Table 1.

Validation and discovery sets used in this study.

Data type	Data portal	“Omic” level	Number of basal samples	Number of non-basal samples	Set type
Gene expression levels	TCGA	Transcriptomic	179	852	Discovery
Gene expression levels	METABRIC	Transcriptomic	331	1655	Validation
Protein expression levels	CPTAC	Proteomic	19	58	Validation
Protein expression levels	TCGA	Proteomic	160	777	Validation