MIT engineers trained a language model on yeast codon usage to design genes that boost protein production, outperforming commercial tools for five of six proteins. The approach could lower drug development costs by improving yields of protein-based medicines.
MIT chemical engineers used a large language model to optimize protein production in industrial yeast. The AI model improved yields for five of six tested proteins, including a cancer monoclonal antibody, potentially reducing drug development costs.
MIT chemical engineers developed a large language model that optimizes codon sequences for protein production in industrial yeast, boosting efficiency for six proteins including human growth hormone and cancer antibodies.
