Dynamo Platform

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.

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.

Understand How To

Drug the Protein

Identify a Chemical

Starting Point

Optimize Until Development

Candidate Selected





Drug Design

Understand How To Drug the Protein

Our first step is to understand how to drug our protein target of interest. For each target, the initial goal is to better understand the structure and conformational dynamics of all domains of a protein to generate a target modulation hypothesis.

First, we synthesize full length proteins through our protein engineering expertise. Next, we use a range of protein visualization methods such as Cryo-EM and ambient 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 to generate virtual simulations (molecular dynamics) of the full-length protein moving over long, biologically relevant timescales. 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.


Swimming Simulation



Identify a Chemical Starting Point

Once we have identified potential binding pockets and established a target modulation hypothesis, we then transition into hit finding and lead generation to identify a chemical starting point.

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.

As an example of tools we deploy to identify these starting points, we have a proprietary capability, our machine learning powered DNA encoded library platform, what we term “REL-DEL” (Relay DEL). Our approach, focused on this integration of computation and experimentation yields a larger number of chemical series and potential therapies to proceed into lead optimization.


Dynamo Enables


Iterative Cycles

at Scale

Optimize Until Development Candidate Selected

Once we have identified a chemical starting point and a lead compound, optimization is necessary to obtain a molecule that has the desired characteristics.

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. We believe that this allows us to optimize molecules more rapidly and effectively.

Due to the integration of computation and experimentation and unlike traditional drug discovery approaches, our approach is not wholly dependent on the conventional highly iterative process in the experimental wet laboratory, which is both time consuming and expensive.