{ "bcoid": "GLY_000322", "title": "Human Protein Site Annotation", "description": "The Human Protein Site Annotation (UniProtKB) dataset contains human [taxid:9606] site annotations for ...", "filename": "human_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8TBF5-1...", "PIGX..." ], [ "Q8TBF4-1...", "ZCRB1..." ] ], "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" }, { "type": "string", "label": "pmid" }, { "type": "string", "label": "ecoid" }, { "type": "string", "label": "ref_aa" }, { "type": "string", "label": "alt_aa" } ], [ "Q8TBF5-1", "PIGX", "Glycosylation_Annotation", "103", "103", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "210", "210", "Phosphoserine", "18669648", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "216", "216", "Phosphoserine", "18669648", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "155", "155", "Phosphoserine", "17081983", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "155", "155", "Phosphoserine", "18669648", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "155", "155", "Phosphoserine", "19690332", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "155", "155", "Phosphoserine", "21406692", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "155", "155", "Phosphoserine", "20068231", "ECO_0000244", "S", "" ], [ "Q8TBF4-1", "ZCRB1", "Modified_Residue_Annotation", "155", "155", "Phosphoserine", "17693683", "ECO_0000244", "S", "" ], [ "Q9NRJ4-1", "TULP4", "Modified_Residue_Annotation", "945", "945", "Asymmetric dimethylarginine", "Q9JIL5", "ECO_0000250", "R", "" ], [ "Q9NRJ4-1", "TULP4", "Modified_Residue_Annotation", "950", "950", "Asymmetric dimethylarginine", "Q9JIL5", "ECO_0000250", "R", "" ], [ "Q9NRJ4-1", "TULP4", "Modified_Residue_Annotation", "577", "577", "Phosphoserine", "23186163", "ECO_0000244", "S", "" ], [ "Q9NRJ4-1", "TULP4", "Modified_Residue_Annotation", "1374", "1374", "Phosphoserine", "23186163", "ECO_0000244", "S", "" ], [ "Q9NRJ4-1", "TULP4", "Modified_Residue_Annotation", "1343", "1343", "Phosphoserine", "23186163", "ECO_0000244", "S", "" ], [ "Q9NQ79-1", "CRTAC1", "Glycosylation_Annotation", "626", "626", "O-linked (GalNAc...) threonine", "", "", "T", "" ], [ "Q9NQ79-1", "CRTAC1", "Glycosylation_Annotation", "621", "621", "O-linked (GalNAc...) threonine", "", "", "T", "" ], [ "Q9NQ79-1", "CRTAC1", "Glycosylation_Annotation", "608", "608", "O-linked (GalNAc...) threonine", "", "", "T", "" ], [ "Q9NQ79-1", "CRTAC1", "Glycosylation_Annotation", "619", "619", "O-linked (GalNAc...) threonine", "", "", "T", "" ], [ "Q9NQ79-1", "CRTAC1", "Glycosylation_Annotation", "618", "618", "O-linked (GalNAc...) threonine", "", "", "T", "" ], [ "Q8IZF5-1", "ADGRF3", "Glycosylation_Annotation", "441", "441", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "Q8IZF5-1", "ADGRF3", "Glycosylation_Annotation", "382", "382", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "Q8IZF5-1", "ADGRF3", "Glycosylation_Annotation", "264", "264", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "Q8IZF5-1", "ADGRF3", "Glycosylation_Annotation", "301", "301", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "Q8IZF5-1", "ADGRF3", "Glycosylation_Annotation", "648", "648", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "Q8IZF5-1", "ADGRF3", "Glycosylation_Annotation", "188", "188", "N-linked (GlcNAc...) asparagine", "", "", "N", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "338", "338", "Substrate; via amide nitrogen", "11960989", "ECO_0000269", "G", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "338", "338", "Substrate; via amide nitrogen", "2VGF", "ECO_0000244", "G", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "313", "313", "Substrate; via amide nitrogen", "11960989", "ECO_0000269", "K", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "313", "313", "Substrate; via amide nitrogen", "2VGF", "ECO_0000244", "K", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "525", "525", "Allosteric activator", "11960989", "ECO_0000269", "W", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "525", "525", "Allosteric activator", "2VGF", "ECO_0000244", "W", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "532", "532", "Allosteric activator", "11960989", "ECO_0000269", "R", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "532", "532", "Allosteric activator", "2VGF", "ECO_0000244", "R", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "371", "371", "Substrate", "11960989", "ECO_0000269", "T", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "371", "371", "Substrate", "2VGF", "ECO_0000244", "T", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "116", "116", "Substrate", "11960989", "ECO_0000269", "R", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "116", "116", "Substrate", "2VGB", "ECO_0000244", "R", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "339", "339", "Substrate; via amide nitrogen", "11960989", "ECO_0000269", "D", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "339", "339", "Substrate; via amide nitrogen", "2VGF", "ECO_0000244", "D", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "163", "163", "ATP", "P14618", "ECO_0000250", "R", "" ], [ "P30613-1", "PKLR", "Binding_Site_Annotation", "250", "250", "ATP", "P14618", "ECO_0000250", "K", "" ], [ "P30613-1", "PKLR", "Site_Annotation", "313", "313", "Transition state stabilizer", "P00549", "ECO_0000250", "K", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "156", "156", "Potassium", "11960989", "ECO_0000269", "D", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "156", "156", "Potassium", "2VGF", "ECO_0000244", "D", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "315", "315", "Manganese", "11960989", "ECO_0000269", "E", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "315", "315", "Manganese", "2VGF", "ECO_0000244", "E", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "118", "118", "Potassium", "11960989", "ECO_0000269", "N", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "118", "118", "Potassium", "2VGF", "ECO_0000244", "N", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "157", "157", "Potassium; via carbonyl oxygen", "11960989", "ECO_0000269", "T", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "157", "157", "Potassium; via carbonyl oxygen", "2VGF", "ECO_0000244", "T", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "120", "120", "Potassium", "11960989", "ECO_0000269", "S", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "120", "120", "Potassium", "2VGB", "ECO_0000244", "S", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "339", "339", "Manganese", "11960989", "ECO_0000269", "D", "" ], [ "P30613-1", "PKLR", "Metal_Binding_Annotation", "339", "339", "Manganese", "2VGF", "ECO_0000244", "D", "" ], [ "P30613-1", "PKLR", "Modified_Residue_Annotation", "2", "2", "Phosphoserine", "23186163", "ECO_0000244", "S", "" ], [ "P30613-1", "PKLR", "Modified_Residue_Annotation", "26", "26", "Phosphoserine", "23186163", "ECO_0000244", "S", "" ], [ "P30613-1", "PKLR", "Modified_Residue_Annotation", "19", "19", "Phosphoserine", "23186163", "ECO_0000244", "S", "" ], [ "P30613-1", "PKLR", "Modified_Residue_Annotation", "292", "292", "Phosphoserine", "24275569", "ECO_0000244", "S", "" ], [ "P30613-1", "PKLR", "Modified_Residue_Annotation", "43", "43", "Phosphoserine", "24275569", "ECO_0000244", "S", "" ], [ "P30613-1", "PKLR", "NP_Binding_Annotation", "118", "121", "ATP", "P14618", "ECO_0000250", "", "" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "134", "134", "In PKRD.", "8483951", "ECO_0000269", "V", "D" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "155", "155", "In PKRD.", "8483951", "ECO_0000269", "L", "P" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "172", "172", "In PKRD; Sassari.", "9827908", "ECO_0000269", "E", "Q" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "163", "163", "In PKRD; Linz.", "2018831", "ECO_0000269", "R", "C" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "331", "331", "In PKRD; Parma.", "7706479", "ECO_0000269", "D", "E" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "332", "332", "In PKRD; loss of catalytical activity.", "11960989", "ECO_0000269", "G", "S" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "332", "332", "In PKRD; loss of catalytical activity.", "9482576", "ECO_0000269", "G", "S" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "332", "332", "In PKRD; loss of catalytical activity.", "8180378", "ECO_0000269", "G", "S" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "336", "336", "In PKRD.", "8180378", "ECO_0000269", "A", "S" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "337", "337", "In PKRD.", "9482576", "ECO_0000269", "R", "P" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "337", "337", "In PKRD.", "9827908", "ECO_0000269", "R", "Q" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "339", "339", "In PKRD.", "9827908", "ECO_0000269", "D", "H" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "341", "341", "In PKRD.", "7706479", "ECO_0000269", "G", "A" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "341", "341", "In PKRD.", "21794208", "ECO_0000269", "G", "A" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "354", "354", "In PKRD.", "8180378", "ECO_0000269", "K", "" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "357", "357", "In PKRD.", "9827908", "ECO_0000269", "I", "T" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "359", "359", "In PKRD.", "8483951", "ECO_0000269", "R", "H" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "361", "361", "In PKRD.", "8180378", "ECO_0000269", "N", "D" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "368", "368", "In PKRD; Osaka.", "8476433", "ECO_0000269", "V", "F" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "384", "384", "In PKRD; Tokyo/Beirut; most common mutation in Japanese population; no conformational change.", "11960989", "ECO_0000269", "T", "M" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "384", "384", "In PKRD; Tokyo/Beirut; most common mutation in Japanese population; no conformational change.", "2018831", "ECO_0000269", "T", "M" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "384", "384", "In PKRD; Tokyo/Beirut; most common mutation in Japanese population; no conformational change.", "1896471", "ECO_0000269", "T", "M" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "392", "392", "In PKRD.", "8180378", "ECO_0000269", "A", "T" ], [ "P30613-1", "PKLR", "Natural_Variant_Annotation", "393", "393", "In PKRD.", "7706479", "ECO_0000269", "N", "K" ] ] }, "readme": "Name\n - Human Protein Site Annotation\n\nVersion\n - 1.5.27\n\nCreated on\n - 2019-12-01T15:29:48.229274\n\nModified on\n - 2020-04-11T11:30:23.073973\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 Protein Site Annotation (UniProtKB) dataset contains human [taxid:9606] 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-homo-sapiens.nt\n URI: https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_site_annotation_uniprotkb.csv\n Name: human_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_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: \"15326\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"13\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"246\"\n Name: \"gene_symbol\"\n Description: \"Official gene name/symbol assigned to the gene. Human gene names/symbols are approved by the HUGO Gene Nomenclature Committee (HGNC)\n Unique Values: \"15302\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"22\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"4102\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"9\"\n Name: \"pmid\"\n Description: \"NCBI PubMed database Identifier\"\n Unique Values: \"35420\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"4105\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"34268\"", "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/human_protein_site_annotation_uniprotkb.csv" }