Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method

被引：22

作者：

Lei, Beilei ^{[1
,2
]}

Ma, Yimeng ^{[1
,2
]}

Li, Jiazhong ^{[1
,2
,4
]}

Liu, Huanxiang ^{[3
]}

Yao, Xiaojun ^{[1
,2
]}

Gramatica, Paola ^{[4
]}

机构：

[1] Lanzhou Univ, State Key Lab Appl Organ Chem, Lanzhou 730000, Peoples R China

[2] Lanzhou Univ, Dept Chem, Lanzhou 730000, Peoples R China

[3] Lanzhou Univ, Sch Pharm, Lanzhou 730000, Peoples R China

[4] Univ Insubria, Dept Struct & Funct Biol, QSAR Res Unit Environm Chem & Ecotoxicol, I-21100 Varese, Italy

来源：

ATMOSPHERIC ENVIRONMENT | 2010年 / 44卷 / 25期

基金：

中国国家自然科学基金;

关键词：

Activated carbon adsorption capability; Quantitative structure-property relationship (QSPR); Genetic algorithm (GA); Local lazy regression (LLR); STRUCTURE/RESPONSE CORRELATIONS; SIMILARITY/DIVERSITY ANALYSIS; GETAWAY DESCRIPTORS; ORGANIC-COMPOUNDS; QSAR; VALIDATION; MODELS; QSPR; CONSTANTS; STRATEGY;

D O I：

10.1016/j.atmosenv.2010.05.021

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Accurate quantitative structure-property relationship (QSPR) models based on a large data set containing a total of 3483 organic compounds were developed to predict chemicals' adsorption capability onto activated carbon in gas phrase. Both global multiple linear regression (MLR) method and local lazy regression (LLR) method were used to develop QSPR models. The results proved that LLR has prediction accuracy 10% higher than that of MLR model. By applying LLR method we can predict the test set (787 compounds) with Q(ext)(2) of 0.900 and root mean square error (RMSE) of 0.129. The accurate model based on this large data set could be useful to predict adsorption property of new compounds since such model covers a highly diverse structural space. (C) 2010 Elsevier Ltd. All rights reserved.

引用

页码：2954 / 2960

页数：7

共 40 条

[1]

Aha DW, 1997, ARTIF INTELL REV, V11, P7, DOI 10.1023/A:1006538427943

[2]

[Anonymous], LAZY LEARNING TOOLBO

[3]

Atkeson CG, 1997, ARTIF INTELL REV, V11, P11, DOI 10.1023/A:1006559212014

[4]

Bontempi G, 1999, INT J CONTROL, V72, P643, DOI 10.1080/002071799220830

[5] Quantitative structure-property relationship (QSPR) for the adsorption of organic compounds onto activated carbon cloth: Comparison between multiple linear regression and neural network [J].

Brasquet, C ;

Bourges, B ;

Le Cloirec, P .

ENVIRONMENTAL SCIENCE & TECHNOLOGY, 1999, 33 (23) :4226-4231

[6] Gas phase adsorption of volatile organic compounds and water vapor on activated carbon cloth [J].

Cal, MP ;

Rood, MJ ;

Larson, SM .

ENERGY & FUELS, 1997, 11 (02) :311-315

[7]

*CAMBR CORP, 1985, CHEMDRAW

[8] Utility-based double auction mechanism using genetic algorithms [J].

Choi, Jin Ho ;

Ahn, Hyunchul ;

Han, Ingoo .

EXPERT SYSTEMS WITH APPLICATIONS, 2008, 34 (01) :150-158

[9] Structure/response correlations and similarity/diversity analysis by GETAWAY descriptors. 2. Application of the novel 3D molecular descriptors to QSAR/QSPR studies [J].

Consonni, V ;

Todeschini, R ;

Pavan, M ;

Gramatica, P .

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2002, 42 (03) :693-705

[10] Structure/response correlations and similarity/diversity analysis by GETAWAY descriptors. 1. Theory of the novel 3D molecular descriptors [J].

Consonni, V ;

Todeschini, R ;

Pavan, M .

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2002, 42 (03) :682-692

← 1 2 3 4 →