S. Korean team develops AI model for 'customised' cancer vaccine

Seoul, Jan 2 A joint research team of the Korea Advanced Institute of Science and Technology (KAIST) and domestic biotechnology firm Neogenlogic has developed a new artificial intelligence (AI) model that can help produce a whole new type of "personalized" cancer vaccine, the joint team said on Friday.

The new AI platform helps identify neoantigens unique to each cancer patient that can train the patient's immune system, and thus prevent recurrence of the illness, reports Yonhap news agency.

"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 professor Choi Jung-kyoon of KAIST, said in a press release.

"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," it added.

Such findings were published in the Dec. 3 edition of Science Advances, a peer-reviewed scientific journal.

According to the research team, its AI model predicts which neoantigens will trigger a "robust B cell response" by learning the structural interaction patterns between mutant peptides and B cell receptors (BCRs).

"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.

Professor Choi highlighted the significance of the study in that it provided empirical evidence on the importance of B cells in developing cancer vaccines.

"While the academic community was aware that studying B cells is important in developing cancer vaccines, there were no tools to verify the concept," Choi told Yonhap News Agency.

Neogenlogic said in a separate release that the new technology has been validated against "large-scale genomic datasets and clinical trial data from global vaccine leaders," adding the new AI framework has also been fully integrated into its proprietary discovery engine DeepNeo.

Choi said his team is preparing an investigational new drug (IND) submission with the U.S. Food and Drug Administration (FDA), with plans to enter clinical trials in 2027.

"Together with Neogenlogic, we are translating this academic breakthrough into a clinical-grade platform," he added. "Our proprietary AI elevates the scientific rigor of neoantigen selection, moving us from theoretical prediction to systematic clinical application."

Disclaimer: This post has been auto-published from an agency feed without any modifications to the text and has not been reviewed by an editor