Evaxion Biotech A/S (NASDAQ: EVAX) has unveiled improved performance of its key AI-Immunology™ building block, EvaxMHC, at the 32nd Intelligent Systems for Molecular Biology conference. The advancements in EvaxMHC are expected to enhance Evaxion's ability to accurately predict vaccine targets for personalized and precision vaccines in cancer and infectious diseases.
The improvements include:
Utilization of a state-of-the-art deep-learning framework
Creation of a unified representation for MHC class I and II molecules
Implementation of a deep transformer encoder-decoder architecture
Adoption of a generative adversarial network (GAN) pretraining mechanism
These enhancements have led to improved vaccine designs demonstrated in preclinical studies, particularly for MHC class II molecules, which have historically been challenging to predict accurately.