Therapeutically Applicable Research to Generate Effective Treatments (TARGET) Dataset for Machine Learning
Install DagsHub:
pip install dagshubTo stream this data directly on DagsHub
from dagshub.streaming import DagsHubFilesystem
fs = DagsHubFilesystem(".", repo_url="https://test.dagshub.com/DagsHub-Datasets/target-dataset")
fs.listdir("s3://gdc-target-phs000218-2-open")Description
Therapeutically Applicable Research to Generate Effective Treatments (TARGET) is the collaborative effort of a large, diverse consortium of extramural and NCI investigators. The goal of the effort is to accelerate molecular discoveries that drive the initiation and progression of hard-to-treat childhood cancers and facilitate rapid translation of those findings into the clinic. TARGET projects provide comprehensive molecular characterization to determine the genetic changes that drive the initiation and progression of childhood cancers.The dataset contains open Clinical Supplement, Biospecimen Supplement, RNA-Seq Gene Expression Quantification, miRNA-Seq Isoform Expression Quantification, miRNA-Seq miRNA Expression Quantification data from Genomic Data Commons (GDC), and open data from GDC Legacy Archive.
Additional information
Documentation
Update frequency
Genomic Data Commons (GDC) is source of truth for this dataset; GDC offers monthly data releases,
although this dataset may not be updated at every release.
Managed by
License
NIH Genomic Data Sharing Policy: https://gdc.cancer.gov/access-data/data-access-policies
