], [ "P01237-1", "protein_xref_pfam", "PF00103", "Hormone_1" ], [ "A0A8I6AEL7-1", "protein_xref_pfam", "PF04802", "PP4R3" ], [ "P01230-1", "protein_xref_pfam", "PF00007", "Cys_knot" ], [ "P09005-1", "protein_xref_pfam", "PF00079", "Serpin" ], [ "P09006-1", "protein_xref_pfam", "PF00079", "Serpin" ], [ "A0A8I5ZLJ0-1", "protein_xref_pfam", "PF15348", "GEMIN8" ], [ "Q6AYS7-1", "protein_xref_pfam", "PF01546", "Peptidase_M20" ], [ "Q6AYS7-1", "protein_xref_pfam", "PF07687", "M20_dimer" ], [ "Q9JHY8-1", "protein_xref_pfam", "PF01068", "DNA_ligase_A_M" ], [ "Q9JHY8-1", "protein_xref_pfam", "PF04675", "DNA_ligase_A_N" ], [ "Q9JHY8-1", "protein_xref_pfam", "PF04679", "DNA_ligase_A_C" ], [ "Q9JHY1-1", "protein_xref_pfam", "PF07686", "V-set" ], [ "Q9JHY1-1", "protein_xref_pfam", "PF13927", "Ig_3" ], [ "Q9JHY2-1", "protein_xref_pfam", "PF03820", "SFXNs" ], [ "Q9JHY7-1", "protein_xref_pfam", "PF00653", "BIR" ], [ "A0JPQ1-1", "protein_xref_pfam", "PF17662", "DUF5524" ], [ "Q9WU49-1", "protein_xref_pfam", "PF00313", "CSD" ], [ "F1MAA4-1", "protein_xref_pfam", "PF12409", "P5-ATPase" ], [ "F1MAA4-1", "protein_xref_pfam", "PF00122", "E1-E2_ATPase" ], [ "F1MAA4-1", "protein_xref_pfam", "PF00702", "Hydrolase" ], [ "P30277-1", "protein_xref_pfam", "PF00134", "Cyclin_N" ], [ "P30277-1", "protein_xref_pfam", "PF02984", "Cyclin_C" ], [ "P31646-1", "protein_xref_pfam", "PF00209", "SNF" ], [ "D3ZKN4-1", "protein_xref_pfam", "PF15871", "JMY" ], [ "D3ZKN4-1", "protein_xref_pfam", "PF02205", "WH2" ], [ "Q66HR5-1", "protein_xref_pfam", "PF07888", "CALCOCO1" ], [ "Q66HR5-1", "protein_xref_pfam", "PF17751", "SKICH" ], [ "Q66HR5-1", "protein_xref_pfam", "PF18112", "Zn-C2H2_12" ], [ "A0A8L2QVZ0-1", "protein_xref_pfam", "PF00210", "Ferritin" ], [ "A0A8I6GF85-1", "protein_xref_pfam", "PF08718", "GLTP" ], [ "A0A8I6GIM3-1", "protein_xref_pfam", "PF03266", "NTPase_1" ], [ "A0A8I6GF81-1", "protein_xref_pfam", "PF00076", "RRM_1" ], [ "Q05474-1", "protein_xref_pfam", "PF00240", "ubiquitin" ], [ "Q5XI22-1", "protein_xref_pfam", "PF00108", "Thiolase_N" ], [ "Q5XI22-1", "protein_xref_pfam", "PF02803", "Thiolase_C" ], [ "Q5XI22-1", "protein_xref_pfam", "PF08333", "DUF1725" ], [ "P83748-1", "protein_xref_pfam", "PF00089", "Trypsin" ] ] }, "readme": "Name\n - Rat UniProtKB Xref Pfam\n\nVersion\n - v-2.1.1\n\nCreated on\n - 2019-09-06T14:06:38.974540\n\nModified on\n - 2022-09-26T09:04:47.909528\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]\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 Pfam contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. \n\nDescription Domain\n Keywords\n - protein family\n - Pfam\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam 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-rattus-norvegicus.nt\n URI: /data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-rattus-norvegicus.nt\n Output Subdomain\n Name: rat_protein_xref_pfam.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pfam.csv\n Name: rat_protein_xref_pfam.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_pfam.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"20714\"\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: \"6565\"\n Name: \"xref_label\"\n Description: \"Label/Name associated with x-ref\"\n Unique Values: \"6565\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_xref_pfam.csv" }