Morphologically constrained and data informed cell segmentation of budding yeast

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.

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.

An Instance Segmentation Dataset of Yeast Cells in Microstructures

Extracting single-cell information from microscopy data requires accurate instance-wise segmentations. Obtaining pixel-wise segmentations from microscopy imagery remains a challenging task, especially with the added complexity of microstructured environments. This paper presents a novel dataset for segmenting yeast cells in microstructures. We offer pixel-wise instance segmentation labels for both cells and trap microstructures. In total, we release 493 densely annotated microscopy images. To facilitate a unified comparison between novel segmentation algorithms, we propose a standardized evaluation strategy for our dataset. The aim of the dataset and evaluation strategy is to facilitate the development of new cell segmentation approaches. The dataset is publicly available at https://christophreich1996.github.io/yeast_in_microstructures_dataset/.

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.

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.

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.

A Cyber-Physical Platform for Model Calibration

Synthetic biology has so far made limited use of mathematical models, mostly because their inference has been traditionally perceived as expensive and/or difficult. We have recently demonstrated how in silico simulations and in vitro/vivo experiments can be integrated to develop a cyber-physical platform that automates model calibration and leads to saving 60-80% of the effort. In this book chapter, we illustrate the protocol used to attain such results. By providing a comprehensive list of steps and pointing the reader to the code we use to operate our platform, we aim at providing synthetic biologists with an additional tool to accelerate the pace at which the field progresses toward applications.

Improved efficiency of urine cell image segmentation using droplet microfluidics technology

Recent advances in the recognition of biological samples using machine vision have made this technology increasingly important in research and detection. Image segmentation is an important step in this process. This study focuses on how to reduce the interference factors such as the overlap between different types (or within the same type) of urine cells according to microfluidics and improve the machine vision segmentation accuracy for cell images. In this study, we demonstrate that the platform can realize this hypothesis using urine cell image segmentation as an example application. We first discuss the reported urine cell droplet microfluidic chip system, which can realize the test conditions in which urine cells are encapsulated in the droplet and isolated from salt crystallization and/or bacteria and other urine-formed elements. Then, based on the analysis conditions set in the aforementioned experiment, the proportions of red blood cells, white blood cells, and squamous epithelial cells covered by various formed elements in the total urine cells in the same urine sample are measured. We simultaneously analyze the percentage of urine cells covered by salt crystallization and the incidence of overlapping between urine cells. Finally, the Otsu algorithm is used to segment the urine cell images encapsulated by the droplet and the urine cell images not encapsulated by the droplet, and the Dice, Jaccard, precision, and recall values are calculated. The results suggest that the method of encapsulating single cells based on droplets can improve the image segmentation effect without optimizing the algorithm.

YeastSpotter: accurate and parameter-free web segmentation for microscopy images of yeast cells

SUMMARY

We introduce YeastSpotter, a web application for the segmentation of yeast microscopy images into single cells. YeastSpotter is user-friendly and generalizable, reducing the computational expertise required for this critical preprocessing step in many image analysis pipelines.

AVAILABILITY AND IMPLEMENTATION

YeastSpotter is available at http://yeastspotter.csb.utoronto.ca/. Code is available at https://github.com/alexxijielu/yeast_segmentation.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Loss of vacuolar acidity results in iron-sulfur cluster defects and divergent homeostatic responses during aging in Saccharomyces cerevisiae

The loss of vacuolar/lysosomal acidity is an early event during aging that has been linked to mitochondrial dysfunction. However, it is unclear how loss of vacuolar acidity results in age-related dysfunction. Through unbiased genetic screens, we determined that increased iron uptake can suppress the mitochondrial respiratory deficiency phenotype of yeast vma mutants, which have lost vacuolar acidity due to genetic disruption of the vacuolar ATPase proton pump. Yeast vma mutants exhibited nuclear localization of Aft1, which turns on the iron regulon in response to iron-sulfur cluster (ISC) deficiency. This led us to find that loss of vacuolar acidity with age in wild-type yeast causes ISC defects and a DNA damage response. Using microfluidics to investigate aging at the single-cell level, we observe grossly divergent trajectories of iron homeostasis within an isogenic and environmentally homogeneous population. One subpopulation of cells fails to mount the expected compensatory iron regulon gene expression program, and suffers progressively severe ISC deficiency with little to no activation of the iron regulon. In contrast, other cells show robust iron regulon activity with limited ISC deficiency, which allows extended passage and survival through a period of genomic instability during aging. These divergent trajectories suggest that iron regulation and ISC homeostasis represent a possible target for aging interventions.

Microfluidic platforms for the dynamic characterisation of synthetic circuitry

Generating novel functionality from well characterised synthetic parts and modules lies at the heart of synthetic biology. Ideally, circuitry is rationally designed in silico with quantitatively predictive models to predetermined design specifications. Synthetic circuits are intrinsically stochastic, often dynamically modulated and set in a dynamic fluctuating environment within a living cell. To build more complex circuits and to gain insight into context effects, intrinsic noise and transient performance, characterisation techniques that resolve both heterogeneity and dynamics are required. Here we review recent advances in both in vitro and in vivo microfluidic technologies that are suitable for the characterisation of synthetic circuitry, modules and parts.

DNA damage checkpoint activation impairs chromatin homeostasis and promotes mitotic catastrophe during aging

Genome instability is a hallmark of aging and contributes to age-related disorders such as cancer and Alzheimer's disease. The accumulation of DNA damage during aging has been linked to altered cell cycle dynamics and the failure of cell cycle checkpoints. Here, we use single cell imaging to study the consequences of increased genomic instability during aging in budding yeast and identify striking age-associated genome missegregation events. This breakdown in mitotic fidelity results from the age-related activation of the DNA damage checkpoint and the resulting degradation of histone proteins. Disrupting the ability of cells to degrade histones in response to DNA damage increases replicative lifespan and reduces genomic missegregations. We present several lines of evidence supporting a model of antagonistic pleiotropy in the DNA damage response where histone degradation, and limited histone transcription are beneficial to respond rapidly to damage but reduce lifespan and genomic stability in the long term.

Advances in quantitative biology methods for studying replicative aging in Saccharomyces cerevisiae

Aging is a complex, yet pervasive phenomenon in biology. As human cells steadily succumb to the deteriorating effects of aging, so too comes a host of age-related ailments such as neurodegenerative disorders, cardiovascular disease and cancer. Therefore, elucidation of the molecular networks that drive aging is of paramount importance to human health. Progress toward this goal has been aided by studies from simple model organisms such as Saccharomyces cerevisiae. While work in budding yeast has already revealed much about the basic biology of aging as well as a number of evolutionarily conserved pathways involved in this process, recent technological advances are poised to greatly expand our knowledge of aging in this simple eukaryote. Here, we review the latest developments in microfluidics, single-cell analysis and high-throughput technologies for studying single-cell replicative aging in S. cerevisiae. We detail the challenges each of these methods addresses as well as the unique insights into aging that each has provided. We conclude with a discussion of potential future applications of these techniques as well as the importance of single-cell dynamics and quantitative biology approaches for understanding cell aging.

Age-dependent deterioration of nuclear pore assembly in mitotic cells decreases transport dynamics

Nuclear transport is facilitated by the Nuclear Pore Complex (NPC) and is essential for life in eukaryotes. The NPC is a long-lived and exceptionally large structure. We asked whether NPC quality control is compromised in aging mitotic cells. Our images of single yeast cells during aging, show that the abundance of several NPC components and NPC assembly factors decreases. Additionally, the single-cell life histories reveal that cells that better maintain those components are longer lived. The presence of herniations at the nuclear envelope of aged cells suggests that misassembled NPCs are accumulated in aged cells. Aged cells show decreased dynamics of transcription factor shuttling and increased nuclear compartmentalization. These functional changes are likely caused by the presence of misassembled NPCs, as we find that two NPC assembly mutants show similar transport phenotypes as aged cells. We conclude that NPC interphase assembly is a major challenge for aging mitotic cells.

A fully-automated, robust, and versatile algorithm for long-term budding yeast segmentation and tracking

Live cell time-lapse microscopy, a widely-used technique to study gene expression and protein dynamics in single cells, relies on segmentation and tracking of individual cells for data generation. The potential of the data that can be extracted from this technique is limited by the inability to accurately segment a large number of cells from such microscopy images and track them over long periods of time. Existing segmentation and tracking algorithms either require additional dyes or markers specific to segmentation or they are highly specific to one imaging condition and cell morphology and/or necessitate manual correction. Here we introduce a fully automated, fast and robust segmentation and tracking algorithm for budding yeast that overcomes these limitations. Full automatization is achieved through a novel automated seeding method, which first generates coarse seeds, then automatically fine-tunes cell boundaries using these seeds and automatically corrects segmentation mistakes. Our algorithm can accurately segment and track individual yeast cells without any specific dye or biomarker. Moreover, we show how existing channels devoted to a biological process of interest can be used to improve the segmentation. The algorithm is versatile in that it accurately segments not only cycling cells with smooth elliptical shapes, but also cells with arbitrary morphologies (e.g. sporulating and pheromone treated cells). In addition, the algorithm is independent of the specific imaging method (bright-field/phase) and objective used (40X/63X/100X). We validate our algorithm's performance on 9 cases each entailing a different imaging condition, objective magnification and/or cell morphology. Taken together, our algorithm presents a powerful segmentation and tracking tool that can be adapted to numerous budding yeast single-cell studies.

Identification of individual cells from z-stacks of bright-field microscopy images

Obtaining single cell data from time-lapse microscopy images is critical for quantitative biology, but bottlenecks in cell identification and segmentation must be overcome. We propose a novel, versatile method that uses machine learning classifiers to identify cell morphologies from z-stack bright-field microscopy images. We show that axial information is enough to successfully classify the pixels of an image, without the need to consider in focus morphological features. This fast, robust method can be used to identify different cell morphologies, including the features of E. coli, S. cerevisiae and epithelial cells, even in mixed cultures. Our method demonstrates the potential of acquiring and processing Z-stacks for single-layer, single-cell imaging and segmentation.

Distributed and dynamic intracellular organization of extracellular information

Although cells respond specifically to environments, how environmental identity is encoded intracellularly is not understood. Here, we study this organization of information in budding yeast by estimating the mutual information between environmental transitions and the dynamics of nuclear translocation for 10 transcription factors. Our method of estimation is general, scalable, and based on decoding from single cells. The dynamics of the transcription factors are necessary to encode the highest amounts of extracellular information, and we show that information is transduced through two channels: Generalists (Msn2/4, Tod6 and Dot6, Maf1, and Sfp1) can encode the nature of multiple stresses, but only if stress is high; specialists (Hog1, Yap1, and Mig1/2) encode one particular stress, but do so more quickly and for a wider range of magnitudes. In particular, Dot6 encodes almost as much information as Msn2, the master regulator of the environmental stress response. Each transcription factor reports differently, and it is only their collective behavior that distinguishes between multiple environmental states. Changes in the dynamics of the localization of transcription factors thus constitute a precise, distributed internal representation of extracellular change. We predict that such multidimensional representations are common in cellular decision-making.

On-chip analysis of carbon dots effect on yeast replicative lifespan

Carbon dots (CDs) are promising nanomaterials for biosensing, bioimaging, and drug delivery due to their large surface area, excellent optical properties, and thermal and chemical stability. However, biosafety of CDs is still understudied, and there is not a generally accepted standard to evaluate the toxicity of CDs. We present a gradient network generator microfluidic device for dose-dependent testing of toxicity of CDs to a unicellular eukaryotic model organism, yeast Pichia pastoris. We fully characterized the microfluidic model and compare its performance with a conventional method. The gradient generator increased the contact area between the mixing species and enabled a high-throughput testing of CDs in a wide range of concentrations in cell chambers. Real time monitoring of yeast cell proliferation in the presence of CDs showed dose-dependent growth inhibition and various budding cell shape profiles. Comparing the result of microfluidic platform and conventional method revealed statistically significant differences in the proliferation rate of the cells between the two platforms. To understand the toxicity mechanism, we studied binding of CDs to P. pastoris and found increasing interactions of CDs with the cell surface at CDs larger concentrations. This study demonstrated the utility of the gradient generator microfluidic device as a convenient tool for toxicity assessment of nanomaterials at a cellular level.

Distributing tasks via multiple input pathways increases cellular survival in stress

Improving in one aspect of a task can undermine performance in another, but how such opposing demands play out in single cells and impact on fitness is mostly unknown. Here we study budding yeast in dynamic environments of hyperosmotic stress and show how the corresponding signalling network increases cellular survival both by assigning the requirements of high response speed and high response accuracy to two separate input pathways and by having these pathways interact to converge on Hog1, a p38 MAP kinase. Cells with only the less accurate, reflex-like pathway are fitter in sudden stress, whereas cells with only the slow, more accurate pathway are fitter in increasing but fluctuating stress. Our results demonstrate that cellular signalling is vulnerable to trade-offs in performance, but that these trade-offs can be mitigated by assigning the opposing tasks to different signalling subnetworks. Such division of labour could function broadly within cellular signal transduction.

DOI:http://dx.doi.org/10.7554/eLife.21415.001

The faster we do tasks the harder it is to do them well. For example, when we wish to judge if, say, a cup, is too hot, we first quickly withdraw our hand after touching it: we know that the cup is hot but not how much. Next we hold a finger against the cup to accurately judge its temperature. Such speed-accuracy trade-offs are studied widely in fields ranging from neuroscience to engineering, but their consequences for single cells are unknown. This is despite the fact that when cells are exposed to stress they must respond both quickly (to survive) and accurately (to reduce how many resources they consume).

One way of stressing yeast cells is to place them in a syrupy substance called sorbitol. This causes the cells to lose water, shrink in size, and launch a stress response to regain volume. If the cells respond inappropriately to the situation, they may die.

The signalling network that produces the stress response is unusual in that it has a Y-shaped structure, where the two ‘arms’ of the Y are the input pathways. Although it was known that one input pathway responds to stress faster than the other, the advantages of having two inputs in the signalling network were not understood. Granados, Crane et al. thought that the differences in speed and the Y-shaped structure could allow the cell to respond to stress with both speed and accuracy.

To investigate this theory, Granados, Crane et al. used a microscope to study individual yeast cells that had been exposed to sorbitol. Combining these results with a mathematical model of the cell signalling network revealed that a mutant yeast cell that only has one of the input pathways specializes in speed but is inaccurate, similar to a reflex-like response. In contrast, a mutant with only the other pathway specializes in accuracy, being slower but matching the level of the cell’s response to the level of stress placed on it. This trade-off is reflected in rates of cell survival: the first mutant survives best in sudden shocks of stress; the second mutant survives best in gradually increasing stress. Normal yeast cells that have both input pathways survive more often than either mutant.

Overall, the results presented by Granados, Crane et al. reveal principles behind cellular decision-making that should hold true in more complex organisms and could be exploited by synthetic biologists to programme cells with new behaviours.

DOI:http://dx.doi.org/10.7554/eLife.21415.002