Prediction of retention times for a large set of pesticides based on improved gene expression programming

Authors:
Kejun Zhang;Shouqian Sun;Hongzong Si
Affiliations:
Zhejiang University, Hangzhou, China;Zhejiang University, Hangzhou, China;Qingdao University, Qingdao, China
Venue:
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Year:
2008

Citing 4
Cited 1

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
An introduction to genetic algorithms

An introduction to genetic algorithms
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning

Adaptive representations for improving evolvability, parameter control, and parallelization of gene expression programming

Applied Computational Intelligence and Soft Computing - Special issue on theory and applications of evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The purpose of the paper is to present a novel way to building Quantitative structure-retention relationship (QSRR) models. Studies was reported for predicting the retention times (RTs) of 110 pesticides which were detected by gas chromatography (GC) with mass selective detector (MSD). Chemical descriptors were calculated from the molecular structure of pesticides and the QSRR models of RTs with descriptors was built using the heuristic method (HM) and Improved Gene Expression Programming (IGEP), respectively. The obtained linear model of HM had a correlation coefficient R2 = 0.913, with a root mean square error (RMS) S2 of 0.0387 for the training set, while R2 =0.907, and RMS =0.0408 for the test set. The nonlinear model by IGEP gave better results: for the training set R2 = 0.971, S2 = 0.0176 and for the test set R2 =0.951, S2 =0.0267. The prediction results from nonlinear model are in agreement with the experimental values The QSRR model also reveals that the gas chromatographic RTs are associated with physicochemical property of pesticides.