Hongmin Li, Goro Terai, Takumi Otagaki, Kiyoshi Asai
We present the Input Data Differentiable Designer (ID3), a unified framework for mRNA codon optimization. ID3 treats trained models as fixed differentiable functions and optimizes input data through continuous probability distributions while preserving the encoded amino acid sequence through three constraint mechanisms. The framework shows strong performance in both accessibility optimization and joint accessibility-CAI optimization across diverse protein targets. We also provide convergence analyses from the perspective of trained model input optimization.
MOTIVATION: Designing mRNA coding sequences that simultaneously optimize RNA accessibility in the translation initiation region and codon adaptation while preserving the encoded protein requires navigating a vast discrete combinatorial space. The inherently discrete nature of codon choices prevents direct application of gradient-based optimization, despite the availability of accurate deep learning predictors such as DeepRaccess for RNA accessibility prediction.
RESULTS: We present the Input Data Differentiable Designer (ID3), a unified framework for mRNA codon optimization. ID3 treats trained models as fixed differentiable functions and optimizes input data through continuous probability distributions while preserving the encoded amino acid sequence through three constraint mechanisms. The framework shows strong performance in both accessibility optimization and joint accessibility-CAI optimization across diverse protein targets. We also provide convergence analyses from the perspective of trained model input optimization.
AVAILABILITY AND IMPLEMENTATION: Code, datasets, and reproduction scripts are available at https://github.com/Li-Hongmin/ID3.git and archived on Zenodo (DOI: 10.5281/zenodo.18917770).