Dataset 10

This article investigates the compatibility of regulatory sequences with metabolic gene expression in Escherichia coli. By constructing fusion proteins and utilizing machine learning models (such as DeepSwarm), it analyzes fluorescence intensity data from 520 combinations, revealing that integrating promoters, RBS, and CDS significantly enhances the prediction of protein expression levels, with promoters having the greatest impact. The study provides a strategy for precise gene expression regulation in E. coli metabolic engineering and offers a new perspective on understanding the interactions between regulatory sequences and target genes.