Nitrogen Subset

For the ionizable basic nitrogen subset, all 544 molecules were protonated with a formal charge on the basic nitrogen. They were divided into a training set (518 compounds) and a test set (26 molecules). To select the test set, the dataset was divided into three groups according to the activity value of pIC50 (2.5 1 l -0.5  

PLS analysis was performed on the reduced set to identify a correlation between the complete set of variables and the activity data. The ALMOND program kept 624 active variables out of a total of 750 variables after filtering out descriptors with no variability. The 45 compounds with two basic nitrogen atoms were proton-ated on just one of the two basic centers. For these compounds, two models were built using one of the two isomers at a time. The isomer that produced the model with the best r was chosen. The PLS analysis resulted in a model with three LVs and r = 0.77. The cross validation of the model by the LOO method yielded q values of 0.74. As shown in Table 9.2, the GRIND descriptors that had high coefficients in the PLS model were 11-36, 44-58, 12-41, 13-40, 14-47, 24-52, and 34-49. 

---

NH O and NH O). Because there are significant differences between covalent and van der Waals radii of oxygen and nitrogen atoms, the relationships between optimum energy and optimum distances were sought separately for the three above-mentioned subsets [48]. Those relationships were not expected to be linear because energy values approach zero as distance increases. In that study a sigmoid function was used ... 

The proton affinities (PA) of two restricted subsets of amines were correlated directly with inductive and polarizability effect parameters, respectively (Figs. 19 and 22). These can be combined with data on other hetero-substituted amines to give a set of 80 amines of different skeletal and substitution types (e.g. Fig. 24). In this and all other systems (below), a residual electronegativity value, %l2, (Eq. 5) derived from those of the atoms of the first, 1, and second, 2, sphere neighbors of the nitrogen atom is preferred as a measure of the inductive effect49). 

We may suppose that not all 600 wavelengths are useful for the prediction of nitrogen contents. A variable selection method called genetic algorithm (GA, Section 4.5.6) has been applied resulting in a subset with only five variables (wavelengths). Figure 1.3c and d shows that models with these five variables are better than models... 

The high contribution of carbon and nitrogen elements as the first atoms of R R5 substituents leads to average interatomic distances D2, D3, D5, D6 and D7 which are close to the values of almost single N—C and/or C—C bond lengths. However, any evaluation of the substituent effects on the bond lengths can be carried out only after division of the set S into subsets with restrictions concerning the first atoms of R R5 substituents. 

---