{ "bcoid": "GLY_000316", "title": "Human Protein PTM Annotation (UniProtKB)", "description": "The Human Protein PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for ...", "filename": "human_protein_ptm_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "PTM annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8TBF5-1...", "protein_xref..." ], [ "Q8TBF5-1...", "protein_xref..." ] ], "headers": [ "uniprotkb_ca...", "xref_key..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "eco_id" }, { "type": "string", "label": "ptm_annotation" } ], [ "Q8TBF5-1", "protein_xref_uniprotkb", "Q8TBF5", "", "N-glycosylated." ], [ "Q8TBF5-1", "protein_xref_pubmed", "", "", "N-glycosylated." ], [ "Q9NQ79-1", "protein_xref_uniprotkb", "Q9NQ79", "ECO_0000269", "O-glycosylated." ], [ "Q9NQ79-1", "protein_xref_pubmed", "17074475", "ECO_0000269", "O-glycosylated." ], [ "Q9BZL4-1", "protein_xref_uniprotkb", "Q9BZL4", "ECO_0000269", "Phosphorylation at Thr-560 is essential for its interaction with PPP1CB." ], [ "Q9BZL4-1", "protein_xref_pubmed", "11399775", "ECO_0000269", "Phosphorylation at Thr-560 is essential for its interaction with PPP1CB." ], [ "Q9NQ75-1", "protein_xref_uniprotkb", "Q9NQ75", "ECO_0000269", "Phosphorylated on tyrosines by SRC." ], [ "Q9NQ75-1", "protein_xref_pubmed", "18256281", "ECO_0000269", "Phosphorylated on tyrosines by SRC." ], [ "P20930-1", "protein_xref_uniprotkb", "P20930", "", "Filaggrin is initially synthesized as a large, insoluble, highly phosphorylated precursor containing many tandem copies of 324 AA, which are not separated by large linker sequences. During terminal differentiation it is dephosphorylated and proteolytically cleaved. The N-terminal of the mature protein is heterogeneous, and is blocked by the formation of pyroglutamate." ], [ "P20930-1", "protein_xref_pubmed", "", "", "Filaggrin is initially synthesized as a large, insoluble, highly phosphorylated precursor containing many tandem copies of 324 AA, which are not separated by large linker sequences. During terminal differentiation it is dephosphorylated and proteolytically cleaved. The N-terminal of the mature protein is heterogeneous, and is blocked by the formation of pyroglutamate." ], [ "P20930-1", "protein_xref_uniprotkb", "P20930", "ECO_0000269", "Undergoes deimination of some arginine residues (citrullination)." ], [ "P20930-1", "protein_xref_pubmed", "8780679", "ECO_0000269", "Undergoes deimination of some arginine residues (citrullination)." ], [ "P20933-1", "protein_xref_uniprotkb", "P20933", "ECO_0000269", "N-glycosylated." ], [ "P20933-1", "protein_xref_pubmed", "2401370", "ECO_0000269", "N-glycosylated." ], [ "P20933-1", "protein_xref_uniprotkb", "P20933", "ECO_0000269", "Cleaved into an alpha and beta chain by autocatalysis; this activates the enzyme. The N-terminal residue of the beta subunit is responsible for the nucleophile hydrolase activity." ], [ "P20933-1", "protein_xref_pubmed", "1281977", "ECO_0000269", "Cleaved into an alpha and beta chain by autocatalysis; this activates the enzyme. The N-terminal residue of the beta subunit is responsible for the nucleophile hydrolase activity." ], [ "P20933-1", "protein_xref_pubmed", "1904874", "ECO_0000269", "Cleaved into an alpha and beta chain by autocatalysis; this activates the enzyme. The N-terminal residue of the beta subunit is responsible for the nucleophile hydrolase activity." ], [ "P20933-1", "protein_xref_pubmed", "1703489", "ECO_0000269", "Cleaved into an alpha and beta chain by autocatalysis; this activates the enzyme. The N-terminal residue of the beta subunit is responsible for the nucleophile hydrolase activity." ], [ "P20936-1", "protein_xref_uniprotkb", "P20936", "", "The N-terminus is blocked." ], [ "P20936-1", "protein_xref_pubmed", "", "", "The N-terminus is blocked." ], [ "P20936-1", "protein_xref_uniprotkb", "P20936", "ECO_0000269", "Phosphorylated by SRC and LCK. The phosphorylation SRC inhibits its ability to stimulate the Ras-GTPase activity, whereas phosphorylation by LCK does not display any effect on stimulation activity." ], [ "P20936-1", "protein_xref_pubmed", "11389730", "ECO_0000269", "Phosphorylated by SRC and LCK. The phosphorylation SRC inhibits its ability to stimulate the Ras-GTPase activity, whereas phosphorylation by LCK does not display any effect on stimulation activity." ], [ "P40617-1", "protein_xref_uniprotkb", "P40617", "ECO_0000269", "Myristoylated." ], [ "P40617-1", "protein_xref_pubmed", "10980193", "ECO_0000269", "Myristoylated." ], [ "Q8NHX9-1", "protein_xref_uniprotkb", "Q8NHX9", "ECO_0000250", "N-glycosylated." ], [ "Q8NHX9-1", "protein_xref_pubmed", "Q8BWC0", "ECO_0000250", "N-glycosylated." ], [ "A8MU46-1", "protein_xref_uniprotkb", "A8MU46", "", "Maximal phosphorylation of Ser-336 correlates with maximal relaxation of aorta in response to acetylcholine." ], [ "A8MU46-1", "protein_xref_pubmed", "", "", "Maximal phosphorylation of Ser-336 correlates with maximal relaxation of aorta in response to acetylcholine." ], [ "Q9C0H2-1", "protein_xref_uniprotkb", "Q9C0H2", "ECO_0000269", "N-glycosylated." ], [ "Q9C0H2-1", "protein_xref_pubmed", "19159218", "ECO_0000269", "N-glycosylated." ], [ "Q9C0H2-1", "protein_xref_pubmed", "15010458", "ECO_0000269", "N-glycosylated." ], [ "Q9C0H9-5", "protein_xref_uniprotkb", "Q9C0H9", "ECO_0000269", "Tyrosine-phosphorylated in response to EGF and to cell adhesion to integrin ligands." ], [ "Q9C0H9-5", "protein_xref_pubmed", "14657239", "ECO_0000269", "Tyrosine-phosphorylated in response to EGF and to cell adhesion to integrin ligands." ], [ "Q9NXR1-2", "protein_xref_uniprotkb", "Q9NXR1", "", "Phosphorylated in mitosis. Phosphorylated in vitro by CDC2. Phosphorylation at Thr-246 is essential for the G2/M transition (By similarity)." ], [ "Q9NXR1-2", "protein_xref_pubmed", "", "", "Phosphorylated in mitosis. Phosphorylated in vitro by CDC2. Phosphorylation at Thr-246 is essential for the G2/M transition (By similarity)." ], [ "Q00536-1", "protein_xref_uniprotkb", "Q00536", "ECO_0000269", "Phosphorylation at Ser-153 inhibits kinase activity." ], [ "Q00536-1", "protein_xref_pubmed", "22798068", "ECO_0000269", "Phosphorylation at Ser-153 inhibits kinase activity." ], [ "O00241-1", "protein_xref_uniprotkb", "O00241", "ECO_0000269", "N-glycosylated." ], [ "O00241-1", "protein_xref_pubmed", "16335952", "ECO_0000269", "N-glycosylated." ], [ "O00241-1", "protein_xref_pubmed", "10604985", "ECO_0000269", "N-glycosylated." ], [ "Q9UBM1-1", "protein_xref_uniprotkb", "Q9UBM1", "ECO_0000269", "Isoform 2 is N-glycosylated with high-mannose oligosaccharides." ], [ "Q9UBM1-1", "protein_xref_pubmed", "20860552", "ECO_0000269", "Isoform 2 is N-glycosylated with high-mannose oligosaccharides." ], [ "Q9UBM4-1", "protein_xref_uniprotkb", "Q9UBM4", "ECO_0000305", "O-glycosylated." ], [ "Q9UBM4-1", "protein_xref_pubmed", "16335952", "ECO_0000305", "O-glycosylated." ], [ "Q9UBM4-1", "protein_xref_uniprotkb", "Q9UBM4", "ECO_0000269", "Proteolytically cleaved by MMP1, MMP2, MMP3, MMP7, MMP8, MMP9, ADAMTS4, and ADAMTS5 (PubMed:23845380). Proteolytically cleaved by MMP13 (By similarity). The degradation of OPTC by proteases may contribute to osteoarthritis pathophysiology (PubMed:23845380)." ], [ "Q9UBM4-1", "protein_xref_pubmed", "23845380", "ECO_0000269", "Proteolytically cleaved by MMP1, MMP2, MMP3, MMP7, MMP8, MMP9, ADAMTS4, and ADAMTS5 (PubMed:23845380). Proteolytically cleaved by MMP13 (By similarity). The degradation of OPTC by proteases may contribute to osteoarthritis pathophysiology (PubMed:23845380)." ], [ "Q9UBM4-1", "protein_xref_uniprotkb", "Q9UBM4", "ECO_0000250", "Proteolytically cleaved by MMP1, MMP2, MMP3, MMP7, MMP8, MMP9, ADAMTS4, and ADAMTS5 (PubMed:23845380). Proteolytically cleaved by MMP13 (By similarity). The degradation of OPTC by proteases may contribute to osteoarthritis pathophysiology (PubMed:23845380)." ], [ "Q9UBM4-1", "protein_xref_pubmed", "P58874", "ECO_0000250", "Proteolytically cleaved by MMP1, MMP2, MMP3, MMP7, MMP8, MMP9, ADAMTS4, and ADAMTS5 (PubMed:23845380). Proteolytically cleaved by MMP13 (By similarity). The degradation of OPTC by proteases may contribute to osteoarthritis pathophysiology (PubMed:23845380)." ], [ "Q9UBM4-1", "protein_xref_uniprotkb", "Q9UBM4", "ECO_0000269", "Sulfated on tyrosine residues." ], [ "Q9UBM4-1", "protein_xref_pubmed", "25136834", "ECO_0000269", "Sulfated on tyrosine residues." ], [ "P40429-1", "protein_xref_uniprotkb", "P40429", "", "Citrullinated by PADI4." ], [ "P40429-1", "protein_xref_pubmed", "", "", "Citrullinated by PADI4." ], [ "P40429-1", "protein_xref_uniprotkb", "P40429", "ECO_0000269", "Phosphorylation at Ser-77 upon interferon-gamma treatment in monocytes involves a DAPK1-DAPK3 kinase cascade and is causing release from the ribosome, association with the GAIT complex and subsequent involvement in transcript-selective translation inhibition." ], [ "P40429-1", "protein_xref_pubmed", "18995835", "ECO_0000269", "Phosphorylation at Ser-77 upon interferon-gamma treatment in monocytes involves a DAPK1-DAPK3 kinase cascade and is causing release from the ribosome, association with the GAIT complex and subsequent involvement in transcript-selective translation inhibition." ], [ "P40429-1", "protein_xref_pubmed", "14567916", "ECO_0000269", "Phosphorylation at Ser-77 upon interferon-gamma treatment in monocytes involves a DAPK1-DAPK3 kinase cascade and is causing release from the ribosome, association with the GAIT complex and subsequent involvement in transcript-selective translation inhibition." ], [ "Q8WTV0-1", "protein_xref_uniprotkb", "Q8WTV0", "ECO_0000250", "The six cysteines of the extracellular domain are all involved in intramolecular disulfide bonds." ], [ "Q8WTV0-1", "protein_xref_pubmed", "Q61009", "ECO_0000250", "The six cysteines of the extracellular domain are all involved in intramolecular disulfide bonds." ], [ "Q8WTV0-1", "protein_xref_uniprotkb", "Q8WTV0", "ECO_0000269", "N-glycosylated." ], [ "Q8WTV0-1", "protein_xref_pubmed", "19159218", "ECO_0000269", "N-glycosylated." ], [ "Q8WTV0-1", "protein_xref_pubmed", "12016218", "ECO_0000269", "N-glycosylated." ], [ "P08842-1", "protein_xref_uniprotkb", "P08842", "ECO_0000269", "The conversion to 3-oxoalanine (also known as C-formylglycine, FGly), of a serine or cysteine residue in prokaryotes and of a cysteine residue in eukaryotes, is critical for catalytic activity." ], [ "P08842-1", "protein_xref_pubmed", "12657638", "ECO_0000269", "The conversion to 3-oxoalanine (also known as C-formylglycine, FGly), of a serine or cysteine residue in prokaryotes and of a cysteine residue in eukaryotes, is critical for catalytic activity." ], [ "P48960-1", "protein_xref_uniprotkb", "P48960", "", "Proteolytically cleaved into 2 subunits, an extracellular alpha subunit and a seven-transmembrane subunit." ], [ "P48960-1", "protein_xref_pubmed", "", "", "Proteolytically cleaved into 2 subunits, an extracellular alpha subunit and a seven-transmembrane subunit." ], [ "P02768-1", "protein_xref_uniprotkb", "P02768", "", "Acetylated on Lys-223 by acetylsalicylic acid." ], [ "P02768-1", "protein_xref_pubmed", "", "", "Acetylated on Lys-223 by acetylsalicylic acid." ], [ "P02768-1", "protein_xref_uniprotkb", "P02768", "", "Glycated in diabetic patients." ], [ "P02768-1", "protein_xref_pubmed", "", "", "Glycated in diabetic patients." ], [ "P02768-1", "protein_xref_uniprotkb", "P02768", "", "Kenitra variant is partially O-glycosylated at Thr-620. It has two new disulfide bonds Cys-600 to Cys-602 and Cys-601 to Cys-606." ], [ "P02768-1", "protein_xref_pubmed", "", "", "Kenitra variant is partially O-glycosylated at Thr-620. It has two new disulfide bonds Cys-600 to Cys-602 and Cys-601 to Cys-606." ], [ "P02768-1", "protein_xref_uniprotkb", "P02768", "ECO_0000269", "Phosphorylated by FAM20C in the extracellular medium." ], [ "P02768-1", "protein_xref_pubmed", "26091039", "ECO_0000269", "Phosphorylated by FAM20C in the extracellular medium." ], [ "P08559-1", "protein_xref_uniprotkb", "P08559", "", "Acetylation alters the phosphorylation pattern. Deacetylated by SIRT3 (By similarity)." ], [ "P08559-1", "protein_xref_pubmed", "", "", "Acetylation alters the phosphorylation pattern. Deacetylated by SIRT3 (By similarity)." ], [ "P08559-1", "protein_xref_uniprotkb", "P08559", "ECO_0000269", "Phosphorylation at Ser-232, Ser-293 and Ser-300 by PDK family kinases inactivates the enzyme; for this phosphorylation at a single site is sufficient. Dephosphorylation at all three sites, i.e. at Ser-232, Ser-293 and Ser-300, is required for reactivation." ], [ "P08559-1", "protein_xref_pubmed", "17474719", "ECO_0000269", "Phosphorylation at Ser-232, Ser-293 and Ser-300 by PDK family kinases inactivates the enzyme; for this phosphorylation at a single site is sufficient. Dephosphorylation at all three sites, i.e. at Ser-232, Ser-293 and Ser-300, is required for reactivation." ], [ "P08559-1", "protein_xref_pubmed", "19081061", "ECO_0000269", "Phosphorylation at Ser-232, Ser-293 and Ser-300 by PDK family kinases inactivates the enzyme; for this phosphorylation at a single site is sufficient. Dephosphorylation at all three sites, i.e. at Ser-232, Ser-293 and Ser-300, is required for reactivation." ], [ "P08559-1", "protein_xref_pubmed", "11486000", "ECO_0000269", "Phosphorylation at Ser-232, Ser-293 and Ser-300 by PDK family kinases inactivates the enzyme; for this phosphorylation at a single site is sufficient. Dephosphorylation at all three sites, i.e. at Ser-232, Ser-293 and Ser-300, is required for reactivation." ], [ "P02760-1", "protein_xref_uniprotkb", "P02760", "", "Heavy chains are interlinked with bikunin via a chondroitin 4-sulfate bridge to the their C-terminal aspartate." ], [ "P02760-1", "protein_xref_pubmed", "", "", "Heavy chains are interlinked with bikunin via a chondroitin 4-sulfate bridge to the their C-terminal aspartate." ], [ "P02760-1", "protein_xref_uniprotkb", "P02760", "ECO_0000269", "N- and O-glycosylated. N-glycan heterogeneity at Asn-115: Hex5HexNAc4 (major), Hex6HexNAc5 (minor) and dHex1Hex6HexNAc5 (minor). N-glycan at Asn-250: Hex5HexNAc4. O-linkage of the glycosaminoglycan, chondroitin sulfate, at Ser-215 allows cross-linking between the three polypeptide chains." ], [ "P02760-1", "protein_xref_pubmed", "7682553", "ECO_0000269", "N- and O-glycosylated. N-glycan heterogeneity at Asn-115: Hex5HexNAc4 (major), Hex6HexNAc5 (minor) and dHex1Hex6HexNAc5 (minor). N-glycan at Asn-250: Hex5HexNAc4. O-linkage of the glycosaminoglycan, chondroitin sulfate, at Ser-215 allows cross-linking between the three polypeptide chains." ], [ "P02760-1", "protein_xref_pubmed", "1898736", "ECO_0000269", "N- and O-glycosylated. N-glycan heterogeneity at Asn-115: Hex5HexNAc4 (major), Hex6HexNAc5 (minor) and dHex1Hex6HexNAc5 (minor). N-glycan at Asn-250: Hex5HexNAc4. O-linkage of the glycosaminoglycan, chondroitin sulfate, at Ser-215 allows cross-linking between the three polypeptide chains." ], [ "P02760-1", "protein_xref_pubmed", "1694784", "ECO_0000269", "N- and O-glycosylated. N-glycan heterogeneity at Asn-115: Hex5HexNAc4 (major), Hex6HexNAc5 (minor) and dHex1Hex6HexNAc5 (minor). N-glycan at Asn-250: Hex5HexNAc4. O-linkage of the glycosaminoglycan, chondroitin sulfate, at Ser-215 allows cross-linking between the three polypeptide chains." ] ] }, "readme": "Name\n - Human Protein PTM Annotation (UniProtKB)\n\nVersion\n - 1.8.25\n\nCreated on\n - 2019-11-30T13:58:37.032006\n\nModified on\n - 2020-04-11T11:28:33.003978\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 PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. 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 - ptm annotation\n - glycosylation\n - phosphorylation\n\n Pipeline Steps\n - Step-1: The script extracts the ptm annotation strings 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/ln2data/releases/data/v-1.8.25/reviewed/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_ptm_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_ptm_annotation_uniprotkb.csv\n Name: human_protein_ptm_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"119\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"119\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"120\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"49\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"118\"\n Name: \"publication_date\"\n Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n Unique Values: \"117\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"115\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.8.25/reviewed/human_protein_ptm_annotation_uniprotkb.csv" }