Artificial neural networks in prediction of antifungal activity of a series of pyridine derivatives against Candida albicans

Quantitative structure-activity relationship model for classifying the diverse series of antifungal agents using ratio weighted penalized logistic regression

One of the most challenging issues when facing a Quantitative structure-activity relationship (QSAR) classification model is to deal with the descriptor selection. Penalized methods have been adapted and have gained popularity as a key for simultaneously performing descriptor selection and QSAR classification model estimation. However, penalized methods have drawbacks such as having biases and inconsistencies that make they lack the oracle properties. This paper proposes an adaptive penalized logistic regression (APLR) to overcome these drawbacks. This is done by employing a ratio (BWR) of the descriptors between-groups sum of squares (BSS) to the within-groups sum of squares (WSS) for each descriptor as a weight inside the L₁-norm. The proposed method was applied to one dataset that consists of a diverse series of antimicrobial agents with their respective bioactivities against Candida albicans. By experimental study, it has been shown that the proposed method (APLR) was more efficient in the selection of descriptors and classification accuracy than the other competitive methods that could be used in developing QSAR classification models. Another dataset was also successfully experienced. Therefore, it can be concluded that the APLR method had significant impact on QSAR analysis and studies.

QSAR classification model for diverse series of antifungal agents based on improved binary differential search algorithm

An improved binary differential search (improved BDS) algorithm is proposed for QSAR classification of diverse series of antimicrobial compounds against Candida albicans inhibitors. The transfer functions is the most important component of the BDS algorithm, and converts continuous values of the donor into discrete values. In this paper, the eight types of transfer functions are investigated to verify their efficiency in improving BDS algorithm performance in QSAR classification. The performance was evaluated using three metrics: classification accuracy (CA), geometric mean of sensitivity and specificity (G-mean), and area under the curve. The Kruskal-Wallis test was also applied to show the statistical differences between the functions. Two functions, S1 and V4, show the best classification achievement, with a slightly better performance of V4 than S1. The V4 function takes the lowest iterations and selects the fewest descriptors. In addition, the V4 function yields the best CA and G-mean of 98.07% and 0.977%, respectively. The results prove that the V4 transfer function significantly improves the performance of the original BDS.

Statistical versus artificial intelligence -based modeling for the optimization of antifungal activity against Fusarium oxysporum using Streptomyces sp. strain TN71

A Streptomyces sp. strain TN71 was isolated from Tunisian Saharan soil and selected for its antimicrobial activity against phytopathogenic fungi. In an attempt to increase its anti-Fusarium oxysporum activity, GYM+S (glucose, yeast extract, malt extract and starch) culture medium was selected out of five different production media. Plackett-Burman design (PBD) was used to select yeast extract, malt extract and calcium carbonate (CaCO₃) as parameters having significant effects on antifungal activity, and a Box-Behnken design was applied for further optimization. The analysis revealed that the optimum concentrations for the anti-F. oxysporum activity of the tested variables were yeast extract 5.03g/L, malt extract 8.05g/L and CaCO₃ 4.51g/L. Artificial Neural Networks (ANNs): the Multilayer perceptron (MLP) and the Radial basis function (RBF) were created to predict the anti-F. oxysporum activity. The comparison between experimental and predicted outputs from ANN and Response Surface Methodology (RSM) were studied. The ANN model presents an improvement of 14.73%. To our knowledge, this is the first work reporting the statistical versus artificial intelligence -based modeling for the optimization of bioactive molecules against mycotoxigenic and phytopathogenic fungi.

Vibrational spectra, normal coordinate analysis, and hydrogen bond investigation of pyridinium perchlorate

The IR and Raman spectra of pyridine perchlorate salt (PyHClO₄) have been recorded in the 4000-300 and 3200-200cm^-1 regions, respectively. The structure and vibrational spectra of pyridine salt have been investigated by means of ab initio and density functional theory (DFT) calculations. To examine the efficiency of basis sets in predicting the vibrational spectra of ClO₄^-1 ion, several basis sets were used with the B3LYP and B2PLYP levels of theory. It was shown that the 6-311(3df) basis set gives reasonably vibrational wavenumbers for simulation of perchlorate ion experimental vibrational wavenumbers. Therefore, the B3LYP/6-311G(3df) level was used to calculate the vibrational spectra of pyridine perchlorate salt in CH₃CN solution. For comparison, the vibrational wavenumbers were also calculated at the B3LYP/aug-cc-pVTZ level. The geometry of PyHClO₄ was calculated in the gas phase as well as in solutions, using SCRF-PCM method. According to these calculations, the structure and hydrogen bonding in PyHClO₄ is highly affected by media. Two hydrogen bonding systems between ClO₄^-1 and pyridinium ions were recognized. The nature of these hydrogen bonds is theoretically investigated by using atoms in molecule (AIM) method and natural bond orbital (NBO) analysis. A normal coordinate analysis was performed by using the internal coordinates calculated at the B3LYP/6-311G(3df,p) level for the vibrational normal modes of the titled compound.

Prediction of antimicrobial activity of imidazole derivatives by artificial neural networks

The main goal of our study is the analysis of data obtained from molecular modeling for a series of imidazole derivatives that possess strong antifungal activity. The research was designed to use artificial neural network (ANN) analysis to determine quantitative relationships between the structural parameters and anti-Streptococcus pyogenes activity of a series of imidazole derivatives. ANN in association with quantitative structure-activity relationships (QSAR) represents a promising tool in the search for drug candidates among the practically unlimited number of possible derivatives. In this work, a series of 286 imidazole derivatives presented as cationic three-dimensional structures was used. The activity was expressed as a logarithm of the reciprocal of the minimal inhibitory concentrations, log 1/MIC. Multilayer perceptron ANN was used for predictions of antimicrobial potency of new imidazole derivatives on the basis of their structural descriptors. The obtained correlation coefficient equaled 0.9461 for the learning set, 0.9060 for the validation set and 0.8824 for the testing set of imidazole derivatives. Hence, satisfactory and practically useful predictions of anti-Streptococcus pyogenes activity for a series of imidazole derivatives was obtained, supporting the future successful interpretation of QSAR analysis for those compounds.

Synthesis, spectral and thermal studies of some transition metal mixed ligand complexes: modeling of equilibrium composition and biological activity

Several mixed ligand Ni(II), Cu(II) and Zn(II) complexes of 2-amino-3-hydroxypyridine (AHP) and imidazoles viz., imidazole (him), benzimidazole (bim), histamine (hist) and L-histidine (his) have been synthesized and characterized by elemental and spectral (vibrational, electronic, 1H NMR and EPR) data as well as by magnetic moment values. On the basis of elemental analysis and molar conductance values, all the complexes can be formulated as [MAB]Cl except histidine complexes as MAB. Thermogravimetric studies reveal the presence of coordinated water molecules in most of the complexes. From the magnetic measurements and electronic spectral data, octahedral structure was proposed for Ni(II) and Cu(II)-AHP-his, tetrahedral for Cu(II)-AHP-him/bim/hist, but square planar for the Cu(II)-AHP complex. The g∥/A∥ calculated supports tetrahedral environment around the Cu(II) in Cu(II)-AHP-him/bim/hist and distorted octahedral for Cu(II)-AHP-his complexes. The morphology of the reported metal complexes was investigated by scanning electron micrographs (SEM). The potentiometric study has been performed in aqueous solution at 37 °C and I=0.15 mol dm(-3) NaClO4. MABH, MAB and MAB2 species has been identified in the present systems. Proton dissociation constants of AHP and stability constants of metal complexes were determined using MINIQUAD-75. The most probable structure of the mixed ligand species is discussed based upon their stability constants. The in vitro biological activity of the complexes was tested against the Gram positive and Gram negative bacteria, fungus and yeast. The oxidative DNA cleavage studies of the complexes were performed using gel electrophoresis method. Cu(II) complexes have been found to promote DNA cleavage in presence of biological reductant such as ascorbate and oxidant like hydrogen peroxide.

Systems biology of infectious diseases: a focus on fungal infections

The study of infectious disease concerns the interaction between the host species and a pathogen organism. The analysis of such complex systems is improving with the evolution of high-throughput technologies and advanced computational resources. This article reviews integrative, systems-oriented approaches to understanding mechanisms underlying infection, immune response and inflammation to find biomarkers of disease and design new drugs. We focus on the systems biology process, especially the data gathering and analysis techniques rather than the experimental technologies or latest computational resources.

Investigations on inhibitors of hedgehog signal pathway: a quantitative structure-activity relationship study

The hedgehog signal pathway is an essential agent in developmental patterning, wherein the local concentration of the Hedgehog morphogens directs cellular differentiation and expansion. Furthermore, the Hedgehog pathway has been implicated in tumor/stromal interaction and cancer stem cell. Nowadays searching novel inhibitors for Hedgehog Signal Pathway is drawing much more attention by biological, chemical and pharmological scientists. In our study, a solid computational model is proposed which incorporates various statistical analysis methods to perform a Quantitative Structure-Activity Relationship (QSAR) study on the inhibitors of Hedgehog signaling. The whole QSAR data contain 93 cyclopamine derivatives as well as their activities against four different cell lines (NCI-H446, BxPC-3, SW1990 and NCI-H157). Our extensive testing indicated that the binary classification model is a better choice for building the QSAR model of inhibitors of Hedgehog signaling compared with other statistical methods and the corresponding in silico analysis provides three possible ways to improve the activity of inhibitors by demethylation, methylation and hydroxylation at specific positions of the compound scaffold respectively. From these, demethylation is the best choice for inhibitor structure modifications. Our investigation also revealed that NCI-H466 served as the best cell line for testing the activities of inhibitors of Hedgehog signal pathway among others.

Contribution of artificial intelligence to the knowledge of prognostic factors in Hodgkin's lymphoma

Hodgkin's lymphoma is one of the most curable malignancies and most patients achieve a lasting complete remission. In this study, artificial neural network (ANN) analysis was shown to provide significant factors with regard to 5-year recurrence after lymphoma treatment. Data from 114 patients treated for Hodgkin's disease were available for evaluation and comparison. A total of 31 variables were subjected to ANN analysis. The ANN approach as an advanced multivariate data processing method was shown to provide objective prognostic data. Some of these prognostic factors are consistent or even identical to the factors evaluated earlier by other statistical methods.

Current trends in antimicrobial agent research: chemo- and bioinformatics approaches

Databases and chemo- and bioinformatics tools that contain genomic, proteomic and functional information have become indispensable for antimicrobial drug research. The combination of chemoinformatics tools, bioinformatics tools and relational databases provides means of analyzing, linking and comparing online search results. The development of computational tools feeds on a diversity of disciplines, including mathematics, statistics, computer science, information technology and molecular biology. The computational approach to antimicrobial agent discovery and design encompasses genomics, molecular simulation and dynamics, molecular docking, structural and/or functional class prediction, and quantitative structure-activity relationships. This article reviews progress in the development of computational methods, tools and databases used for organizing and extracting biological meaning from antimicrobial research.

Determination of free amino acid content in Radix Pseudostellariae using near infrared (NIR) spectroscopy and different multivariate calibrations

Near infrared (NIR) spectroscopy combined with multivariate calibration was attempted to analyze free amino acid content of Radix Pseudostellariae. The original spectra of Pseudostellariae samples in wavelength range of 10000-4000 cm(-1) were acquired. Partial least squares (PLS), kernel PLS (k-PLS), back propagation neural network (BP-NN), and support vector regression (SVR) algorithms were performed comparatively to develop calibration models. Some parameters of the calibration models were optimized by cross-validation. The performance of BP-NN model was better than PLS, k-PLS, and SVR models. The root mean square error of prediction (RMSEP) and the correlation coefficient (R) of BP-NN model were 0.687 and 0.889 in prediction set respectively. Results showed that NIR spectroscopy combined with multivariate calibration has significant potential in quantitative analysis of free amino acid content in Radix Pseudostellariae.