{ "object_id": "https://biocomputeobject.org/GLY_000479/1.11.2", "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": "Reviewed", "category_name": "status" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "SARS coronavirus (SARS-CoV-2 or 2019-nCoV)", "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 [SARS CoV 2 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": [ "contributedBy" ], "name": "Matthew Campbell ", "email": "m.campbell2@griffith.edu.au" }, { "affiliation": "George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@email.gwu.edu" }, { "affiliation": "Georgetown University", "contribution": [ "contributedBy" ], "name": "Nathan Edwards", "email": "Georgetown University" }, { "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": "2020-04-20T16:02:18.234465", "modified": "2020-04-23T10:50:25.427448", "version": "1.11.2" }, "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/crispin_azadi_yang_covid.csv", "filename": "crispin_azadi_yang_covid.csv" }, { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv", "filename": "sarscov2_protein_masterlist.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/sarscov2_protein_allsequences.fasta", "filename": "sarscov2_protein_allsequences.fasta" }, { "uri": "https://data.glygen.org/ln2wwwdata/source/aadict.csv", "filename": "aadict.csv" }, { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv", "filename": "glycan_xref_unicarbkb.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log", "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log" }, { "uri": "https://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log", "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log" }, { "uri": "http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv" } ], "prerequisite": [], "description": "The input file was received directly from the provider (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 (sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (sarscov2_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_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": "", "param": "", "value": "" } ], "usability_domain": [ "List of SARS coronavirus (SARS-CoV-2 or 2019-nCoV) [taxid:2697049] 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/GLYDS000434)" ], "etag": "0ace549b1721c6af7d3f381260833a2c", "io_domain": { "input_subdomain": [ { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt" } }, { "uri": { "filename": "known_legacy_dbogap_dbogap2_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv" } }, { "uri": { "filename": "known_34106099_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv" } }, { "uri": { "filename": "known_unicarbkb_glycomics_study.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv" } }, { "uri": { "filename": "fuzzy_legacy_cph_start_end_positions.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv" } }, { "uri": { "filename": "known_legacy_cph_single_positions.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv" } }, { "uri": { "filename": "unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv" } }, { "uri": { "filename": "known_legacy_human_mouse_rat_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv" } }, { "uri": { "filename": "known_34004174_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv" } }, { "uri": { "filename": "known_33806155_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv" } }, { "uri": { "filename": "known_33167210_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv" } }, { "uri": { "filename": "known_legacy_reis_gastric_ags.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv" } }, { "uri": { "filename": "known_legacy_sarscov2_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv" } }, { "uri": { "filename": "unknown_20131323_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv" } }, { "uri": { "filename": "fuzzy_simplecell_all_glygen_qc.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv" } }, { "uri": { "filename": "mixed_34089345_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv" } }, { "uri": { "filename": "known_33064451_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv" } }, { "uri": { "filename": "unknown_33993882_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv" } }, { "uri": { "filename": "fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv" } }, { "uri": { "filename": "unknown_34083726_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv" } }, { "uri": { "filename": "known_legacy_larsson_xyl.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv" } }, { "uri": { "filename": "unknown_34327564_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv" } }, { "uri": { "filename": "fuzzy_legacy_qin_oglanac.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv" } }, { "uri": { "filename": "unknown_34191522_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv" } }, { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt" } }, { "uri": { "filename": "known_legacy_dbogap_dbogap2_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv" } }, { "uri": { "filename": "known_34106099_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv" } }, { "uri": { "filename": "known_unicarbkb_glycomics_study.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv" } }, { "uri": { "filename": "fuzzy_legacy_cph_start_end_positions.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv" } }, { "uri": { "filename": "known_legacy_cph_single_positions.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv" } }, { "uri": { "filename": "unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv" } }, { "uri": { "filename": "known_legacy_human_mouse_rat_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv" } }, { "uri": { "filename": "known_34004174_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv" } }, { "uri": { "filename": "known_33806155_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv" } }, { "uri": { "filename": "known_33167210_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv" } }, { "uri": { "filename": "known_legacy_reis_gastric_ags.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv" } }, { "uri": { "filename": "known_legacy_sarscov2_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv" } }, { "uri": { "filename": "unknown_20131323_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv" } }, { "uri": { "filename": "fuzzy_simplecell_all_glygen_qc.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv" } }, { "uri": { "filename": "mixed_34089345_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv" } }, { "uri": { "filename": "known_33064451_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv" } }, { "uri": { "filename": "unknown_33993882_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv" } }, { "uri": { "filename": "fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv" } }, { "uri": { "filename": "unknown_34083726_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv" } }, { "uri": { "filename": "known_legacy_larsson_xyl.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv" } }, { "uri": { "filename": "unknown_34327564_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv" } }, { "uri": { "filename": "fuzzy_legacy_qin_oglanac.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv" } }, { "uri": { "filename": "unknown_34191522_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv" } }, { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt" } }, { "uri": { "filename": "known_legacy_dbogap_dbogap2_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv" } }, { "uri": { "filename": "known_34106099_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv" } }, { "uri": { "filename": "known_unicarbkb_glycomics_study.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv" } }, { "uri": { "filename": "fuzzy_legacy_cph_start_end_positions.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv" } }, { "uri": { "filename": "known_legacy_cph_single_positions.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv" } }, { "uri": { "filename": "unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv" } }, { "uri": { "filename": "known_legacy_human_mouse_rat_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv" } }, { "uri": { "filename": "known_34004174_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv" } }, { "uri": { "filename": "known_33806155_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv" } }, { "uri": { "filename": "known_33167210_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv" } }, { "uri": { "filename": "known_legacy_reis_gastric_ags.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv" } }, { "uri": { "filename": "known_legacy_sarscov2_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv" } }, { "uri": { "filename": "unknown_20131323_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv" } }, { "uri": { "filename": "fuzzy_simplecell_all_glygen_qc.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv" } }, { "uri": { "filename": "mixed_34089345_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv" } }, { "uri": { "filename": "known_33064451_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv" } }, { "uri": { "filename": "unknown_33993882_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv" } }, { "uri": { "filename": "fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv" } }, { "uri": { "filename": "unknown_34083726_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv" } }, { "uri": { "filename": "known_legacy_larsson_xyl.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv" } }, { "uri": { "filename": "unknown_34327564_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv" } }, { "uri": { "filename": "fuzzy_legacy_qin_oglanac.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv" } }, { "uri": { "filename": "unknown_34191522_glygen.csv", "uri": "https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv" } }, { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv", "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv" } } ] } }