Using AI to Transform Medical Research Landscape

(EDITOR’S NOTE: This story was originally published in the fall 2025 issue of the UB Medicine alumni magazine.)

By Dirk Hoffman

AI rapidly analyzes massive datasets — such as genomic data, clinical trial results, and electronic health records — to identify patterns and insights. Machine learning algorithms improve diagnostic accuracy in areas such as imaging and pathology.

AI models can also predict how compounds interact with biological targets, significantly speeding up drug discovery and reducing costs.

Ram Samudrala, PhD, professor of biomedical informatics and chief of the Division of Bioinformatics, has created the Computational Analysis of Novel Drug Opportunities (CANDO) platform to make drug discovery faster and less expensive while also being safe and effective.

CANDO has already led to the creation of innovative biotech startups like AmritX, Meditati and Mansarover Therapeutics, companies that are using the platform to develop treatments for non-small cell lung cancer, opioid use disorder and aging, respectively.

Traditional drug discovery often takes more than a decade to produce results. 

Samudrala wanted a smarter and faster way, so he created a platform that looks at how compounds affect the whole body, not just one protein.

“CANDO simulates how thousands of compounds interact with the human body at once — like running millions of experiments in seconds,” Samudrala says.

AI is at the heart of CANDO — using machine learning to analyze huge datasets of drug-protein interactions, predict new uses for existing drugs and design new ones with optimal properties.

“Think of AI in CANDO as the engine that sifts through the noise to find hidden patterns and connections that no human could easily spot,” Samudrala says.

Thomas D. Grant, PhD ’13, assistant professor of structural biology, is also interested in developing drugs faster, but with a focus on precision medicine to enable the drugs to be designed for individual patients based on their own DNA.

Grant’s latest National Institutes of Health funding is aimed at revolutionizing the way proteins are studied in their natural environment.

To accomplish this, Grant is employing a technique called SWAXS (small- and wide-angle X-ray scattering) in combination with computational AI tools.

Grant uses SWAXSFold, an AI model he developed using the computing capacity of Empire AI, the $500 million New York State-based research consortium advancing artificial intelligence for the public good.

Empire AI’s computing center, located at the University at Buffalo, is a major resource for the researchers.

“Empire AI is a big part of this, as we wouldn’t be able to do this level of computation without it,” Grant says.

Grant and his colleagues are also developing tools that will help researchers understand how disease-causing mutations change protein structure.

“If we can see exactly how a mutation alters a protein’s shape and function, we can design personalized therapies targeted to that specific change,” he says.