September 14, 2023
Alexander Tropsha, Ph.D., is exploring unchartered territory through research into ways artificial intelligence and machine learning can help advance the drug discovery process.
Tropsha, a professor in the Division of Chemical Biology and Medicinal Chemistry at the UNC Eshelman School of Pharmacy and director of the Laboratory for Molecular Modeling, is an expert in the fields of computational chemistry, cheminformatics and structural bioinformatics who works to develop new methodologies and software tools for computer-assisted drug design.
His particular expertise lies in the field of cheminformatics, a discipline where information and informatics methodologies are applied to storing, managing, exploring and exploiting chemical databases. Cheminformatics combines chemistry and computer science to aid in the discovery of new drugs.
Early stages in modern drug discovery often involve screening small molecules for their effects on a selected protein target or a model of a biological pathway. Managing, understanding, analyzing and exploiting this data to enable rational design of new experiments requires skills and computational tools.
Recently, Tropsha, along with principal investigator Junier Oliva, Ph.D., a professor in the UNC Computer Science Department, received at two-year grant from the National Science Foundation for a new project, “Extrapolative Analyses for Reliable Machine Learning Driven Scientific Discovery”.
The goal is to give machines the ability to introspectively assess training set limitations and either address them or alert human users. This new project will directly impact the drug discovery process.
“In computer-assisted drug discovery, the molecules we design with machine learning use previously generated data on chemical bioactivity. This study will develop new approaches to assess confidence in our predictions of molecules as being biologically active,” Tropsha said. “We also don’t want to stay in the virtual world all the time—we need to find the practical application. Currently, a lot of work is being done with the READDI-AViDD project. That’s where the results of this theoretical grant will be applied.”
In addition to his role at the UNC Eshelman School of Pharmacy, Tropsha holds appointments as the chief domain scientist for molecular informatics at the Renaissance Computing Institute (RENCI) at Carolina, as well as an adjunct professor in the Department of Biomedical Engineering, the Department of Computer Science and the Department of Applied Physical Sciences. He was honored as the K. H. Lee Distinguished Professor in 2008.
Tropsha also wanted to thank James Wellnitz, graduate research assistant, and Travis Maxfield, his former postdoctoral research associate, for their contributions to this grant proposal and research.