Drug Designing: Open Access
Open Access

A decision support system for the identification of synthetically accessible HCV inhibitors

International Conference and Exhibition on Computer Aided Drug Design & QSAR

October 29-31, 2012 DoubleTree by Hilton Chicago-North Shore, USA

Georgia Melagraki and Antreas Afantitis

Accepted Abstracts: Drug Design

Abstract :

Chronic infection with hepatitis C virus (HCV) is associated with liver cirrhosis that often leads to hepatic failure and hepatocellular carcinoma (HCC). Although the number of new infections has been significantly reduced by the introduction of reliable blood testing, more than 170 million people world-wide are chronically infected with hepatitis C virus (HCV), which has become a global health threat and the main cause of adult liver transplants in developed nations. There is as yet no effective therapy for HCV-associated chronic hepatitis and current therapies still call for major improvements. In this work we have developed an in silico workflow for the exploration of the relationship between the structural characteristics of compounds and their HCV inhibition activity. Among a pool of 777 descriptors the most important features responsible for the HCV inhibition activity were identified. Different machine learning and variable selection methodologies have been explored individually and in combination. One of the common core structures identified in the study has been used for data mining databases of commercially available chemicals to identify more similar molecules in terms of structural, pharmacophore, shape similarity and scaffold relatedness. Several promising synthetically accessible small molecules have been identified with our database mining methods which are based on principles of chemical similarity to a probe (lead compound) and/or predictions from in silico models and/or chemical space. In addition solubility and toxicity prediction studies have been performed by applying in house models. The proposed methodology utilize multiple sources of information rather than just activity assay data. The series of compounds identified in silico by the proposed workflow, will be evaluated in vitro. Acknowledgement: The research leading to these results has received funding from the European Union?s Seventh Framework Program (FP7/2007-2013) under grant agreement no 267429 (SysPatho).