{
    "object_id": "https://biocomputeobject.org/GLY_000335/1.11.2",
    "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": "Hepatitis C virus (genotype 1a, isolate H)",
                        "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": "external",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "HCV1a Glycosylation Sites (Literature + UniCarbKB)",
        "contributors": [
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy",
                    "contributedBy"
                ],
                "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": "UniCarbKB",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Matthew Campbell",
                "email": "m.campbell2@griffith.edu.au"
            },
            {
                "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": "2020-02-10T14:13:38.047090",
        "modified": "2020-05-04T10:54:34.390088",
        "version": "1.11.2"
    },
    "description_domain": {
        "keywords": [
            "reported glycosylation",
            "HCV"
        ],
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/hcv1a_proteoform_glycosylation_sites_literature.csv",
                        "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv",
                        "filename": "hcv1a_protein_masterlist.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.fasta",
                        "filename": "hcv1a_protein_canonicalsequences.fasta"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv",
                        "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv"
                    }
                ],
                "prerequisite": [],
                "description": "1) The data was extracted from the publications using supplemental material (Table 1,2,3). 2) The GenBank accession number (AF009606) retrieved from the paper was matched to the best hit UniProtKB Ac. (P27958) using the NCBI BLAST. 3) The glycan compositions provided by the paper were mapped to GlyTouCan Accession manually.  4) The source cell-line and mass-spectrometry data such as analyzer, chromatography, etc. were also extracted from the paper. 5) QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions and checked the validity of amino acid and glycosite position on the .fasta sequence of the 2019-09 UniProtKB release for that protein."
            }
        ]
    },
    "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 HCV1a [TaxID:1108] glycosylations sites dataset contains glycosylation sites experimentally reported on Hepatitis C Virus 1a protein. The data was extracted from publication PMID:18187336. (Iacob RE, Perdivara I, Przybylski M, Tomer KB. Mass spectrometric characterization of glycosylation of hepatitis C virus E2 envelope glycoprotein reveals extended microheterogeneity of N-glycans. J Am Soc Mass Spectrom. 2008;19(3):428\u2013444. doi:10.1016/j.jasms.2007.11.022). The glycan compositions from publication [PMID:18187336] were assigned to GlyTouCan accessions by UniCarbKB. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"
    ],
    "etag": "c5e6cfd7d87568a72c3d6e3feb4f01e9",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_masterlist.csv",
                    "filename": "hcv1a_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv",
                    "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_protein_canonicalsequences.fasta",
                    "filename": "hcv_protein_canonicalsequences.fasta"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv",
                    "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv"
                }
            }
        ]
    }
}