QSAR Models to Predict Activity of Camptothecin Analogues as Antitumor Agents Using Genetic Algorithm-Partial Least Square Method

A quantitative structure-activity relationship (QSAR) modeling was carried out for the camptothecin (CPT) as antitumor agent derivatives. The Electric-field gradient (EFG) tensors were used as a feature selection (descriptor selection) and model development method. Modeling of the relationship between selected molecular descriptors and EFG tensors was achieved by GA-nonlinear partial least square (PLS) method. To predict properties by the QSAR models were in good agreement with the corresponding Computational values. EFG tensors are related to nuclear quadrupole resonance (NQR) parameters Comparison of the results obtained from models, as well as, PLS models were constructed for some specific families based on their chemical structures. These predictive models should be useful to rapidly identify analyze the influence of nitrogen nucleus the position of the heterocycles rings.