{ "object_id": "https://biocomputeobject.org/GLY_000041/v-1.0.13", "license": "https://creativecommons.org/licenses/by/4.0/", "contributors": [ { "orcid": "", "affiliation": "George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "orcid": "", "affiliation": "UniCarbKB", "contribution": [ "authoredBy" ], "name": "Matthew Campbell ", "email": "m.campbell2@griffith.edu.au" }, { "orcid": "", "affiliation": "George Washington University", "contribution": [ "contributedBy" ], "name": "Robel Kahsay", "email": "rykahsay@email.gwu.edu" }, { "orcid": "", "affiliation": "George Washington University", "contribution": [ "contributedBy" ], "name": "Brian Fochtman ", "email": "bfochtman@email.gwu.edu" } ], "created": "2019-01-23T17:21:05.908793", "spec_version": "1.3.0", "modified": "2019-02-20T11:18:49.050326", "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": "Reviewed", "category_name": "status" } ] } } ], "io_domain": { "input_subdomain": [ { "uri": { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/unicarbkb_mouse_2018_10_31_02_16_31.clean.csv", "filename": "unicarbkb_mouse_2018_10_31_02_16_31.clean.csv" } }, { "uri": { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/mouse_glytoucan_140918_2018_10_31_02_18_55.txt", "filename": "mouse_glytoucan_140918_2018_10_31_02_18_55.txt" } }, { "uri": { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_all.fasta", "filename": "mouse_protein_all.fasta" } } ], "output_subdomain": [ { "mediatype": "", "uri": { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv" } }, { "mediatype": "csv", "uri": { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv" } } ] }, "provenance_domain": { "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Mouse Glycosylation Sites (UniCarbKB)", "contributors": [ { "affiliation": "George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "affiliation": "George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "UniCarbKB", "contribution": [ "authoredBy" ], "name": "Matthew Campbell ", "email": "m.campbell2@griffith.edu.au" }, { "affiliation": "George Washington University", "contribution": [ "contributedBy" ], "name": "Brian Fochtman ", "email": "bfochtman@email.gwu.edu" }, { "affiliation": "George Washington University", "contribution": [ "contributedBy" ], "name": "Robel Kahsay", "email": "rykahsay@email.gwu.edu" } ], "created": "2019-01-23T17:21:05.908793", "modified": "2019-04-11T13:45:56.393647", "version": "v-1.0.13" }, "description_domain": { "keywords": [ "proteins", "canonical", "glycosylation", "glycan" ], "pipeline_steps": [ { "name": "python", "step_number": 1, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/unicarbkb_mouse_2018_10_31_02_16_31.clean.csv", "filename": "unicarbkb_mouse_2018_10_31_02_16_31.clean.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/mouse_glytoucan_140918_2018_10_31_02_18_55.txt", "filename": "mouse_glytoucan_140918_2018_10_31_02_18_55.txt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/mouse_glycosylation_types.csv", "filename": "mouse_glycosylation_types.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/logs/mouse_glycosylation_types.log", "filename": "mouse_glycosylation_types.log" } ], "prerequisite": [], "description": "The input file was retrieved directly from source was \"cleaned\" for further processing and the glycosylation type (linkage type) was assigned using a python script [make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py] based on motif label provided by the author. " }, { "name": "python", "step_number": 2, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/mouse_glytoucan_140918_2018_10_31_02_18_55.txt", "filename": "mouse_glytoucan_140918_2018_10_31_02_18_55.txt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_protein_all.fasta", "filename": "mouse_protein_all.fasta" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/logs/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.log", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.log" } ], "prerequisite": [], "description": "The UniProtKB protein accessions were mapped to canonical accessions and the final data was processed for quality check using a python script[make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.py] and the records which fall under one or more following criteria's were flagged and eliminated (eliminated records can be accessed using the log file through Output subdomain): a. If the protein accession is not included in UniProt protein list [UniProt Nov-2017 Release] b. If the amino acid position does not match to the amino acid on the associated position on fasta sequence [UniProt Nov-2017 Release] c. If the id (UnicarbKB structure id) is not present in input file. d. If the glycosylation type (linkage type) is not retrieved through step 2. e. If a serine or threonine is reported for an N-linked glycan structure. f. If an asparagine is reported for an O-linked glycan structure. g. If the glycosylation type (linkage type) has both \"N-linked;O-linked\" assignment through step 2" } ] }, "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/blob/master/integration/", "filename": "make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py, " } }, { "uri": { "uri": "https://github.com/glygener/glygen-backend/blob/master/integration/", "filename": " make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.py" } } ] }, "version": "1.0.5", "error_domain": { "empirical_error": {}, "algorithmic_error": {}, "emperical_error": {} }, "parametric_domain": [ { "step": "", "value": "", "param": "" } ], "usability_domain": [ "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]" ], "etag": "1996b783b78e53755a752b595e130df2", "_id": { "$oid": "5c48e8d1f5c47b65ae4b5d14" }, "name": "Mouse Glycosylation Sites (UniCarbKB)" }