SDEP value

Table 7.3. External SDEP values obtained for the ER different test sets. ...

A test set of 330 compounds, obtained from different literature sources, was used for external validation of the VolSurf equation. Test set compounds are reported in Fig. 8.4 and listed together with their experimental and calculated logP values in Table 8.3 the SDEP value amounts to 0.81 this closely resembles... 

During 1994-1997 the Sdep values were higher than CLmaxS values at about one third of terrestrial Korean ecosystems (38%). Among them, the ExS values were in the range 176-500 eq/ha/yr for 16.1% of total number of ecosystems, in the range of 500-1000 eq/ha/yr were for 7.9%, in the range of 1000-2000 eq/ha/yr were 10.7% and the values even higher than 2000 eq/ha/yr were found for 3.5% of Korean ecosystems. 

Figure 4 Predictive power analysis actual versus predicted pK, (p,M) activities for 17 aromatase inhibitors, based on the 33-compound model with the lowest PRESS and SDEP values (the two-component model). Data modified from Ref. 96.

SDEP (the standard deviation of the error of predictions) corresponds to jpress but the number of degrees of freedom is not considered in the calculation of the SDEP value. The smallest -spress or SDEP value should be taken as the criterion for the optimum number of components. Alternatively, an increase of the value by a certain percentage, e.g., 5%, may be defined as the criterion to accept a further PLS component. As long as only significant components are extracted in the PLS analysis, PRESS, SDEP and Jpress will decrease if too many components are derived, overprediction results and PRESS, SDEP and spress increase. 

The LOO cross-validated q oo values for the initial models was 0.875 using the water probe and 0.850 using the methyl probe. The application of the SRD/FFD variable selection resulted in an improvement of the significance of both models. The analysis yielded a correlation coefficient with a cross-validated q Loo of 0.937 for the water probe and 0.923 for the methyl probe. In addition we tested the reliability of the models by applying leave-20%-out and leave-50%-out cross-validation. Both models are also robust, indicated by high correlation coefficients of = 0.910 (water probe, SDEP = 0.409) and 0.895 (methyl probe, SDEP = 0.440) obtained by using the leave-50%-out cross-validation procedure. The statistical results gave confidence that the derived model could also be used for the prediction of novel compounds. 

For each reduced data set, the model is calculated, and responses for the deleted objects are predicted from the model. The squared differences between the true response and the predicted response for each object left out are added to PRESS (predictive residual sum of squares). From the final PRESS, the (or R cv) and SDEP (standard deviation error of prediction) values are usually calculated [Cruciani et ah, 1992]. 

Afzelius et al. [112] applied GRIND descriptors to generate quantitative and qualitative models for CYP2C9 inhibition. The resulting PLS model gave loo (Jlgo values of 0.60 and 0.57, respectively. Application to an external test set of 12 compounds gave a standard deviation of prediction errors (SDEP) of 0.37 log units ... 

For q calculations, the following parameters were used for the external set based index, 7, F -" = 1.951 (with SD = 3.246), and, for the training set based index, q], Y" "" = 0.211 (with SD = 1.003). SDEP subscripted indices are as follows E, external set 1, leave-one-out 5, five groups random model 2, two groups random model. Internal PRESS values not given because SDEP = (PRESS/N) -. No. is the number of PLS components other abbreviations are given in the text. Data from Ref. 96. 

---