{ "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": [ [ "P05451-1...", "O-linked..." ], [ "Q14118-1...", "O-linked..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "evidence" }, { "type": "string", "label": "pdb_id" }, { "type": "string", "label": "amino_acid_chain" }, { "type": "string", "label": "glycosylation_site_pdb" } ], [ "P05451-1", "O-linked", "NDG", "Thr", "27", "", "1QDD", "A", "5" ], [ "Q14118-1", "O-linked", "A2G", "Thr", "422", "", "2MK7", "A", "5" ], [ "Q14118-1", "O-linked", "A2G", "Thr", "424", "", "2MK7", "A", "7" ], [ "Q14118-1", "O-linked", "A2G", "Thr", "423", "", "2MK7", "A", "6" ], [ "Q14118-1", "O-linked", "A2G", "Thr", "421", "", "2MK7", "A", "4" ], [ "P04062-1", "O-linked", "NAG", "Thr", "60", "", "2NT0", "D", "21" ], [ "P13671-1", "O-linked", "FUC", "Thr", "38", "", "3T5O", "A", "17" ], [ "P13671-1", "O-linked", "FUL", "Thr", "392", "", "3T5O", "A", "371" ], [ "Q86YL7-1", "O-linked", "A2G", "Thr", "89", "", "3WSR", "C", "52" ], [ "Q86YL7-1", "O-linked", "A2G", "Thr", "89", "", "3WSR", "D", "52" ], [ "P00747-1", "O-linked", "NGA", "Thr", "365", "", "4A5T", "S", "346" ], [ "P00747-1", "O-linked", "NAG", "Thr", "365", "", "4DUR", "A", "346" ], [ "P00747-1", "O-linked", "NAG", "Thr", "365", "", "4DUR", "B", "346" ], [ "P13671-1", "O-linked", "FUC", "Thr", "38", "", "4E0S", "B", "17" ], [ "P98088-1", "O-linked", "A2G", "Thr", "4567", "", "5AJO", "B", "3" ], [ "P98088-1", "O-linked", "A2G", "Thr", "4577", "", "5AJO", "B", "13" ], [ "P98088-1", "O-linked", "A2G", "Thr", "4577", "", "5AJP", "B", "13" ], [ "P32926-1", "O-linked", "MAN", "Thr", "476", "", "5EQX", "A", "427" ], [ "P32926-1", "O-linked", "MAN", "Thr", "478", "", "5EQX", "A", "429" ], [ "P32926-1", "O-linked", "MAN", "Thr", "480", "", "5EQX", "A", "431" ], [ "Q14126-1", "O-linked", "MAN", "Thr", "480", "", "5ERD", "B", "431" ], [ "Q14126-1", "O-linked", "MAN", "Thr", "482", "", "5ERD", "B", "433" ], [ "Q14126-1", "O-linked", "MAN", "Thr", "484", "", "5ERD", "B", "435" ], [ "Q14126-1", "O-linked", "MAN", "Thr", "480", "", "5ERD", "A", "431" ], [ "Q14126-1", "O-linked", "MAN", "Thr", "482", "", "5ERD", "A", "433" ], [ "Q14126-1", "O-linked", "MAN", "Thr", "484", "", "5ERD", "A", "435" ], [ "Q14118-1", "O-linked", "MAN", "Thr", "319", "", "5GGP", "C", "4" ], [ "Q14118-1", "O-linked", "MAN", "Thr", "319", "", "5GGP", "D", "4" ], [ "Q08554-1", "O-linked", "MAN", "Thr", "562", "", "5IRY", "B", "428" ], [ "Q08554-1", "O-linked", "MAN", "Thr", "337", "", "5IRY", "A", "203" ], [ "Q08554-1", "O-linked", "MAN", "Thr", "339", "", "5IRY", "A", "205" ], [ "Q08554-1", "O-linked", "MAN", "Thr", "560", "", "5IRY", "A", "426" ], [ "Q08554-1", "O-linked", "MAN", "Thr", "337", "", "5IRY", "B", "203" ], [ "Q08554-1", "O-linked", "MAN", "Thr", "339", "", "5IRY", "B", "205" ], [ "P15941-1", "O-linked", "NGA", "Thr", "924", "", "5T78", "F", "4" ], [ "P15941-1", "O-linked", "NGA", "Thr", "924", "", "5T78", "E", "4" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "E", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "F", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "G", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "H", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "I", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "A", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "J", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "K", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "L", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "M", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "N", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "O", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "P", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "Q", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "R", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "S", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "B", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "T", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "U", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "V", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "C", "497" ], [ "P02748-1", "O-linked", "NAG", "Thr", "518", "", "6DLW", "D", "497" ], [ "P61586-1", "O-linked", "NDG", "Tyr", "34", "", "5A0F", "A", "34" ], [ "O15118-1", "O-linked", "NAG", "Tyr", "475", "", "5U74", "A", "475" ], [ "P14384-1", "O-linked", "NAG", "Asp", "240", "", "1UWY", "A", "223" ], [ "P04746-1", "O-linked", "B9D", "Asp", "212", "", "3IJ7", "A", "197" ], [ "P04746-1", "O-linked", "B9D", "Asp", "212", "", "3IJ8", "A", "197" ], [ "P04746-1", "O-linked", "B9D", "Asp", "212", "", "3IJ9", "A", "197" ], [ "P08637-1", "O-linked", "NAG", "Asp", "82", "", "3SGK", "C", "64" ], [ "P12821-1", "O-linked", "NAG", "Glu", "625", "", "2C6F", "A", "596" ], [ "Q9H227-1", "O-linked", "GLC", "Glu", "373", "", "2ZOX", "A", "373" ], [ "Q9H227-1", "O-linked", "MAN", "Glu", "373", "", "3VKK", "A", "373" ], [ "O15118-1", "O-linked", "NAG", "Glu", "1067", "", "5U73", "A", "1067" ], [ "P05121-1", "N-linked", "NAG", "Asn", "288", "", "1A7C", "A", "265" ], [ "P05121-1", "N-linked", "NAG", "Asn", "232", "", "1A7C", "A", "209" ], [ "P20160-1", "N-linked", "NAG", "Asn", "140", "", "1A7S", "A", "114" ], [ "P20160-1", "N-linked", "NAG", "Asn", "171", "", "1A7S", "A", "145" ], [ "P20160-1", "N-linked", "NAG", "Asn", "140", "", "1AE5", "A", "114" ], [ "P20160-1", "N-linked", "NAG", "Asn", "171", "", "1AE5", "A", "145" ], [ "P20933-1", "N-linked", "NAG", "Asn", "38", "", "1APY", "A", "15" ], [ "P20933-1", "N-linked", "NAG", "Asn", "38", "", "1APY", "C", "15" ], [ "P20933-1", "N-linked", "NAG", "Asn", "38", "", "1APZ", "A", "15" ], [ "P20933-1", "N-linked", "NAG", "Asn", "38", "", "1APZ", "C", "15" ], [ "P01574-1", "N-linked", "BGC", "Asn", "101", "", "1AU1", "A", "80" ], [ "P01574-1", "N-linked", "BGC", "Asn", "101", "", "1AU1", "B", "80" ], [ "P01008-1", "N-linked", "NAG", "Asn", "187", "", "1AZX", "I", "155" ], [ "P01008-1", "N-linked", "NAG", "Asn", "187", "", "1AZX", "L", "155" ], [ "P01008-1", "N-linked", "NAG", "Asn", "224", "", "1AZX", "L", "192" ] ] }, "readme": "Name\n - Human Glycosylation Sites (RCSB PDB)\n\nVersion\n - 1.5.11\n\nCreated on\n - 2019-01-23T17:21:05.909814\n\nModified on\n - 2019-11-26T16:30:40.904331\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: The script extracts the PDB IDs from the N-linked and O-linked files and extract the PDB files containing the glycosylation information from RCSB PDB using their API. The script using also checks the position of UniProtKB aa position in the file with the current sequences and finally maps the UniProtKB accession to the UniProtKB canonical accessions for the given organism.\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: N-linked-ARG\n URI: https://data.glygen.org/ln2wwwdata/source/N-linked-ARG\n Name: pdb_chain_uniprot_2018_11_8_11_44_50.csv\n URI: https://data.glygen.org/ln2wwwdata/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv\n Name: O-linked-ASP\n URI: https://data.glygen.org/ln2wwwdata/source/O-linked-ASP\n Name: O-linked-GLU\n URI: https://data.glygen.org/ln2wwwdata/source/O-linked-GLU\n Name: O-linked-SER\n URI: https://data.glygen.org/ln2wwwdata/source/O-linked-SER\n Name: O-linked-THR\n URI: https://data.glygen.org/ln2wwwdata/source/O-linked-THR\n Name: O-linked-TYR\n URI: https://data.glygen.org/ln2wwwdata/source/O-linked-TYR\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_pdb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.csv\n Name: human_proteoform_glycosylation_sites_pdb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/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: \"240\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"422\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"6\"\n Name: \"glycosylation_site_pdb\"\n Description: \"\"\n Unique Values: \"411\"\n Name: \"evidence\"\n Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n Unique Values: \"1\"\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: \"829\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"12\"\n Name: \"amino_acid_chain\"\n Description: \"\"\n Unique Values: \"26\"", "downloadurl": "/ln2data/releases/data/v-1.5.11/reviewed/human_proteoform_glycosylation_sites_pdb.csv" }