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

DeepKymoTracker: A tool for accurate construction of cell lineage trees for highly motile cells

Time-lapse microscopy has long been used to record cell lineage trees. Successful construction of a lineage tree requires tracking and preserving the identity of multiple cells across many images. If a single cell is misidentified the identity of all its progeny will be corrupted and inferences about heritability may be incorrect. Successfully avoiding such identity errors is challenging, however, when studying highly-motile cells such as T lymphocytes which readily change shape from one image to the next. To address this problem, we developed DeepKymoTracker, a pipeline for combined tracking and segmentation. Central to DeepKymoTracker is the use of a seed, a marker for each cell which transmits information about cell position and identity between sets of images during tracking, as well as between tracking and segmentation steps. The seed allows a 3D convolutional neural network (CNN) to detect and associate cells across several consecutive images in an integrated way, reducing the risk of a single poor image corrupting cell identity. DeepKymoTracker was trained extensively on synthetic and experimental T lymphocyte images. It was benchmarked against five publicly available, automatic analysis tools and outperformed them in almost all respects. The software is written in pure Python and is freely available. We suggest this tool is particularly suited to the tracking of cells in suspension, whose fast motion makes lineage assembly particularly difficult.

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.

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.

When yeast cells change their mind: cell cycle "Start" is reversible under starvation

Eukaryotic cells decide in late G1 phase of the cell cycle whether to commit to another round of division. This point of cell cycle commitment is termed "Restriction Point" in mammals and "Start" in the budding yeast Saccharomyces cerevisiae. At Start, yeast cells integrate multiple signals such as pheromones and nutrients, and will not pass Start if nutrients are lacking. However, how cells respond to nutrient depletion after the Start decision remains poorly understood. Here, we analyze how post-Start cells respond to nutrient depletion, by monitoring Whi5, the cell cycle inhibitor whose export from the nucleus determines Start. Surprisingly, we find that cells that have passed Start can re-import Whi5 into the nucleus. In these cells, the positive feedback loop activating G1/S transcription is interrupted, and the Whi5 repressor re-binds DNA. Cells which re-import Whi5 become again sensitive to mating pheromone, like pre-Start cells, and CDK activation can occur a second time upon replenishment of nutrients. These results demonstrate that upon starvation, the commitment decision at Start can be reversed. We therefore propose that cell cycle commitment in yeast is a multi-step process, similar to what has been suggested for mammalian cells.

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.

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.

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.

Cdc14 spatiotemporally dephosphorylates Atg13 to activate autophagy during meiotic divisions

Autophagy is a conserved eukaryotic lysosomal degradation pathway that responds to environmental and cellular cues. Autophagy is essential for the meiotic exit and sporulation in budding yeast, but the underlying molecular mechanisms remain unknown. Here, we show that autophagy is maintained during meiosis and stimulated in anaphase I and II. Cells with higher levels of autophagy complete meiosis faster, and genetically enhanced autophagy increases meiotic kinetics and sporulation efficiency. Strikingly, our data reveal that the conserved phosphatase Cdc14 regulates meiosis-specific autophagy. Cdc14 is activated in anaphase I and II, accompanying its subcellular relocation from the nucleolus to the cytoplasm, where it dephosphorylates Atg13 to stimulate Atg1 kinase activity and thus autophagy. Together, our findings reveal a meiosis-tailored mechanism that spatiotemporally controls meiotic autophagy activity to ensure meiosis progression, exit, and sporulation.

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.

Cell cycle-independent integration of stress signals by Xbp1 promotes Non-G1/G0 quiescence entry

Cellular quiescence is a nonproliferative state required for cell survival under stress and during development. In most quiescent cells, proliferation is stopped in a reversible state of low Cdk1 kinase activity; in many organisms, however, quiescent states with high-Cdk1 activity can also be established through still uncharacterized stress or developmental mechanisms. Here, we used a microfluidics approach coupled to phenotypic classification by machine learning to identify stress pathways associated with starvation-triggered high-Cdk1 quiescent states in Saccharomyces cerevisiae. We found that low- and high-Cdk1 quiescent states shared a core of stress-associated processes, such as autophagy, protein aggregation, and mitochondrial up-regulation, but differed in the nuclear accumulation of the stress transcription factors Xbp1, Gln3, and Sfp1. The decision between low- or high-Cdk1 quiescence was controlled by cell cycle-independent accumulation of Xbp1, which acted as a time-delayed integrator of the duration of stress stimuli. Our results show how cell cycle-independent stress-activated factors promote cellular quiescence outside G1/G0.

YeastNet: Deep-Learning-Enabled Accurate Segmentation of Budding Yeast Cells in Bright-Field Microscopy

Accurate and efficient segmentation of live-cell images is critical in maximizing data extraction and knowledge generation from high-throughput biology experiments. Despite recent development of deep-learning tools for biomedical imaging applications, great demand for automated segmentation tools for high-resolution live-cell microscopy images remains in order to accelerate the analysis. YeastNet dramatically improves the performance of the non-trainable classic algorithm, and performs considerably better than the current state-of-the-art yeast-cell segmentation tools. We have designed and trained a U-Net convolutional network (named YeastNet) to conduct semantic segmentation on bright-field microscopy images and generate segmentation masks for cell labeling and tracking. YeastNet enables accurate automatic segmentation and tracking of yeast cells in biomedical applications. YeastNet is freely provided with model weights as a Python package on GitHub.

Nutrient Signaling, Stress Response, and Inter-organelle Communication Are Non-canonical Determinants of Cell Fate

Isogenic cells manifest distinct cellular fates for a single stress; however, the nongenetic mechanisms driving such fates remain poorly understood. Here, we implement a robust multi-channel live-cell imaging approach to uncover noncanonical factors governing cell fate. We show that in response to acute glucose removal (AGR), budding yeast undergoes distinct fates, becoming either quiescent or senescent. Senescent cells fail to resume mitotic cycles following glucose replenishment but remain responsive to nutrient stimuli. Whereas quiescent cells manifest starvation-induced adaptation, senescent cells display perturbed endomembrane trafficking and defective nucleus-vacuole junction (NVJ) expansion. Surprisingly, senescence occurs even in the absence of lipid droplets. Importantly, we identify the nutrient-sensing kinase Rim15 as a key biomarker predicting cell fates before AGR stress. We propose that isogenic yeast challenged with acute nutrient shortage contains determinants influencing post-stress fate and demonstrate that specific nutrient signaling, stress response, trafficking, and inter-organelle biomarkers are early indicators for long-term fate outcomes.

A convolutional neural network segments yeast microscopy images with high accuracy

The identification of cell borders ('segmentation') in microscopy images constitutes a bottleneck for large-scale experiments. For the model organism Saccharomyces cerevisiae, current segmentation methods face challenges when cells bud, crowd, or exhibit irregular features. We present a convolutional neural network (CNN) named YeaZ, the underlying training set of high-quality segmented yeast images (>10 000 cells) including mutants, stressed cells, and time courses, as well as a graphical user interface and a web application ( www.quantsysbio.com/data-and-software ) to efficiently employ, test, and expand the system. A key feature is a cell-cell boundary test which avoids the need for fluorescent markers. Our CNN is highly accurate, including for buds, and outperforms existing methods on benchmark images, indicating it transfers well to other conditions. To demonstrate how efficient large-scale image processing uncovers new biology, we analyze the geometries of ≈2200 wild-type and cyclin mutant cells and find that morphogenesis control occurs unexpectedly early and gradually.

DeLTA: Automated cell segmentation, tracking, and lineage reconstruction using deep learning

Microscopy image analysis is a major bottleneck in quantification of single-cell microscopy data, typically requiring human oversight and curation, which limit both accuracy and throughput. To address this, we developed a deep learning-based image analysis pipeline that performs segmentation, tracking, and lineage reconstruction. Our analysis focuses on time-lapse movies of Escherichia coli cells trapped in a "mother machine" microfluidic device, a scalable platform for long-term single-cell analysis that is widely used in the field. While deep learning has been applied to cell segmentation problems before, our approach is fundamentally innovative in that it also uses machine learning to perform cell tracking and lineage reconstruction. With this framework we are able to get high fidelity results (1% error rate), without human intervention. Further, the algorithm is fast, with complete analysis of a typical frame containing ~150 cells taking <700msec. The framework is not constrained to a particular experimental set up and has the potential to generalize to time-lapse images of other organisms or different experimental configurations. These advances open the door to a myriad of applications including real-time tracking of gene expression and high throughput analysis of strain libraries at single-cell resolution.