Machine-Learning-Assisted Pathway Optimization in Large Combinatorial Design Spaces: A p -Coumaric Acid Case Study
ACS Synthetic Biology · 21.08.2026 · 15 (8) · 3146-3157
DOI: 10.1021/acssynbio.5c00864 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Synthetic Biology, online erschienen am 22.07.2026. Verfasst von Paul van Lent und 7 weiteren Autor:innen. Beteiligte Einrichtung: Intelligent Systems, Delft University of Technology, 2628 ATDelft, The Netherlands. Hauptthemen laut MEDLINE: Propionates, Saccharomyces cerevisiae, Machine Learning, Metabolic Engineering. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Rijksdienst voor Ondernemend Nederland, dsm-firmenich.
Abstract (Originalsprache)
Combinatorial pathway optimization is a powerful approach in metabolic engineering to improve strain performance. While machine learning (ML) has shown promise in guiding the Design–Build–Test–Learn (DBTL) cycle, most applications have been limited to small design spaces, thereby restricting the potential of predictive and exploration-exploitation strategies. In this work, we applied two DBTL cycles to optimize p-coumaric acid production in Saccharomyces cerevisiae. The first cycle involved constructing a large combinatorial library of 18 genes and 20 promoters (170 million possible designs). In the second cycle, we employed a gradient bandit-based machine learning recommendation strategy, tuned to balance exploration and exploitation. Our results show that this balanced strategy outperforms greedy, feature importance-based approaches, leading to greater diversity in strain performance and improved top-producer identification. Notably, applying the same strategy to an alternative parent strain yielded the highest p-coumaric acid titer (1.23 g/L), a 2.37-fold improvement over the original. These findings highlight the value of ML-guided exploration in large design spaces and demonstrate that balancing exploration and exploitation is critical for successful strain optimization.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Intelligent Systems, Delft University of Technology, 2628 ATDelft, The Netherlands.
- Department of Science and Research, dsm-firmenich, 2613 AXDelft, The Netherlands.
- Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge02142, United States.
ORCID-Profile: Paul van Lent, Thomas Abeel
Förderung
- Rijksdienst voor Ondernemend Nederland
- dsm-firmenich
Zitieren
APA
van Lent, P., van der Hoek, R., Moreno Paz, S., Kooi, I., Jonkers, M., Zwartjens, P., Schmitz, J., & Abeel, T. (2026). Machine-Learning-Assisted Pathway Optimization in Large Combinatorial Design Spaces: A p -Coumaric Acid Case Study. ACS Synthetic Biology, 15(8), 3146-3157. https://doi.org/10.1021/acssynbio.5c00864
Vancouver
van Lent P, van der Hoek R, Moreno Paz S, Kooi I, Jonkers M, Zwartjens P, et al. Machine-Learning-Assisted Pathway Optimization in Large Combinatorial Design Spaces: A p -Coumaric Acid Case Study. ACS Synthetic Biology. 2026;15(8):3146-3157. doi:10.1021/acssynbio.5c00864
BibTeX
@article{vanLent2026,
author = {van Lent, Paul and van der Hoek, Rianne and Moreno Paz, Sara and Kooi, Irsan and Jonkers, Moniek and Zwartjens, Priscilla and Schmitz, Joep and Abeel, Thomas},
title = {Machine-Learning-Assisted Pathway Optimization in Large Combinatorial Design Spaces: A p -Coumaric Acid Case Study},
journal = {ACS Synthetic Biology},
year = {2026},
volume = {15},
number = {8},
pages = {3146--3157},
doi = {10.1021/acssynbio.5c00864}
}
EUVIMED