Fig. 3
An orthogonal projection to latent structures discriminant analysis (OPLS-DA) model for data processing of leaf extracts of the MgSO4 control vs. FlgII-28 treatment at the 24 h incubation. A Scores plot showing group separation of control vs. treated (FlgII− 24 - purple vs. MgSO4 − 24 - blue). The calculated model yielded R2X (cum) = 54.5 %, R2Y (cum) = 99.2 % and Q2 (cum) = 96.7 %. The goodness-of-fit parameters for the OPLS model, R2X and R2Y, represent the fraction of the variance of the x and y variable explained by the model, while Q2Y suggests the predictive performance of the model. Model validation by 7-fold cross-validated analysis of variance (CV-ANOVA, [19]) was statistically significant with p-value = 1.636 × 10− 9. B The corresponding OPLS-DA loadings S-plot. Variables at the extremes of the loadings S-plot (|p(corr)| of ≥ 0.5; |(p1)| ≥ 0.05) represent possible discriminating variables. C A receiver operating characteristic (ROC) curve summarizing the selective ability of the binary classifier (S-plot), with a classifier having a perfect discrimination (top left corner) to indicate 100 % sensitivity and specificity. D The response permutation test plot (n = 100) for the OPLS-DA model