Virtual Screening Methods as Tools for Drug Lead Discovery from Large Chemical Libraries

Virtual screening methods have been developed and explored as useful tools for searching drug lead compounds from chemical libraries, including large libraries that have become publically available. In this review, we discussed the new developments in exploring virtual screening methods for enhanced performance in searching large chemical libraries, their applications in screening libraries of ~ 1 million or more compounds in the last five years, the difficulties in their applications, and the strategies for further improving these methods. Keywords: Machine learning, molecular docking, pharmacophore, quantitative structure activity relationship, similarity searching, support vector machines, Virtual screening, "cal libraries", "strategies"