Prospective Validation of HydraScreen: Virtual Screening and Hit Identification in IRAK1

In this proof-of-concept study, we combine Ro5's digital drug discovery platforms SpectraView and HydraScreen with Strateos' robotic cloud labs capabilities to augment and accelerate target and hit identification. Using SpectraView to select IRAK1 as the target, we prospectively validate HydraScreen, a structure-based deep learning model. We demonstrate that HydraScreen could identify up to 23.8% of all hit compounds by screening only 1% of the compound library, simultaneously identifying the three of the most potent (nanomolar) scaffolds present in the library. All three nanomolar scaffolds identified in our project are novel for IRAK1 and lend themselves for future development. HydraScreen outperforms traditional methods in an unbiased prospective evaluation and offers advanced features such as ligand pose confidence scoring. Thus, SpectraView and HydraScreen are innovative tools which can aid and expedite the stages of early drug discovery.