QSAR Study on the Toxicity of Phenols for Fathead Minnows by Using Support Vector Machine and Neural Networks

Author

Cui, Xiujun ; Wang, Zhinxin ; Zhang, Zhuoyong ; Yuan, Xing ; de B.Harrington, P.

Author_Institution

Fac. of Chem., Northeast Normal Univ., Changchun

Volume

2

fYear

2008

fDate

18-20 Oct. 2008

Firstpage

134

Lastpage

138

Abstract

Support victor machine (SVM) and artificial neural networks (ANNs) including back-propagation network (BPNN) and radial basis function network (RBFNN) were used to investigate toxic effect of phenols on fathead minnows. Molecular connectivity index was used as structural descriptor. The applicability of established BPNNs, RBFNNs and SVM models based on optimized parameters was compared using leave-one-out (LOO) cross-validation method. Results showed that all the models investigated were applicable for the quantitative structure-activity relationship (QSAR) studies and the SVM model is slightly better than others. The correlation coefficients between measured toxicities and predicted values of SVM, BPNN and RBFNN models are 0.959, 0.94, and 0.945, respectively.

Keywords

backpropagation; chemical engineering computing; radial basis function networks; support vector machines; artificial neural networks; back-propagation network; fathead minnows; leave-one-out cross-validation method; molecular connectivity index; quantitative structure-activity relationship; radial basis function network; support vector machine; Artificial intelligence; Chemical hazards; Chemistry; Computer networks; Educational institutions; Neural networks; Predictive models; Radial basis function networks; Raw materials; Support vector machines; BPNN; Molecular connectivity index; Phenol; QSAR; RBFNN; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation, 2008. ICNC '08. Fourth International Conference on

Conference_Location

Jinan

Print_ISBN

978-0-7695-3304-9

Type

conf

DOI

10.1109/ICNC.2008.931

Filename

4666972