Misic, a general deep learning-based method for the high-throughput cell segmentation of complex bacterial communities

Segmentation of dense and multi-species bacterial colonies using models trained on synthetic microscopy images

The spread of microbial infections is governed by the self-organization of bacteria on surfaces. Bacterial interactions in clinically relevant settings remain challenging to quantify, especially in systems with multiple species or varied material properties. Quantitative image analysis methods based on machine learning show promise to overcome this challenge and support the development of novel antimicrobial treatments, but are limited by a lack of high-quality training data. Here, novel experimental and image analysis techniques for high-fidelity single-cell segmentation of bacterial colonies are developed. Machine learning-based segmentation models are trained solely using synthetic microscopy images that are processed to look realistic using a state-of-the-art image-to-image translation method (cycleGAN), requiring no biophysical modeling. Accurate single-cell segmentation is achieved for densely packed single-species colonies and multi-species colonies of common pathogenic bacteria, even under suboptimal imaging conditions and for both brightfield and confocal laser scanning microscopy. The resulting data provide quantitative insights into the self-organization of bacteria on soft surfaces. Thanks to their high adaptability and relatively simple implementation, these methods promise to greatly facilitate quantitative descriptions of bacterial infections in varied environments, and may be used for the development of rapid diagnostic tools in clinical settings.

Light-dependent modulation of protein localization and function in living bacteria cells

Most bacteria lack membrane-enclosed organelles and rely on macromolecular scaffolds at different subcellular locations to recruit proteins for specific functions. Here, we demonstrate that the optogenetic CRY2-CIB1 system from Arabidopsis thaliana can be used to rapidly direct proteins to different subcellular locations with varying efficiencies in live Escherichia coli cells, including the nucleoid, the cell pole, the membrane, and the midcell division plane. Such light-induced re-localization can be used to rapidly inhibit cytokinesis in actively dividing E. coli cells. We further show that CRY2-CIBN binding kinetics can be modulated by green light, adding a new dimension of control to the system. Finally, we test this optogenetic system in three additional bacterial species, Bacillus subtilis, Caulobacter crescentus, and Streptococcus pneumoniae, providing important considerations for this system's applicability in bacterial cell biology.

Quantification of cell shape, intracellular flows and transport based on DIC object detection and tracking

Computational image analysis combined with label-free imaging has helped maintain its relevance for cell biology, despite the rapid technical improvements in fluorescence microscopy with the molecular specificity of tags. Here, we discuss some computational tools developed in our lab and their application to quantify cell shape, intracellular organelle movement and bead transport in vitro, using differential interference contrast (DIC) microscopy data as inputs. The focus of these methods is image filtering to enhance image gradients, and combining them with segmentation and single particle tracking (SPT). We demonstrate the application of these methods to Escherichia coli cell length estimation and tracking of densely packed lipid granules in Caenorhabditis elegans one-celled embryos, diffusing beads in solutions of different viscosities and kinesin-driven transport on microtubules. These approaches demonstrate how improvements to low-level image analysis methods can help obtain insights through quantitative cellular and subcellular microscopy.

Gear up! An overview of the molecular equipment used by Myxococcus to move, kill, and divide in prey colonies

Myxococcus relies on motility to efficiently invade and predate a prey colony. Upon contact with prey, Myxococcus temporarily halts its motility and initiates prey cell lysis, which involves two contact-dependent predatory machineries, the Kil system and the needleless T3SS*. Predatory cells grow as they invade and feed on prey cells. When dividing, Myxococcus cells systematically pause their movements before division. This highlights a high level of co-ordination between motility and contact-dependent killing but also with cell division. In this review, we give an overview of the different nanomachines used by Myxococcus to move on surfaces, kill by contact, and divide, and we discuss the potential regulatory mechanisms at play during these different processes.

Emergence of bacterial glass

Densely packed, motile bacteria can adopt collective states not seen in conventional, passive materials. These states remain in many ways mysterious, and their physical characterization can aid our understanding of natural bacterial colonies and biofilms as well as materials in general. Here, we overcome challenges associated with generating uniformly growing, large, quasi-two-dimensional bacterial assemblies by a membrane-based microfluidic device and report the emergence of glassy states in two-dimensional suspension of Escherichia coli. As the number density increases by cell growth, populations of motile bacteria transition to a glassy state, where cells are packed and unable to move. This takes place in two steps, the first one suppressing only the orientational modes and the second one vitrifying the motion completely. Characterizing each phase through statistical analyses and investigations of individual motion of bacteria, we find not only characteristic features of glass such as rapid slowdown, dynamic heterogeneity, and cage effects, but also a few properties distinguished from those of thermal glass. These distinctive properties include the spontaneous formation of micro-domains of aligned cells with collective motion, the appearance of an unusual signal in the dynamic susceptibility, and the dynamic slowdown with a density dependence generally forbidden for thermal systems. Our results are expected to capture general characteristics of such active rod glass, which may serve as a physical mechanism underlying dense bacterial aggregates.

Travelling waves for a fast reaction limit of a discrete coagulation-fragmentation model with diffusion and proliferation

We study traveling wave solutions for a reaction-diffusion model, introduced in the article Calvez et al. (Regime switching on the propagation speed of travelling waves of some size-structured myxobacteriapopulation models, 2023), describing the spread of the social bacterium Myxococcus xanthus. This model describes the spatial dynamics of two different cluster sizes: isolated bacteria and paired bacteria. Two isolated bacteria can coagulate to form a cluster of two bacteria and conversely, a pair of bacteria can fragment into two isolated bacteria. Coagulation and fragmentation are assumed to occur at a certain rate denoted by k. In this article we study theoretically the limit of fast coagulation fragmentation corresponding mathematically to the limit when the value of the parameter k tends to + ∞ . For this regime, we demonstrate the existence and uniqueness of a transition between pulled and pushed fronts for a certain critical ratio θ ⋆ between the diffusion coefficient of isolated bacteria and the diffusion coefficient of paired bacteria. When the ratio is below θ ⋆ , the critical front speed is constant and corresponds to the linear speed. Conversely, when the ratio is above the critical threshold, the critical spreading speed becomes strictly greater than the linear speed.

Tools and methods for high-throughput single-cell imaging with the mother machine

Despite much progress, image processing remains a significant bottleneck for high-throughput analysis of microscopy data. One popular platform for single-cell time-lapse imaging is the mother machine, which enables long-term tracking of microbial cells under precisely controlled growth conditions. While several mother machine image analysis pipelines have been developed in the past several years, adoption by a non-expert audience remains a challenge. To fill this gap, we implemented our own software, MM3, as a plugin for the multidimensional image viewer napari. napari-MM3 is a complete and modular image analysis pipeline for mother machine data, which takes advantage of the high-level interactivity of napari. Here, we give an overview of napari-MM3 and test it against several well-designed and widely used image analysis pipelines, including BACMMAN and DeLTA. Researchers often analyze mother machine data with custom scripts using varied image analysis methods, but a quantitative comparison of the output of different pipelines has been lacking. To this end, we show that key single-cell physiological parameter correlations and distributions are robust to the choice of analysis method. However, we also find that small changes in thresholding parameters can systematically alter parameters extracted from single-cell imaging experiments. Moreover, we explicitly show that in deep learning-based segmentation, 'what you put is what you get' (WYPIWYG) - that is, pixel-level variation in training data for cell segmentation can propagate to the model output and bias spatial and temporal measurements. Finally, while the primary purpose of this work is to introduce the image analysis software that we have developed over the last decade in our lab, we also provide information for those who want to implement mother machine-based high-throughput imaging and analysis methods in their research.

Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges

Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.

Tools and methods for high-throughput single-cell imaging with the mother machine

Despite much progress, image processing remains a significant bottleneck for high-throughput analysis of microscopy data. One popular platform for single-cell time-lapse imaging is the mother machine, which enables long-term tracking of microbial cells under precisely controlled growth conditions. While several mother machine image analysis pipelines have been developed in the past several years, adoption by a non-expert audience remains a challenge. To fill this gap, we implemented our own software, MM3, as a plugin for the multidimensional image viewer napari. napari-MM3 is a complete and modular image analysis pipeline for mother machine data, which takes advantage of the high-level interactivity of napari. Here, we give an overview of napari-MM3 and test it against several well-designed and widely-used image analysis pipelines, including BACMMAN and DeLTA. Researchers often analyze mother machine data with custom scripts using varied image analysis methods, but a quantitative comparison of the output of different pipelines has been lacking. To this end, we show that key single-cell physiological parameter correlations and distributions are robust to the choice of analysis method. However, we also find that small changes in thresholding parameters can systematically alter parameters extracted from single-cell imaging experiments. Moreover, we explicitly show that in deep learning based segmentation, "what you put is what you get" (WYPIWYG) - i.e., pixel-level variation in training data for cell segmentation can propagate to the model output and bias spatial and temporal measurements. Finally, while the primary purpose of this work is to introduce the image analysis software that we have developed over the last decade in our lab, we also provide information for those who want to implement mother-machine-based high-throughput imaging and analysis methods in their research.

Label-free deep learning-based species classification of bacteria imaged by phase-contrast microscopy

Reliable detection and classification of bacteria and other pathogens in the human body, animals, food, and water is crucial for improving and safeguarding public health. For instance, identifying the species and its antibiotic susceptibility is vital for effective bacterial infection treatment. Here we show that phase contrast time-lapse microscopy combined with deep learning is sufficient to classify four species of bacteria relevant to human health. The classification is performed on living bacteria and does not require fixation or staining, meaning that the bacterial species can be determined as the bacteria reproduce in a microfluidic device, enabling parallel determination of susceptibility to antibiotics. We assess the performance of convolutional neural networks and vision transformers, where the best model attained a class-average accuracy exceeding 98%. Our successful proof-of-principle results suggest that the methods should be challenged with data covering more species and clinically relevant isolates for future clinical use.

Tracking bacteria at high density with FAST, the Feature-Assisted Segmenter/Tracker

Most bacteria live attached to surfaces in densely-packed communities. While new experimental and imaging techniques are beginning to provide a window on the complex processes that play out in these communities, resolving the behaviour of individual cells through time and space remains a major challenge. Although a number of different software solutions have been developed to track microorganisms, these typically require users either to tune a large number of parameters or to groundtruth a large volume of imaging data to train a deep learning model-both manual processes which can be very time consuming for novel experiments. To overcome these limitations, we have developed FAST, the Feature-Assisted Segmenter/Tracker, which uses unsupervised machine learning to optimise tracking while maintaining ease of use. Our approach, rooted in information theory, largely eliminates the need for users to iteratively adjust parameters manually and make qualitative assessments of the resulting cell trajectories. Instead, FAST measures multiple distinguishing 'features' for each cell and then autonomously quantifies the amount of unique information each feature provides. We then use these measurements to determine how data from different features should be combined to minimize tracking errors. Comparing our algorithm with a naïve approach that uses cell position alone revealed that FAST produced 4 to 10 fold fewer tracking errors. The modular design of FAST combines our novel tracking method with tools for segmentation, extensive data visualisation, lineage assignment, and manual track correction. It is also highly extensible, allowing users to extract custom information from images and seamlessly integrate it into downstream analyses. FAST therefore enables high-throughput, data-rich analyses with minimal user input. It has been released for use either in Matlab or as a compiled stand-alone application, and is available at https://bit.ly/3vovDHn, along with extensive tutorials and detailed documentation.

Multi-scale dynamic imaging reveals that cooperative motility behaviors promote efficient predation in bacteria

Many species, such as fish schools or bird flocks, rely on collective motion to forage, prey, or escape predators. Likewise, Myxococcus xanthus forages and moves collectively to prey and feed on other bacterial species. These activities require two distinct motility machines enabling adventurous (A) and social (S) gliding, however when and how these mechanisms are used has remained elusive. Here, we address this long-standing question by applying multiscale semantic cell tracking during predation. We show that: (1) foragers and swarms can comprise A- and S-motile cells, with single cells exchanging frequently between these groups; (2) A-motility is critical to ensure the directional movement of both foragers and swarms; (3) the combined action of A- and S-motile cells within swarms leads to increased predation efficiencies. These results challenge the notion that A- and S-motilities are exclusive to foragers and swarms, and show that these machines act synergistically to enhance predation efficiency.

Acinetobacter type VI secretion system comprises a non-canonical membrane complex

A. baumannii can rapidly acquire new resistance mechanisms and persist on abiotic surface, enabling the colonization of asymptomatic human host. In Acinetobacter the type VI secretion system (T6SS) is involved in twitching, surface motility and is used for interbacterial competition allowing the bacteria to uptake DNA. A. baumannii possesses a T6SS that has been well studied for its regulation and specific activity, but little is known concerning its assembly and architecture. The T6SS nanomachine is built from three architectural sub-complexes. Unlike the baseplate (BP) and the tail-tube complex (TTC), which are inherited from bacteriophages, the membrane complex (MC) originates from bacteria. The MC is the most external part of the T6SS and, as such, is subjected to evolution and adaptation. One unanswered question on the MC is how such a gigantesque molecular edifice is inserted and crosses the bacterial cell envelope. The A. baumannii MC lacks an essential component, the TssJ lipoprotein, which anchors the MC to the outer membrane. In this work, we studied how A. baumannii compensates the absence of a TssJ. We have characterized for the first time the A. baumannii's specific T6SS MC, its unique characteristic, its membrane localization, and assembly dynamics. We also defined its composition, demonstrating that its biogenesis employs three Acinetobacter-specific envelope-associated proteins that define an intricate network leading to the assembly of a five-proteins membrane super-complex. Our data suggest that A. baumannii has divided the function of TssJ by (1) co-opting a new protein TsmK that stabilizes the MC and by (2) evolving a new domain in TssM for homo-oligomerization, a prerequisite to build the T6SS channel. We believe that the atypical species-specific features we report in this study will have profound implication in our understanding of the assembly and evolutionary diversity of different T6SSs, that warrants future investigation.

Phage-antibiotic synergy: Cell filamentation is a key driver of successful phage predation

Phages are promising tools to fight antibiotic-resistant bacteria, and as for now, phage therapy is essentially performed in combination with antibiotics. Interestingly, combined treatments including phages and a wide range of antibiotics lead to an increased bacterial killing, a phenomenon called phage-antibiotic synergy (PAS), suggesting that antibiotic-induced changes in bacterial physiology alter the dynamics of phage propagation. Using single-phage and single-cell techniques, each step of the lytic cycle of phage HK620 was studied in E. coli cultures treated with either ceftazidime, cephalexin or ciprofloxacin, three filamentation-inducing antibiotics. In the presence of sublethal doses of antibiotics, multiple stress tolerance and DNA repair pathways are triggered following activation of the SOS response. One of the most notable effects is the inhibition of bacterial division. As a result, a significant fraction of cells forms filaments that stop dividing but have higher rates of mutagenesis. Antibiotic-induced filaments become easy targets for phages due to their enlarged surface areas, as demonstrated by fluorescence microscopy and flow cytometry techniques. Adsorption, infection and lysis occur more often in filamentous cells compared to regular-sized bacteria. In addition, the reduction in bacterial numbers caused by impaired cell division may account for the faster elimination of bacteria during PAS. We developed a mathematical model to capture the interaction between sublethal doses of antibiotics and exposition to phages. This model shows that the induction of filamentation by sublethal doses of antibiotics can amplify the replication of phages and therefore yield PAS. We also use this model to study the consequences of PAS on the emergence of antibiotic resistance. A significant percentage of hyper-mutagenic filamentous bacteria are effectively killed by phages due to their increased susceptibility to infection. As a result, the addition of even a very low number of bacteriophages produced a strong reduction of the mutagenesis rate of the entire bacterial population. We confirm this prediction experimentally using reporters for bacterial DNA repair. Our work highlights the multiple benefits associated with the combination of sublethal doses of antibiotics with bacteriophages.

Mechanobiology as a tool for addressing the genotype-to-phenotype problem in microbiology

The central hypothesis of the genotype-phenotype relationship is that the phenotype of a developing organism (i.e., its set of observable attributes) depends on its genome and the environment. However, as we learn more about the genetics and biochemistry of living systems, our understanding does not fully extend to the complex multiscale nature of how cells move, interact, and organize; this gap in understanding is referred to as the genotype-to-phenotype problem. The physics of soft matter sets the background on which living organisms evolved, and the cell environment is a strong determinant of cell phenotype. This inevitably leads to challenges as the full function of many genes, and the diversity of cellular behaviors cannot be assessed without wide screens of environmental conditions. Cellular mechanobiology is an emerging field that provides methodologies to understand how cells integrate chemical and physical environmental stress and signals, and how they are transduced to control cell function. Biofilm forming bacteria represent an attractive model because they are fast growing, genetically malleable and can display sophisticated self-organizing developmental behaviors similar to those found in higher organisms. Here, we propose mechanobiology as a new area of study in prokaryotic systems and describe its potential for unveiling new links between an organism's genome and phenome.

A review of open-source image analysis tools for mammalian cell culture: algorithms, features and implementations

Cell culture is undeniably important for multiple scientific applications, including pharmaceuticals, transplants, and cosmetics. However, cell culture involves multiple manual steps, such as regularly analyzing cell images for their health and morphology. Computer scientists have developed algorithms to automate cell imaging analysis, but they are not widely adopted by biologists, especially those lacking an interactive platform. To address the issue, we compile and review existing open-source cell image processing tools that provide interactive interfaces for management and prediction tasks. We highlight the prediction tools that can detect, segment, and track different mammalian cell morphologies across various image modalities and present a comparison of algorithms and unique features of these tools, whether they work locally or in the cloud. This would guide non-experts to determine which is best suited for their purposes and, developers to acknowledge what is worth further expansion. In addition, we provide a general discussion on potential implementations of the tools for a more extensive scope, which guides the reader to not restrict them to prediction tasks only. Finally, we conclude the article by stating new considerations for the development of interactive cell imaging tools and suggesting new directions for future research.

High content quantitative imaging of Mycobacterium tuberculosis responses to acidic microenvironments within human macrophages

Intracellular pathogens such as Mycobacterium tuberculosis (Mtb) have evolved diverse strategies to counteract macrophage defence mechanisms including phagolysosomal biogenesis. Within macrophages, Mtb initially resides inside membrane-bound phagosomes that interact with lysosomes and become acidified. The ability of Mtb to control and subvert the fusion between phagosomes and lysosomes plays a key role in the pathogenesis of tuberculosis. Therefore, understanding how pathogens interact with the endolysosomal network and cope with intracellular acidification is important to better understand the disease. Here, we describe in detail the use of fluorescence microscopy-based approaches to investigate Mtb responses to acidic environments in cellulo. We report high-content imaging modalities to probe Mtb sensing of external pH or visualise in real-time Mtb intrabacterial pH within infected human macrophages. We discuss various methodologies with step-by-step analyses that enable robust image-based quantifications. Finally, we highlight the advantages and limitations of these different approaches and discuss potential alternatives that can be applied to further investigate Mtb-host cell interactions. These methods can be adapted to study host-pathogen interactions in different biological systems and experimental settings. Altogether, these approaches represent a valuable tool to further broaden our understanding of the cellular and molecular mechanisms underlying intracellular pathogen survival.

Synthetic Micrographs of Bacteria (SyMBac) allows accurate segmentation of bacterial cells using deep neural networks

BACKGROUND

Deep-learning-based image segmentation models are required for accurate processing of high-throughput timelapse imaging data of bacterial cells. However, the performance of any such model strictly depends on the quality and quantity of training data, which is difficult to generate for bacterial cell images. Here, we present a novel method of bacterial image segmentation using machine learning models trained with Synthetic Micrographs of Bacteria (SyMBac).

RESULTS

We have developed SyMBac, a tool that allows for rapid, automatic creation of arbitrary amounts of training data, combining detailed models of cell growth, physical interactions, and microscope optics to create synthetic images which closely resemble real micrographs, and is capable of training accurate image segmentation models. The major advantages of our approach are as follows: (1) synthetic training data can be generated virtually instantly and on demand; (2) these synthetic images are accompanied by perfect ground truth positions of cells, meaning no data curation is required; (3) different biological conditions, imaging platforms, and imaging modalities can be rapidly simulated, meaning any change in one's experimental setup no longer requires the laborious process of manually generating new training data for each change. Deep-learning models trained with SyMBac data are capable of analysing data from various imaging platforms and are robust to drastic changes in cell size and morphology. Our benchmarking results demonstrate that models trained on SyMBac data generate more accurate cell identifications and precise cell masks than those trained on human-annotated data, because the model learns the true position of the cell irrespective of imaging artefacts. We illustrate the approach by analysing the growth and size regulation of bacterial cells during entry and exit from dormancy, which revealed novel insights about the physiological dynamics of cells under various growth conditions.

CONCLUSIONS

The SyMBac approach will help to adapt and improve the performance of deep-learning-based image segmentation models for accurate processing of high-throughput timelapse image data.

microbeSEG: A deep learning software tool with OMERO data management for efficient and accurate cell segmentation

In biotechnology, cell growth is one of the most important properties for the characterization and optimization of microbial cultures. Novel live-cell imaging methods are leading to an ever better understanding of cell cultures and their development. The key to analyzing acquired data is accurate and automated cell segmentation at the single-cell level. Therefore, we present microbeSEG, a user-friendly Python-based cell segmentation tool with a graphical user interface and OMERO data management. microbeSEG utilizes a state-of-the-art deep learning-based segmentation method and can be used for instance segmentation of a wide range of cell morphologies and imaging techniques, e.g., phase contrast or fluorescence microscopy. The main focus of microbeSEG is a comprehensible, easy, efficient, and complete workflow from the creation of training data to the final application of the trained segmentation model. We demonstrate that accurate cell segmentation results can be obtained within 45 minutes of user time. Utilizing public segmentation datasets or pre-labeling further accelerates the microbeSEG workflow. This opens the door for accurate and efficient data analysis of microbial cultures.

Efflux-linked accelerated evolution of antibiotic resistance at a population edge

Efflux is a common mechanism of resistance to antibiotics. We show that efflux itself promotes accumulation of antibiotic-resistance mutations (ARMs). This phenomenon was initially discovered in a bacterial swarm where the linked phenotypes of high efflux and high mutation frequencies spatially segregated to the edge, driven there by motility. We have uncovered and validated a global regulatory network connecting high efflux to downregulation of specific DNA-repair pathways even in non-swarming states. The efflux-DNA repair link was corroborated in a clinical "resistome" database: genomes with mutations that increase efflux exhibit a significant increase in ARMs. Accordingly, efflux inhibitors decreased evolvability to antibiotic resistance. Swarms also revealed how bacterial populations serve as a reservoir of ARMs even in the absence of antibiotic selection pressure. High efflux at the edge births mutants that, despite compromised fitness, survive there because of reduced competition. This finding is relevant to biofilms where efflux activity is high.

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.

DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches

This work demonstrates and guides how to use a range of state-of-the-art artificial neural-networks to analyse bacterial microscopy images using the recently developed ZeroCostDL4Mic platform. We generated a database of image datasets used to train networks for various image analysis tasks and present strategies for data acquisition and curation, as well as model training. We showcase different deep learning (DL) approaches for segmenting bright field and fluorescence images of different bacterial species, use object detection to classify different growth stages in time-lapse imaging data, and carry out DL-assisted phenotypic profiling of antibiotic-treated cells. To also demonstrate the ability of DL to enhance low-phototoxicity live-cell microscopy, we showcase how image denoising can allow researchers to attain high-fidelity data in faster and longer imaging. Finally, artificial labelling of cell membranes and predictions of super-resolution images allow for accurate mapping of cell shape and intracellular targets. Our purposefully-built database of training and testing data aids in novice users' training, enabling them to quickly explore how to analyse their data through DL. We hope this lays a fertile ground for the efficient application of DL in microbiology and fosters the creation of tools for bacterial cell biology and antibiotic research.

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.

A Tad-like apparatus is required for contact-dependent prey killing in predatory social bacteria

Myxococcus xanthus, a soil bacterium, predates collectively using motility to invade prey colonies. Prey lysis is mostly thought to rely on secreted factors, cocktails of antibiotics and enzymes, and direct contact with Myxococcus cells. In this study, we show that on surfaces the coupling of A-motility and contact-dependent killing is the central predatory mechanism driving effective prey colony invasion and consumption. At the molecular level, contact-dependent killing involves a newly discovered type IV filament-like machinery (Kil) that both promotes motility arrest and prey cell plasmolysis. In this process, Kil proteins assemble at the predator-prey contact site, suggesting that they allow tight contact with prey cells for their intoxication. Kil-like systems form a new class of Tad-like machineries in predatory bacteria, suggesting a conserved function in predator-prey interactions. This study further reveals a novel cell-cell interaction function for bacterial pili-like assemblages.