Our research advances drug discovery and materials discovery using machine learning. Our ethos is to go from lab to impact - testing our AI/ML advances with lab experiments, and launching scalable platforms from the science. Along the way, we develop fundamental statistical techniques to make sense of scientific data. You can see a selection of our ongoing projects below.
We are developing algorithms which will predict whether a small molecule will bind to a given receptor. Moreover, we are devising ways to search through the space of all possible compounds for drug candidates - even those never seen in nature or synthesized - and predict reactions that could synthesize them in the lab. In order to achieve this goal, we analyse why machine learning algorithms work, and come up with new algorithms, using methods in statistical physics.
Accelerate drug design with machine learning
Chemical virology and pandemic preparedness
A way to prepare against future pandemics is to preemptively discover drug candidates against viruses of pandemic concern, and ensuring these antiviral candidates can be accessed globally in a pandemic. We are building a non-profit that systematically elucidates promising new antiviral targets using genetics, discover chemical probes against these targets using machine learning, and develop these probes into clinic-ready drugs with an intentional access strategy that prioritizes global health.
Understanding and optimizing energy materials
We study the physics behind soft materials such as electrolytes and devices such as supercapacitors and batteries. In those materials, thermal fluctuations play an important role in determining their properties. We use both bottom-up approaches where modelling is used to provide insights, as well as top-down approaches where machine learning is used to fish out patterns directly from data. We also apply machine learning to understand inorganic materials where first principles models would struggle.