Agentic AI: From new targets to the clinic

IQVIA’s Greg Lever joins the BioCentury This Week podcast to discuss AI’s promise in drug development

AI is bringing sweeping changes to drug development, from how targets are discovered to optimizing clinical trials to maximize an asset’s chance for success. On a special edition of the BioCentury This Week podcast, IQVIA’s Greg Lever joins BioCentury’s analysts to discuss agentic AI’s short- and long-term prospects to help biotechs discover new targets, predict success in preclinical development, and enhance clinical operations. 

Agentic AI, Lever said, offers smaller biotechs the ability “to compete at scale, whether it’s identifying novel opportunities, designing smarter trials, [or] accelerating development with fewer resources.” It can also help predict future trends in a disease area and de-risk pipelines.

“It’s the sort of thing that may enable a biotech to move beyond just incremental innovation and actually pursue some truly novel approaches,” said Lever, director of AI solutions delivery at IQVIA Holdings Inc. (NYSE:IQV), parent organization of BioCentury This Week sponsor IQVIA Biotech.

For target discovery, AI can mitigate pain points such as fragmented data sources or a company’s limited resources for taking on in-depth landscape analyses, thereby reducing the risk of missing opportunities. 

Once a company has identified its target, AI tools can help it increase its confidence in designing a development strategy.

“AI agents are going to increasingly be used to assess things like technical, regulatory, operational success, and really how [small biotechs] can reduce their risk,” he said.

He envisions creating end-to-end systems by employing separate agents optimized for specific tasks, then synthesizing their outputs via an “orchestrator agent.”

For example, he said, one agent could look at mechanisms of action and patient populations of approved drugs for a particular indication. A second agent could evaluate the scientific literature and conference abstracts, while a third could analyze existing clinical trials. The orchestrator agent would be designed to generate insights across these specialized agents.

“By extension,” he added, “we can utilize existing molecular design approaches or target design approaches to say, ‘Is there some better design that I could think of here that will really accelerate my clinical development?’”

AI is also dramatically transforming trial design, Lever said, with users quantifying site and patient burden, assessing and optimizing protocols and simulating operational outcomes.

“We know there’s uncertainty in these operational outcomes, and also we know that the biotechs have these resource constraints,” Lever said. “You can begin to demonstrate this value and sort of leapfrog across a lot of these constraints by utilizing AI.” 

De-risking investment decisions was another potentially impactful application of the tech that Lever discussed. Different AI approaches, he said, “could be helpful in attracting investment, utilizing these approaches to give this more objective, data-driven view of asset risk, but also asset value.”

For now, Lever said, it might be best to leave clinical trial simulations to deep pocketed pharmas.