{ "object_id": "https://biocomputeobject.org/GLY_001046/v-2.12.1", "spec_version": "1.3.0", "etag": "4168ca2ddd9e036ea0b703f213fd2ef0", "provenance_domain": { "name": "Human ccRCC Glycoproteomics (ML Ready)", "version": "v-2.12.1", "license": "https://creativecommons.org/licenses/by/4.0/", "created": "2024-06-28T06:27:01", "modified": "2024-07-23T00:48:08.852Z", "contributors": [ { "name": "Karina Martinez", "affiliation": "The George Washington University", "email": "karinamartinez@gwu.edu", "contribution": [ "createdBy", "curatedBy" ] } ] }, "usability_domain": [ "The Human Glycosylation Sites (PDC) dataset contains intact glycopeptide abundances, biospecimen and clinical metadata from Homo sapiens (taxid:9606) clear cell renal cell carcinoma (ccRCC) tumor and normal adjacent tissues collected by the CPTAC program and can be used to stratify risk groups of ccRCC patients. The data was retrieved from the Proteomic Data Commons (PDC) and can be accessed at https://proteomic.datacommons.cancer.gov/pdc/study/PDC000471. The abundances and clinical features were combined and cleaned by the GlyGen team to make ready for machine learning algorithms. If you use this dataset please provide proper attribution to the source publication [1], PDC and GlyGen.", "References: 1) Lih TM, Cho KC, Schnaubelt M, Hu Y, Zhang H. Integrated glycoproteomic characterization of clear cell renal cell carcinoma. Cell Rep. 2023 May 30;42(5):112409. doi: 10.1016/j.celrep.2023.112409. Epub 2023 Apr 18. PMID: 37074911; PMCID: PMC10247542.", "Content: This dataset consists of 183 instances with 11103 columns. Columns 1-10815 contain glycopeptide abundances with missing values imputed for intact glycopeptides quantified in >50% of the samples using DreamAI (https://github.com/WangLab-MSSM/DreamAI). A description of key biospecimen and clinical headers follows. tissue type: Normal or Tumor. cause of death: Cancer related, Infection, Unknown. days to death: Days to death after resection. vital status: Alive or Dead. last known disease status: With tumor, Tumor free or Unknown tumor status. progression or recurrence: Yes, No or Not Reported. disease response: PD-Progressive Disease or CR-Complete Response. ", "Processing scripts, exploratory data analysis and models trained on this dataset can be found at https://github.com/glygener/glygen-machine-learning/tree/main/pdc_ccrcc" ], "description_domain": { "pipeline_steps": [ { "step_number": 1, "input_list": [ { "filename": "ccRCC_TMT_intact glycopeptide_abundance_MD-MAD_50percentQuant_imputed.tsv", "uri": "https://data.glygen.org/ln2downloads/v-2.12.1/current/ccRCC_TMT_intact%20glycopeptide_abundance_MD-MAD_50percentQuant_imputed.tsv" }, { "filename": "PDC_study_biospecimen_09182023_104440.tsv", "uri": "https://data.glygen.org/ln2downloads/v-2.12.1/current/PDC_study_biospecimen_09182023_104440.tsv" }, { "filename": "PDC_study_clinical_09182023_105327.tsv", "uri": "https://data.glygen.org/ln2downloads/v-2.12.1/current/PDC_study_clinical_09182023_105327.tsv" }, { "filename": "PDC_study_clinical_exposure_09182023_105327.tsv", "uri": "https://data.glygen.org/ln2downloads/v-2.12.1/current/PDC_study_clinical_exposure_09182023_105327.tsv" }, { "filename": "PDC_study_clinical_followup_09182023_105327.tsv", "uri": "https://data.glygen.org/ln2downloads/v-2.12.1/current/PDC_study_clinical_followup_09182023_105327.tsv" } ], "name": "https://github.com/glygener/glygen-machine-learning/blob/main/pdc_ccrcc/ccrcc_preprocessing.py", "description": "Processing script that formats the data and combines abundance, biospecimen and clinical data into one file.", "output_list": [ { "filename": "human_proteoform_ml_ready_pdc_ccrcc.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_proteoform_ml_ready_pdc_ccrcc.csv" } ], "prerequisite": [] } ], "keywords": [ "N-linked glycosylation", "glycoproteomics", "clear cell renal cell carcinoma", "PDC", "Machine Learning", "Data Science", "Artificial Intelligence", "AI" ] }, "parametric_domain": [ { "value": "" } ], "io_domain": { "input_subdomain": [], "output_subdomain": [ { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_proteoform_ml_ready_pdc_ccrcc.csv", "filename": "human_proteoform_ml_ready_pdc_ccrcc.csv" }, "mediatype": "csv" }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/human_proteoform_ml_ready_pdc_ccrcc.stat.csv", "filename": "human_proteoform_ml_ready_pdc_ccrcc.stat.csv" } } ] }, "execution_domain": { "script": [ { "uri": { "filename": "ccrcc_preprocessing.py", "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/ccrcc_preprocessing.py" } } ], "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/1.1.0/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": "Homo sapiens", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Glycosylation Sites ccRCC (PDC)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Machine Learning", "category_name": "usability" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" }, { "category_name": "file_category", "category_value": "others" } ] } } ], "error_domain": {} }