{ "bcoid": "GLY_000623", "title": "Human Glycogenes", "description": "This Human glycogenes dataset is retrieved a publication from UGA [PMID:18411279]. It contains a list ...", "filename": "human_protein_glycogenes.csv", "filetype": "csv", "categories": { "species": [ "Homo sapiens" ], "molecule": [ "Protein" ], "tag": [ "Glycogenes" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q6UWM9-1...", "79799..." ], [ "Q16880-1...", "7368..." ] ], "headers": [ "uniprotkb_ca...", "gene_id..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_id" }, { "type": "string", "label": "gene_name" }, { "type": "string", "label": "gene_names_alternative" }, { "type": "string", "label": "uniprotkb_protein_recommended_name" }, { "type": "string", "label": "glycoenzyme_gene_id" }, { "type": "string", "label": "gene_group" } ], [ "Q6UWM9-1", "79799", "UGT2A3", "", "UDP-glucuronosyltransferase 2A3", "HGT01_M01", "Glycosyltransferase" ], [ "Q16880-1", "7368", "UGT8", "CGT;UGT4", "2-hydroxyacylsphingosine 1-beta-galactosyltransferase", "HGT01_M03", "Glycosyltransferase" ], [ "P19224-1", "54578", "UGT1A6", "UGT1;GNT1", "UDP-glucuronosyltransferase 1-6", "HGT01_M05", "Glycosyltransferase" ], [ "O60656-1", "54600", "UGT1A9", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A9", "HGT01_M06", "Glycosyltransferase" ], [ "P22309-1", "54658", "UGT1A1", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A1", "HGT01_M07", "Glycosyltransferase" ], [ "P0DTE4-5", "10941", "UGT2A1", "", "UDP-glucuronosyltransferase 2A1", "HGT01_M08", "Glycosyltransferase" ], [ "Q3SY77-1", "167127", "UGT3A2", "", "UDP-glucuronosyltransferase 3A2", "HGT01_M13", "Glycosyltransferase" ], [ "Q6NUS8-1", "133688", "UGT3A1", "", "UDP-glucuronosyltransferase 3A1", "HGT01_M14", "Glycosyltransferase" ], [ "Q96F25-1", "199857", "ALG14", "", "UDP-N-acetylglucosamine transferase subunit ALG14 homolog", "HGT01_M15", "Glycosyltransferase" ], [ "Q9NP73-1", "79868", "ALG13", "CXorf45;GLT28D1", "Putative bifunctional UDP-N-acetylglucosamine transferase and deubiquitinase ALG13", "HGT01_M22", "Glycosyltransferase" ], [ "P0DTE5-1", "574537", "UGT2A2", "", "UDP-glucuronosyltransferase 2A2", "HGT01_M23", "Glycosyltransferase" ], [ "P35503-1", "54659", "UGT1A3", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A3", "HGT01_M25", "Glycosyltransferase" ], [ "P22310-1", "54657", "UGT1A4", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A4", "HGT01_M26", "Glycosyltransferase" ], [ "P35504-1", "54579", "UGT1A5", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A5", "HGT01_M27", "Glycosyltransferase" ], [ "Q9HAW7-1", "54577", "UGT1A7", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A7", "HGT01_M28", "Glycosyltransferase" ], [ "Q9HAW9-1", "54576", "UGT1A8", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A8", "HGT01_M29", "Glycosyltransferase" ], [ "Q9HAW8-1", "54575", "UGT1A10", "UGT1;GNT1", "UDP-glucuronosyltransferase 1A10", "HGT01_M30", "Glycosyltransferase" ], [ "P06133-1", "7363", "UGT2B4", "UGT2B11", "UDP-glucuronosyltransferase 2B4", "HGT01_M31", "Glycosyltransferase" ], [ "P16662-1", "7364", "UGT2B7", "UGTB2B9", "UDP-glucuronosyltransferase 2B7", "HGT01_M32", "Glycosyltransferase" ], [ "P36537-1", "7365", "UGT2B10", "", "UDP-glucuronosyltransferase 2B10", "HGT01_M33", "Glycosyltransferase" ], [ "O75310-1", "10720", "UGT2B11", "", "UDP-glucuronosyltransferase 2B11", "HGT01_M34", "Glycosyltransferase" ], [ "P54855-1", "", "UGT2B15", "UGT2B8", "UDP-glucuronosyltransferase 2B15", "HGT01_M35", "Glycosyltransferase" ], [ "O75795-1", "7367", "UGT2B17", "", "UDP-glucuronosyltransferase 2B17", "HGT01_M36", "Glycosyltransferase" ], [ "Q9BY64-1", "54490", "UGT2B28", "", "UDP-glucuronosyltransferase 2B28", "HGT01_M37", "Glycosyltransferase" ], [ "Q9Y673-1", "29880", "ALG5", "", "Dolichyl-phosphate beta-glucosyltransferase", "HGT02_M01", "Glycosyltransferase" ], [ "Q67FW5-1", "146712", "B3GNTL1", "B3GNT8", "UDP-GlcNAc:betaGal beta-1,3-N-acetylglucosaminyltransferase-like protein 1", "HGT02_M02", "Glycosyltransferase" ], [ "O60762-1", "8813", "DPM1", "", "Dolichol-phosphate mannosyltransferase subunit 1", "HGT02_M03", "Glycosyltransferase" ], [ "Q92839-1", "3036", "HAS1", "HAS", "Hyaluronan synthase 1", "HGT02_M04", "Glycosyltransferase" ], [ "Q92819-1", "3037", "HAS2", "", "Hyaluronan synthase 2", "HGT02_M05", "Glycosyltransferase" ], [ "O00219-1", "3038", "HAS3", "", "Hyaluronan synthase 3", "HGT02_M06", "Glycosyltransferase" ], [ "P13807-1", "2997", "GYS1", "GYS", "Glycogen [starch] synthase, muscle", "HGT03_M01", "Glycosyltransferase" ], [ "P54840-1", "2998", "GYS2", "", "Glycogen [starch] synthase, liver", "HGT03_M02", "Glycosyltransferase" ], [ "Q9H553-1", "85365", "ALG2", "", "Alpha-1,3/1,6-mannosyltransferase ALG2", "HGT04_M01", "Glycosyltransferase" ], [ "Q2TAA5-1", "440138", "ALG11", "GT8", "GDP-Man:Man(3)GlcNAc(2)-PP-Dol alpha-1,2-mannosyltransferase", "HGT04_M02", "Glycosyltransferase" ], [ "P37287-1", "5277", "PIGA", "", "Phosphatidylinositol N-acetylglucosaminyltransferase subunit A", "HGT04_M03", "Glycosyltransferase" ], [ "Q4AE62-1", "79712", "GTDC1", "", "Glycosyltransferase-like domain-containing protein 1", "HGT04_M04", "Glycosyltransferase" ], [ "Q96MS3-1", "144423", "GLT1D1", "", "Glycosyltransferase 1 domain-containing protein 1", "HGT04_M05", "Glycosyltransferase" ], [ "Q5TAP6-1", "9724", "UTP14C", "KIAA0266", "U3 small nucleolar RNA-associated protein 14 homolog C", "HGT04_M06", "Glycosyltransferase" ], [ "P16442-1", "28", "ABO", "", "Histo-blood group ABO system transferase", "HGT06_M02", "Glycosyltransferase" ], [ "Q8N5D6-1", "26301", "GBGT1", "", "Globoside alpha-1,3-N-acetylgalactosaminyltransferase 1", "HGT06_M03", "Glycosyltransferase" ], [ "U3KPV4-1", "127550", "A3GALT2", "A3GALT2P;IGBS3S", "Alpha-1,3-galactosyltransferase 2", "HGT06_M05", "Glycosyltransferase" ], [ "Q7Z4J2-1", "360203", "GLT6D1", "GLTDC1;GT6M7", "Putative glycosyltransferase 6 domain-containing protein 1", "HGT06_M06", "Glycosyltransferase" ], [ "Q8TDX6-1", "55790", "CSGALNACT1", "CHGN;GALNACT1", "Chondroitin sulfate N-acetylgalactosaminyltransferase 1", "HGT07_M01", "Glycosyltransferase" ], [ "P15291-1", "2683", "B4GALT1", "GGTB2", "Beta-1,4-galactosyltransferase 1", "HGT07_M02", "Glycosyltransferase" ], [ "O60909-1", "8704", "B4GALT2", "", "Beta-1,4-galactosyltransferase 2", "HGT07_M03", "Glycosyltransferase" ], [ "O60512-1", "8703", "B4GALT3", "", "Beta-1,4-galactosyltransferase 3", "HGT07_M04", "Glycosyltransferase" ], [ "O60513-1", "8702", "B4GALT4", "", "Beta-1,4-galactosyltransferase 4", "HGT07_M05", "Glycosyltransferase" ], [ "O43286-1", "9334", "B4GALT5", "", "Beta-1,4-galactosyltransferase 5", "HGT07_M06", "Glycosyltransferase" ], [ "Q9UBX8-1", "9331", "B4GALT6", "", "Beta-1,4-galactosyltransferase 6", "HGT07_M07", "Glycosyltransferase" ], [ "Q9UBV7-1", "11285", "B4GALT7", "XGALT1", "Beta-1,4-galactosyltransferase 7", "HGT07_M08", "Glycosyltransferase" ], [ "Q76KP1-1", "338707", "B4GALNT4", "", "N-acetyl-beta-glucosaminyl-glycoprotein 4-beta-N-acetylgalactosaminyltransferase 1", "HGT07_M09", "Glycosyltransferase" ], [ "Q6L9W6-1", "283358", "B4GALNT3", "", "Beta-1,4-N-acetylgalactosaminyltransferase 3", "HGT07_M10", "Glycosyltransferase" ], [ "Q86X52-1", "22856", "CHSY1", "CHSY;CSS1;KIAA0990", "Chondroitin sulfate synthase 1", "HGT07_M11", "Glycosyltransferase" ], [ "Q8IZ52-1", "79586", "CHPF", "CSS2", "Chondroitin sulfate synthase 2", "HGT07_M12", "Glycosyltransferase" ], [ "Q8N6G5-1", "55454", "CSGALNACT2", "CHGN2;GALNACT2", "Chondroitin sulfate N-acetylgalactosaminyltransferase 2", "HGT07_M13", "Glycosyltransferase" ], [ "Q9P2E5-1", "54480", "CHPF2", "CSGlcA-T;CHSY3;CSGLCAT;KIAA1402", "Chondroitin sulfate glucuronyltransferase", "HGT07_M14", "Glycosyltransferase" ], [ "Q70JA7-1", "337876", "CHSY3", "CHSY2;CSS3", "Chondroitin sulfate synthase 3", "HGT07_M15", "Glycosyltransferase" ], [ "Q68CQ7-1", "55830", "GLT8D1", "GALA4A", "Glycosyltransferase 8 domain-containing protein 1", "HGT08_M01", "Glycosyltransferase" ], [ "P46976-1", "2992", "GYG1", "GYG", "Glycogenin-1", "HGT08_M02", "Glycosyltransferase" ], [ "Q8NBI6-1", "152002", "XXYLT1", "C3orf21", "Xyloside xylosyltransferase 1", "HGT08_M03", "Glycosyltransferase" ], [ "O95461-1", "9215", "LARGE1", "LARGE;KIAA0609", "Xylosyl- and glucuronyltransferase LARGE1", "HGT08_M04", "Glycosyltransferase" ], [ "Q9H1C3-1", "83468", "GLT8D2", "GALA4A", "Glycosyltransferase 8 domain-containing protein 2", "HGT08_M05", "Glycosyltransferase" ], [ "Q8N3Y3-1", "120071", "LARGE2", "GYLTL1B", "Xylosyl- and glucuronyltransferase LARGE2", "HGT08_M06", "Glycosyltransferase" ], [ "A0PJZ3-1", "727936", "GXYLT2", "GLT8D4", "Glucoside xylosyltransferase 2", "HGT08_M07", "Glycosyltransferase" ], [ "Q4G148-1", "283464", "GXYLT1", "GLT8D3", "Glucoside xylosyltransferase 1", "HGT08_M08", "Glycosyltransferase" ], [ "O15488-1", "8908", "GYG2", "", "Glycogenin-2", "HGT08_M09", "Glycosyltransferase" ], [ "Q495W5-1", "170384", "FUT11", "", "Alpha-(1,3)-fucosyltransferase 11", "HGT10_M01", "Glycosyltransferase" ], [ "P22083-1", "2526", "FUT4", "FCT3A;ELFT", "Alpha-(1,3)-fucosyltransferase 4", "HGT10_M02", "Glycosyltransferase" ], [ "Q11130-1", "2529", "FUT7", "", "Alpha-(1,3)-fucosyltransferase 7", "HGT10_M03", "Glycosyltransferase" ], [ "Q9Y231-1", "10690", "FUT9", "", "4-galactosyl-N-acetylglucosaminide 3-alpha-L-fucosyltransferase 9", "HGT10_M04", "Glycosyltransferase" ], [ "Q6P4F1-1", "84750", "FUT10", "", "Alpha-(1,3)-fucosyltransferase 10", "HGT10_M05", "Glycosyltransferase" ], [ "P51993-1", "2528", "FUT6", "FCT3A", "4-galactosyl-N-acetylglucosaminide 3-alpha-L-fucosyltransferase FUT6", "HGT10_M06", "Glycosyltransferase" ], [ "Q11128-1", "2527", "FUT5", "", "4-galactosyl-N-acetylglucosaminide 3-alpha-L-fucosyltransferase FUT5", "HGT10_M07", "Glycosyltransferase" ], [ "P21217-1", "2525", "FUT3", "LE;FT3B", "3-galactosyl-N-acetylglucosaminide 4-alpha-L-fucosyltransferase FUT3", "HGT10_M08", "Glycosyltransferase" ], [ "P19526-1", "2523", "FUT1", "H;HSC", "Galactoside alpha-(1,2)-fucosyltransferase 1", "HGT11_M01", "Glycosyltransferase" ], [ "Q10981-1", "2524", "FUT2", "SEC2", "Galactoside alpha-(1,2)-fucosyltransferase 2", "HGT11_M02", "Glycosyltransferase" ], [ "Q8NHY0-1", "124872", "B4GALNT2", "GALGT2", "Beta-1,4 N-acetylgalactosaminyltransferase 2", "HGT12_M01", "Glycosyltransferase" ], [ "Q00973-1", "2583", "B4GALNT1", "GALGT;SIAT2", "Beta-1,4 N-acetylgalactosaminyltransferase 1", "HGT12_M02", "Glycosyltransferase" ], [ "P26572-1", "4245", "MGAT1", "GGNT1;GLCT1;GLYT1;MGAT", "Alpha-1,3-mannosyl-glycoprotein 2-beta-N-acetylglucosaminyltransferase", "HGT13_M01", "Glycosyltransferase" ], [ "Q8WZA1-1", "55624", "POMGNT1", "MGAT1.2;DKFZp761B182", "Protein O-linked-mannose beta-1,2-N-acetylglucosaminyltransferase 1", "HGT13_M02", "Glycosyltransferase" ], [ "Q8N0V5-1", "2651", "GCNT2", "II;GCNT5;NACGT1", "N-acetyllactosaminide beta-1,6-N-acetylglucosaminyl-transferase", "HGT14_M01", "Glycosyltransferase" ], [ "Q02742-1", "2650", "GCNT1", "NACGT2", "Beta-1,3-galactosyl-O-glycosyl-glycoprotein beta-1,6-N-acetylglucosaminyltransferase", "HGT14_M02", "Glycosyltransferase" ], [ "O95395-1", "9245", "GCNT3", "", "Beta-1,3-galactosyl-O-glycosyl-glycoprotein beta-1,6-N-acetylglucosaminyltransferase 3", "HGT14_M03", "Glycosyltransferase" ], [ "Q9H1B5-1", "64132", "XYLT2", "XT2", "Xylosyltransferase 2", "HGT14_M04", "Glycosyltransferase" ] ] }, "readme": "Name\n - Human Glycogenes\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2022-03-29T10:11:35.122210\n\nModified on\n - 2022-09-26T09:08:12.447031\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 - \n\nChecksum\n - \n\nUsability Domain\n - This Human glycogenes dataset is retrieved a publication from UGA [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened human [taxonomy:9606] protein names mapped to NCBI gene and HGNC IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer\u2019s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy.\n\nDescription Domain\n Keywords\n - glycogenes\n\n Pipeline Steps\n - Step-1: The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file.\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: human_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_xref_geneid.csv\n Name: human_glycogenes.csv\n URI: https:/data.glygen.org/ln2downloads/glycogenes/2022_02_16/human_glycogenes.csv\n Output Subdomain\n Name: human_protein_glycogenes.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_glycogenes.csv\n Name: human_protein_glycogenes.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_glycogenes.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"883\"\n Name: \"gene_id\"\n Description: \"NCBI Gene identifier\"\n Unique Values: \"865\"\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: \"883\"\n Name: \"gene_names_alternative\"\n Description: \"\"\n Unique Values: \"565\"\n Name: \"uniprotkb_protein_recommended_name\"\n Description: \"The recommended full name of the protein in UniProtKB\"\n Unique Values: \"883\"\n Name: \"glycoenzyme_gene_id\"\n Description: \"\"\n Unique Values: \"912\"\n Name: \"gene_group\"\n Description: \"\"\n Unique Values: \"74\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/human_protein_glycogenes.csv" }