Copy number data for the training set
A matrix with 714 rows and 997 columns. Rows are features and columns are training samples.
Each row corresponds to one copy number feature for all samples in the training set. Note that it includes all features in the classifier. Note also that, depending on the data available and the type of matching (gene or probe) only some of the features will be used.
Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.