There are many diseases for which suitable drugs have not been identified. As the population increases and the environment gets polluted, new infections are reported. Random screening of synthesized compounds for biological activity is time consuming. QSAR has a prominent role in drug design and optimization. It is derived from the correlation between the physicochemical properties and biological activity. QSAR equations are generated using statistical methods like regression analysis and genetic function approximation. Both 2D parameters and 3D parameters are involved in generating the equation. Among several QSAR equations generated, the best ones are selected based on statistical parameters. Validation techniques usually verify the predictive power of generated QSAR equations. Once the developed QSAR model is validated to be good, the results of that model may be applied to predict the biological activity of newer analogues. This chapter illustrates the various steps in QSAR and describes the significance of statistical parameters and software used in QSAR.
A Genetic-Function-Approximation-Based QSAR Model for the Affinity of Arylpiperazines Toward α1 Adrenoceptors.