/metabric_data

Public breast cancer dataset with competing risks ready for machine learning applications.

Primary LanguageROtherNOASSERTION

METABRIC Breast Cancer Competing Risk Dataset

A slightly curated and processed version of the METABRIC dataset found on cBioPortal. The code for querying cBioPortal, cleaning the clinical and mutation data, preparing outcomes, and creating the test/train split is found in create_files.R.

Files

metabric_clinical.tsv
metabric_mutations.tsv
metabric_survival.tsv

References