Search

Through advanced mechanistic modeling and the generation of large high-quality datasets, machine learning is becoming an integral part of understanding and engineering living systems. Here we show that mechanistic and machine learning models can be combined to enable accurate genotype-to-phenotype predictions. We use a genome-scale model to pinpoint engineering targets, efficient library construction of metabolic pathway designs, and high-throughput biosensor-enabled screening for training diverse machine learning algorithms. From a single data-generation cycle, this enables successful forward engineering of complex aromatic amino acid metabolism in yeast, with the best machine learning-guided design recommendations improving tryptophan titer and productivity by up to 74 and 43%, respectively, compared to the best designs used for algorithm training. Thus, this study highlights the power of combining mechanistic and machine learning models to effectively direct metabolic engineering efforts.

Metabolic models can estimate intrinsic product yields for microbial factories, but such frameworks struggle to predict cell performance (including product titer or rate) under suboptimal metabolism and complex bioprocess conditions. On the other hand, machine learning, complementary to metabolic modeling necessitates large amounts of data. Building such a database for metabolic engineering designs requires significant manpower and is prone to human errors and bias. We propose an approach to integrate data-driven methods with genome scale metabolic model for assessment of microbial bio-production (yield, titer and rate). Using engineered E. coli as an example, we manually extracted and curated a data set comprising about 1200 experimentally realized cell factories from ~100 papers. We furthermore augmented the key design features (e.g., genetic modifications and bioprocess variables) extracted from literature with additional features derived from running the genome-scale metabolic model iML1515 simulations with constraints that match the experimental data. Then, data augmentation and ensemble learning (e.g., support vector machines, gradient boosted trees, and neural networks in a stacked regressor model) are employed to alleviate the challenges of sparse, non-standardized, and incomplete data sets, while multiple correspondence analysis/principal component analysis are used to rank influential factors on bio-production. The hybrid framework demonstrates a reasonably high cross-validation accuracy for prediction of E.coli factory performance metrics under presumed bioprocess and pathway conditions (Pearson correlation coefficients between 0.8 and 0.93 on new data not seen by the model)., Competing Interests: The authors have declared that no competing interests exist.

Genome scale modeling (GSM) predicts the performance of microbial workhorses and helps identify beneficial gene targets. GSM integrated with intracellular flux dynamics, omics, and thermodynamics have shown remarkable progress in both elucidating complex cellular phenomena and computational strain design (CSD). Nonetheless, these models still show high uncertainty due to a poor understanding of innate pathway regulations, metabolic burdens, and other factors (such as stress tolerance and metabolite channeling). Besides, the engineered hosts may have genetic mutations or non-genetic variations in bioreactor conditions and thus CSD rarely foresees fermentation rate and titer. Metabolic models play important role in design-build-test-learn cycles for strain improvement, and machine learning (ML) may provide a viable complementary approach for driving strain design and deciphering cellular processes. In order to develop quality ML models, knowledge engineering leverages and standardizes the wealth of information in literature (e.g., genomic/phenomic data, synthetic biology strategies, and bioprocess variables). Data driven frameworks can offer new constraints for mechanistic models to describe cellular regulations, to design pathways, to search gene targets, and to estimate fermentation titer/rate/yield under specified growth conditions (e.g., mixing, nutrients, and O 2 ). This review highlights the scope of information collections, database constructions, and machine learning techniques (such as deep learning and transfer learning), which may facilitate "Learn and Design" for strain development., (Copyright © 2018 Elsevier Inc. All rights reserved.)

Biology has changed radically in the past two decades, growing from a purely descriptive science into also a design science. The availability of tools that enable the precise modification of cells, as well as the ability to collect large amounts of multimodal data, open the possibility of sophisticated bioengineering to produce fuels, specialty and commodity chemicals, materials, and other renewable bioproducts. However, despite new tools and exponentially increasing data volumes, synthetic biology cannot yet fulfill its true potential due to our inability to predict the behavior of biological systems. Here, we showcase a set of computational tools that, combined, provide the ability to store, visualize, and leverage multiomics data to predict the outcome of bioengineering efforts. We show how to upload, visualize, and output multiomics data, as well as strain information, into online repositories for several isoprenol-producing strain designs. We then use these data to train machine learning algorithms that recommend new strain designs that are correctly predicted to improve isoprenol production by 23%. This demonstration is done by using synthetic data, as provided by a novel library, that can produce credible multiomics data for testing algorithms and computational tools. In short, this paper provides a step-by-step tutorial to leverage these computational tools to improve production in bioengineered strains.

The Design-Build-Test-Learn (DBTL) cycle, facilitated by exponentially improving capabilities in synthetic biology, is an increasingly adopted metabolic engineering framework that represents a more systematic and efficient approach to strain development than historical efforts in biofuels and biobased products. Here, we report on implementation of two DBTL cycles to optimize 1-dodecanol production from glucose using 60 engineered Escherichia coli MG1655 strains. The first DBTL cycle employed a simple strategy to learn efficiently from a relatively small number of strains (36), wherein only the choice of ribosome-binding sites and an acyl-ACP/acyl-CoA reductase were modulated in a single pathway operon including genes encoding a thioesterase (UcFatB1), an acyl-ACP/acyl-CoA reductase (Maqu_2507, Maqu_2220, or Acr1), and an acyl-CoA synthetase (FadD). Measured variables included concentrations of dodecanol and all proteins in the engineered pathway. We used the data produced in the first DBTL cycle to train several machine-learning algorithms and to suggest protein profiles for the second DBTL cycle that would increase production. These strategies resulted in a 21% increase in dodecanol titer in Cycle 2 (up to 0.83 g/L, which is more than 6-fold greater than previously reported batch values for minimal medium). Beyond specific lessons learned about optimizing dodecanol titer in E. coli, this study had findings of broader relevance across synthetic biology applications, such as the importance of sequencing checks on plasmids in production strains as well as in cloning strains, and the critical need for more accurate protein expression predictive tools.

Robust fermentation of biomass-derived sugars into bioproducts demands the reliable microbial expression of metabolic pathways. Plasmid-based expression systems may suffer from instability and result in highly variable titers, rates, and yields. An established mitigation approach, chemical induced chromosomal expansion (CIChE), expands a singly integrated pathway to plasmid-like copy numbers while maintaining stability in the absence of antibiotic selection pressure. Here, we report parallel integration and chromosomal expansion (PIACE), extensions to CIChE that enable independent expansions of pathway components across multiple loci, use suicide vectors to achieve high-efficiency site-specific integration of sequence-validated multigene components, and introduce a heat-curable plasmid to obviate recA deletion post pathway expansion. We applied PIACE to stabilize an isopentenol pathway across three loci in E. coli DH1 and then generate libraries of pathway component copy number variants to screen for improved titers. Polynomial regressor statistical modeling of the production screening data suggests that increasing copy numbers of all isopentenol pathway components would further improve titers.

New synthetic biology capabilities hold the promise of dramatically improving our ability to engineer biological systems. However, a fundamental hurdle in realizing this potential is our inability to accurately predict biological behavior after modifying the corresponding genotype. Kinetic models have traditionally been used to predict pathway dynamics in bioengineered systems, but they take significant time to develop, and rely heavily on domain expertise. Here, we show that the combination of machine learning and abundant multiomics data (proteomics and metabolomics) can be used to effectively predict pathway dynamics in an automated fashion. The new method outperforms a classical kinetic model, and produces qualitative and quantitative predictions that can be used to productively guide bioengineering efforts. This method systematically leverages arbitrary amounts of new data to improve predictions, and does not assume any particular interactions, but rather implicitly chooses the most predictive ones. Using artificial intelligence to predict biological dynamics: New synthetic biology capabilities (e.g. CRISPR) dramatically improve our ability to engineer biological systems for the benefit of society (biofuels, medical drugs). However, this effort is hampered because we cannot reliably predict the outcome of our bioengineering efforts. Mathematical kinetic models have been traditionally used to predict pathway dynamics, but they take a long time to develop and require significant biological expertize. Here, we substitute traditional kinetic models with a machine learning approach that is able to learn pathway dynamics straight from data examples. This new approach can be systematically applied to any product, pathway or host and significantly speeds up bioengineering. [ABSTRACT FROM AUTHOR]