Inhibitors for the hepatitis C virus RNA polymerase explored by SAR with advanced machine learning methods

Abstract

Hepatitis C virus (HCV) is a global health challenge, affecting approximately 200 million people worldwide. In this study we developed SAR models with advanced machine learning classifiers Random Forest and k Nearest Neighbor Simulated Annealing for 679 small molecules with measured inhibition activity for NS5B genotype 1b. The activity was expressed as a binary value (active/inactive), where actives were considered molecules with IC50 ≤ 0.95 μM. We applied our SAR models to various drug-like databases and identified novel chemical scaffolds for NS5B inhibitors. Subsequent in vitro antiviral assays suggested a new activity for an existing prodrug, Candesartan cilexetil, which is currently used to treat hypertension and heart failure but has not been previously tested for anti-HCV activity. We also identified NS5B inhibitors with two novel non-nucleoside chemical motifs.

Molecular simulations to delineate functional conformational transitions in the HCV polymerase

“…The fact that mammalian cells lack a homologous enzyme also makes NS5B an attractive drug target due to the potential for selective inhibition of viral replication. Consequently, this enzyme has been the object of numerous studies in the last decade . Both nucleoside (of which sofosbuvir is an example) and non‐nucleoside inhibitors have demonstrated activity against the enzyme.…”

Improved prediction of drug-target interactions using regularized least squares integrating with kernel fusion technique

“…In this work, it is predicted to interact with hsa2099 (Estrogen receptor 1). To validate this prediction, we searched the bioactivity data of D00182 in the PubChem BioAssay database [30], which has been successfully used by many studies [31–34]. It is interesting that both the confirmatory assays deposited by Tox21 (PubChem BioAssay ID: AID 743075 and AID 743079) and the binding assay from ChEMBL [35] (AID 625258) support our prediction.…”

Development and implementation of (Q)SAR modeling within the CHARMMing web-user interface

“…An introduction to the use of the SAR and QSAR application presented here is described in more detail in the form of tutorials located at www.charmmtutorial.org. 44,45,46,1 These tutorials provide a guided example with a detailed explanation of each step of the process and a definitely correct answer; the same data set employed for the study of NS5B 23 is currently used.…”

“…22 We identified novel non-nucleoside chemical motifs and Candesartan cilexetil (a drug used to treat hypertension and heart failu re) 23 for NS5B, hepatitis C virus RNA polymerase activity. Herein, we describe the development of a general (Q)SAR infrastructure based around the CHARMM Web-user interface, charmming.org to be used to build these types of models.…”