Automatic recognition of protein subcellular location patterns in single cells from immunofluorescence images based on deep learning.

With the improvement of single-cell measurement techniques, there is a growing awareness that individual differences exist among cells, and protein expression distribution can vary across cells in the same tissue or cell line. Pinpointing the protein subcellular locations in single cells is crucial for mapping functional specificity of proteins and studying related diseases. Currently, research about single-cell protein location is still in its infancy, and most studies and databases do not annotate proteins at the cell level. For example, in the human protein atlas database, an immunofluorescence image stained for a particular protein shows multiple cells, but the subcellular location annotation is for the whole image, ignoring intercellular difference. In this study, we used large-scale immunofluorescence images and image-level subcellular locations to develop a deep-learning-based pipeline that could accurately recognize protein localizations in single cells. The pipeline consisted of two deep learning models, i.e. an image-based model and a cell-based model. The former used a multi-instance learning framework to comprehensively model protein distribution in multiple cells in each image, and could give both image-level and cell-level predictions. The latter firstly used clustering and heuristics algorithms to assign pseudo-labels of subcellular locations to the segmented cell images, and then used the pseudo-labels to train a classification model. Finally, the image-based model was fused with the cell-based model at the decision level to obtain the final ensemble model for single-cell prediction. Our experimental results showed that the ensemble model could achieve higher accuracy and robustness on independent test sets than state-of-the-art methods.

A bioimage informatics platform for high-throughput embryo phenotyping.

High-throughput phenotyping is a cornerstone of numerous functional genomics projects. In recent years, imaging screens have become increasingly important in understanding gene-phenotype relationships in studies of cells, tissues and whole organisms. Three-dimensional (3D) imaging has risen to prominence in the field of developmental biology for its ability to capture whole embryo morphology and gene expression, as exemplified by the International Mouse Phenotyping Consortium (IMPC). Large volumes of image data are being acquired by multiple institutions around the world that encompass a range of modalities, proprietary software and metadata. To facilitate robust downstream analysis, images and metadata must be standardized to account for these differences. As an open scientific enterprise, making the data readily accessible is essential so that members of biomedical and clinical research communities can study the images for themselves without the need for highly specialized software or technical expertise. In this article, we present a platform of software tools that facilitate the upload, analysis and dissemination of 3D images for the IMPC. Over 750 reconstructions from 80 embryonic lethal and subviable lines have been captured to date, all of which are openly accessible at mousephenotype.org. Although designed for the IMPC, all software is available under an open-source licence for others to use and develop further. Ongoing developments aim to increase throughput and improve the analysis and dissemination of image data. Furthermore, we aim to ensure that images are searchable so that users can locate relevant images associated with genes, phenotypes or human diseases of interest.

An automated quantitative image analysis tool for the identification of microtubule patterns in plants.

High throughput confocal imaging poses challenges in the computational image analysis of complex subcellular structures such as the microtubule cytoskeleton. Here, we developed CellArchitect, an automated image analysis tool that quantifies changes to subcellular patterns illustrated by microtubule markers in plants. We screened microtubule-targeted herbicides and demonstrate that high throughput confocal imaging with integrated image analysis by CellArchitect can distinguish effects induced by the known herbicides indaziflam and trifluralin. The same platform was used to examine 6 other compounds with herbicidal activity, and at least 3 different effects induced by these compounds were profiled. We further show that CellArchitect can detect subcellular patterns tagged by actin and endoplasmic reticulum markers. Thus, the platform developed here can be used to automate image analysis of complex subcellular patterns for purposes such as herbicide discovery and mode of action characterisation. The capacity to use this tool to quantitatively characterize cellular responses lends itself to application across many areas of biology.

MIC_Locator: a novel image-based protein subcellular location multi-label prediction model based on multi-scale monogenic signal representation and intensity encoding strategy.

BACKGROUND: Protein subcellular localization plays a crucial role in understanding cell function. Proteins need to be in the right place at the right time, and combine with the corresponding molecules to fulfill their functions. Furthermore, prediction of protein subcellular location not only should be a guiding role in drug design and development due to potential molecular targets but also be an essential role in genome annotation. Taking the current status of image-based protein subcellular localization as an example, there are three common drawbacks, i.e., obsolete datasets without updating label information, stereotypical feature descriptor on spatial domain or grey level, and single-function prediction algorithm's limited capacity of handling single-label database. RESULTS: In this paper, a novel human protein subcellular localization prediction model MIC_Locator is proposed. Firstly, the latest datasets are collected and collated as our benchmark dataset instead of obsolete data while training prediction model. Secondly, Fourier transformation, Riesz transformation, Log-Gabor filter and intensity coding strategy are employed to obtain frequency feature based on three components of monogenic signal with different frequency scales. Thirdly, a chained prediction model is proposed to handle multi-label instead of single-label datasets. The experiment results showed that the MIC_Locator can achieve 60.56% subset accuracy and outperform the existing majority of prediction models, and the frequency feature and intensity coding strategy can be conducive to improving the classification accuracy. CONCLUSIONS: Our results demonstrate that the frequency feature is more beneficial for improving the performance of model compared to features extracted from spatial domain, and the MIC_Locator proposed in this paper can speed up validation of protein annotation, knowledge of protein function and proteomics research.

Image analysis of neural stem cell division patterns in the zebrafish brain.

Proliferating stem cells in the adult body are the source of constant regeneration. In the brain, neural stem cells (NSCs) divide to maintain the stem cell population and generate neural progenitor cells that eventually replenish mature neurons and glial cells. How much spatial coordination of NSC division and differentiation is present in a functional brain is an open question. To quantify the patterns of stem cell divisions, one has to (i) identify the pool of NSCs that have the ability to divide, (ii) determine NSCs that divide within a given time window, and (iii) analyze the degree of spatial coordination. Here, we present a bioimage informatics pipeline that automatically identifies GFP expressing NSCs in three-dimensional image stacks of zebrafish brain from whole-mount preparations. We exploit the fact that NSCs in the zebrafish hemispheres are located on a two-dimensional surface and identify between 1,500 and 2,500 NSCs in six brain hemispheres. We then determine the position of dividing NSCs in the hemisphere by EdU incorporation into cells undergoing S-phase and calculate all pairwise NSC distances with three alternative metrics. Finally, we fit a probabilistic model to the observed spatial patterns that accounts for the non-homogeneous distribution of NSCs. We find a weak positive coordination between dividing NSCs irrespective of the metric and conclude that neither strong inhibitory nor strong attractive signals drive NSC divisions in the adult zebrafish brain. © 2017 International Society for Advancement of Cytometry.

An Overview of data science uses in bioimage informatics.

This review aims at providing a practical overview of the use of statistical features and associated data science methods in bioimage informatics. To achieve a quantitative link between images and biological concepts, one typically replaces an object coming from an image (a segmented cell or intracellular object, a pattern of expression or localisation, even a whole image) by a vector of numbers. They range from carefully crafted biologically relevant measurements to features learnt through deep neural networks. This replacement allows for the use of practical algorithms for visualisation, comparison and inference, such as the ones from machine learning or multivariate statistics. While originating mainly, for biology, in high content screening, those methods are integral to the use of data science for the quantitative analysis of microscopy images to gain biological insight, and they are sure to gather more interest as the need to make sense of the increasing amount of acquired imaging data grows more pressing.

Biologically constrained optimization based cell membrane segmentation in C. elegans embryos.

BACKGROUND: Recent advances in bioimaging and automated analysis methods have enabled the large-scale systematic analysis of cellular dynamics during the embryonic development of Caenorhabditis elegans. Most of these analyses have focused on cell lineage tracing rather than cell shape dynamics. Cell shape analysis requires cell membrane segmentation, which is challenging because of insufficient resolution and image quality. This problem is currently solved by complicated segmentation methods requiring laborious and time consuming parameter adjustments. RESULTS: Our new framework BCOMS (Biologically Constrained Optimization based cell Membrane Segmentation) automates the extraction of the cell shape of C. elegans embryos. Both the segmentation and evaluation processes are automated. To automate the evaluation, we solve an optimization problem under biological constraints. The performance of BCOMS was validated against a manually created ground truth of the 24-cell stage embryo. The average deviation of 25 cell shape features was 5.6%. The deviation was mainly caused by membranes parallel to the focal planes, which either contact the surfaces of adjacent cells or make no contact with other cells. Because segmentation of these membranes was difficult even by manual inspection, the automated segmentation was sufficiently accurate for cell shape analysis. As the number of manually created ground truths is necessarily limited, we compared the segmentation results between two adjacent time points. Across all cells and all cell cycles, the average deviation of the 25 cell shape features was 4.3%, smaller than that between the automated segmentation result and ground truth. CONCLUSIONS: BCOMS automated the accurate extraction of cell shapes in developing C. elegans embryos. By replacing image processing parameters with easily adjustable biological constraints, BCOMS provides a user-friendly framework. The framework is also applicable to other model organisms. Creating the biological constraints is a critical step requiring collaboration between an experimentalist and a software developer.

Amoeboid movement in protozoan pathogens.

Entamoeba histolytica, the causative agent of amoebiasis, is a protozoan parasite characterised by its amoeboid motility, which is essential to its survival and invasion of the human host. Elucidating the molecular mechanisms leading to invasion of human tissues by E. histolytica requires a quantitative understanding of how its cytoskeleton deforms and tailors its mode of migration to the local microenvironment. Here we review the wide range of methods available to extract biophysical information from amoeboid cells, from interventional techniques to computational modelling approaches, and discuss how recent developments in bioimaging and bioimage informatics can complement our understanding of cellular morphodynamics at the intracellular level.

Machine learning in cell biology - teaching computers to recognize phenotypes.

Recent advances in microscope automation provide new opportunities for high-throughput cell biology, such as image-based screening. High-complex image analysis tasks often make the implementation of static and predefined processing rules a cumbersome effort. Machine-learning methods, instead, seek to use intrinsic data structure, as well as the expert annotations of biologists to infer models that can be used to solve versatile data analysis tasks. Here, we explain how machine-learning methods work and what needs to be considered for their successful application in cell biology. We outline how microscopy images can be converted into a data representation suitable for machine learning, and then introduce various state-of-the-art machine-learning algorithms, highlighting recent applications in image-based screening. Our Commentary aims to provide the biologist with a guide to the application of machine learning to microscopy assays and we therefore include extensive discussion on how to optimize experimental workflow as well as the data analysis pipeline.

On comparing heterogeneity across biomarkers.

Microscopy reveals complex patterns of cellular heterogeneity that can be biologically informative. However, a limitation of microscopy is that only a small number of biomarkers can typically be monitored simultaneously. Thus, a natural question is whether additional biomarkers provide a deeper characterization of the distribution of cellular states in a population. How much information about a cell's phenotypic state in one biomarker is gained by knowing its state in another biomarker? Here, we describe a framework for comparing phenotypic states across biomarkers. Our approach overcomes the current limitation of microscopy by not requiring costaining biomarkers on the same cells; instead, we require staining of biomarkers (possibly separately) on a common collection of phenotypically diverse cell lines. We evaluate our approach on two image datasets: 33 oncogenically diverse lung cancer cell lines stained with 7 biomarkers, and 49 less diverse subclones of one lung cancer cell line stained with 12 biomarkers. We first validate our method by comparing it to the "gold standard" of costaining. We then apply our approach to all pairs of biomarkers and use it to identify biomarkers that yield similar patterns of heterogeneity. The results presented in this work suggest that many biomarkers provide redundant information about heterogeneity. Thus, our approach provides a practical guide for selecting independently informative biomarkers and, more generally, will yield insights into both the connectivity of biological networks and the complexity of the state space of biological systems.

pyHiM: a new open-source, multi-platform software package for spatial genomics based on multiplexed DNA-FISH imaging.

Genome-wide ensemble sequencing methods improved our understanding of chromatin organization in eukaryotes but lack the ability to capture single-cell heterogeneity and spatial organization. To overcome these limitations, new imaging-based methods have emerged, giving rise to the field of spatial genomics. Here, we present pyHiM, a user-friendly python toolbox specifically designed for the analysis of multiplexed DNA-FISH data and the reconstruction of chromatin traces in individual cells. pyHiM employs a modular architecture, allowing independent execution of analysis steps and customization according to sample specificity and computing resources. pyHiM aims to facilitate the democratization and standardization of spatial genomics analysis.

Automated identification of protein expression intensity and classification of protein cellular locations in mouse brain regions from immunofluorescence images.

Knowledge of protein expression in mammalian brains at regional and cellular levels can facilitate understanding of protein functions and associated diseases. As the mouse brain is a typical mammalian brain considering cell type and structure, several studies have been conducted to analyze protein expression in mouse brains. However, labeling protein expression using biotechnology is costly and time-consuming. Therefore, automated models that can accurately recognize protein expression are needed. Here, we constructed machine learning models to automatically annotate the protein expression intensity and cellular location in different mouse brain regions from immunofluorescence images. The brain regions and sub-regions were segmented through learning image features using an autoencoder and then performing K-means clustering and registration to align with the anatomical references. The protein expression intensities for those segmented structures were computed on the basis of the statistics of the image pixels, and patch-based weakly supervised methods and multi-instance learning were used to classify the cellular locations. Results demonstrated that the models achieved high accuracy in the expression intensity estimation, and the F1 score of the cellular location prediction was 74.5%. This work established an automated pipeline for analyzing mouse brain images and provided a foundation for further study of protein expression and functions.

Systematic analysis of cell morphodynamics in C. elegans early embryogenesis.

The invariant cell lineage of Caenorhabditis elegans allows unambiguous assignment of the identity for each cell, which offers a unique opportunity to study developmental dynamics such as the timing of cell division, dynamics of gene expression, and cell fate decisions at single-cell resolution. However, little is known about cell morphodynamics, including the extent to which they are variable between individuals, mainly due to the lack of sufficient amount and quality of quantified data. In this study, we systematically quantified the cell morphodynamics in 52 C. elegans embryos from the two-cell stage to mid-gastrulation at the high spatiotemporal resolution, 0.5 µm thickness of optical sections, and 30-second intervals of recordings. Our data allowed systematic analyses of the morphological features. We analyzed sphericity dynamics and found a significant increase at the end of metaphase in every cell, indicating the universality of the mitotic cell rounding. Concomitant with the rounding, the volume also increased in most but not all cells, suggesting less universality of the mitotic swelling. Combining all features showed that cell morphodynamics was unique for each cell type. The cells before the onset of gastrulation could be distinguished from all the other cell types. Quantification of reproducibility in cell-cell contact revealed that variability in division timings and cell arrangements produced variability in contacts between the embryos. However, the area of such contacts occupied less than 5% of the total area, suggesting the high reproducibility of spatial occupancies and adjacency relationships of the cells. By comparing the morphodynamics of identical cells between the embryos, we observed diversity in the variability between cells and found it was determined by multiple factors, including cell lineage, cell generation, and cell-cell contact. We compared the variabilities of cell morphodynamics and cell-cell contacts with those in ascidian Phallusia mammillata embryos. The variabilities were larger in C. elegans, despite smaller differences in embryo size and number of cells at each developmental stage.

Automated quantification of dopaminergic immunostained neurons in substantia nigra using freely available software.

Computerized techniques for image analysis are critical for progress in cell biology. The complexity of the data in current methods eliminates the need for manual image analysis and usually requires the application of multiple algorithms sequentially to the images. Our aim was to develop a software for immunohistochemical analysis of brain dopaminergic neurons combining several computational approaches to automatically analyze and quantify their number in the substantia nigra after a neurotoxic injury. For this purpose, we used a Parkinson's disease animal model to test our application. The dopaminergic neurotoxin, 6-hydroxydopamine, was administered in adult male rats to damage dopaminergic neurons in substantia nigra and to induce hemiparkinsonism. The lesion was corroborated by behavioral evaluation in response to apomorphine and amphetamine. The animals were euthanized and their brains processed for tyrosine hydroxylase immunohistochemistry for dopamine neuron identification. Neurons positive for tyrosine hydroxylase were evaluated in substantia nigra by light microscopy. The images were used to show quantification applicability. To test our software counting accuracy and validity, automatic dopamine neuron number was correlated with the data obtained by three independent observers. Several parameters were used to depict neuronal function in dataset images from control and lesioned brains. In conclusion, we could perform an automated quantification of dopaminergic neurons and corroborate the validity and accuracy of a freely available software.

GeNePy3D: a quantitative geometry python toolbox for bioimaging.

The advent of large-scale fluorescence and electronic microscopy techniques along with maturing image analysis is giving life sciences a deluge of geometrical objects in 2D/3D(+t) to deal with. These objects take the form of large scale, localised, precise, single cell, quantitative data such as cells' positions, shapes, trajectories or lineages, axon traces in whole brains atlases or varied intracellular protein localisations, often in multiple experimental conditions. The data mining of those geometrical objects requires a variety of mathematical and computational tools of diverse accessibility and complexity. Here we present a new Python library for quantitative 3D geometry called GeNePy3D which helps handle and mine information and knowledge from geometric data, providing a unified application programming interface (API) to methods from several domains including computational geometry, scale space methods or spatial statistics. By framing this library as generically as possible, and by linking it to as many state-of-the-art reference algorithms and projects as needed, we help render those often specialist methods accessible to a larger community. We exemplify the usefulness of the  GeNePy3D toolbox by re-analysing a recently published whole-brain zebrafish neuronal atlas, with other applications and examples available online. Along with an open source, documented and exemplified code, we release reusable containers to allow for convenient and wide usability and increased reproducibility.

ACDC: Automated Cell Detection and Counting for Time-Lapse Fluorescence Microscopy.

Advances in microscopy imaging technologies have enabled the visualization of live-cell dynamic processes using time-lapse microscopy imaging. However, modern methods exhibit several limitations related to the training phases and to time constraints, hindering their application in the laboratory practice. In this work, we present a novel method, named Automated Cell Detection and Counting (ACDC), designed for activity detection of fluorescent labeled cell nuclei in time-lapse microscopy. ACDC overcomes the limitations of the literature methods, by first applying bilateral filtering on the original image to smooth the input cell images while preserving edge sharpness, and then by exploiting the watershed transform and morphological filtering. Moreover, ACDC represents a feasible solution for the laboratory practice, as it can leverage multi-core architectures in computer clusters to efficiently handle large-scale imaging datasets. Indeed, our Parent-Workers implementation of ACDC allows to obtain up to a 3.7× speed-up compared to the sequential counterpart. ACDC was tested on two distinct cell imaging datasets to assess its accuracy and effectiveness on images with different characteristics. We achieved an accurate cell-count and nuclei segmentation without relying on large-scale annotated datasets, a result confirmed by the average Dice Similarity Coefficients of 76.84 and 88.64 and the Pearson coefficients of 0.99 and 0.96, calculated against the manual cell counting, on the two tested datasets.

On the objectivity, reliability, and validity of deep learning enabled bioimage analyses.

Bioimage analysis of fluorescent labels is widely used in the life sciences. Recent advances in deep learning (DL) allow automating time-consuming manual image analysis processes based on annotated training data. However, manual annotation of fluorescent features with a low signal-to-noise ratio is somewhat subjective. Training DL models on subjective annotations may be instable or yield biased models. In turn, these models may be unable to reliably detect biological effects. An analysis pipeline integrating data annotation, ground truth estimation, and model training can mitigate this risk. To evaluate this integrated process, we compared different DL-based analysis approaches. With data from two model organisms (mice, zebrafish) and five laboratories, we show that ground truth estimation from multiple human annotators helps to establish objectivity in fluorescent feature annotations. Furthermore, ensembles of multiple models trained on the estimated ground truth establish reliability and validity. Our research provides guidelines for reproducible DL-based bioimage analyses.

Research in biology generates many image datasets, mostly from microscopy. These images have to be analyzed, and much of this analysis relies on a human expert looking at the images and manually annotating features. Image datasets are often large, and human annotation can be subjective, so automating image analysis is highly desirable. This is where machine learning algorithms, such as deep learning, have proven to be useful. In order for deep learning algorithms to work first they have to be 'trained'. Deep learning algorithms are trained by being given a training dataset that has been annotated by human experts. The algorithms extract the relevant features to look out for from this training dataset and can then look for these features in other image data. However, it is also worth noting that because these models try to mimic the annotation behavior presented to them during training as well as possible, they can sometimes also mimic an expert's subjectivity when annotating data. Segebarth, Griebel et al. asked whether this was the case, whether it had an impact on the outcome of the image data analysis, and whether it was possible to avoid this problem when using deep learning for imaging dataset analysis. For this research, Segebarth, Griebel et al. used microscopy images of mouse brain sections, where a protein called cFOS had been labeled with a fluorescent tag. This protein typically controls the rate at which DNA information is copied into RNA, leading to the production of proteins. Its activity can be influenced experimentally by testing the behaviors of mice. Thus, this experimental manipulation can be used to evaluate the results of deep learning-based image analyses. First, the fluorescent images were interpreted manually by a group of human experts. Then, their results were used to train a large variety of deep learning models. Models were trained either on the results of an individual expert or on the results pooled from all experts to come up with a consensus model, a deep learning model that learned from the personal annotation preferences of all experts. This made it possible to test whether training a model on multiple experts reduces the risk of subjectivity. As the training of deep learning models is random, Segebarth, Griebel et al. also tested whether combining the predictions from multiple models in a so-called model ensemble improves the consistency of the analyses. For evaluation, the annotations of the deep learning models were compared to those of the human experts, to ensure that the results were not influenced by the subjective behavior of one person. The results of all bioimage annotations were finally compared to the experimental results from analyzing the mice's behaviors in order to check whether the models were able to find the behavioral effect on cFOS. Segebarth, Griebel et al. concluded that combining the expert knowledge of multiple experts reduces the subjectivity of bioimage annotation by deep learning algorithms. Combining such consensus information in a group of deep learning models improves the quality of bioimage analysis, so that the results are reliable, transparent and less subjective.

Tackling the challenges of bioimage analysis.

Using multiple human annotators and ensembles of trained networks can improve the performance of deep-learning methods in research.

Rapid discrimination of fungal species by the colony fingerprinting.

The contamination of foods and beverages by fungi is a severe health hazard. The rapid identification of fungi species in contaminated goods is important to avoid further contamination. To this end, we developed a fungal discrimination method based on the bioimage informatics approach of colony fingerprinting. This method involves imaging and visualizing microbial colonies (referred to as colony fingerprints) using a lens-less imaging system. Subsequently, the quantitative image features were extracted as discriminative parameters and subjected to analysis using machine learning approaches. Colony fingerprinting has been previously found to be a promising approach to discriminate bacteria. In the present proof-of-concept study, we tested whether this method is also useful for fungal discrimination. As a result, 5 fungi belonging to the Aspergillus, Penicilium, Eurotium, Alternaria, and Fusarium genera were successfully discriminated based on the extracted parameters, including the number of hyphae and their branches, and their intensity distributions on the images. The discrimination of 6 closely-related Aspergillus spp. was also demonstrated using additional parameters. The cultivation time required to generate the fungal colonies with a sufficient size for colony fingerprinting was less than 48 h, shorter than those for other discrimination methods, including MALDI-TOF-MS. In addition, colony fingerprinting did not require any cumbersome pre-treatment steps prior to discrimination. Colony fingerprinting is promising for the rapid and easy discrimination of fungi for use in the ensuring the safety of food manufacturing.

A Novel Methodology for Characterizing Cell Subpopulations in Automated Time-lapse Microscopy.

Time-lapse imaging of cell colonies in microfluidic chambers provides time series of bioimages, i.e., biomovies. They show the behavior of cells over time under controlled conditions. One of the main remaining bottlenecks in this area of research is the analysis of experimental data and the extraction of cell growth characteristics, such as lineage information. The extraction of the cell line by human observers is time-consuming and error-prone. Previously proposed methods often fail because of their reliance on the accurate detection of a single cell, which is not possible for high density, high diversity of cell shapes and numbers, and high-resolution images with high noise. Our task is to characterize subpopulations in biomovies. In order to shift the analysis of the data from individual cell level to cellular groups with similar fluorescence or even subpopulations, we propose to represent the cells by two new abstractions: the particle and the patch. We use a three-step framework: preprocessing, particle tracking, and construction of the patch lineage. First, preprocessing improves the signal-to-noise ratio and spatially aligns the biomovie frames. Second, cell sampling is performed by assuming particles, which represent a part of a cell, cell or group of contiguous cells in space. Particle analysis includes the following: particle tracking, trajectory linking, filtering, and color information, respectively. Particle tracking consists of following the spatiotemporal position of a particle and gives rise to coherent particle trajectories over time. Typical tracking problems may occur (e.g., appearance or disappearance of cells, spurious artifacts). They are effectively processed using trajectory linking and filtering. Third, the construction of the patch lineage consists in joining particle trajectories that share common attributes (i.e., proximity and fluorescence intensity) and feature common ancestry. This step is based on patch finding, patching trajectory propagation, patch splitting, and patch merging. The main idea is to group together the trajectories of particles in order to gain spatial coherence. The final result of CYCASP is the complete graph of the patch lineage. Finally, the graph encodes the temporal and spatial coherence of the development of cellular colonies. We present results showing a computation time of less than 5 min for biomovies and simulated films. The method, presented here, allowed for the separation of colonies into subpopulations and allowed us to interpret the growth of colonies in a timely manner.