AI Discovers New Non-Opioid Pain Relief Options

Chronic pain affects approximately one in five Americans, yet current treatment options often fall short of providing relief without significant side effects. Now, thanks to the work of Dr. Feixiong Cheng, Director of Cleveland Clinic's Genome Center, and his team, AI may offer new solutions for non-addictive pain relief. Partnering with IBM, the researchers are utilizing AI to repurpose FDA-approved drugs and gut microbiome-derived metabolites as non-opioid alternatives for treating chronic pain.

Breakthroughs in Pain Management Using AI

The findings, published in Cell Press, stem from the Discovery Accelerator partnership between Cleveland Clinic and IBM. The team’s deep-learning AI framework identified several compounds that target pain receptors without the risk of addiction or the severe side effects associated with opioid use.

According to Yunguang Qiu, Ph.D., a postdoctoral fellow in Dr. Cheng’s lab, treating chronic pain with opioids remains problematic due to the dependency risks. However, recent research has shown that targeting G protein-coupled receptors (GPCRs) may provide a pathway to non-addictive pain relief. The challenge, Dr. Qiu explains, is figuring out how to target these receptors effectively.

Repurposing Existing Drugs Through AI

Instead of developing new molecules from scratch, Dr. Cheng’s team turned to existing FDA-approved drugs. They focused on identifying metabolites from the gut microbiome that could potentially target these pain receptors. By repurposing existing compounds, they aimed to find faster, more accessible solutions to chronic pain management.

Using AI-powered drug discovery tools, Dr. Cheng’s team was able to map gut metabolites and identify potential drug candidates. A key contributor to this research, Yuxin Yang, Ph.D., who completed his thesis in Dr. Cheng’s lab, collaborated with IBM scientists to enhance the AI algorithm used in the study.

“Our IBM collaborators provided valuable advice that helped us develop advanced computational techniques,” Dr. Yang says. “I'm happy for the opportunity to work with and learn from peers in the industry sector.”

The Role of AI in Drug Discovery

To determine whether a molecule might work as a drug, the researchers needed to predict how the molecule would interact with pain receptors in the body. This required a 3D understanding of both the drug and the receptor, drawn from vast amounts of 2D data on the compounds’ physical, structural, and chemical properties.

Dr. Cheng explains, “AI can rapidly make full use of both compound and protein data gained from imaging, evolutionary and chemical experiments to predict which compound has the best chance of influencing our pain receptors in the right way.”

The team developed an AI tool called LISA-CPI (Ligand Image- and receptor's three-dimensional Structures-Aware framework to predict Compound-Protein Interactions). This tool uses deep learning to predict:

• Whether a molecule can bind to a specific pain receptor

• Where the molecule will attach to the receptor

• The strength of the molecule's attachment

• Whether binding the molecule will turn receptor signaling on or off

Promising Results for Non-Opioid Pain Relief

Using LISA-CPI, the team analyzed how 369 gut microbial metabolites and 2,308 FDA-approved drugs interacted with 13 pain-associated receptors. The AI framework identified several compounds that could be repurposed to treat pain. Ongoing lab studies aim to validate these findings.

“This algorithm's predictions can lessen the experimental burden researchers must overcome to even come up with a list of candidate drugs for further testing,” says Dr. Yang. “We can use this tool to test even more drugs, metabolites, GPCRs and other receptors to find therapeutics that treat diseases beyond pain, like Alzheimer's disease.”

Expanding AI's Role in Drug Discovery

Dr. Cheng sees the success of LISA-CPI as just one step in their collaboration with IBM. The team is also working on novel drug discovery projects using AI to create small molecule foundation models, which will help rapidly develop therapeutics for a range of health issues.

“We believe that these foundation models will offer powerful AI technologies to rapidly develop therapeutics for multiple challenging human health issues,” says Dr. Cheng.

What This Means Moving Forward

This AI-driven approach offers new hope for treating chronic pain without the risk of opioid addiction. By repurposing existing drugs and identifying gut microbiome-derived compounds, researchers can rapidly test and validate new therapies. As AI technology advances, it will likely open new doors for pain management and therapeutic discovery, potentially transforming the healthcare landscape in the years to come.