Quantitative structure—retention relationship analysis of nanoparticle compounds

Genetic algorithm and partial least square (GA-PLS), the kernel PLS (KPLS) and Levenberg-Marquardt artificial neural network (L-M ANN) techniques were used to investigate the correlationbetween retention time (RT) and descriptors for 15 nanoparticle compounds which obtained by thecomprehensive two dimensional gas chromatography system (GC x GC). Application of thedodecanethiol monolayer-protected gold nanoparticle (MPN) column was for a high-speed separationas the second column of GC x GC. The L-M ANN model with the final optimum networkarchitecture of [9-4-1] gave a significantly better performance than the other models. This is the firstresearch on the quantitative structure—retention relationship (QSRR) of the nanoparticle compoundsusing the GA-PLS, GA-KPLS and L-M ANN.