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

摘要

The quantitative structure-property relationship (QSPR) of atmospheric nanoparticles against the comprehensive two-dimensional gaschromatography 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 partialleast squares (PLS) and the kernel partial least squares (KPLS) were utilized to construct the linear and nonlinear quantitative stmcture-property relatioriship models. The models were validated using leave-group-out cross validation (LGO-CV). The results indicate thatgenetic algorithm-kernel partial least squares can be used as an alternative modeling tool for quantitative structure-property relationshipstudies. This is the first research on the quantitative structure-property relationship of the nanoparticle compounds using the geneticalgorithm-partial least squares and genetic algorithm-kernel partial least squares.