Linear QSAR study of Sulfonamide drugs using by imperialist competitive algorithm

Multiple linear regression (MLR) as modeling tools and Imperialist Competitive Algorithm (ICA) as optimization techniques were employed to choose the best set of descriptors for linear -log(IC50) (the empirical negative logarithm half maximal inhibitory concentration) prediction of the Sulfonamide derivatives. A high predictive ability was observed for the MLR-ICA model with the best number of empires/ imperialists (nEmp=20) and (nEmp=60) with root mean sum square errors (RMSE) of 0.03375 and 0.036665 in gas phase and in solvent, respectively. The results obtained using the MLR-ICA method indicated that the activity of the derivatives of Sulfonamide depends on different parameters such as HVcpx, RDF090u, E1v, Wap, R5e, Mor15v, MPC08, RDF115p descriptors in the gas phase and including RDCHI,MATS1v, RDF115v, RDF080v, D/Dr06, piPC05,BEHp6 and G3m descriptors in the solvent phase. It was concluded that simultaneous utilization of MLR-ICA method can lead to a more comprehensive understanding of the relation between physico-chemical, structural or theoretical molecular descriptors of drugs to their biological activities and facilitate designing of new drugs.