Simulated Design-Build-Test-Learn Cycles for Consistent Comparison of Machine Learning Methods in Metabolic Engineering

16Citations
Citations of this article
50Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Combinatorial pathway optimization is an important tool in metabolic flux optimization. Simultaneous optimization of a large number of pathway genes often leads to combinatorial explosions. Strain optimization is therefore often performed using iterative design-build-test-learn (DBTL) cycles. The aim of these cycles is to develop a product strain iteratively, every time incorporating learning from the previous cycle. Machine learning methods provide a potentially powerful tool to learn from data and propose new designs for the next DBTL cycle. However, due to the lack of a framework for consistently testing the performance of machine learning methods over multiple DBTL cycles, evaluating the effectiveness of these methods remains a challenge. In this work, we propose a mechanistic kinetic model-based framework to test and optimize machine learning for iterative combinatorial pathway optimization. Using this framework, we show that gradient boosting and random forest models outperform the other tested methods in the low-data regime. We demonstrate that these methods are robust for training set biases and experimental noise. Finally, we introduce an algorithm for recommending new designs using machine learning model predictions. We show that when the number of strains to be built is limited, starting with a large initial DBTL cycle is favorable over building the same number of strains for every cycle.

References Powered by Scopus

COBRApy: COnstraints-Based Reconstruction and Analysis for Python

817Citations
N/AReaders
Get full text

Tuning genetic control through promoter engineering

760Citations
N/AReaders
Get full text

A review of multi-objective optimization: Methods and its applications

729Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Application of fermented Chinese herbal medicines in food and medicine field: From an antioxidant perspective

15Citations
N/AReaders
Get full text

Enabling pathway design by multiplex experimentation and machine learning

12Citations
N/AReaders
Get full text

Engineering oleaginous red yeasts as versatile chassis for the production of oleochemicals and valuable compounds: Current advances and perspectives

6Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

van Lent, P., Schmitz, J., & Abeel, T. (2023). Simulated Design-Build-Test-Learn Cycles for Consistent Comparison of Machine Learning Methods in Metabolic Engineering. ACS Synthetic Biology, 12(9), 2588–2599. https://doi.org/10.1021/acssynbio.3c00186

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 14

93%

Researcher 1

7%

Readers' Discipline

Tooltip

Biochemistry, Genetics and Molecular Bi... 10

48%

Agricultural and Biological Sciences 7

33%

Chemical Engineering 2

10%

Environmental Science 2

10%

Save time finding and organizing research with Mendeley

Sign up for free