Systems biology approaches integrated with artificial intelligence for optimized metabolic engineering

Abstract

Metabolic engineering aims to maximize the production of bio-economically important substances (compounds, enzymes, or other proteins) through the optimization of the genetics, cellular processes and growth conditions of microorganisms. This requires detailed understanding of underlying metabolic pathways involved in the production of the targeted substances, and how the cellular processes or growth conditions are regulated by the engineering. To achieve this goal, a large system of experimental techniques, compound libraries, computational methods and data resources, including multi-omics data, are used. The recent advent of multi-omics systems biology approaches significantly impacted the field by opening new avenues to perform dynamic and large-scale analyses that deepen our knowledge on the manipulations. However, with the enormous transcriptomics, proteomics and metabolomics available, it is a daunting task to integrate the data for a more holistic understanding. Novel data mining and analytics approaches, including Artificial Intelligence (AI), can provide breakthroughs where traditional low-throughput experiment-alone methods cannot easily achieve. Here, we review the latest attempts of combining systems biology and AI in metabolic engineering research, and highlight how this alliance can help overcome the current challenges facing industrial biotechnology, especially for food-related substances and compounds using microorganisms.

Keywords: Artificial intelligence; Food industry; Machine learning; Metabolic engineering; Systems biology.

Fig. 1

Overview of the modeling strategies in the metabolic engineering research. (A) Data from different sources are used to construct (B) the metabolic pathways that produces the substance of interest. (C) An appropriate computational modeling approach is used to simulate the pathway response to a given perturbation in silico. The simulation results are analyzed to identity key regulatory steps, such as bottlenecks, which will then be tested using data from different conditions (e.g. gene knockouts or different growth conditions) (figure adapted from Helmy et al., 2009). (D) Finally, the model predictions are experimentally validated.

Fig. 2

Schematic representation of dynamic and constraint-based modeling approaches used in metabolic engineering. A) Dynamic kinetic modeling of metabolic pathways using differential equations. B) Flux balance analysis (FBA) modeling.

Fig. 3

Schematic representation of different modeling approaches used in metabolic engineering. Modeling steps of A) promoter-strength simulations using statistical models and mutations data, B) Ensemble modeling combining different sub-model simulations.

Fig. 4

Integrating systems biology and machine learning in metabolic engineering research. Systems biology and ML approaches are highly suitable for processing and analyzing multi-omics data with massive sizes and features. Starting from an initial strain and design (i), transcriptomics (ii), proteomics and metabolomics data generation (iii) provide multitudes of data which require integration by data analytics, modelling and machine learning (iv). This will help provide targets for re-design/-engineering which need to be experimentally tested (v). This will lead to an enhanced engineering process to generate engineered microbes that can be used in the modern bio-industries such as food industry.