{ "bcoid": "GLY_000328", "title": "Rat Protein Site Annotation", "description": "The Rat Protein Site Annotation (UniProtKB) dataset contains rat [taxid:10116] site annotations for UniProtKB ...", "filename": "rat_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Rattus Norvegicus", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q5RJK8-1...", "Acbd6..." ], [ "Q5RJK8-1...", "Acbd6..." ] ], "headers": [ "uniprotkb_ca...", "gene_symbol..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_symbol" }, { "type": "string", "label": "ann_type" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "annotation" } ], [ "Q5RJK8-1", "Acbd6", "Binding_Site_Annotation", "114", "114", "Acyl-CoA" ], [ "Q5RJK8-1", "Acbd6", "Binding_Site_Annotation", "95", "95", "Acyl-CoA" ], [ "Q5RJK8-1", "Acbd6", "Modified_Residue_Annotation", "106", "106", "Phosphoserine" ], [ "Q5RJK8-1", "Acbd6", "Modified_Residue_Annotation", "41", "41", "Phosphoserine" ], [ "Q5RJK0-1", "Tmem106c", "Glycosylation_Annotation", "171", "171", "N-linked (GlcNAc...) asparagine" ], [ "P30349-1", "Lta4h", "Active_Site_Annotation", "296", "296", "Proton acceptor" ], [ "P30349-1", "Lta4h", "Active_Site_Annotation", "383", "383", "Proton donor" ], [ "P30349-1", "Lta4h", "Site_Annotation", "378", "378", "Covalently modified during suicide inhibition by leukotrienes" ], [ "P30349-1", "Lta4h", "Site_Annotation", "375", "375", "Essential for epoxide hydrolase activity, but not for aminopeptidase activity" ], [ "P30349-1", "Lta4h", "Metal_Binding_Annotation", "295", "295", "Zinc; catalytic" ], [ "P30349-1", "Lta4h", "Metal_Binding_Annotation", "299", "299", "Zinc; catalytic" ], [ "P30349-1", "Lta4h", "Metal_Binding_Annotation", "318", "318", "Zinc; catalytic" ], [ "P30349-1", "Lta4h", "Modified_Residue_Annotation", "413", "413", "N6-acetyllysine" ], [ "P30349-1", "Lta4h", "Modified_Residue_Annotation", "73", "73", "N6-acetyllysine" ], [ "P30349-1", "Lta4h", "Modified_Residue_Annotation", "336", "336", "N6-acetyllysine" ], [ "P30349-1", "Lta4h", "Modified_Residue_Annotation", "415", "415", "Phosphoserine" ], [ "P30349-1", "Lta4h", "Modified_Residue_Annotation", "572", "572", "N6-acetyllysine" ], [ "Q6MG55-1", "Abhd16a", "Active_Site_Annotation", "507", "507", "Charge relay system" ], [ "Q6MG55-1", "Abhd16a", "Active_Site_Annotation", "355", "355", "Charge relay system" ], [ "Q6MG55-1", "Abhd16a", "Active_Site_Annotation", "430", "430", "Charge relay system" ], [ "Q6MG56-1", "Ly6g6f", "Glycosylation_Annotation", "90", "90", "N-linked (GlcNAc...) asparagine" ], [ "Q6MG56-1", "Ly6g6f", "Modified_Residue_Annotation", "284", "284", "Phosphotyrosine" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "60", "60", "Phosphoserine; by MTOR" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "68", "68", "Phosphoserine; by MTOR" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "214", "214", "Phosphoserine" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "212", "212", "Phosphothreonine" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "75", "75", "Phosphoserine; by MTOR" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "70", "70", "Phosphoserine" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "65", "65", "Phosphoserine" ], [ "Q5XIH0-1", "Maf1", "Modified_Residue_Annotation", "64", "64", "Phosphothreonine" ], [ "Q6MG51-1", "G4", "Modified_Residue_Annotation", "35", "35", "Phosphoserine" ], [ "Q6MG51-1", "G4", "Modified_Residue_Annotation", "89", "89", "Phosphoserine" ], [ "Q6MG51-1", "G4", "Modified_Residue_Annotation", "34", "34", "Phosphoserine" ], [ "Q6MG53-1", "Ly6g5b", "Glycosylation_Annotation", "182", "182", "N-linked (GlcNAc...) asparagine" ], [ "P20961-1", "Serpine1", "Site_Annotation", "369", "370", "Reactive bond" ], [ "P20961-1", "Serpine1", "Glycosylation_Annotation", "232", "232", "N-linked (GlcNAc...) asparagine" ], [ "P20961-1", "Serpine1", "Glycosylation_Annotation", "352", "352", "N-linked (GlcNAc...) asparagine" ], [ "P20961-1", "Serpine1", "Glycosylation_Annotation", "88", "88", "N-linked (GlcNAc...) asparagine" ], [ "P20961-1", "Serpine1", "Glycosylation_Annotation", "288", "288", "N-linked (GlcNAc...) asparagine" ], [ "Q6MG59-1", "Mpig6b", "Glycosylation_Annotation", "32", "32", "N-linked (GlcNAc...) asparagine" ], [ "Q6MG59-1", "Mpig6b", "Glycosylation_Annotation", "112", "112", "N-linked (GlcNAc...) asparagine" ], [ "Q6MG59-1", "Mpig6b", "Modified_Residue_Annotation", "202", "202", "Phosphotyrosine" ], [ "Q4KLP0-1", "Dhtkd1", "Modified_Residue_Annotation", "183", "183", "N6-succinyllysine" ], [ "Q4KLP0-1", "Dhtkd1", "Modified_Residue_Annotation", "188", "188", "N6-succinyllysine" ], [ "Q4KLP0-1", "Dhtkd1", "Modified_Residue_Annotation", "800", "800", "N6-succinyllysine" ], [ "Q4KLP0-1", "Dhtkd1", "Modified_Residue_Annotation", "818", "818", "N6-succinyllysine" ], [ "P34997-1", "Cxcr5", "Glycosylation_Annotation", "28", "28", "N-linked (GlcNAc...) asparagine" ], [ "P34997-1", "Cxcr5", "Glycosylation_Annotation", "198", "198", "N-linked (GlcNAc...) asparagine" ], [ "Q9WUD9-1", "Src", "Active_Site_Annotation", "389", "389", "Proton acceptor" ], [ "Q9WUD9-1", "Src", "Binding_Site_Annotation", "298", "298", "ATP" ], [ "Q9WUD9-1", "Src", "Modified_Residue_Annotation", "187", "187", "Phosphotyrosine" ], [ "Q9WUD9-1", "Src", "Modified_Residue_Annotation", "420", "420", "Phosphothreonine; by autocatalysis" ], [ "Q9WUD9-1", "Src", "Modified_Residue_Annotation", "419", "419", "Phosphotyrosine; by FAK2" ], [ "Q9WUD9-1", "Src", "Modified_Residue_Annotation", "17", "17", "Phosphoserine" ], [ "Q9WUD9-1", "Src", "Modified_Residue_Annotation", "530", "530", "Phosphotyrosine; by CSK" ], [ "Q9WUD9-1", "Src", "Modified_Residue_Annotation", "75", "75", "Phosphoserine; by CDK5" ], [ "Q9WUD9-1", "Src", "NP_Binding_Annotation", "276", "284", "ATP" ], [ "Q8R553-1", "Clstn3", "Glycosylation_Annotation", "327", "327", "N-linked (GlcNAc...) asparagine" ], [ "Q8R553-1", "Clstn3", "Glycosylation_Annotation", "508", "508", "N-linked (GlcNAc...) asparagine" ], [ "Q8R553-1", "Clstn3", "Glycosylation_Annotation", "299", "299", "N-linked (GlcNAc...) asparagine" ], [ "Q8R553-1", "Clstn3", "Glycosylation_Annotation", "347", "347", "N-linked (GlcNAc...) asparagine" ], [ "Q8R553-1", "Clstn3", "Glycosylation_Annotation", "741", "741", "N-linked (GlcNAc...) asparagine" ], [ "Q925Q4-1", "Gpha2", "Glycosylation_Annotation", "38", "38", "N-linked (GlcNAc...) asparagine" ], [ "Q925Q4-1", "Gpha2", "Glycosylation_Annotation", "82", "82", "N-linked (GlcNAc...) asparagine" ], [ "Q9QX69-1", "Lancl1", "Binding_Site_Annotation", "317", "317", "Glutathione" ], [ "Q9QX69-1", "Lancl1", "Metal_Binding_Annotation", "322", "322", "Zinc" ], [ "Q9QX69-1", "Lancl1", "Metal_Binding_Annotation", "276", "276", "Zinc" ], [ "Q9QX69-1", "Lancl1", "Metal_Binding_Annotation", "323", "323", "Zinc" ], [ "Q9QX69-1", "Lancl1", "Modified_Residue_Annotation", "142", "142", "N6-acetyllysine" ], [ "Q9QX69-1", "Lancl1", "Modified_Residue_Annotation", "2", "2", "N-acetylalanine" ], [ "Q9WUD2-1", "Trpv2", "Glycosylation_Annotation", "572", "572", "N-linked (GlcNAc...) asparagine" ], [ "Q9WUD2-1", "Trpv2", "Glycosylation_Annotation", "571", "571", "N-linked (GlcNAc...) asparagine" ], [ "Q9WUD2-1", "Trpv2", "Modified_Residue_Annotation", "6", "6", "Phosphoserine" ], [ "Q9WUD2-1", "Trpv2", "Modified_Residue_Annotation", "748", "748", "Phosphoserine" ], [ "Q9WUD2-1", "Trpv2", "Modified_Residue_Annotation", "82", "82", "Phosphoserine" ], [ "Q9WUD2-1", "Trpv2", "Modified_Residue_Annotation", "760", "760", "Phosphoserine" ], [ "Q9WUD2-1", "Trpv2", "Modified_Residue_Annotation", "15", "15", "Phosphoserine" ], [ "Q07969-1", "Cd36", "Site_Annotation", "463", "463", "Critical for TLR4-TLR6 dimerization and signaling" ], [ "Q07969-1", "Cd36", "Glycosylation_Annotation", "247", "247", "N-linked (GlcNAc...) asparagine" ], [ "Q07969-1", "Cd36", "Glycosylation_Annotation", "205", "205", "N-linked (GlcNAc...) asparagine" ], [ "Q07969-1", "Cd36", "Glycosylation_Annotation", "321", "321", "N-linked (GlcNAc...) asparagine" ], [ "Q07969-1", "Cd36", "Glycosylation_Annotation", "134", "134", "N-linked (GlcNAc...) asparagine" ], [ "Q07969-1", "Cd36", "Glycosylation_Annotation", "235", "235", "N-linked (GlcNAc...) asparagine" ], [ "Q07969-1", "Cd36", "Glycosylation_Annotation", "102", "102", "N-linked (GlcNAc...) asparagine" ] ] }, "readme": "Name\n - Rat Protein Site Annotation\n\nVersion\n - 1.5.12\n\nCreated on\n - 2019-12-04T12:24:09.578947\n\nModified on\n - 2019-12-04T15:29:29.874520\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 Protein Site Annotation (UniProtKB) dataset contains rat [taxid:10116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - site annotation\n - amino acid range\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format\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-1.5.12/reviewed/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.12/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.12/reviewed/rat_protein_site_annotation_uniprotkb.csv\n Name: rat_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.12/reviewed/rat_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"7323\"\n Name: \"ann_type\"\n Description: \"\"\n Unique Values: \"11\"\n Name: \"gene_symbol\"\n Description: \"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\n Unique Values: \"7188\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"2408\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"2402\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"1991\"", "downloadurl": "/ln2data/releases/data/v-1.5.12/reviewed/rat_protein_site_annotation_uniprotkb.csv" }