Figure 7

Clustering results used in the N-way HC-PLSR metamodelling with six clusters. A) Plot of the ${\mathit{T}}_{\text{XA,NWay}}$factors (Fac 1-Fac 3) from the global inverse metamodelling (=T _{Output,A,Inverse} ). The observations are coloured according to cluster memberships. Cluster1=blue, cluster2=red, cluster3=yellow, cluster4=green, cluster5=magenta, cluster6=cyan. X is the 3-way state variable trajectory array, while Y is the parameters. The clustering was done on the ${\mathit{T}}_{\text{XA,NWay}}$factors explaining a significant amount of the variation in the state variable space, that is the 19 first factors. B) Plot of the predicted Y - scores ${\widehat{\mathit{T}}}_{\text{YA,NWay}}$ (see Additional file 1, eq. S12c) from the global classical metamodelling, colour coded according to the cluster memberships of the observations found using T _{Output,A,Inverse} . The classification of the test set observations to be predicted in the classical metamodelling was based on ${\widehat{\mathit{T}}}_{\text{Output,A,Inverse}}$, predicted from ${\widehat{\mathit{T}}}_{\text{YA,NWay}}$ using second order polynomial OLS regression. This OLS prediction model was calibrated in the calibration step of the classical metamodelling, based on the ${\mathit{T}}_{\text{XA,NWay}}$factors from the inverse metamodelling (=${\mathit{T}}_{\text{Output,A,Inverse}}$, plotted in panel A) and calibration set ${\widehat{\mathit{T}}}_{\text{YA,NWay}}$ (plotted here). C) Circadian clock state trajectories for the observations belonging to each cluster, coloured according to cluster memberships from the inverse N-way HC-PLSR. Cluster1 = blue, cluster2 = red, cluster3 = yellow, cluster4 = green, cluster5 = magenta, cluster6 = cyan. All state variables are given in nM units.