Systems Metabolic Engineering Meets Machine Learning: A New Era for Data‐Driven Metabolic Engineering

Abstract

The recent increase in high‐throughput capacity of ‘omics datasets combined with advances and interest in machine learning (ML) have created great opportunities for systems metabolic engineering. In this regard, data‐driven modeling methods have become increasingly valuable to metabolic strain design. In this review, the nature of ‘omics is discussed and a broad introduction to the ML algorithms combining these datasets into predictive models of metabolism and metabolic rewiring is provided. Next, this review highlights recent work in the literature that utilizes such data‐driven methods to inform various metabolic engineering efforts for different classes of application including product maximization, understanding and profiling phenotypes, de novo metabolic pathway design, and creation of robust system‐scale models for biotechnology. Overall, this review aims to highlight the potential and promise of using ML algorithms with metabolic engineering and systems biology related datasets.

Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism

“…Indeed, ML methods for the generation of predictive models on living systems are becoming ubiquitous, including applications within genome annotation, de novo pathway discovery, product maximization in engineered microbial cells, pathway dynamics, and transcriptional drivers of disease states 14 . While being able to provide predictive power based on complex multivariate relationships 15 , the training of ML algorithms requires large datasets of high quality, and thereby imposes certain standards for the experimental workflows. For instance, for genotype-to-phenotype predictions, it is desirable that datasets contain a high variation between both genotypes and phenotypes 16 .…”

“…While mechanistic models require a priori knowledge of the living system of interest, and ML-guided predictions require ample multivariate experimental data for training, the combination of mechanistic and ML models holds promise for improved performance of predictive engineering of cells by uniting the advantages of the causal understanding of mechanism from mechanistic models, with the predictive power of ML 15,17 . Metabolic pathways are known to be regulated at multiple levels, including transcriptional, translational, and allosteric levels 13 .…”

13C Metabolic Flux Analysis of Escherichia coli Engineered for Gamma‐Aminobutyrate Production

“…The natural isotope abundance of non‐amino acid carbon backbone‐originated atoms were considered by built‐in function of the INCA. [ 5,9 ] The boundaries for lower and upper limits of fluxes were set to zero and infinity, respectively. Reversible reactions were modeled as separate forward and backward fluxes.…”

“…[ 1–4 ] However, cellular metabolism is composed of complicated reaction networks, and detailed consideration of metabolic perturbation caused by genetic manipulation is also required for efficient metabolite production. [ 5 ] Metabolic fluxes, representing material and energy flow among enzymes, are often changed significantly by genetic modification, which is targeted to modify the expression levels or activities of enzymes. [ 6,7 ] The comparison of metabolic fluxes before and after genetic manipulation could provide us a systematic and comprehensive understanding of the introduced genotypic changes.…”

Evaluating the Potential of Applying Machine Learning Tools to Metabolic Pathway Optimization

“…For example, machine learning has been utilised in reconstruction of metabolic model of a species [8][9][10][11][12]. De novo pathway engineering is another aspect that has benefited from application of machine learning tools [13]. Machine learning tools have also enabled the deciphering of kinetic parameters of enzymes from metabolomics data [14,15].…”