Our Dynamo platform capitalizes on recent advances in experimental techniques such as room-temperature crystallography and cryoEM, and computational techniques such as long-timescale molecular dynamics simulations and machine learning, to enable a deep understanding of protein motion that will allow us to develop medicines optimized for specificity and potency.
Using a range of protein visualization methods, we can 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 to generate virtual simulations (molecular dynamics) of the full-length protein moving over long, biologically relevant timescales. We use these insights to develop unique motion-based hypotheses for how best to modulate a protein’s behavior, and to identify potential novel allosteric binding sites for new therapeutic agents.
The integration of our computational and experimental platforms affords a deeper functional understanding of our targets and enables the design of physiologically relevant activity-based, ligand-centric and computational screens. These highly differentiated screens yield a larger number of chemical series and potential therapies to proceed into lead optimization than conventional experimental techniques alone.
The Dynamo platform uses advanced machine learning models 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. Conventional optimization of small molecule lead compounds involves a highly iterative, time-consuming and capital-intensive process.