{ "bcoid": "GLY_000043", "title": "Mouse Glycosylation Sites (RCSB PDB)", "description": "List of mouse [taxid:10090] proteins with information on glycosylation sites from UniCarbKB database. ...", "filename": "mouse_proteoform_glycosylation_sites_pdb.csv", "filetype": "csv", "categories": { "status": "Reviewed" }, "minitable": { "content": [ [ "P01731-1...", "1BQH..." ], [ "P27038-1...", "1BTE..." ] ], "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" } ], [ "P01731-1", "1BQH", "ASN", "N-Linked", "H", "42", "69", "Asn" ], [ "P27038-1", "1BTE", "ASN", "N-Linked", "A", "24", "43", "Asn" ], [ "P27038-1", "1BTE", "ASN", "N-Linked", "A", "47", "66", "Asn" ], [ "P40223-1", "1CD9", "ASN", "N-Linked", "B", "10", "129", "Asn" ], [ "Q05769-1", "1CVU", "ASN", "N-Linked", "A", "68", "53", "Asn" ], [ "Q05769-1", "1CVU", "ASN", "N-Linked", "B", "2068", "53", "Asn" ], [ "Q05769-1", "1CX2", "ASN", "N-Linked", "A", "68", "53", "Asn" ], [ "Q05769-1", "1DDX", "ASN", "N-Linked", "A", "68", "53", "Asn" ], [ "Q05769-1", "1DDX", "ASN", "N-Linked", "B", "1068", "53", "Asn" ], [ "Q05769-1", "1DDX", "ASN", "N-Linked", "C", "2068", "53", "Asn" ], [ "Q05769-1", "1DDX", "ASN", "N-Linked", "D", "3068", "53", "Asn" ], [ "P04224-1", "1I3R", "ASN", "N-Linked", "A", "118", "143", "Asn" ], [ "P04224-1", "1I3R", "ASN", "N-Linked", "G", "78", "103", "Asn" ], [ "P01738-1", "1I9E", "ASN", "N-Linked", "A", "70", "90", "Asn" ], [ "P52800-1", "1IKO", "ASN", "N-Linked", "P", "39", "39", "Asn" ], [ "P21836-1", "1J06", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "1J06", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "1J07", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "1J07", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P06344-1", "1K2D", "ASN", "N-Linked", "B", "19", "46", "Asn" ], [ "P28078-1", "1K8I", "ASN", "N-Linked", "A", "12", "41", "Asn" ], [ "P28078-1", "1K8I", "ASN", "N-Linked", "A", "162", "191", "Asn" ], [ "P21836-1", "1KU6", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P01897-1", "1LDP", "ASN", "N-Linked", "H", "86", "110", "Asn" ], [ "P01897-1", "1LDP", "ASN", "N-Linked", "H", "176", "200", "Asn" ], [ "P27038-1", "1LX5", "ASN", "N-Linked", "B", "24", "43", "Asn" ], [ "P27038-1", "1LX5", "ASN", "N-Linked", "B", "47", "66", "Asn" ], [ "P21836-1", "1MAA", "ASN", "N-Linked", "D", "350", "381", "Asn" ], [ "P21836-1", "1MAH", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "Q31093-1", "1MHC", "ASN", "N-Linked", "D", "86", "110", "Asn" ], [ "P21836-1", "1N5M", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "1N5R", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "1N5R", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P01731-1", "1NEZ", "ASN", "N-Linked", "G", "42", "69", "Asn" ], [ "P01731-1", "1NEZ", "ASN", "N-Linked", "G", "70", "97", "Asn" ], [ "P01852-1", "1NFD", "ASN", "N-Linked", "B", "121", "5", "Asn" ], [ "P45700-1", "1NXC", "ASN", "N-Linked", "A", "515", "515", "Asn" ], [ "P23188-1", "1P8J", "ASN", "N-Linked", "A", "387", "387", "Asn" ], [ "P23188-1", "1P8J", "ASN", "N-Linked", "A", "440", "440", "Asn" ], [ "Q05769-1", "1PXX", "ASN", "N-Linked", "A", "68", "53", "Asn" ], [ "Q05769-1", "1PXX", "ASN", "N-Linked", "B", "1068", "53", "Asn" ], [ "Q05769-1", "1PXX", "ASN", "N-Linked", "C", "2068", "53", "Asn" ], [ "Q05769-1", "1PXX", "ASN", "N-Linked", "D", "3068", "53", "Asn" ], [ "O08665-1", "1Q47", "ASN", "N-Linked", "A", "53", "53", "Asn" ], [ "O08665-1", "1Q47", "ASN", "N-Linked", "A", "125", "125", "Asn" ], [ "P21836-1", "1Q83", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "1Q83", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "1Q84", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "1Q84", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "O08543-1", "1SHX", "ASN", "N-Linked", "A", "41", "37", "Asn" ], [ "P10810-1", "1WWL", "ASN", "N-Linked", "A", "132", "147", "Asn" ], [ "P10810-1", "1WWL", "ASN", "N-Linked", "A", "165", "180", "Asn" ], [ "P10810-1", "1WWL", "ASN", "N-Linked", "A", "261", "276", "Asn" ], [ "O08912-1", "1XHB", "ASN", "N-Linked", "A", "552", "552", "Asn" ], [ "P11609-1", "2AKR", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "2AKR", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "P11609-1", "2AKR", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "P01731-1", "2ATP", "ASN", "N-Linked", "A", "42", "69", "Asn" ], [ "P10300-1", "2ATP", "ASN", "N-Linked", "D", "13", "34", "Asn" ], [ "Q60841-1", "2E26", "ASN", "N-Linked", "A", "2145", "2145", "Asn" ], [ "Q60841-1", "2E26", "ASN", "N-Linked", "A", "2269", "2269", "Asn" ], [ "Q60841-1", "2E26", "ASN", "N-Linked", "A", "2317", "2317", "Asn" ], [ "Q60841-1", "2E26", "ASN", "N-Linked", "A", "2569", "2569", "Asn" ], [ "P01810-1", "2FBJ", "ASN", "N-Linked", "H", "59", "59", "Asn" ], [ "P11609-1", "2FIK", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "2FIK", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "P11609-1", "2FIK", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "Q09324-1", "2GAK", "ASN", "N-Linked", "A", "58", "58", "Asn" ], [ "Q09324-1", "2GAK", "ASN", "N-Linked", "A", "95", "95", "Asn" ], [ "P11609-1", "2GAZ", "ASN", "N-Linked", "A", "20", "38", "Asn" ], [ "P11609-1", "2GAZ", "ASN", "N-Linked", "A", "42", "60", "Asn" ], [ "P11609-1", "2GAZ", "ASN", "N-Linked", "A", "165", "183", "Asn" ], [ "P21836-1", "2GYU", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "2GYU", "ASN", "N-Linked", "B", "350", "381", "Asn" ], [ "P21836-1", "2GYV", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "2GYV", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "2GYW", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "2GYW", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "2H9Y", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "2H9Y", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "2HA0", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "2HA0", "ASN", "N-Linked", "A", "464", "495", "Asn" ], [ "P21836-1", "2HA2", "ASN", "N-Linked", "A", "350", "381", "Asn" ], [ "P21836-1", "2HA2", "ASN", "N-Linked", "A", "464", "495", "Asn" ] ] }, "readme": "Name\n - Mouse Glycosylation Sites (RCSB PDB)\n\nVersion\n - 1.0.13\n\nCreated on\n - 2019-01-23T17:21:05.910839\n\nModified on\n - 2019-04-11T13:56:50.790064\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu]\n\nAuthors\n - Jasmine Young [jasmine@rcsb.rutgers.edu], Chenghua Shao [chenghua@rcsb.rutgers.edu], Nagarajan Pattabiraman [pattabir@email.gwu.edu], Reza Mousavi [rezamousavi@gwmail.gwu.edu]\n\nChecksum\n - \n\nUsability Domain\n - List of mouse [taxid:10090] proteins with information on glycosylation sites from UniCarbKB database. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation\n\n Pipeline Steps\n - Step-1: The list of PDB Id's was retrieved from the source and their PDB header files were downloaded on september 27, 2018 and the header files were parsed to extract information on glycosylation positions for PDB Id's and UniProt accessions using headers 'DBREF', 'LINK' and 'MODRES' using a script [make-proteoform-glycosylation_sites_pdb_step1-csv.py].\n - Step-1: PDB Ids where information in the header files was either not available or was incorrect were eliminated. [The eliminated PDB Id's can be accessed through log file- proteoform_glycosylation_sites_pdb.log in output subdomain].\n - Step-2: Records which fall under one or more following conditions were flagged and eliminated. [The eliminated records can be accessed through log file- mouse_proteoform_glycosylation_sites_pdb.log in output subdomain]: a. A mismatch between 'amino_acid_pdb' and 'amino_acid_uniprotkb' is observed. b. A mismatch between 'amino_acid_uniprotkb' and amino acid retrieved from fasta sequences (UniProtKB NOV-17 version) is observed. \n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend/blob/master/integration/\n - https://github.com/glygener/glygen-backend/blob/master/integration/\n - https://github.com/glygener/glygen-backend/blob/master/integration/\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-ASN.txt\n URI: source/N-linked-ASN.txt\n Name: O-linked-SER.txt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/O-linked-SER.txt\n Name: https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/O-linked-THR.txt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/O-linked-THR.txt\n Name: mouse_protein_all.fasta\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_all.fasta\n Output Subdomain\n Name: mouse_proteoform_glycosylation_sites_pdb.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv\n Name: mouse_proteoform_glycosylation_sites_pdb.stat.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_proteoform_glycosylation_sites_pdb.stat.csv\n\nFields", "downloadurl": "/ln2data/releases/data/v-1.0.13/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv" }