MIT chemical engineers used AI to optimize the selection of codon sequences for protein drugs produced by yeast, which could reduce the costs of developing and manufacturing these drugs.

MIT is a renowned institution for education and research, offering insights into science, engineering, and technology. Through publications, research papers, and academic programs, MIT's platform provides insights into  research, innovation, and education in various fields. Students, researchers, and technology enthusiasts can learn about MIT's contributions to science and technology and explore opportunities for academic and professional development.

MIT News

MIT researchers developed an AI model using large language models to optimize codon sequences for protein production in industrial yeast. The model analyzes DNA patterns in Komagataella phaffii and predicts optimal codon arrangements, outperforming commercial tools in producing six different proteins including human growth hormone and cancer-treating antibodies. This approach could reduce the 15-20% development costs associated with bringing new biologic drugs to market by making the protein engineering process more predictable and efficient.

New AI model could cut the costs of developing protein drugs