Related Experiment Video
Updated: Jun 13, 2026
12:03
Expression, Isolation, and Purification of Soluble and Insoluble Biotinylated Proteins for Nerve Tissue Regeneration
Published on: January 22, 2014
Deep Learning-Guided Reverse Translation Enhances Soluble Expression of Recombinant Proteins in Escherichia coli
Dong Yu1, Nan Geng1, Lin Fan2,3
1College of Biotechnology, Tianjin University of Science and Technology, Tianjin 300457, China.
International Journal of Molecular Sciences
|June 12, 2026
Summary
We developed a deep learning framework (SCG-GELP) to optimize DNA sequences for enhanced soluble protein expression in microorganisms. This method significantly boosts protein yield by considering codon context, not just frequency.
Area of Science:
- Synthetic biology and protein engineering
- Computational biology and bioinformatics
Background:
- Soluble expression of heterologous proteins is crucial for research and industry.
- Existing DNA sequence optimization methods often overlook codon context, limiting protein expression.
Purpose of the Study:
- To develop an advanced deep learning framework for designing DNA sequences that enhance soluble protein expression.
- To improve the efficiency and yield of industrial enzyme production through optimized gene sequences.
Main Methods:
- Developed an integrated deep learning framework combining a synonymous codon generation (SCG) model and a gene expression level prediction (GELP) model.
- Utilized large-scale genomic data from *Escherichia coli* for the SCG model and gene expression data for the GELP model.
- Applied the SCG-GELP framework to optimize DNA sequences for industrial enzymes α-glucan phosphorylase (αGP) and isoamylase (IA).
Main Results:
- Achieved significant and reproducible improvements in soluble expression for αGP (mean 12.2-16.9-fold) and IA (mean 2.6-3.4-fold).
- Validated the effectiveness of the SCG-GELP approach through statistical analyses (one-way ANOVA, one-sample t-tests).
- Identified a core-avoiding codon optimization strategy that substantially enhances soluble protein yield.
Conclusions:
- The SCG-GELP framework provides a powerful tool for designing DNA sequences to achieve high soluble protein expression.
- This approach advances our understanding of the relationship between DNA sequence and protein expression levels.
- The optimized sequences and strategy offer practical benefits for synthetic biology and industrial applications.
