Rapid lead discovery in the drug development process relies on highthroughput screening of diverse compounds against protein targets. These compounds come from traditional organic synthesis, natural products isolation, and combinatorial synthesis ( 1 ). For compounds from combinatorial synthesis, the hit rate highly depends on the quality of the compounds. We employ parallel solid-phase ( 2 ) and solution-phase ( 3 ) synthesis methods to make lead discovery libraries containing approx 6000 compounds in each library. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.