Multiclass Prediction with Partial Least Square Regression for Gene Expression Data: Applications in Breast Cancer Intrinsic Taxonomy

Table 6

Compositions and weight vectors of five PLS-regressions for each molecular subtype.

Basal-like		HER2-enriched		Luminal-A		Luminal-B		Normal breast-like
ANLN	0.271	ACTR3B	−0.316	BIRC5	−0.299	BCL2	−0.325	CCNB1	−0.272
CEP55	0.271	BAG1	−0.083	CDCA1	−0.294	CDH3	−0.667	CDC6	−0.241
ESR1	−0.319	BLVRA	0.317	CENPF	−0.288	CXXC5	0.484	KRT14	0.350
FOXA1	−0.417	CCNE1	−0.067	EXO1	−0.293	EGFR	−0.316	KRT17	0.241
FOXC1	0.370	CDC20	−0.069	MAPT	0.352	KIF2C	−0.050	KRT5	0.276
GPR160	−0.297	ERBB2	0.452	MYBL2	−0.328	MDM2	0.027	MLPH	0.376
KNTC2	0.303	FGFR4	0.365	NAT1	0.421	MKI67	−0.136	MMP11	−0.404
MELK	0.270	GRB7	0.470	PTTG1	−0.299	ORC6L	−0.049	RRM2	−0.359
MIA	0.296	MYC	−0.390	SLC39A6	0.339	PR	−0.143	TYMS	−0.286
TMEM45B	−0.323	SFRP1	−0.343	UBE2C	−0.296	PHGDH	−0.529	UBE2T	−0.374