TABLE 4.

Prediction accuracies for seven end-use quality traits using four different uni- and multi-trait genomic selection models for the two locations across the years, namely, Pullman and Lind using the cross-validation approach.

		Uni-trait models				Multi-trait models
Location	Trait	GBLUP	BayesB	RF	MLP	GBLUP	BayesB	RF	MLP
Pullman	GPC	0.55	0.54	0.59	0.60	0.59	0.50	0.76	0.72
	FPROT	0.58	0.58	0.61	0.62	0.64	0.61	0.66	0.79
	FASH	0.55	0.59	0.58	0.59	0.63	0.58	0.62	0.63
	MSCOR	0.58	0.52	0.60	0.63	0.66	0.57	0.64	0.68
	FYELD	0.71	0.64	0.76	0.75	0.68	0.65	0.75	0.73
	CODI	0.67	0.67	0.69	0.69	0.64	0.61	0.67	0.64
	FSDS	0.67	0.66	0.69	0.70	0.71	0.72	0.73	0.77
Lind	GPC	0.51	0.51	0.54	0.55	0.55	0.53	0.58	0.62
	FPROT	0.48	0.46	0.51	0.53	0.53	0.50	0.56	0.54
	FASH	0.51	0.44	0.54	0.56	0.59	0.40	0.62	0.60
	MSCOR	0.48	0.53	0.50	0.52	0.57	0.57	0.55	0.63
	FYELD	0.64	0.58	0.68	0.67	0.66	0.59	0.69	0.70
	CODI	0.56	0.54	0.57	0.58	0.55	0.54	0.58	0.59
	FSDS	0.59	0.59	0.62	0.63	0.64	0.62	0.67	0.64
Average		0.58	0.56	0.61	0.62	0.62	0.57	0.65	0.66

Highest prediction accuracies are bolded for each trait.