.png){kind=icon}
.png){kind=icon}
Return
MooSeeker: A Metabolic Pathway Design Tool Based on Multi-Objective Optimization Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1109/TCBB.2023.3307363.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, metabolic pathway design has attracted considerable attention and become an increasingly important area in metabolic engineering. Manual or computational methods have been introduced to retrieve the metabolic pathway. These methods model metabolic pathway design as a single-objective optimization problem with the weighted sum of a variety of criteria as the final score. While these methods have demonstrated promising results, the majority of current methods do not account for comparisons and competition among criteria. Here, we propose MooSeeker, a metabolic pathway design tool based on the multi-objective optimization algorithm that aims to trade off all the criteria optimally. The metabolic pathway design problem is characterized as a multi-objective optimization problem with three objectives including pathway length, thermodynamic feasibility and theoretical yield. In order to digitize the continuous metabolic pathway, MooSeeker develops the encoding strategy, BioCrossover and BioMutation operators to search for the candidate pathways. Finally, MooSeeker outputs the Pareto optimal solutions of the candidate metabolic pathways with three criterion values. The experiment results show that MooSeeker is capable of constructing the experimentally validated pathways and finding the higher-performance pathway than the single-objective-based methods.
Keywords:
Optimization
Compounds
Pareto optimization
Encoding
Thermodynamics
Statistics
Sociology
Metabolic engineering
metabolic pathway design
multi-objective optimization algorithm
Journal
I
IF:
3.4
Papers:
3.3K
Citations:
6.4K