Machine learning-driving optimization and spatial assembly of a cell-free system for high-yield liquiritigenin production

TL;DR

Researchers created a cell-free system using machine learning and enzyme assembly to efficiently produce the medicinal compound liquiritigenin.

Contribution

A novel cell-free system combining machine learning and spatial enzyme assembly for high-yield biosynthesis of liquiritigenin.

Findings

Optimized enzyme combinations achieved 155.32 ± 14.39 mg/L liquiritigenin production.

Spatial assembly with scaffold proteins increased yield to 439.42 ± 19.53 mg/L.

Machine learning and iterative experiments improved enzyme ratios and cofactor concentrations.

Abstract

Liquiritigenin is a medicinal flavonoid whose production is constrained by inefficient plant extraction and complex chemical synthesis. To overcome this, we developed a modular cell-free multi-enzyme system for its efficient biosynthesis from tyrosine, integrating spatial enzyme assembly with machine learning-guided optimization. Using a combined cell-free metabolic engineering (CFME) and cell-free protein synthesis-driven metabolic engineering (CFPS-ME) approach, we screened and optimized five key pathway enzymes to establish a one-pot reaction. The optimal enzyme combination (phenylalanine ammonia-lyase from Zea mays, 4-coumarate-coenzyme A ligase 4 from Arabidopsis thaliana, chalcone synthase from Glycine max, chalcone reductase from Medicago sativa, chalcone flavonone isomerase from Zea mays) was identified through systematic screening and ratio optimization. After Plackett–Burman and steepest-ascent experiments, three rounds of iterative machine learning fine-tuned key parameters, including enzyme ratios and cofactor concentrations, yielding 155.32 ± 14.39 mg/L. Spatial enzyme assembly was further enhanced via covalent peptide tags and scaffold proteins (γPFD-SpyCatcher) under CFME. Combining CFPS-ME with scaffold-assisted co-immobilization significantly boosted production, reaching a final titer of 439.42 ± 19.53 mg/L. This study demonstrates that machine learning-driven optimization and spatial assembly of multienzyme complexes is a powerful approach for cell-free biosynthesis.

The online version contains supplementary material available at 10.1007/s44307-026-00103-0.

Figures