The development of a predictive model to identify potential HIV-1 attachment inhibitors

McGarry, Kenneth, Ashton, Mark, Gong, Yu and Hosny, Amer (2020) The development of a predictive model to identify potential HIV-1 attachment inhibitors. Computers in Biology and Medicine. ISSN 0010-4825

[img] PDF
QSAR_Hosny.pdf - Accepted Version
Restricted to Repository staff only until 1 April 2021.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Request a copy

Search Google Scholar

Abstract

Despite the significant progress in managing patients infected with HIV through the development of Highly Active Anti-Retroviral Therapy (HAART), major challenges and opportunities remain to be explored. Of particular interest, is the binding of glycoprotein 120 (gp120) to the primary cellular receptor Cluster of Differentiation 4 (CD4). In this work we describe our two phased computational process to identify useful compounds capable of binding to the gp120 protein for therapeutic purposes. We identified 187 compounds from the literature that conform to active binding sites on these proteins and use these as training/test sets. The data in the form of quantitative structure-activity relationships (QSAR) is downloaded from the ZINC database and transformed using principal components analysis. In the first phase we developed a Radial Basis Function neural network model that identifies potential inhibitors from a virtual screen of a subset of the ZINC database. In the second phase we modelled the top performing compounds using the Discovery Studio docking and screening software. By employing this approach, we identified that those compounds with a LogP value of approx 2-4 performed well in the binding simulations while the lower scoring compounds do not bind well.

Item Type: Article
Uncontrolled Keywords: HIV, gp120, CD4, QSAR, RBF, neural network, PCA
Subjects: Computing > Data Science
Computing > Artificial Intelligence
Sciences > Biomedical Sciences
Computing > Databases
Computing
Divisions: Faculty of Technology > School of Computer Science
Depositing User: Kenneth McGarry
Date Deposited: 06 Apr 2020 06:49
Last Modified: 16 Apr 2020 07:21
URI: http://sure.sunderland.ac.uk/id/eprint/11904
ORCID for Kenneth McGarry: ORCID iD orcid.org/0000-0002-9329-9835

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year