{ "bcoid": "GLY_000327", "title": "Mouse Protein Site Annotation", "description": "The Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] site annotations for ...", "filename": "mouse_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8BH24-1...", "Tm9sf4..." ], [ "Q8BH24-1...", "Tm9sf4..." ] ], "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" } ], [ "Q8BH24-1", "Tm9sf4", "Modified_Residue_Annotation", "313", "313", "Phosphotyrosine", "ECO_0000250", "Y", "", "protein_xref_uniprotkb", "Q8BH24" ], [ "Q8BH24-1", "Tm9sf4", "Modified_Residue_Annotation", "313", "313", "Phosphotyrosine", "ECO_0000250", "Y", "", "protein_xref_pubmed", "Q92544" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "466", "466", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "179", "179", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "203", "203", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "479", "479", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "243", "243", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "216", "216", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "498", "498", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "265", "265", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "303", "303", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "357", "357", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "36", "36", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q8BH27-1", "Megf9", "Glycosylation_Annotation", "426", "426", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8BH27" ], [ "Q9JHR7-1", "Ide", "Active_Site_Annotation", "111", "111", "Proton acceptor", "ECO_0000255", "E", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Active_Site_Annotation", "111", "111", "Proton acceptor", "ECO_0000255", "E", "", "protein_xref_pubmed", "PRU10096" ], [ "Q9JHR7-1", "Ide", "Binding_Site_Annotation", "429", "429", "ATP", "ECO_0000250", "R", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Binding_Site_Annotation", "429", "429", "ATP", "ECO_0000250", "R", "", "protein_xref_pubmed", "P35559" ], [ "Q9JHR7-1", "Ide", "Metal_Binding_Annotation", "189", "189", "Zinc", "ECO_0000255", "E", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Metal_Binding_Annotation", "189", "189", "Zinc", "ECO_0000255", "E", "", "protein_xref_pubmed", "PRU10096" ], [ "Q9JHR7-1", "Ide", "Metal_Binding_Annotation", "108", "108", "Zinc", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Metal_Binding_Annotation", "108", "108", "Zinc", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU10096" ], [ "Q9JHR7-1", "Ide", "Metal_Binding_Annotation", "112", "112", "Zinc", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Metal_Binding_Annotation", "112", "112", "Zinc", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU10096" ], [ "Q9JHR7-1", "Ide", "Modified_Residue_Annotation", "697", "697", "N6-succinyllysine", "ECO_0000244", "K", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Modified_Residue_Annotation", "697", "697", "N6-succinyllysine", "ECO_0000244", "K", "", "protein_xref_pubmed", "23806337" ], [ "Q9JHR7-1", "Ide", "Modified_Residue_Annotation", "192", "192", "N6-succinyllysine", "ECO_0000244", "K", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Modified_Residue_Annotation", "192", "192", "N6-succinyllysine", "ECO_0000244", "K", "", "protein_xref_pubmed", "23806337" ], [ "Q9JHR7-1", "Ide", "NP_Binding_Annotation", "895", "901", "ATP", "ECO_0000250", "DKPKKLS", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "NP_Binding_Annotation", "895", "901", "ATP", "ECO_0000250", "DKPKKLS", "", "protein_xref_pubmed", "P35559" ], [ "Q9JHR7-1", "Ide", "Mutagenesis_Annotation", "853", "858", "Marked decrease in secretion.", "ECO_0000269", "EKPPHY", "", "protein_xref_uniprotkb", "Q9JHR7" ], [ "Q9JHR7-1", "Ide", "Mutagenesis_Annotation", "853", "858", "Marked decrease in secretion.", "ECO_0000269", "EKPPHY", "", "protein_xref_pubmed", "21576244" ], [ "Q8VF66-1", "Olfr469", "Glycosylation_Annotation", "8", "8", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8VF66" ], [ "Q8VF65-1", "Olfr470", "Glycosylation_Annotation", "8", "8", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q8VF65" ], [ "B2RXV4-1", "Flvcr1", "Glycosylation_Annotation", "270", "270", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "B2RXV4" ], [ "B2RXV4-1", "Flvcr1", "Modified_Residue_Annotation", "542", "542", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "B2RXV4" ], [ "B2RXV4-1", "Flvcr1", "Modified_Residue_Annotation", "542", "542", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q9Y5Y0" ], [ "Q9CXG9-1", "Phf19", "Binding_Site_Annotation", "45", "45", "Histone H3K36me3", "", "L", "", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Binding_Site_Annotation", "53", "53", "Histone H3K36me3", "", "Y", "", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Modified_Residue_Annotation", "363", "363", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Modified_Residue_Annotation", "363", "363", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q5T6S3" ], [ "Q9CXG9-1", "Phf19", "Modified_Residue_Annotation", "185", "185", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Modified_Residue_Annotation", "185", "185", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q5T6S3" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "75", "75", "Does not affect ability to promote H3K27me3 methylation; when associated with S-78.", "ECO_0000269", "N", "S", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "75", "75", "Does not affect ability to promote H3K27me3 methylation; when associated with S-78.", "ECO_0000269", "N", "S", "protein_xref_pubmed", "22438827" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "78", "78", "Does not affect ability to promote H3K27me3 methylation; when associated with S-75.", "ECO_0000269", "Y", "S", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "78", "78", "Does not affect ability to promote H3K27me3 methylation; when associated with S-75.", "ECO_0000269", "Y", "S", "protein_xref_pubmed", "22438827" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "74", "74", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-72.", "ECO_0000269", "D", "A", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "74", "74", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-72.", "ECO_0000269", "D", "A", "protein_xref_pubmed", "22438827" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "48", "48", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-54.", "ECO_0000269", "W", "A", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "48", "48", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-54.", "ECO_0000269", "W", "A", "protein_xref_pubmed", "22438827" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "54", "54", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-48.", "ECO_0000269", "Y", "A", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "54", "54", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-48.", "ECO_0000269", "Y", "A", "protein_xref_pubmed", "22438827" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "72", "72", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-74.", "ECO_0000269", "F", "A", "protein_xref_uniprotkb", "Q9CXG9" ], [ "Q9CXG9-1", "Phf19", "Mutagenesis_Annotation", "72", "72", "Impairs ability to promote H3K27me3 methylation without affecting ability to associate with the PRC2 complex; when associated with A-74.", "ECO_0000269", "F", "A", "protein_xref_pubmed", "22438827" ], [ "Q07968-1", "F13b", "Glycosylation_Annotation", "546", "546", "N-linked (GlcNAc...) asparagine", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "Q07968" ], [ "Q07968-1", "F13b", "Glycosylation_Annotation", "546", "546", "N-linked (GlcNAc...) asparagine", "ECO_0000269", "N", "", "protein_xref_pubmed", "17330941" ], [ "Q07968-1", "F13b", "Glycosylation_Annotation", "546", "546", "N-linked (GlcNAc...) asparagine", "ECO_0000269", "N", "", "protein_xref_pubmed", "16944957" ], [ "Q07968-1", "F13b", "Glycosylation_Annotation", "163", "163", "N-linked (GlcNAc...) asparagine", "", "N", "", "protein_xref_uniprotkb", "Q07968" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "178", "178", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_uniprotkb", "Q9CXG3" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "178", "178", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_pubmed", "21183079" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "182", "182", "Phosphothreonine", "ECO_0000250", "T", "", "protein_xref_uniprotkb", "Q9CXG3" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "182", "182", "Phosphothreonine", "ECO_0000250", "T", "", "protein_xref_pubmed", "Q8WUA2" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "393", "393", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_uniprotkb", "Q9CXG3" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "393", "393", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_pubmed", "21183079" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "471", "471", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "Q9CXG3" ], [ "Q9CXG3-1", "Ppil4", "Modified_Residue_Annotation", "471", "471", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q8WUA2" ], [ "P01942-1", "Hba", "Metal_Binding_Annotation", "88", "88", "Iron (heme proximal ligand)", "", "H", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Metal_Binding_Annotation", "59", "59", "Iron (heme distal ligand)", "", "H", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "25", "25", "Phosphotyrosine", "ECO_0000244", "Y", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "25", "25", "Phosphotyrosine", "ECO_0000244", "Y", "", "protein_xref_pubmed", "21183079" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "8", "8", "N6-succinyllysine", "ECO_0000244", "K", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "8", "8", "N6-succinyllysine", "ECO_0000244", "K", "", "protein_xref_pubmed", "23806337" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "125", "125", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "125", "125", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_pubmed", "21183079" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "17", "17", "N6-succinyllysine; alternate", "ECO_0000244", "K", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "17", "17", "N6-succinyllysine; alternate", "ECO_0000244", "K", "", "protein_xref_pubmed", "23806337" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "17", "17", "N6-acetyllysine; alternate", "ECO_0000250", "K", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "17", "17", "N6-acetyllysine; alternate", "ECO_0000250", "K", "", "protein_xref_pubmed", "P69905" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "50", "50", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "50", "50", "Phosphoserine", "ECO_0000250", "S", "", "protein_xref_pubmed", "P69905" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "109", "109", "Phosphothreonine", "ECO_0000244", "T", "", "protein_xref_uniprotkb", "P01942" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "109", "109", "Phosphothreonine", "ECO_0000244", "T", "", "protein_xref_pubmed", "21183079" ], [ "P01942-1", "Hba", "Modified_Residue_Annotation", "139", "139", "Phosphoserine", "ECO_0000244", "S", "", "protein_xref_uniprotkb", "P01942" ] ] }, "readme": "Name\n - Mouse Protein Site Annotation\n\nVersion\n - 1.7.13\n\nCreated on\n - 2019-12-04T12:16:57.929402\n\nModified on\n - 2020-04-10T12:48:40.647497\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 Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] 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-mus-musculus.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/uniprot-proteome-mus-musculus.nt\n Name: mouse_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/mouse_protein_masterlist.csv\n Output Subdomain\n Name: mouse_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/mouse_protein_site_annotation_uniprotkb.csv\n Name: mouse_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/mouse_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"13269\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"13\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"25649\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"332\"\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: \"13167\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"3564\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"3263\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"10\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"3259\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"7736\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.7.13/reviewed/mouse_protein_site_annotation_uniprotkb.csv" }