{ "bcoid": "GLY_000042", "title": "Human Glycosylation Sites (RCSB PDB)", "description": "The Human Glycosylation Sites (RCSB PDB) dataset contains human [taxid:9606] proteins with RCSB PDB Id's ...", "filename": "human_proteoform_glycosylation_sites_pdb.csv", "filetype": "csv", "categories": { "species": "Homo Sapiens", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q13563-1...", "6d1w..." ], [ "Q13563-1...", "6d1w..." ] ], "headers": [ "uniprotkb_ca...", "pdb_id..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "pdb_id" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "amino_acid_chain" }, { "type": "string", "label": "glycosylation_site_pdb" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "amino_acid_uniprotkb" } ], [ "Q13563-1", "6d1w", "ASN", "N-Linked", "A", "328", "328", "Asn" ], [ "Q13563-1", "6d1w", "ASN", "N-Linked", "A", "362", "362", "Asn" ], [ "Q13563-1", "6d1w", "ASN", "N-Linked", "A", "375", "375", "Asn" ], [ "P12319-1", "1rpq", "ASN", "N-Linked", "A", "21", "46", "Asn" ], [ "P12319-1", "1rpq", "ASN", "N-Linked", "A", "42", "67", "Asn" ], [ "P12319-1", "1rpq", "ASN", "N-Linked", "A", "140", "165", "Asn" ], [ "P12319-1", "1rpq", "ASN", "N-Linked", "A", "166", "191", "Asn" ], [ "P06756-1", "6djp", "ASN", "N-Linked", "A", "44", "74", "Asn" ], [ "P06756-1", "6djp", "ASN", "N-Linked", "A", "260", "290", "Asn" ], [ "P06756-1", "6djp", "ASN", "N-Linked", "A", "266", "296", "Asn" ], [ "P06756-1", "6djp", "ASN", "N-Linked", "A", "524", "554", "Asn" ], [ "P06756-1", "6djp", "ASN", "N-Linked", "A", "585", "615", "Asn" ], [ "P26012-1", "6djp", "ASN", "N-Linked", "B", "191", "233", "Asn" ], [ "P26012-1", "6djp", "ASN", "N-Linked", "B", "360", "402", "Asn" ], [ "P26012-1", "6djp", "ASN", "N-Linked", "B", "379", "421", "Asn" ], [ "P26012-1", "6djp", "ASN", "N-Linked", "B", "389", "431", "Asn" ], [ "P26012-1", "6djp", "ASN", "N-Linked", "B", "414", "456", "Asn" ], [ "P18075-1", "1lxi", "ASN", "N-Linked", "A", "80", "372", "Asn" ], [ "Q8N2Q7-1", "5ojk", "ASN", "N-Linked", "A", "109", "109", "Asn" ], [ "Q9Y3Q0-1", "3fed", "ASN", "N-Linked", "A", "111", "111", "Asn" ], [ "Q9Y3Q0-1", "3fed", "ASN", "N-Linked", "A", "185", "185", "Asn" ], [ "Q9Y3Q0-1", "3fed", "ASN", "N-Linked", "A", "449", "449", "Asn" ], [ "Q9Y3Q0-1", "3fed", "ASN", "N-Linked", "A", "628", "628", "Asn" ], [ "P07686-1", "1now", "ASN", "N-Linked", "A", "190", "190", "Asn" ], [ "P05106-1", "3nif", "ASN", "N-Linked", "B", "320", "346", "Asn" ], [ "P05106-1", "3nif", "ASN", "N-Linked", "B", "371", "397", "Asn" ], [ "P05106-1", "3nif", "ASN", "N-Linked", "D", "99", "125", "Asn" ], [ "P14207-1", "4kn1", "ASN", "N-Linked", "A", "195", "195", "Asn" ], [ "P02743-1", "4avt", "ASN", "N-Linked", "A", "32", "51", "Asn" ], [ "Q9NZK5-1", "3lgd", "ASN", "N-Linked", "B", "101", "127", "Asn" ], [ "Q9NZK5-1", "3lgd", "ASN", "N-Linked", "A", "159", "185", "Asn" ], [ "Q9NZK5-1", "3lgd", "ASN", "N-Linked", "A", "352", "378", "Asn" ], [ "P07339-1", "4obz", "ASN", "N-Linked", "A", "70", "134", "Asn" ], [ "O95970-1", "5y2z", "ASN", "N-Linked", "B", "277", "277", "Asn" ], [ "O95970-1", "5y2z", "ASN", "N-Linked", "B", "422", "422", "Asn" ], [ "P20273-1", "5vkj", "ASN", "N-Linked", "A", "101", "101", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "943", "973", "Asn" ], [ "P05106-1", "4g1m", "ASN", "N-Linked", "B", "320", "346", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "260", "290", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "266", "296", "Asn" ], [ "P05106-1", "4g1m", "ASN", "N-Linked", "B", "99", "125", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "950", "980", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "674", "704", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "524", "554", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "821", "851", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "585", "615", "Asn" ], [ "P05106-1", "4g1m", "ASN", "N-Linked", "B", "371", "397", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "458", "488", "Asn" ], [ "P05106-1", "4g1m", "ASN", "N-Linked", "B", "559", "585", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "44", "74", "Asn" ], [ "P06756-1", "4g1m", "ASN", "N-Linked", "A", "805", "835", "Asn" ], [ "P05106-1", "4g1m", "ASN", "N-Linked", "B", "452", "478", "Asn" ], [ "P04180-1", "5txf", "ASN", "N-Linked", "A", "272", "296", "Asn" ], [ "P04180-1", "5txf", "ASN", "N-Linked", "A", "384", "408", "Asn" ], [ "P27487-1", "3o9v", "ASN", "N-Linked", "A", "150", "150", "Asn" ], [ "P27487-1", "3o9v", "ASN", "N-Linked", "A", "229", "229", "Asn" ], [ "P27487-1", "3o9v", "ASN", "N-Linked", "A", "281", "281", "Asn" ], [ "P27487-1", "3o9v", "ASN", "N-Linked", "A", "321", "321", "Asn" ], [ "P27487-1", "3o9v", "ASN", "N-Linked", "B", "85", "85", "Asn" ], [ "P27487-1", "3o9v", "ASN", "N-Linked", "B", "219", "219", "Asn" ], [ "P56373-1", "5svs", "ASN", "N-Linked", "A", "170", "170", "Asn" ], [ "P56373-1", "5svs", "ASN", "N-Linked", "A", "194", "194", "Asn" ], [ "P56373-1", "5svs", "ASN", "N-Linked", "A", "290", "290", "Asn" ], [ "Q04609-1", "5ely", "ASN", "N-Linked", "A", "76", "76", "Asn" ], [ "Q04609-1", "5ely", "ASN", "N-Linked", "A", "121", "121", "Asn" ], [ "Q04609-1", "5ely", "ASN", "N-Linked", "A", "140", "140", "Asn" ], [ "Q04609-1", "5ely", "ASN", "N-Linked", "A", "459", "459", "Asn" ], [ "Q04609-1", "5ely", "ASN", "N-Linked", "A", "476", "476", "Asn" ], [ "Q04609-1", "5ely", "ASN", "N-Linked", "A", "638", "638", "Asn" ], [ "P27487-1", "5t4b", "ASN", "N-Linked", "A", "85", "85", "Asn" ], [ "P27487-1", "5t4b", "ASN", "N-Linked", "A", "150", "150", "Asn" ], [ "P27487-1", "5t4b", "ASN", "N-Linked", "A", "219", "219", "Asn" ], [ "P27487-1", "5t4b", "ASN", "N-Linked", "A", "229", "229", "Asn" ], [ "P27487-1", "5t4b", "ASN", "N-Linked", "A", "281", "281", "Asn" ], [ "P27487-1", "5t4b", "ASN", "N-Linked", "A", "321", "321", "Asn" ], [ "P35499-1", "6agf", "ASN", "N-Linked", "A", "362", "362", "Asn" ], [ "P35499-1", "6agf", "ASN", "N-Linked", "A", "1205", "1205", "Asn" ], [ "Q07699-1", "6agf", "ASN", "N-Linked", "B", "110", "110", "Asn" ], [ "Q07699-1", "6agf", "ASN", "N-Linked", "B", "114", "114", "Asn" ], [ "O15118-1", "5hns", "ASN", "N-Linked", "A", "478", "478", "Asn" ], [ "O15118-1", "5hns", "ASN", "N-Linked", "A", "524", "524", "Asn" ], [ "O15118-1", "5hns", "ASN", "N-Linked", "A", "557", "557", "Asn" ], [ "O15118-1", "5hns", "ASN", "N-Linked", "A", "572", "572", "Asn" ], [ "O15118-1", "5hns", "ASN", "N-Linked", "A", "598", "598", "Asn" ] ] }, "readme": "Name\n - Human Glycosylation Sites (RCSB PDB)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-01-23T17:21:05.909814\n\nModified on\n - 2019-04-11T13:51:44.162252\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]\n\nAuthors\n - Jasmine Young [jasmine@rcsb.rutgers.edu], Chenghua Shao [chenghua@rcsb.rutgers.edu]\n\nChecksum\n - \n\nUsability Domain\n - The Human Glycosylation Sites (RCSB PDB) dataset contains human [taxid:9606] proteins with RCSB PDB Id's and with the information of glycosylation sites which are also mapped to the UniProtKB accession's sequence position glycosylation and RCSB PDB Id's [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)].\n\nDescription Domain\n Keywords\n - PDB\n - glycosylation sites\n - amino acid\n - amino acid chain\n\n Pipeline Steps\n - Step-1: \n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-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: pdblist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/pdblist.csv\n Name: pdb_chain_uniprot_2018_11_8_11_44_50.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv\n Name: human_protein_idmapping.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_protein_idmapping.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_pdb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_pdb.csv\n Name: human_proteoform_glycosylation_sites_pdb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_pdb.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: \"462\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"612\"\n Name: \"amino_acid_uniprotkb\"\n Description: \"Three letter abbreviation code of amino acid at glycosylation site on the protein sequence of UniProtKB entry\"\n Unique Values: \"2\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"2\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"glycosylation_site_pdb\"\n Description: \"\"\n Unique Values: \"660\"\n Name: \"pdb_id\"\n Description: \"4-character id assigned to each protein structure in Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB)\"\n Unique Values: \"1846\"\n Name: \"amino_acid_chain\"\n Description: \"\"\n Unique Values: \"27\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_pdb.csv" }