{ "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": [ [ "Q8NHX9-1...", "protein_xref..." ], [ "Q8NHX9-1...", "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" } ], [ "Q8NHX9-1", "protein_xref_uniprotkb", "Q8NHX9", "ECO_0000250", "N-glycosylated." ], [ "Q8NHX9-1", "protein_xref_pubmed", "Q8BWC0", "ECO_0000250", "N-glycosylated." ], [ "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." ], [ "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." ], [ "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." ], [ "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." ], [ "P02760-1", "protein_xref_pubmed", "22171320", "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", "6171497", "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." ], [ "P02763-1", "protein_xref_uniprotkb", "P02763", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "1567356", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "19159218", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "12754519", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "16335952", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "19838169", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "16740002", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "15253437", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "14760718", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "15084671", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02763-1", "protein_xref_pubmed", "22171320", "ECO_0000269", "N-glycosylated. N-glycan heterogeneity at Asn-33: Hex5HexNAc4 (minor), Hex6HexNAc5 (major) and dHex1Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_uniprotkb", "P02765", "ECO_0000269", "Phosphorylated by FAM20C in the extracellular medium." ], [ "P02765-1", "protein_xref_pubmed", "11439093", "ECO_0000269", "Phosphorylated by FAM20C in the extracellular medium." ], [ "P02765-1", "protein_xref_pubmed", "26091039", "ECO_0000269", "Phosphorylated by FAM20C in the extracellular medium." ], [ "P02765-1", "protein_xref_uniprotkb", "P02765", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "19159218", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "12754519", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "16335952", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "19838169", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "16740002", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "14760718", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "19139490", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02765-1", "protein_xref_pubmed", "22171320", "ECO_0000269", "O- and N-glycosylated. O-glycosylated with core 1 or possibly core 8 glycans. N-glycan at Asn-156: Hex5HexNAc4; N-glycan heterogeneity at Asn-176: Hex5HexNAc4 (major) and Hex6HexNAc5 (minor)." ], [ "P02766-1", "protein_xref_uniprotkb", "P02766", "ECO_0000269", "Not glycosylated under normal conditions. Following unfolding, caused for example by variant AMYL-TTR 'Gly-38', the cryptic Asn-118 site is exposed and glycosylated by STT3B-containing OST complex, leading to its degradation by the ER-associated degradation (ERAD) pathway." ], [ "P02766-1", "protein_xref_pubmed", "16335952", "ECO_0000269", "Not glycosylated under normal conditions. Following unfolding, caused for example by variant AMYL-TTR 'Gly-38', the cryptic Asn-118 site is exposed and glycosylated by STT3B-containing OST complex, leading to its degradation by the ER-associated degradation (ERAD) pathway." ], [ "P02766-1", "protein_xref_pubmed", "19167329", "ECO_0000269", "Not glycosylated under normal conditions. Following unfolding, caused for example by variant AMYL-TTR 'Gly-38', the cryptic Asn-118 site is exposed and glycosylated by STT3B-containing OST complex, leading to its degradation by the ER-associated degradation (ERAD) pathway." ], [ "P02766-1", "protein_xref_pubmed", "14760718", "ECO_0000269", "Not glycosylated under normal conditions. Following unfolding, caused for example by variant AMYL-TTR 'Gly-38', the cryptic Asn-118 site is exposed and glycosylated by STT3B-containing OST complex, leading to its degradation by the ER-associated degradation (ERAD) pathway." ], [ "Q9BZG2-1", "protein_xref_uniprotkb", "Q9BZG2", "ECO_0000305", "Glycosylated." ], [ "Q9BZG2-1", "protein_xref_pubmed", "15219672", "ECO_0000305", "Glycosylated." ], [ "Q14566-1", "protein_xref_uniprotkb", "Q14566", "ECO_0000269", "O-glycosylated (O-GlcNAcylated), in a cell cycle-dependent manner." ], [ "Q14566-1", "protein_xref_pubmed", "22967762", "ECO_0000269", "O-glycosylated (O-GlcNAcylated), in a cell cycle-dependent manner." ], [ "Q6ZMG9-1", "protein_xref_uniprotkb", "Q6ZMG9", "ECO_0000250", "Acetylated. Deacetylation by SIRT3 increases enzyme activity and promotes mitochondrial ceramide accumulation." ], [ "Q6ZMG9-1", "protein_xref_pubmed", "Q8C172", "ECO_0000250", "Acetylated. Deacetylation by SIRT3 increases enzyme activity and promotes mitochondrial ceramide accumulation." ], [ "Q6ZMG9-1", "protein_xref_uniprotkb", "Q6ZMG9", "ECO_0000269", "Phosphorylated at the C-terminus by CK2." ], [ "Q6ZMG9-1", "protein_xref_pubmed", "26887952", "ECO_0000269", "Phosphorylated at the C-terminus by CK2." ], [ "Q96BT3-1", "protein_xref_uniprotkb", "Q96BT3", "ECO_0000269", "Dynamically phosphorylated at Ser-47 and probably also other sites during the cell cycle. Phosphorylated at Ser-47 during G2 phase, metaphase and anaphase, but not during telophase or G1 phase." ], [ "Q96BT3-1", "protein_xref_pubmed", "21529714", "ECO_0000269", "Dynamically phosphorylated at Ser-47 and probably also other sites during the cell cycle. Phosphorylated at Ser-47 during G2 phase, metaphase and anaphase, but not during telophase or G1 phase." ], [ "Q99519-1", "protein_xref_uniprotkb", "Q99519", "ECO_0000269", "N-glycosylated." ], [ "Q99519-1", "protein_xref_pubmed", "19159218", "ECO_0000269", "N-glycosylated." ], [ "Q99519-1", "protein_xref_pubmed", "9480870", "ECO_0000269", "N-glycosylated." ], [ "Q99519-1", "protein_xref_pubmed", "8985184", "ECO_0000269", "N-glycosylated." ], [ "Q96RU2-1", "protein_xref_uniprotkb", "Q96RU2", "ECO_0000269", "Phosphorylated upon DNA damage at Ser-67 and Ser-714, by ATM or ATR (PubMed:16901786). Phosphorylated by PRKD1 (PubMed:24623306)." ], [ "Q96RU2-1", "protein_xref_pubmed", "24623306", "ECO_0000269", "Phosphorylated upon DNA damage at Ser-67 and Ser-714, by ATM or ATR (PubMed:16901786). Phosphorylated by PRKD1 (PubMed:24623306)." ], [ "Q96RU2-1", "protein_xref_pubmed", "16901786", "ECO_0000269", "Phosphorylated upon DNA damage at Ser-67 and Ser-714, by ATM or ATR (PubMed:16901786). Phosphorylated by PRKD1 (PubMed:24623306)." ], [ "Q13641-1", "protein_xref_uniprotkb", "Q13641", "ECO_0000269", "Highly glycosylated." ], [ "Q13641-1", "protein_xref_pubmed", "19159218", "ECO_0000269", "Highly glycosylated." ], [ "Q13641-1", "protein_xref_pubmed", "24582434", "ECO_0000269", "Highly glycosylated." ], [ "Q9Y5A9-1", "protein_xref_uniprotkb", "Q9Y5A9", "ECO_0000269", "Ubiquitinated by the SCF(SKP2) complex, leading to its degradation." ], [ "Q9Y5A9-1", "protein_xref_pubmed", "32267835", "ECO_0000269", "Ubiquitinated by the SCF(SKP2) complex, leading to its degradation." ], [ "Q9Y294-1", "protein_xref_uniprotkb", "Q9Y294", "ECO_0000269", "Phosphorylated by TLK1 and TLK2. Highly phosphorylated in S-phase and at lower levels in M-phase. TLK2-mediated phosphorylation at Ser-192 prevents proteasome-dependent degradation." ], [ "Q9Y294-1", "protein_xref_pubmed", "11470414", "ECO_0000269", "Phosphorylated by TLK1 and TLK2. Highly phosphorylated in S-phase and at lower levels in M-phase. TLK2-mediated phosphorylation at Ser-192 prevents proteasome-dependent degradation." ], [ "Q9Y294-1", "protein_xref_pubmed", "20016786", "ECO_0000269", "Phosphorylated by TLK1 and TLK2. Highly phosphorylated in S-phase and at lower levels in M-phase. TLK2-mediated phosphorylation at Ser-192 prevents proteasome-dependent degradation." ], [ "Q9Y295-1", "protein_xref_uniprotkb", "Q9Y295", "ECO_0000269", "Sumoylated by UBE2I in response to MEKK1-mediated stimuli." ], [ "Q9Y295-1", "protein_xref_pubmed", "17709345", "ECO_0000269", "Sumoylated by UBE2I in response to MEKK1-mediated stimuli." ], [ "Q9Y295-1", "protein_xref_uniprotkb", "Q9Y295", "ECO_0000269", "Hydroxylated (with S stereochemistry) at C-3 of Lys-22 by JMJD7; this modification hinders trypsin-catalyzed proteolysis in vitro." ], [ "Q9Y295-1", "protein_xref_pubmed", "29915238", "ECO_0000269", "Hydroxylated (with S stereochemistry) at C-3 of Lys-22 by JMJD7; this modification hinders trypsin-catalyzed proteolysis in vitro." ], [ "Q9Y295-1", "protein_xref_uniprotkb", "Q9Y295", "ECO_0000269", "Phosphorylated at Thr-100 by STK16." ], [ "Q9Y295-1", "protein_xref_pubmed", "18184589", "ECO_0000269", "Phosphorylated at Thr-100 by STK16." ], [ "Q9Y295-1", "protein_xref_uniprotkb", "Q9Y295", "ECO_0000250", "Polyubiquitinated; this modification induces proteolytic degradation and is impaired by interaction with ZC3H15." ], [ "Q9Y295-1", "protein_xref_pubmed", "P32233", "ECO_0000250", "Polyubiquitinated; this modification induces proteolytic degradation and is impaired by interaction with ZC3H15." ], [ "P61289-1", "protein_xref_uniprotkb", "P61289", "ECO_0000269", "Phosphorylated by MAP3K3 (By similarity). Phosphorylation at Ser-247 promotes its association with CCAR2." ], [ "P61289-1", "protein_xref_pubmed", "25361978", "ECO_0000269", "Phosphorylated by MAP3K3 (By similarity). Phosphorylation at Ser-247 promotes its association with CCAR2." ], [ "P61289-1", "protein_xref_uniprotkb", "P61289", "ECO_0000250", "Phosphorylated by MAP3K3 (By similarity). Phosphorylation at Ser-247 promotes its association with CCAR2." ], [ "P61289-1", "protein_xref_pubmed", "P61290", "ECO_0000250", "Phosphorylated by MAP3K3 (By similarity). Phosphorylation at Ser-247 promotes its association with CCAR2." ], [ "P61289-1", "protein_xref_uniprotkb", "P61289", "ECO_0000269", "Acetylation at the major site Lys-195 is important for oligomerization and ability to degrade its target substrates. Deacetylated by SIRT1." ], [ "P61289-1", "protein_xref_pubmed", "SIPE5468F94A72A33A3", "ECO_0000269", "Acetylation at the major site Lys-195 is important for oligomerization and ability to degrade its target substrates. Deacetylated by SIRT1." ] ] }, "readme": "Name\n - Human Protein PTM Annotation (UniProtKB)\n\nVersion\n - 1.11.2\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], 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 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/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_ptm_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.csv\n Name: human_protein_ptm_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"16\"\n Name: \"motif_start\"\n Description: \"\"\n Unique Values: \"23\"\n Name: \"filter_flags\"\n Description: \"Filter tags/flags assigned to the mutation entries that have passed the mutation filter criteria\"\n Unique Values: \"19\"\n Name: \"sift_prediction\"\n Description: \"The SIFT qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"3\"\n Name: \"somatic_status\"\n Description: \"The status of the variant whether it is germline (somatic status =0) or somatic (somatic status =1) variant\"\n Unique Values: \"1\"\n Name: \"chr_pos\"\n Description: \"Chromosome Position of a gene\"\n Unique Values: \"19\"\n Name: \"chr_id\"\n Description: \"\"\n Unique Values: \"10\"\n Name: \"dbsnp_id\"\n Description: \"\"A reference SNP ID number\"\n Unique Values: \"19\"\n Name: \"evidence_ECO:0000313\"\n Description: \"A type of evidence that is imported information used in an automatic assertion\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"19\"\n Name: \"mim_id\"\n Description: \"Disease ID from the OMIM database\"\n Unique Values: \"1\"\n Name: \"description\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"begin_aa_pos\"\n Description: \"Start position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"cytogenic_band\"\n Description: \"One of the subregions of a chromosome visible microscopically after special staining\"\n Unique Values: \"14\"\n Name: \"aa_pos\"\n Description: \"Position of the amino acid in canonical sequence of protein in the UniProtKB database\"\n Unique Values: \"18\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"9\"\n Name: \"sift_score\"\n Description: \"SIFT predicts whether an amino acid substitution is likely to affect protein function based on sequence homology and the physico-chemical similarity between the alternate amino acids. The data we provide for each amino acid substitution is a score and a qualitative prediction (either 'tolerated' or 'deleterious'). The score is the normalized probability that the amino acid change is tolerated so scores nearer zero are more likely to be deleterious. The qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"10\"\n Name: \"alt_motif\"\n Description: \"Altered motif\"\n Unique Values: \"24\"\n Name: \"disease_xrefs\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"polyphen_score\"\n Description: \"The score assigned to a amino acid substitution by a tool called as PolyPhen (=Polymorphism Phenotyping) which predicts possible impact of an amino acid substitution on the structure and function of a human protein using straightforward physical and comparative considerations. The PolyPhen score ranges from 0.0 (tolerated) to 1.0 (deleterious). Variants with scores of 0.0 are predicted to be benign. Values closer to 1.0 are more confidently predicted to be deleterious\"\n Unique Values: \"1\"\n Name: \"polyphen_prediction\"\n Description: \"\"The PolyPhen prediction values are - greater than 0.908 - \"\"Probably Damaging\"\"; greater than 0.446 and less than or equal to 0.908 - \"\"Possibly Damaging\"\"; less than or equal to 0.446 - \"\"Benign\"\"\"\n Unique Values: \"1\"\n Name: \"is_known_glycoprotein\"\n Description: \"Yes or no flag to denote if a protein is experimentally proven glycoprotein\"\n Unique Values: \"1\"\n Name: \"alt_nt\"\n Description: \"Alternative nucleotide\"\n Unique Values: \"1\"\n Name: \"protein_name\"\n Description: \"Protein name in the UniProtKB\"\n Unique Values: \"16\"\n Name: \"disease_evidence_ECO:0000313\"\n Description: \"The evidence that could be a PMID or a ClinVar ID that associates disease with the variant\"\n Unique Values: \"1\"\n Name: \"effect\"\n Description: \"The effect on glycosylation or N-sequon due to variation at site of glycosylated amino acid.\"\n Unique Values: \"3\"\n Name: \"end_aa_pos\"\n Description: \"End position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"mutation_type\"\n Description: \"Denotes whether mutation was reported with reference to amino acid or nucleotide\"\n Unique Values: \"1\"\n Name: \"disease_description\"\n Description: \"The disease description and/or definition \"\n Unique Values: \"1\"\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"1\"\n Name: \"evidence_ECO:0000269\"\n Description: \"A type of experimental evidence that is used in a manual assertion. Usually the values are PMIDs\"\n Unique Values: \"1\"\n Name: \"ref_nt\"\n Description: \"Reference nucleotide\"\n Unique Values: \"4\"\n Name: \"disease\"\n Description: \"The disease name for the cell line\"\n Unique Values: \"1\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"10\"\n Name: \"cosmic_id\"\n Description: \"Legacy mutation identifier (COSM) in Catalogue of Somatic Mutations in Cancer (COSMIC) represents existing COSM mutation identifiers. This identifier remains the same between different assemblies (GRCh37 and GRCh38). All the COSM ids at the same genomic location have been collapsed into one representative COSM id. These ids are maintained to help track existing mutations\"\n Unique Values: \"1\"\n Name: \"ref_motif\"\n Description: \"Reference motif\"\n Unique Values: \"20\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"minor_allelic_frequency\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"gene_name\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\"\n Unique Values: \"17\"\n Name: \"disease_evidence_ECO:0000269\"\n Description: \"The PMID evidence for the association of the disease with the variant.\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.11.2/reviewed/human_protein_ptm_annotation_uniprotkb.csv" }