Researchers at Texas A&M AgriLife are using artificial intelligence to improve the process of discovering new drugs for tuberculosis, a disease that remains a major global health threat. On July 29, James Sacchettini, Ph.D., a scientist and professor at Texas A&M AgriLife Research, described how his lab has developed AI tools to help scientists focus their efforts after initial drug screening and to organize years of collaborative data into a searchable form.
“When researchers screen potential tuberculosis drugs, they often end up with too many options. Some look promising but later prove to be costly dead ends. We might get thousands of compounds from a screen and then have to decide, which one are we going to work on?” Sacchettini said. “What information can we get that really helps us make decisions? If we can use AI to shorten the time it takes to go from an idea to a real treatment, that would be wonderful.”
The lab’s work is significant due to the persistent challenge tuberculosis poses. According to the World Health Organization, tuberculosis is the world’s deadliest infectious disease. Standard therapies can take months, and drug-resistant strains or co-infection with HIV can make treatment even longer. Sacchettini said, “People had thought, ‘oh, we cured that many years ago, right?’ Then it turned out that Rikers Island was completely covered with tuberculosis. People were getting out of prison and getting in an elevator with six other people, and by the time they got to the sixth floor, five other people were infected.”
To address the challenge of managing research data, Sacchettini’s lab built DAIKON, an open-source platform published in 2023, to track a drug target from gene to years of chemistry work in one place. The Gates Foundation-supported Tuberculosis Drug Accelerator uses DAIKON across its partnership of labs and companies. “We’re not hoping for AI to give us the exact right answer, but it can tell us what not to work on, which then informs us what we should be working on. And it really is a big time saver,” Sacchettini said.
The team also developed an AI model called CAGE-Fusion to identify false signals in early drug screening. “These ‘nuisance molecules’ cost us so much time. One goal is to identify them so we don’t spend months, years or hundreds of thousands of dollars working on them,” Sacchettini said. The model, funded by the Gates Foundation and the Welch Foundation, learns from published screening data to sort compounds into four categories of problematic behavior. Siddhant Rath, an AgriLife Research scientist, said, “The model can walk you through the process and show you which regions of the molecules it thought were problematic.”
Rath and colleague Saswati Panda also developed an AI system to sort through the Tuberculosis Drug Accelerator’s data, making it easier for researchers to trace molecules and access information. Sacchettini said, “It will tell me in a matter of seconds who presented something, what they said about it, and give me the presentation so I can see the slides.” The project received funding from the Gates Foundation, National Institutes of Health, and the Welch Foundation. Scientists around the world are introducing AI tools into different stages of drug design, and Sacchettini said the models his lab created are already helping make the process easier.
