Application of MIA-QSAR Method for Study of Benzamidin Derivatives and Design of New Compounds

Malaria is known as an infectious disease that is transmitted from the parasite anopheles mosquitoes from the plasmodium species. Nowadays, this disease is a serious problem around the world, which imposes many costs for treatment to countries. Therefore, the design of new drugs for this disease is one of the serious concerns of chemical researchers and pharmacists. In this paper, quantitative structure-activity relationship (QSAR) analysis has been carried out for the prediction of inhibitory activity of a set of Benzamidin compounds. In this paper, we studied the effect of variable selection by application of genetic algorithms (GAs) for the PLS model. The GAs is very useful in the variable selection in modeling and selecting the subset of pixels with the low prediction error. We applied to orthogonal pixel correction (OPC) as pre-processing methods. These models were applied for the prediction of the molecules inhibition, which were not in the modeling procedure. The resulting model showed a high predictive ability with the root mean square error of prediction (RMSEP) of 0.3464 for PLS and 0.1986 for GA-PLS and 0.7550 for OPC-GA-PLS models, respectively. Finally, the proposed QSAR model with the OPC-GA-PLS method was used to predict the inhibitory activity of the new compounds.