Linear and non-linear relationships mapping the Henry's law parameters of organic pesticides

被引：14
作者：
Goodarzi, Mohammad [1 ]
Ortiz, Erlinda V. [2 ]
Coelho, Leandro dos S. [3 ]
Duchowicz, Pablo R. [1 ]
机构：
[1] UNLP, CCT La Plata CONICET, INIFTA, Inst Invest Fisicoquim Teor & Aplicadas, RA-1900 La Plata, Argentina
[2] Univ Natl Catamarca, Fac Tecnol & Ciencias Aplicadas, RA-4700 Catamarca, Argentina
[3] Pontifical Catholic Univ Parana PUCPR, Ind & Syst Engn Grad Program PPGEPS, BR-80215901 Curitiba, Parana, Brazil
来源：
ATMOSPHERIC ENVIRONMENT | 2010年 / 44卷 / 26期
关键词：
QSPR-QSAR Theory; Replacement method; Artificial neural networks; Henry's law constant; Dragon molecular descriptors; STRUCTURE-PROPERTY RELATIONSHIP; AQUEOUS SOLUBILITY; VARIABLE SELECTION; DIVERSE SET; CONSTANT; QSPR; PREDICTION; QSAR; REGRESSION; ALGORITHM;
D O I：
10.1016/j.atmosenv.2010.05.025
中图分类号：
X [环境科学、安全科学];
学科分类号：
08 ; 0830 ;
摘要：
This work aims to predict the air to water partitioning for 96 organic pesticides by means of the Quantitative Structure-Property Relationships Theory. After performing structural feature selection with Genetics Algorithms and Replacement Method linear approaches, it is found that among the most important molecular features appears the Moriguchi octanol-water partition coefficient, and higher lipophilicities would lead to compounds having higher Henry's law constants. We also compare the statistical performance achieved by four fully-connected Feed-Forward Multilayer Perceptrons Artificial Neural Networks. The statistical results found reveal that the best performing model uses the Levenberg-Marquardt with Bayesian regularization (BR) weighting function for achieving the most accurate predictions. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码：3179 / 3186
页数：8
相关论文
共 47 条
[1]   Henry's law constants for a diverse set of organic chemicals: Experimental determination and comparison of estimation methods [J].
Altschuh, J ;
Bruggemann, R ;
Santl, H ;
Eichinger, G ;
Piringer, OG .
CHEMOSPHERE, 1999, 39 (11) :1871-1887
[2]  
Barcelo D., 1997, Trace determination of pesticides and their degradation products in water, VFirst
[3]   Comparison of predictive methods for Henrys Law Coefficients of organic chemicals [J].
Brennan, RA ;
Nirmalakhandan, N ;
Speece, RE .
WATER RESEARCH, 1998, 32 (06) :1901-1911
[4]   Validation of a headspace solid-phase microextraction procedure with gas chromatography-electron capture detection of pesticide residues in fruits and vegetables [J].
Chai, Mee Kin ;
Tan, Guan Huat .
FOOD CHEMISTRY, 2009, 117 (03) :561-567
[5]   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
[6]   New multicollinearity indicators in linear regression models [J].
Curto, Jose Dias ;
Pinto, Jose Castro .
INTERNATIONAL STATISTICAL REVIEW, 2007, 75 (01) :114-121
[7]  
Demuth H., 2003, NEURAL NETWORK TOOLB
[8]   New QSPR study for the prediction of aqueous solubility of drug-like compounds [J].
Duchowicz, Pablo R. ;
Talevi, Alan ;
Bruno-Blanch, Luis E. ;
Castro, Eduardo A. .
BIOORGANIC & MEDICINAL CHEMISTRY, 2008, 16 (17) :7944-7955
[9]   QSPR study of the Henry's Law constant for hydrocarbons [J].
Duchowicz, Pablo R. ;
Garro, Juan C. M. ;
Castro, Eduardo A. .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2008, 91 (02) :133-140
[10]   Application of the replacement method as novel variable selection in QSPR.: 2.: Soil sorption coefficients [J].
Duchowicz, Pablo R. ;
Perez Gonzalez, Maykel ;
Morales Helguera, Aliuska ;
Dias Soeiro Cordeiro, Maria Natalia ;
Castro, Eduardo A. .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2007, 88 (02) :197-203
12345