QSPR studies of PCBs by the combination of genetic algorithms and PLS analysis.

A hybrid approach that combines genetic algorithms (GA) with PLS analysis is proposed, and a modified cross-validation correlation coefficient (MCVR2) is used as fitness function. The method is applied to QSPR studies of PCBs, in comparison with class regression, and many better models are obtained for each property studied. By MCVR2, not only can the low dimensional PLS models be obtained, but also the best multiple least squares regression (MLS) models. Moreover, the results show the WHIM descriptors that contain information about the whole 3D-molecular structure are excellent descriptors for molecular modeling, but by adding some common molecular parameters representing total molecular properties the quality of the models is still improved slightly.