QSAR analysis of tyrosine kinase inhibitor using modified ant colony optimization and multiple linear regression.

Quantitative structure-activity relationship (QSAR) models of inhibiting action of some analogues of 4-(3-bromoanilino)-6,7-dimethoxyquinazoline on epidermal growth factor receptor tyrosine kinase were constructed using modified ant colony optimization (ACO) method. As a comparison to this method, the evolutionary algorithm (EA) was also tested. It has been demonstrated that the modified ACO is a useful tool for variable selection comparable to EA. In the selected descriptors, electronic descriptor sigma(Y)(-) is the most important descriptor in predicting EGFR inhibitory activity. Electron-donating groups such as Y-substituents enhance the activity as evident by negative sigma(Y)(-). In addition, for quinazoline substituents, nitro group has a large deactivating effect.