Related Experiment Video
Updated: May 12, 2026
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
Published on: October 17, 2025
Quantitative design of regulatory elements based on high-precision strength prediction using artificial neural
Hailin Meng1, Jianfeng Wang, Zhiqiang Xiong
1Key Laboratory of Synthetic Biology, Institute of Plant Physiology and Ecology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China.
Researchers developed a new method using artificial neural networks (ANNs) to design synthetic biology regulatory elements. This quantitative approach accurately predicts and creates promoters and ribosome binding sites (RBSs) with desired strengths for gene expression control.
Area of Science:
- Synthetic Biology
- Molecular Biology
- Bioengineering
Background:
- Accurate regulatory elements like promoters and ribosome binding sites (RBSs) are crucial for precise gene expression control in synthetic biology.
- De novo design of these elements is a key area of research for advancing rational pathway engineering.
Purpose of the Study:
- To develop a quantitative design method for novel regulatory elements using artificial neural networks (ANNs).
- To enable the de novo design of promoters and RBSs with predictable and controllable strengths for gene expression.
Main Methods:
- Developed an artificial neural network (ANN) model for predicting the strength of promoter and RBS sequences.
- Trained and validated the ANN model using 100 characterized mutated Trc promoter & RBS sequences with strengths ranging from 0 to 3.559.
- In silico designed 16 artificial regulatory elements using the validated ANN model.
Main Results:
- Achieved high prediction accuracy with regression correlation coefficients of 0.98 for both ANN model training and testing.
- Demonstrated good consistency between the measured and desired strengths for all 16 designed elements.
- Validated the functional reliability of the designed elements in two different genetic contexts, improving peptide toxin expression and pathway fine-tuning in E. coli.
Conclusions:
- The ANN-based methodology enables the de novo and quantitative design of regulatory elements with specific strengths.
- This approach significantly contributes to synthetic biology applications requiring precise gene expression regulation.
- The designed elements show functional reliability and applicability in improving biological systems.
