{ "bcoid": "GLY_000043", "title": "Mouse Glycosylation Sites (RCSB PDB)", "description": "The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins with RCSB PDB ...", "filename": "mouse_proteoform_glycosylation_sites_pdb.csv", "filetype": "csv", "categories": { "species": "Mus Musculus", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P70158-1...", "5fca..." ], [ "P70158-1...", "5fca..." ] ], "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" } ], [ "P70158-1", "5fca", "ASN", "N-Linked", "A", "66", "66", "Asn" ], [ "P70158-1", "5fca", "ASN", "N-Linked", "A", "128", "128", "Asn" ], [ "P70158-1", "5fca", "ASN", "N-Linked", "A", "235", "235", "Asn" ], [ "P70158-1", "5fca", "ASN", "N-Linked", "A", "353", "353", "Asn" ], [ "Q05769-1", "4rry", "ASN", "N-Linked", "D", "68", "53", "Asn" ], [ "P11609-1", "3gmm", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "3gmm", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "P11609-1", "3gmm", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "Q8BHN3-1", "5ied", "ASN", "N-Linked", "A", "97", "97", "Asn" ], [ "P04224-1", "3qiw", "ASN", "N-Linked", "A", "118", "143", "Asn" ], [ "P21836-1", "5fpp", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P01852-1", "1nfd", "ASN", "N-Linked", "B", "121", "5", "Asn" ], [ "P01901-1", "1leg", "ASN", "N-Linked", "A", "86", "107", "Asn" ], [ "P01901-1", "1leg", "ASN", "N-Linked", "A", "176", "197", "Asn" ], [ "Q05769-1", "3ln0", "ASN", "N-Linked", "B", "396", "396", "Asn" ], [ "Q05769-1", "3ln0", "ASN", "N-Linked", "A", "53", "53", "Asn" ], [ "Q05769-1", "3ln0", "ASN", "N-Linked", "A", "130", "130", "Asn" ], [ "P01731-1", "1nez", "ASN", "N-Linked", "G", "42", "69", "Asn" ], [ "P01731-1", "1nez", "ASN", "N-Linked", "G", "70", "97", "Asn" ], [ "P06802-1", "4gtz", "ASN", "N-Linked", "A", "567", "567", "Asn" ], [ "P06802-1", "4gtz", "ASN", "N-Linked", "A", "323", "323", "Asn" ], [ "P06802-1", "4gtz", "ASN", "N-Linked", "B", "267", "267", "Asn" ], [ "P52800-1", "1iko", "ASN", "N-Linked", "P", "39", "39", "Asn" ], [ "P01901-1", "1g7p", "ASN", "N-Linked", "A", "86", "107", "Asn" ], [ "P01901-1", "1g7p", "ASN", "N-Linked", "A", "176", "197", "Asn" ], [ "P21836-1", "2y2v", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "2y2v", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "4ara", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "4ara", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "Q64487-4", "4yfg", "ASN", "N-Linked", "B", "251", "244", "Asn" ], [ "P11609-1", "3he7", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "3he7", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "P11609-1", "3he7", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "Q9EQF4-1", "5jyj", "ASN", "N-Linked", "A", "185", "185", "Asn" ], [ "P15116-1", "3q2w", "ASN", "N-Linked", "A", "166", "325", "Asn" ], [ "P15116-1", "3q2w", "ASN", "N-Linked", "A", "243", "402", "Asn" ], [ "P15116-1", "3q2w", "ASN", "N-Linked", "A", "413", "572", "Asn" ], [ "P15116-1", "3q2w", "ASN", "N-Linked", "A", "114", "273", "Asn" ], [ "P15116-1", "3q2w", "ASN", "N-Linked", "A", "492", "651", "Asn" ], [ "P15116-1", "3q2w", "SER", "O-Linked", "A", "427", "586", "Ser" ], [ "P15116-1", "3q2w", "SER", "O-Linked", "A", "326", "485", "Ser" ], [ "P54818-1", "4ufi", "ASN", "N-Linked", "A", "284", "300", "Asn" ], [ "P54818-1", "4ufi", "ASN", "N-Linked", "A", "363", "379", "Asn" ], [ "P54818-1", "4ufi", "ASN", "N-Linked", "A", "387", "403", "Asn" ], [ "P54818-1", "4ufi", "ASN", "N-Linked", "A", "542", "558", "Asn" ], [ "P11609-1", "3ard", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "P11609-1", "3ard", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "3ard", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "Q91Y09-1", "4zpm", "SER", "O-Linked", "A", "196", "237", "Ser" ], [ "Q91Y09-1", "4zpm", "ASN", "N-Linked", "A", "238", "279", "Asn" ], [ "Q99PJ1-1", "6c13", "ASN", "N-Linked", "A", "1069", "1069", "Asn" ], [ "Q99PJ1-1", "6c13", "ASN", "N-Linked", "A", "1089", "1089", "Asn" ], [ "Q99PJ1-1", "6c13", "ASN", "N-Linked", "A", "1180", "1180", "Asn" ], [ "Q60675-1", "5ik5", "ASN", "N-Linked", "A", "2889", "2889", "Asn" ], [ "P70206-1", "5l7n", "ASN", "N-Linked", "A", "1041", "1041", "Asn" ], [ "P70206-1", "5l7n", "ASN", "N-Linked", "A", "1096", "1096", "Asn" ], [ "P70206-1", "5l7n", "ASN", "N-Linked", "A", "1185", "1185", "Asn" ], [ "P11609-1", "3qi9", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "3qi9", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "P11609-1", "3qi9", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "P10820-1", "3nsj", "ASN", "N-Linked", "A", "204", "204", "Asn" ], [ "Q05769-1", "4rrw", "ASN", "N-Linked", "A", "68", "53", "Asn" ], [ "P59823-1", "4yh6", "ASN", "N-Linked", "A", "122", "122", "Asn" ], [ "P59823-1", "4yh6", "ASN", "N-Linked", "A", "138", "138", "Asn" ], [ "P59823-1", "4yh6", "ASN", "N-Linked", "A", "213", "213", "Asn" ], [ "P59823-1", "4yh6", "ASN", "N-Linked", "A", "264", "264", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "121", "164", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "156", "199", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "195", "238", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "218", "261", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "342", "385", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "359", "402", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "378", "421", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "397", "440", "Asn" ], [ "P42703-1", "2q7n", "ASN", "N-Linked", "A", "410", "453", "Asn" ], [ "Q04519-1", "5fib", "ASN", "N-Linked", "A", "84", "84", "Asn" ], [ "Q04519-1", "5fib", "ASN", "N-Linked", "A", "173", "173", "Asn" ], [ "Q04519-1", "5fib", "ASN", "N-Linked", "A", "333", "333", "Asn" ], [ "Q04519-1", "5fib", "ASN", "N-Linked", "A", "393", "393", "Asn" ], [ "Q04519-1", "5fib", "ASN", "N-Linked", "A", "518", "518", "Asn" ], [ "Q8BHN3-1", "5hjo", "ASN", "N-Linked", "A", "97", "97", "Asn" ], [ "O35464-1", "3okw", "ASN", "N-Linked", "A", "434", "434", "Asn" ], [ "O35464-1", "3okw", "ASN", "N-Linked", "B", "461", "461", "Asn" ], [ "O35464-1", "3okw", "ASN", "N-Linked", "A", "282", "282", "Asn" ] ] }, "readme": "Name\n - Mouse Glycosylation Sites (RCSB PDB)\n\nVersion\n - 1.4.5\n\nCreated on\n - 2019-01-23T17:21:05.910839\n\nModified on\n - 2019-04-11T13:56:50.790064\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 Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] 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: mouse_protein_idmapping.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/mouse_protein_idmapping.csv\n Output Subdomain\n Name: mouse_proteoform_glycosylation_sites_pdb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv\n Name: mouse_proteoform_glycosylation_sites_pdb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.4.5/reviewed/mouse_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: \"138\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"278\"\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: \"291\"\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: \"457\"\n Name: \"amino_acid_chain\"\n Description: \"\"\n Unique Values: \"14\"", "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv" }