PLS-DA statistical data and confusion matrix for the 36 biostimulant samples using the 14 amino acid variables. Cross validation leave one out method was used by setting a maximum of twelve latent variables. In confusion matrix, true classes are read along the columns and estimated classes along the rows. The total accuracy was also reported. Cal: Calibration; CV: Cross Validation.

Table 2: PLS-DA statistical data and confusion matrix for the 36 biostimulant samples using the 14 amino acid variables. Cross validation leave one out method was used by setting a maximum of twelve latent variables. In confusion matrix, true classes are read along the columns and estimated classes along the rows. The total accuracy was also reported. Cal: Calibration; CV: Cross Validation.

Parameters classification			Confusion matrix
	Animal	Vegetal	Fitting
Sensitivity (Cal)	1.00	1.00	Real/predicted	Animal	Vegetal	%
Specificity (Cal)	1.00	1.00	Animal	17	0	100
Sensitivity (CV)	1.00	0.94	Vegetal	0	16	100
Specificity (CV)	0.94	1.00	Total (%)	100
Class. err (Cal)	0.00	0.00	Cross validation
Class. err (CV)	0.03	0.03	Real/predicted	Animal	Vegetal	%
RMSEC	9.98E-02	9.98E-02	Animal	17	0	100
RMSECV	0.159	0.159	Vegetal	0	16	100
Bias	0	-5.55E-17	Total (%)	100
CV Bias	-4.60E-03	-4.60E-03
R²	0.96	0.96
CV R²	0.901	0.901