Sharif Digital Repository

This chapter covers a part of the spectrum of neural-network uses in analytical chemistry. Different architectures of neural networks are described briefly. The chapter focuses on the development of three-layer artificial neural network for modeling the anti-HIV activity of the HETP derivatives and activity parameters (pIC 50) of heparanase inhibitors. The use of a genetic algorithm-kernel partial least squares algorithm combined with an artificial neural network (GA-KPLS-ANN) is described for predicting the activities of a series of aromatic sulfonamides. The retention behavior of terpenes and volatile organic compounds and predicting the response surface of different detection systems are... 

Essential oils (EOs) are valuable natural products that are popular nowadays in the world due to their effects on the health conditions of human beings and their role in preventing and curing diseases. In addition, EOs have a broad range of applications in foods, perfumes, cosmetics and human nutrition. Among different techniques for analysis of EOs, gas chromatography-mass spectrometry (GC-MS) is the most important one in recent years. However, there are some fundamental problems in GC-MS analysis including baseline drift, spectral background, noise, low S/N (signal to noise) ratio, changes in the peak shapes and co-elution. Multivariate curve resolution (MCR) approaches cope with ongoing... 

Multivariate curve resolution based on the minimization of an objective function (MCR-FMIN) defined directly from the non-fulfillment of constraints was applied for the first time as a deconvolution method to separate co-eluted gas chromatographic-mass spectrometric (GC-MS) signals. Simulated and real (standard real mixture and limon oil) GC-MS data were used to evaluate the feasibility of this method. The MCR-FMIN solutions have been obtained based on the rotation of principal component analysis (PCA) solutions using the non-linear optimization algorithms. Calculation of the initial values of R rotation matrix using model free analysis methods such as fixed-size moving window-evolving... 

A novel method for extraction and analysis of volatile compounds of Artemisia haussknechtii Boiss., using simultaneous hydro-distillation and static headspace liquid microextraction followed by gas chromatography-mass spectrometry (SHD-SHLPME-GCMS) is developed. SHLPME parameters including nature of extracting solvent, headspace volume and design, extraction time, sample weight and microdrop volume were optimized. Comparison of hydro-distillation gas chromatography-mass spectrometry and HD-SHLPME-GCMS showed that the latter method is fast, simple, inexpensive and effective for the analysis of volatile compounds of aromatic plants. By using this method, 56 compounds were extracted and... 

This paper introduces the genetic algorithm-kernel partial least square (GA-KPLS), as a novel nonlinear feature selection method. This technique combines genetic algorithms (GAs) as powerful optimization methods with KPLS as a robust nonlinear statistical method for variable selection. This feature selection method is combined with artificial neural network to develop a nonlinear QSAR model for predicting activities of a series of substituted aromatic sulfonamides as carbonic anhydrase II (CA II) inhibitors. Eight simple one- and two-dimensional descriptors were selected by GA-KPLS and considered as inputs for developing artificial neural networks (ANNs). These parameters represent the role... 

This paper compares the Shuffling-Adaptive Neuro Fuzzy Inference System (Shuffling-ANFIS) with conventional ANFIS as the method for selecting the features of nonlinear systems. Shuffling-ANFIS technique uses the advantage of data splitting with the ANFIS as a powerful feature selection method to select the most important factors affecting nonlinear phenomena. In this technique, the features with the largest percent of frequency can be found by running the conventional ANFIS sequential forward search on the large number of training and test sets using leave-one-out validation criteria. The superiority of Shuffling-ANFIS over the conventional ANFIS was evaluated by using two synthetic and one... 

The purpose of this study was to develop the structure-toxicity relationships for a large group of 268 substituted benzene to the ciliate Tetrahymena pyriformis using mechanistically interpretable descriptors. The shuffling-adaptive neuro fuzzy inference system (Shuffling-ANFIS) has been successfully applied to select the important factors affecting the toxicity of substituted benzenes to T. pyriformis. The results of the proposed model were compared with the model of linear-free energy response surface and also the principal component analysis Bayesian-regularized neural network (PCA-BRANN) trained using the same data. The presented model shows a better statistical parameter in comparison... 

A quantitative structure-mobility relationship was developed to accurately predict the electrophoretic mobility of organic acids. The absolute electrophoretic mobilities (μ0) of a diverse dataset consisting of 115 carboxylic and sulfonic acids were investigated. A set of 1195 zero- to three-dimensional descriptors representing various structural characteristics was calculated for each molecule in the dataset. Classification and regression trees were successfully used as a descriptor selection method. Four descriptors were selected and used as inputs for adaptive neuro-fuzzy inference system. The root mean square errors for the calibration and prediction sets are 1.61 and 2.27, respectively,... 

The critical micelle concentration (CMC) of a set of 30 alkyltrimethylammonium [RN+(R′)3X-] and alkylpyridinium salts [RN+φX-] was related to topological, electronic, and molecular structure parameters using a stepwise regression method. Among different models obtained, two equations were selected as the best and their specifications are given. The statistics for these models together with the crossvalidation results indicate the capability of both models to predict the CMC of cationic surfactants. The results obtained for alkyltrimethylammonium salts indicate that geometric characteristics such as volume of the tail of the molecule, maximum distance between the atoms, and surface area play... 

The quantities of residues of some triazines such as prometon, propazine, atrazine and simazine in complex matrices of apple samples were determined, using gas chromatography-selected ion mass (GC-SIM) spectrometry. Generalized rank annihilation method (GRAM) as a second-order calibration technique was used for screening, resolving and finally determining the amounts of the residues. Before the GRAM analysis, different steps of data preprocessing such as background correction, de-skewing and standardization for rank alignment was used for every target analyte. The de-skewing and rank alignment algorithms were used for bilinearity and trilinearity corrections, respectively. The two data... 

A hybrid method consisting of principal component analysis (PCA), multiple linear regressions (MLR), and artificial neural network (ANN) was developed to predict the retention time of 149 C3 - C12 volatile organic compounds for a DB-1 stationary phase. PCA and MLR methods were used as feature-selection tools, and a neural network was employed for predicting the retention times. The regression method was also used as a calibration model for calculating the retention time of VOCs and investigating their linear characteristics. The descriptors of the total information index of atomic composition, IAC, Wiener number, W, solvation connectivity index, Xlsol, and number of substituted aromatic... 

Characterization and determination of a complex mixture of fatty acid methyl esters was performed for commercial fish oil using two-dimensional GC-MS data coupled with resolution techniques. Various principle component analysis methods such as significant factor analysis and fixed size moving window evolving factor analysis were used for the number of factors, zero concentration and selective regions. Then, the convoluted chromatograms were resolved into pure chromatograms and mass spectra using heuristic evolving latent projections (HELP) method. Fatty acids of C16:1ω7, C18:4ω3, C18:1ω11, C18:1ω9, C18:0, C20:2ω6, C20:1ω9, C 22:1ω11, C22:1ω9 and C24:1ω9 were resolved and identified by using... 

A new series of six comprehensive descriptors that represent different features of the gas-liquid partition coefficient, K(L), for commonly used stationary phases is developed. These descriptors can be considered as counterparts of the parameters in the Abraham solvatochromic model of solution. A separate multiple linear regression (MLR) model was developed by using the six descriptors for each stationary phase of poly(ethylene glycol adipate) (EGAD), N,N,N',N'-tetrakis(2-hydroxypropyl) ethylenediamine (THPED), poly(ethylene glycol) (Ucon 50 HB 660) (U50HB), di(2-ethylhexyl)phosphoric acid (DEHPA) and tetra-n-butylammonium N,N-(bis-2-hydroxylethyl)-2-aminoethanesulfonate (QBES). The results... 

The CMC of a set of51 alkylpolyoxyethylene glycol ethers, R(EO)(m), and alkylphenol (ethylene oxide) ethers, RΦ(EO)(m), was related to topological, electronic and molecular structure parameters using a stepwise regression method. In development of the models linear and quadratic terms were used without the use of cross terms. Different strategies including Akaike Information Criterion (AIC) were used for choosing the best model. Specification of the best model in agreement with the experiment indicates that volume of the hydrophobic group and surface area of the molecule play a major role in the mechanism of micellization of nonionic surfactants. It was demonstrated that the CMC of these... 

Computer-assisted methods were employed to develop a statistical relationship between molecular-based structural parameters and log critical micelle concentration (CMC) of some anionic surfactants. The CMC of 31 alkyl sulfates and alkanesulfonates were used for model generation. Among different models, two equations were selected as the best, and their specifications are given. The statistics of these models together with cross-validation results indicate the capability of both models to predict the CMC of anionic surfactants. Three descriptors of Wiener number, reciprocal of the dipole moment, and reciprocal of the Randic index appear in the models. Results indicate that topological... 

Anti-HIV activity for a set of 107 inhibitors of the HIV-1 reverse transcriptase, derivatives of 1-[2-hydroxyethoxy)methyl]-6-(phenylthio)thymine (HEPT), was modeled with the aid of chemometric techniques. The activity of these compounds was estimated by means of multiple linear regression (MLR) and artificial neural network (ANN) techniques and compared with the previous works. The results obtained using the MLR method indicate that the anti-HIV activity of the HEPT derivatives depends on the reverse of standard shadow area on the YZ plane and the ratio of the partial charges of the most positive atom to the most negative atom of the molecule. The best computational neural network model was... 

A total of 6289 drug-like anticancer molecules were collected from Binding database and were analyzed by using the classification techniques. The collected molecules were encoded to a diverse set of descriptors, spanning different physical and chemical properties of the molecules. A combination of genetic algorithms and counterpropagation artificial neural networks was used for navigating the generated drug-like chemical space and selecting the most relevant molecular descriptors. The proposed method was used for the classification of the molecules according to their therapeutic targets and activities. The selected molecular descriptors in this work define discrete areas in chemical space,...