According to koreatimes.co.kr, a joint research team from the Korea Advanced Institute of Science and Technology (KAIST) and local biotech company Neogenlogic says it has developed a new artificial intelligence platform designed to support a next-generation “personalized” cancer vaccine.
AI aims to tailor vaccines to each patient’s tumor
The platform is designed to pinpoint neoantigens—tumor-specific targets that can be used to train a patient’s immune system and potentially reduce the risk of cancer coming back.
“Neoantigens — mutation-derived protein fragments unique to a patient’s tumor — are the ‘fingerprints’ used by vaccines to train the immune system,”
the team, led by KAIST professor Choi Jung-kyoon, said in a press release.
Spotlight on B cells for longer-lasting protection
Most personalized cancer vaccine approaches have focused on activating cytotoxic T cells for an immediate immune attack, but the team says its work reflects growing evidence that B cell-driven immune memory may be crucial for durable, long-term responses.
“While current vaccines focus almost exclusively on activating cytotoxic T cells for immediate attack, emerging clinical evidence highlights that B cell-mediated immune memory is the key to durable, long-term antitumor responses and the prevention of recurrence,”
the team said.
Study published in Science Advances
The findings were published in the Dec. 3 issue of Science Advances, a peer-reviewed journal, the researchers said.
Predicting B cell responses alongside T cell targets
The team said the AI model predicts which neoantigens are most likely to generate a strong B cell response by learning structural interaction patterns between mutant peptides and B cell receptors.
“The study introduces the world’s first AI framework capable of predicting B cell immunogenicity alongside T cell responses for the design of personalized cancer vaccines,”
it said.
Company integration and clinical timeline
Neogenlogic said the approach was validated using large-scale genomic datasets and clinical trial data from global vaccine developers, and that the framework has been incorporated into its proprietary discovery engine, DeepNeo. Choi said the group is preparing an investigational new drug (IND) submission to the U.S. Food and Drug Administration, with the aim of entering clinical trials in 2027.
“While the academic community was aware that studying B cells is important in developing cancer vaccines, there were no tools to verify the concept,”
he told Yonhap News Agency.