Technology for the hardest challenges in small molecule discovery
Mapping protein surfaces for novel interaction features
PocketExpander™ can identify potential interaction features (light purple, charcoal grey and royal blue) to design molecular glues that span two proteins (grey and purple) and stabilize their interaction
Our proprietary PocketExpander™ uses AI and physics-based methods to identify physical and chemical features on the protein surface that can interact with small molecules. The technology includes quantum mechanical simulations to calculate binding energies and molecular dynamics simulations of protein folding.
DeepCure is able to pursue targets with no known ligand and to tackle tough challenges for small molecule discovery such as disrupting protein-protein interactions and designing molecular glues. Additional advantages include de novo design of molecules with less bias for known binders and designing molecules to exploit novel interactions on the protein surface to obtain new functions.
Truly novel molecules that are lead-like and synthesizable
Our molecular generation tool, MolGen™, generates custom libraries of compounds that are designed to selectively interact with features identified by PocketExpander™. The process leverages state-of-the-art deep reinforcement learning (RL) to build readily synthesizable molecules using millions of available building blocks and more than 200 robust chemical reactions. MolGen™ also ensures that each molecule has the desired ADME-Tox profile and target candidate profile (TCP).
With our MolGen™ technology, DeepCure’s researchers can explore large, diverse, and novel chemical spaces that are needed to identify solutions for challenging problems in drug design. At the same time, DeepCure can avoid bias toward existing libraries and known ligands, and ensure that synthetic feasibility is not limiting and compatible with accelerated timelines.
MolGen™ generates novel compounds (green) that are readily synthesizable and can selectively interact with the features identified by PocketExpander™ as well as meet ADMET and TCP requirements.
Turning AI designs into testable molecules
DiscoveryHub™ is a platform that is designed to ensure that every research team member can access the data, use the AI tools and contribute to each step of molecule design, synthesis and analysis.
Our DiscoveryHub™ platform was created to enable seamless sharing of data and molecule designs between structural biologists, computational chemists, AI engineers, medicinal chemists, biologists and project managers. The platform includes tools to design, visualize and evaluate compound structures as well as plan the optimal synthetic route for each molecule selected for synthesis.
These tools and our workflow are made to accelerate and improve design, make, test and analyze (DMTA) cycles. DiscoveryHub workflows have been rigorously validated for thousands of compounds to ensure the full enablement of our AI and physics-based technology, and they spur creativity and execution in drug discovery.