Identification of inhibitors of the Human Papillomavirus type 5 replication using high-throughput screening and machine learning

Abstract

Human papillomaviruses (HPVs) have been known to cause a wide variety of health complications from warts to cancer. Although vaccination against several high-risk types of HPVs is available, there is currently no treatment method that would target already established infections. The focus of this study is to perform high-throughput screening of 1584 randomly selected chemicals in order to identify potential inhibitors of the HPV type 5 replication, and then use machine learning to predict interactions between those compounds and proteins expressed in basal keratinocytes, the only cell type that supports HPV replication. At the end of this study, several potential inhibitors were discovered and connections were made to proteins and pathways absolutely necessary for the replication of the viral genome or occurrence of the cancer.