{ "object_id": "https://biocomputeobject.org/GLY_000024/v-2.12.1", "spec_version": "1.3.0", "etag": "133a99273038407039aece91d3968e46", "provenance_domain": { "name": "Human Cancer Mutation", "version": "v-2.12.1", "license": "https://creativecommons.org/licenses/by/4.0/", "created": "2019-01-23T17:21:05.891293", "modified": "2026-07-08T10:52:25.123Z", "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "email": "jeetvora@gwu.edu", "contribution": [ "createdBy" ] }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "BioMuta - The George Washington University", "contribution": [ "importedFrom" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Luke Johnson", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "luke.johnson@email.gwu.edu" }, { "name": "Urnisha Bhuiyan", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "sbhuiyan28@email.gwu.edu" }, { "name": "Cyrus Au-Yeung", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "cyruschauyeung@gwu.edu" }, { "name": "Kate Warner", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "k.warner1@gwu.edu" }, { "name": "Mariia Kim", "affiliation": "The George Washington University", "email": "maria.kim@gwu.edu", "contribution": [ "createdBy" ] } ] }, "usability_domain": [ "The Human Cancer Mutation dataset contains Homo sapiens [taxid:9606] mutation data from the BioMuta database (https://hive.biochemistry.gwu.edu/biomuta). The BioMuta pipeline documentation can be found on the HIVE Lab Wiki: https://hivelab.biochemistry.gwu.edu/wiki/BioMuta_pipeline_README.", "The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.", "BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.", "The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset, please provide proper attribution to BioMuta and GlyGen.", "Note that the mutations in GlyGen are annotated based on passing of one or more filter criteria.", "Filter criterion 1 - Positive Patients Frequency Ratio \u2265 1.0%", "Filter criterion 2 - Presence of mutation in \u2265 3 cancer types", "Filter criterion 3 - Positive Patients count \u2265 10 patients", "Filter criterion 4 - Mutation reported and annotated in number of databases", "Filter criterion 5 - Mutation mined from literature using literature mining tools (human_protein_mutation_literature.csv)", "Filter criterion 6 - At least one glyco-relevant mutation effect i.e. N-glycosylation sequon loss, N-glycosylation sequon gain or O-glycosylation site loss.", "If there is also a germline mutation reported in dbSNP, the rsid is also shown", "Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim." ], "description_domain": { "pipeline_steps": [ { "name": "make-protein-dataset.py", "step_number": 1, "input_list": [], "description": "The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias", "prerequisite": [], "output_list": [] } ], "keywords": [ "single-nucleotide variations (nsSNVs)", "cancer mutations", "BioMuta", "disease" ] }, "parametric_domain": [ { "value": "" } ], "io_domain": { "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_protein_mutation_cancer.csv", "filename": "human_protein_mutation_cancer.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_protein_mutation_cancer.stat.csv", "filename": "human_protein_mutation_cancer.stat.csv" } } ], "input_subdomain": [ { "uri": { "filename": "glycan_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/glycan_masterlist.csv" } }, { "uri": { "filename": "human_protein_gene_groups.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_protein_gene_groups.csv" } }, { "uri": { "filename": "human_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_protein_masterlist.csv" } }, { "uri": { "filename": "human_protein_mutation_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_protein_mutation_literature.csv" } }, { "uri": { "filename": "protein_disease_idmap.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/protein_disease_idmap.csv" } }, { "uri": { "filename": "aadict.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/misc/aadict.csv" } }, { "uri": { "filename": "biomuta.csv", "uri": "https:/data.glygen.org/ln2downloads/biomuta/2025_05_27/biomuta.csv" } }, { "uri": { "filename": "clinical_information.csv", "uri": "https:/data.glygen.org/ln2downloads/biomuta/2025_05_27/clinical_information.csv" } }, { "uri": { "filename": "dbSNP-homo-sapiens.tsv", "uri": "https:/data.glygen.org/ln2downloads/ebi/2026_06_13/dbSNP-homo-sapiens.tsv" } } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/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": "Homo sapiens", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Somatic Cancer Mutations", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" }, { "category_name": "file_category", "category_value": "mutation_" } ] } } ], "error_domain": {} }