A convolutional neural network segments yeast microscopy images with high accuracy

Phenotypic heterogeneity follows a growth-viability tradeoff in response to amino acid identity

In their natural environments, microorganisms mainly operate at suboptimal growth conditions with fluctuations in nutrient abundance. The resulting cellular adaptation is subject to conflicting tasks: growth or survival maximisation. Here, we study this adaptation by systematically measuring the impact of a nitrogen downshift to 24 nitrogen sources on cellular metabolism at the single-cell level. Saccharomyces lineages grown in rich media and exposed to a nitrogen downshift gradually differentiate to form two subpopulations of different cell sizes where one favours growth while the other favours viability with an extended chronological lifespan. This differentiation is asymmetrical with daughter cells representing the new differentiated state with increased viability. We characterise the metabolic response of the subpopulations using RNA sequencing, metabolic biosensors and a transcription factor-tagged GFP library coupled to high-throughput microscopy, imaging more than 800,000 cells. We find that the subpopulation with increased viability is associated with a dormant quiescent state displaying differences in MAPK signalling. Depending on the identity of the nitrogen source present, differentiation into the quiescent state can be actively maintained, attenuated, or aborted. These results establish amino acids as important signalling molecules for the formation of genetically identical subpopulations, involved in chronological lifespan and growth rate determination.

Artificial intelligence for high content imaging in drug discovery

Artificial intelligence (AI) and high-content imaging (HCI) are contributing to advancements in drug discovery, propelled by the recent progress in deep neural networks. This review highlights AI's role in analysis of HCI data from fixed and live-cell imaging, enabling novel label-free and multi-channel fluorescent screening methods, and improving compound profiling. HCI experiments are rapid and cost-effective, facilitating large data set accumulation for AI model training. However, the success of AI in drug discovery also depends on high-quality data, reproducible experiments, and robust validation to ensure model performance. Despite challenges like the need for annotated compounds and managing vast image data, AI's potential in phenotypic screening and drug profiling is significant. Future improvements in AI, including increased interpretability and integration of multiple modalities, are expected to solidify AI and HCI's role in drug discovery.

Genome dilution by cell growth drives starvation-like proteome remodeling in mammalian and yeast cells

Cell size is tightly controlled in healthy tissues and single-celled organisms, but it remains unclear how cell size influences physiology. Increasing cell size was recently shown to remodel the proteomes of cultured human cells, demonstrating that large and small cells of the same type can be compositionally different. In the present study, we utilize the natural heterogeneity of hepatocyte ploidy and yeast genetics to establish that the ploidy-to-cell size ratio is a highly conserved determinant of proteome composition. In both mammalian and yeast cells, genome dilution by cell growth elicits a starvation-like phenotype, suggesting that growth in large cells is restricted by genome concentration in a manner that mimics a limiting nutrient. Moreover, genome dilution explains some proteomic changes ascribed to yeast aging. Overall, our data indicate that genome concentration drives changes in cell composition independently of external environmental cues.

Automated, image-based quantification of peroxisome characteristics with perox-per-cell

SUMMARY

perox-per-cell automates cumbersome, image-based data collection tasks often encountered in peroxisome research. The software processes microscopy images to quantify peroxisome features in yeast cells. It uses off-the-shelf image processing tools to automatically segment cells and peroxisomes and then outputs quantitative metrics including peroxisome counts per cell and spatial areas. In validation tests, we found that perox-per-cell output agrees well with manually quantified peroxisomal counts and cell instances, thereby enabling high-throughput quantification of peroxisomal characteristics.

AVAILABILITY AND IMPLEMENTATION

The software is coded in Python. Compiled executables and source code are available at https://github.com/AitchisonLab/perox-per-cell.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

High-throughput classification of S. cerevisiae tetrads using deep learning

Meiotic crossovers play a vital role in proper chromosome segregation and evolution of most sexually reproducing organisms. Meiotic recombination can be visually observed in Saccharomyces cerevisiae tetrads using linked spore-autonomous fluorescent markers placed at defined intervals within the genome, which allows for analysis of meiotic segregation without the need for tetrad dissection. To automate the analysis, we developed a deep learning-based image recognition and classification pipeline for high-throughput tetrad detection and meiotic crossover classification. As a proof of concept, we analyzed a large image data set from wild-type and selected gene knock-out mutants to quantify crossover frequency, interference, chromosome missegregation, and gene conversion events. The deep learning-based method has the potential to accelerate the discovery of new genes involved in meiotic recombination in S. cerevisiae such as the underlying factors controlling crossover frequency and interference.

How scanning probe microscopy can be supported by artificial intelligence and quantum computing?

The impact of Artificial Intelligence (AI) is rapidly expanding, revolutionizing both science and society. It is applied to practically all areas of life, science, and technology, including materials science, which continuously requires novel tools for effective materials characterization. One of the widely used techniques is scanning probe microscopy (SPM). SPM has fundamentally changed materials engineering, biology, and chemistry by providing tools for atomic-precision surface mapping. Despite its many advantages, it also has some drawbacks, such as long scanning times or the possibility of damaging soft-surface materials. In this paper, we focus on the potential for supporting SPM-based measurements, with an emphasis on the application of AI-based algorithms, especially Machine Learning-based algorithms, as well as quantum computing (QC). It has been found that AI can be helpful in automating experimental processes in routine operations, algorithmically searching for optimal sample regions, and elucidating structure-property relationships. Thus, it contributes to increasing the efficiency and accuracy of optical nanoscopy scanning probes. Moreover, the combination of AI-based algorithms and QC may have enormous potential to enhance the practical application of SPM. The limitations of the AI-QC-based approach were also discussed. Finally, we outline a research path for improving AI-QC-powered SPM. RESEARCH HIGHLIGHTS: Artificial intelligence and quantum computing as support for scanning probe microscopy. The analysis indicates a research gap in the field of scanning probe microscopy. The research aims to shed light into ai-qc-powered scanning probe microscopy.

Whi5 hypo- and hyper-phosphorylation dynamics control cell-cycle entry and progression

Progression through the cell cycle depends on the phosphorylation of key substrates by cyclin-dependent kinases. In budding yeast, these substrates include the transcriptional inhibitor Whi5 that regulates G1/S transition. In early G1 phase, Whi5 is hypo-phosphorylated and inhibits the Swi4/Swi6 (SBF) complex that promotes transcription of the cyclins CLN1 and CLN2. In late G1, Whi5 is rapidly hyper-phosphorylated by Cln1 and Cln2 in complex with the cyclin-dependent kinase Cdk1. This hyper-phosphorylation inactivates Whi5 and excludes it from the nucleus. Here, we set out to determine the molecular mechanisms responsible for Whi5's multi-site phosphorylation and how they regulate the cell cycle. To do this, we first identified the 19 Whi5 sites that are appreciably phosphorylated and then determined which of these sites are responsible for G1 hypo-phosphorylation. Mutation of 7 sites removed G1 hypo-phosphorylation, increased cell size, and delayed the G1/S transition. Moreover, the rapidity of Whi5 hyper-phosphorylation in late G1 depends on "priming" sites that dock the Cks1 subunit of Cln1,2-Cdk1 complexes. Hyper-phosphorylation is crucial for Whi5 nuclear export, normal cell size, full expression of SBF target genes, and timely progression through both the G1/S transition and S/G2/M phases. Thus, our work shows how Whi5 phosphorylation regulates the G1/S transition and how it is required for timely progression through S/G2/M phases and not only G1 as previously thought.

The multimodality cell segmentation challenge: toward universal solutions

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimental settings. Here, we present a multimodality cell segmentation benchmark, comprising more than 1,500 labeled images derived from more than 50 diverse biological experiments. The top participants developed a Transformer-based deep-learning algorithm that not only exceeds existing methods but can also be applied to diverse microscopy images across imaging platforms and tissue types without manual parameter adjustments. This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging.

Deep learning-driven imaging of cell division and cell growth across an entire eukaryotic life cycle

The life cycle of biomedical and agriculturally relevant eukaryotic microorganisms involves complex transitions between proliferative and non-proliferative states such as dormancy, mating, meiosis, and cell division. New drugs, pesticides, and vaccines can be created by targeting specific life cycle stages of parasites and pathogens. However, defining the structure of a microbial life cycle often relies on partial observations that are theoretically assembled in an ideal life cycle path. To create a more quantitative approach to studying complete eukaryotic life cycles, we generated a deep learning-driven imaging framework to track microorganisms across sexually reproducing generations. Our approach combines microfluidic culturing, life cycle stage-specific segmentation of microscopy images using convolutional neural networks, and a novel cell tracking algorithm, FIEST, based on enhancing the overlap of single cell masks in consecutive images through deep learning video frame interpolation. As proof of principle, we used this approach to quantitatively image and compare cell growth and cell cycle regulation across the sexual life cycle of Saccharomyces cerevisiae . We developed a fluorescent reporter system based on a fluorescently labeled Whi5 protein, the yeast analog of mammalian Rb, and a new High-Cdk1 activity sensor, LiCHI, designed to report during DNA replication, mitosis, meiotic homologous recombination, meiosis I, and meiosis II. We found that cell growth preceded the exit from non-proliferative states such as mitotic G1, pre-meiotic G1, and the G0 spore state during germination. A decrease in the total cell concentration of Whi5 characterized the exit from non-proliferative states, which is consistent with a Whi5 dilution model. The nuclear accumulation of Whi5 was developmentally regulated, being at its highest during meiotic exit and spore formation. The temporal coordination of cell division and growth was not significantly different across three sexually reproducing generations. Our framework could be used to quantitatively characterize other single-cell eukaryotic life cycles that remain incompletely described. An off-the-shelf user interface Yeastvision provides free access to our image processing and single-cell tracking algorithms.

Automated, image-based quantification of peroxisome characteristics with perox-per-cell

perox-per-cell automates cumbersome, image-based data collection tasks often encountered in peroxisome research. The software processes microscopy images to quantify peroxisome features in yeast cells. It uses off-the-shelf image processing tools to automatically segment cells and peroxisomes and then outputs quantitative metrics including peroxisome counts per cell and spatial areas. In validation tests, we found that perox-per-cell output agrees well with manually-quantified peroxisomal counts and cell instances, thereby enabling high-throughput quantification of peroxisomal characteristics. The software is available at https://github.com/AitchisonLab/perox-per-cell.

Intelligent classification and pollution characteristics analysis of microplastics in urban surface waters using YNet

Microplastics (MPs, ≤ 5 mm in size) are hazardous contaminants that pose threats to ecosystems and human health. YNet was developed to analyze MPs abundance and shape to gain insights into MPs pollution characteristics in urban surface waters. The study found that YNet achieved an accurate identification and intelligent classification performance, with a dice similarity coefficient (DSC) of 90.78%, precision of 94.17%, and recall of 89.14%. Analysis of initial MPs levels in wetlands and reservoirs revealed 127.3 items/L and 56.0 items/L. Additionally, the MPs in effluents were 27.0 items/L and 26.3 items/L, indicating the ability of wetlands and reservoirs to retain MPs. The concentration of MPs in the lower reaches of the river was higher (45.6 items/L) compared to the upper reaches (22.0 items/L). The majority of MPs detected in this study were fragments, accounting for 51.63%, 54.94%, and 74.74% in the river, wetland, and reservoir. Conversely, granules accounted for the smallest proportion of MPs in the river, wetland, and reservoir, representing only 11.43%, 10.38%, and 6.5%. The study proves that the trained YNet accurately identify and intelligently classify MPs. This tool is essential in comprehending the distribution of MPs in urban surface waters and researching their sources and fate.

Automated quantification of vacuole fusion and lipophagy in Saccharomyces cerevisiae from fluorescence and cryo-soft X-ray microscopy data using deep learning

During starvation in the yeast Saccharomyces cerevisiae vacuolar vesicles fuse and lipid droplets (LDs) can become internalized into the vacuole in an autophagic process named lipophagy. There is a lack of tools to quantitatively assess starvation-induced vacuole fusion and lipophagy in intact cells with high resolution and throughput. Here, we combine soft X-ray tomography (SXT) with fluorescence microscopy and use a deep-learning computational approach to visualize and quantify these processes in yeast. We focus on yeast homologs of mammalian NPC1 (NPC intracellular cholesterol transporter 1; Ncr1 in yeast) and NPC2 proteins, whose dysfunction leads to Niemann Pick type C (NPC) disease in humans. We developed a convolutional neural network (CNN) model which classifies fully fused versus partially fused vacuoles based on fluorescence images of stained cells. This CNN, named Deep Yeast Fusion Network (DYFNet), revealed that cells lacking Ncr1 (ncr1∆ cells) or Npc2 (npc2∆ cells) have a reduced capacity for vacuole fusion. Using a second CNN model, we implemented a pipeline named LipoSeg to perform automated instance segmentation of LDs and vacuoles from high-resolution reconstructions of X-ray tomograms. From that, we obtained 3D renderings of LDs inside and outside of the vacuole in a fully automated manner and additionally measured droplet volume, number, and distribution. We find that ncr1∆ and npc2∆ cells could ingest LDs into vacuoles normally but showed compromised degradation of LDs and accumulation of lipid vesicles inside vacuoles. Our new method is versatile and allows for analysis of vacuole fusion, droplet size and lipophagy in intact cells.Abbreviations: BODIPY493/503: 4,4-difluoro-1,3,5,7,8-pentamethyl-4-bora-3a,4a-diaza-s-Indacene; BPS: bathophenanthrolinedisulfonic acid disodium salt hydrate; CNN: convolutional neural network; DHE; dehydroergosterol; npc2∆, yeast deficient in Npc2; DSC, Dice similarity coefficient; EM, electron microscopy; EVs, extracellular vesicles; FIB-SEM, focused ion beam milling-scanning electron microscopy; FM 4-64, N-(3-triethylammoniumpropyl)-4-(6-[4-{diethylamino} phenyl] hexatrienyl)-pyridinium dibromide; LDs, lipid droplets; Ncr1, yeast homolog of human NPC1 protein; ncr1∆, yeast deficient in Ncr1; NPC, Niemann Pick type C; NPC2, Niemann Pick type C homolog; OD600, optical density at 600 nm; ReLU, rectifier linear unit; PPV, positive predictive value; NPV, negative predictive value; MCC, Matthews correlation coefficient; SXT, soft X-ray tomography; UV, ultraviolet; YPD, yeast extract peptone dextrose.

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.

Quantifying microbial robustness in dynamic environments using microfluidic single-cell cultivation

BACKGROUND

Microorganisms must respond to changes in their environment. Analysing the robustness of functions (i.e. performance stability) to such dynamic perturbations is of great interest in both laboratory and industrial settings. Recently, a quantification method capable of assessing the robustness of various functions, such as specific growth rate or product yield, across different conditions, time frames, and populations has been developed for microorganisms grown in a 96-well plate. In micro-titer-plates, environmental change is slow and undefined. Dynamic microfluidic single-cell cultivation (dMSCC) enables the precise maintenance and manipulation of microenvironments, while tracking single cells over time using live-cell imaging. Here, we combined dMSCC and a robustness quantification method to a pipeline for assessing performance stability to changes occurring within seconds or minutes.

RESULTS

Saccharomyces cerevisiae CEN.PK113-7D, harbouring a biosensor for intracellular ATP levels, was exposed to glucose feast-starvation cycles, with each condition lasting from 1.5 to 48 min over a 20 h period. A semi-automated image and data analysis pipeline was developed and applied to assess the performance and robustness of various functions at population, subpopulation, and single-cell resolution. We observed a decrease in specific growth rate but an increase in intracellular ATP levels with longer oscillation intervals. Cells subjected to 48 min oscillations exhibited the highest average ATP content, but the lowest stability over time and the highest heterogeneity within the population.

CONCLUSION

The proposed pipeline enabled the investigation of function stability in dynamic environments, both over time and within populations. The strategy allows for parallelisation and automation, and is easily adaptable to new organisms, biosensors, cultivation conditions, and oscillation frequencies. Insights on the microbial response to changing environments will guide strain development and bioprocess optimisation.

Automated quantification of lipid contents of Lipomyces starkeyi using deep-learning-based image segmentation

Intracellular lipid droplets (LDs), subcellular organelles playing a role in long-term carbon storage, have immense potential in biofuel and dietary lipid production. Monitoring the state of LDs in living cells is of utmost importance for quick biomass harvest and screening promising isolates. Here, a deep-learning-based segmentation model was developed for automatic detection and segmentation of LDs using the model yeast species Lipomyces starkeyi, leading to fast and accurate quantification of lipid contents in liquid cultures. The trained model detected the yeast's cell and LDs in light microscopic images with an accuracy of 98% and 92%, respectively. Lipid content prediction using pixel numbers counted in segmented LDs showed high similarity to lipid quantification results obtained with gas chromatography-mass spectrometry. This automated quantification can highly reduce cost and time in real-time monitoring of lipid production, thereby providing an efficient tool in bio-fermentation.

A computer vision and residual neural network (ResNet) combined method for automated and accurate yeast replicative aging analysis of high-throughput microfluidic single-cell images

With the rapid development of microfluidic platforms in high-throughput single-cell culturing, laborious operation to manipulate massive budding yeast cells (Saccharomyces cerevisiae) in replicative aging studies has been greatly simplified and automated. As a result, large datasets of microscopy images bring challenges to fast and accurately determine yeast replicative lifespan (RLS), which is the most important parameter to study cell aging. Based on our microfluidic diploid yeast long-term culturing (DYLC) chip that features 1100 traps to immobilize single cells and record their proliferation and aging via time-lapse imaging, herein, a dedicated algorithm combined with computer vision and residual neural network (ResNet) was presented to efficiently process tremendous micrographs in a high-throughput and automated manner. The image-processing algorithm includes following pivotal steps: (i) segmenting multi-trap micrographs into time-lapse single-trap sub-images, (ii) labeling 8 yeast budding features and training the 18-layer ResNet, (iii) converting the ResNet predictions in analog values into digital signals, (iv) recognizing cell dynamic events, and (v) determining yeast RLS and budding time interval (BTI) ultimately. The ResNet algorithm achieved high F1 scores (over 92%) demonstrating the effectiveness and accuracy in the recognition of yeast budding events, such as bud appearance, daughter dissection and cell death. Therefore, the results conduct that similar deep learning algorithms could be tailored to analyze high-throughput microscopy images and extract multiple cell behaviors in microfluidic single-cell analysis.

Construction and Characterization of Light-Responsive Transcriptional Systems

Optogenetic tools provide a means for controlling cellular processes that is rapid, noninvasive, and spatially and temporally precise. With the increase in available optogenetic systems, quantitative comparisons of their performances become important to guide experiments. In this chapter, we first discuss how photoreceptors can be repurposed for light-mediated control of transcription. Then, we provide a detailed protocol for characterizing light-regulated transcriptional systems in budding yeast using fluorescence time-lapse microscopy and mathematical modeling, expanding on our recent publication (Gligorovski et al., Nat Commun 14:3810, 2023).

Automated neuron tracking inside moving and deforming C. elegans using deep learning and targeted augmentation

Reading out neuronal activity from three-dimensional (3D) functional imaging requires segmenting and tracking individual neurons. This is challenging in behaving animals if the brain moves and deforms. The traditional approach is to train a convolutional neural network with ground-truth (GT) annotations of images representing different brain postures. For 3D images, this is very labor intensive. We introduce 'targeted augmentation', a method to automatically synthesize artificial annotations from a few manual annotations. Our method ('Targettrack') learns the internal deformations of the brain to synthesize annotations for new postures by deforming GT annotations. This reduces the need for manual annotation and proofreading. A graphical user interface allows the application of the method end-to-end. We demonstrate Targettrack on recordings where neurons are labeled as key points or 3D volumes. Analyzing freely moving animals exposed to odor pulses, we uncover rich patterns in interneuron dynamics, including switching neuronal entrainment on and off.

Whi5 hypo- and hyper-phosphorylation dynamics control cell cycle entry and progression

Progression through the cell cycle depends on the phosphorylation of key substrates by cyclin-dependent kinases. In budding yeast, these substrates include the transcriptional inhibitor Whi5 that regulates the G1/S transition. In early G1 phase, Whi5 is hypo-phosphorylated and inhibits the SBF complex that promotes transcription of the cyclins CLN1 and CLN2 . In late-G1, Whi5 is rapidly hyper-phosphorylated by Cln1,2 in complex with the cyclin-dependent kinase Cdk1. This hyper-phosphorylation inactivates Whi5 and excludes it from the nucleus. Here, we set out to determine the molecular mechanisms responsible for Whi5's multi-site phosphorylation and how they regulate the cell cycle. To do this, we first identified the 19 Whi5 sites that are appreciably phosphorylated and then determined which of these sites are responsible for G1 hypo-phosphorylation. Mutation of 7 sites removed G1 hypo-phosphorylation, increased cell size, and delayed the G1/S transition. Moreover, the rapidity of Whi5 hyper-phosphorylation in late G1 depends on 'priming' sites that dock the Cks1 subunit of Cln1,2-Cdk1 complexes. Hyper-phosphorylation is crucial for Whi5 nuclear export, normal cell size, full expression of SBF target genes, and timely progression through both the G1/S transition and S/G2/M phases. Thus, our work shows how Whi5 phosphorylation regulates the G1/S transition and how it is required for timely progression through S/G2/M phases and not only G1 as previously thought.

Fitness cost associated with cell phenotypic switching drives population diversification dynamics and controllability

Isogenic cell populations can cope with stress conditions by switching to alternative phenotypes. Even if it can lead to increased fitness in a natural context, this feature is typically unwanted for a range of applications (e.g., bioproduction, synthetic biology, and biomedicine) where it tends to make cellular response unpredictable. However, little is known about the diversification profiles that can be adopted by a cell population. Here, we characterize the diversification dynamics for various systems (bacteria and yeast) and for different phenotypes (utilization of alternative carbon sources, general stress response and more complex development patterns). Our results suggest that the diversification dynamics and the fitness cost associated with cell switching are coupled. To quantify the contribution of the switching cost on population dynamics, we design a stochastic model that let us reproduce the dynamics observed experimentally and identify three diversification regimes, i.e., constrained (at low switching cost), dispersed (at medium and high switching cost), and bursty (for very high switching cost). Furthermore, we use a cell-machine interface called Segregostat to demonstrate that different levels of control can be applied to these diversification regimes, enabling applications involving more precise cellular responses.

Yeast cell detection using fuzzy automatic contrast enhancement (FACE) and you only look once (YOLO)

In contemporary biomedical research, the accurate automatic detection of cells within intricate microscopic imagery stands as a cornerstone for scientific advancement. Leveraging state-of-the-art deep learning techniques, this study introduces a novel amalgamation of Fuzzy Automatic Contrast Enhancement (FACE) and the You Only Look Once (YOLO) framework to address this critical challenge of automatic cell detection. Yeast cells, representing a vital component of the fungi family, hold profound significance in elucidating the intricacies of eukaryotic cells and human biology. The proposed methodology introduces a paradigm shift in cell detection by optimizing image contrast through optimal fuzzy clustering within the FACE approach. This advancement mitigates the shortcomings of conventional contrast enhancement techniques, minimizing artifacts and suboptimal outcomes. Further enhancing contrast, a universal contrast enhancement variable is ingeniously introduced, enriching image clarity with automatic precision. Experimental validation encompasses a diverse range of yeast cell images subjected to rigorous quantitative assessment via Root-Mean-Square Contrast and Root-Mean-Square Deviation (RMSD). Comparative analyses against conventional enhancement methods showcase the superior performance of the FACE-enhanced images. Notably, the integration of the innovative You Only Look Once (YOLOv5) facilitates automatic cell detection within a finely partitioned grid system. This leads to the development of two models-one operating on pristine raw images, the other harnessing the enriched landscape of FACE-enhanced imagery. Strikingly, the FACE enhancement achieves exceptional accuracy in automatic yeast cell detection by YOLOv5 across both raw and enhanced images. Comprehensive performance evaluations encompassing tenfold accuracy assessments and confidence scoring substantiate the robustness of the FACE-YOLO model. Notably, the integration of FACE-enhanced images serves as a catalyst, significantly elevating the performance of YOLOv5 detection. Complementing these efforts, OpenCV lends computational acumen to delineate precise yeast cell contours and coordinates, augmenting the precision of cell detection.

Convolution Neural Network-Assisted Smart Fluorescent-Tongue Based on Lanthanide Ion-Induced Forming MOF/HOF Composite for Differentiation of Flavor Compounds and Wine Identification

Wine flavor is a vital quality characteristic in wine, influenced by those flavor components with low sensory thresholds. It is crucial to recognize and classify the wine components related to their flavor contribution. The integration of fluorescent sensors and artificial intelligence shows huge potential in flavor recognition by emulation of the gustatory perception system. Meanwhile, achieving information identification of wine based on multiple information barcodes has hopeful applications in anticounterfeiting. In this study, we present a simple method in which organic linkers are weaved into a hydrogen-bonded organic framework (HOF) for the available transformation of a metal-bonded organic framework (MOF) induced by lanthanide ions (Ln3+). The fluorescent Ln-MOF/HOF composite exhibits high sensitivity, rapid response, and good recyclability for detecting seven flavor compounds in wine, including tannic acid, ionone, vanillin, anethole, anisaldehyde, hydroxybenzaldehyde, and 4-hydroxy-2-methylacetophenone. Depending on its satisfactory detectability, a novel strategy is provided in which a fluorescent sensor is able to function as a smart fluorescent-tongue (F-tongue) by the aid of convolutional neural network to differentiate these seven flavor compounds. In addition, the Ln-MOF/HOF composite has been used to prepare multiple information barcodes for wine information identification on the basis of dynamic fluorescence response toward tannic acid. The mimetic gustatory perception system developed in this study may offer a promising strategy for flavor recognition in food and further food anticounterfeiting.

pomBseen: An automated pipeline for analysis of fission yeast images

Fission yeast is a model organism widely used for studies of eukaryotic cell biology. As such, it is subject to bright-field and fluorescent microscopy. Manual analysis of such data can be laborious and subjective. Therefore, we have developed pomBseen, an image analysis pipeline for the quantitation of fission yeast micrographs containing a bright-field channel and up to two fluorescent channels. It accepts a wide range of image formats and produces a table with the size and total and nuclear fluorescent intensities of the cells in the image. Benchmarking of the pipeline against manually annotated datasets demonstrates that it reliably segments cells and acquires their image parameters. Written in MATLAB, pomBseen is also available as a standalone application.

Multidimensional characterization of inducible promoters and a highly light-sensitive LOV-transcription factor

The ability to independently control the expression of different genes is important for quantitative biology. Using budding yeast, we characterize GAL1pr, GALL, MET3pr, CUP1pr, PHO5pr, tetOpr, terminator-tetOpr, Z₃EV, blue-light inducible optogenetic systems El222-LIP, El222-GLIP, and red-light inducible PhyB-PIF3. We report kinetic parameters, noise scaling, impact on growth, and the fundamental leakiness of each system using an intuitive unit, maxGAL1. We uncover disadvantages of widely used tools, e.g., nonmonotonic activity of MET3pr and GALL, slow off kinetics of the doxycycline- and estradiol-inducible systems tetOpr and Z₃EV, and high variability of PHO5pr and red-light activated PhyB-PIF3 system. We introduce two previously uncharacterized systems: strongLOV, a more light-sensitive El222 mutant, and ARG3pr, which is induced in the absence of arginine or presence of methionine. To demonstrate fine control over gene circuits, we experimentally tune the time between cell cycle Start and mitosis, artificially simulating near-wild-type timing. All strains, constructs, code, and data ( https://promoter-benchmark.epfl.ch/ ) are made available.

CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation

Nucleus segmentation is a challenging task due to the crowded distribution and blurry boundaries of nuclei. To differentiate between touching and overlapping nuclei, recent approaches have represented nuclei in the form of polygons, and have accordingly achieved promising performance. Each polygon is represented by a set of centroid-to-boundary distances, which are in turn predicted by features of the centroid pixel for a single nucleus. However, the use of the centroid pixel alone does not provide sufficient contextual information for robust prediction and therefore affects the segmentation accuracy. To address this problem, we propose a Context-aware Polygon Proposal Network (CPP-Net) for nucleus segmentation. First, we sample a point set rather than a single pixel within each cell for distance prediction; this strategy substantially enhances the contextual information and thereby improves the prediction robustness. Second, we propose a Confidence-basedWeighting Module, which adaptively fuses the predictions from the sampled point set. Third, we introduce a novel Shape-Aware Perceptual (SAP) loss that constrains the shape of the predicted polygons. This SAP loss is based on an additional network that is pre-trained by means of mapping the centroid probability map and the pixel-to-boundary distance maps to a different nucleus representation. Extensive experiments demonstrate the effectiveness of each component in the proposed CPP-Net. Finally, CPP-Net is found to achieve state-of-the-art performance on three publicly available databases, namely DSB2018, BBBC06, and PanNuke. The code of this paper will be released.

Applications of artificial neural networks in microorganism image analysis: a comprehensive review from conventional multilayer perceptron to popular convolutional neural network and potential visual transformer

Microorganisms are widely distributed in the human daily living environment. They play an essential role in environmental pollution control, disease prevention and treatment, and food and drug production. The analysis of microorganisms is essential for making full use of different microorganisms. The conventional analysis methods are laborious and time-consuming. Therefore, the automatic image analysis based on artificial neural networks is introduced to optimize it. However, the automatic microorganism image analysis faces many challenges, such as the requirement of a robust algorithm caused by various application occasions, insignificant features and easy under-segmentation caused by the image characteristic, and various analysis tasks. Therefore, we conduct this review to comprehensively discuss the characteristics of microorganism image analysis based on artificial neural networks. In this review, the background and motivation are introduced first. Then, the development of artificial neural networks and representative networks are presented. After that, the papers related to microorganism image analysis based on classical and deep neural networks are reviewed from the perspectives of different tasks. In the end, the methodology analysis and potential direction are discussed.

Single-molecule experiments reveal the elbow as an essential folding guide in SMC coiled-coil arms

Structural maintenance of chromosome (SMC) complexes form ring-like structures through exceptional elongated coiled-coils (CCs). Recent studies found that variable CC conformations, including open and collapsed forms, which might result from discontinuities in the CC, facilitate the diverse functions of SMCs in DNA organization. However, a detailed description of the SMC CC architecture is still missing. Here, we study the structural composition and mechanical properties of SMC proteins with optical tweezers unfolding experiments using the isolated Psm3 CC as a model system. We find a comparatively unstable protein with three unzipping intermediates, which we could directly assign to CC features by crosslinking experiments and state-of-the-art prediction software. Particularly, the CC elbow is shown to be a flexible, potentially non-structured feature, which divides the CC into sections, induces a pairing shift from one CC strand to the other and could facilitate large-scale conformational changes, most likely via thermal fluctuations of the flanking CC sections. A replacement of the elbow amino acids hinders folding of the consecutive CC region and frequently leads to non-native misalignments, revealing the elbow as a guide for proper folding. Additional in vivo manipulation of the elbow flexibility resulted in impaired cohesin complexes, which directly link the sensitive CC architecture to the biological function of cohesin.

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.

Comparing the Clinical Viability of Automated Fundus Image Segmentation Methods

Recent methods for automatic blood vessel segmentation from fundus images have been commonly implemented as convolutional neural networks. While these networks report high values for objective metrics, the clinical viability of recovered segmentation masks remains unexplored. In this paper, we perform a pilot study to assess the clinical viability of automatically generated segmentation masks in the diagnosis of diseases affecting retinal vascularization. Five ophthalmologists with clinical experience were asked to participate in the study. The results demonstrate low classification accuracy, inferring that generated segmentation masks cannot be used as a standalone resource in general clinical practice. The results also hint at possible clinical infeasibility in experimental design. In the follow-up experiment, we evaluate the clinical quality of masks by having ophthalmologists rank generation methods. The ranking is established with high intra-observer consistency, indicating better subjective performance for a subset of tested networks. The study also demonstrates that objective metrics are not correlated with subjective metrics in retinal segmentation tasks for the methods involved, suggesting that objective metrics commonly used in scientific papers to measure the method's performance are not plausible criteria for choosing clinically robust solutions.

Controlling microbial co-culture based on substrate pulsing can lead to stability through differential fitness advantages

Microbial consortia are an exciting alternative for increasing the performances of bioprocesses for the production of complex metabolic products. However, the functional properties of microbial communities remain challenging to control, considering the complex interaction mechanisms occurring between co-cultured microbial species. Indeed, microbial communities are highly dynamic and can adapt to changing environmental conditions through complex mechanisms, such as phenotypic diversification. We focused on stabilizing a co-culture of Saccharomyces cerevisiae and Escherichia coli in continuous cultures. Our preliminary data pointed out that transient diauxic shifts could lead to stable co-culture by providing periodic fitness advantages to the yeast. Based on a computational toolbox called MONCKS (for MONod-type Co-culture Kinetic Simulation), we were able to predict the dynamics of diauxic shift for both species based on a cybernetic approach. This toolbox was further used to predict the frequency of diauxic shift to be applied to reach co-culture stability. These simulations were successfully reproduced experimentally in continuous bioreactors with glucose pulsing. Finally, based on a bet-hedging reporter, we observed that the yeast population exhibited an increased phenotypic diversification process in co-culture compared with mono-culture, suggesting that this mechanism could be the basis of the metabolic fitness of the yeast.

Being able to manipulate the dynamics of microbial co-cultures is a technical challenge that need to be addressed in order to get a deeper insight about how microbial communities are evolving in their ecological context, as well as for exploiting the potential offered by such communities in an applied context e.g., for setting up more robust bioprocesses relying on the use of several microbial species. In this study, we used continuous cultures of bacteria (E. coli) and yeast (S. cerevisiae) in order to demonstrate that a simple nutrient pulsing strategy can be used for adjusting the composition of the community with time. As expected, during growth on glucose, E. coli quickly outcompeted S. cerevisiae. However, when glucose is pulsed into the culture, increased metabolic fitness of the yeast was observed upon reconsumption of the main side metabolites i.e., acetate and ethanol, leading to a robust oscillating growth profile for both species. The optimal pulsing frequency was predicted based on a cybernetic version of a Monod growth model taking into account the main metabolic routes involved in the process. Considering the limited number of metabolic details needed, this cybernetic approach could be generalized to other communities.

Altered expression response upon repeated gene repression in single yeast cells

Cells must continuously adjust to changing environments and, thus, have evolved mechanisms allowing them to respond to repeated stimuli. While faster gene induction upon a repeated stimulus is known as reinduction memory, responses to repeated repression have been less studied so far. Here, we studied gene repression across repeated carbon source shifts in over 1,500 single Saccharomyces cerevisiae cells. By monitoring the expression of a carbon source-responsive gene, galactokinase 1 (Gal1), and fitting a mathematical model to the single-cell data, we observed a faster response upon repeated repressions at the population level. Exploiting our single-cell data and quantitative modeling approach, we discovered that the faster response is mediated by a shortened repression response delay, the estimated time between carbon source shift and Gal1 protein production termination. Interestingly, we can exclude two alternative hypotheses, i) stronger dilution because of e.g., increased proliferation, and ii) a larger fraction of repressing cells upon repeated repressions. Collectively, our study provides a quantitative description of repression kinetics in single cells and allows us to pinpoint potential mechanisms underlying a faster response upon repeated repression. The computational results of our study can serve as the starting point for experimental follow-up studies.

Cells have to continuously adjust to their environment and cope with changing temperature, stress conditions, or metabolic resources. Yeast cells exposed to repeated carbon source shifts have shown to be “primed” by their first exposure, exhibiting enhanced gene expression of specific genes later on. However, how cells respond to a repeated repressive stimulus, e.g., withdrawal of metabolic resources, has been so far much less studied.

For this, we investigated the expression kinetics of a carbon source-responsive gene across repeated repressions. We measured single-cell expression and used mathematical modeling to evaluate potential causes underlying an observed faster repression response upon a repeated stimulus. Specifically, we investigated whether i) an increased dilution due to e.g., proliferation, ii) an increased fraction of repressing cells, or iii) different kinetic parameters in the repeated repression cause the observed faster response in the second repression. Leveraging quantitative mathematical model comparison, we discovered that the faster response is mediated by a shortened estimated time between carbon source shift and protein production termination at the single-cell level.

Our study provides a quantitative description of repression kinetics in single cells and allows us to pinpoint potential mechanisms underlying a faster response upon repeated repression.

Cell region fingerprints enable highly precise single-cell tracking and lineage reconstruction

Experimental studies of cell growth, inheritance and their associated processes by microscopy require accurate single-cell observations of sufficient duration to reconstruct the genealogy. However, cell tracking-assigning identical cells on consecutive images to a track-is often challenging, resulting in laborious manual verification. Here, we propose fingerprints to identify problematic assignments rapidly. A fingerprint distance compares the structural information contained in the low frequencies of a Fourier transform to measure the similarity between cells in two consecutive images. We show that fingerprints are broadly applicable across cell types and image modalities, provided the image has sufficient structural information. Our tracker (Trac^X) uses fingerprints to reject unlikely assignments, thereby increasing tracking performance on published and newly generated long-term data sets. For Saccharomyces cerevisiae, we propose a comprehensive model for cell size control at the single-cell and population level centered on the Whi5 regulator, demonstrating how precise tracking can help uncover previously undescribed single-cell biology.

A quantitative and spatial analysis of cell cycle regulators during the fission yeast cycle

Across eukaryotes, the increasing level of cyclin-dependent kinase (CDK) activity drives progression through the cell cycle. As most cells divide at specific sizes, information responding to the size of the cell must feed into the regulation of CDK activity. In this study, we use fission yeast to precisely measure how proteins that have been previously identified in genome-wide screens as cell cycle regulators change in their levels with cell cycle progression. We identify the mitotic B-type cyclin Cdc13 and the mitotic inhibitory phosphatase Cdc25 as the only two proteins that change in both whole-cell and nuclear concentration through the cell cycle, making them potential candidates for universal cell size sensors at the onset of mitosis and cell division.

We have carried out a systems-level analysis of the spatial and temporal dynamics of cell cycle regulators in the fission yeast Schizosaccharomyces pombe. In a comprehensive single-cell analysis, we have precisely quantified the levels of 38 proteins previously identified as regulators of the G2 to mitosis transition and of 7 proteins acting at the G1- to S-phase transition. Only 2 of the 38 mitotic regulators exhibit changes in concentration at the whole-cell level: the mitotic B-type cyclin Cdc13, which accumulates continually throughout the cell cycle, and the regulatory phosphatase Cdc25, which exhibits a complex cell cycle pattern. Both proteins show similar patterns of change within the nucleus as in the whole cell but at higher concentrations. In addition, the concentrations of the major fission yeast cyclin-dependent kinase (CDK) Cdc2, the CDK regulator Suc1, and the inhibitory kinase Wee1 also increase in the nucleus, peaking at mitotic onset, but are constant in the whole cell. The significant increase in concentration with size for Cdc13 supports the view that mitotic B-type cyclin accumulation could act as a cell size sensor. We propose a two-step process for the control of mitosis. First, Cdc13 accumulates in a size-dependent manner, which drives increasing CDK activity. Second, from mid-G2, the increasing nuclear accumulation of Cdc25 and the counteracting Wee1 introduce a bistability switch that results in a rapid rise of CDK activity at the end of G2 and thus, brings about an orderly progression into mitosis.

A Comprehensive Survey with Quantitative Comparison of Image Analysis Methods for Microorganism Biovolume Measurements

With the acceleration of urbanization and living standards, microorganisms play an increasingly important role in industrial production, bio-technique, and food safety testing. Microorganism biovolume measurements are one of the essential parts of microbial analysis. However, traditional manual measurement methods are time-consuming and challenging to measure the characteristics precisely. With the development of digital image processing techniques, the characteristics of the microbial population can be detected and quantified. The applications of the microorganism biovolume measurement method have developed since the 1980s. More than 62 articles are reviewed in this study, and the articles are grouped by digital image analysis methods with time. This study has high research significance and application value, which can be referred to as microbial researchers to comprehensively understand microorganism biovolume measurements using digital image analysis methods and potential applications.

Automated Nuclear Segmentation in Head and Neck Squamous Cell Carcinoma Pathology Reveals Relationships between Cytometric Features and ESTIMATE Stromal and Immune Scores

The tumor microenvironment (TME) plays an important role in the progression of head and neck squamous cell carcinoma (HNSCC). Currently, pathologic assessment of TME is nonstandardized and subject to observer bias. Genome-wide transcriptomic approaches to understanding the TME, while less subject to bias, are expensive and not currently a part of the standard of care for HNSCC. To identify pathology-based biomarkers that correlate with genomic and transcriptomic signatures of TME in HNSCC, cytometric feature maps were generated in a publicly available data set from a cohort of patients with HNSCC, including whole-slide tissue images and genomic and transcriptomic phenotyping (N = 49). Cytometric feature maps were generated based on whole-slide nuclear detection, using a deep-learning algorithm trained for StarDist nuclear segmentation. Cytometric features in each patient were compared to transcriptomic measurements, including Estimation of Stromal and Immune Cells in Malignant Tumor Tissues Using Expression Data (ESTIMATE) scores and stemness scores. With correction for multiple comparisons, one feature (nuclear circularity) demonstrated a significant linear correlation with ESTIMATE stromal score. Two features (nuclear maximum and minimum diameter) correlated significantly with ESTIMATE immune score. Three features (nuclear solidity, nuclear minimum diameter, and nuclear circularity) correlated significantly with transcriptomic stemness score. This study provides preliminary evidence that observer-independent, automated tissue-slide analysis can provide insights into the HNSCC TME which correlate with genomic and transcriptomic assessments.

DetecDiv, a generalist deep-learning platform for automated cell division tracking and survival analysis

Automating the extraction of meaningful temporal information from sequences of microscopy images represents a major challenge to characterize dynamical biological processes. So far, strong limitations in the ability to quantitatively analyze single-cell trajectories have prevented large-scale investigations to assess the dynamics of entry into replicative senescence in yeast. Here, we have developed DetecDiv, a microfluidic-based image acquisition platform combined with deep learning-based software for high-throughput single-cell division tracking. We show that DetecDiv can automatically reconstruct cellular replicative lifespans with high accuracy and performs similarly with various imaging platforms and geometries of microfluidic traps. In addition, this methodology provides comprehensive temporal cellular metrics using time-series classification and image semantic segmentation. Last, we show that this method can be further applied to automatically quantify the dynamics of cellular adaptation and real-time cell survival upon exposure to environmental stress. Hence, this methodology provides an all-in-one toolbox for high-throughput phenotyping for cell cycle, stress response, and replicative lifespan assays.

Segmentation, tracking and cell cycle analysis of live-cell imaging data with Cell-ACDC

Background

High-throughput live-cell imaging is a powerful tool to study dynamic cellular processes in single cells but creates a bottleneck at the stage of data analysis, due to the large amount of data generated and limitations of analytical pipelines. Recent progress on deep learning dramatically improved cell segmentation and tracking. Nevertheless, manual data validation and correction is typically still required and tools spanning the complete range of image analysis are still needed.

Results

We present Cell-ACDC, an open-source user-friendly GUI-based framework written in Python, for segmentation, tracking and cell cycle annotations. We included state-of-the-art deep learning models for single-cell segmentation of mammalian and yeast cells alongside cell tracking methods and an intuitive, semi-automated workflow for cell cycle annotation of single cells. Using Cell-ACDC, we found that mTOR activity in hematopoietic stem cells is largely independent of cell volume. By contrast, smaller cells exhibit higher p38 activity, consistent with a role of p38 in regulation of cell size. Additionally, we show that, in S. cerevisiae, histone Htb1 concentrations decrease with replicative age.

Conclusions

Cell-ACDC provides a framework for the application of state-of-the-art deep learning models to the analysis of live cell imaging data without programming knowledge. Furthermore, it allows for visualization and correction of segmentation and tracking errors as well as annotation of cell cycle stages. We embedded several smart algorithms that make the correction and annotation process fast and intuitive. Finally, the open-source and modularized nature of Cell-ACDC will enable simple and fast integration of new deep learning-based and traditional methods for cell segmentation, tracking, and downstream image analysis.

Source code: https://github.com/SchmollerLab/Cell_ACDC

Supplementary Information

The online version contains supplementary material available at 10.1186/s12915-022-01372-6.

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.

An Application of Pixel Interval Down-Sampling (PID) for Dense Tiny Microorganism Counting on Environmental Microorganism Images

This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder–decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting.

Mitotic checkpoint gene expression is tuned by codon usage bias

The mitotic checkpoint (also called spindle assembly checkpoint, SAC) is a signaling pathway that safeguards proper chromosome segregation. Correct functioning of the SAC depends on adequate protein concentrations and appropriate stoichiometries between SAC proteins. Yet very little is known about the regulation of SAC gene expression. Here, we show in the fission yeast Schizosaccharomyces pombe that a combination of short mRNA half-lives and long protein half-lives supports stable SAC protein levels. For the SAC genes mad2⁺ and mad3⁺ , their short mRNA half-lives are caused, in part, by a high frequency of nonoptimal codons. In contrast, mad1⁺ mRNA has a short half-life despite a higher frequency of optimal codons, and despite the lack of known RNA-destabilizing motifs. Hence, different SAC genes employ different strategies of expression. We further show that Mad1 homodimers form co-translationally, which may necessitate a certain codon usage pattern. Taken together, we propose that the codon usage of SAC genes is fine-tuned to ensure proper SAC function. Our work shines light on gene expression features that promote spindle assembly checkpoint function and suggests that synonymous mutations may weaken the checkpoint.

The optimal strategy balancing risk and speed predicts DNA damage checkpoint override times

Checkpoints arrest biological processes allowing time for error correction. The phenomenon of checkpoint override (also known as checkpoint adaptation, slippage, or leakage), during cellular self-replication is biologically critical but currently lacks a quantitative, functional, or system-level understanding. To uncover fundamental laws governing error-correction systems, we derived a general theory of optimal checkpoint strategies, balancing the trade-off between risk and self-replication speed. Mathematically, the problem maps onto the optimization of an absorbing boundary for a random walk. We applied the theory to the DNA damage checkpoint (DDC) in budding yeast, an intensively researched model checkpoint. Using novel reporters for double-strand DNA breaks (DSBs), we first quantified the probability distribution of DSB repair in time including rare events and, secondly, the survival probability after override. With these inputs, the optimal theory predicted remarkably accurately override times as a function of DSB numbers, which we measured precisely for the first time. Thus, a first-principles calculation revealed undiscovered patterns underlying highly noisy override processes. Our multi-DSB measurements revise well-known past results and show that override is more general than previously thought.

Live cell microscopy: From image to insight

Live-cell microscopy is a powerful tool that can reveal cellular behavior as well as the underlying molecular processes. A key advantage of microscopy is that by visualizing biological processes, it can provide direct insights. Nevertheless, live-cell imaging can be technically challenging and prone to artifacts. For a successful experiment, many careful decisions are required at all steps from hardware selection to downstream image analysis. Facing these questions can be particularly intimidating due to the requirement for expertise in multiple disciplines, ranging from optics, biophysics, and programming to cell biology. In this review, we aim to summarize the key points that need to be considered when setting up and analyzing a live-cell imaging experiment. While we put a particular focus on yeast, many of the concepts discussed are applicable also to other organisms. In addition, we discuss reporting and data sharing strategies that we think are critical to improve reproducibility in the field.

Intron-mediated induction of phenotypic heterogeneity

Intragenic regions that are removed during maturation of the RNA transcript—introns—are universally present in the nuclear genomes of eukaryotes¹. The budding yeast, an otherwise intron-poor species, preserves two sets of ribosomal protein genes that differ primarily in their introns^2,3. Although studies have shed light on the role of ribosomal protein introns under stress and starvation^4–6, understanding the contribution of introns to ribosome regulation remains challenging. Here, by combining isogrowth profiling⁷ with single-cell protein measurements⁸, we show that introns can mediate inducible phenotypic heterogeneity that confers a clear fitness advantage. Osmotic stress leads to bimodal expression of the small ribosomal subunit protein Rps22B, which is mediated by an intron in the 5′ untranslated region of its transcript. The two resulting yeast subpopulations differ in their ability to cope with starvation. Low levels of Rps22B protein result in prolonged survival under sustained starvation, whereas high levels of Rps22B enable cells to grow faster after transient starvation. Furthermore, yeasts growing at high concentrations of sugar, similar to those in ripe grapes, exhibit bimodal expression of Rps22B when approaching the stationary phase. Differential intron-mediated regulation of ribosomal protein genes thus provides a way to diversify the population when starvation threatens in natural environments. Our findings reveal a role for introns in inducing phenotypic heterogeneity in changing environments, and suggest that duplicated ribosomal protein genes in yeast contribute to resolving the evolutionary conflict between precise expression control and environmental responsiveness⁹.

Experiments in yeast show that introns have a role in inducing phenotypic heterogeneity and that intron-mediated regulation of ribosomal proteins confers a fitness advantage by enabling yeast populations to diversify under nutrient-scarce conditions.

YeastMate: Neural network-assisted segmentation of mating and budding events in S. cerevisiae

SUMMARY

Here, we introduce YeastMate, a user-friendly deep learning-based application for automated detection and segmentation of Saccharomyces cerevisiae cells and their mating and budding events in microscopy images. We build upon Mask R-CNN with a custom segmentation head for the subclassification of mother and daughter cells during lifecycle transitions. YeastMate can be used directly as a Python library or through a stand-alone GUI application and a Fiji plugin as easy to use frontends.

AVAILABILITY AND IMPLEMENTATION

The source code for YeastMate is freely available at https://github.com/hoerlteam/YeastMate under the MIT license. We offer installers for our software stack for Windows, macOS and Linux. A detailed user guide is available at https://yeastmate.readthedocs.io.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A convolutional neural network for segmentation of yeast cells without manual training annotations

MOTIVATION

Single-cell time-lapse microscopy is a ubiquitous tool for studying the dynamics of complex cellular processes. While imaging can be automated to generate very large volumes of data, the processing of the resulting movies to extract high-quality single-cell information remains a challenging task. The development of software tools that automatically identify and track cells is essential for realizing the full potential of time-lapse microscopy data. Convolutional neural networks (CNNs) are ideally suited for such applications, but require great amounts of manually annotated data for training, a time-consuming and tedious process.

RESULTS

We developed a new approach to CNN training for yeast cell segmentation based on synthetic data and present (i) a software tool for the generation of synthetic images mimicking brightfield images of budding yeast cells and (ii) a convolutional neural network (Mask R-CNN) for yeast segmentation that was trained on a fully synthetic dataset. The Mask R-CNN performed excellently on segmenting actual microscopy images of budding yeast cells, and a density-based spatial clustering algorithm (DBSCAN) was able to track the detected cells across the frames of microscopy movies. Our synthetic data creation tool completely bypassed the laborious generation of manually annotated training datasets, and can be easily adjusted to produce images with many different features. The incorporation of synthetic data creation into the development pipeline of CNN-based tools for budding yeast microscopy is a critical step toward the generation of more powerful, widely applicable and user-friendly image processing tools for this microorganism.

AVAILABILITY AND IMPLEMENTATION

The synthetic data generation code can be found at https://github.com/prhbrt/synthetic-yeast-cells. The Mask R-CNN as well as the tuning and benchmarking scripts can be found at https://github.com/ymzayek/yeastcells-detection-maskrcnn. We also provide Google Colab scripts that reproduce all the results of this work.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Transcriptional and chromatin-based partitioning mechanisms uncouple protein scaling from cell size

Biosynthesis scales with cell size such that protein concentrations generally remain constant as cells grow. As an exception, synthesis of the cell-cycle inhibitor Whi5 "sub-scales" with cell size so that its concentration is lower in larger cells to promote cell-cycle entry. Here, we find that transcriptional control uncouples Whi5 synthesis from cell size, and we identify histones as the major class of sub-scaling transcripts besides WHI5 by screening for similar genes. Histone synthesis is thereby matched to genome content rather than cell size. Such sub-scaling proteins are challenged by asymmetric cell division because proteins are typically partitioned in proportion to newborn cell volume. To avoid this fate, Whi5 uses chromatin-binding to partition similar protein amounts to each newborn cell regardless of cell size. Disrupting both Whi5 synthesis and chromatin-based partitioning weakens G1 size control. Thus, specific transcriptional and partitioning mechanisms determine protein sub-scaling to control cell size.

Yeast cell segmentation in microstructured environments with deep learning

Cell segmentation is a major bottleneck in extracting quantitative single-cell information from microscopy data. The challenge is exasperated in the setting of microstructured environments. While deep learning approaches have proven useful for general cell segmentation tasks, previously available segmentation tools for the yeast-microstructure setting rely on traditional machine learning approaches. Here we present convolutional neural networks trained for multiclass segmenting of individual yeast cells and discerning these from cell-similar microstructures. An U-Net based semantic segmentaiton approach, as well as a direct instance segmentation approach with a Mask R-CNN are demonstrated. We give an overview of the datasets recorded for training, validating and testing the networks, as well as a typical use-case. We showcase the methods' contribution to segmenting yeast in microstructured environments with a typical systems or synthetic biology application. The models achieve robust segmentation results, outperforming the previous state-of-the-art in both accuracy and speed. The combination of fast and accurate segmentation is not only beneficial for a posteriori data processing, it also makes online monitoring of thousands of trapped cells or closed-loop optimal experimental design feasible from an image processing perspective. Code is and data samples are available at https://git.rwth-aachen.de/bcs/projects/tp/multiclass-yeast-seg.