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

Artificial intelligence in bacterial diagnostics and antimicrobial susceptibility testing: Current advances and future prospects

Recently, artificial intelligence (AI) has emerged as a transformative tool, enhancing the speed, accuracy, and scalability of bacterial diagnostics. This review explores the role of AI in revolutionizing bacterial detection and antimicrobial susceptibility testing (AST) by leveraging machine learning models, including Random Forest, Support Vector Machines (SVM), and deep learning architectures such as Convolutional Neural Networks (CNNs) and transformers. The integration of AI into these methods promises to address the current limitations of traditional techniques, offering a path toward more efficient, accessible, and reliable diagnostic solutions. In particular, AI-based approaches have demonstrated significant potential in resource-limited settings by enabling cost-effective and portable diagnostic solutions, reducing dependency on specialized infrastructure, and facilitating remote bacterial detection through smartphone-integrated platforms and telemedicine applications. This review highlights AI's transformative role in automating data analysis, minimizing human error, and delivering real-time diagnostic results, ultimately improving patient outcomes and optimizing healthcare efficiency. In addition, we not only examine the current advances in machine learning and deep learning but also review their applications in plate counting, mass spectrometry, morphology-based and motion-based microscopic detection, holographic microscopy, colorimetric and fluorescence detection, electrochemical sensors, Raman and Surface-Enhanced Raman Spectroscopy (SERS), and Atomic Force Microscopy (AFM) for bacterial diagnostics and AST. Finally, we discuss the future directions and potential advancements in AI-driven bacterial diagnostics.

Revolutionizing biological digital twins: Integrating internet of bio-nano things, convolutional neural networks, and federated learning

Digital twins (DTs) are advancing biotechnology by providing digital models for drug discovery, digital health applications, and biological assets, including microorganisms. However, the hypothesis posits that implementing micro- and nanoscale DTs, especially for biological entities like bacteria, presents substantial challenges. These challenges stem from the complexities of data extraction, transmission, and computation, along with the necessity for a specialized Internet of Things (IoT) infrastructure. To address these challenges, this article proposes a novel framework that leverages bio-network technologies, including the Internet of Bio-Nano Things (IoBNT), and decentralized deep learning algorithms such as federated learning (FL) and convolutional neural networks (CNN). The methodology involves using CNNs for robust pattern recognition and FL to reduce bandwidth consumption while enhancing security. IoBNT devices are utilized for precise microscopic data acquisition and transmission, which ensures minimal error rates. The results demonstrate a multi-class classification accuracy of 98.7% across 33 bacteria categories, achieving over 99% bandwidth savings. Additionally, IoBNT integration reduces biological data transfer errors by up to 98%, even under worst-case conditions. This framework is further supported by an adaptable, user-friendly dashboard, expanding its applicability across pharmaceutical and biotechnology industries.

The nucleoid of rapidly growing Escherichia coli localizes close to the inner membrane and is organized by transcription, translation, and cell geometry

Bacterial chromosomes are spatiotemporally organized and sensitive to environmental changes. However, the mechanisms underlying chromosome configuration and reorganization are not fully understood. Here, we use single-molecule localization microscopy and live-cell imaging to show that the Escherichia coli nucleoid adopts a condensed, membrane-proximal configuration during rapid growth. Drug treatment induces a rapid collapse of the nucleoid from an apparently membrane-bound state within 10 min of halting transcription and translation. This hints toward an active role of transertion (coupled transcription, translation, and membrane insertion) in nucleoid organization, while cell wall synthesis inhibitors only affect nucleoid organization during morphological changes. Further, we provide evidence that the nucleoid spatially correlates with elongasomes in unperturbed cells, suggesting that large membrane-bound complexes might be hotspots for transertion. The observed correlation diminishes in cells with changed cell geometry or upon inhibition of protein biosynthesis. Replication inhibition experiments, as well as multi-drug treatments highlight the role of entropic effects and transcription in nucleoid condensation and positioning. Thus, our results indicate that transcription and translation, possibly in the context of transertion, act as a principal organizer of the bacterial nucleoid, and show that an altered metabolic state and antibiotic treatment lead to major changes in the spatial organization of the nucleoid.

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.

Computational Analysis of Morphological Changes in Lactiplantibacillus plantarum Under Acidic Stress

Shape and size often define the characteristics of individual microorganisms. Hence, characterizing cell morphology using computational image analysis can aid in the accurate, quick, unbiased, and reliable identification of bacterial morphology. Modifications in the cell morphology of Lactiplantibacillus plantarum were determined in response to acidic stress, during the growth stage of the cells at a pH 3.5 compared to a pH of 6.5. Consequently, we developed a computational method to sort, detect, analyze, and measure bacterial size in a single-species culture. We applied a deep learning methodology composed of object detection followed by image classification to measure bacterial cell dimensions. The results of our computational analysis showed a significant change in cell morphology in response to alterations of the environmental pH. Specifically, we found that the bacteria existed as a long unseparated cell, with a dramatic increase in length of 41% at a low pH compared to the control. Bacterial width was not altered in the low pH compared to the control. Those changes could be attributed to modifications in membrane properties, such as increased cell membrane fluidity in acidic pH. The integration of deep learning and object detection techniques, with microbial microscopic imaging, is an advanced methodology for studying cellular structures that can be projected for use in other bacterial species or cells. These trained models and scripts can be applied to other microbes and cells.

Segment Anything for Microscopy

Accurate segmentation of objects in microscopy images remains a bottleneck for many researchers despite the number of tools developed for this purpose. Here, we present Segment Anything for Microscopy (μSAM), a tool for segmentation and tracking in multidimensional microscopy data. It is based on Segment Anything, a vision foundation model for image segmentation. We extend it by fine-tuning generalist models for light and electron microscopy that clearly improve segmentation quality for a wide range of imaging conditions. We also implement interactive and automatic segmentation in a napari plugin that can speed up diverse segmentation tasks and provides a unified solution for microscopy annotation across different microscopy modalities. Our work constitutes the application of vision foundation models in microscopy, laying the groundwork for solving image analysis tasks in this domain with a small set of powerful deep learning models.

Cellpose3: one-click image restoration for improved cellular segmentation

Generalist methods for cellular segmentation have good out-of-the-box performance on a variety of image types; however, existing methods struggle for images that are degraded by noise, blurring or undersampling, all of which are common in microscopy. We focused the development of Cellpose3 on addressing these cases and here we demonstrate substantial out-of-the-box gains in segmentation and image quality for noisy, blurry and undersampled images. Unlike previous approaches that train models to restore pixel values, we trained Cellpose3 to output images that are well segmented by a generalist segmentation model, while maintaining perceptual similarity to the target images. Furthermore, we trained the restoration models on a large, varied collection of datasets, thus ensuring good generalization to user images. We provide these tools as 'one-click' buttons inside the graphical interface of Cellpose as well as in the Cellpose API.

CellSAM: A Foundation Model for Cell Segmentation

Cells are a fundamental unit of biological organization, and identifying them in imaging data - cell segmentation - is a critical task for various cellular imaging experiments. While deep learning methods have led to substantial progress on this problem, most models are specialist models that work well for specific domains but cannot be applied across domains or scale well with large amounts of data. In this work, we present CellSAM, a universal model for cell segmentation that generalizes across diverse cellular imaging data. CellSAM builds on top of the Segment Anything Model (SAM) by developing a prompt engineering approach for mask generation. We train an object detector, CellFinder, to automatically detect cells and prompt SAM to generate segmentations. We show that this approach allows a single model to achieve human-level performance for segmenting images of mammalian cells, yeast, and bacteria collected across various imaging modalities. We show that CellSAM has strong zero-shot performance and can be improved with a few examples via few-shot learning. Additionally, we demonstrate how CellSAM can be applied across diverse bioimage analysis workflows. A deployed version of CellSAM is available at https://cellsam.deepcell.org/.

Advancing antibiotic discovery with bacterial cytological profiling: a high-throughput solution to antimicrobial resistance

Developing new antibiotics poses a significant challenge in the fight against antimicrobial resistance (AMR), a critical global health threat responsible for approximately 5 million deaths annually. Finding new classes of antibiotics that are safe, have acceptable pharmacokinetic properties, and are appropriately active against pathogens is a lengthy and expensive process. Therefore, high-throughput platforms are needed to screen large libraries of synthetic and natural compounds. In this review, we present bacterial cytological profiling (BCP) as a rapid, scalable, and cost-effective method for identifying antibiotic mechanisms of action. Notably, BCP has proven its potential in drug discovery, demonstrated by the identification of the cellular target of spirohexenolide A against methicillin-resistant Staphylococcus aureus. We present the application of BCP for different bacterial organisms and different classes of antibiotics and discuss BCP's advantages, limitations, and potential improvements. Furthermore, we highlight the studies that have utilized BCP to investigate pathogens listed in the Bacterial Priority Pathogens List 2024 and we identify the pathogens whose cytological profiles are missing. We also explore the most recent artificial intelligence and deep learning techniques that could enhance the analysis of data generated by BCP, potentially advancing our understanding of antibiotic resistance mechanisms and the discovery of novel druggable pathways.

A novel ensemble approach with deep transfer learning for accurate identification of foodborne bacteria from hyperspectral microscopy

The detection of foodborne bacteria is critical in ensuring both consumer safety and food safety. If these pathogens are not properly identified, it can lead to dangerous cross-contamination. One of the most common methods for classifying bacteria is through the examination of Hyperspectral microscope imaging (HMI). A widely used technique for measuring microbial growth is microscopic cell counting. HMI is a laborious and expensive process, producing voluminous data and needing specialized equipment, which might not be widely available. Machine learning (ML) methods are now frequently utilized to automatically interpret data from hyperspectral microscopy. The objective of our study is to devise a technique that employs deep transfer learning to address the challenge of limited data and utilizes four base classifiers - InceptionResNetV2, MobileNet, ResNet101V2, and Xception - to create an ensemble-based classification model for distinguishing live and dead bacterial cells of six pathogenic strains. In order to determine the optimal weights for the base classifiers, a Powell's optimization method was utilized in conjunction with a weighted average ensemble (WAVE) technique. We carried out an extensive experimental study to verify the efficiency of our proposed ensemble model on live and dead cell images of six different foodborne bacteria. In order to gain a better understanding of the regions, we performed a Grad-CAM analysis to explain the predictions made by our model. Through a series of experiments, our proposed framework has proven its capacity to effectively and precisely detect numerous bacterial pathogens. Specifically, it achieved a perfect identification rate of 100 % for Escherichia coli (EC), Listeria innocua (LI), and Salmonella Enteritidis (SE), while achieving rates of 96.30 % for Salmonella Typhimurium (ST), 87.13 % for Staphylococcus aureus (SA), and 94.12 % for Salmonella Heidelberg (SH). As a result, it can be considered as an effective tool for the identification of foodborne pathogens, due to its high level of efficiency.

OmniSegger: A time-lapse image analysis pipeline for bacterial cells

Time-lapse microscopy is a powerful tool for studying the cell biology of bacterial cells. The development of pipelines that facilitate the automated analysis of these datasets is a long-standing goal of the field. In this paper, we describe OmniSegger , an updated version of our SuperSegger pipeline, developed as an open-source, modular, and holistic suite of algorithms whose input is raw microscopy images and whose output is a wide range of quantitative cellular analyses, including dynamical cell cytometry data and cellular visualizations. The updated version described in this paper introduces two principal refinements: (i) robustness to cell morphologies and (ii) support for a range of common imaging modalities. To demonstrate robustness to cell morphology, we present an analysis of the proliferation dynamics of Escherichia coli treated with a drug that induces filamentation. To demonstrate extended support for new image modalities, we analyze cells imaged by five distinct modalities: phase-contrast, two brightfield modalities, and cytoplasmic and membrane fluorescence. Together, this pipeline should greatly increase the scope of tractable analyses for bacterial microscopists.

MedSegBench: A comprehensive benchmark for medical image segmentation in diverse data modalities

MedSegBench is a comprehensive benchmark designed to evaluate deep learning models for medical image segmentation across a wide range of modalities. It covers a wide range of modalities, including 35 datasets with over 60,000 images from ultrasound, MRI, and X-ray. The benchmark addresses challenges in medical imaging by providing standardized datasets with train/validation/test splits, considering variability in image quality and dataset imbalances. The benchmark supports binary and multi-class segmentation tasks with up to 19 classes and uses the U-Net architecture with various encoder/decoder networks such as ResNets, EfficientNet, and DenseNet for evaluations. MedSegBench is a valuable resource for developing robust and flexible segmentation algorithms and allows for fair comparisons across different models, promoting the development of universal models for medical tasks. It is the most comprehensive study among medical segmentation datasets. The datasets and source code are publicly available, encouraging further research and development in medical image analysis.

Quantitative microbiology with widefield microscopy: navigating optical artefacts for accurate interpretations

Time-resolved live-cell imaging using widefield microscopy is instrumental in quantitative microbiology research. It allows researchers to track and measure the size, shape, and content of individual microbial cells over time. However, the small size of microbial cells poses a significant challenge in interpreting image data, as their dimensions approache that of the microscope's depth of field, and they begin to experience significant diffraction effects. As a result, 2D widefield images of microbial cells contain projected 3D information, blurred by the 3D point spread function. In this study, we employed simulations and targeted experiments to investigate the impact of diffraction and projection on our ability to quantify the size and content of microbial cells from 2D microscopic images. This study points to some new and often unconsidered artefacts resulting from the interplay of projection and diffraction effects, within the context of quantitative microbiology. These artefacts introduce substantial errors and biases in size, fluorescence quantification, and even single-molecule counting, making the elimination of these errors a complex task. Awareness of these artefacts is crucial for designing strategies to accurately interpret micrographs of microbes. To address this, we present new experimental designs and machine learning-based analysis methods that account for these effects, resulting in accurate quantification of microbiological processes.

A comparison of super-resolution microscopy techniques for imaging tightly packed microcolonies of an obligate intracellular bacterium

Conventional optical microscopy imaging of obligate intracellular bacteria is hampered by the small size of bacterial cells, tight clustering exhibited by some bacterial species and challenges relating to labelling such as background from host cells, a lack of validated reagents, and a lack of tools for genetic manipulation. In this study we imaged intracellular bacteria from the species Orientia tsutsugamushi (Ot) using five different fluorescence microscopy techniques: standard confocal, Airyscan confocal, instant Structured Illumination Microscopy (iSIM), three-dimensional Structured Illumination Microscopy (3D-SIM) and Stimulated Emission Depletion Microscopy (STED). We compared the ability of each to resolve bacterial cells in intracellular clumps in the lateral (xy) axis, using full width half maximum (FWHM) measurements of a labelled outer membrane protein (ScaA) and the ability to detect small, outer membrane vesicles external to the cells. We next compared the ability of each technique to sufficiently resolve bacteria in the axial (z) direction and found 3D-STED to be the most successful method for this. We then combined this approach with a custom 3D cell segmentation and analysis pipeline using the open-source, deep learning software, Cellpose to segment the cells and subsequently the commercial software Imaris to analyze their 3D shape and size. Using this combination, we demonstrated differences in bacterial shape, but not their size, when grown in different mammalian cell lines. Overall, we compare the advantages and disadvantages of different super-resolution microscopy techniques for imaging this cytoplasmic obligate intracellular bacterium based on the specific research question being addressed.

Quantifying Membrane Alterations with Tailored Fluorescent Dyes: A Rapid Antibiotic Resistance Profiling Methodology

Accurate detection of bacterial antibiotic sensitivity is crucial for theranostics and the containment of antibiotic-resistant infections. However, the intricate task of detecting and quantifying the antibiotic-induced changes in the bacterial cytoplasmic membrane, and their correlation with other metabolic pathways leading to antibiotic resistance, poses significant challenges. Using a novel class of 4-aminophthalimide (4AP)-based fluorescent dyes with precisely tailored alkyl chains, namely 4AP-C9 and 4AP-C13, we quantify stress-mediated alterations in E. coli membranes. Leveraging the unique depth-dependent positioning and environment-sensitive fluorescence properties of these dyes, we detect antibiotic-induced membrane damage through single-cell imaging and monitoring the fluorescence peak maxima difference ratio (PMDR) of the dyes within the bacterial membrane, complemented by other methods. The correlation between the ROS-induced cytoplasmic membrane damage and the PMDR of dyes quantifies sensitivity against bactericidal antibiotics, which correlates to antibiotic-induced lipid peroxidation. Significantly, our findings largely extend to clinical isolates of E. coli and other ESKAPE pathogens like K. pneumoniae and Enterobacter subspecies. Our data reveal that 4AP-Cn probes can potentially act as precise scales to detect antibiotic-induced membrane damage ("thinning") occurring at a subnanometer scale through the quantification of dyes' PMDR, making them promising membrane dyes for rapid detection of bacterial antibiotic resistance, distinguishing sensitive and resistant infections with high specificity in a clinical setup.

Bacterial image analysis using multi-task deep learning approaches for clinical microscopy

Background

Bacterial image analysis plays a vital role in various fields, providing valuable information and insights for studying bacterial structural biology, diagnosing and treating infectious diseases caused by pathogenic bacteria, discovering and developing drugs that can combat bacterial infections, etc. As a result, it has prompted efforts to automate bacterial image analysis tasks. By automating analysis tasks and leveraging more advanced computational techniques, such as deep learning (DL) algorithms, bacterial image analysis can contribute to rapid, more accurate, efficient, reliable, and standardised analysis, leading to enhanced understanding, diagnosis, and control of bacterial-related phenomena.

Methods

Three object detection networks of DL algorithms, namely SSD-MobileNetV2, EfficientDet, and YOLOv4, were developed to automatically detect Escherichia coli (E. coli) bacteria from microscopic images. The multi-task DL framework is developed to classify the bacteria according to their respective growth stages, which include rod-shaped cells, dividing cells, and microcolonies. Data preprocessing steps were carried out before training the object detection models, including image augmentation, image annotation, and data splitting. The performance of the DL techniques is evaluated using the quantitative assessment method based on mean average precision (mAP), precision, recall, and F1-score. The performance metrics of the models were compared and analysed. The best DL model was then selected to perform multi-task object detections in identifying rod-shaped cells, dividing cells, and microcolonies.

Results

The output of the test images generated from the three proposed DL models displayed high detection accuracy, with YOLOv4 achieving the highest confidence score range of detection and being able to create different coloured bounding boxes for different growth stages of E. coli bacteria. In terms of statistical analysis, among the three proposed models, YOLOv4 demonstrates superior performance, achieving the highest mAP of 98% with the highest precision, recall, and F1-score of 86%, 97%, and 91%, respectively.

Conclusions

This study has demonstrated the effectiveness, potential, and applicability of DL approaches in multi-task bacterial image analysis, focusing on automating the detection and classification of bacteria from microscopic images. The proposed models can output images with bounding boxes surrounding each detected E. coli bacteria, labelled with their growth stage and confidence level of detection. All proposed object detection models have achieved promising results, with YOLOv4 outperforming the other models.

Pretraining a foundation model for generalizable fluorescence microscopy-based image restoration

Fluorescence microscopy-based image restoration has received widespread attention in the life sciences and has led to significant progress, benefiting from deep learning technology. However, most current task-specific methods have limited generalizability to different fluorescence microscopy-based image restoration problems. Here, we seek to improve generalizability and explore the potential of applying a pretrained foundation model to fluorescence microscopy-based image restoration. We provide a universal fluorescence microscopy-based image restoration (UniFMIR) model to address different restoration problems, and show that UniFMIR offers higher image restoration precision, better generalization and increased versatility. Demonstrations on five tasks and 14 datasets covering a wide range of microscopy imaging modalities and biological samples demonstrate that the pretrained UniFMIR can effectively transfer knowledge to a specific situation via fine-tuning, uncover clear nanoscale biomolecular structures and facilitate high-quality imaging. This work has the potential to inspire and trigger new research highlights for fluorescence microscopy-based image restoration.

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.

Protocol to train a support vector machine for the automatic curation of bacterial cell detections in microscopy images

Manual curation of bacterial cell detections in microscopy images remains a time-consuming and laborious task. This work offers a comprehensive, step-by-step tutorial on training a support vector machine to autonomously distinguish between good and bad cell detections. Jupyter notebooks are included to perform feature extraction, labeling, and training of the machine learning model. This method can readily be incorporated into profiling pipelines aimed at extracting a multitude of features across large collections of individual cells, strains, and species. For complete details on the use and execution of this protocol, please refer to Govers et al.1.

Toward the novel AI tasks in infection biology

Machine learning and artificial intelligence (AI) are becoming more common in infection biology laboratories around the world. Yet, as they gain traction in research, novel frontiers arise. Novel artificial intelligence algorithms are capable of addressing advanced tasks like image generation and question answering. However, similar algorithms can prove useful in addressing advanced questions in infection biology like prediction of host-pathogen interactions or inferring virus protein conformations. Addressing such tasks requires large annotated data sets, which are often scarce in biomedical research. In this review, I bring together several successful examples where such tasks were addressed. I underline the importance of formulating novel AI tasks in infection biology accompanied by freely available benchmark data sets to address these tasks. Furthermore, I discuss the current state of the field and potential future trends. I argue that one such trend involves AI tools becoming more versatile.

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.

Harnessing artificial intelligence to reduce phototoxicity in live imaging

Fluorescence microscopy is essential for studying living cells, tissues and organisms. However, the fluorescent light that switches on fluorescent molecules also harms the samples, jeopardizing the validity of results - particularly in techniques such as super-resolution microscopy, which demands extended illumination. Artificial intelligence (AI)-enabled software capable of denoising, image restoration, temporal interpolation or cross-modal style transfer has great potential to rescue live imaging data and limit photodamage. Yet we believe the focus should be on maintaining light-induced damage at levels that preserve natural cell behaviour. In this Opinion piece, we argue that a shift in role for AIs is needed - AI should be used to extract rich insights from gentle imaging rather than recover compromised data from harsh illumination. Although AI can enhance imaging, our ultimate goal should be to uncover biological truths, not just retrieve data. It is essential to prioritize minimizing photodamage over merely pushing technical limits. Our approach is aimed towards gentle acquisition and observation of undisturbed living systems, aligning with the essence of live-cell fluorescence microscopy.

Assembling membraneless organelles from de novo designed proteins

Recent advances in de novo protein design have delivered a diversity of discrete de novo protein structures and complexes. A new challenge for the field is to use these designs directly in cells to intervene in biological processes and augment natural systems. The bottom-up design of self-assembled objects such as microcompartments and membraneless organelles is one such challenge. Here we describe the design of genetically encoded polypeptides that form membraneless organelles in Escherichia coli. To do this, we combine de novo α-helical sequences, intrinsically disordered linkers and client proteins in single-polypeptide constructs. We tailor the properties of the helical regions to shift protein assembly from arrested assemblies to dynamic condensates. The designs are characterized in cells and in vitro using biophysical methods and soft-matter physics. Finally, we use the designed polypeptide to co-compartmentalize a functional enzyme pair in E. coli, improving product formation close to the theoretical limit.

Live-cell imaging in the deep learning era

Live imaging is a powerful tool, enabling scientists to observe living organisms in real time. In particular, when combined with fluorescence microscopy, live imaging allows the monitoring of cellular components with high sensitivity and specificity. Yet, due to critical challenges (i.e., drift, phototoxicity, dataset size), implementing live imaging and analyzing the resulting datasets is rarely straightforward. Over the past years, the development of bioimage analysis tools, including deep learning, is changing how we perform live imaging. Here we briefly cover important computational methods aiding live imaging and carrying out key tasks such as drift correction, denoising, super-resolution imaging, artificial labeling, tracking, and time series analysis. We also cover recent advances in self-driving microscopy.

Deep learning and single-cell phenotyping for rapid antimicrobial susceptibility detection in Escherichia coli

The rise of antimicrobial resistance (AMR) is one of the greatest public health challenges, already causing up to 1.2 million deaths annually and rising. Current culture-based turnaround times for bacterial identification in clinical samples and antimicrobial susceptibility testing (AST) are typically 18-24 h. We present a novel proof-of-concept methodological advance in susceptibility testing based on the deep-learning of single-cell specific morphological phenotypes directly associated with antimicrobial susceptibility in Escherichia coli. Our models can reliably (80% single-cell accuracy) classify untreated and treated susceptible cells for a lab-reference fully susceptible E. coli strain, across four antibiotics (ciprofloxacin, gentamicin, rifampicin and co-amoxiclav). For ciprofloxacin, we demonstrate our models reveal significant (p < 0.001) differences between bacterial cell populations affected and unaffected by antibiotic treatment, and show that given treatment with a fixed concentration of 10 mg/L over 30 min these phenotypic effects correlate with clinical susceptibility defined by established clinical breakpoints. Deploying our approach on cell populations from six E. coli strains obtained from human bloodstream infections with varying degrees of ciprofloxacin resistance and treated with a range of ciprofloxacin concentrations, we show single-cell phenotyping has the potential to provide equivalent information to growth-based AST assays, but in as little as 30 min.

Addressing annotation and data scarcity when designing machine learning strategies for neurophotonics

Machine learning has revolutionized the way data are processed, allowing information to be extracted in a fraction of the time it would take an expert. In the field of neurophotonics, machine learning approaches are used to automatically detect and classify features of interest in complex images. One of the key challenges in applying machine learning methods to the field of neurophotonics is the scarcity of available data and the complexity associated with labeling them, which can limit the performance of data-driven algorithms. We present an overview of various strategies, such as weakly supervised learning, active learning, and domain adaptation that can be used to address the problem of labeled data scarcity in neurophotonics. We provide a comprehensive overview of the strengths and limitations of each approach and discuss their potential applications to bioimaging datasets. In addition, we highlight how different strategies can be combined to increase model performance on those datasets. The approaches we describe can help to improve the accessibility of machine learning-based analysis with limited number of annotated images for training and can enable researchers to extract more meaningful insights from small datasets.

Sensing of Antibiotic-Bacteria Interactions

Sensing of antibiotic-bacteria interactions is an important area of research that has gained significant attention in recent years. Antibiotic resistance is a major public health concern, and it is essential to develop new strategies for detecting and monitoring bacterial responses to antibiotics in order to maintain effective antibiotic development and antibacterial treatment. This review summarizes recent advances in sensing strategies for antibiotic-bacteria interactions, which are divided into two main parts: studies on the mechanism of action for sensitive bacteria and interrogation of the defense mechanisms for resistant ones. In conclusion, this review provides an overview of the present research landscape concerning antibiotic-bacteria interactions, emphasizing the potential for method adaptation and the integration of machine learning techniques in data analysis, which could potentially lead to a transformative impact on mechanistic studies within the field.

Resolution enhancement with a task-assisted GAN to guide optical nanoscopy image analysis and acquisition

Super-resolution fluorescence microscopy methods enable the characterization of nanostructures in living and fixed biological tissues. However, they require the adjustment of multiple imaging parameters while attempting to satisfy conflicting objectives, such as maximizing spatial and temporal resolution while minimizing light exposure. To overcome the limitations imposed by these trade-offs, post-acquisition algorithmic approaches have been proposed for resolution enhancement and image-quality improvement. Here we introduce the task-assisted generative adversarial network (TA-GAN), which incorporates an auxiliary task (for example, segmentation, localization) closely related to the observed biological nanostructure characterization. We evaluate how the TA-GAN improves generative accuracy over unassisted methods, using images acquired with different modalities such as confocal, bright-field, stimulated emission depletion and structured illumination microscopy. The TA-GAN is incorporated directly into the acquisition pipeline of the microscope to predict the nanometric content of the field of view without requiring the acquisition of a super-resolved image. This information is used to automatically select the imaging modality and regions of interest, optimizing the acquisition sequence by reducing light exposure. Data-driven microscopy methods like the TA-GAN will enable the observation of dynamic molecular processes with spatial and temporal resolutions that surpass the limits currently imposed by the trade-offs constraining super-resolution microscopy.

The Quantification of Bacterial Cell Size: Discrepancies Arise from Varied Quantification Methods

The robust regulation of the cell cycle is critical for the survival and proliferation of bacteria. To gain a comprehensive understanding of the mechanisms regulating the bacterial cell cycle, it is essential to accurately quantify cell-cycle-related parameters and to uncover quantitative relationships. In this paper, we demonstrate that the quantification of cell size parameters using microscopic images can be influenced by software and by the parameter settings used. Remarkably, even if the consistent use of a particular software and specific parameter settings is maintained throughout a study, the type of software and the parameter settings can significantly impact the validation of quantitative relationships, such as the constant-initiation-mass hypothesis. Given these inherent characteristics of microscopic image-based quantification methods, it is recommended that conclusions be cross-validated using independent methods, especially when the conclusions are associated with cell size parameters that were obtained under different conditions. To this end, we presented a flexible workflow for simultaneously quantifying multiple bacterial cell-cycle-related parameters using microscope-independent methods.

Growth rate is modulated by monitoring cell wall precursors in Bacillus subtilis

How bacteria link their growth rate to external nutrient conditions is unknown. To investigate how Bacillus subtilis cells alter the rate at which they expand their cell walls as they grow, we compared single-cell growth rates of cells grown under agar pads with the density of moving MreB filaments under a variety of growth conditions. MreB filament density increases proportionally with growth rate. We show that both MreB filament density and growth rate depend on the abundance of Lipid II and murAA, the first gene in the biosynthetic pathway creating the cell wall precursor Lipid II. Lipid II is sensed by the serine/threonine kinase PrkC, which phosphorylates RodZ and other proteins. We show that phosphorylated RodZ increases MreB filament density, which in turn increases cell growth rate. We also show that increasing the activity of this pathway in nutrient-poor media results in cells that elongate faster than wild-type cells, which means that B. subtilis contains spare 'growth capacity'. We conclude that PrkC functions as a cellular rheostat, enabling fine-tuning of cell growth rates in response to Lipid II in different nutrient conditions.

A mechanism of salt bridge-mediated resistance to FtsZ inhibitor PC190723 revealed by a cell-based screen

Bacterial cell division proteins, especially the tubulin homologue FtsZ, have emerged as strong targets for developing new antibiotics. Here, we have utilized the fission yeast heterologous expression system to develop a cell-based assay to screen for small molecules that directly and specifically target the bacterial cell division protein FtsZ. The strategy also allows for simultaneous assessment of the toxicity of the drugs to eukaryotic yeast cells. As a proof-of-concept of the utility of this assay, we demonstrate the effect of the inhibitors sanguinarine, berberine, and PC190723 on FtsZ. Though sanguinarine and berberine affect FtsZ polymerization, they exert a toxic effect on the cells. Further, using this assay system, we show that PC190723 affects Helicobacter pylori FtsZ function and gain new insights into the molecular determinants of resistance to PC190723. On the basis of sequence and structural analysis and site-specific mutations, we demonstrate that the presence of salt bridge interactions between the central H7 helix and β-strands S9 and S10 mediates resistance to PC190723 in FtsZ. The single-step in vivo cell-based assay using fission yeast enabled us to dissect the contribution of sequence-specific features of FtsZ and cell permeability effects associated with bacterial cell envelopes. Thus, our assay serves as a potent tool to rapidly identify novel compounds targeting polymeric bacterial cytoskeletal proteins like FtsZ to understand how they alter polymerization dynamics and address resistance determinants in targets.

Opportunities and challenges of machine learning in bioprocesses: Categorization from different perspectives and future direction

Recent advances in machine learning (ML) have revolutionized an extensive range of research and industry fields by successfully addressing intricate problems that cannot be resolved with conventional approaches. However, low interpretability and incompatibility make it challenging to apply ML to complicated bioprocesses, which rely on the delicate metabolic interplay among living cells. This overview attempts to delineate ML applications to bioprocess from different perspectives, and their inherent limitations (i.e., uncertainties in prediction) were then discussed with unique attempts to supplement the ML models. A clear classification can be made depending on the purpose of the ML (supervised vs unsupervised) per application, as well as on their system boundaries (engineered vs natural). Although a limited number of hybrid approaches with meaningful outcomes (e.g., improved accuracy) are available, there is still a need to further enhance the interpretability, compatibility, and user-friendliness of ML models.