Quantitative Structure-Activity Relationship Model for HCVNS5B inhibitors based on an Antlion Optimizer-Adaptive Neuro-Fuzzy Inference System

Mohamed Abd Elaziz,Aboul Ella Hassanien,Yasmine S. Moemen,Shengwu Xiong

doi:10.1038/s41598-017-19122-y

Mohamed Abd Elaziz, Aboul Ella Hassanien + Show 2 more

Open Access

PDF Available

https://doi.org/10.1038/s41598-017-19122-y

Copy DOI

Export

Save

Cite

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

The global prevalence of hepatitis C Virus (HCV) is approximately 3% and one-fifth of all HCV carriers live in the Middle East, where Egypt has the highest global incidence of HCV infection. Quantitative structure-activity relationship (QSAR) models were used in many applications for predicting the potential effects of chemicals on human health and environment. The adaptive neuro-fuzzy inference system (ANFIS) is one of the most popular regression methods for building a nonlinear QSAR model. However, the quality of ANFIS is influenced by the size of the descriptors, so descriptor selection methods have been proposed, although these methods are affected by slow convergence and high time complexity. To avoid these limitations, the antlion optimizer was used to select relevant descriptors, before constructing a nonlinear QSAR model based on the PIC50 and these descriptors using ANFIS. In our experiments, 1029 compounds were used, which comprised 579 HCVNS5B inhibitors (PIC50 < ~14) and 450 non-HCVNS5B inhibitors (PIC50 > ~14). The experimental results showed that the proposed QSAR model obtained acceptable accuracy according to different measures, where {{boldsymbol{R}}}^{{boldsymbol{2}}} was 0.952 and 0.923 for the training and testing sets, respectively, using cross-validation, while {{boldsymbol{R}}}_{{boldsymbol{L}}{boldsymbol{O}}{boldsymbol{O}}}^{{boldsymbol{2}}} was 0.8822 using leave-one-out (LOO).

Highlights

The global prevalence of hepatitis C Virus (HCV) is about 3%4,5 and one-fifth of all HCV carriers live in the Middle East[2]
Dimensionality can be used to define the type of Quantitative structure-activity relationship (QSAR) used according to the chemical structure dimension. one-dimensional (1D)-QSAR describes the activity based on the total molecular properties such as logp and constitutional properties. 2D-QSAR associates the activity with the chemical structure such as a pharmacophore.3D-QSAR relates the activity to the interaction fields of molecules. 4D-QSAR is represented by using a group of 3D-ligand conformations, 5D-QSAR considers diverse induced-fit models of 4D-complexes, and 6D-QSAR includes various solvation models[20]
HCV NS5B is an interesting target for antiviral therapy with limited side effects and it has been the subject of extensive trials to develop nucleoside and non-nucleoside inhibitors

Summary

Introduction

The global prevalence of HCV is about 3%4,5 and one-fifth of all HCV carriers live in the Middle East[2]. The quantitative structure-activity relationship)QSAR(model has attracted much attention in pharmaceutical research because it can produce high-quality leads in the early stages of drug discovery[12]. QSAR was developed in physical chemistry, before being applied to data sets containing many thousands of compounds with varied molecular structures, while it evolved from modest regression approaches to wide-ranging statistical and machine learning methods. QSAR is used to determine the relationship between the chemical structural features (molecular descriptors) of compounds and their biological activity by using mathematical equations. Other studies have employed computational approaches to determine different effects of substituents on potency[18,19]. One-dimensional (1D)-QSAR describes the activity based on the total molecular properties such as logp and constitutional properties Dimensionality can be used to define the type of QSAR used according to the chemical structure dimension. one-dimensional (1D)-QSAR describes the activity based on the total molecular properties such as logp and constitutional properties (no. of atoms of oxygen, nitrogen, etc.). 2D-QSAR associates the activity with the chemical structure such as a pharmacophore.3D-QSAR relates the activity to the interaction fields of molecules. 4D-QSAR is represented by using a group of 3D-ligand conformations, 5D-QSAR considers diverse induced-fit models of 4D-complexes, and 6D-QSAR includes various solvation models[20]

Methods

Results

Conclusion