{ "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": [ [ "Q0HA29-1...", "Nmnat2..." ], [ "Q0HA29-1...", "Nmnat2..." ] ], "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": "ecoid" }, { "type": "string", "label": "ref_aa" }, { "type": "string", "label": "alt_aa" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" } ], [ "Q0HA29-1", "Nmnat2", "Binding_Site_Annotation", "24", "24", "in other chain", "ECO_0000250", "H", "", "protein_xref_uniprotkb", "Q0HA29" ], [ "Q0HA29-1", "Nmnat2", "Binding_Site_Annotation", "24", "24", "in other chain", "ECO_0000250", "H", "", "protein_xref_pubmed", "Q96T66" ], [ "Q0HA29-1", "Nmnat2", "Binding_Site_Annotation", "271", "274", "in other chain", "ECO_0000250", "TKSR", "", "protein_xref_uniprotkb", "Q0HA29" ], [ "Q0HA29-1", "Nmnat2", "Binding_Site_Annotation", "271", "274", "in other chain", "ECO_0000250", "TKSR", "", "protein_xref_pubmed", "Q96T66" ], [ "P30938-1", "Sstr5", "Glycosylation_Annotation", "186", "186", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P30938" ], [ "P30938-1", "Sstr5", "Glycosylation_Annotation", "13", "13", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P30938" ], [ "P30938-1", "Sstr5", "Glycosylation_Annotation", "23", "23", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P30938" ], [ "P30937-1", "Sstr4", "Glycosylation_Annotation", "21", "21", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P30937" ], [ "O35152-1", "Bet1l", "Modified_Residue_Annotation", "9", "9", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "O35152" ], [ "O35152-1", "Bet1l", "Modified_Residue_Annotation", "9", "9", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q9NYM9" ], [ "O35152-1", "Bet1l", "Modified_Residue_Annotation", "37", "37", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "O35152" ], [ "O35152-1", "Bet1l", "Modified_Residue_Annotation", "37", "37", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q9NYM9" ], [ "P30936-1", "Sstr3", "Glycosylation_Annotation", "18", "18", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Glycosylation_Annotation", "31", "31", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "341", "341", "Phosphoserine", "ECO_0000305", "S", "", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "341", "341", "Phosphoserine", "ECO_0000305", "S", "", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "351", "351", "Phosphoserine", "ECO_0000305", "S", "", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "351", "351", "Phosphoserine", "ECO_0000305", "S", "", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "357", "357", "Phosphothreonine", "ECO_0000269", "T", "", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "357", "357", "Phosphothreonine", "ECO_0000269", "T", "", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "346", "346", "Phosphoserine", "ECO_0000305", "S", "", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Modified_Residue_Annotation", "346", "346", "Phosphoserine", "ECO_0000305", "S", "", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "341", "341", "Impaired internalization after somatostatin binding.", "ECO_0000269", "S", "A", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "341", "341", "Impaired internalization after somatostatin binding.", "ECO_0000269", "S", "A", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "351", "351", "Impaired internalization after somatostatin binding.", "ECO_0000269", "S", "A", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "351", "351", "Impaired internalization after somatostatin binding.", "ECO_0000269", "S", "A", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "357", "357", "Reduced basal and somatostatin-induced phosphorylation. Impaired internalization after somatostatin binding.", "ECO_0000269", "T", "A", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "357", "357", "Reduced basal and somatostatin-induced phosphorylation. Impaired internalization after somatostatin binding.", "ECO_0000269", "T", "A", "protein_xref_pubmed", "9295322" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "346", "346", "Impaired internalization after somatostatin binding.", "ECO_0000269", "S", "A", "protein_xref_uniprotkb", "P30936" ], [ "P30936-1", "Sstr3", "Mutagenesis_Annotation", "346", "346", "Impaired internalization after somatostatin binding.", "ECO_0000269", "S", "A", "protein_xref_pubmed", "9295322" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "179", "179", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "870", "870", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "342", "342", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "294", "294", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "293", "293", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "99", "99", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "286", "286", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "427", "427", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Glycosylation_Annotation", "570", "570", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "937", "937", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains some residual activity during overexpression. The mutant protein interacts with SHH, but does not interact with PTCH1 or GAS1. The mutation protein has a shorted half-life compared to wild-type and may have an altered conformation resulting in destabilization.", "ECO_0000269", "S", "R", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "937", "937", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains some residual activity during overexpression. The mutant protein interacts with SHH, but does not interact with PTCH1 or GAS1. The mutation protein has a shorted half-life compared to wild-type and may have an altered conformation resulting in destabilization.", "ECO_0000269", "S", "R", "protein_xref_pubmed", "21802063" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "787", "787", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains some residual activity during overexpression. The mutant protein interacts with SHH, but does not interact with GAS1.", "ECO_0000269", "I", "A", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "787", "787", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains some residual activity during overexpression. The mutant protein interacts with SHH, but does not interact with GAS1.", "ECO_0000269", "I", "A", "protein_xref_pubmed", "21802063" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "777", "777", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains some residual activity during overexpression. The mutant protein interacts with SHH, but does not interact with PTCH1. The mutation protein has a shorted half-life compared to wild-type and may have an altered conformation resulting in destabilization.", "ECO_0000269", "V", "E", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "777", "777", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains some residual activity during overexpression. The mutant protein interacts with SHH, but does not interact with PTCH1. The mutation protein has a shorted half-life compared to wild-type and may have an altered conformation resulting in destabilization.", "ECO_0000269", "V", "E", "protein_xref_pubmed", "21802063" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "686", "686", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains very little residual activity even during overexpression and interacts with SHH, but does not interact with PTCH1, BOC, or GAS1.", "ECO_0000269", "P", "A", "protein_xref_uniprotkb", "O35158" ], [ "O35158-1", "Cdon", "Mutagenesis_Annotation", "686", "686", "Fails to support induction of the Sonic hedgehog/SSH receptors PTCH1 and GLI1. The mutant protein retains very little residual activity even during overexpression and interacts with SHH, but does not interact with PTCH1, BOC, or GAS1.", "ECO_0000269", "P", "A", "protein_xref_pubmed", "21802063" ], [ "P02761-1", "", "Glycosylation_Annotation", "54", "54", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02761" ], [ "P02764-1", "Orm1", "Glycosylation_Annotation", "104", "104", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02764" ], [ "P02764-1", "Orm1", "Glycosylation_Annotation", "94", "94", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02764" ], [ "P02764-1", "Orm1", "Glycosylation_Annotation", "134", "134", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02764" ], [ "P02764-1", "Orm1", "Glycosylation_Annotation", "76", "76", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02764" ], [ "P02764-1", "Orm1", "Glycosylation_Annotation", "34", "34", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02764" ], [ "P02764-1", "Orm1", "Glycosylation_Annotation", "25", "25", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02764" ], [ "P02767-1", "Ttr", "Glycosylation_Annotation", "118", "118", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P02767" ], [ "P02767-1", "Ttr", "Modified_Residue_Annotation", "62", "62", "4-carboxyglutamate", "ECO_0000250", "E", "", "protein_xref_uniprotkb", "P02767" ], [ "P02767-1", "Ttr", "Modified_Residue_Annotation", "62", "62", "4-carboxyglutamate", "ECO_0000250", "E", "", "protein_xref_pubmed", "P02766" ], [ "P02767-1", "Ttr", "Modified_Residue_Annotation", "72", "72", "Phosphoserine", "ECO_0007744", "S", "", "protein_xref_uniprotkb", "P02767" ], [ "P02767-1", "Ttr", "Modified_Residue_Annotation", "72", "72", "Phosphoserine", "ECO_0007744", "S", "", "protein_xref_pubmed", "22673903" ], [ "P07727-1", "Glra1", "Site_Annotation", "276", "276", "Important for obstruction of the ion pore in the closed conformation", "ECO_0000256", "A", "", "protein_xref_uniprotkb", "A0A8I6GGT5" ], [ "P07727-1", "Glra1", "Site_Annotation", "276", "276", "Important for obstruction of the ion pore in the closed conformation", "ECO_0000256", "A", "", "protein_xref_pubmed", "PIRSR608127-51" ], [ "P01237-1", "Prl", "Modified_Residue_Annotation", "117", "117", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "P01237" ], [ "P01237-1", "Prl", "Modified_Residue_Annotation", "117", "117", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "P01239" ], [ "P01237-1", "Prl", "Modified_Residue_Annotation", "53", "53", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "P01237" ], [ "P01237-1", "Prl", "Modified_Residue_Annotation", "53", "53", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "P01239" ], [ "P01230-1", "Lhb", "Glycosylation_Annotation", "33", "33", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P01230" ], [ "P09005-1", "", "Site_Annotation", "180", "181", "Reactive bond", "", "RR", "", "protein_xref_uniprotkb", "P09005" ], [ "P09006-1", "Serpina3n", "Site_Annotation", "381", "382", "Reactive bond", "", "MS", "", "protein_xref_uniprotkb", "P09006" ], [ "P09006-1", "Serpina3n", "Glycosylation_Annotation", "269", "269", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P09006" ], [ "P09006-1", "Serpina3n", "Glycosylation_Annotation", "104", "104", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P09006" ], [ "P09006-1", "Serpina3n", "Glycosylation_Annotation", "258", "258", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "P09006" ], [ "P09006-1", "Serpina3n", "Modified_Residue_Annotation", "93", "93", "Phosphoserine", "ECO_0007744", "S", "", "protein_xref_uniprotkb", "P09006" ], [ "P09006-1", "Serpina3n", "Modified_Residue_Annotation", "93", "93", "Phosphoserine", "ECO_0007744", "S", "", "protein_xref_pubmed", "22673903" ], [ "Q9JHY8-1", "Lig1", "Active_Site_Annotation", "568", "568", "N6-AMP-lysine intermediate", "", "K", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Site_Annotation", "795", "795", "Interaction with target DNA", "", "K", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Site_Annotation", "305", "305", "Interaction with target DNA", "", "R", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Site_Annotation", "590", "590", "Interaction with target DNA", "", "N", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Site_Annotation", "770", "770", "Interaction with target DNA", "", "K", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Modified_Residue_Annotation", "913", "913", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Modified_Residue_Annotation", "913", "913", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "P18858" ], [ "Q9JHY8-1", "Lig1", "Modified_Residue_Annotation", "231", "231", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Modified_Residue_Annotation", "231", "231", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "P18858" ], [ "Q9JHY8-1", "Lig1", "Modified_Residue_Annotation", "50", "50", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "Q9JHY8" ], [ "Q9JHY8-1", "Lig1", "Modified_Residue_Annotation", "50", "50", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "P18858" ] ] }, "readme": "Name\n - Rat Protein Site Annotation\n\nVersion\n - v-2.1.1\n\nCreated on\n - 2019-12-04T12:24:09.578947\n\nModified on\n - 2022-09-26T09:05:27.686743\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 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 sequences and extracts as a dataset in a csv format\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: rat_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_masterlist.csv\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_site_annotation_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_site_annotation_uniprotkb.csv\n Name: rat_protein_site_annotation_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"7197\"\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: \"7125\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"10\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"2462\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"2463\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"3681\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"8\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"1108\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"116\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"16478\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/rat_protein_site_annotation_uniprotkb.csv" }