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

Mohammad Goodarzi; Erlinda V. Ortiz; Leandro dos S. Coelho; Pablo R. Duchowicz

doi:10.1016/j.atmosenv.2010.05.025

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

Mohammad Goodarzi, Erlinda V. Ortiz, Leandro dos S. Coelho, Pablo R. Duchowicz

Research output: Contribution to journal › Article › peer-review

14 Scopus citations

Abstract

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.

Original language	English (US)
Pages (from-to)	3179-3186
Number of pages	8
Journal	Atmospheric Environment
Volume	44
Issue number	26
DOIs	https://doi.org/10.1016/j.atmosenv.2010.05.025
State	Published - Aug 1 2010

Keywords

Artificial neural networks
Dragon molecular descriptors
Henry's law constant
QSPR-QSAR Theory
Replacement method

ASJC Scopus subject areas

Environmental Science(all)
Atmospheric Science

Access to Document

10.1016/j.atmosenv.2010.05.025

Cite this

@article{d6a95d1f381e499a953f2f2f71a29d90,

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

abstract = "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.",

keywords = "Artificial neural networks, Dragon molecular descriptors, Henry's law constant, QSPR-QSAR Theory, Replacement method",

author = "Mohammad Goodarzi and Ortiz, {Erlinda V.} and Coelho, {Leandro dos S.} and Duchowicz, {Pablo R.}",

year = "2010",

month = aug,

day = "1",

doi = "10.1016/j.atmosenv.2010.05.025",

language = "English (US)",

volume = "44",

pages = "3179--3186",

journal = "Atmospheric Environment",

issn = "1352-2310",

publisher = "Elsevier Limited",

number = "26",

}

TY - JOUR

T1 - Linear and non-linear relationships mapping the Henry's law parameters of organic pesticides

AU - Goodarzi, Mohammad

AU - Ortiz, Erlinda V.

AU - Coelho, Leandro dos S.

AU - Duchowicz, Pablo R.

PY - 2010/8/1

Y1 - 2010/8/1

N2 - 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.

AB - 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.

KW - Artificial neural networks

KW - Dragon molecular descriptors

KW - Henry's law constant

KW - QSPR-QSAR Theory

KW - Replacement method

UR - http://www.scopus.com/inward/record.url?scp=77954657899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954657899&partnerID=8YFLogxK

U2 - 10.1016/j.atmosenv.2010.05.025

DO - 10.1016/j.atmosenv.2010.05.025

M3 - Article

AN - SCOPUS:77954657899

VL - 44

SP - 3179

EP - 3186

JO - Atmospheric Environment

JF - Atmospheric Environment

SN - 1352-2310

IS - 26

ER -

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

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this