{ "io_domain": { "input_subdomain": [ { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/source/mouse_2019_07_16_05_30_05.csv", "filename": "mouse_2019_07_16_05_30_05.csv" } }, { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv", "filename": "mouse_protein_idmapping.csv" } }, { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/source/classification.tsv", "filename": "classification.tsv" } }, { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv", "filename": "glycan_properties.tsv" } }, { "uri": { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta", "filename": "mouse_protein_allsequences.fasta" } }, { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/source/aadict.csv", "filename": "aadict.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.1.log" } }, { "mediatype": "csv", "uri": { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.2.log" } }, { "mediatype": "csv", "uri": { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.stats.csv" } }, { "mediatype": "csv", "uri": { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv" } } ] }, "spec_version": "1.3.0", "object_id": "https://biocomputeobject.org/GLY_000041/1.4.5", "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" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Mus musculus", "category_name": "species" }, { "category_value": "UniCarbKB glycosylation sites", "category_name": "tags" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "provenance_domain": { "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Glycosylation sites - UniCarbKB [Mouse proteins]", "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": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@email.gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Xavier Holmes", "email": "xavierh@gwu.edu" }, { "affiliation": "Georgetown University", "contribution": [ "authoredBy" ], "name": "Nathan Edwards", "email": "Georgetown University" } ], "created": "2019-01-23T17:21:05.908793", "modified": "2019-09-12T12:45:58.215607", "version": "1.4.5" }, "description_domain": { "keywords": [ "proteins", "canonical", "glycosylation sites", "glycan", "UniCarbKB", "GlyTouCan" ], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "step_number": 1, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/source/mouse_2019_07_16_05_30_05.csv", "filename": " mouse_2019_07_16_05_30_05.csv" }, { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv", "filename": "mouse_protein_idmapping.csv" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/classification.tsv", "filename": "classification.tsv" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv", "filename": "glycan_properties.tsv" }, { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta", "filename": "mouse_protein_allsequences.fasta" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/aadict.csv", "filename": "aadict.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb.1.log", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.1.log" }, { "uri": "https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb.2.log", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.2.log" }, { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv" } ], "prerequisite": [], "description": "The input file (mouse_2019_07_16_05_30_05.csv ;for script:mouse_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (mouse_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The script additionally implements 10 QC checks. Any row that falls for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (mouse_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid. " } ] }, "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": "", "value": "", "param": "" } ], "usability_domain": [ "List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007)." ], "etag": "", "_id": { "$oid": "5c48e8d1f5c47b65ae4b5d14" } }