Structure-based virtual screening has gained momentum
again as
the high attrition rate at every stage of drug discovery drives the
need to explore a greater chemical space. From the Bayesian perspective,
its shortcomings as a viable strategy for sustainable hit discovery
are discussed, with regard to the prior hit rates of screening libraries
and the performance of computational methods. Lessons are shared in
selecting virtual hits for experimental validation learned from a
series of eight successful campaigns, one of which impacted the discovery
of a drug candidate currently in clinical trials.