Pioneering Motion-Based Drug DesignTM
Dynamo leverages unparalleled insights into protein dynamics and function to create a new drug discovery paradigm.
Relay Therapeutics® was built to integrate a broad and tailored array of leading-edge experimental and computational techniques with a company culture that fosters deep collaboration between these previously disparate fields. We are committed to continuously incorporating new experimental and computational techniques to enhance the power of our platform and push the boundaries of what’s possible in drug discovery.
Enables Motion Based
Motion-Based Drug Design
Our Dynamo platform puts protein dynamics at the heart of our drug discovery process. We deploy our Dynamo platform in three key phases of Motion-Based Drug Design.
Hit Finding and
Target Modulation Hypothesis
First, we use our team’s substantial protein engineering know-how to synthesize full length proteins. Next, we use a range of protein visualization methods such as Cryo-EM and Room Temperature X-Ray Crystallography to generate a rich experimental understanding of the dynamic conformations of the target protein of interest.
We then deploy these experimental data sets in our computational platform, using a custom-built supercomputer called Anton 2 to generate virtual simulations (molecular dynamics) of the full-length protein moving over long, biologically relevant timescales. The Anton supercomputer, which we have access to via our collaboration with D.E. Shaw Research, allows our team to routinely perform long timescale molecular dynamics simulations that would not be feasible on conventional GPUs or cloud computing resources.
We use these insights to develop unique hypotheses for how best to modulate a protein’s behavior, and to identify potential novel allosteric binding sites for new therapeutic agents.
Hit Finding and Lead Generation
The integration of our computational and experimental capabilities affords a deeper functional understanding of our targets and enables the design of physiologically relevant activity-based, ligand-centric and computational screens.
The data from these screens provides input for the machine learning components of the Dynamo platform, which enable us to rapidly identify starting points for our drug discovery programs.
This integration of computation and experimentation yields a larger number of chemical series and potential therapies to proceed into lead optimization.
Once we find a lead compound, we are no longer wholly dependent on hand-to-hand combat in the experimental wet lab to optimize it, which is both time consuming and expensive.
Instead, our Dynamo platform combines advanced machine learning models and molecular dynamics simulations in tight integration with our medicinal chemistry, structural biology, enzymology and biophysics capabilities to predict and design the compounds that will achieve the most desirable characteristics, including potency, selectivity, bioavailability and drug-like properties. This allows us to optimize molecules more rapidly and effectively