Efficient Bayesian inference for mechanistic modelling with high-throughput data.

Bayesian methods are routinely used to combine experimental data with detailed mathematical models to obtain insights into physical phenomena. However, the computational cost of Bayesian computation with detailed models has been a notorious problem. Moreover, while high-throughput data presents opportunities to calibrate sophisticated models, comparing large amounts of data with model simulations quickly becomes computationally prohibitive. Inspired by the method of Stochastic Gradient Descent, we propose a minibatch approach to approximate Bayesian computation. Through a case study of a high-throughput imaging scratch assay experiment, we show that reliable inference can be performed at a fraction of the computational cost of a traditional Bayesian inference scheme. By applying a detailed mathematical model of single cell motility, proliferation and death to a data set of 118 gene knockdowns, we characterise functional subgroups of gene knockdowns, each displaying its own typical combination of local cell density-dependent and -independent motility and proliferation patterns. By comparing these patterns to experimental measurements of cell counts and wound closure, we find that density-dependent interactions play a crucial role in the process of wound healing.

KCML: a machine-learning framework for inference of multi-scale gene functions from genetic perturbation screens.

Characterising context-dependent gene functions is crucial for understanding the genetic bases of health and disease. To date, inference of gene functions from large-scale genetic perturbation screens is based on ad hoc analysis pipelines involving unsupervised clustering and functional enrichment. We present Knowledge- and Context-driven Machine Learning (KCML), a framework that systematically predicts multiple context-specific functions for a given gene based on the similarity of its perturbation phenotype to those with known function. As a proof of concept, we test KCML on three datasets describing phenotypes at the molecular, cellular and population levels and show that it outperforms traditional analysis pipelines. In particular, KCML identified an abnormal multicellular organisation phenotype associated with the depletion of olfactory receptors, and TGFß and WNT signalling genes in colorectal cancer cells. We validate these predictions in colorectal cancer patients and show that olfactory receptors expression is predictive of worse patient outcomes. These results highlight KCML as a systematic framework for discovering novel scale-crossing and context-dependent gene functions. KCML is highly generalisable and applicable to various large-scale genetic perturbation screens.

Identification of clinically predictive metagenes that encode components of a network coupling cell shape to transcription by image-omics.

The associations between clinical phenotypes (tumor grade, survival) and cell phenotypes, such as shape, signaling activity, and gene expression, are the basis for cancer pathology, but the mechanisms explaining these relationships are not always clear. The generation of large data sets containing information regarding cell phenotypes and clinical data provides an opportunity to describe these mechanisms. Here, we develop an image-omics approach to integrate quantitative cell imaging data, gene expression, and protein-protein interaction data to systematically describe a "shape-gene network" that couples specific aspects of breast cancer cell shape to signaling and transcriptional events. The actions of this network converge on NF-κB, and support the idea that NF-κB is responsive to mechanical stimuli. By integrating RNAi screening data, we identify components of the shape-gene network that regulate NF-κB in response to cell shape changes. This network was also used to generate metagene models that predict NF-κB activity and aspects of morphology such as cell area, elongation, and protrusiveness. Critically, these metagenes also have predictive value regarding tumor grade and patient outcomes. Taken together, these data strongly suggest that changes in cell shape, driven by gene expression and/or mechanical forces, can promote breast cancer progression by modulating NF-κB activation. Our findings highlight the importance of integrating phenotypic data at the molecular level (signaling and gene expression) with those at the cellular and tissue levels to better understand breast cancer oncogenesis.

Visualizing quantitative microscopy data: History and challenges.

Data visualization is a fundamental aspect of science. In the context of microscopy-based studies, visualization typically involves presentation of the images themselves. However, data visualization is challenging when microscopy experiments entail imaging of millions of cells, and complex cellular phenotypes are quantified in a high-content manner. Most well-established visualization tools are inappropriate for displaying high-content data, which has driven the development of new visualization methodology. In this review, we discuss how data has been visualized in both classical and high-content microscopy studies; as well as the advantages, and disadvantages, of different visualization methods.

Analysis of live cell images: Methods, tools and opportunities.

Advances in optical microscopy, biosensors and cell culturing technologies have transformed live cell imaging. Thanks to these advances live cell imaging plays an increasingly important role in basic biology research as well as at all stages of drug development. Image analysis methods are needed to extract quantitative information from these vast and complex data sets. The aim of this review is to provide an overview of available image analysis methods for live cell imaging, in particular required preprocessing image segmentation, cell tracking and data visualisation methods. The potential opportunities recent advances in machine learning, especially deep learning, and computer vision provide are being discussed. This review includes overview of the different available software packages and toolkits.

Microenvironmental Heterogeneity Parallels Breast Cancer Progression: A Histology-Genomic Integration Analysis.

BACKGROUND: The intra-tumor diversity of cancer cells is under intense investigation; however, little is known about the heterogeneity of the tumor microenvironment that is key to cancer progression and evolution. We aimed to assess the degree of microenvironmental heterogeneity in breast cancer and correlate this with genomic and clinical parameters. METHODS AND FINDINGS: We developed a quantitative measure of microenvironmental heterogeneity along three spatial dimensions (3-D) in solid tumors, termed the tumor ecosystem diversity index (EDI), using fully automated histology image analysis coupled with statistical measures commonly used in ecology. This measure was compared with disease-specific survival, key mutations, genome-wide copy number, and expression profiling data in a retrospective study of 510 breast cancer patients as a test set and 516 breast cancer patients as an independent validation set. In high-grade (grade 3) breast cancers, we uncovered a striking link between high microenvironmental heterogeneity measured by EDI and a poor prognosis that cannot be explained by tumor size, genomics, or any other data types. However, this association was not observed in low-grade (grade 1 and 2) breast cancers. The prognostic value of EDI was superior to known prognostic factors and was enhanced with the addition of TP53 mutation status (multivariate analysis test set, p = 9 × 10-4, hazard ratio = 1.47, 95% CI 1.17-1.84; validation set, p = 0.0011, hazard ratio = 1.78, 95% CI 1.26-2.52). Integration with genome-wide profiling data identified losses of specific genes on 4p14 and 5q13 that were enriched in grade 3 tumors with high microenvironmental diversity that also substratified patients into poor prognostic groups. Limitations of this study include the number of cell types included in the model, that EDI has prognostic value only in grade 3 tumors, and that our spatial heterogeneity measure was dependent on spatial scale and tumor size. CONCLUSIONS: To our knowledge, this is the first study to couple unbiased measures of microenvironmental heterogeneity with genomic alterations to predict breast cancer clinical outcome. We propose a clinically relevant role of microenvironmental heterogeneity for advanced breast tumors, and highlight that ecological statistics can be translated into medical advances for identifying a new type of biomarker and, furthermore, for understanding the synergistic interplay of microenvironmental heterogeneity with genomic alterations in cancer cells.

Cell shape and the microenvironment regulate nuclear translocation of NF-κB in breast epithelial and tumor cells.

Although a great deal is known about the signaling events that promote nuclear translocation of NF-κB, how cellular biophysics and the microenvironment might regulate the dynamics of this pathway is poorly understood. In this study, we used high-content image analysis and Bayesian network modeling to ask whether cell shape and context features influence NF-κB activation using the inherent variability present in unperturbed populations of breast tumor and non-tumor cell lines. Cell­cell contact, cell and nuclear area, and protrusiveness all contributed to variability in NF-κB localization in the absence and presence of TNFα. Higher levels of nuclear NF-κB were associated with mesenchymal-like versus epithelial-like morphologies, and RhoA-ROCK-myosin II signaling was critical for mediating shape-based differences in NF-κB localization and oscillations. Thus, mechanical factors such as cell shape and the microenvironment can influence NF-κB signaling and may in part explain how different phenotypic outcomes can arise from the same chemical cues.

How cells explore shape space: a quantitative statistical perspective of cellular morphogenesis.

Through statistical analysis of datasets describing single cell shape following systematic gene depletion, we have found that the morphological landscapes explored by cells are composed of a small number of attractor states. We propose that the topology of these landscapes is in large part determined by cell-intrinsic factors, such as biophysical constraints on cytoskeletal organization, and reflects different stable signaling and/or transcriptional states. Cell-extrinsic factors act to determine how cells explore these landscapes, and the topology of the landscapes themselves. Informational stimuli primarily drive transitions between stable states by engaging signaling networks, while mechanical stimuli tune, or even radically alter, the topology of these landscapes. As environments fluctuate, the topology of morphological landscapes explored by cells dynamically adapts to these fluctuations. Finally we hypothesize how complex cellular and tissue morphologies can be generated from a limited number of simple cell shapes.

Evolution and impact of high content imaging.

The field of high content imaging has steadily evolved and expanded substantially across many industry and academic research institutions since it was first described in the early 1990's. High content imaging refers to the automated acquisition and analysis of microscopic images from a variety of biological sample types. Integration of high content imaging microscopes with multiwell plate handling robotics enables high content imaging to be performed at scale and support medium- to high-throughput screening of pharmacological, genetic and diverse environmental perturbations upon complex biological systems ranging from 2D cell cultures to 3D tissue organoids to small model organisms. In this perspective article the authors provide a collective view on the following key discussion points relevant to the evolution of high content imaging: • Evolution and impact of high content imaging: An academic perspective • Evolution and impact of high content imaging: An industry perspective • Evolution of high content image analysis • Evolution of high content data analysis pipelines towards multiparametric and phenotypic profiling applications • The role of data integration and multiomics • The role and evolution of image data repositories and sharing standards • Future perspective of high content imaging hardware and software.

Decoding mTOR signalling heterogeneity in the tumour microenvironment using multiplexed imaging and graph convolutional networks.

Evaluating the contribution of the tumour microenvironment (TME) in tumour progression has proven a complex challenge due to the intricate interactions within the TME. Multiplexed imaging is an emerging technology that allows concurrent assessment of multiple of these components simultaneously. Here we utilise a highly multiplexed dataset of 61 markers across 746 colorectal tumours to investigate how complex mTOR signalling in different tissue compartments influences patient prognosis. We found that the signalling of mTOR pathway can have heterogeneous activation patterns in tumour and immune compartments which correlate with patient prognosis. Using graph neural networks, we determined the most predictive features of mTOR activity in immune cells and identified relevant cellular subpopulations. We validated our observations using spatial transcriptomics data analysis in an independent patient cohort. Our work provides a framework for studying complex cell signalling and reveals important insights for developing mTOR-based therapies.

Malignant Mesothelioma subtyping via sampling driven multiple instance prediction on tissue image and cell morphology data.

Malignant Mesothelioma is a difficult to diagnose and highly lethal cancer usually associated with asbestos exposure. It can be broadly classified into three subtypes: Epithelioid, Sarcomatoid, and a hybrid Biphasic subtype in which significant components of both of the previous subtypes are present. Early diagnosis and identification of the subtype informs treatment and can help improve patient outcome. However, the subtyping of malignant mesothelioma, and specifically the recognition of transitional features from routine histology slides has a high level of inter-observer variability. In this work, we propose an end-to-end multiple instance learning (MIL) approach for malignant mesothelioma subtyping. This uses an adaptive instance-based sampling scheme for training deep convolutional neural networks on bags of image patches that allows learning on a wider range of relevant instances compared to max or top-N based MIL approaches. We also investigate augmenting the instance representation to include aggregate cellular morphology features from cell segmentation. The proposed MIL approach enables identification of malignant mesothelial subtypes of specific tissue regions. From this a continuous characterisation of a sample according to predominance of sarcomatoid vs epithelioid regions is possible, thus avoiding the arbitrary and highly subjective categorisation by currently used subtypes. Instance scoring also enables studying tumor heterogeneity and identifying patterns associated with different subtypes. We have evaluated the proposed method on a dataset of 234 tissue micro-array cores with an AUROC of 0.89±0.05 for this task. The dataset and developed methodology is available for the community at: https://github.com/measty/PINS.

MesoGraph: Automatic profiling of mesothelioma subtypes from histological images.

Mesothelioma is classified into three histological subtypes, epithelioid, sarcomatoid, and biphasic, according to the relative proportions of epithelioid and sarcomatoid tumor cells present. Current guidelines recommend that the sarcomatoid component of each mesothelioma is quantified, as a higher percentage of sarcomatoid pattern in biphasic mesothelioma shows poorer prognosis. In this work, we develop a dual-task graph neural network (GNN) architecture with ranking loss to learn a model capable of scoring regions of tissue down to cellular resolution. This allows quantitative profiling of a tumor sample according to the aggregate sarcomatoid association score. Tissue is represented by a cell graph with both cell-level morphological and regional features. We use an external multicentric test set from Mesobank, on which we demonstrate the predictive performance of our model. We additionally validate our model predictions through an analysis of the typical morphological features of cells according to their predicted score.

ShapoGraphy: A User-Friendly Web Application for Creating Bespoke and Intuitive Visualisation of Biomedical Data.

Effective visualisation of quantitative microscopy data is crucial for interpreting and discovering new patterns from complex bioimage data. Existing visualisation approaches, such as bar charts, scatter plots and heat maps, do not accommodate the complexity of visual information present in microscopy data. Here we develop ShapoGraphy, a first of its kind method accompanied by an interactive web-based application for creating customisable quantitative pictorial representations to facilitate the understanding and analysis of image datasets (www.shapography.com). ShapoGraphy enables the user to create a structure of interest as a set of shapes. Each shape can encode different variables that are mapped to the shape dimensions, colours, symbols, or outline. We illustrate the utility of ShapoGraphy using various image data, including high dimensional multiplexed data. Our results show that ShapoGraphy allows a better understanding of cellular phenotypes and relationships between variables. In conclusion, ShapoGraphy supports scientific discovery and communication by providing a rich vocabulary to create engaging and intuitive representations of diverse data types.

A Graph Based Neural Network Approach to Immune Profiling of Multiplexed Tissue Samples.

Multiplexed immunofluorescence provides an un-precedented opportunity for studying specific cell-to-cell and cell microenvironment interactions. We employ graph neural networks to combine features obtained from tissue morphology with measurements of protein expression to profile the tumour microenvironment associated with different tumour stages. Our framework presents a new approach to analysing and processing these complex multi-dimensional datasets that overcomes some of the key challenges in analysing these data and opens up the opportunity to abstract biologically meaningful interactions.

High-Content Imaging to Phenotype Human Primary and iPSC-Derived Cells.

Increasingly powerful microscopy, liquid handling, and computational techniques have enabled cell imaging in high throughput. Microscopy images are quantified using high-content analysis platforms linking object features to cell behavior. This can be attempted on physiologically relevant cell models, including stem cells and primary cells, in complex environments, and conceivably in the presence of perturbations. Recently, substantial focus has been devoted to cell profiling for cell therapy, assays for drug discovery or biomarker identification for clinical decision-making protocols, bringing this wealth of information into translational applications. In this chapter, we focus on two protocols enabling to (1) benchmark human cells, in particular human endothelial cells as a case study and (2) extract cells from blood for follow-up experiments including image-based drug testing. We also present concepts of high-content imaging and discuss the benefits and challenges, with the aim of enabling readers to tailor existing pipelines and bring such approaches closer to translational research and the clinic.

DeepScratch: Single-cell based topological metrics of scratch wound assays.

Changes in tissue architecture and multicellular organisation contribute to many diseases, including cancer and cardiovascular diseases. Scratch wound assay is a commonly used tool that assesses cells' migratory ability based on the area of a wound they cover over a certain time. However, analysis of changes in the organisational patterns formed by migrating cells following genetic or pharmacological perturbations are not well explored in these assays, in part because analysing the resulting imaging data is challenging. Here we present DeepScratch, a neural network that accurately detects the cells in scratch assays based on a heterogeneous set of markers. We demonstrate the utility of DeepScratch by analysing images of more than 232,000 lymphatic endothelial cells. In addition, we propose various topological measures of cell connectivity and local cell density (LCD) to characterise tissue remodelling during wound healing. We show that LCD-based metrics allow classification of CDH5 and CDC42 genetic perturbations that are known to affect cell migration through different biological mechanisms. Such differences cannot be captured when considering only the wound area. Taken together, single-cell detection using DeepScratch allows more detailed investigation of the roles of various genetic components in tissue topology and the biological mechanisms underlying their effects on collective cell migration.

Morphological landscape of endothelial cell networks reveals a functional role of glutamate receptors in angiogenesis.

Angiogenesis plays a key role in several diseases including cancer, ischemic vascular disease, and Alzheimer's disease. Chemical genetic screening of endothelial tube formation provides a robust approach for identifying signalling components that impact microvascular network morphology as well as endothelial cell biology. However, the analysis of the resulting imaging datasets has been limited to a few phenotypic features such as the total tube length or the number of branching points. Here we developed a high content analysis framework for detailed quantification of various aspects of network morphology including network complexity, symmetry and topology. By applying our approach to a high content screen of 1,280 characterised drugs, we found that drugs that result in a similar phenotype share the same mechanism of action or common downstream signalling pathways. Our multiparametric analysis revealed that a group of glutamate receptor antagonists enhances branching and network connectivity. Using an integrative meta-analysis approach, we validated the link between these receptors and angiogenesis. We further found that the expression of these genes is associated with the prognosis of Alzheimer's patients. In conclusion, our work shows that detailed image analysis of complex endothelial phenotypes can reveal new insights into biological mechanisms modulating the morphogenesis of endothelial networks and identify potential therapeutics for angiogenesis-related diseases.

HighVia-A Flexible Live-Cell High-Content Screening Pipeline to Assess Cellular Toxicity.

High-content screening to monitor disease-modifying phenotypes upon small-molecule addition has become an essential component of many drug and target discovery platforms. One of the most common phenotypic approaches, especially in the field of oncology research, is the assessment of cell viability. However, frequently used viability readouts employing metabolic proxy assays based on homogeneous colorimetric/fluorescent reagents are one-dimensional, provide limited information, and can in many cases yield conflicting or difficult-to-interpret results, leading to misinterpretation of data and wasted resources.The resurgence of high-content, phenotypic screening has significantly improved the quality and breadth of cell viability data, which can be obtained at the very earliest stages of drug and target discovery. Here, we describe a relatively inexpensive, high-throughput, high-content, multiparametric, fluorescent imaging protocol using a live-cell method of three fluorescent probes (Hoechst, Yo-Pro-3, and annexin V), that is amenable to the addition of further fluorophores. The protocol enables the accurate description and profiling of multiple cell death mechanisms, including apoptosis and necrosis, as well as accurate determination of compound IC50, and has been validated on a range of high-content imagers and image analysis software. To validate the protocol, we have used a small library of approximately 200 narrow-spectrum kinase inhibitors and clinically approved drugs. This fully developed, easy-to-use pipeline has subsequently been implemented in several academic screening facilities, yielding fast, flexible, and rich cell viability data for a range of early-stage high-throughput drug and target discovery programs.

Identification of molecular targets for the targeted treatment of gastric cancer using dasatinib.

Gastric cancer (GC) remains the third leading cause of cancer-related death despite several improvements in targeted therapy. There is therefore an urgent need to investigate new treatment strategies, including the identification of novel biomarkers for patient stratification. In this study, we evaluated the effect of FDA-approved kinase inhibitors on GC. Through a combination of cell growth, migration and invasion assays, we identified dasatinib as an efficient inhibitor of GC proliferation. Mass-spectrometry-based selectivity profiling and subsequent knockdown experiments identified members of the SRC family of kinases including SRC, FRK, LYN and YES, as well as other kinases such as DDR1, ABL2, SIK2, RIPK2, EPHA2, and EPHB2 as dasatinib targets. The expression levels of the identified kinases were investigated on RNA and protein level in 200 classified tumor samples from patients, who had undergone gastrectomy, but had received no treatment. Levels of FRK, DDR1 and SRC expression on both mRNA and protein level were significantly higher in metastatic patient samples regardless of the tumor stage, while expression levels of SIK2 correlated with tumor size. Collectively, our data suggest dasatinib for treatment of GC based on its unique property, inhibiting a small number of key kinases (SRC, FRK, DDR1 and SIK2), highly expressed in GC patients.

Proteomics profiling of interactome dynamics by colocalisation analysis (COLA).

Localisation and protein function are intimately linked in eukaryotes, as proteins are localised to specific compartments where they come into proximity of other functionally relevant proteins. Significant co-localisation of two proteins can therefore be indicative of their functional association. We here present COLA, a proteomics based strategy coupled with a bioinformatics framework to detect protein-protein co-localisations on a global scale. COLA reveals functional interactions by matching proteins with significant similarity in their subcellular localisation signatures. The rapid nature of COLA allows mapping of interactome dynamics across different conditions or treatments with high precision.