Biosystems Design by Machine Learning

Abstract

Biosystems such as enzymes, pathways, and whole cells have been increasingly explored for biotechnological applications. However, the intricate connectivity and resulting complexity of biosystems poses a major hurdle in designing biosystems with desirable features. As -omics and other high throughput technologies have been rapidly developed, the promise of applying machine learning (ML) techniques in biosystems design has started to become a reality. ML models enable the identification of patterns within complicated biological data across multiple scales of analysis and can augment biosystems design applications by predicting new candidates for optimized performance. ML is being used at every stage of biosystems design to help find nonobvious engineering solutions with fewer design iterations. In this review, we first describe commonly used models and modeling paradigms within ML. We then discuss some applications of these models that have already shown success in biotechnological applications. Moreover, we discuss successful applications at all scales of biosystems design, including nucleic acids, genetic circuits, proteins, pathways, genomes, and bioprocesses. Finally, we discuss some limitations of these methods and potential solutions as well as prospects of the combination of ML and biosystems design.

In-situ monitoring of xenobiotics using genetically engineered whole-cell-based microbial biosensors: recent advances and outlook

“…However, the new scenario is changing as scientists begin to incorporate decision tree models to identify numerous xenobiotics and pattern-learning algorithms via speci c light emission pro les. Moreover, machine learning tools become an intricate tool to design biosystems with optimised performance and desired properties because of their power of better predictability (Volk et al 2020). Despite all the advantages of microbial biosensors, it is crucial to investigate the portability and miniaturisation of signal detection systems to increase the use in the eld.…”

Constraint-based modeling and machine learning applications for analysis and optimization of fermentation parameters

“…Therefore, contrary to popular belief, big data is any dataset with at least one of these seven traits, and high-volume datasets are not always required for ML models [78]. However, the greater the amount of appropriate data provided, the more accurate the model built [79]. Each dataset consists of rows and columns, which rows are called samples, and each column can represent a feature or a target value.…”

Streamlining Natural Products Biomanufacturing With Omics and Machine Learning Driven Microbial Engineering

“…Following this, the integration of transcriptome, proteome, and/or metabolome datasets with ML methods is particularly useful in the development of mathematical models in the Test and Learn cycle that would guide and facilitate in silico optimization of the DBTL pipeline (Presnell and Alper, 2019;St. John and Bomble, 2019;Volk et al, 2020). Thanks to the growing list of genome, transcriptome, and GEM resources, further adoption and implementation of in silico and ML tools on these biological datasets are expected to bring about a markedly improved and accurate predictive engineering and retrosynthetic design of metabolic pathways to existing and new-to-nature chemicals (Lin et al, 2019;Zhang et al, 2020).…”