Data-Driven Prediction of CRISPR-Based Transcription Regulation for Programmable Control of Metabolic Flux

Abstract

Multiplex and multi-directional control of metabolic pathways is crucial for metabolic engineering to improve product yield of fuels, chemicals, and pharmaceuticals. To achieve this goal, artificial transcriptional regulators such as CRISPR-based transcription regulators have been developed to specifically activate or repress genes of interest. Here, we found that by deploying guide RNAs to target on DNA sites at different locations of genetic cassettes, we could use just one synthetic CRISPR-based transcriptional regulator to simultaneously activate and repress gene expressions. By using the pairwise datasets of guide RNAs and gene expressions, we developed a data-driven predictive model to rationally design this system for fine-tuning expression of target genes. We demonstrated that this system could achieve programmable control of metabolic fluxes when using yeast to produce versatile chemicals. We anticipate that this master CRISPR-based transcription regulator will be a valuable addition to the synthetic biology toolkit for metabolic engineering, speeding up the “design-build-test” cycle in industrial biomanufacturing as well as generating new biological insights on the fates of eukaryotic cells.

Leveraging knowledge engineering and machine learning for microbial bio-manufacturing

“…The authors used pairwise datasets of guideRNAs and gene expression to build a predictive model Sheng et al (2017) SVM Predict the essential genes in E. coli metabolism The authors proposed a strategy of data curation and feature selection to improve the performance of SVM model. Instead of performing flux balance analysis, which are condition specific, to obtain flux features, they applied flux coupling analysis to get the higher sensitivity and specificity of the model.…”