Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Jan 24;8(1):1506.
doi: 10.1038/s41598-017-19122-y.

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

Mohamed Abd Elaziz  1   2 , Yasmine S Moemen  3 , Aboul Ella Hassanien  4 , Shengwu Xiong  5
Affiliations

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

Mohamed Abd Elaziz et al. Sci Rep. .

Abstract

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 [Formula: see text] was 0.952 and 0.923 for the training and testing sets, respectively, using cross-validation, while [Formula: see text] was 0.8822 using leave-one-out (LOO).

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Figure 1
Figure 1
HCV inhibitors.
Figure 2
Figure 2
ANFIS layers.
Figure 3
Figure 3
The structures of experimental (aqua) and docked structure (orange) to 3HHK receptor.
Figure 4
Figure 4
Correlation matrix.
Figure 5
Figure 5
Training set results obtained by the proposed QSAR model (the output in the legend refers to the actual training set), (A) the predicted versus the actual, (B) the MSE and RMSE values, (C) the histogram of the Error.
Figure 6
Figure 6
Testing set results obtained by the proposed QSAR model (the output in the legend refer to the actual testing set), (A) the predicted versus the actual, (B) the MSE and RMSE values, (C) the histogram of the Error.
Figure 7
Figure 7
The Correlation results for the experimental PIC50 values versus the values predicted by the ALO-ANFIS model.
Figure 8
Figure 8
Williams plot for the ALO-ANFIS model with h* = 0.5.
Figure 9
Figure 9
Training set results obtained by the PSO-ANFIS QSAR model (the output in the legend refer to the actual testing set), (A) the predicted versus the actual, (B) the MSE and RMSE values, (C) the histogram of the Error.
Figure 10
Figure 10
Training set results obtained by the GA-ANFIS QSAR model (the output in the legend refer to the actual testing set), (A) the predicted versus the actual, (B) the MSE and RMSE values, (C) the histogram of the Error.
Figure 11
Figure 11
Testing set results obtained by the PSO-ANFIS QSAR model (the output in the legend refer to the actual testing set), (A) the predicted versus the actual, (B) the MSE and RMSE values, (C) The histogram of the Error.
Figure 12
Figure 12
Testing set results obtained by the GA-ANFIS model (the output in the legend refer to the actual testing set), (A) the predicted versus the actual, (B) the MSE and RMSE values, (C) The histogram of the Error.
Figure 13
Figure 13
The lowest and best hit in the current docking set were shown in hit (A–D) respectively.
Figure 14
Figure 14
The correlation between the PIC50, Bending energy and the 9 descriptors.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Simmonds P, et al. Evolutionary analysis of variants of hepatitis C virus found in South-East Asia: comparison with classifications based upon sequence similarity. Journal of General Virology. 1996;77:3013–3024. doi: 10.1099/0022-1317-77-12-3013. - DOI - PubMed
    1. Ramia S, Eid-Fares J. Distribution of hepatitis C virus genotypes in the Middle East. International Journal of Infectious Diseases. 2006;10:272–277. doi: 10.1016/j.ijid.2005.07.008. - DOI - PubMed
    1. Watson JP, Al-Mardini H, Awadh S, Ukabam S, Record CO. Hepatitis C virus genotypes in a cohort of Middle Eastern patients. Annals of Saudi medicine. 1999;19:410–412. doi: 10.5144/0256-4947.1999.410. - DOI - PubMed
    1. Fallahian F, Najafi A. Epidemiology of hepatitis C in the Middle East. Saudi Journal of Kidney Diseases and Transplantation. 2011;22:31. - PubMed
    1. Craxì A, et al. EASL clinical practice guidelines: management of hepatitis C. J Hepatol. 2011;55:245–64. doi: 10.1016/j.jhep.2011.02.023. - DOI - PubMed

Publication types

MeSH terms

Substances

LinkOut - more resources