A new algorithm can design custom RNA structures while simultaneously following the complex genetic codes required for vaccines.
Designing an RNA molecule that folds into the right shape while also telling a cell to make the right protein is a massive math problem. There are more possible combinations of these genetic instructions than there are atoms in the universe. This tensor-based algorithm can navigate that complexity to find the most stable and effective RNA sequences. It removes a major bottleneck that has slowed down the development of new mRNA therapies. This tool could significantly speed up how quickly we design and produce vaccines for emerging diseases.
Direct RNA sequence design under codon constraints using expressive tensor-based secondary structure models
arXiv · 2604.19718
Nucleic acid sequence design via codon optimization is a fundamental task with applications across synthetic biology, mRNA therapeutics, and vaccine design. Given a target protein, it is a major open challenge to navigate the combinatorially large design space of codon sequences mapping to its amino acid sequence. Computational approaches generally seek to optimize simple objectives based on the codon sequence, possibly together with more complicated contributions based on secondary structure an