QSPR Modeling of Soil Sorption Coefficients (K OC) of Pesticides Using SPA-ANN and SPA-MLR

Nasser Goudarzi, Mohammad Goodarzi, Mario Cesar Ugulino Araujo, Roberto Kawakami Harrop Galvão

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

A quantitative structure-property relationship (QSPR) study was conducted to predict the adsorption coefficients of some pesticides. The successive projection algorithm feature selection (SPA) strategy was used as descriptor selection and model development method. Modeling of the relationship between selected molecular descriptors and adsorption coefficient data was achieved by linear (multiple linear regression; MLR) and nonlinear (artificial neural network; ANN) methods. The QSPR models were validated by cross-validation as well as application of the models to predict the K OC of external set compounds, which did not contribute to model development steps. Both linear and nonlinear methods provided accurate predictions, although more accurate results were obtained by the ANN model. The root-mean-square errors of test set obtained by MLR and ANN models were 0.3705 and 0.2888, respectively.

Original languageEnglish (US)
Pages (from-to)7153-7158
Number of pages6
JournalJournal of Agricultural and Food Chemistry
Volume57
Issue number15
DOIs
StatePublished - Aug 12 2009

Fingerprint

quantitative structure-activity relationships
Quantitative Structure-Activity Relationship
Pesticides
sorption
Sorption
pesticides
Soil
Soils
Adsorption
soil
Linear Models
adsorption
Linear regression
Mean square error
Feature extraction
neural networks
Neural networks
methodology
prediction

Keywords

  • Artificial neural network
  • Quantitative structure-activity relationship
  • Soil sorption coefficients
  • Successive projection algorithm

ASJC Scopus subject areas

  • Chemistry(all)
  • Agricultural and Biological Sciences(all)

Cite this

QSPR Modeling of Soil Sorption Coefficients (K OC) of Pesticides Using SPA-ANN and SPA-MLR. / Goudarzi, Nasser; Goodarzi, Mohammad; Araujo, Mario Cesar Ugulino; Galvão, Roberto Kawakami Harrop.

In: Journal of Agricultural and Food Chemistry, Vol. 57, No. 15, 12.08.2009, p. 7153-7158.

Research output: Contribution to journalArticle

Goudarzi, Nasser ; Goodarzi, Mohammad ; Araujo, Mario Cesar Ugulino ; Galvão, Roberto Kawakami Harrop. / QSPR Modeling of Soil Sorption Coefficients (K OC) of Pesticides Using SPA-ANN and SPA-MLR. In: Journal of Agricultural and Food Chemistry. 2009 ; Vol. 57, No. 15. pp. 7153-7158.
@article{a3e1c2b06b0c490ca6da50f2231981fb,
title = "QSPR Modeling of Soil Sorption Coefficients (K OC) of Pesticides Using SPA-ANN and SPA-MLR",
abstract = "A quantitative structure-property relationship (QSPR) study was conducted to predict the adsorption coefficients of some pesticides. The successive projection algorithm feature selection (SPA) strategy was used as descriptor selection and model development method. Modeling of the relationship between selected molecular descriptors and adsorption coefficient data was achieved by linear (multiple linear regression; MLR) and nonlinear (artificial neural network; ANN) methods. The QSPR models were validated by cross-validation as well as application of the models to predict the K OC of external set compounds, which did not contribute to model development steps. Both linear and nonlinear methods provided accurate predictions, although more accurate results were obtained by the ANN model. The root-mean-square errors of test set obtained by MLR and ANN models were 0.3705 and 0.2888, respectively.",
keywords = "Artificial neural network, Quantitative structure-activity relationship, Soil sorption coefficients, Successive projection algorithm",
author = "Nasser Goudarzi and Mohammad Goodarzi and Araujo, {Mario Cesar Ugulino} and Galv{\~a}o, {Roberto Kawakami Harrop}",
year = "2009",
month = "8",
day = "12",
doi = "10.1021/jf9008839",
language = "English (US)",
volume = "57",
pages = "7153--7158",
journal = "Journal of Agricultural and Food Chemistry",
issn = "0021-8561",
publisher = "American Chemical Society",
number = "15",

}

TY - JOUR

T1 - QSPR Modeling of Soil Sorption Coefficients (K OC) of Pesticides Using SPA-ANN and SPA-MLR

AU - Goudarzi, Nasser

AU - Goodarzi, Mohammad

AU - Araujo, Mario Cesar Ugulino

AU - Galvão, Roberto Kawakami Harrop

PY - 2009/8/12

Y1 - 2009/8/12

N2 - A quantitative structure-property relationship (QSPR) study was conducted to predict the adsorption coefficients of some pesticides. The successive projection algorithm feature selection (SPA) strategy was used as descriptor selection and model development method. Modeling of the relationship between selected molecular descriptors and adsorption coefficient data was achieved by linear (multiple linear regression; MLR) and nonlinear (artificial neural network; ANN) methods. The QSPR models were validated by cross-validation as well as application of the models to predict the K OC of external set compounds, which did not contribute to model development steps. Both linear and nonlinear methods provided accurate predictions, although more accurate results were obtained by the ANN model. The root-mean-square errors of test set obtained by MLR and ANN models were 0.3705 and 0.2888, respectively.

AB - A quantitative structure-property relationship (QSPR) study was conducted to predict the adsorption coefficients of some pesticides. The successive projection algorithm feature selection (SPA) strategy was used as descriptor selection and model development method. Modeling of the relationship between selected molecular descriptors and adsorption coefficient data was achieved by linear (multiple linear regression; MLR) and nonlinear (artificial neural network; ANN) methods. The QSPR models were validated by cross-validation as well as application of the models to predict the K OC of external set compounds, which did not contribute to model development steps. Both linear and nonlinear methods provided accurate predictions, although more accurate results were obtained by the ANN model. The root-mean-square errors of test set obtained by MLR and ANN models were 0.3705 and 0.2888, respectively.

KW - Artificial neural network

KW - Quantitative structure-activity relationship

KW - Soil sorption coefficients

KW - Successive projection algorithm

UR - http://www.scopus.com/inward/record.url?scp=68249117442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68249117442&partnerID=8YFLogxK

U2 - 10.1021/jf9008839

DO - 10.1021/jf9008839

M3 - Article

C2 - 19722589

AN - SCOPUS:68249117442

VL - 57

SP - 7153

EP - 7158

JO - Journal of Agricultural and Food Chemistry

JF - Journal of Agricultural and Food Chemistry

SN - 0021-8561

IS - 15

ER -