We use artificial intelligence (AI) technology to explain the physical and chemical nature of biological systems. We harness AI to accelerate drug discovery.

We aim to create and work from a data-driven foundation. We use a hybrid approach – computational drug design followed by wet lab validation – to greatly reduce the time and cost necessary for traditional drug discovery efforts.

We have developed a data-driven atom-based scoring function learned from 100,000 protein crystal structures containing the information of >100 million amino acid side chains and a dynamic deep neural network specifically designed for chemical informatics.

Our work beats the current industry gold standard in computation-aided drug discovery. We use drug pocket side chain conformation prediction and drug docking with a significantly increased accuracy compared to the standard methods. Our prediction of chemical compound characteristics (solubility, binding affinity, etc.) is also significantly better than the current standard.