GA Strategy for Variable Selection in QSAR Studies: GA-Based Region Selection for CoMFA Modeling

Abstract

A novel approach using a genetic algorithm (GA) for variable selection in comparative molecular field analysis (CoMFA) was developed. This approach is named GA-based region selection (GARGS) since the regularly splitting regions in 3D space are used as variables instead of each field variable. GARGS was applied to the data set of polychlorinated dibenzofurans (PCDF) as a test example. The number of field variables was reduced from 1275 to 43, and the values of cross-validated r2(q2) indicating the internal predictivity of the model equation was increased from 0.88 to 0.95 by GARGS. The structural requirements for the PCDF molecules could be easily estimated from the coefficient contour maps of the simplified CoMFA model equation. These structural requirements were consistent with the result from the previous studies, and the utility of GARGS was demonstrated.