{ "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" ], "tag": [ "enzyme annotation" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q03519-1...", "7.4.2.14..." ], [ "Q03519-1...", "7.4.2.14..." ] ], "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" } ], [ "Q03519-1", "7.4.2.14", "a peptide antigen(in) + ATP + H2O = a peptide antigen(out) + ADP + H(+) + phosphate." ], [ "Q03519-1", "7.4.2.14", "" ], [ "Q8IVT5-1", "2.7.11.1", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q8IVT5-1", "2.7.11.1", "" ], [ "P52758-1", "3.5.99.10", "2-iminobutanoate + H2O = 2-oxobutanoate + NH4(+)." ], [ "P52758-1", "3.5.99.10", "" ], [ "P06746-1", "2.7.7.7", "a 2'-deoxyribonucleoside 5'-triphosphate + DNA(n) = diphosphate + DNA(n+1)." ], [ "P06746-1", "2.7.7.7", "" ], [ "Q8TBF2-1", "1.11.1.20", "[thioredoxin]-disulfide + prostamide F2alpha = [thioredoxin]-dithiol + prostamide H2." ], [ "Q8TBF2-1", "1.11.1.20", "" ], [ "Q9NVL1-1", "2.1.1.-", "" ], [ "P24666-1", "3.1.3.2", "a phosphate monoester + H2O = an alcohol + phosphate." ], [ "P24666-1", "3.1.3.2", "" ], [ "Q9H5K3-1", "2.7.1.183", "3-O-[beta-D-GalNAc-(1->3)-beta-D-GlcNAc-(1->4)-alpha-D-Man]-L-Thr-[protein] + ATP = 3-O-[beta-D-GalNAc-(1->3)-beta-D-GlcNAc-(1->4)-(O-6-P-alpha-D-Man)]-Thr-[protein] + ADP + H(+)." ], [ "Q9H5K3-1", "2.7.1.183", "" ], [ "A0A1W2PQ27-1", "3.1.3.16", "H2O + O-phospho-L-threonyl-[protein] = L-threonyl-[protein] + phosphate." ], [ "Q9P212-1", "3.1.4.11", "a 1,2-diacyl-sn-glycero-3-phospho-(1D-myo-inositol-4,5-bisphosphate) + H2O = 1D-myo-inositol 1,4,5-trisphosphate + a 1,2-diacyl-sn-glycerol + H(+)." ], [ "Q9P212-1", "3.1.4.11", "" ], [ "P30613-1", "2.7.1.40", "CTP + pyruvate = CDP + H(+) + phosphoenolpyruvate." ], [ "P30613-1", "2.7.1.40", "" ], [ "Q15349-1", "2.7.11.1", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q15349-1", "2.7.11.1", "" ], [ "Q99447-1", "2.7.7.14", "CTP + H(+) + phosphoethanolamine = CDP-ethanolamine + diphosphate." ], [ "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 + H(+)." ], [ "Q6ZNW5-1", "2.7.7.78", "" ], [ "P38606-1", "7.1.2.2", "ATP + 4 H(+)(in) + H2O = ADP + 5 H(+)(out) + phosphate." ], [ "P38606-1", "7.1.2.2", "" ], [ "Q00535-1", "2.7.11.1", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q00535-1", "2.7.11.1", "" ], [ "Q00534-1", "2.7.11.22", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q00534-1", "2.7.11.22", "" ], [ "Q00537-1", "2.7.11.22", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q00537-1", "2.7.11.22", "" ], [ "Q00536-1", "2.7.11.22", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q00536-1", "2.7.11.22", "" ], [ "Q00532-1", "2.7.11.22", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q00532-1", "2.7.11.22", "" ], [ "Q96J66-1", "7.6.2.2", "ATP + daunorubicin(in) + H2O = ADP + daunorubicin(out) + H(+) + phosphate." ], [ "Q96J66-1", "7.6.2.3", "an S-substituted glutathione(in) + ATP + H2O = ADP + an S-substituted glutathione(out) + H(+) + phosphate." ], [ "Q96J66-1", "7.6.2.3", "" ], [ "Q96J66-1", "7.6.2.2", "" ], [ "Q9UBM8-1", "2.4.1.145", "N(4)-{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}-L-asparaginyl-[protein] + UDP-N-acetyl-alpha-D-glucosamine = H(+) + N(4)-{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}-L-asparaginyl-[protein] + UDP." ], [ "Q9UBM8-1", "2.4.1.145", "" ], [ "P10620-1", "2.5.1.18", "glutathione + RX = a halide anion + an S-substituted glutathione + H(+)." ], [ "P10620-1", "2.5.1.18", "" ], [ "Q9UBM1-1", "2.1.1.17", "a 1,2-diacyl-sn-glycero-3-phosphoethanolamine + S-adenosyl-L-methionine = 1,2-diacyl-sn-glycero-3-phospho-N-methylethanolamine + H(+) + S-adenosyl-L-homocysteine." ], [ "Q9UBM1-1", "2.1.1.71", "1,2-diacyl-sn-glycero-3-phospho-N-methylethanolamine + S-adenosyl-L-methionine = 1,2-diacyl-sn-glycero-3-phospho-N,N-dimethylethanolamine + H(+) + S-adenosyl-L-homocysteine." ], [ "Q9UBM1-1", "2.1.1.17", "" ], [ "Q9UBM1-1", "2.1.1.71", "" ], [ "Q9UBM7-1", "1.3.1.21", "cholesterol + NADP(+) = 7-dehydrocholesterol + H(+) + NADPH." ], [ "Q9UBM7-1", "1.3.1.21", "" ], [ "P20648-1", "7.2.2.19", "ATP + H(+)(in) + H2O + K(+)(out) = ADP + 2 H(+)(out) + K(+)(in) + phosphate." ], [ "P20648-1", "7.2.2.19", "" ], [ "Q13838-1", "3.6.4.13", "ATP + H2O = ADP + H(+) + phosphate." ], [ "Q13838-1", "3.6.4.13", "" ], [ "P20933-1", "3.5.1.26", "H2O + N(4)-(beta-N-acetyl-D-glucosaminyl)-L-asparagine = H(+) + L-aspartate + N-acetyl-beta-D-glucosaminylamine." ], [ "P20933-1", "3.5.1.26", "" ], [ "P08842-1", "3.1.6.2", "dehydroepiandrosterone 3-sulfate + H2O = 3beta-hydroxyandrost-5-en-17-one + H(+) + sulfate." ], [ "P08842-1", "3.1.6.2", "" ], [ "P03891-1", "7.1.1.2", "a ubiquinone + 5 H(+)(in) + NADH = a ubiquinol + 4 H(+)(out) + NAD(+)." ], [ "P03891-1", "7.1.1.2", "" ], [ "P03897-1", "7.1.1.2", "a ubiquinone + 5 H(+)(in) + NADH = a ubiquinol + 4 H(+)(out) + NAD(+)." ], [ "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", "[protein]-peptidylproline (omega=180) = [protein]-peptidylproline (omega=0)." ], [ "Q9Y237-1", "5.2.1.8", "" ], [ "P02760-1", "1.6.2.-", "" ], [ "P40145-1", "4.6.1.1", "ATP = 3',5'-cyclic AMP + diphosphate." ], [ "P40145-1", "4.6.1.1", "" ], [ "Q9H4B0-1", "2.3.1.234", "adenosine(37) in tRNA + L-threonylcarbamoyladenylate = AMP + H(+) + N(6)-L-threonylcarbamoyladenosine(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", "H2O + L-asparagine = L-aspartate + NH4(+)." ], [ "Q7L266-1", "3.5.1.1", "" ], [ "Q7L266-1", "3.4.19.5", "" ], [ "Q9UQ07-1", "2.7.11.22", "ATP + L-seryl-[protein] = ADP + H(+) + O-phospho-L-seryl-[protein]." ], [ "Q9UQ07-1", "2.7.11.22", "" ], [ "Q9UJ70-1", "2.7.1.60", "an N-acyl-D-mannosamine + ATP = ADP + an N-acyl-D-mannosamine 6-phosphate + H(+)." ], [ "Q9UJ70-1", "2.7.1.59", "ATP + N-acetyl-D-glucosamine = ADP + H(+) + N-acetyl-D-glucosamine 6-phosphate." ], [ "Q9UJ70-1", "2.7.1.-", "" ] ] }, "readme": "Name\n - Human Protein Enzyme Annotation (UniProtKB)\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2019-12-01T15:54:04.720467\n\nModified on\n - 2022-09-26T09:05:27.769723\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@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/glygener/glygen-backend-integration/blob/master/dataset-maker/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/ln2downloads/ebi/2023_10_30/uniprot-proteome-homo-sapiens.nt\n Output Subdomain\n Name: human_protein_enzyme_annotation_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_enzyme_annotation_uniprotkb.csv\n Name: human_protein_enzyme_annotation_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_protein_enzyme_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"4484\"\n Name: \"enzyme_ec\"\n Description: \"Enzyme Commision number assigned to an enzyme by Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (IUBMB)\"\n Unique Values: \"1616\"\n Name: \"enzyme_activity\"\n Description: \"The catalytic reaction activity of an enzyme in UniProtKB\"\n Unique Values: \"1453\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/human_protein_enzyme_annotation_uniprotkb.csv" }