Deep model predictive control of gene expression in thousands of single cells.

Gene expression is inherently dynamic, due to complex regulation and stochastic biochemical events. However, the effects of these dynamics on cell phenotypes can be difficult to determine. Researchers have historically been limited to passive observations of natural dynamics, which can preclude studies of elusive and noisy cellular events where large amounts of data are required to reveal statistically significant effects. Here, using recent advances in the fields of machine learning and control theory, we train a deep neural network to accurately predict the response of an optogenetic system in Escherichia coli cells. We then use the network in a deep model predictive control framework to impose arbitrary and cell-specific gene expression dynamics on thousands of single cells in real time, applying the framework to generate complex time-varying patterns. We also showcase the framework's ability to link expression patterns to dynamic functional outcomes by controlling expression of the tetA antibiotic resistance gene. This study highlights how deep learning-enabled feedback control can be used to tailor distributions of gene expression dynamics with high accuracy and throughput without expert knowledge of the biological system.

Light-inducible protein degradation in E. coli with the LOVdeg tag.

Molecular tools for optogenetic control allow for spatial and temporal regulation of cell behavior. In particular, light-controlled protein degradation is a valuable mechanism of regulation because it can be highly modular, used in tandem with other control mechanisms, and maintain functionality throughout growth phases. Here, we engineered LOVdeg, a tag that can be appended to a protein of interest for inducible degradation in Escherichia coli using blue light. We demonstrate the modularity of LOVdeg by using it to tag a range of proteins, including the LacI repressor, CRISPRa activator, and the AcrB efflux pump. Additionally, we demonstrate the utility of pairing the LOVdeg tag with existing optogenetic tools to enhance performance by developing a combined EL222 and LOVdeg system. Finally, we use the LOVdeg tag in a metabolic engineering application to demonstrate post-translational control of metabolism. Together, our results highlight the modularity and functionality of the LOVdeg tag system and introduce a powerful new tool for bacterial optogenetics.

Generating information-dense promoter sequences with optimal string packing.

Dense arrangements of binding sites within nucleotide sequences can collectively influence downstream transcription rates or initiate biomolecular interactions. For example, natural promoter regions can harbor many overlapping transcription factor binding sites that influence the rate of transcription initiation. Despite the prevalence of overlapping binding sites in nature, rapid design of nucleotide sequences with many overlapping sites remains a challenge. Here, we show that this is an NP-hard problem, coined here as the nucleotide String Packing Problem (SPP). We then introduce a computational technique that efficiently assembles sets of DNA-protein binding sites into dense, contiguous stretches of double-stranded DNA. For the efficient design of nucleotide sequences spanning hundreds of base pairs, we reduce the SPP to an Orienteering Problem with integer distances, and then leverage modern integer linear programming solvers. Our method optimally packs libraries of 20-100 binding sites into dense nucleotide arrays of 50-300 base pairs in 0.05-10 seconds. Unlike approximation algorithms or meta-heuristics, our approach finds provably optimal solutions. We demonstrate how our method can generate large sets of diverse sequences suitable for library generation, where the frequency of binding site usage across the returned sequences can be controlled by modulating the objective function. As an example, we then show how adding additional constraints, like the inclusion of sequence elements with fixed positions, allows for the design of bacterial promoters. The nucleotide string packing approach we present can accelerate the design of sequences with complex DNA-protein interactions. When used in combination with synthesis and high-throughput screening, this design strategy could help interrogate how complex binding site arrangements impact either gene expression or biomolecular mechanisms in varied cellular contexts. Author Summary: The way protein binding sites are arranged on DNA can control the regulation and transcription of downstream genes. Areas with a high concentration of binding sites can enable complex interplay between transcription factors, a feature that is exploited by natural promoters. However, designing synthetic promoters that contain dense arrangements of binding sites is a challenge. The task involves overlapping many binding sites, each typically about 10 nucleotides long, within a constrained sequence area, which becomes increasingly difficult as sequence length decreases, and binding site variety increases. We introduce an approach to design nucleotide sequences with optimally packed protein binding sites, which we call the nucleotide String Packing Problem (SPP). We show that the SPP can be solved efficiently using integer linear programming to identify the densest arrangements of binding sites for a specified sequence length. We show how adding additional constraints, like the inclusion of sequence elements with fixed positions, allows for the design of bacterial promoters. The presented approach enables the rapid design and study of nucleotide sequences with complex, dense binding site architectures.

Comprehensive Screening of a Light-Inducible Split Cre Recombinase with Domain Insertion Profiling.

Splitting proteins with light- or chemically inducible dimers provides a mechanism for post-translational control of protein function. However, current methods for engineering stimulus-responsive split proteins often require significant protein engineering expertise and the laborious screening of individual constructs. To address this challenge, we use a pooled library approach that enables rapid generation and screening of nearly all possible split protein constructs in parallel, where results can be read out by using sequencing. We perform our method on Cre recombinase with optogenetic dimers as a proof of concept, resulting in comprehensive data on the split sites throughout the protein. To improve the accuracy in predicting split protein behavior, we develop a Bayesian computational approach to contextualize errors inherent to experimental procedures. Overall, our method provides a streamlined approach for achieving inducible post-translational control of a protein of interest.

Deep Neural Networks for Predicting Single-Cell Responses and Probability Landscapes.

Engineering biology relies on the accurate prediction of cell responses. However, making these predictions is challenging for a variety of reasons, including the stochasticity of biochemical reactions, variability between cells, and incomplete information about underlying biological processes. Machine learning methods, which can model diverse input-output relationships without requiring a priori mechanistic knowledge, are an ideal tool for this task. For example, such approaches can be used to predict gene expression dynamics given time-series data of past expression history. To explore this application, we computationally simulated single-cell responses, incorporating different sources of noise and alternative genetic circuit designs. We showed that deep neural networks trained on these simulated data were able to correctly infer the underlying dynamics of a cell response even in the presence of measurement noise and stochasticity in the biochemical reactions. The training set size and the amount of past data provided as inputs both affected prediction quality, with cascaded genetic circuits that introduce delays requiring more past data. We also tested prediction performance on a bistable auto-activation circuit, finding that our initial method for predicting a single trajectory was fundamentally ill-suited for multimodal dynamics. To address this, we updated the network architecture to predict the entire distribution of future states, showing it could accurately predict bimodal expression distributions. Overall, these methods can be readily applied to the diverse prediction tasks necessary to predict and control a variety of biological circuits, a key aspect of many synthetic biology applications.

Longitudinal Single-Cell Imaging of Engineered Strains with Stimulated Raman Scattering to Characterize Heterogeneity in Fatty Acid Production.

Understanding metabolic heterogeneity is critical for optimizing microbial production of valuable chemicals, but requires tools that can quantify metabolites at the single-cell level over time. Here, longitudinal hyperspectral stimulated Raman scattering (SRS) chemical imaging is developed to directly visualize free fatty acids in engineered Escherichia coli over many cell cycles. Compositional analysis is also developed to estimate the chain length and unsaturation of the fatty acids in living cells. This method reveals substantial heterogeneity in fatty acid production among and within colonies that emerges over the course of many generations. Interestingly, the strains display distinct types of production heterogeneity in an enzyme-dependent manner. By pairing time-lapse and SRS imaging, the relationship between growth and production at the single-cell level are examined. The results demonstrate that cell-to-cell production heterogeneity is pervasive and provides a means to link single-cell and population-level production.

Comprehensive screening of a light-inducible split Cre recombinase with domain insertion profiling.

Splitting proteins with light- or chemically-inducible dimers provides a mechanism for post-translational control of protein function. However, current methods for engineering stimulus-responsive split proteins often require significant protein engineering expertise and laborious screening of individual constructs. To address this challenge, we use a pooled library approach that enables rapid generation and screening of nearly all possible split protein constructs in parallel, where results can be read out using sequencing. We perform our method on Cre recombinase with optogenetic dimers as a proof of concept, resulting in comprehensive data on split sites throughout the protein. To improve accuracy in predicting split protein behavior, we develop a Bayesian computational approach to contextualize errors inherent to experimental procedures. Overall, our method provides a streamlined approach for achieving inducible post-translational control of a protein of interest.

Controlled Protein Activities with Viral Proteases, Antiviral Peptides, and Antiviral Drugs.

Chemical control of protein activity is a powerful tool for scientific study, synthetic biology, and cell therapy; however, for broad use, effective chemical inducer systems must minimally crosstalk with endogenous processes and exhibit desirable drug delivery properties. Accordingly, the drug-controllable proteolytic activity of hepatitis C cis-protease NS3 and its associated antiviral drugs have been used to regulate protein activity and gene modulation. These tools advantageously exploit non-eukaryotic and non-prokaryotic proteins and clinically approved inhibitors. Here, we expand the toolkit by utilizing catalytically inactive NS3 protease as a high affinity binder to genetically encoded, antiviral peptides. Through our approach, we create NS3-peptide complexes that can be displaced by FDA-approved drugs to modulate transcription, cell signaling, and split-protein complementation. With our developed system, we invented a new mechanism to allosterically regulate Cre recombinase. Allosteric Cre regulation with NS3 ligands enables orthogonal recombination tools in eukaryotic cells and functions in divergent organisms to control prokaryotic recombinase activity.

Light inducible protein degradation in E. coli with the LOVdeg tag.

Molecular tools for optogenetic control allow for spatial and temporal regulation of cell behavior. In particular, light controlled protein degradation is a valuable mechanism of regulation because it can be highly modular, used in tandem with other control mechanisms, and maintain functionality throughout growth phases. Here, we engineered LOVdeg, a tag that can be appended to a protein of interest for inducible degradation in Escherichia coli using blue light. We demonstrate the modularity of LOVdeg by using it to tag a range of proteins, including the LacI repressor, CRISPRa activator, and the AcrB efflux pump. Additionally, we demonstrate the utility of pairing the LOVdeg tag with existing optogenetic tools to enhance performance by developing a combined EL222 and LOVdeg system. Finally, we use the LOVdeg tag in a metabolic engineering application to demonstrate post-translational control of metabolism. Together, our results highlight the modularity and functionality of the LOVdeg tag system, and introduce a powerful new tool for bacterial optogenetics.

Controlled protein activities with viral proteases, antiviral peptides, and antiviral drugs.

Chemical control of protein activity is a powerful tool for scientific study, synthetic biology, and cell therapy; however, for broad use, effective chemical inducer systems must minimally crosstalk with endogenous processes and exhibit desirable drug delivery properties. Accordingly, the drug-controllable proteolytic activity of hepatitis C cis- protease NS3 and its associated antiviral drugs have been used to regulate protein activity and gene modulation. These tools advantageously exploit non-eukaryotic/prokaryotic proteins and clinically approved inhibitors. Here we expand the toolkit by utilizing catalytically inactive NS3 protease as a high affinity binder to genetically encoded, antiviral peptides. Through our approach, we create NS3-peptide complexes that can be displaced by FDA-approved drugs to modulate transcription, cell signaling, split-protein complementation. With our developed system, we discover a new mechanism to allosterically regulate Cre recombinase. Allosteric Cre regulation with NS3 ligands enables orthogonal recombination tools in eukaryotic cells and functions in divergent organisms to control prokaryotic recombinase activity.

An optogenetic toolkit for light-inducible antibiotic resistance.

Antibiotics are a key control mechanism for synthetic biology and microbiology. Resistance genes are used to select desired cells and regulate bacterial populations, however their use to-date has been largely static. Precise spatiotemporal control of antibiotic resistance could enable a wide variety of applications that require dynamic control of susceptibility and survival. Here, we use light-inducible Cre recombinase to activate expression of drug resistance genes in Escherichia coli. We demonstrate light-activated resistance to four antibiotics: carbenicillin, kanamycin, chloramphenicol, and tetracycline. Cells exposed to blue light survive in the presence of lethal antibiotic concentrations, while those kept in the dark do not. To optimize resistance induction, we vary promoter, ribosome binding site, and enzyme variant strength using chromosome and plasmid-based constructs. We then link inducible resistance to expression of a heterologous fatty acid enzyme to increase production of octanoic acid. These optogenetic resistance tools pave the way for spatiotemporal control of cell survival.

Advances in linking single-cell bacterial stress response to population-level survival.

Stress response mechanisms can allow bacteria to survive a myriad of challenges, including nutrient changes, antibiotic encounters, and antagonistic interactions with other microbes. Expression of these stress response pathways, in addition to other cell features such as growth rate and metabolic state, can be heterogeneous across cells and over time. Collectively, these single-cell-level phenotypes contribute to an overall population-level response to stress. These include diversifying actions, which can be used to enable bet-hedging, and coordinated actions, such as biofilm production, horizontal gene transfer, and cross-feeding. Here, we highlight recent results and emerging technologies focused on both single-cell and population-level responses to stressors, and we draw connections about the combined impact of these effects on survival of bacterial communities.

Visualization of a Limonene Synthesis Metabolon Inside Living Bacteria by Hyperspectral SRS Microscopy.

Monitoring biosynthesis activity at single-cell level is key to metabolic engineering but is still difficult to achieve in a label-free manner. Using hyperspectral stimulated Raman scattering imaging in the 670-900 cm-1 region, localized limonene synthesis are visualized inside engineered Escherichia coli. The colocalization of limonene and GFP-fused limonene synthase is confirmed by co-registered stimulated Raman scattering and two-photon fluorescence images. The finding suggests a limonene synthesis metabolon with a polar distribution inside the cells. This finding expands the knowledge of de novo limonene biosynthesis in engineered bacteria and highlights the potential of SRS chemical imaging in metabolic engineering research.

Deep Learning Concepts and Applications for Synthetic Biology.

Synthetic biology has a natural synergy with deep learning. It can be used to generate large data sets to train models, for example by using DNA synthesis, and deep learning models can be used to inform design, such as by generating novel parts or suggesting optimal experiments to conduct. Recently, research at the interface of engineering biology and deep learning has highlighted this potential through successes including the design of novel biological parts, protein structure prediction, automated analysis of microscopy data, optimal experimental design, and biomolecular implementations of artificial neural networks. In this review, we present an overview of synthetic biology-relevant classes of data and deep learning architectures. We also highlight emerging studies in synthetic biology that capitalize on deep learning to enable novel understanding and design, and discuss challenges and future opportunities in this space.

Transcriptional Tuning of Mevalonate Pathway Enzymes to Identify the Impact on Limonene Production in Escherichia coli.

Heterologous production of limonene in microorganisms through the mevalonate (MVA) pathway has traditionally imposed metabolic burden and reduced cell fitness, where imbalanced stoichiometries among sequential enzymes result in the accumulation of toxic intermediates. Although prior studies have shown that changes to mRNA stability, RBS strength, and protein homology can be effective strategies for balancing enzyme levels in the MVA pathway, testing different variations of these parameters often requires distinct genetic constructs, which can exponentially increase assembly costs as pathways increase in size. Here, we developed a multi-input transcriptional circuit to regulate the MVA pathway, where four chemical inducers, l-arabinose (Ara), choline chloride (Cho), cuminic acid (Cuma), and isopropyl ß-d-1-thiogalactopyranoside (IPTG), each regulate one of four orthogonal promoters. We tested modular transcriptional regulation of the MVA pathway by placing this circuit in an engineered Escherichia coli "marionette" strain, which enabled systematic and independent tuning of the first three enzymes (AtoB, HMGS, and HMGR) in the MVA pathway. By systematically testing combinations of chemical inducers as inputs, we investigated relationships between the expressions of different MVA pathway submodules, finding that limonene yields are sensitive to the coordinated transcriptional regulation of HMGS and HMGR.

Dynamic gene expression and growth underlie cell-to-cell heterogeneity in Escherichia coli stress response.

Cell-to-cell heterogeneity in gene expression and growth can have critical functional consequences, such as determining whether individual bacteria survive or die following stress. Although phenotypic variability is well documented, the dynamics that underlie it are often unknown. This information is important because dramatically different outcomes can arise from gradual versus rapid changes in expression and growth. Using single-cell time-lapse microscopy, we measured the temporal expression of a suite of stress-response reporters in Escherichia coli, while simultaneously monitoring growth rate. In conditions without stress, we found several examples of pulsatile expression. Single-cell growth rates were often anticorrelated with reporter levels, with changes in growth preceding changes in expression. These dynamics have functional consequences, which we demonstrate by measuring survival after challenging cells with the antibiotic ciprofloxacin. Our results suggest that fluctuations in both gene expression and growth dynamics in stress-response networks have direct consequences on survival.

Anticipating antibiotic resistance.

Machine learning can use clinical history to lower the risk of infection recurrence.

DeLTA 2.0: A deep learning pipeline for quantifying single-cell spatial and temporal dynamics.

Improvements in microscopy software and hardware have dramatically increased the pace of image acquisition, making analysis a major bottleneck in generating quantitative, single-cell data. Although tools for segmenting and tracking bacteria within time-lapse images exist, most require human input, are specialized to the experimental set up, or lack accuracy. Here, we introduce DeLTA 2.0, a purely Python workflow that can rapidly and accurately analyze images of single cells on two-dimensional surfaces to quantify gene expression and cell growth. The algorithm uses deep convolutional neural networks to extract single-cell information from time-lapse images, requiring no human input after training. DeLTA 2.0 retains all the functionality of the original version, which was optimized for bacteria growing in the mother machine microfluidic device, but extends results to two-dimensional growth environments. Two-dimensional environments represent an important class of data because they are more straightforward to implement experimentally, they offer the potential for studies using co-cultures of cells, and they can be used to quantify spatial effects and multi-generational phenomena. However, segmentation and tracking are significantly more challenging tasks in two-dimensions due to exponential increases in the number of cells. To showcase this new functionality, we analyze mixed populations of antibiotic resistant and susceptible cells, and also track pole age and growth rate across generations. In addition to the two-dimensional capabilities, we also introduce several major improvements to the code that increase accessibility, including the ability to accept many standard microscopy file formats as inputs and the introduction of a Google Colab notebook so users can try the software without installing the code on their local machine. DeLTA 2.0 is rapid, with run times of less than 10 minutes for complete movies with hundreds of cells, and is highly accurate, with error rates around 1%, making it a powerful tool for analyzing time-lapse microscopy data.

Microsecond fingerprint stimulated Raman spectroscopic imaging by ultrafast tuning and spatial-spectral learning.

Label-free vibrational imaging by stimulated Raman scattering (SRS) provides unprecedented insight into real-time chemical distributions. Specifically, SRS in the fingerprint region (400-1800 cm-1) can resolve multiple chemicals in a complex bio-environment. However, due to the intrinsic weak Raman cross-sections and the lack of ultrafast spectral acquisition schemes with high spectral fidelity, SRS in the fingerprint region is not viable for studying living cells or large-scale tissue samples. Here, we report a fingerprint spectroscopic SRS platform that acquires a distortion-free SRS spectrum at 10 cm-1 spectral resolution within 20 µs using a polygon scanner. Meanwhile, we significantly improve the signal-to-noise ratio by employing a spatial-spectral residual learning network, reaching a level comparable to that with 100 times integration. Collectively, our system enables high-speed vibrational spectroscopic imaging of multiple biomolecules in samples ranging from a single live microbe to a tissue slice.

Programmable gene regulation for metabolic engineering using decoy transcription factor binding sites.

Transcription factor decoy binding sites are short DNA sequences that can titrate a transcription factor away from its natural binding site, therefore regulating gene expression. In this study, we harness synthetic transcription factor decoy systems to regulate gene expression for metabolic pathways in Escherichia coli. We show that transcription factor decoys can effectively regulate expression of native and heterologous genes. Tunability of the decoy can be engineered via changes in copy number or modifications to the DNA decoy site sequence. Using arginine biosynthesis as a showcase, we observed a 16-fold increase in arginine production when we introduced the decoy system to steer metabolic flux towards increased arginine biosynthesis, with negligible growth differences compared to the wild type strain. The decoy-based production strain retains high genetic integrity; in contrast to a gene knock-out approach where mutations were common, we detected no mutations in the production system using the decoy-based strain. We further show that transcription factor decoys are amenable to multiplexed library screening by demonstrating enhanced tolerance to pinene with a combinatorial decoy library. Our study shows that transcription factor decoy binding sites are a powerful and compact tool for metabolic engineering.