Evolutionary programming as a platform for in silico metabolic engineering

Abstract

Background: Through genetic engineering it is possible to introduce targeted genetic changes and hereby engineer the metabolism of microbial cells with the objective to obtain desirable phenotypes. However, owing to the complexity of metabolic networks, both in terms of structure and regulation, it is often difficult to predict the effects of genetic modifications on the resulting phenotype. Recently genome-scale metabolic models have been compiled for several different microorganisms where structural and stoichiometric complexity is inherently accounted for. New algorithms are being developed by using genome-scale metabolic models that enable identification of gene knockout strategies for obtaining improved phenotypes. However, the problem of finding optimal gene deletion strategy is combinatorial and consequently the computational time increases exponentially with the size of the problem, and it is therefore interesting to develop new faster algorithms.

Results: In this study we report an evolutionary programming based method to rapidly identify gene deletion strategies for optimization of a desired phenotypic objective function. We illustrate the proposed method for two important design parameters in industrial fermentations, one linear and other non-linear, by using a genome-scale model of the yeast Saccharomyces cerevisiae. Potential metabolic engineering targets for improved production of succinic acid, glycerol and vanillin are identified and underlying flux changes for the predicted mutants are discussed.

Conclusion: We show that evolutionary programming enables solving large gene knockout problems in relatively short computational time. The proposed algorithm also allows the optimization of non-linear objective functions or incorporation of non-linear constraints and additionally provides a family of close to optimal solutions. The identified metabolic engineering strategies suggest that non-intuitive genetic modifications span several different pathways and may be necessary for solving challenging metabolic engineering problems.

Figure 1

Schematic overview of the OptGene algorithm. A population of individuals is initiated by specifying a present/absent status for each gene in each of the individuals. Individuals are then scored for their fitness by using FBA/MOMA/other method of choice and the objective function (/s). Individuals are selected for mating based on their fitness score, and subsequently crossed to produce new offspring. Mutations are introduced in individuals randomly at specified mutation rate and thus a new population is obtained. This cycle of evolution is repeated until a mutant (or mutants) with a desired phenotypic characteristics is obtained. Please refer to the text for detailed description of each step in the algorithm. Grey shaded or red walled boxes are used to represent different individuals in the cross-over process. Ind.- Individual. FBA- Flux balance analysis [13,14]. MOMA- Minimization of the metabolic adjustment [19]. ROOM- Regulatory on/off minimization [20].

Figure 2

Representation of the metabolic genotype. Each gene of the microorganism is assigned a binary value, representing its absence/presence in the mutant (A). The individual genes are associated with one or more reactions in the metabolic network (B). When a given reaction is in the absent status, the upper and lower bonds for the corresponding metabolic flux are set to zero, resulting in a modified metabolic model (C).

Figure 3

Schematic overview of the Saccharomyces cerevisiae central carbon metabolism. The figure shows important pathways in the central carbon metabolism including certain branch points towards the amino acid metabolism. The thick arrows indicate the drain of metabolites towards biomass production. Arrows with the style indicates a lumped pathway. Multiple names for a reaction indicate the presence of iso-enzymes. The nomenclature of the metabolites can be found in the Supplementary table 1 [see Additional file 1]. The figure is partially adapted from Forster et al. (2002) [32].

Figure 4

Typical shape of the convergence curve of OptGene.