Recently, a research team helmed by Professor Jiang Huifeng from the Tianjin Institute of Industrial Biotechnology at the Chinese Academy of Sciences has achieved a notable breakthrough in codon optimization. They've developed a deep learning-based codon optimization model, dubbed DeepCodon. This innovative model leverages artificial intelligence to grasp codon selection patterns. It not only boosts codon preference but also strives to retain functionally significant rare codon characteristics to the fullest extent possible. In doing so, it paves a fresh path for sequence design in engineered bacterial strains.

Experimental verification has revealed that genes optimized by DeepCodon show markedly better expression results compared to those optimized through traditional methods. At present, this tool is mainly tailored for application scenarios involving Escherichia coli and provides complimentary online codon optimization services.