The accurate QSPR models to predict the bioconcentration factors of nonionic organic compounds based on the heuristic method and support vector machine

被引:41
作者
Liu, HX
Yao, XJ [1 ]
Zhang, RS
Liu, MC
Hu, ZD
Fan, BT
机构
[1] Lanzhou Univ, Dept Chem, Lanzhou 730000, Peoples R China
[2] Lanzhou Univ, Dept Comp Sci, Lanzhou 730000, Peoples R China
[3] Univ Paris 07, ITODYS, F-75005 Paris, France
关键词
bioconcentration factors; QSPR; support vector machine; heuristic method;
D O I
10.1016/j.chemosphere.2005.08.031
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The heuristic method (HM) and support vector machine (SVM) were used to build the linear and nonlinear quantitive structure-property relationship (QSPR) models for the prediction of the fish bioconcentration factors (BCF) for 122 diverse nonionic organic chemicals using the three descriptors calculated from the molecular structure alone and selected by HM. Both the linear and nonlinear model can give very satisfactory prediction results: the square of correlation coefficient R-2 was 0.929 and 0.953, the root mean square (RMS) error was 0.404 and 0.331, respectively for the whole dataset. The prediction result of the SVM model is better than that obtained by heuristic method, which proved SVM was a useful tool in the prediction of the BCF. At the same time, the HM model showed the influencing degree of different molecular descriptors on bioconcentration factors and then could improve the understanding for the bioconcentration mechanism of organic pollutants from molecular level. (c) 2005 Elsevier Ltd. All rights reserved.
引用
收藏
页码:722 / 733
页数:12
相关论文
共 38 条
[1]  
[Anonymous], [No title captured], DOI DOI 10.1023/A:1009715923555
[2]   Identifying genes related to drug anticancer mechanisms using support vector machine [J].
Bao, L ;
Sun, ZR .
FEBS LETTERS, 2002, 521 (1-3) :109-114
[3]   BIOCONCENTRATION [J].
BARRON, MG .
ENVIRONMENTAL SCIENCE & TECHNOLOGY, 1990, 24 (11) :1612-1618
[4]   A flexible classification approach with optimal generalisation performance: support vector machines [J].
Belousov, AI ;
Verzakov, SA ;
von Frese, J .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2002, 64 (01) :15-25
[5]   Drug design by machine learning: support vector machines for pharmaceutical data analysis [J].
Burbidge, R ;
Trotter, M ;
Buxton, B ;
Holden, S .
COMPUTERS & CHEMISTRY, 2001, 26 (01) :5-14
[6]   Prediction of protein structural classes by support vector machines [J].
Cai, YD ;
Liu, XJ ;
Xu, XB ;
Chou, KC .
COMPUTERS & CHEMISTRY, 2002, 26 (03) :293-296
[7]   Support vector machines for predicting HIV protease cleavage sites in protein [J].
Cai, YD ;
Liu, XJ ;
Xu, XB ;
Chou, KC .
JOURNAL OF COMPUTATIONAL CHEMISTRY, 2002, 23 (02) :267-274
[8]  
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[9]  
Cristianini N., 2000, Intelligent Data Analysis: An Introduction, DOI 10.1017/CBO9780511801389
[10]   THE DEVELOPMENT AND USE OF QUANTUM MOLECULAR-MODELS .75. COMPARATIVE TESTS OF THEORETICAL PROCEDURES FOR STUDYING CHEMICAL-REACTIONS [J].
DEWAR, MJS ;
STORCH, DM .
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY, 1985, 107 (13) :3898-3902