Drug discovery and development is an incredibly important yet capital intensive, lengthy and low efficiency process. In recent years, biology and chemistry has become increasingly high-throughput and data-driven thanks to massively parallel sequencing, robotic liquid handling robots, advanced imaging techniques and more. This has opened up the opportunity for machine learning techniques to not only improve experimental analysis but also to generate novel experimental hypotheses that are worth testing. For example, machine learning models can be used in virtual screens where they generate candidate molecules that are likely to have a desired phenotypic effect. While the number of virtual screens is increasing, there are fewer studies that close the loop with empirical results.