The focus of our current research is to develop machine learning methods to accelerate molecular simulations. These surrogate models are of particular interest for the expansion of molecular discovery to larger chemical spaces of billions of chemicals.

Another research line focus in extending the accuracy of electronic Density Functional Theory (DFT) to systems in which electronic correlation plays a prominent role. In particular using machine learning methods and the Stricly Correlated Electron (SCE) formalism to help in the construction of improved approximate functionals.

We are particularly interested in developing new machine learning and physics-based tools to improve ligand discovery, as well as aiding the design of drug candidates with novel mechanisms of action. The ultimate goal of our research is to contribute to the development of novel therapeutics. One of the main applications of our work is on the investigation of proteins that can be pharmacologically targeted to combat drug resistance in cancer.