Computational epitope profiling and AI-driven protein engineering enable rational design of multi-epitope vaccines against Mycobacterium tuberculosis.

Tuberculosis (TB), caused by Mycobacterium tuberculosis (Mtb), remains a major global health threat, accounting for approximately 1.5 million deaths annually. The rise of antibiotic-resistant strains further complicates treatment efforts. While vaccination is a cornerstone of disease control, the only licensed TB vaccine, Bacille Calmette-Guérin (BCG), shows limited efficacy in adults. There is thus a critical need for more effective vaccines. Multi-epitope vaccines, which incorporate key epitopes from multiple antigens, offer a promising strategy by eliciting both humoral and cellular immunity. Here, we employed a comparative epitopomics approach to identify immunodominant epitopes from eight major Mtb antigens and selected 17 potent epitopes for the design of a multi-epitope antigen. Using AI-driven protein design, we systematically optimized epitope arrangement and flanking sequences to generate a stable, structurally integrated antigen-MtbEpi-17. Computational analyses suggest that MtbEpi-17 can effectively interact with TLR2 and TLR4, potentially stimulating robust innate and adaptive immune responses. Our study provides a rational design framework for multi-epitope vaccines, and proposes MtbEpi-17 as a strong candidate for further preclinical and clinical evaluation.