Data-analysis strategies for image-based cell profiling

CLANet: A comprehensive framework for cross-batch cell line identification using brightfield images

Cell line authentication plays a crucial role in the biomedical field, ensuring researchers work with accurately identified cells. Supervised deep learning has made remarkable strides in cell line identification by studying cell morphological features through cell imaging. However, biological batch (bio-batch) effects, a significant issue stemming from the different times at which data is generated, lead to substantial shifts in the underlying data distribution, thus complicating reliable differentiation between cell lines from distinct batch cultures. To address this challenge, we introduce CLANet, a pioneering framework for cross-batch cell line identification using brightfield images, specifically designed to tackle three distinct bio-batch effects. We propose a cell cluster-level selection method to efficiently capture cell density variations, and a self-supervised learning strategy to manage image quality variations, thus producing reliable patch representations. Additionally, we adopt multiple instance learning(MIL) for effective aggregation of instance-level features for cell line identification. Our innovative time-series segment sampling module further enhances MIL's feature-learning capabilities, mitigating biases from varying incubation times across batches. We validate CLANet using data from 32 cell lines across 93 experimental bio-batches from the AstraZeneca Global Cell Bank. Our results show that CLANet outperforms related approaches (e.g. domain adaptation, MIL), demonstrating its effectiveness in addressing bio-batch effects in cell line identification.

PI3K/mTOR inhibition induces tumour microenvironment remodelling and sensitises pS6high uterine leiomyosarcoma to PD-1 blockade

BACKGROUND

Uterine leiomyosarcomas (uLMS) are aggressive tumours with poor prognosis and limited treatment options. Although immune checkpoint blockade (ICB) has proven effective in some 'challenging-to-treat' cancers, clinical trials showed that uLMS do not respond to ICB. Emerging evidence suggests that aberrant PI3K/mTOR signalling can drive resistance to ICB. We therefore explored the relevance of the PI3K/mTOR pathway for ICB treatment in uLMS and explored pharmacological inhibition of this pathway to sensitise these tumours to ICB.

METHODS

We performed an integrated multiomics analysis based on TCGA data to explore the correlation between PI3K/mTOR dysregulation and immune infiltration in 101 LMS. We assessed response to PI3K/mTOR inhibitors in immunodeficient and humanized uLMS patient-derived xenografts (PDXs) by evaluating tumour microenvironment modulation using multiplex immunofluorescence. We explored response to single-agent and a combination of PI3K/mTOR inhibitors with PD-1 blockade in humanized uLMS PDXs. We mapped intratumoural dynamics using single-cell RNA/TCR sequencing of serially collected biopsies.

RESULTS

PI3K/mTOR over-activation (pS6high) associated with lymphocyte depletion and wound healing immune landscapes in (u)LMS, suggesting it contributes to immune evasion. In contrast, PI3K/mTOR inhibition induced profound tumour microenvironment remodelling in an ICB-resistant humanized uLMS PDX model, fostering adaptive anti-tumour immune responses. Indeed, PI3K/mTOR inhibition induced macrophage repolarisation towards an anti-tumourigenic phenotype and increased antigen presentation on dendritic and tumour cells, but also promoted infiltration of PD-1+ T cells displaying an exhausted phenotype. When combined with anti-PD-1, PI3K/mTOR inhibition led to partial or complete tumour responses, whereas no response to single-agent anti-PD-1 was observed. Combination therapy reinvigorated exhausted T cells and induced clonal hyper-expansion of a cytotoxic CD8+ T-cell population supported by a CD4+ Th1 niche.

CONCLUSIONS

Our findings indicate that aberrant PI3K/mTOR pathway activation contributes to immune escape in uLMS and provides a rationale for combining PI3K/mTOR inhibition with ICB for the treatment of this patient population.

An autophagy program that promotes T cell egress from the lymph node controls responses to immune checkpoint blockade

Lymphatic endothelial cells (LECs) of the lymph node (LN) parenchyma orchestrate leukocyte trafficking and peripheral T cell dynamics. T cell responses to immunotherapy largely rely on peripheral T cell recruitment in tumors. Yet, a systematic and molecular understanding of how LECs within the LNs control T cell dynamics under steady-state and tumor-bearing conditions is lacking. Intravital imaging combined with immune phenotyping shows that LEC-specific deletion of the essential autophagy gene Atg5 alters intranodal positioning of lymphocytes and accrues their persistence in the LNs by increasing the availability of the main egress signal sphingosine-1-phosphate. Single-cell RNA sequencing of tumor-draining LNs shows that loss of ATG5 remodels niche-specific LEC phenotypes involved in molecular pathways regulating lymphocyte trafficking and LEC-T cell interactions. Functionally, loss of LEC autophagy prevents recruitment of tumor-infiltrating T and natural killer cells and abrogates response to immunotherapy. Thus, an LEC-autophagy program boosts immune-checkpoint responses by guiding systemic T cell dynamics.

Enhancing the Small-Scale Screenable Biological Space beyond Known Chemogenomics Libraries with Gray Chemical Matter─Compounds with Novel Mechanisms from High-Throughput Screening Profiles

Phenotypic assays have become an established approach to drug discovery. Greater disease relevance is often achieved through cellular models with increased complexity and more detailed readouts, such as gene expression or advanced imaging. However, the intricate nature and cost of these assays impose limitations on their screening capacity, often restricting screens to well-characterized small compound sets such as chemogenomics libraries. Here, we outline a cheminformatics approach to identify a small set of compounds with likely novel mechanisms of action (MoAs), expanding the MoA search space for throughput limited phenotypic assays. Our approach is based on mining existing large-scale, phenotypic high-throughput screening (HTS) data. It enables the identification of chemotypes that exhibit selectivity across multiple cell-based assays, which are characterized by persistent and broad structure activity relationships (SAR). We validate the effectiveness of our approach in broad cellular profiling assays (Cell Painting, DRUG-seq, and Promotor Signature Profiling) and chemical proteomics experiments. These experiments revealed that the compounds behave similarly to known chemogenetic libraries, but with a notable bias toward novel protein targets. To foster collaboration and advance research in this area, we have curated a public set of such compounds based on the PubChem BioAssay dataset and made it available for use by the scientific community.

High throughput functional profiling of genes at intraocular pressure loci reveals distinct networks for glaucoma

INTRODUCTION

Primary open angle glaucoma (POAG) is a leading cause of blindness globally. Characterized by progressive retinal ganglion cell degeneration, the precise pathogenesis remains unknown. Genome-wide association studies (GWAS) have uncovered many genetic variants associated with elevated intraocular pressure (IOP), one of the key risk factors for POAG. We aimed to identify genetic and morphological variation that can be attributed to trabecular meshwork cell (TMC) dysfunction and raised IOP in POAG.

METHODS

62 genes across 55 loci were knocked-out in a primary human TMC line. Each knockout group, including five non-targeting control groups, underwent single-cell RNA-sequencing (scRNA-seq) for differentially-expressed gene (DEG) analysis. Multiplexed fluorescence coupled with CellProfiler image analysis allowed for single-cell morphological profiling.

RESULTS

Many gene knockouts invoked DEGs relating to matrix metalloproteinases and interferon-induced proteins. We have prioritized genes at four loci of interest to identify gene knockouts that may contribute to the pathogenesis of POAG, including ANGPTL2, LMX1B, CAV1, and KREMEN1. Three genetic networks of gene knockouts with similar transcriptomic profiles were identified, suggesting a synergistic function in trabecular meshwork cell physiology. TEK knockout caused significant upregulation of nuclear granularity on morphological analysis, while knockout of TRIOBP, TMCO1 and PLEKHA7 increased granularity and intensity of actin and the cell-membrane.

CONCLUSION

High-throughput analysis of cellular structure and function through multiplex fluorescent single-cell analysis and scRNA-seq assays enabled the direct study of genetic perturbations at the single-cell resolution. This work provides a framework for investigating the role of genes in the pathogenesis of glaucoma and heterogenous diseases with a strong genetic basis.

da_Tracker: Automated workflow for high throughput single cell and single phagosome tracking in infected cells

Time-lapse microscopy has emerged as a crucial tool in cell biology, facilitating a deeper understanding of dynamic cellular processes. While existing tracking tools have proven effective in detecting and monitoring objects over time, the quantification of signals within these tracked objects often faces implementation constraints. In the context of infectious diseases, the quantification of signals at localized compartments within the cell and around intracellular pathogens can provide even deeper insight into the interactions between the pathogen and host cell organelles. Existing quantitative analysis at a single-phagosome level remains limited and dependent on manual tracking methods. We developed a near-fully automated workflow that performs with limited bias, high-throughput cell segmentation and quantitative tracking of both single cell and single bacterium/phagosome within multi-channel, z-stack, time-lapse confocal microscopy videos. We took advantage of the PyImageJ library to bring Fiji functionality into a Python environment and combined deep-learning-based segmentation from Cellpose with tracking algorithms from Trackmate. Our workflow provides a versatile toolkit of functions for measuring relevant signal parameters at the single-cell level (such as velocity or bacterial burden) and at the single-phagosome level (i.e. assessment of phagosome maturation over time). It's capabilities in both single-cell and single-phagosome quantification, its flexibility and open-source nature should assist studies that aim to decipher for example the pathogenicity of bacteria and the mechanism of virulence factors that could pave the way for the development of innovative therapeutic approaches.

SPACe (Swift Phenotypic Analysis of Cells): an open-source, single cell analysis of Cell Painting data

Phenotypic profiling by high throughput microscopy has become one of the leading tools for screening large sets of perturbations in cellular models. Of the numerous methods used over the years, the flexible and economical Cell Painting (CP) assay has been central in the field, allowing for large screening campaigns leading to a vast number of data-rich images. Currently, to analyze data of this scale, available open-source software ( i.e. , CellProfiler) requires computational resources that are not available to most laboratories worldwide. In addition, the image-embedded cell-to-cell variation of responses within a population, while collected and analyzed, is usually averaged and unused. Here we introduce SPACe ( S wift P henotypic A nalysis of Ce lls), an open source, Python-based platform for the analysis of single cell image-based morphological profiles produced by CP experiments. SPACe can process a typical dataset approximately ten times faster than CellProfiler on common desktop computers without loss in mechanism of action (MOA) recognition accuracy. It also computes directional distribution-based distances (Earth Mover's Distance - EMD) of morphological features for quality control and hit calling. We highlight several advantages of SPACe analysis on CP assays, including reproducibility across multiple biological replicates, easy applicability to multiple (∼20) cell lines, sensitivity to variable cell-to-cell responses, and biological interpretability to explain image-based features. We ultimately illustrate the advantages of SPACe in a screening campaign of cell metabolism small molecule inhibitors which we performed in seven cell lines to highlight the importance of testing perturbations across models.

PhagoStat a scalable and interpretable end to end framework for efficient quantification of cell phagocytosis in neurodegenerative disease studies

Quantifying the phagocytosis of dynamic, unstained cells is essential for evaluating neurodegenerative diseases. However, measuring rapid cell interactions and distinguishing cells from background make this task very challenging when processing time-lapse phase-contrast video microscopy. In this study, we introduce an end-to-end, scalable, and versatile real-time framework for quantifying and analyzing phagocytic activity. Our proposed pipeline is able to process large data-sets and includes a data quality verification module to counteract potential perturbations such as microscope movements and frame blurring. We also propose an explainable cell segmentation module to improve the interpretability of deep learning methods compared to black-box algorithms. This includes two interpretable deep learning capabilities: visual explanation and model simplification. We demonstrate that interpretability in deep learning is not the opposite of high performance, by additionally providing essential deep learning algorithm optimization insights and solutions. Besides, incorporating interpretable modules results in an efficient architecture design and optimized execution time. We apply this pipeline to quantify and analyze microglial cell phagocytosis in frontotemporal dementia (FTD) and obtain statistically reliable results showing that FTD mutant cells are larger and more aggressive than control cells. The method has been tested and validated on several public benchmarks by generating state-of-the art performances. To stimulate translational approaches and future studies, we release an open-source end-to-end pipeline and a unique microglial cells phagocytosis dataset for immune system characterization in neurodegenerative diseases research. This pipeline and the associated dataset will consistently crystallize future advances in this field, promoting the development of efficient and effective interpretable algorithms dedicated to the critical domain of neurodegenerative diseases' characterization. https://github.com/ounissimehdi/PhagoStat .

High-content analysis identified synergistic drug interactions between INK128, an mTOR inhibitor, and HDAC inhibitors in a non-small cell lung cancer cell line

BACKGROUND

The development of drug resistance is a major cause of cancer therapy failures. To inhibit drug resistance, multiple drugs are often treated together as a combinatorial therapy. In particular, synergistic drug combinations, which kill cancer cells at a lower concentration, guarantee a better prognosis and fewer side effects in cancer patients. Many studies have sought out synergistic combinations by small-scale function-based targeted growth assays or large-scale nontargeted growth assays, but their discoveries are always challenging due to technical problems such as a large number of possible test combinations.

METHODS

To address this issue, we carried out a medium-scale optical drug synergy screening in a non-small cell lung cancer cell line and further investigated individual drug interactions in combination drug responses by high-content image analysis. Optical high-content analysis of cellular responses has recently attracted much interest in the field of drug discovery, functional genomics, and toxicology. Here, we adopted a similar approach to study combinatorial drug responses.

RESULTS

By examining all possible combinations of 12 drug compounds in 6 different drug classes, such as mTOR inhibitors, HDAC inhibitors, HSP90 inhibitors, MT inhibitors, DNA inhibitors, and proteasome inhibitors, we successfully identified synergism between INK128, an mTOR inhibitor, and HDAC inhibitors, which has also been reported elsewhere. Our high-content analysis further showed that HDAC inhibitors, HSP90 inhibitors, and proteasome inhibitors played a dominant role in combinatorial drug responses when they were mixed with MT inhibitors, DNA inhibitors, or mTOR inhibitors, suggesting that recessive drugs could be less prioritized as components of multidrug cocktails.

CONCLUSIONS

In conclusion, our optical drug screening platform efficiently identified synergistic drug combinations in a non-small cell lung cancer cell line, and our high-content analysis further revealed how individual drugs in the drug mix interact with each other to generate combinatorial drug response.

Cross-Species Extrapolation of Biological Data to Guide the Environmental Safety Assessment of Pharmaceuticals-The State of the Art and Future Priorities

The extrapolation of biological data across species is a key aspect of biomedical research and drug development. In this context, comparative biology considerations are applied with the goal of understanding human disease and guiding the development of effective and safe medicines. However, the widespread occurrence of pharmaceuticals in the environment and the need to assess the risk posed to wildlife have prompted a renewed interest in the extrapolation of pharmacological and toxicological data across the entire tree of life. To address this challenge, a biological "read-across" approach, based on the use of mammalian data to inform toxicity predictions in wildlife species, has been proposed as an effective way to streamline the environmental safety assessment of pharmaceuticals. Yet, how effective has this approach been, and are we any closer to being able to accurately predict environmental risk based on known human risk? We discuss the main theoretical and experimental advancements achieved in the last 10 years of research in this field. We propose that a better understanding of the functional conservation of drug targets across species and of the quantitative relationship between target modulation and adverse effects should be considered as future research priorities. This pharmacodynamic focus should be complemented with the application of higher-throughput experimental and computational approaches to accelerate the prediction of internal exposure dynamics. The translation of comparative (eco)toxicology research into real-world applications, however, relies on the (limited) availability of experts with the skill set needed to navigate the complexity of the problem; hence, we also call for synergistic multistakeholder efforts to support and strengthen comparative toxicology research and education at a global level. Environ Toxicol Chem 2024;43:513-525. © 2023 The Authors. Environmental Toxicology and Chemistry published by Wiley Periodicals LLC on behalf of SETAC.

Cooperative polarization of MCAM/CD146 and ERM family proteins in melanoma

The WRAMP structure is a protein network associated with tail-end actomyosin contractility, membrane retraction, and directional persistence during cell migration. A marker of WRAMP structures is melanoma cell adhesion molecule (MCAM) which dynamically polarizes to the cell rear. However, factors that mediate MCAM polarization are still unknown. In this study, BioID using MCAM as bait identifies the ERM family proteins, moesin, ezrin, and radixin, as WRAMP structure components. We also present a novel image analysis pipeline, Protein Polarity by Percentile ("3P"), which classifies protein polarization using machine learning and facilitates quantitative analysis. Using 3P, we find that depletion of moesin, and to a lesser extent ezrin, decreases the proportion of cells with polarized MCAM. Furthermore, although copolarized MCAM and ERM proteins show high spatial overlap, 3P identifies subpopulations with ERM proteins closer to the cell periphery. Live-cell imaging confirms that MCAM and ERM protein polarization is tightly coordinated, but ERM proteins enrich at the cell edge first. Finally, deletion of a juxtamembrane segment in MCAM previously shown to promote ERM protein interactions impedes MCAM polarization. Our findings highlight the requirement for ERM proteins in recruitment of MCAM to WRAMP structures and an advanced computational tool to characterize protein polarization.

AI-organoid integrated systems for biomedical studies and applications

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

Evaluating batch correction methods for image-based cell profiling

High-throughput image-based profiling platforms are powerful technologies capable of collecting data from billions of cells exposed to thousands of perturbations in a time- and cost-effective manner. Therefore, image-based profiling data has been increasingly used for diverse biological applications, such as predicting drug mechanism of action or gene function. However, batch effects pose severe limitations to community-wide efforts to integrate and interpret image-based profiling data collected across different laboratories and equipment. To address this problem, we benchmarked seven high-performing scRNA-seq batch correction techniques, representing diverse approaches, using a newly released Cell Painting dataset, the largest publicly accessible image-based dataset. We focused on five different scenarios with varying complexity, and we found that Harmony, a mixture-model based method, consistently outperformed the other tested methods. Our proposed framework, benchmark, and metrics can additionally be used to assess new batch correction methods in the future. Overall, this work paves the way for improvements that allow the community to make best use of public Cell Painting data for scientific discovery.

SEMORE: SEgmentation and MORphological fingErprinting by machine learning automates super-resolution data analysis

The morphology of protein assemblies impacts their behaviour and contributes to beneficial and aberrant cellular responses. While single-molecule localization microscopy provides the required spatial resolution to investigate these assemblies, the lack of universal robust analytical tools to extract and quantify underlying structures limits this powerful technique. Here we present SEMORE, a semi-automatic machine learning framework for universal, system- and input-dependent, analysis of super-resolution data. SEMORE implements a multi-layered density-based clustering module to dissect biological assemblies and a morphology fingerprinting module for quantification by multiple geometric and kinetics-based descriptors. We demonstrate SEMORE on simulations and diverse raw super-resolution data: time-resolved insulin aggregates, and published data of dSTORM imaging of nuclear pore complexes, fibroblast growth receptor 1, sptPALM of Syntaxin 1a and dynamic live-cell PALM of ryanodine receptors. SEMORE extracts and quantifies all protein assemblies, their temporal morphology evolution and provides quantitative insights, e.g. classification of heterogeneous insulin aggregation pathways and NPC geometry in minutes. SEMORE is a general analysis platform for super-resolution data, and being a time-aware framework can also support the rise of 4D super-resolution data.

Learning representations for image-based profiling of perturbations

Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient.

Machine learning-assisted high-content imaging analysis of 3D MCF7 microtissues for estrogenic effect prediction

Endocrine-disrupting chemicals (EDCs) pose a significant threat to human well-being and the ecosystem. However, in managing the many thousands of uncharacterized chemical entities, the high-throughput screening of EDCs using relevant biological endpoints remains challenging. Three-dimensional (3D) culture technology enables the development of more physiologically relevant systems in more realistic biochemical microenvironments. The high-content and quantitative imaging techniques enable quantifying endpoints associated with cell morphology, cell-cell interaction, and microtissue organization. In the present study, 3D microtissues formed by MCF-7 breast cancer cells were exposed to the model EDCs estradiol (E2) and propyl pyrazole triol (PPT). A 3D imaging and image analysis pipeline was established to extract quantitative image features from estrogen-exposed microtissues. Moreover, a machine-learning classification model was built using estrogenic-associated differential imaging features. Based on 140 common differential image features found between the E2 and PPT group, the classification model predicted E2 and PPT exposure with AUC-ROC at 0.9528 and 0.9513, respectively. Deep learning-assisted analysis software was developed to characterize microtissue gland lumen formation. The fully automated tool can accurately characterize the number of identified lumens and the total luminal volume of each microtissue. Overall, the current study established an integrated approach by combining non-supervised image feature profiling and supervised luminal volume characterization, which reflected the complexity of functional ER signaling and highlighted a promising conceptual framework for estrogenic EDC risk assessment.

Orientation-invariant autoencoders learn robust representations for shape profiling of cells and organelles

Cell and organelle shape are driven by diverse genetic and environmental factors and thus accurate quantification of cellular morphology is essential to experimental cell biology. Autoencoders are a popular tool for unsupervised biological image analysis because they learn a low-dimensional representation that maps images to feature vectors to generate a semantically meaningful embedding space of morphological variation. The learned feature vectors can also be used for clustering, dimensionality reduction, outlier detection, and supervised learning problems. Shape properties do not change with orientation, and thus we argue that representation learning methods should encode this orientation invariance. We show that conventional autoencoders are sensitive to orientation, which can lead to suboptimal performance on downstream tasks. To address this, we develop O2-variational autoencoder (O2-VAE), an unsupervised method that learns robust, orientation-invariant representations. We use O2-VAE to discover morphology subgroups in segmented cells and mitochondria, detect outlier cells, and rapidly characterise cellular shape and texture in large datasets, including in a newly generated synthetic benchmark.

Harnessing artificial intelligence to reduce phototoxicity in live imaging

Fluorescence microscopy is essential for studying living cells, tissues and organisms. However, the fluorescent light that switches on fluorescent molecules also harms the samples, jeopardizing the validity of results - particularly in techniques such as super-resolution microscopy, which demands extended illumination. Artificial intelligence (AI)-enabled software capable of denoising, image restoration, temporal interpolation or cross-modal style transfer has great potential to rescue live imaging data and limit photodamage. Yet we believe the focus should be on maintaining light-induced damage at levels that preserve natural cell behaviour. In this Opinion piece, we argue that a shift in role for AIs is needed - AI should be used to extract rich insights from gentle imaging rather than recover compromised data from harsh illumination. Although AI can enhance imaging, our ultimate goal should be to uncover biological truths, not just retrieve data. It is essential to prioritize minimizing photodamage over merely pushing technical limits. Our approach is aimed towards gentle acquisition and observation of undisturbed living systems, aligning with the essence of live-cell fluorescence microscopy.

From pixels to insights: Machine learning and deep learning for bioimage analysis

Bioimage analysis plays a critical role in extracting information from biological images, enabling deeper insights into cellular structures and processes. The integration of machine learning and deep learning techniques has revolutionized the field, enabling the automated, reproducible, and accurate analysis of biological images. Here, we provide an overview of the history and principles of machine learning and deep learning in the context of bioimage analysis. We discuss the essential steps of the bioimage analysis workflow, emphasizing how machine learning and deep learning have improved preprocessing, segmentation, feature extraction, object tracking, and classification. We provide examples that showcase the application of machine learning and deep learning in bioimage analysis. We examine user-friendly software and tools that enable biologists to leverage these techniques without extensive computational expertise. This review is a resource for researchers seeking to incorporate machine learning and deep learning in their bioimage analysis workflows and enhance their research in this rapidly evolving field.

Integrating single-cell transcriptomics with cellular phenotypes: cell morphology, Ca2+ imaging and electrophysiology

I review recent technological advancements in coupling single-cell transcriptomics with cellular phenotypes including morphology, calcium signaling, and electrophysiology. Single-cell RNA sequencing (scRNAseq) has revolutionized cell type classifications by capturing the transcriptional diversity of cells. A new wave of methods to integrate scRNAseq and biophysical measurements is facilitating the linkage of transcriptomic data to cellular function, which provides physiological insight into cellular states. I briefly discuss critical factors of these phenotypical characterizations such as timescales, information content, and analytical tools. Dedicated sections focus on the integration with cell morphology, calcium imaging, and electrophysiology (patch-seq), emphasizing their complementary roles. I discuss their application in elucidating cellular states, refining cell type classifications, and uncovering functional differences in cell subtypes. To illustrate the practical applications and benefits of these methods, I highlight their use in tissues with excitable cell-types such as the brain, pancreatic islets, and the retina. The potential of combining functional phenotyping with spatial transcriptomics for a detailed mapping of cell phenotypes in situ is explored. Finally, I discuss open questions and future perspectives, emphasizing the need for a shift towards broader accessibility through increased throughput.

Anticancer Drug Discovery Based on Natural Products: From Computational Approaches to Clinical Studies

Globally, malignancies cause one out of six mortalities, which is a serious health problem. Cancer therapy has always been challenging, apart from major advances in immunotherapies, stem cell transplantation, targeted therapies, hormonal therapies, precision medicine, and palliative care, and traditional therapies such as surgery, radiation therapy, and chemotherapy. Natural products are integral to the development of innovative anticancer drugs in cancer research, offering the scientific community the possibility of exploring novel natural compounds against cancers. The role of natural products like Vincristine and Vinblastine has been thoroughly implicated in the management of leukemia and Hodgkin's disease. The computational method is the initial key approach in drug discovery, among various approaches. This review investigates the synergy between natural products and computational techniques, and highlights their significance in the drug discovery process. The transition from computational to experimental validation has been highlighted through in vitro and in vivo studies, with examples such as betulinic acid and withaferin A. The path toward therapeutic applications have been demonstrated through clinical studies of compounds such as silvestrol and artemisinin, from preclinical investigations to clinical trials. This article also addresses the challenges and limitations in the development of natural products as potential anti-cancer drugs. Moreover, the integration of deep learning and artificial intelligence with traditional computational drug discovery methods may be useful for enhancing the anticancer potential of natural products.

Generative modeling of biological shapes and images using a probabilistic α-shape sampler

Understanding morphological variation is an important task in many areas of computational biology. Recent studies have focused on developing computational tools for the task of sub-image selection which aims at identifying structural features that best describe the variation between classes of shapes. A major part in assessing the utility of these approaches is to demonstrate their performance on both simulated and real datasets. However, when creating a model for shape statistics, real data can be difficult to access and the sample sizes for these data are often small due to them being expensive to collect. Meanwhile, the current landscape of generative models for shapes has been mostly limited to approaches that use black-box inference-making it difficult to systematically assess the power and calibration of sub-image models. In this paper, we introduce the α -shape sampler: a probabilistic framework for generating realistic 2D and 3D shapes based on probability distributions which can be learned from real data. We demonstrate our framework using proof-of-concept examples and in two real applications in biology where we generate (i) 2D images of healthy and septic neutrophils and (ii) 3D computed tomography (CT) scans of primate mandibular molars. The α -shape sampler R package is open-source and can be downloaded at https://github.com/lcrawlab/ashapesampler.

Microsnoop: A generalist tool for microscopy image representation

Accurate profiling of microscopy images from small scale to high throughput is an essential procedure in basic and applied biological research. Here, we present Microsnoop, a novel deep learning-based representation tool trained on large-scale microscopy images using masked self-supervised learning. Microsnoop can process various complex and heterogeneous images, and we classified images into three categories: single-cell, full-field, and batch-experiment images. Our benchmark study on 10 high-quality evaluation datasets, containing over 2,230,000 images, demonstrated Microsnoop's robust and state-of-the-art microscopy image representation ability, surpassing existing generalist and even several custom algorithms. Microsnoop can be integrated with other pipelines to perform tasks such as superresolution histopathology image and multimodal analysis. Furthermore, Microsnoop can be adapted to various hardware and can be easily deployed on local or cloud computing platforms. We will regularly retrain and reevaluate the model using community-contributed data to consistently improve Microsnoop.

High-dimensional phenotyping to define the genetic basis of cellular morphology

The morphology of cells is dynamic and mediated by genetic and environmental factors. Characterizing how genetic variation impacts cell morphology can provide an important link between disease association and cellular function. Here, we combine genomic sequencing and high-content imaging approaches on iPSCs from 297 unique donors to investigate the relationship between genetic variants and cellular morphology to map what we term cell morphological quantitative trait loci (cmQTLs). We identify novel associations between rare protein altering variants in WASF2, TSPAN15, and PRLR with several morphological traits related to cell shape, nucleic granularity, and mitochondrial distribution. Knockdown of these genes by CRISPRi confirms their role in cell morphology. Analysis of common variants yields one significant association and nominate over 300 variants with suggestive evidence (P < 10-6) of association with one or more morphology traits. We then use these data to make predictions about sample size requirements for increasing discovery in cellular genetic studies. We conclude that, similar to molecular phenotypes, morphological profiling can yield insight about the function of genes and variants.

A TCF4-dependent gene regulatory network confers resistance to immunotherapy in melanoma

To better understand intrinsic resistance to immune checkpoint blockade (ICB), we established a comprehensive view of the cellular architecture of the treatment-naive melanoma ecosystem and studied its evolution under ICB. Using single-cell, spatial multi-omics, we showed that the tumor microenvironment promotes the emergence of a complex melanoma transcriptomic landscape. Melanoma cells harboring a mesenchymal-like (MES) state, a population known to confer resistance to targeted therapy, were significantly enriched in early on-treatment biopsies from non-responders to ICB. TCF4 serves as the hub of this landscape by being a master regulator of the MES signature and a suppressor of the melanocytic and antigen presentation transcriptional programs. Targeting TCF4 genetically or pharmacologically, using a bromodomain inhibitor, increased immunogenicity and sensitivity of MES cells to ICB and targeted therapy. We thereby uncovered a TCF4-dependent regulatory network that orchestrates multiple transcriptional programs and contributes to resistance to both targeted therapy and ICB in melanoma.

ESQmodel: biologically informed evaluation of 2-D cell segmentation quality in multiplexed tissue images

MOTIVATION

Single cell segmentation is critical in the processing of spatial omics data to accurately perform cell type identification and analyze spatial expression patterns. Segmentation methods often rely on semi-supervised annotation or labeled training data which are highly dependent on user expertise. To ensure the quality of segmentation, current evaluation strategies quantify accuracy by assessing cellular masks or through iterative inspection by pathologists. While these strategies each address either the statistical or biological aspects of segmentation, there lacks a unified approach to evaluating segmentation accuracy.

RESULTS

In this article, we present ESQmodel, a Bayesian probabilistic method to evaluate single cell segmentation using expression data. By using the extracted cellular data from segmentation and a prior belief of cellular composition as input, ESQmodel computes per cell entropy to assess segmentation quality by how consistent cellular expression profiles match with cell type expectations.

AVAILABILITY AND IMPLEMENTATION

Source code is available on Github at: https://github.com/Roth-Lab/ESQmodel.

Using Dimensionality Reduction to Visualize Phenotypic Changes in High-Throughput Microscopy

High-throughput microscopy has enabled screening of cell phenotypes at unprecedented scale. Systematic identification of cell phenotype changes (such as cell morphology and protein localization changes) is a major analysis goal. Because cell phenotypes are high-dimensional, unbiased approaches to detect and visualize the changes in phenotypes are still needed. Here, we suggest that changes in cellular phenotype can be visualized in reduced dimensionality representations of the image feature space. We describe a freely available analysis pipeline to visualize changes in protein localization in feature spaces obtained from deep learning. As an example, we use the pipeline to identify changes in subcellular localization after the yeast GFP collection was treated with hydroxyurea.

OPTIMAL: An OPTimized Imaging Mass cytometry AnaLysis framework for benchmarking segmentation and data exploration

Analysis of imaging mass cytometry (IMC) data and other low-resolution multiplexed tissue imaging technologies is often confounded by poor single-cell segmentation and suboptimal approaches for data visualization and exploration. This can lead to inaccurate identification of cell phenotypes, states, or spatial relationships compared to reference data from single-cell suspension technologies. To this end we have developed the "OPTimized Imaging Mass cytometry AnaLysis (OPTIMAL)" framework to benchmark any approaches for cell segmentation, parameter transformation, batch effect correction, data visualization/clustering, and spatial neighborhood analysis. Using a panel of 27 metal-tagged antibodies recognizing well-characterized phenotypic and functional markers to stain the same Formalin-Fixed Paraffin Embedded (FFPE) human tonsil sample tissue microarray over 12 temporally distinct batches we tested several cell segmentation models, a range of different arcsinh cofactor parameter transformation values, 5 different dimensionality reduction algorithms, and 2 clustering methods. Finally, we assessed the optimal approach for performing neighborhood analysis. We found that single-cell segmentation was improved by the use of an Ilastik-derived probability map but that issues with poor segmentation were only really evident after clustering and cell type/state identification and not always evident when using "classical" bivariate data display techniques. The optimal arcsinh cofactor for parameter transformation was 1 as it maximized the statistical separation between negative and positive signal distributions and a simple Z-score normalization step after arcsinh transformation eliminated batch effects. Of the five different dimensionality reduction approaches tested, PacMap gave the best data structure with FLOWSOM clustering out-performing phenograph in terms of cell type identification. We also found that neighborhood analysis was influenced by the method used for finding neighboring cells with a "disc" pixel expansion outperforming a "bounding box" approach combined with the need for filtering objects based on size and image-edge location. Importantly, OPTIMAL can be used to assess and integrate with any existing approach to IMC data analysis and, as it creates .FCS files from the segmentation output and allows for single-cell exploration to be conducted using a wide variety of accessible software and algorithms familiar to conventional flow cytometrists.

High content screening strategies for large-scale compound libraries with a focus on high-containment viruses

A majority of viral diseases do not have FDA-approved drugs. The recent outbreaks caused by SARS-CoV-2, monkeypox, and Sudan ebolavirus have exposed the critical need for rapid screening and identification of antiviral compounds against emerging/re-emerging viral pathogens. A high-content screening (HCS) platform is becoming an essential part of the drug discovery process, thanks to developments in image acquisition and analysis. While HCS has several advantages, its full potential has not been realized in antiviral drug discovery compared to conventional drug screening approaches, such as fluorescence or luminescence-based microplate assays. Therefore, this review aims to summarize HCS workflow, strategies, and developments in image-based drug screening, focusing on high-containment viruses.

Single-cell quantitative bioimaging of P. berghei liver stage translation

IMPORTANCE

Plasmodium parasites cause malaria in humans. New multistage active antimalarial drugs are needed, and a promising class of drugs targets the core cellular process of translation, which has many potential molecular targets. During the obligate liver stage, Plasmodium parasites grow in metabolically active hepatocytes, making it challenging to study core cellular processes common to both host cells and parasites, as the signal from the host typically overwhelms that of the parasite. Here, we present and validate a flexible assay to quantify Plasmodium liver stage translation using a technique to fluorescently label the newly synthesized proteins of both host and parasite followed by computational separation of their respective nascent proteomes in confocal image sets. We use the assay to determine whether a test set of known compounds are direct or indirect liver stage translation inhibitors and show that the assay can also predict the mode of action for novel antimalarial compounds.

Discovery of Molecular Glue Degraders via Isogenic Morphological Profiling

Molecular glue degraders (MGDs) are small molecules that degrade proteins of interest via the ubiquitin-proteasome system. While MGDs were historically discovered serendipitously, approaches for MGD discovery now include cell-viability-based drug screens or data mining of public transcriptomics and drug response datasets. These approaches, however, have target spaces restricted to the essential proteins. Here we develop a high-throughput workflow for MGD discovery that also reaches the nonessential proteome. This workflow begins with the rapid synthesis of a compound library by sulfur(VI) fluoride exchange chemistry coupled to a morphological profiling assay in isogenic cell lines that vary in levels of the E3 ligase CRBN. By comparing the morphological changes induced by compound treatment across the isogenic cell lines, we were able to identify FL2-14 as a CRBN-dependent MGD targeting the nonessential protein GSPT2. We envision that this workflow would contribute to the discovery and characterization of MGDs that target a wider range of proteins.

Tumor endothelial cell autophagy is a key vascular-immune checkpoint in melanoma

Tumor endothelial cells (TECs) actively repress inflammatory responses and maintain an immune-excluded tumor phenotype. However, the molecular mechanisms that sustain TEC-mediated immunosuppression remain largely elusive. Here, we show that autophagy ablation in TECs boosts antitumor immunity by supporting infiltration and effector function of T-cells, thereby restricting melanoma growth. In melanoma-bearing mice, loss of TEC autophagy leads to the transcriptional expression of an immunostimulatory/inflammatory TEC phenotype driven by heightened NF-kB and STING signaling. In line, single-cell transcriptomic datasets from melanoma patients disclose an enriched InflammatoryHigh /AutophagyLow TEC phenotype in correlation with clinical responses to immunotherapy, and responders exhibit an increased presence of inflamed vessels interfacing with infiltrating CD8+ T-cells. Mechanistically, STING-dependent immunity in TECs is not critical for the immunomodulatory effects of autophagy ablation, since NF-kB-driven inflammation remains functional in STING/ATG5 double knockout TECs. Hence, our study identifies autophagy as a principal tumor vascular anti-inflammatory mechanism dampening melanoma antitumor immunity.

Explainable machine learning for profiling the immunological synapse and functional characterization of therapeutic antibodies

Therapeutic antibodies are widely used to treat severe diseases. Most of them alter immune cells and act within the immunological synapse; an essential cell-to-cell interaction to direct the humoral immune response. Although many antibody designs are generated and evaluated, a high-throughput tool for systematic antibody characterization and prediction of function is lacking. Here, we introduce the first comprehensive open-source framework, scifAI (single-cell imaging flow cytometry AI), for preprocessing, feature engineering, and explainable, predictive machine learning on imaging flow cytometry (IFC) data. Additionally, we generate the largest publicly available IFC dataset of the human immunological synapse containing over 2.8 million images. Using scifAI, we analyze class frequency and morphological changes under different immune stimulation. T cell cytokine production across multiple donors and therapeutic antibodies is quantitatively predicted in vitro, linking morphological features with function and demonstrating the potential to significantly impact antibody design. scifAI is universally applicable to IFC data. Given its modular architecture, it is straightforward to incorporate into existing workflows and analysis pipelines, e.g., for rapid antibody screening and functional characterization.

Morphology-Based Prediction of Proliferation and Differentiation Potencies of Porcine Muscle Stem Cells for Cultured Meat Production

Inconsistent efficiency of cell production caused by cellular quality variations has become a significant problem in the cultured meat industry. In our study, morphological information on passages 5-9 of porcine muscle stem cells (pMuSCs) from three lots was analyzed and used as input data in prediction models. Cell proliferation and differentiation potencies were measured by cell growth rate and average stained area of the myosin heavy chain. Analysis of PCA and heatmap showed that the morphological parameters could be used to discriminate the differences of passages and lots. Various morphological parameters were analyzed, which revealed that accumulating time-course information regarding morphological heterogeneity in cell populations is crucial to predicting the potencies. Based on the 36 and 60 h morphological profiles, the best proliferation potency prediction model (R2 = 0.95, RMSE = 1.1) and differentiation potency prediction model (R2 = 0.74, RMSE = 1.2) were explored. Correlation analysis demonstrated that morphological parameters selected in models are related to the quality of porcine muscle stem cells.

Deep-Learning Terahertz Single-Cell Metabolic Viability Study

Cell viability assessment is critical, yet existing assessments are not accurate enough. We report a cell viability evaluation method based on the metabolic ability of a single cell. Without culture medium, we measured the absorption of cells to terahertz laser beams, which could target a single cell. The cell viability was assessed with a convolution neural classification network based on cell morphology. We established a cell viability assessment model based on the THz-AS (terahertz-absorption spectrum) results as y = a = (x - b)c, where x is the terahertz absorbance and y is the cell viability, and a, b, and c are the fitting parameters of the model. Under water stress the changes in terahertz absorbance of cells corresponded one-to-one with the apoptosis process, and we propose a cell 0 viability definition as terahertz absorbance remains unchanged based on the cell metabolic mechanism. Compared with typical methods, our method is accurate, label-free, contact-free, and almost interference-free and could help visualize the cell apoptosis process for broad applications including drug screening.

CLOOME: contrastive learning unlocks bioimaging databases for queries with chemical structures

The field of bioimage analysis is currently impacted by a profound transformation, driven by the advancements in imaging technologies and artificial intelligence. The emergence of multi-modal AI systems could allow extracting and utilizing knowledge from bioimaging databases based on information from other data modalities. We leverage the multi-modal contrastive learning paradigm, which enables the embedding of both bioimages and chemical structures into a unified space by means of bioimage and molecular structure encoders. This common embedding space unlocks the possibility of querying bioimaging databases with chemical structures that induce different phenotypic effects. Concretely, in this work we show that a retrieval system based on multi-modal contrastive learning is capable of identifying the correct bioimage corresponding to a given chemical structure from a database of ~2000 candidate images with a top-1 accuracy >70 times higher than a random baseline. Additionally, the bioimage encoder demonstrates remarkable transferability to various further prediction tasks within the domain of drug discovery, such as activity prediction, molecule classification, and mechanism of action identification. Thus, our approach not only addresses the current limitations of bioimaging databases but also paves the way towards foundation models for microscopy images.

Single-cell profiling and zebrafish avatars reveal LGALS1 as immunomodulating target in glioblastoma

Glioblastoma (GBM) remains the most malignant primary brain tumor, with a median survival rarely exceeding 2 years. Tumor heterogeneity and an immunosuppressive microenvironment are key factors contributing to the poor response rates of current therapeutic approaches. GBM-associated macrophages (GAMs) often exhibit immunosuppressive features that promote tumor progression. However, their dynamic interactions with GBM tumor cells remain poorly understood. Here, we used patient-derived GBM stem cell cultures and combined single-cell RNA sequencing of GAM-GBM co-cultures and real-time in vivo monitoring of GAM-GBM interactions in orthotopic zebrafish xenograft models to provide insight into the cellular, molecular, and spatial heterogeneity. Our analyses revealed substantial heterogeneity across GBM patients in GBM-induced GAM polarization and the ability to attract and activate GAMs-features that correlated with patient survival. Differential gene expression analysis, immunohistochemistry on original tumor samples, and knock-out experiments in zebrafish subsequently identified LGALS1 as a primary regulator of immunosuppression. Overall, our work highlights that GAM-GBM interactions can be studied in a clinically relevant way using co-cultures and avatar models, while offering new opportunities to identify promising immune-modulating targets.

Genetic analysis and multimodal imaging identify novel mtDNA 12148T>C leading to multisystem dysfunction with tissue-specific heteroplasmy

Patients with mitochondrial disorders present with clinically diverse symptoms, largely driven by heterogeneous mutations in mitochondrial-encoded and nuclear-encoded mitochondrial genes. These mutations ultimately lead to complex biochemical disorders with a myriad of clinical manifestations, often accumulating during childhood on into adulthood, contributing to life-altering and sometimes fatal events. It is therefore important to diagnose and characterize the associated disorders for each mitochondrial mutation as early as possible since medical management might be able to improve the quality and longevity of life in mitochondrial disease patients. Here we identify a novel mitochondrial variant in a mitochondrial transfer RNA for histidine (mt-tRNA-his) [m.12148T>C], that is associated with the development of ocular, aural, neurological, renal, and muscular dysfunctions. We provide a detailed account of a family harboring this mutation, as well as the molecular underpinnings contributing to cellular and mitochondrial dysfunction. In conclusion, this investigation provides clinical, biochemical, and morphological evidence of the pathogenicity of m.12148T>C. We highlight the importance of multiple tissue testing and in vitro disease modeling in diagnosing mitochondrial disease.

Increased proliferation and neuronal fate in prairie vole brain progenitor cells cultured in vitro: effects by social exposure and sexual dimorphism

BACKGROUND

The prairie vole (Microtus ochrogaster) is a socially monogamous rodent that establishes an enduring pair bond after cohabitation, with (6 h) or without (24 h) mating. Previously, we reported that social interaction and mating increased cell proliferation and differentiation to neuronal fate in neurogenic niches in male voles. We hypothesized that neurogenesis may be a neural plasticity mechanism involved in mating-induced pair bond formation. Here, we evaluated the differentiation potential of neural progenitor cells (NPCs) isolated from the subventricular zone (SVZ) of both female and male adult voles as a function of sociosexual experience. Animals were assigned to one of the following groups: (1) control (Co), sexually naive female and male voles that had no contact with another vole of the opposite sex; (2) social exposure (SE), males and females exposed to olfactory, auditory, and visual stimuli from a vole of the opposite sex, but without physical contact; and (3) social cohabitation with mating (SCM), male and female voles copulating to induce pair bonding formation. Subsequently, the NPCs were isolated from the SVZ, maintained, and supplemented with growth factors to form neurospheres in vitro.

RESULTS

Notably, we detected in SE and SCM voles, a higher proliferation of neurosphere-derived Nestin + cells, as well as an increase in mature neurons (MAP2 +) and a decrease in glial (GFAP +) differentiated cells with some sex differences. These data suggest that when voles are exposed to sociosexual experiences that induce pair bonding, undifferentiated cells of the SVZ acquire a commitment to a neuronal lineage, and the determined potential of the neurosphere is conserved despite adaptations under in vitro conditions. Finally, we repeated the culture to obtain neurospheres under treatments with different hormones and factors (brain-derived neurotrophic factor, estradiol, prolactin, oxytocin, and progesterone); the ability of SVZ-isolated cells to generate neurospheres and differentiate in vitro into neurons or glial lineages in response to hormones or factors is also dependent on sex and sociosexual context.

CONCLUSION

Social interactions that promote pair bonding in voles change the properties of cells isolated from the SVZ. Thus, SE or SCM induces a bias in the differentiation potential in both sexes, while SE is sufficient to promote proliferation in SVZ-isolated cells from male brains. In females, proliferation increases when mating is performed. The next question is whether the rise in proliferation and neurogenesis of cells from the SVZ are plastic processes essential for establishing, enhancing, maintaining, or accelerating pair bond formation. Highlights 1. Sociosexual experiences that promote pair bonding (social exposure and social cohabitation with mating) induce changes in the properties of neural stem/progenitor cells isolated from the SVZ in adult prairie voles. 2. Social interactions lead to increased proliferation and induce a bias in the differentiation potential of SVZ-isolated cells in both male and female voles. 3. The differentiation potential of SVZ-isolated cells is conserved under in vitro conditions, suggesting a commitment to a neuronal lineage under a sociosexual context. 4. Hormonal and growth factors treatments (brain-derived neurotrophic factor, estradiol, prolactin, oxytocin, and progesterone) affect the generation and differentiation of neurospheres, with dependencies on sex and sociosexual context. 5. Proliferation and neurogenesis in the SVZ may play a crucial role in establishing, enhancing, maintaining, or accelerating pair bond formation.

Multiscale quantification of morphological heterogeneity with creation of a predictor of longer survival in glioblastoma

Intratumor heterogeneity is a main cause of the dismal prognosis of glioblastoma (GBM). Yet, there remains a lack of a uniform assessment of the degree of heterogeneity. With a multiscale approach, we addressed the hypothesis that intratumor heterogeneity exists on different levels comprising traditional regional analyses, but also innovative methods including computer-assisted analysis of tumor morphology combined with epigenomic data. With this aim, 157 biopsies of 37 patients with therapy-naive IDH-wildtype GBM were analyzed regarding the intratumor variance of protein expression of glial marker GFAP, microglia marker Iba1 and proliferation marker Mib1. Hematoxylin and eosin stained slides were evaluated for tumor vascularization. For the estimation of pixel intensity and nuclear profiling, automated analysis was used. Additionally, DNA methylation profiling was conducted separately for the single biopsies. Scoring systems were established to integrate several parameters into one score for the four examined modalities of heterogeneity (regional, cellular, pixel-level and epigenomic). As a result, we could show that heterogeneity was detected in all four modalities. Furthermore, for the regional, cellular and epigenomic level, we confirmed the results of earlier studies stating that a higher degree of heterogeneity is associated with poorer overall survival. To integrate all modalities into one score, we designed a predictor of longer survival, which showed a highly significant separation regarding the OS. In conclusion, multiscale intratumor heterogeneity exists in glioblastoma and its degree has an impact on overall survival. In future studies, the implementation of a broadly feasible heterogeneity index should be considered.

Assessing the performance of the Cell Painting assay across different imaging systems

Quantitative microscopy is a powerful method for performing phenotypic screens from which image-based profiling can extract a wealth of information, termed profiles. These profiles can be used to elucidate the changes in cellular phenotypes across cell populations from different patient samples or following genetic or chemical perturbations. One such image-based profiling method is the Cell Painting assay, which provides morphological insight through the imaging of eight cellular compartments. Here, we examine the performance of the Cell Painting assay across multiple high-throughput microscope systems and find that all are compatible with this assay. Furthermore, we determine independently for each microscope system the best performing settings, providing those who wish to adopt this assay an ideal starting point for their own assays. We also explore the impact of microscopy setting changes in the Cell Painting assay and find that few dramatically reduce the quality of a Cell Painting profile, regardless of the microscope used.

Quantitative phase imaging for characterization of single cell growth dynamics

Quantitative phase imaging (QPI) has emerged as an indispensable tool in the field of biomedicine, offering the ability to obtain quantitative maps of phase changes due to optical path length delays without the need for contrast agents. These maps provide valuable information about cellular morphology and dynamics, unperturbed by the introduction of exogenous substances. In this review, a summary of recent studies that have focused on elucidating the growth dynamics of individual cells using QPI is presented. Specifically, investigations into cellular changes occurring during mitosis, the differentiation of cellular organelles, the assessment of distinct cell death processes (i.e., apoptosis, necrosis, and oncosis) and the precise measurement of live cell temperature are explored. Furthermore, the captivating applications of QPI in theragnostics, where its potential for transformative impact is prominently showcased, are highlighted. Finally, the challenges that need to be overcome for its wider adoption and successful integration into biomedical research are outlined.

Machine Learning-Assisted High-Content Imaging Analysis of 3D MCF7 Microtissues for Estrogenic Effect Prediction

Endocrine-disrupting chemicals (EDCs) pose a significant threat to human well-being and the ecosystem. However, in managing the many thousands of uncharacterized chemical entities, the high-throughput screening of EDCs using relevant biological endpoints remains challenging. Three-dimensional (3D) culture technology enables the development of more physiologically relevant systems in more realistic biochemical microenvironments. The high-content and quantitative imaging techniques enable quantifying endpoints associated with cell morphology, cell-cell interaction, and microtissue organization. In the present study, 3D microtissues formed by MCF-7 breast cancer cells were exposed to the model EDCs estradiol (E2) and propyl pyrazole triol (PPT). A 3D imaging and image analysis pipeline was established to extract quantitative image features from estrogen-exposed microtissues. Moreover, a machine-learning classification model was built using estrogenic-associated differential imaging features. Based on 140 common differential image features found between the E2 and PPT group, the classification model predicted E2 and PPT exposure with AUC-ROC at 0.9528 and 0.9513, respectively. Deep learning-assisted analysis software was developed to characterize microtissue gland lumen formation. The fully automated tool can accurately characterize the number of identified lumens and the total luminal volume of each microtissue. Overall, the current study established an integrated approach by combining non-supervised image feature profiling and supervised luminal volume characterization, which reflected the complexity of functional ER signaling and highlighted a promising conceptual framework for estrogenic EDC risk assessment.

High throughput microscopy and single cell phenotypic image-based analysis in toxicology and drug discovery

Measuring single cell responses to the universe of chemicals (drugs, natural products, environmental toxicants etc.) is of paramount importance to human health as phenotypic variability in sensing stimuli is a hallmark of biology that is considered during high throughput screening. One of the ways to approach this problem is via high throughput, microscopy-based assays coupled with multi-dimensional single cell analysis methods. Here, we will summarize some of the efforts in this vast and growing field, focusing on phenotypic screens (e.g., Cell Painting), single cell analytics and quality control, with particular attention to environmental toxicology and drug screening. We will discuss advantages and limitations of high throughput assays with various end points and levels of complexity.

Yearning for machine learning: applications for the classification and characterisation of senescence

Senescence is a widely appreciated tumour suppressive mechanism, which acts as a barrier to cancer development by arresting cell cycle progression in response to harmful stimuli. However, senescent cell accumulation becomes deleterious in aging and contributes to a wide range of age-related pathologies. Furthermore, senescence has beneficial roles and is associated with a growing list of normal physiological processes including wound healing and embryonic development. Therefore, the biological role of senescent cells has become increasingly nuanced and complex. The emergence of sophisticated, next-generation profiling technologies, such as single-cell RNA sequencing, has accelerated our understanding of the heterogeneity of senescence, with distinct final cell states emerging within models as well as between cell types and tissues. In order to explore data sets of increasing size and complexity, the senescence field has begun to employ machine learning (ML) methodologies to probe these intricacies. Most notably, ML has been used to aid the classification of cells as senescent, as well as to characterise the final senescence phenotypes. Here, we provide a background to the principles of ML tasks, as well as some of the most commonly used methodologies from both traditional and deep ML. We focus on the application of these within the context of senescence research, by addressing the utility of ML for the analysis of data from different laboratory technologies (microscopy, transcriptomics, proteomics, methylomics), as well as the potential within senolytic drug discovery. Together, we aim to highlight both the progress and potential for the application of ML within senescence research.

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.

An Early Neoplasia Index (ENI10), Based on Molecular Identity of CD10 Cells and Associated Stemness Biomarkers, is a Predictor of Patient Outcome in Many Cancers

An accurate estimate of patient survival at diagnosis is critical to plan efficient therapeutic options. A simple and multiapplication tool is needed to move forward the precision medicine era. Taking advantage of the broad and high CD10 expression in stem and cancers cells, we evaluated the molecular identity of aggressive cancer cells. We used epithelial primary cells and developed a breast cancer stem cell–based progressive model. The superiority of the early-transformed isolated molecular index was evaluated by large-scale analysis in solid cancers. BMP2-driven cell transformation increases CD10 expression which preserves stemness properties. Our model identified a unique set of 159 genes enriched in G2–M cell-cycle phases and spindle assembly complex. Using samples predisposed to transformation, we confirmed the value of an early neoplasia index associated to CD10 (ENI10) to discriminate premalignant status of a human tissue. Using a stratified Cox model, a large-scale analysis (>10,000 samples, The Cancer Genome Atlas Pan-Cancer) validated a strong risk gradient (HRs reaching HR = 5.15; 95% confidence interval: 4.00–6.64) for high ENI10 levels. Through different databases, Cox regression model analyses highlighted an association between ENI10 and poor progression-free intervals for more than 50% of cancer subtypes tested, and the potential of ENI10 to predict drug efficacy. The ENI10 index constitutes a robust tool to detect pretransformed tissues and identify high-risk patients at diagnosis. Owing to its biological link with refractory cancer stem cells, the ENI10 index constitutes a unique way of identifying effective treatments to improve clinical care.

SIGNIFICANCE

We identified a molecular signature called ENI10 which, owing to its biological link with stem cell properties, predicts patient outcome and drugs efficiency in breast and several other cancers. ENI10 should allow early and optimized clinical management of a broad number of cancers, regardless of the stage of tumor progression.

High-content microscopy reveals a morphological signature of bortezomib resistance

Drug resistance is a challenge in anticancer therapy. In many cases, cancers can be resistant to the drug prior to exposure, that is, possess intrinsic drug resistance. However, we lack target-independent methods to anticipate resistance in cancer cell lines or characterize intrinsic drug resistance without a priori knowledge of its cause. We hypothesized that cell morphology could provide an unbiased readout of drug resistance. To test this hypothesis, we used HCT116 cells, a mismatch repair-deficient cancer cell line, to isolate clones that were resistant or sensitive to bortezomib, a well-characterized proteasome inhibitor and anticancer drug to which many cancer cells possess intrinsic resistance. We then expanded these clones and measured high-dimensional single-cell morphology profiles using Cell Painting, a high-content microscopy assay. Our imaging- and computation-based profiling pipeline identified morphological features that differed between resistant and sensitive cells. We used these features to generate a morphological signature of bortezomib resistance. We then employed this morphological signature to analyze a set of HCT116 clones (five resistant and five sensitive) that had not been included in the signature training dataset, and correctly predicted sensitivity to bortezomib in seven cases, in the absence of drug treatment. This signature predicted bortezomib resistance better than resistance to other drugs targeting the ubiquitin-proteasome system, indicating specificity for mechanisms of resistance to bortezomib. Our results establish a proof-of-concept framework for the unbiased analysis of drug resistance using high-content microscopy of cancer cells, in the absence of drug treatment.

pH-gated nanoparticles selectively regulate lysosomal function of tumour-associated macrophages for cancer immunotherapy

Tumour-associated macrophages (TAMs), as one of the most abundant tumour-infiltrating immune cells, play a pivotal role in tumour antigen clearance and immune suppression. M2-like TAMs present a heightened lysosomal acidity and protease activity, limiting an effective antigen cross-presentation. How to selectively reprogram M2-like TAMs to reinvigorate anti-tumour immune responses is challenging. Here, we report a pH-gated nanoadjuvant (PGN) that selectively targets the lysosomes of M2-like TAMs in tumours rather than the corresponding organelles from macrophages in healthy tissues. Enabled by the PGN nanotechnology, M2-like TAMs are specifically switched to a M1-like phenotype with attenuated lysosomal acidity and cathepsin activity for improved antigen cross-presentation, thus eliciting adaptive immune response and sustained tumour regression in tumour-bearing female mice. Our findings provide insights into how to specifically regulate lysosomal function of TAMs for efficient cancer immunotherapy.

Assessment of Drug-Induced Liver Injury through Cell Morphology and Gene Expression Analysis

Drug-induced liver injury (DILI) is a significant concern in drug development, often leading to drug withdrawal. Although many studies aim to identify biomarkers and gene/pathway signatures related to liver toxicity and aim to predict DILI compounds, this remains a challenge in drug discovery. With a strong development of high-content screening/imaging (HCS/HCI) for phenotypic screening, we explored the morphological cell perturbations induced by DILI compounds. In the first step, cell morphological signatures were associated with two datasets of DILI chemicals (DILIRank and eTox). The mechanisms of action were then analyzed for chemicals having transcriptomics data and sharing similar morphological perturbations. Signaling pathways associated with liver toxicity (cell cycle, cell growth, apoptosis, ...) were then captured, and a hypothetical relation between cell morphological perturbations and gene deregulation was illustrated within our analysis. Finally, using the cell morphological signatures, machine learning approaches were developed to predict chemicals with a potential risk of DILI. Some models showed relevant performance with validation set balanced accuracies between 0.645 and 0.739. Overall, our findings demonstrate the utility of combining HCI with transcriptomics data to identify the morphological and gene expression signatures related to DILI chemicals. Moreover, our protocol could be extended to other toxicity end points, offering a promising avenue for comprehensive toxicity assessment in drug discovery.