{ "object_id": "https://biocomputeobject.org/GLY_000332/v-2.0.2", "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": "Homo sapiens", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "MatrixDB", "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": "Human Interaction data (MatrixDB)", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "MatrixDB", "contribution": [ "contributedBy" ], "name": "Sylvie Ricard-Blum", "email": "sylvie.ricard-blum@univ-lyon1.fr" }, { "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": "2020-02-10T12:42:38.432328", "modified": "2020-05-01T15:23:10.031133", "version": "v-2.0.2" }, "description_domain": { "keywords": [ "protein-GAGs interaction", "MatrixDB" ], "pipeline_steps": [ { "name": "make-protein-dataset.py", "step_number": 1, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/matrixdb_CORE.csv", "filename": "matrixdb_CORE.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv", "filename": "human_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_matrixdb.csv", "filename": "human_protein_matrixdb.csv" } ], "prerequisite": [], "description": "The tab file (matrixdb_CORE.tab (labeled as \u201cCore MatrixDB dataset as PSI-MI TAB 2.7 file\u201d) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)." } ] }, "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/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ] }, "usability_domain": [ "The Human Interaction data (MatrixDB) dataset contains interaction data between Human [taxid:9606] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen." ], "etag": "93ce451b4271b8d5dbb9058025a2df75", "io_domain": { "input_subdomain": [ { "uri": { "filename": "matrix_db_label.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/matrix_db_label.csv" } }, { "uri": { "filename": "matrixdb.tsv", "uri": "https:/data.glygen.org/ln2downloads/glytoucan/gtc_08_31_2022/export/matrixdb.tsv" } }, { "uri": { "filename": "matrixdb_CORE.csv", "uri": "https:/data.glygen.org/ln2downloads/matrixdb/2019_08_07/matrixdb_CORE.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_matrixdb.csv", "filename": "human_protein_matrixdb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_matrixdb.stat.csv", "filename": "human_protein_matrixdb.stat.csv" } } ] } }