Prediction of air-to-blood partition coefficients of volatile organic compounds using genetic algorithm and artificial neural network

Konoz, Elaheh; Golmohammadi, Hassan

doi:10.1016/j.aca.2008.04.065

Cited by 25 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…index for a O atom' is also the d3 descriptor of the QSAR index for a C atom (d2) and HOMO energy (d5), an indicator of charge distribution and electronegativity. 56,57 The statistical significance of the descriptors d2, d3 and d5 is confirmed. The QSAR analysis was also performed on the compound set only with aromatic bonds = 0 and the best QSAR models were obtained with three descriptors, Number of N atoms (d 00 1), HOMO-LUOM energy gap (d 00 2), and Tot hybridization comp.…”

Section: Introductionsupporting

confidence: 51%

Quantitative structure–activity relationship of antifungal activity of rosin derivatives

Wang

Nguyen

et al. 2015

Bioorganic & Medicinal Chemistry Letters

View full text Add to dashboard Cite

Section: Introductionsupporting

confidence: 51%

Quantitative structure–activity relationship of antifungal activity of rosin derivatives

Wang

Nguyen

et al. 2015

Bioorganic & Medicinal Chemistry Letters

View full text Add to dashboard Cite

“…For example, genetic algorithm multiple linear regression (GA-MLR) [21][22] , genetic algorithm partial least squares (GA-PLS), genetic algorithm support vector machine (GA-SVM) 23 , genetic algorithm, and artificial neural network (GA-ANN) [24][25] .…”

Section: Introductionmentioning

confidence: 99%

Exploring Novel QSRRs for Simulation of Gas Chromatographic Retention Indices of Diverse Sets of Terpenoids inPistacia LentiscusL. Essential Oil Using Stepwise and Genetic Algorithm Multiple Linear Regressions

Mohammadhosseini

Deeb

Alavi-Gharabagh

et al. 2012

Analytical Chemistry Letters

View full text Add to dashboard Cite

The present work describes convenient and interpretable models by step-wise multiple linear regression (SW-MLR) and genetic algorithm-multiple linear regression (GA-MLR). These quantitative structure-retention relationship (QSRR) based strategies have been successfully used to predict the retention indices (RIs) of a series of natural compounds found in the essential oil of Pistacia lentiscus L. The dataset was divided into training set (51 compounds) and test set (25 compounds), randomly. The prediction capabilities of both approaches have been appraised by their exertion to test set compounds. The fitness statistics of the models were assessed to be satisfactory which resulted in accurate predictions. The best optimized models for SW-MLR and GA-MLR consisted 5 (X0, Qtot, Dv, HATS3e and MATS4e) and 6 (MATS2e, DELS, ATS4e, PW5, PCD and W) molecular descriptors, respectively. Our investigation revealed the superiority of SW-MLR (R 2 =0.96, Q 2 LOO =0.95 and Q 2 LGO =0.94 for training set; REP=3.7 for test set) standpoint against the best GA-MLR model (R 2 =0.955, Q 2 LOO =0.937 and Q 2 LGO =0.934 for training set; REP=7.5 for test set) for estimation of RIs of similar or unknown compounds.

show abstract

“…ANNs have been applied to QSPR analysis since the late 1980s due to its flexibility in modeling of nonlinear problems, mainly in response to increase accuracy demands; they have been widely used to predict many physicochemical properties [13][14][15][16][17][18][19]. The main aim of this work was development of a QSPR model by using ANN to predict the partition coefficients of various organic compounds.…”

Section: Introductionmentioning

confidence: 99%

Quantitative structure–property relationship studies of gas-to-wet butyl acetate partition coefficient of some organic compounds using genetic algorithm and artificial neural network

Golmohammadi

Dashtbozorgi

2010

Struct Chem

Self Cite

View full text Add to dashboard Cite

A Quantitative Structure-Property Relationship (QSPR) study based on artificial neural network (ANN) was carried out for the prediction of the gas-to-wet butyl acetate partition coefficient of a set of 81 organic compounds of very different chemical nature. The genetic algorithm-partial least squares (GA-PLS) method was applied as a variable selection tool. A PLS method was used to select the best descriptors and the selected descriptors were used as input neurons in neural network model. These descriptors are: Randic index (order 2) ( 2 v), atomic charge weighted partial positively charged surface area (PPSA-3), difference between atomic charge weighted partial positive and negative surface areas (DPSA-3), minimum net atomic charge for a O atom (q min O) and hydrogen bonding donor ability of the molecule (HDSA1). The results obtained showed the ability of developed ANN for prediction of the gas-to-wet butyl acetate partition coefficients of various compounds. Also result reveals the superiority of the ANN over the PLS model.

show abstract

Prediction of air-to-blood partition coefficients of volatile organic compounds using genetic algorithm and artificial neural network

Cited by 25 publications

References 23 publications

Quantitative structure–activity relationship of antifungal activity of rosin derivatives

Quantitative structure–activity relationship of antifungal activity of rosin derivatives

Exploring Novel QSRRs for Simulation of Gas Chromatographic Retention Indices of Diverse Sets of Terpenoids inPistacia LentiscusL. Essential Oil Using Stepwise and Genetic Algorithm Multiple Linear Regressions

Quantitative structure–property relationship studies of gas-to-wet butyl acetate partition coefficient of some organic compounds using genetic algorithm and artificial neural network

Contact Info

Product

Resources

About