An artificial intelligence (AI)-based technology for designing personalized cancer vaccines to optimize anticancer effects for each individual has been developed. This approach adds B cell reactivity to neoantigens, which are unique markers that distinguish cancer cells. In this way, the cancer vaccine not only provides a one-time attack and short-term memory, but also enables the immune system to 'remember cancer in the long term,' thereby effectively preventing cancer recurrence.
KAIST announced on January 2 that a research team led by Professor Choi Junggyun from the Department of Bio and Brain Engineering, in collaboration with Neogen Logic Co., Ltd., has developed a new AI model to predict neoantigens and has identified the importance of B cells in immuno-oncology.
The joint research team developed an AI-based neoantigen prediction technology that integrates the reactivity of both T cells and B cells, moving away from the conventional approach that relied solely on predicting T cell reactivity in neoantigen discovery.
This technology is regarded as the first AI technology capable of quantitatively predicting B cell reactivity to neoantigens. The joint research team validated the technology using large-scale cancer genome data, animal experiments, and clinical trial data on cancer vaccines.
Neoantigens are antigens composed of protein fragments derived from mutations in cancer cells. Because they are specific to cancer cells, they are attracting attention as key targets for next-generation cancer vaccines.
Previously, Moderna and BioNTech used the mRNA platform they developed while advancing neoantigen-based cancer vaccine technology to create COVID-19 vaccines. These companies are currently conducting active clinical trials of cancer vaccines in collaboration with global pharmaceutical firms.
However, most current cancer vaccine technologies focus on T cell-mediated immune responses and fail to sufficiently reflect immune responses mediated by B cells.
For example, in May last year, a research team led by Professors Mark Yarchoan and Elizabeth Jaffee at Johns Hopkins University pointed out in Nature Review Cancer that "despite accumulating evidence for the role of B cells in tumor immunity, most cancer vaccine clinical trials still focus only on T cell responses."
In contrast, the new AI model developed by the joint research team overcomes existing limitations by learning the structural binding characteristics between mutant proteins and B cell receptors (BCRs) to predict B cell reactivity.
In particular, analysis of cancer vaccine clinical trial data confirmed that when B cell responses are also comprehensively considered, the actual antitumor immune effect in clinical settings can be enhanced.
Professor Choi stated, "Our research team is currently conducting preclinical development of a personalized cancer vaccine platform with Neogen Logic and is preparing to submit an 'FDA IND' (the process of obtaining clinical trial approval from the U.S. Food and Drug Administration) with the goal of entering clinical trials next year." He added, "We plan to enhance the scientific completeness of cancer vaccine development with our proprietary AI technology and to gradually transition to the clinical stage."
Meanwhile, Dr. Kim Jungyeon and Dr. Ahn Jinhyun participated as co-first authors in this study. The research results were recently published in the international journal Science Advances.
© The Asia Business Daily(www.asiae.co.kr). All rights reserved.
