On July 23, 2026, the Center for Technology Transfer and Commercialization (CTTC) hosted 280 people – mostly Vanderbilt, but with a wide spread of industry, too – at the Student Life Center. With an industry audience in mind, they showcased AI-based research developed at Vanderbilt, especially in the domains of protein dynamics and drug discovery.
These early adopters of AI illustrate Vanderbilt’s unique strategic advantage in applying AI tools to life science data. With our world-leading expertise on generating structured biomedical data (e.g., tools like BioVU, the Synthetic Derivative, or REDCap), we can use AI tools to analyze and gain insight into those big data.
Industry representatives included those from Amazon Web Services, Bristol Myers Squibb, Regeneron, NashBio, and Genentech. They presented their challenges in AI adoption and how they suggest academia could help them with tools, public data, and cohorts.
Vanderbilt speakers gave most of the presentations, describing how LLMs, with enough data, can move beyond mere memorization of terms into the grammar of processes to predict protein structure, molecular dynamics, high-throughput screens, and antibody generation. Most people think of LLMs like Chat-GPT as text-generation and text-prediction tools, but provided enough data, other LLMs have been trained to instead analyze certain kinds of data, like protein structures or other molecules. Like their own “language,” these data form a “corpus” that AI can analyze and figure out its own “grammatical structure” to predict how new molecules will act.
Several speakers focused on how molecules could be designed to target RNA pockets, antigens, and other microbiological features. Ivelin Georgiev’s lab was able to test generating target-specific antibodies against a recent hantavirus outbreak. Allison Walker’s lab isolated four natural products for drug discovery through AI prediction; these natural products are the elements often used to form 50% of new drug therapies. Carlos Oliver’s lab generated computational software used to identify relevant protein structures for drug targets. Ben Brown’s lab works on generative prediction models for molecular discovery. Ken Lau and Laurie Novak described the myriad capabilities in Vanderbilt’s research centers that use AI in the life sciences.
Vanderbilt resources filled the table representatives, including the VALIANT Lab, the Center for Computational Systems Biology, and the Department of Biomedical Informatics. They advertised their copious resources and efforts in the domain of AI and healthcare.
To conclude, a panel with industry perspectives along with Colleen Niswender discussed looming issues in AI adoption, like whether humans or AI will drive research; getting clean, structured data for AI to process; and how AI will change student training.
