Researchers use AI to find non-opioid pain relief options

An estimated one in five Americans suffer from chronic pain, and current treatment options leave much to be desired. Feixiong Cheng, Ph.D., director of the Genome Center at the Cleveland Clinic, and IBM are using artificial intelligence (AI) for drug discovery for advanced pain management. The team’s deep learning framework identified several gut microbiome-derived metabolites and FDA-approved drugs that can be repurposed to select non-addictive, non-opioid options to treat chronic pain.

The results, published in Cell Press, represent one of many ways the Discovery Accelerator partnership between the organizations is helping to advance research in healthcare and life sciences.

Treating chronic pain with opioids remains a challenge due to the risk of serious side effects and addiction, says co-first author Yunguang Qiu, Ph.D., a postdoctoral researcher in Dr. Cheng’s lab whose research program focuses on focuses on developing therapies for nerve treatment. system disorders. Recent evidence has shown that treating a specific subset of pain receptors in a class of proteins called G protein-coupled receptors (GPCRs) can provide non-addictive, non-opioid pain relief. The question is how to target these receptors, says Dr. Qiu.

Instead of inventing new molecules from scratch, the team wondered if they could apply the research methods they had already developed to find pre-existing FDA-approved drugs for a potential pain indication. . Part of this process involves mapping gut metabolites to spot drug targets.

To identify these molecules, first author and computer scientist Yuxin Yang, Ph.D., a former graduate student at Kent State University. Dr. Yang completed his dissertation in Dr. Cheng’s lab and continues to work there as a data scientist. Drs. Yang and Qiu led a team to update a previous drug discovery AI algorithm that the Cheng lab had developed. IBM collaborators helped write and edit the manuscript.

“Our IBM collaborators have given us valuable advice and insight in developing advanced computing techniques,” says Dr. Yang. “I am excited to have the opportunity to work with and learn from industry peers.”

To determine whether a molecule will work as a drug, researchers must predict how it will physically interact with and influence proteins in our body (in this case, our pain receptors). To do this, researchers need a 3D understanding of both molecules, based on extensive 2D data on their physical, structural and chemical properties.

“Even with the help of current computational methods, combining the amount of data we need for our predictive analyzes is extremely complex and time-consuming,” says Dr. Cheng. “AI can quickly take full advantage of compound and protein data obtained from imaging, evolutionary and chemical experiments to predict which compound is most likely to correctly influence our pain receptors.”

The research team’s tool, called LISA-CPI (Ligand Image- and Receiver’s three-dimensional (3D) Structures-Aware framework to predict compound-protein interactions) uses a form of artificial intelligence called deep learning to predict:

• whether a molecule can bind to a specific pain receptor

• where on the receptor a molecule will physically attach

• the strength with which the molecule will attach to this receptor

• whether binding of a molecule to a receptor will activate or deactivate signaling effects

The team used LISA-CPI to predict how 369 gut microbial metabolites and 2,308 FDA-approved drugs would interact with 13 pain-associated receptors. The AI ​​framework identified several compounds that could be repurposed to treat pain. Studies are underway to validate these compounds in the laboratory.

“The predictions from this algorithm can reduce the experimental burden that researchers must overcome to compile 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 treatments that treat diseases beyond pain, like Alzheimer’s disease.”

Dr. Cheng added that this is just one example of how the team is collaborating with IBM to develop basic models of small molecules for drug development, including both reuse of drugs in this study and an ongoing new drug discovery project.

“We believe these core models will deliver powerful AI technologies to rapidly develop treatments for multiple challenging human health problems,” he says.