The utility of ML-assisted evolution for engineering Rubisco with improved carboxylation efficiency and potential for enhancing crop productivity is demonstrated.
Abstract
Ribulose-1,5-bisphosphate carboxylase/oxygenase (Rubisco) is foundational to life on Earth, catalyzing carbon dioxide (CO2) fixation to generate biomass. However, Rubisco is a slow and inefficient enzyme that has proven challenging to engineer. We applied the structure-informed machine learning (ML) model ESM-IF1 to identify plausible amino acid sites in the large subunit of Nicotiana tabacum Rubisco to target for directed evolution. ML-assisted library design followed by selection in Rubisco-dependent Escherichia coli identified multiple enriched variants displaying improved catalytic efficiency. Several improved variants carried amino acid changes not found in the evolutionary lineage of plants, despite being assembly competent in plant chloroplasts, demonstrating that ML-assisted protein design can explore functional sequence space beyond what is observed from natural sequence diversity. Most prominently, the T391I substitution improved carboxylation rate by 29% and aerobic carboxylation efficiency by 43%. Our findings demonstrate the utility of ML-assisted evolution for engineering Rubisco with improved carboxylation efficiency and potential for enhancing crop productivity.
This work demonstrates that integrating cell-free enzyme engineering with machine learning enables opportunities for high-throughput experimental measurements to benchmark and improve protein language models, accelerate design loops, and expand functional exploration within protein families where experimental information is limited.
J. Lazar, Evan Komp, I. Martínez et al.· bioRxiv· 1 citation
Results indicate that supervised machine learning can help guide the construction of high-value enzyme libraries with expanded catalytic scope, and suggest that supervised machine learning can help guide the construction of high-value enzyme libraries with expanded catalytic scope.
Ravi G. Lal, Jason Yang, Ziyan Zhang et al.· bioRxiv· 0 citations
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.
Peerapat Khamwachirapithak, K. Sae-tang, Suriyaporn Bubphasawan et al.· ACS Omega· 0 citations
A systematic comparison of zero-shot ML models is provided and an iterative framework for integrating machine learning with directed evolution to accelerate enzyme engineering is established to accelerate enzyme engineering.
Daniel Gutierrez, Isa Madrigal Harrison, Aaron L. Feller et al.· bioRxiv· 0 citations