Predicting the Mechanism of Action for Polar and Nonpolar Narcotic Compounds

Predicting the Mechanism of Action for Polar and Nonpolar Narcotic Compounds 

Using a descriptor selection procedure, we found that only three descriptors ( homo lumo nd Q ) are essential for the SVM model. To exemplify the shape of the classification hyperplane for polar and nonpolar narcotic pollutants, we selected 20 compounds (Table 7) as a test set (nonpolar compounds, class +1 polar compounds, class —1). 

The statistics for all SVM models that were considered for this example are presented in Table 8. The calibration of the SVM models was performed with the whole set of 190 compounds, whereas the prediction was tested with a leave-20%-out cross-validation method. All notations are explained in the footnote of Table 8. 

The RBF kernel (experiments 16-24), with ACp between 0.96 and 0.97, has better calibration statistics than the linear kernel, but its performance in prediction only equals that of the linear SVM. Although many tests were performed for the neural kernel (experiments 25-51), the prediction statistics are low, with ACp between 0.64 and 0.88. This result is surprising, because the tanh function gives very good results in neural networks. Even the training statistics are low for the neural kernel, with AC, between 0.68 and 0.89 

The last set of SVM models were obtained with the anova kernel (experiments 52-78), with ACp between 0.94 and 0.98. In fact, only experiment 58 has a better prediction accuracy (ACp = 0.98) than the liner SVM model from experiment 3. The linear SVM has six errors in prediction (all nonpolar compounds predicted to be polar), whereas the anova SVM has four prediction errors, also for nonpolar compounds. 

---