{ "object_id": "https://biocomputeobject.org/GLY_000043/1.11.2", "spec_version": "1.3.0", "extension_domain": [ { "extension_schema": "http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Mus musculus", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Glycosylation Sites", "category_name": "tags" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "provenance_domain": { "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Mouse Glycosylation Sites (RCSB PDB)", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Xavier Holmes", "email": "xavierh@email.gwu.edu" }, { "affiliation": "RCSB PDB", "contribution": [ "contributedBy" ], "name": "Jasmine Young", "email": "jasmine@rcsb.rutgers.edu" }, { "affiliation": "RCSB PDB", "contribution": [ "contributedBy" ], "name": "Chenghua Shao", "email": "chenghua@rcsb.rutgers.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Amanda Bell", "email": "amandab2140@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jonathon Keeney", "email": "keeneyjg@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Millicent Quartey", "email": "mquartey@email.gwu.edu" } ], "created": "2019-01-23T17:21:05.910839", "modified": "2020-04-10T12:35:07.324192", "version": "1.11.2" }, "description_domain": { "keywords": [ "PDB", "glycosylation sites", "amino acid", "amino acid chain" ], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "step_number": 1, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/source/N-linked-ARG", "filename": "N-linked-ARG-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/N-linked-ASN", "filename": "N-linked-ASN-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-ASP", "filename": "O-linked-ASP-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-GLU", "filename": "O-linked-GLU-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-SER", "filename": "O-linked-SER-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-THR", "filename": "O-linked-THR-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-TYR", "filename": "O-linked-TYR-details" }, { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv", "filename": "mouse_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv", "filename": "mouse_proteoform_glycosylation_sites_pdb.csv" } ], "prerequisite": [], "description": "The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB." } ] }, "execution_domain": { "external_data_endpoints": [], "environment_variables": {}, "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [ { "uri": { "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {}, "emperical_error": {} }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "usability_domain": [ "The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]." ], "etag": "fb43b4f1d185a8a723b78e9c60116498", "io_domain": { "input_subdomain": [ { "uri": { "uri": "https:/data.glygen.org/ln2downloads/old_source/pdb_chain_uniprot_2018_11_8_11_44_50.csv", "filename": "pdb_chain_uniprot_2018_11_8_11_44_50.csv" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/pdb/v-x.x.x/O-linked-TYR-details", "filename": "O-linked-TYR-details" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/pdb/v-x.x.x/O-linked-ASP-details", "filename": "O-linked-ASP-details" } }, { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_canonicalsequences.fasta", "filename": "mouse_protein_canonicalsequences.fasta" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/pdb/v-x.x.x/O-linked-THR-details", "filename": "O-linked-THR-details" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/pdb/v-x.x.x/O-linked-SER-details", "filename": "O-linked-SER-details" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/pdb/v-x.x.x/O-linked-GLU-details", "filename": "O-linked-GLU-details" } }, { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_protein_masterlist.csv", "filename": "mouse_protein_masterlist.csv" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/pdb/v-x.x.x/N-linked-ARG-details", "filename": "N-linked-ARG-details" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv", "filename": "mouse_proteoform_glycosylation_sites_pdb.csv" } } ] } }