Skip to main content

Cleveland Clinic-IBM Partnership Trains AI on Cancer Research

Analysis  |  By Eric Wicklund  
   January 25, 2024

The collaboration is one of several between health systems and Big Tech to develop and scale AI programs

A partnership between the Cleveland Clinic and IBM is applying AI to cancer care, with the goal of creating better and more effective treatments.

In a study recently published in Briefings in Bioinformatics, the research team reported that it was able to use both supervised and unsupervised AI technology to better understand the molecular details of peptide antigens, the first step in using them to attack cancer cells or cells infected with viruses. Researchers can use this data to tailor vaccines and engineered immune cells.

“In the past, all our data on cancer antigen targets came from trial and error,” Timothy Chan, MD, PhD, chair of Cleveland Clinic’s Center for Immunotherapy and Precision Immuno-Oncology and Sheikha Fatima Bint Mubarak Endowed Chair in Immunotherapy and Precision Immuno-Oncology, said in a press release. “Partnering with IBM allows us to push the boundaries of artificial intelligence and health sciences research to change the way we develop and evaluate targets for cancer therapy.”

The research proves the value of using AI to gather and analyze data faster and more accurately. According to the Cleveland Clinic team, antigen peptides interact with immune cells based on specific features on the surface of those cells.

“Research has been limited by the sheer number of variables that affect how immune systems recognize these targets,” Cleveland Clinic executives said in the press release. “Identifying these variables is difficult and time intensive with regular computing, so current models are limited and at times inaccurate.”

Using supervised and unsupervised algorithms “can highlight subtle but key determinants of peptide immunogenicity within the [atomistic molecular dynamics] trajectory data and can … provide significantly more predictive power over a baseline sequence architecture on peptide datasets,” the research team said in the study. 

“These insights highlight how MD can help predict and foster understanding of immunogenicity, and the methods developed here lay a framework for broad HLA [ human leukocyte antigen] allele studies to further elucidate mechanisms of immune responses and inform T cell therapies,” they concluded.

The project was borne out of Discovery Accelerator, a collaboration launched in 2021 to match Cleveland Clinic’s biomedical research capabilities with IBM’s AI and quantum computing technology. It’s one of several partnerships forged between health systems and Big Tech to expand access to AI tools for research as well as administrative and clinical services.

Eric Wicklund is the associate content manager and senior editor for Innovation, Technology, and Pharma for HealthLeaders.


Research into peptide antigens is often laborious and ineffective, due to the volume of data and high number of variables that affect how immune systems work.

Researchers at the Cleveland Clinic and IBM are using supported and unsupported AI to fine-tune that process, allowing them to better understand how peptide antigens work.

The research will help clinicians design more effective vaccines and immunotherapy treatments.

Get the latest on healthcare leadership in your inbox.