{ "bcoid": "GLY_000323", "title": "Human Protein Enzyme Annotation (UniProtKB)", "description": "The Human Protein Enzyme Annotation (UniProtKB) dataset contains human [taxid:9606] enzyme annotations ...", "filename": "human_protein_enzyme_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "enzyme annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P24666-1...", "3.1.3.2..." ], [ "P24666-1...", "3.1.3.2..." ] ], "headers": [ "uniprotkb_ca...", "enzyme_ec..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "enzyme_ec" }, { "type": "string", "label": "enzyme_activity" } ], [ "P24666-1", "3.1.3.2", "A phosphate monoester + H(2)O = an alcohol + phosphate." ], [ "P24666-1", "3.1.3.2", "" ], [ "P52758-1", "3.5.99.10", "2-iminopropanoate + H(2)O = pyruvate + NH(3)." ], [ "P52758-1", "3.5.99.10", "" ], [ "P20807-1", "3.4.22.54", "Broad endopeptidase activity." ], [ "P20807-1", "3.4.22.54", "" ], [ "P06746-1", "2.7.7.7", "Deoxynucleoside triphosphate + DNA(n) = diphosphate + DNA(n+1)." ], [ "P06746-1", "2.7.7.7", "" ], [ "Q8TBF2-1", "1.11.1.20", "Thioredoxin + prostaglandin H(2) = thioredoxin disulfide + prostaglandin F(2-alpha)." ], [ "Q8TBF2-1", "1.11.1.20", "" ], [ "Q9NVL1-1", "2.1.1.-", "" ], [ "P20933-1", "3.5.1.26", "N(4)-(beta-N-acetyl-D-glucosaminyl)-L-asparagine + H(2)O = N-acetyl-beta-D-glucosaminylamine + L-aspartate." ], [ "P20933-1", "3.5.1.26", "" ], [ "Q9H5K3-1", "2.7.1.183", "ATP + O(3)-(N-acetyl-beta-D-galactosaminyl-(1->3)-N-acetyl-beta-D-glucosaminyl-(1->4)-alpha-D-mannosyl)-L-threonyl/L-seryl-[protein] = ADP + O(3)-(N-acetyl-beta-D-galactosaminyl-(1->3)-N-acetyl-beta-D-glucosaminyl-(1->4)-alpha-D-(6-phospho)mannosyl)-L-threonyl/L-seryl-[protein]." ], [ "Q9H5K3-1", "2.7.1.183", "" ], [ "O00429-1", "3.6.5.5", "GTP + H(2)O = GDP + phosphate." ], [ "O00429-1", "3.6.5.5", "" ], [ "Q9P212-1", "3.1.4.11", "1-phosphatidyl-1D-myo-inositol 4,5-bisphosphate + H(2)O = 1D-myo-inositol 1,4,5-trisphosphate + diacylglycerol." ], [ "Q9P212-1", "3.1.4.11", "" ], [ "P30613-1", "2.7.1.40", "ATP + pyruvate = ADP + phosphoenolpyruvate." ], [ "P30613-1", "2.7.1.40", "" ], [ "Q15349-1", "2.7.11.1", "ATP + a protein = ADP + a phosphoprotein." ], [ "Q15349-1", "2.7.11.1", "" ], [ "Q99447-1", "2.7.7.14", "CTP + ethanolamine phosphate = diphosphate + CDP-ethanolamine." ], [ "Q99447-1", "2.7.7.14", "" ], [ "P23919-1", "2.7.4.9", "ATP + dTMP = ADP + dTDP." ], [ "P23919-1", "2.7.4.9", "" ], [ "Q6ZNW5-1", "2.7.7.78", "GDP-alpha-D-glucose + phosphate = alpha-D-glucose 1-phosphate + GDP." ], [ "Q6ZNW5-1", "2.7.7.78", "" ], [ "Q8N2K0-1", "3.1.1.23", "Hydrolyzes glycerol monoesters of long-chain fatty acids." ], [ "Q8N2K0-1", "3.1.1.23", "" ], [ "Q00535-1", "2.7.11.1", "ATP + a protein = ADP + a phosphoprotein." ], [ "Q00535-1", "2.7.11.1", "" ], [ "Q00534-1", "2.7.11.22", "ATP + a protein = ADP + a phosphoprotein." ], [ "Q00534-1", "2.7.11.22", "" ], [ "Q00537-1", "2.7.11.22", "ATP + a protein = ADP + a phosphoprotein." ], [ "Q00537-1", "2.7.11.22", "" ], [ "Q00536-1", "2.7.11.22", "ATP + a protein = ADP + a phosphoprotein." ], [ "Q00536-1", "2.7.11.22", "" ], [ "Q86TM6-1", "2.3.2.27", "S-ubiquitinyl-[E2 ubiquitin-conjugating enzyme]-L-cysteine + [acceptor protein]-L-lysine = [E2 ubiquitin-conjugating enzyme]-L-cysteine + N(6)-ubiquitinyl-[acceptor protein]-L-lysine." ], [ "Q86TM6-1", "2.3.2.27", "" ], [ "Q00532-1", "2.7.11.22", "ATP + a protein = ADP + a phosphoprotein." ], [ "Q00532-1", "2.7.11.22", "" ], [ "Q96J66-1", "7.6.2.2", "ATP + H(2)O + xenobiotic(Side 1) = ADP + phosphate + xenobiotic(Side 2)." ], [ "Q96J66-1", "7.6.2.3", "ATP + H(2)O + glutathione-S-conjugate(Side 1) = ADP + phosphate + glutathione-S-conjugate(Side 2)." ], [ "Q96J66-1", "7.6.2.3", "" ], [ "Q96J66-1", "7.6.2.2", "" ], [ "Q9UBM8-1", "2.4.1.145", "UDP-N-acetyl-alpha-D-glucosamine + beta-D-GlcNAc-(1->2)-alpha-D-Man-(1->3)-(beta-D-GlcNAc-(1->2)-alpha-D-Man-(1->6))-beta-D-Man-(1->4)-beta-D-GlcNAc-(1->4)-beta-D-GlcNAc-N-Asn-[protein] = UDP + beta-D-GlcNAc-(1->2)-(beta-D-GlcNAc-(1->4))-alpha-D-Man-(1->3)-(beta-D-GlcNAc-(1->2)-alpha-D-Man-(1->6))-beta-D-Man-(1->4)-beta-D-GlcNAc-(1->4)-beta-D-GlcNAc-N-Asn-[protein]." ], [ "Q9UBM8-1", "2.4.1.145", "" ], [ "P10620-1", "2.5.1.18", "RX + glutathione = HX + R-S-glutathione." ], [ "P10620-1", "2.5.1.18", "" ], [ "Q9UBM1-1", "2.1.1.17", "S-adenosyl-L-methionine + phosphatidylethanolamine = S-adenosyl-L-homocysteine + phosphatidyl-N-methylethanolamine." ], [ "Q9UBM1-1", "2.1.1.71", "S-adenosyl-L-methionine + phosphatidyl-N-methylethanolamine = S-adenosyl-L-homocysteine + phosphatidyl-N-dimethylethanolamine." ], [ "Q9UBM1-1", "2.1.1.71", "" ], [ "Q9UBM1-1", "2.1.1.17", "" ], [ "Q9UBM7-1", "1.3.1.21", "Cholesterol + NADP(+) = cholesta-5,7-dien-3-beta-ol + NADPH." ], [ "Q9UBM7-1", "1.3.1.21", "" ], [ "P20648-1", "7.2.2.19", "ATP + H(2)O + H(+)(Side 1) + K(+)(Side 2) = ADP + phosphate + H(+)(Side 2) + K(+)(Side 1)." ], [ "P20648-1", "7.2.2.19", "" ], [ "Q13838-1", "3.6.4.13", "ATP + H(2)O = ADP + phosphate." ], [ "Q13838-1", "3.6.4.13", "" ], [ "P08842-1", "3.1.6.2", "3-beta-hydroxyandrost-5-en-17-one 3-sulfate + H(2)O = 3-beta-hydroxyandrost-5-en-17-one + sulfate." ], [ "P08842-1", "3.1.6.2", "" ], [ "P03891-1", "7.1.1.2", "NADH + ubiquinone + 5 H(+)(Side 1) = NAD(+) + ubiquinol + 4 H(+)(Side 2)." ], [ "P03891-1", "7.1.1.2", "" ], [ "P03897-1", "7.1.1.2", "NADH + ubiquinone + 5 H(+)(Side 1) = NAD(+) + ubiquinol + 4 H(+)(Side 2)." ], [ "P03897-1", "7.1.1.2", "" ], [ "Q92995-1", "3.4.19.12", "Thiol-dependent hydrolysis of ester, thioester, amide, peptide and isopeptide bonds formed by the C-terminal Gly of ubiquitin (a 76-residue protein attached to proteins as an intracellular targeting signal)." ], [ "Q92995-1", "3.4.19.12", "" ], [ "Q9Y237-1", "5.2.1.8", "Peptidylproline (omega=180) = peptidylproline (omega=0)." ], [ "Q9Y237-1", "5.2.1.8", "" ], [ "P40145-1", "4.6.1.1", "ATP = 3',5'-cyclic AMP + diphosphate." ], [ "P40145-1", "4.6.1.1", "" ], [ "Q9H4B0-1", "2.3.1.234", "L-threonylcarbamoyladenylate + adenine(37) in tRNA = AMP + N(6)-L-threonylcarbamoyladenine(37) in tRNA." ], [ "Q9H4B0-1", "2.3.1.234", "" ], [ "Q7L266-1", "3.4.19.5", "Cleavage of a beta-linked Asp residue from the N-terminus of a polypeptide." ], [ "Q7L266-1", "3.5.1.1", "L-asparagine + H(2)O = L-aspartate + NH(3)." ], [ "Q7L266-1", "3.4.19.5", "" ], [ "Q7L266-1", "3.5.1.1", "" ], [ "A0A1W2PQ27-1", "3.1.3.16", "[a protein]-serine/threonine phosphate + H(2)O = [a protein]-serine/threonine + phosphate." ], [ "A0A1W2PQ27-1", "3.1.3.16", "" ], [ "Q9UJ70-1", "2.7.1.59", "ATP + N-acetyl-D-glucosamine = ADP + N-acetyl-D-glucosamine 6-phosphate." ], [ "Q9UJ70-1", "2.7.1.59", "" ], [ "Q99707-1", "2.1.1.13", "5-methyltetrahydrofolate + L-homocysteine = tetrahydrofolate + L-methionine." ] ] }, "readme": "Name\n - Human Protein Enzyme Annotation (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-12-01T15:54:04.720467\n\nModified on\n - 2020-04-10T11:47:40.652475\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 Human Protein Enzyme Annotation (UniProtKB) dataset contains human [taxid:9606] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. 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 - enzyme annotation\n - enzyme \n - UniProtKB\n - enzyme activity\n - EC number\n\n Pipeline Steps\n - Step-1: The script extracts the enzyme 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-homo-sapiens.nt\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_ntdata.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_enzyme_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_enzyme_annotation_uniprotkb.csv\n Name: human_protein_enzyme_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_enzyme_annotation_uniprotkb.stat.csv", "downloadurl": "/ln2data/releases/data/v-1.12.1/reviewed/human_protein_enzyme_annotation_uniprotkb.csv" }