Integrating Machine Learning and Transcriptomics to Enhance β-Carotene Production in Saccharomyces cerevisiae

Abstract

Optimization of microbial production by synthetic biology is essential for industrial and sustainable biotechnology applications. β-carotene is a high-value compound that can be heterologously produced in the budding yeast Saccharomyces cerevisiae, providing an alternative to natural extraction. In this study, we aimed to enhance β-carotene production by machine learning–guided combinatorial strain engineering and transcriptomic analyses. We fine-tuned the expression of rate-limiting enzymes in the mevalonate (MVA) pathway through combinatorial engineering of promoters and terminators. XGBoost was applied to the Design-Build-Test-Learn (DBTL) cycle to facilitate rapid optimization. In the second DBTL cycle of 1 mL culture screening, fine-tuning MVA gene expression resulted in a 139% improvement in β-carotene titer. Additionally, guided by transcriptomic insights into altered expression of iron uptake genes, we supplemented β-carotene production cultures with iron, resulting in a 70.54% increase in β-carotene titer. Furthermore, integrating the fine-tuned MVA cassette with iron supplementation in 250 mL shake-flasks yielded up to 72.07 mg/L of β-carotene at 72 h, representing a 67.79% increase compared to the β-carotene-producing strain without MVA gene fine-tuning. Our study demonstrates the effectiveness of XGBoost in predicting complex combinatorial designs and highlights the potential of combining machine learning and transcriptomic insights to optimize non-native biochemical production in yeast.