LiveCellMiner: A new tool to analyze mitotic progression

Predicting cell cycle stage from 3D single-cell nuclear-stained images

The cell cycle governs the proliferation of all eukaryotic cells. Profiling cell cycle dynamics is therefore central to basic and biomedical research. However, current approaches to cell cycle profiling involve complex interventions that may confound experimental interpretation. We developed CellCycleNet, a machine learning (ML) workflow, to simplify cell cycle staging from fluorescent microscopy data with minimal experimenter intervention and cost. CellCycleNet accurately predicts cell cycle phase using only a fluorescent nuclear stain (DAPI) in fixed interphase cells. Using the Fucci2a cell cycle reporter system as ground truth, we collected two benchmarking image datasets and trained 2D and 3D ML models-of support vector machine and deep neural network architecture-to classify nuclei in the G1 or S/G2 phases. Our results show that 3D CellCycleNet outperforms support vector machine models on each dataset. When trained on two image datasets simultaneously, CellCycleNet achieves the highest classification accuracy (AUROC of 0.94-0.95). Overall, we found that using 3D features, rather than 2D features alone, significantly improves classification performance for all model architectures. We released our image data, models, and software as a community resource.

The DEAD-box helicase eIF4A1/2 acts as RNA chaperone during mitotic exit enabling chromatin decondensation

During mitosis, chromosomes condense and decondense to segregate faithfully and undamaged. The exact molecular mechanisms are not well understood. We identify the DEAD-box helicase eIF4A1/2 as a critical factor in this process. In a cell-free condensation assay eIF4A1/2 is crucial for this process, relying on its RNA-binding ability but not its ATPase activity. Reducing eIF4A1/2 levels in cells consistently slows down chromatin decondensation during nuclear reformation. Conversely, increasing eIF4A1/2 concentration on mitotic chromosomes accelerates their decondensation. The absence of eIF4A1/2 affects the perichromatin layer, which surrounds the chromosomes during mitosis and consists of RNA and mainly nucleolar proteins. In vitro, eIF4A1/2 acts as an RNA chaperone, dissociating biomolecular condensates of RNA and perichromatin proteins. During mitosis, the chaperone activity of eIF4A1/2 is required to regulate the composition and fluidity of the perichromatin layer, which is crucial for the dynamic reorganization of chromatin as cells exit mitosis.

Quantitative Live-Cell Imaging to Study Chromatin Segregation and Nuclear Reformation

Live-cell imaging is a powerful tool for the investigation of different steps of the life and fate of single cells and cell populations. In this chapter, we describe how to perform live-cell imaging in tissue culture cells and the subsequent image analysis to precisely characterize the cytological events occurring during mitotic exit and nuclear reformation.

Automatic detection of cell-cycle stages using recurrent neural networks

Mitosis is the process by which eukaryotic cells divide to produce two similar daughter cells with identical genetic material. Research into the process of mitosis is therefore of critical importance both for the basic understanding of cell biology and for the clinical approach to manifold pathologies resulting from its malfunctioning, including cancer. In this paper, we propose an approach to study mitotic progression automatically using deep learning. We used neural networks to predict different mitosis stages. We extracted video sequences of cells undergoing division and trained a Recurrent Neural Network (RNN) to extract image features. The use of RNN enabled better extraction of features. The RNN-based approach gave better performance compared to classifier based feature extraction methods which do not use time information. Evaluation of precision, recall, and F-score indicates the superiority of the proposed model compared to the baseline. To study the loss in performance due to confusion between adjacent classes, we plotted the confusion matrix as well. In addition, we visualized the feature space to understand why RNNs are better at classifying the mitosis stages than other classifier models, which indicated the formation of strong clusters for the different classes, clearly confirming the advantage of the proposed RNN-based approach.

Denoising diffusion probabilistic models for generation of realistic fully-annotated microscopy image datasets

Recent advances in computer vision have led to significant progress in the generation of realistic image data, with denoising diffusion probabilistic models proving to be a particularly effective method. In this study, we demonstrate that diffusion models can effectively generate fully-annotated microscopy image data sets through an unsupervised and intuitive approach, using rough sketches of desired structures as the starting point. The proposed pipeline helps to reduce the reliance on manual annotations when training deep learning-based segmentation approaches and enables the segmentation of diverse datasets without the need for human annotations. We demonstrate that segmentation models trained with a small set of synthetic image data reach accuracy levels comparable to those of generalist models trained with a large and diverse collection of manually annotated image data, thereby offering a streamlined and specialized application of segmentation models.