QSAR study of necroptosis inhibitory activities (EC50) of [1,2,3] thiadiazole and thiophene derivatives using Bayesian regularized artificial neural network and calculated descriptors

The efficiency of ligand-receptor interaction information alone as new descriptors in QSAR modeling via random forest artificial neural network

A new approach is introduced for the construction of a predictive quantitative structure-activity relationship model in which only ligand-receptor (LR) interaction features are used as relevant descriptors. This approach combines the benefit of the random forest (RF) as a new variable selection method with the intrinsic capability of the artificial neural network (ANN). The interaction information of the ligand-receptor (LR) complex was used as molecular docking descriptors. The most relevant descriptors were selected using the RF technique and used as inputs of ANN. The proposed RF ANN (RF-LM-ANN) method was optimized and then evaluated by the prediction of pEC₅₀ for some of the azine derivatives as non-nucleoside reverse transcriptase inhibitors. RF-LM-ANN model under the optimal conditions was evaluated using internal (validation) and external test sets. The determination coefficients of the external test and validation sets were 0.88 and 0.89, respectively. The mean square deviation (MSE) values for the prediction of biological activities in the external test and validation sets were found to be 0.10 and 0.11, respectively. The results obtained demonstrated the good prediction ability and high generalizability of the proposed RF-LM-ANN model based on the MMDs alone.

Prediction of the maximum nonseizure load of lubricant additives

Lubricating additives can improve the lubricant performance of base oil in reducing friction and wear and minimizing loss of energy. It is of great significance to study the relationship between chemical structures and lubrication properties of lubricant additives. This paper reports a quantitative structure–property relationship (QSPR) model of the maximum nonseizure loads ([Formula: see text]) of 79 lubricant additives by applying artificial neural network (ANN) based on the algorithm of backward propagation of errors. Six molecular descriptors appearing in the multiple linear regression (MLR) model were used as vectors to develop the ANN model. The optimal condition of ANN with network structure of [6-4-1] was obtained by adjusting various parameters by trial-and-error. The root-mean-square (rms) errors from ANN model are [Formula: see text] ([Formula: see text]) for the training set and [Formula: see text] ([Formula: see text]) for the test set, which are superior to the MLR results of [Formula: see text] ([Formula: see text]) for the training set and [Formula: see text] ([Formula: see text]) for the test set. Compared to the existing model for [Formula: see text], our model has better statistical quality. The results indicate that our ANN model can be applied to predict the [Formula: see text] values for lubricant additives.

Application of linear and non-linear methods for modeling removal efficiency of textile dyes from aqueous solutions using magnetic Fe3O4 impregnated onto walnut shell

The performance of the Nano-magnetite Fe₃O₄ impregnated onto walnut shell (Fe₃O₄-WNS), which possessed the adsorption features of walnut shell and the magnetic property of Fe₃O₄, was investigated for the elimination of the methyl violet and Rhodamine 6G from contaminated aqueous solutions. The effects of different experimental variables on the removal efficiency of the cited dyes were examined. Then these variables were used as the inputs to generate linear and non-linear models such as the multiple linear regression, random forest, and artificial neural network to predict the removal efficiency of these dye species at different experimental conditions. The validation studies of these models were performed using the test set, which was not present in the modeling procedure. It was found that ANN had a higher ability to predict the adsorption process under different experimental conditions, and could be applied for the development of an automated dye wastewater removal plant. Also the maximum adsorption capacity (q_max) indicated that the q_max value for Fe₃O₄-WNS for removal of cationic dyes was comparable or better than that for some reported adsorbents. Also it should be cited that exhausted Fe₃O₄-WNS was regenerated using dishwashing liquid, and reused for removal of the cited dye species from aqueous solutions.

QSAR methods for the discovery of new inflammatory bowel disease drugs

INTRODUCTION

Inflammatory bowel disease (IBD) represents an important class of chronic gastrointestinal tract disease. And although there are already several useful treatments to reduce and control the symptoms, there is still no cure. One drug discovery technique used is the computer-aided (in silico) discovery approach which has largely demonstrated efficacy. Computational techniques, when used in combination with traditional drug discovery methodology, greatly increase the chance of drug discovery in a sustainable and economical fashion.

AREAS COVERED

This review aims to provide the most recent and important advances of in silico IBD drug discovery. While this review is mainly focused on QSAR methods, especially those based on molecular topology (MT), additional topics, such as docking or comparative field analysis are also addressed.

EXPERT OPINION

IBD is a worldwide growing health concern that can only be currently treated in symptomatic and palliative way; thus, the search for new drugs is imperative. Computer-aided methods, which focus on the drug-receptor interaction, are essential tool in this regard. It is noted, however that a major problem is that although there are many known receptors associated with IBD, none of these have yet been found essential. The use of other approaches, including QSAR methodology, is certainly a complementary and attractive alternative; especially QSAR methods based on MT, which has proven successful in other drug discovery.