Application of Wavelet and Genetic Algorithms for QSAR Study on 5-Lipoxygenase Inhibitors and Design New Compounds

Abstract

A quantitative structure-activity relationship (QSAR) modeling was carried out for the prediction of inhibitory activity of 1-phenyl[2H]-tetrahydro-triazine-3-one analogues as inhibitors of 5-lipoxygenase. Partial least squares (PLS) algorithm was employed to model the relationships between molecular descriptors and inhibitory activity of molecules using the genetic algorithm (GA) method as variable selection tool. Pre-processing methods such as wavelet transform (WT) were also used to enhance the predictive power of multivariate calibration methods. To evaluate the models applied in this study (PLS, GA-PLS and WT-GA-PLS), the inhibitory activities of several compounds, not included in the modeling procedure, were predicted. The results of models showed high prediction ability with root mean square error of prediction 0.194, 0.161 and 0.140 for PLS, GA-PLS and WT-GA-PLS, respectively. The WT-GA-PLS method was employed to predict the inhibitory activity of the new inhibitor derivatives.

Comparative QSAR modeling of 2‐phenylindol derivatives for predicting the anticancer activity using genetic algorithm multiple linear regression and back‐propagation‐artificial neural network techniques

“…The GA is a random‐based classical evolutionary algorithm for solving both constrained and unconstrained optimization problems [33–38] based on the Darwin's evolutionary theory [39–42].…”

Comparison between genetic algorithm‐multiple linear regression and back‐propagation‐artificial neural network methods for predicting the LD50 of organo (phosphate and thiophosphate) compounds

“…The parameters used in the GA setup of the MATLAB 2010 program based on Leardiʼ flowchart were 200 generations with 30 chromosomes, mutation probability of 1%, and cross‐over probability of 50% in 1,000. The theory and explanation of this method has been described in quite a number of publications …”