AI Transforms Drug Discovery at NCCU

The future of medicine is being written not only in laboratories, but also in lines of code at North Carolina Central University (NCCU).

Weifan Zheng, Ph.D., a professor in the department of pharmaceutical sciences, leads research placing NCCU at the intersection of artificial intelligence (AI), biomedical discovery and workforce development.

Accelerating the Search for New Medicines

Before joining NCCU, Zheng spent several years in the pharmaceutical industry working with computational machine learning, long before the term 'AI' became widely used.

On average, it takes more than a decade and costs $2.6 billion for a drug to reach the market, and only 12% of new molecular entities entering clinical trials are approved by the U.S. Food and Drug Administration, according to Pharmaceutical Research and Manufacturers of America.

Zheng's research aims to shorten that timeline and reduce costs by using AI to identify promising drug candidates before they are synthesized in a lab.

"We use computational tools to help scientists select potential drug molecules before they are even made," Zheng said. "If we can do as much work as possible inside the computer first, we can save enormous amounts of time and resources."

Through techniques such as biomedical text mining, knowledge graphs and deep neural networks, Zheng's lab analyzes scientific literature and biological data to uncover patterns researchers might otherwise miss.

Turning Data into Breakthroughs for Rare Diseases

One of the most significant applications of this work is happening through Zheng's collaboration with Kevin Williams, Ph.D., a professor of pharmaceutical sciences in the Biomanufacturing Research Institute and Technology Enterprise (BRITE), who has spent his career researching breast cancer therapeutics.

Williams focuses on inflammatory breast cancer (IBC), a rare and highly aggressive form of the disease that is difficult to diagnose because it does not typically form a lump and is often missed by routine mammograms.

According to the National Cancer Institute, IBC accounts for 1% to 5% of all breast cancer cases in the U.S., and approximately 8% to 10% of related deaths. It is more common in women younger than 40 and more prevalent in Black women.

"It's a hard disease to treat and a hard disease to diagnose," Williams said. "So, we're trying to find new ways to identify and target it."

Identifying potential treatments traditionally requires screening hundreds of thousands of compounds in the lab, a time-consuming and resource-intensive process. Together, Zheng and Williams are using AI to streamline that approach.

By applying text mining and machine learning models, Zheng's lab analyzes millions of studies to uncover connections between diseases and existing drugs, with the goal of identifying drugs that could be repurposed.

"The answer may already exist in the literature; we just can't find it by reading millions of papers," Williams said. "AI allows us to make those connections."

Their work has produced published research led by Xiaojia Ji, Ph.D., senior research scientist in Williams' lab, with AI-generated predictions now being tested in lab models. The collaboration also uses computational methods to analyze gene expression in cancer cells, identifying therapies that may help restore normal function.

"The AI gives us the prediction," Williams explained. "Then we validate it in the lab."

Unlocking New Uses for Existing Drugs

The approach is part of a broader focus on drug repurposing, identifying new medical uses for existing medications.

By analyzing large volumes of biomedical research, AI models can reveal connections between approved or previously tested drugs and diseases they were not originally designed to treat. Because many of these drugs already have established safety data, this approach can significantly shorten the path to clinical use.

"If a new disease emerges or an urgent health crisis happens, developing a new drug from scratch can take years," Zheng said. "But if we can identify an existing drug that might work, we can potentially move much faster."

Investigating the Root Causes of Disease

Beyond drug discovery, Zheng's research explores whether many diseases share a common biological origin.

His lab studies bioenergetics, the process by which the body converts nutrients into cellular energy. When this process breaks down, it may trigger a cascade of chronic conditions.

"If our cells cannot properly generate energy from the food we eat, many systems in the body begin to fail," Zheng said. "You may start to see diseases such as cancer, Alzheimer's or metabolic disorders."

AI as a Tool

Inside Zheng's lab, AI is a practical research tool.

Using the programming language Python alongside AI systems such as ChatGPT, Zheng and his students build computational models that analyze biomedical data and generate predictive insights.

"I jokingly say ChatGPT is my best technician," Zheng said. "It helps generate the code I need, and then my job is to verify and refine it."

A Platform for Collaboration

The partnership between Zheng and Williams highlights a broader strength at NCCU, collaboration across disciplines.

Williams, who has also worked with public health experts to raise awareness about IBC and improve diagnostic criteria, sees these cross-campus connections as essential to advancing research.

"The biggest lesson is to reach across disciplines," Williams said. "Whether it's AI, public health or clinical research, bringing those perspectives together is where real progress happens."

Preparing Students for the AI Era

While Zheng's research holds promise for the future of medicine, he believes its most immediate impact may be in the classroom.

At NCCU, undergraduate and graduate students participate directly in his research projects, learning to apply AI tools to real scientific questions.

Since 2023, more than 10 students have worked in Zheng's lab.

Biruktawit Sanbi, a graduate student in pharmaceutical sciences who earned her undergraduate degree from NCCU in December 2025, says the hands-on experience has reshaped how she approaches research.

"I've always been interested in pharmacy, but research helped me understand what happens behind the drugs, how they're developed and how they work," she said. "That's what made me want to focus more on the science."

After taking a data science course as an undergraduate, Sanbi began exploring how AI could enhance her research. She used tools like ChatGPT and biomedical databases to analyze large volumes of scientific literature and identify potential drug candidates for further study.

"You can't just rely on AI, you have to guide it and verify the results," she said. "It helps you move faster, but the responsibility is still on the researcher."

Now in her first semester of her master's degree program, Sanbi plans to continue working in AI-driven drug discovery and hopes to build a career as a scientist in the field.

"I want to contribute to developing drugs that can improve people's lives," she said.

"Students are the future," Zheng added. "Wherever they go, they will carry these tools and ideas with them."