{
  "bco_id": "http://data.glygen.org/GLY_000626",
  "checksum": "97b86cd38e771aa090ffafc91261e8f9",
  "bco_spec_version": "1.3",
  "provenance_domain": {
    "name": "Rat Somatic Mutation",
    "version": "1.12.3",
    "created": "",
    "modified": "2022-09-06T17:46:41.941997",
    "contributors": [
      {
        "orcid": "",
        "affiliation": "The George Washington University",
        "contribution": [
          "createdBy"
        ],
        "name": "Jeet Vora",
        "email": "jeetvora@gwu.edu"
      },
      {
        "orcid": "",
        "affiliation": "The George Washington University",
        "contribution": [
          "createdBy"
        ],
        "name": "Robel Kahsay",
        "email": "rykahsay@gwu.edu"
      },
      {
        "orcid": "",
        "affiliation": "The George Washington University",
        "contribution": [
          "createdBy"
        ],
        "name": "Karina Martinez",
        "email": "karinamartinez@gwu.edu"
      }
    ],
    "license": "https://creativecommons.org/licenses/by/4.0/"
  },
  "usability_domain": [
    "This mouse glycogenes dataset is retrieved from stem cell analysis which was done with qRT-PCR analysis [PMID:18411279]. It contains a list of UniProtKB accessions full and shortened mouse[taxonomy:10090] protein names mapped to NCBI gene and MGI IDs. The GT, GH, CBM and CE groups are defined by CAZy families. Following those groups are Lectins (following Kurt Drickamer’s groupings), then several other glycan-related genes like GL (Glycolipid-related), GR (GAG-related), etc. If you use this dataset, please provide proper attribution to RefSeq, EMBL-EBI-UniProtKB and GlyGen. Cite:PMID:26553804, PMID:33237286 and PMID:31616925. The dataset can be used for obtaining UniProtKB recommended names (full and short) and HGNC gene names for UniProtKB canonical proteins. If you use this dataset, please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. This dataset can be used for obtaining proteins grouped as they are defined by CAZy. "
  ],
  "extension_domain": {
    "fhir_extension": [],
    "scm_extension": {
      "scm_repository": "",
      "scm_type": "git",
      "scm_commit": "",
      "scm_path": ""
    },
    "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": "Mus musculus",
        "category_name": "species"
      },
      {
        "category_value": "Protein",
        "category_name": "molecule"
      },
      {
        "category_value": "Glycogenes",
        "category_name": "tags"
      },
      {
        "category_value": "csv",
        "category_name": "file_type"
      },
      {
        "category_value": "Reviewed",
        "category_name": "status"
      },
      {
        "category_value": "internal",
        "category_name": "scope"
      }
    ]
  },
  "description_domain": {
    "keywords": [
      "glycogenes"
    ],
    "pipeline_steps": [
      {
        "step_number": 1,
        "name": "make-protein-dataset.py",
        "description": "The script maps the gene ids and gene names from the source file to UniProtKB canonical accession and then then adds the protein recommneded name and alternative gene names. The script extracts gene identifier and group fields as is from the source input file. The script filters entries that are not mapped in the log file.",
        "version": "",
        "prerequisite": [],
        "input_list": [
          {
            "access_time": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/source/mouse_glycogenes.csv",
            "filename": "mouse_glycogenes.csv"
          },
          {
            "access_time": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_masterlist.csv",
            "filename": "mouse_protein_masterlist.csv"
          },
          {
            "access_time": "",
            "sha1_chksum": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_genenames_uniprotkb.csv",
            "filename": "mouse_protein_genenames_uniprotkb.csv"
          },
          {
            "access_time": "",
            "sha1_chksum": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_recnames.csv",
            "filename": "mouse_protein_recnames.csv"
          },
          {
            "access_time": "",
            "sha1_chksum": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_xref_geneid.csv",
            "filename": "mouse_protein_xref_geneid.csv"
          }
        ],
        "output_list": [
          {
            "access_time": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_glycogenes.csv",
            "filename": "mouse_protein_glycogenes.csv"
          },
          {
            "access_time": "",
            "sha1_chksum": "",
            "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/logs/mouse_protein_glycogenes.log",
            "filename": "mouse_protein_glycogenes.log"
          }
        ]
      }
    ]
  },
  "execution_domain": {
    "script": [
      {
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py",
          "filename": "make-protein-dataset.py"
        }
      }
    ],
    "script_driver": "manual",
    "software_prerequisites": [
      {
        "name": "Python",
        "version": "2.7.5",
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://www.python.org/download/releases/2.7.5/"
        }
      }
    ],
    "external_data_endpoints": [],
    "environment_variables": {}
  },
  "parametric_domain": [
    {
      "param": "",
      "value": "",
      "step": ""
    }
  ],
  "io_domain": {
    "input_subdomain": [
      {
        "uri": {
          "access_time": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/source/mouse_glycogenes.csv",
          "filename": "mouse_glycogenes.csv"
        }
      },
      {
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_genenames_uniprotkb.csv",
          "filename": "mouse_protein_genenames_uniprotkb.csv"
        }
      },
      {
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_recnames.csv",
          "filename": "mouse_protein_recnames.csv"
        }
      },
      {
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_xref_geneid.csv",
          "filename": "mouse_protein_xref_geneid.csv"
        }
      },
      {
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_masterlist.csv",
          "filename": "mouse_protein_masterlist.csv"
        }
      }
    ],
    "output_subdomain": [
      {
        "mediatype": "csv",
        "uri": {
          "access_time": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_glycogenes.csv",
          "filename": "mouse_protein_glycogenes.csv"
        }
      },
      {
        "mediatype": "txt",
        "uri": {
          "access_time": "",
          "sha1_chksum": "",
          "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/logs/mouse_protein_glycogenes.log",
          "filename": "mouse_protein_glycogenes.log"
        }
      }
    ]
  },
  "error_domain": {
    "empirical_error": {},
    "algorithmic_error": {},
    "emperical_error": {}
  }
}