Affiliations: Molecular Epidemiology & Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA, USA | Department of Molecular Microbiology and Immunology, Saint Louis University School of Medicine, MI, USA | Saint Louis University Liver Center, Saint Louis University School of Medicine, Saint Louis, MI, USA | Divisions of Digestive and Liver Disease and Infectious Diseases, UT Southwestern Medical Center at Dallas, Dallas, TX, USA | Center for Hepatitis C, Atlanta Medical Center, Atlanta, GA, USA
Note:  Corresponding author: James Lara, Molecular Epidemiology & Bioinformatics Laboratory, Division of Viral Hepatitis, Centers for Disease Control and Prevention, Atlanta, GA, USA. E-mail: [email protected].
Abstract: Machine-learning methods in the form of Bayesian networks (BN), linear projection (LP) and self-organizing tree (SOT) models were used to explore association among polymorphic sites within the HVR1 and NS5a regions of the HCV genome, host demographic factors (ethnicity, gender and age) and response to the combined interferon (IFN) and ribavirin (RBV) therapy. The BN models predicted therapy outcomes, gender and ethnicity with accuracy of 90%, 90% and 88.9%, respectively. The LP and SOT models strongly confirmed associations of the HVR1 and NS5A structures with response to therapy and demographic host factors identified by BN. The data indicate host specificity of HCV evolution and suggest the application of these models to predict outcomes of IFN/RBV therapy.