{ "bcoid": "GLY_000284", "title": "Glycan Enzyme", "description": "The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures ...", "filename": "glycan_enzyme.csv", "filetype": "csv", "categories": { "molecule": "Glycan", "tags": "Biosynthetic Enzyme", "status": "Reviewed", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "G00176HZ...", "N-glycan_cor..." ], [ "G00176HZ...", "N-glycan_cor..." ] ], "headers": [ "glytoucan_ac...", "residue_name..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "glytoucan_ac" }, { "type": "string", "label": "residue_name" }, { "type": "string", "label": "residue_id" }, { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_name" }, { "type": "string", "label": "gene_id" }, { "type": "string", "label": "parent_residue_id" }, { "type": "string", "label": "recommended_name_full" } ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q921Q3-1", "Alg1", "208211", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9D8C3-1", "Alg13", "67574", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9D081-1", "Alg14", "66789", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9DBE8-1", "Alg2", "56737", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "P42867-1", "Dpagt1", "13478", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9WTS2-1", "Fut8", "53618", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q8BML3-1", "Glt28d2", "320302", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "P27808-1", "Mgat1", "17308", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q921V5-1", "Mgat2", "217664", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q812G0-1", "Mgat4a", "269181", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q812F8-1", "Mgat4b", "103534", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9D306-1", "Mgat4c", "67569", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q8R4G6-1", "Mgat5", "107895", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q765H6-1", "Mgat5b", "268510", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9BT22-1", "ALG1", "56052", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9NP73-1", "ALG13", "79868", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q96F25-1", "ALG14", "199857", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9H553-1", "ALG2", "85365", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9H3H5-1", "DPAGT1", "1798", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9BYC5-1", "FUT8", "2530", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "P26572-1", "MGAT1", "4245", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q10469-1", "MGAT2", "4247", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9UM21-1", "MGAT4A", "11320", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9UQ53-1", "MGAT4B", "11282", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q9UBM8-1", "MGAT4C", "25834", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q09328-1", "MGAT5", "4249", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_A", "NA", "Q3V5L5-1", "MGAT5B", "146664", "no_id", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q921Q3-1", "Alg1", "208211", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9D8C3-1", "Alg13", "67574", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9D081-1", "Alg14", "66789", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9DBE8-1", "Alg2", "56737", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "P42867-1", "Dpagt1", "13478", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9WTS2-1", "Fut8", "53618", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q8BML3-1", "Glt28d2", "320302", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "P27808-1", "Mgat1", "17308", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q921V5-1", "Mgat2", "217664", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q812G0-1", "Mgat4a", "269181", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q812F8-1", "Mgat4b", "103534", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9D306-1", "Mgat4c", "67569", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q8R4G6-1", "Mgat5", "107895", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q765H6-1", "Mgat5b", "268510", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9BT22-1", "ALG1", "56052", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9NP73-1", "ALG13", "79868", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q96F25-1", "ALG14", "199857", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9H553-1", "ALG2", "85365", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9H3H5-1", "DPAGT1", "1798", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9BYC5-1", "FUT8", "2530", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "P26572-1", "MGAT1", "4245", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q10469-1", "MGAT2", "4247", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9UM21-1", "MGAT4A", "11320", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9UQ53-1", "MGAT4B", "11282", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q9UBM8-1", "MGAT4C", "25834", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q09328-1", "MGAT5", "4249", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-GlcpNAc_B", "NB", "Q3V5L5-1", "MGAT5B", "146664", "NA", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q921Q3-1", "Alg1", "208211", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9D8C3-1", "Alg13", "67574", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9D081-1", "Alg14", "66789", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9DBE8-1", "Alg2", "56737", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "P42867-1", "Dpagt1", "13478", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9WTS2-1", "Fut8", "53618", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q8BML3-1", "Glt28d2", "320302", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "P27808-1", "Mgat1", "17308", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q921V5-1", "Mgat2", "217664", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q812G0-1", "Mgat4a", "269181", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q812F8-1", "Mgat4b", "103534", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9D306-1", "Mgat4c", "67569", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q8R4G6-1", "Mgat5", "107895", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q765H6-1", "Mgat5b", "268510", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9BT22-1", "ALG1", "56052", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9NP73-1", "ALG13", "79868", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q96F25-1", "ALG14", "199857", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9H553-1", "ALG2", "85365", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9H3H5-1", "DPAGT1", "1798", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9BYC5-1", "FUT8", "2530", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "P26572-1", "MGAT1", "4245", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q10469-1", "MGAT2", "4247", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9UM21-1", "MGAT4A", "11320", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9UQ53-1", "MGAT4B", "11282", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q9UBM8-1", "MGAT4C", "25834", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q09328-1", "MGAT5", "4249", "NB", "" ], [ "G00176HZ", "N-glycan_core_b-D-Manp", "NC", "Q3V5L5-1", "MGAT5B", "146664", "NB", "" ], [ "G00176HZ", "N-glycan_a-D-Manp_1", "N1", "Q921Q3-1", "Alg1", "208211", "NC", "" ], [ "G00176HZ", "N-glycan_a-D-Manp_1", "N1", "Q9D8C3-1", "Alg13", "67574", "NC", "" ], [ "G00176HZ", "N-glycan_a-D-Manp_1", "N1", "Q9D081-1", "Alg14", "66789", "NC", "" ] ] }, "readme": "Name\n - Glycan Enzyme\n\nVersion\n - 1.5.27\n\nCreated on\n - 2019-11-13T13:19:08.883378\n\nModified on\n - 2020-05-01T15:02:15.485634\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n - Will York [will@ccrc.uga.edu], Allison Nairn [avnairn@uga.edu], Nathan Edwards [nje5@georgetown.edu]\n\nChecksum\n - \n\nUsability Domain\n - The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human or mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the GlycO tree model. The glycans listed in the database may or may not have a human (TaxID:9606) or mouse (TaxID:10090) species annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human or mouse biosynthetic enzyme association should not be considered as a human or mouse species annotation for that glycan.\n\nDescription Domain\n Keywords\n - Glycan\n - GlyTouCan Accession\n - Enzyme\n\n Pipeline Steps\n - Step-1: The input files were downloaded from the authors and a python script was used to extract columns- GlyTouCanAccession,Enzyme_UniProtAccession, Enzyme_GeneName,Enzyme_GeneID,Enzyme_TaxonomyID from input file 1 and columns- glycan_ID,residue,residue_ID,parent_ID from input file 2 . The script additionally maps the UniProtKB accession to UniProtKB canonical accessions and extracts rows where UniProtKB canonical accession has taxid=9606 or Taxid=10090\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-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: enz.tsv\n URI: https://data.glygen.org/ln2wwwdata/source/enz.tsv\n Name: mapped_n_glycans.csv\n URI: https://data.glygen.org/ln2wwwdata/source/mapped_n_glycans.csv\n Output Subdomain\n Name: glycan_enzyme.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/glycan_enzyme.csv\n Name: glycan_enzyme.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/glycan_enzyme.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"91\"\n Name: \"residue_id\"\n Description: \"residue id associated with the glycan\"\n Unique Values: \"199\"\n Name: \"gene_id\"\n Description: \"NCBI Gene identifier\"\n Unique Values: \"91\"\n Name: \"residue_name\"\n Description: \"Residue name of the glycan\"\n Unique Values: \"192\"\n Name: \"recommended_name_full\"\n Description: \"Recommended full name of the protein in the UniProtKB database\"\n Unique Values: \"1\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"1490\"\n Name: \"gene_name\"\n Description: \"Official gene name/symbol assigned to the gene. Human gene names/symbols are approved by the HUGO Gene Nomenclature Committee (HGNC)\n Unique Values: \"90\"\n Name: \"parent_residue_id\"\n Description: \"parent residue id associated with the glycan\"\n Unique Values: \"60\"", "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/glycan_enzyme.csv" }