Codon Optimization with Deep Learning Models

Codon optimization can have dramatic effects on protein expression level. Several codon optimization strategies have been developed to enhance expression, but these methods can produce often unreliable results.

In this technical poster we develop deep contextual language models that learn the codon usage rules from natural protein coding sequences. Ultimately demonstrating in silico design of gene sequences for optimal expressions. This approach provides a novel and reliable method for tuning gene expression across a variety of industries.