{ "bcoid": "GLY_000444", "title": "SARS-CoV2 Protein Site Annotation", "description": "The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 ...", "filename": "sarscov2_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "SARS coronavirus (SARS-CoV-2 or 2019-nCoV)", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P0DTC7-1...", "..." ], [ "P0DTC7-1...", "..." ] ], "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" } ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "119", "119", "Complete loss of ubiquitination. Partial loss of interferon pathway inhibition.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "119", "119", "Complete loss of ubiquitination. Partial loss of interferon pathway inhibition.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "117", "117", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "117", "117", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "72", "72", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "72", "72", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "32", "32", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "32", "32", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "2", "2", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "2", "2", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "85", "85", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "85", "85", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "53", "53", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Mutagenesis_Annotation", "53", "53", "No effect on ubiquitination.", "ECO_0000269", "K", "A", "protein_xref_pubmed", "33473190" ], [ "P0DTC7-1", "", "Natural_Variant_Annotation", "14", "14", "In strain: B.1.1.7.", "ECO_0000305", "T", "I", "protein_xref_uniprotkb", "P0DTC7" ], [ "P0DTC7-1", "", "Natural_Variant_Annotation", "14", "14", "In strain: B.1.1.7.", "ECO_0000305", "T", "I", "protein_xref_pubmed", "33413740" ], [ "P0DTC6-1", "", "Mutagenesis_Annotation", "58", "58", "Complete loss of binding to the NUP98-RAE1 complex and IFN antagonistic function.", "ECO_0000269", "M", "R", "protein_xref_uniprotkb", "P0DTC6" ], [ "P0DTC6-1", "", "Mutagenesis_Annotation", "58", "58", "Complete loss of binding to the NUP98-RAE1 complex and IFN antagonistic function.", "ECO_0000269", "M", "R", "protein_xref_pubmed", "33097660" ], [ "P0DTC3-1", "", "Site_Annotation", "133", "133", "Involved in polymerization", "ECO_0000250", "C", "", "protein_xref_uniprotkb", "P0DTC3" ], [ "P0DTC3-1", "", "Site_Annotation", "133", "133", "Involved in polymerization", "ECO_0000250", "C", "", "protein_xref_pubmed", "P59632" ], [ "P0DTC3-1", "", "Glycosylation_Annotation", "32", "32", "O-linked (GalNAc...) threonine; by host", "ECO_0000250", "T", "", "protein_xref_uniprotkb", "P0DTC3" ], [ "P0DTC3-1", "", "Glycosylation_Annotation", "32", "32", "O-linked (GalNAc...) threonine; by host", "ECO_0000250", "T", "", "protein_xref_pubmed", "P59632" ], [ "P0DTC3-1", "", "Glycosylation_Annotation", "34", "34", "O-linked (GalNAc...) threonine; by host", "", "T", "", "protein_xref_uniprotkb", "P0DTC3" ], [ "P0DTC3-1", "", "Natural_Variant_Annotation", "57", "57", "In strain: B.1.427 and B.1.429.", "", "Q", "H", "protein_xref_uniprotkb", "P0DTC3" ], [ "P0DTC3-1", "", "Natural_Variant_Annotation", "174", "174", "In strain: P1/B1.1.28.1.", "", "G", "C", "protein_xref_uniprotkb", "P0DTC3" ], [ "P0DTC2-1", "S", "Site_Annotation", "815", "816", "Cleavage; by host", "ECO_0000255", "RS", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Site_Annotation", "815", "816", "Cleavage; by host", "ECO_0000255", "RS", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Site_Annotation", "685", "686", "Cleavage; by TMPRSS2 or furin", "ECO_0000255", "RS", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Site_Annotation", "685", "686", "Cleavage; by TMPRSS2 or furin", "ECO_0000255", "RS", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Site_Annotation", "685", "686", "Cleavage; by TMPRSS2 or furin", "ECO_0000269", "RS", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Site_Annotation", "685", "686", "Cleavage; by TMPRSS2 or furin", "ECO_0000269", "RS", "", "protein_xref_pubmed", "32142651" ], [ "P0DTC2-1", "S", "Site_Annotation", "685", "686", "Cleavage; by TMPRSS2 or furin", "ECO_0000269", "RS", "", "protein_xref_pubmed", "32362314" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32363391" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "717", "717", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32155444" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32363391" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1074", "1074", "N-linked (GlcNAc...) (hybrid) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32155444" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32363391" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "709", "709", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32155444" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32363391" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1098", "1098", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32155444" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32363391" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "616", "616", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32155444" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1134", "1134", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1134", "1134", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1134", "1134", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1134", "1134", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1134", "1134", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1134", "1134", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32155444" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1158", "1158", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1158", "1158", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1158", "1158", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1158", "1158", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "1158", "1158", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "17", "17", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "17", "17", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000255", "N", "", "protein_xref_pubmed", "MF_04099" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "17", "17", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "17", "17", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32979942" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "17", "17", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "32366695" ], [ "P0DTC2-1", "S", "Glycosylation_Annotation", "149", "149", "N-linked (GlcNAc...) (complex) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P0DTC2" ] ] }, "readme": "Name\n - SARS-CoV2 Protein Site Annotation\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-04-03T11:59:02.009860\n\nModified on\n - 2022-01-13T16:28:14.972312\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@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 SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] 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/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: sarscov2_protein_masterlist.csv\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/sarscov2_protein_masterlist.csv\n Name: uniprot-proteome-sars-cov-2.nt\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/sarscov2_protein_ntdata.nt\n Output Subdomain\n Name: sarscov2_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv\n Name: sarscov2_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_site_annotation_uniprotkb.stat.csv", "downloadurl": "/ln2data/releases/data/v-1.12.1/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv" }