Vapour Pressure of Atmospheric Nanoparticles Using Genetic Algorithm-Partial Least Squares and Genetic Algorithm - Kernel Partial Least Squares

Abstract

The quantitative structure-property relationship (QSPR) of atmospheric nanoparticles against the comprehensive two-dimensional gas chromatography system coupled to time-of-flight mass spectrometry vapour pressure (P) was studied. A suitable set of molecular descriptors was calculated and the genetic algorithm (GA) was employed to select those descriptors that resulted in the best-fit models. The partial least squares (PLS) and the kernel partial least squares (KPLS) were utilized to construct the linear and nonlinear quantitative structure-property relationship models. The models were validated using leave-group-out cross validation (LGO-CV). The results indicate that genetic algorithm-kernel partial least squares can be used as an alternative modeling tool for quantitative structure-property relationship studies. This is the first research on the quantitative structure-property relationship of the nanoparticle compounds using the genetic algorithm-partial least squares and genetic algorithm-kernel partial least squares.