Skip to main content
Figure 11 | BMC Systems Biology

Figure 11

From: Hierarchical Cluster-based Partial Least Squares Regression (HC-PLSR) is an efficient tool for metamodelling of nonlinear dynamic models

Figure 11

Test set prediction results from HC-PLSR, PLSR and OLS for the mouse ventricular myocyte. Histograms of A) R2 values and B) RMSEP values from test set predictions of the mouse ventricular myocyte state variable time series as functions of the parameters, with HC-PLSR, global polynomial PLSR and global polynomial OLS. The average values over the three data set parts (separated according to the stimulus period) are shown. In HC-PLSR, 2-20 PLS components were used in the regression models, while in PLSR 2-8 PLS components were used. The mean R2test set over all state variables was 0.98 for HC-PLSR and 0.94 for both PLSR and OLS.

Back to article page