A joint research team from the Korea Advanced Institute of Science and Technology (KAIST) and the biotechnology company Neogenlogic has developed a new AI-based model that could help create a fundamentally new type of “personalized” cancer vaccines. The platform identifies neoantigens that are unique to each patient, which can train the patient’s immune system and therefore prevent disease recurrence. Neoantigens are protein fragments derived from mutations and are unique to the patient’s tumor. According to Professor Choi Jung Kyun from KAIST, they serve as a kind of “fingerprint” used by vaccines to train the immune system.
If current vaccines focus almost exclusively on activating cytotoxic T-cells for immediate attack, new clinical data show that immunological memory, mediated by B-cells, is key to a long-term anti-tumor response and prevention of recurrences. B-cells are lymphocytes that play a crucial role in humoral immunity. They recognize antigens and produce antibodies, providing long-term protection against infections and, as it turns out, against cancer cells.
According to the research group, their model predicts which neoantigens will elicit a “robust B-cell response” by studying the structural patterns of interaction between mutant peptides and B-cell receptors (BCR). The study represents the world’s first AI platform capable of predicting B-cell immunogenicity alongside T-cell responses for developing personalized cancer vaccines, the working group said. In recent developments, Neogenlogic has announced partnerships with major pharmaceutical companies to further enhance their AI-driven vaccine research, indicating substantial progress in the biotech field.
Neogenlogic stated that the new technology has been tested on “large-scale genomic datasets and clinical trial data from global leaders in the vaccine field,” adding that the new platform has also been fully integrated into their own DeepNeo discovery engine. Choi noted that his team is preparing an investigational new drug (IND) application, which contains data on the safety and efficacy of the drug as well as the clinical trial plan, for submission to the U.S. Food and Drug Administration (FDA) and plans to begin clinical trials in 2027. Experts have lauded Neogenlogic’s initiative as a pivotal step towards a new era in personalized medicine, with the potential to significantly enhance patient outcomes.
