High-dimensional gene expression and morphology profiles of cells across 28,000 genetic and chemical perturbations

BiDAC-dependent degradation of plasma membrane proteins by the endolysosomal system

The discovery of bifunctional degradation activating compounds (BiDACs) has led to the development of a new class of drugs that promote the clearance of their protein targets. BiDAC-induced ubiquitination is generally believed to direct cytosolic and nuclear proteins to proteolytic destruction by proteasomes. However, pathways that govern the degradation of other classes of BiDAC targets, such as integral membrane and intraorganellar proteins, have not been investigated in depth. In this study we use morphological profiling and CRISPR/Cas9 genetic screens to investigate the mechanisms by which BiDACs induce the degradation of plasma membrane receptor tyrosine kinases (RTKs) EGFR and Her2. We find that BiDAC-dependent ubiquitination triggers the trafficking of RTKs from the plasma membrane to lysosomes for degradation. Notably, functional proteasomes are required for endocytosis of RTKs upstream of the lysosome. Additionally, our screen uncovers a non-canonical function of the lysosome-associated arginine/lysine transporter PQLC2 in EGFR degradation. Our data show that BiDACs can target proteins to proteolytic machinery other than the proteasome and motivate further investigation of mechanisms that govern the degradation of diverse classes of BiDAC targets.

Universal consensus 3D segmentation of cells from 2D segmented stacks

Cell segmentation is the foundation of a wide range of microscopy-based biological studies. Deep learning has revolutionized 2D cell segmentation, enabling generalized solutions across cell types and imaging modalities. This has been driven by the ease of scaling up image acquisition, annotation, and computation. However, 3D cell segmentation, requiring dense annotation of 2D slices still poses significant challenges. Manual labeling of 3D cells to train broadly applicable segmentation models is prohibitive. Even in high-contrast images annotation is ambiguous and time-consuming. Here we develop a theory and toolbox, u-Segment3D, for 2D-to-3D segmentation, compatible with any 2D method generating pixel-based instance cell masks. u-Segment3D translates and enhances 2D instance segmentations to a 3D consensus instance segmentation without training data, as demonstrated on 11 real-life datasets, >70,000 cells, spanning single cells, cell aggregates, and tissue. Moreover, u-Segment3D is competitive with native 3D segmentation, even exceeding when cells are crowded and have complex morphologies.

Cell Painting: a decade of discovery and innovation in cellular imaging

Modern quantitative image analysis techniques have enabled high-throughput, high-content imaging experiments. Image-based profiling leverages the rich information in images to identify similarities or differences among biological samples, rather than measuring a few features, as in high-content screening. Here, we review a decade of advancements and applications of Cell Painting, a microscopy-based cell-labeling assay aiming to capture a cell's state, introduced in 2013 to optimize and standardize image-based profiling. Cell Painting's ability to capture cellular responses to various perturbations has expanded owing to improvements in the protocol, adaptations for different perturbations, and enhanced methodologies for feature extraction, quality control, and batch-effect correction. Cell Painting is a versatile tool that has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects. Future advances will likely involve computational and experimental techniques, new publicly available datasets, and integration with other high-content data types.

Progress in toxicogenomics to protect human health

Toxicogenomics measures molecular features, such as transcripts, proteins, metabolites and epigenomic modifications, to understand and predict the toxicological effects of environmental and pharmaceutical exposures. Transcriptomics has become an integral tool in contemporary toxicology research owing to innovations in gene expression profiling that can provide mechanistic and quantitative information at scale. These data can be used to predict toxicological hazards through the use of transcriptomic biomarkers, network inference analyses, pattern-matching approaches and artificial intelligence. Furthermore, emerging approaches, such as high-throughput dose-response modelling, can leverage toxicogenomic data for human health protection even in the absence of predicting specific hazards. Finally, single-cell transcriptomics and multi-omics provide detailed insights into toxicological mechanisms. Here, we review the progress since the inception of toxicogenomics in applying transcriptomics towards toxicology testing and highlight advances that are transforming risk assessment.

Attention-based deep learning for accurate cell image analysis

High-content analysis (HCA) holds enormous potential for drug discovery and research, but widely used methods can be cumbersome and yield inaccurate results. Noisy and redundant signals in cell images impede accurate deep learning-based image analysis. To address these issues, we introduce X-Profiler, a novel HCA method that combines cellular experiments, image processing, and deep learning modeling. X-Profiler combines the convolutional neural network and Transformer to encode high-content images, effectively filtering out noisy signals and precisely characterizing cell phenotypes. In comparative tests on drug-induced cardiotoxicity, mitochondrial toxicity classification, and compound classification, X-Profiler outperformed both DeepProfiler and CellProfiler, as two highly recognized and representative methods in this field. Our results demonstrate the utility and versatility of X-Profiler, and we anticipate its wide application in HCA for advancing drug development and disease research.

SPACe: an open-source, single-cell analysis of Cell Painting data

Phenotypic profiling by high throughput microscopy, including Cell Painting, has become a leading tool for screening large sets of perturbations in cellular models. To efficiently analyze this big data, available open-source software requires computational resources usually not available to most laboratories. In addition, the cell-to-cell variation of responses within a population, while collected and analyzed, is usually averaged and unused. We introduce SPACe (Swift Phenotypic Analysis of Cells), an open-source platform for analysis of single-cell image-based morphological profiles produced by Cell Painting. We highlight several advantages of SPACe, including processing speed, accuracy in mechanism of action recognition, reproducibility across biological replicates, applicability to multiple models, sensitivity to variable cell-to-cell responses, and biological interpretability to explain image-based features. We illustrate SPACe in a defined screening campaign of cell metabolism small-molecule inhibitors tested in seven cell lines to highlight the importance of analyzing perturbations across models.

Towards functional maps of non-coding variants in cancer

Large scale cancer genomic studies in patients have unveiled millions of non-coding variants. While a handful have been shown to drive cancer development, the vast majority have unknown function. This review describes the challenges of functionally annotating non-coding cancer variants and understanding how they contribute to cancer. We summarize recently developed high-throughput technologies to address these challenges. Finally, we outline future prospects for non-coding cancer genetics to help catalyze personalized cancer therapy.

Single-cell transcriptomes identify patient-tailored therapies for selective co-inhibition of cancer clones

Intratumoral cellular heterogeneity necessitates multi-targeting therapies for improved clinical benefits in advanced malignancies. However, systematic identification of patient-specific treatments that selectively co-inhibit cancerous cell populations poses a combinatorial challenge, since the number of possible drug-dose combinations vastly exceeds what could be tested in patient cells. Here, we describe a machine learning approach, scTherapy, which leverages single-cell transcriptomic profiles to prioritize multi-targeting treatment options for individual patients with hematological cancers or solid tumors. Patient-specific treatments reveal a wide spectrum of co-inhibitors of multiple biological pathways predicted for primary cells from heterogenous cohorts of patients with acute myeloid leukemia and high-grade serous ovarian carcinoma, each with unique resistance patterns and synergy mechanisms. Experimental validations confirm that 96% of the multi-targeting treatments exhibit selective efficacy or synergy, and 83% demonstrate low toxicity to normal cells, highlighting their potential for therapeutic efficacy and safety. In a pan-cancer analysis across five cancer types, 25% of the predicted treatments are shared among the patients of the same tumor type, while 19% of the treatments are patient-specific. Our approach provides a widely-applicable strategy to identify personalized treatment regimens that selectively co-inhibit malignant cells and avoid inhibition of non-cancerous cells, thereby increasing their likelihood for clinical success.

High-Throughput Transcriptomics Screen of ToxCast Chemicals in U-2 OS Cells

New approach methodologies (NAMs) aim to accelerate the pace of chemical risk assessment while simultaneously reducing cost and dependency on animal studies. High Throughput Transcriptomics (HTTr) is an emerging NAM in the field of chemical hazard evaluation for establishing in vitro points-of-departure and providing mechanistic insight. In the current study, 1201 test chemicals were screened for bioactivity at eight concentrations using a 24-h exposure duration in the human- derived U-2 OS osteosarcoma cell line with HTTr. Assay reproducibility was assessed using three reference chemicals that were screened on every assay plate. The resulting transcriptomics data were analyzed by aggregating signal from genes into signature scores using gene set enrichment analysis, followed by concentration-response modeling of signatures scores. Signature scores were used to predict putative mechanisms of action, and to identify biological pathway altering concentrations (BPACs). BPACs were consistent across replicates for each reference chemical, with replicate BPAC standard deviations as low as 5.6 × 10-3 μM, demonstrating the internal reproducibility of HTTr-derived potency estimates. BPACs of test chemicals showed modest agreement (R2 = 0.55) with existing phenotype altering concentrations from high throughput phenotypic profiling using Cell Painting of the same chemicals in the same cell line. Altogether, this HTTr based chemical screen contributes to an accumulating pool of publicly available transcriptomic data relevant for chemical hazard evaluation and reinforces the utility of cell based molecular profiling methods in estimating chemical potency and predicting mechanism of action across a diverse set of chemicals.

MorphLink: Bridging Cell Morphological Behaviors and Molecular Dynamics in Multi-modal Spatial Omics

Multi-modal spatial omics data are invaluable for exploring complex cellular behaviors in diseases from both morphological and molecular perspectives. Current analytical methods primarily focus on clustering and classification, and do not adequately examine the relationship between cell morphology and molecular dynamics. Here, we present MorphLink, a framework designed to systematically identify disease-related morphological-molecular interplays. MorphLink has been evaluated across a wide array of datasets, showcasing its effectiveness in extracting and linking interpretable morphological features with various molecular measurements in multi-modal spatial omics analyses. These linkages provide a transparent depiction of cellular behaviors that drive transcriptomic heterogeneity and immune diversity across different regions within diseased tissues, such as cancer. Additionally, MorphLink is scalable and robust against cross-sample batch effects, making it an efficient method for integrative spatial omics data analysis across samples, cohorts, and modalities, and enhancing the interpretation of results for large-scale studies.

Cell-vision fusion: A Swin transformer-based approach for predicting kinase inhibitor mechanism of action from Cell Painting data

Image-based profiling of the cellular response to drug compounds has proven effective at characterizing the morphological changes resulting from perturbation experiments. As data availability increases, however, there are growing demands for novel deep-learning methods. We applied the SwinV2 computer vision architecture to predict the mechanism of action of 10 kinase inhibitor compounds directly from Cell Painting images. This method outperforms the standard approach of using image-based profiles (IBP)-multidimensional feature set representations generated by bioimaging software. Furthermore, our fusion approach-cell-vision fusion, combining three different data modalities, images, IBPs, and chemical structures-achieved 69.79% accuracy and 70.56% F1 score, 4.20% and 5.49% higher, respectively, than the best-performing IBP method. We provide three techniques, specific to Cell Painting images, which enable deep-learning architectures to train effectively and demonstrate approaches to combat the significant batch effects present in large Cell Painting datasets.

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 severely limit community-wide efforts to integrate and interpret image-based profiling data collected across different laboratories and equipment. To address this problem, we benchmark ten high-performing single-cell RNA sequencing (scRNA-seq) batch correction techniques, representing diverse approaches, using a newly released Cell Painting dataset, JUMP. We focus on five scenarios with varying complexity, ranging from batches prepared in a single lab over time to batches imaged using different microscopes in multiple labs. We find that Harmony and Seurat RPCA are noteworthy, consistently ranking among the top three methods for all tested scenarios while maintaining computational efficiency. Our proposed framework, benchmark, and metrics can be used to assess new batch correction methods in the future. This work paves the way for improvements that enable the community to make the best use of public Cell Painting data for scientific discovery.

Changes in the Expression of Genes Regulating the Response to Hypoxia, Inflammation, Cell Cycle, Apoptosis, and Epithelial Barrier Functioning during Colitis-Associated Colorectal Cancer Depend on Individual Hypoxia Tolerance

One of the factors contributing to colorectal cancer (CRC) development is inflammation, which is mostly hypoxia-associated. This study aimed to characterize the morphological and molecular biological features of colon tumors in mice that were tolerant and susceptible to hypoxia based on colitis-associated CRC (CAC). Hypoxia tolerance was assessed through a gasping time evaluation in a decompression chamber. One month later, the animals were experimentally modeled for colitis-associated CRC by intraperitoneal azoxymethane administration and three dextran sulfate sodium consumption cycles. The incidence of tumor development in the distal colon in the susceptible to hypoxia mice was two times higher and all tumors (100%) were represented by adenocarcinomas, while in the tolerant mice, only 14% were adenocarcinomas and 86% were glandular intraepithelial neoplasia. The tumor area assessed on serially stepped sections was statistically significantly higher in the susceptible animals. The number of macrophages, CD3-CD19+, CD3+CD4+, and NK cells in tumors did not differ between animals; however, the number of CD3+CD8+ and vimentin+ cells was higher in the susceptible mice. Changes in the expression of genes regulating the response to hypoxia, inflammation, cell cycle, apoptosis, and epithelial barrier functioning in tumors and the peritumoral area depended on the initial mouse's hypoxia tolerance, which should be taken into account for new CAC diagnostics and treatment approaches development.

Data Efficiency, Dimensionality Reduction, and the Generalized Symmetric Information Bottleneck

The symmetric information bottleneck (SIB), an extension of the more familiar information bottleneck, is a dimensionality-reduction technique that simultaneously compresses two random variables to preserve information between their compressed versions. We introduce the generalized symmetric information bottleneck (GSIB), which explores different functional forms of the cost of such simultaneous reduction. We then explore the data set size requirements of such simultaneous compression. We do this by deriving bounds and root-mean-squared estimates of statistical fluctuations of the involved loss functions. We show that in typical situations, the simultaneous GSIB compression requires qualitatively less data to achieve the same errors compared to compressing variables one at a time. We suggest that this is an example of a more general principle that simultaneous compression is more data efficient than independent compression of each of the input variables.

Anomaly detection for high-content image-based phenotypic cell profiling

High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology.

Morphological profiling for drug discovery in the era of deep learning

Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high throughput. These efforts have facilitated understanding of compound mechanism of action, drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering- and deep learning-based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.

A Decade in a Systematic Review: The Evolution and Impact of Cell Painting

High-content image-based assays have fueled significant discoveries in the life sciences in the past decade (2013-2023), including novel insights into disease etiology, mechanism of action, new therapeutics, and toxicology predictions. Here, we systematically review the substantial methodological advancements and applications of Cell Painting. Advancements include improvements in the Cell Painting protocol, assay adaptations for different types of perturbations and applications, and improved methodologies for feature extraction, quality control, and batch effect correction. Moreover, machine learning methods recently surpassed classical approaches in their ability to extract biologically useful information from Cell Painting images. Cell Painting data have been used alone or in combination with other - omics data to decipher the mechanism of action of a compound, its toxicity profile, and many other biological effects. Overall, key methodological advances have expanded Cell Painting's ability to capture cellular responses to various perturbations. Future advances will likely lie in advancing computational and experimental techniques, developing new publicly available datasets, and integrating them with other high-content data types.

A Decade in a Systematic Review: The Evolution and Impact of Cell Painting

High-content image-based assays have fueled significant discoveries in the life sciences in the past decade (2013-2023), including novel insights into disease etiology, mechanism of action, new therapeutics, and toxicology predictions. Here, we systematically review the substantial methodological advancements and applications of Cell Painting. Advancements include improvements in the Cell Painting protocol, assay adaptations for different types of perturbations and applications, and improved methodologies for feature extraction, quality control, and batch effect correction. Moreover, machine learning methods recently surpassed classical approaches in their ability to extract biologically useful information from Cell Painting images. Cell Painting data have been used alone or in combination with other -omics data to decipher the mechanism of action of a compound, its toxicity profile, and many other biological effects. Overall, key methodological advances have expanded Cell Painting's ability to capture cellular responses to various perturbations. Future advances will likely lie in advancing computational and experimental techniques, developing new publicly available datasets, and integrating them with other high-content data types.

Autocorrelation analysis of a phenotypic screen reveals hidden drug activity

Phenotype based screening is a powerful tool to evaluate cellular drug response. Through high content fluorescence imaging of simple fluorescent labels and complex image analysis phenotypic measurements can identify subtle compound-induced cellular changes unique to compound mechanisms of action (MoA). Recently, a screen of 1008 compounds in three cell lines was reported where analysis detected changes in cellular phenotypes and accurately identified compound MoA for roughly half the compounds. However, we were surprised that DNA alkylating agents and other compounds known to induce or impact the DNA damage response produced no measured activity in cells with fluorescently labeled 53BP1-a canonical DNA damage marker. We hypothesized that phenotype analysis is not sensitive enough to detect small changes in 53BP1 distribution and analyzed the screen images with autocorrelation image analysis. We found that autocorrelation analysis, which quantifies fluorescently-labeled protein clustering, identified higher compound activity for compounds and MoAs known to impact the DNA damage response, suggesting altered 53BP1 recruitment to damaged DNA sites. We then performed experiments under more ideal imaging settings and found autocorrelation analysis to be a robust measure of changes to 53BP1 clustering in the DNA damage response. These results demonstrate the capacity of autocorrelation to detect otherwise undetectable compound activity and suggest that autocorrelation analysis of specific proteins could serve as a powerful screening tool.

Compound Activity Prediction with Dose-Dependent Transcriptomic Profiles and Deep Learning

Predicting compound activity in assays is a long-standing challenge in drug discovery. Computational models based on compound-induced gene expression signatures from a single profiling assay have shown promise toward predicting compound activity in other, seemingly unrelated, assays. Applications of such models include predicting mechanisms-of-action (MoA) for phenotypic hits, identifying off-target activities, and identifying polypharmacologies. Here, we introduce transcriptomics-to-activity transformer (TAT) models that leverage gene expression profiles observed over compound treatment at multiple concentrations to predict the compound activity in other biochemical or cellular assays. We built TAT models based on gene expression data from a RASL-seq assay to predict the activity of 2692 compounds in 262 dose-response assays. We obtained useful models for 51% of the assays, as determined through a realistic held-out set. Prospectively, we experimentally validated the activity predictions of a TAT model in a malaria inhibition assay. With a 63% hit rate, TAT successfully identified several submicromolar malaria inhibitors. Our results thus demonstrate the potential of transcriptomic responses over compound concentration and the TAT modeling framework as a cost-efficient way to identify the bioactivities of promising compounds across many assays.

Unraveling the genetics of arsenic toxicity with cellular morphology QTL

The health risks that arise from environmental exposures vary widely within and across human populations, and these differences are largely determined by genetic variation and gene-by-environment (gene-environment) interactions. However, risk assessment in laboratory mice typically involves isogenic strains and therefore, does not account for these known genetic effects. In this context, genetically heterogenous cell lines from laboratory mice are promising tools for population-based screening because they provide a way to introduce genetic variation in risk assessment without increasing animal use. Cell lines from genetic reference populations of laboratory mice offer genetic diversity, power for genetic mapping, and potentially, predictive value for in vivo experimentation in genetically matched individuals. To explore this further, we derived a panel of fibroblast lines from a genetic reference population of laboratory mice (the Diversity Outbred, DO). We then used high-content imaging to capture hundreds of cell morphology traits in cells exposed to the oxidative stress-inducing arsenic metabolite monomethylarsonous acid (MMAIII). We employed dose-response modeling to capture latent parameters of response and we then used these parameters to identify several hundred cell morphology quantitative trait loci (cmQTL). Response cmQTL encompass genes with established associations with cellular responses to arsenic exposure, including Abcc4 and Txnrd1, as well as novel gene candidates like Xrcc2. Moreover, baseline trait cmQTL highlight the influence of natural variation on fundamental aspects of nuclear morphology. We show that the natural variants influencing response include both coding and non-coding variation, and that cmQTL haplotypes can be used to predict response in orthogonal cell lines. Our study sheds light on the major molecular initiating events of oxidative stress that are under genetic regulation, including the NRF2-mediated antioxidant response, cellular detoxification pathways, DNA damage repair response, and cell death trajectories.

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.

Resource allocation in mammalian systems

Cells execute biological functions to support phenotypes such as growth, migration, and secretion. Complementarily, each function of a cell has resource costs that constrain phenotype. Resource allocation by a cell allows it to manage these costs and optimize their phenotypes. In fact, the management of resource constraints (e.g., nutrient availability, bioenergetic capacity, and macromolecular machinery production) shape activity and ultimately impact phenotype. In mammalian systems, quantification of resource allocation provides important insights into higher-order multicellular functions; it shapes intercellular interactions and relays environmental cues for tissues to coordinate individual cells to overcome resource constraints and achieve population-level behavior. Furthermore, these constraints, objectives, and phenotypes are context-dependent, with cells adapting their behavior according to their microenvironment, resulting in distinct steady-states. This review will highlight the biological insights gained from probing resource allocation in mammalian cells and tissues.

VIBRANT: spectral profiling for single-cell drug responses

High-content cell profiling has proven invaluable for single-cell phenotyping in response to chemical perturbations. However, methods with improved throughput, information content and affordability are still needed. We present a new high-content spectral profiling method named vibrational painting (VIBRANT), integrating mid-infrared vibrational imaging, multiplexed vibrational probes and an optimized data analysis pipeline for measuring single-cell drug responses. Three infrared-active vibrational probes were designed to measure distinct essential metabolic activities in human cancer cells. More than 20,000 single-cell drug responses were collected, corresponding to 23 drug treatments. The resulting spectral profile is highly sensitive to phenotypic changes under drug perturbation. Using this property, we built a machine learning classifier to accurately predict drug mechanism of action at single-cell level with minimal batch effects. We further designed an algorithm to discover drug candidates with new mechanisms of action and evaluate drug combinations. Overall, VIBRANT has demonstrated great potential across multiple areas of phenotypic screening.

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.

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.

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.

stMMR: accurate and robust spatial domain identification from spatially resolved transcriptomics with multimodal feature representation

BACKGROUND

Deciphering spatial domains using spatially resolved transcriptomics (SRT) is of great value for characterizing and understanding tissue architecture. However, the inherent heterogeneity and varying spatial resolutions present challenges in the joint analysis of multimodal SRT data.

RESULTS

We introduce a multimodal geometric deep learning method, named stMMR, to effectively integrate gene expression, spatial location, and histological information for accurate identifying spatial domains from SRT data. stMMR uses graph convolutional networks and a self-attention module for deep embedding of features within unimodality and incorporates similarity contrastive learning for integrating features across modalities.

CONCLUSIONS

Comprehensive benchmark analysis on various types of spatial data shows superior performance of stMMR in multiple analyses, including spatial domain identification, pseudo-spatiotemporal analysis, and domain-specific gene discovery. In chicken heart development, stMMR reconstructed the spatiotemporal lineage structures, indicating an accurate developmental sequence. In breast cancer and lung cancer, stMMR clearly delineated the tumor microenvironment and identified marker genes associated with diagnosis and prognosis. Overall, stMMR is capable of effectively utilizing the multimodal information of various SRT data to explore and characterize tissue architectures of homeostasis, development, and tumor.

Particulate matter composition drives differential molecular and morphological responses in lung epithelial cells

Particulate matter (PM) is a ubiquitous component of air pollution that is epidemiologically linked to human pulmonary diseases. PM chemical composition varies widely, and the development of high-throughput experimental techniques enables direct profiling of cellular effects using compositionally unique PM mixtures. Here, we show that in a human bronchial epithelial cell model, exposure to three chemically distinct PM mixtures drive unique cell viability patterns, transcriptional remodeling, and the emergence of distinct morphological subtypes. Specifically, PM mixtures modulate cell viability, DNA damage responses, and induce the remodeling of gene expression associated with cell morphology, extracellular matrix organization, and cellular motility. Profiling cellular responses showed that cell morphologies change in a PM composition-dependent manner. Finally, we observed that PM mixtures with higher cadmium content induced increased DNA damage and drove redistribution among morphological subtypes. Our results demonstrate that quantitative measurement of individual cellular morphologies provides a robust, high-throughput approach to gauge the effects of environmental stressors on biological systems and score cellular susceptibilities to pollution.

Cell morphology QTL reveal gene by environment interactions in a genetically diverse cell population

Genetically heterogenous cell lines from laboratory mice are promising tools for population-based screening as they offer power for genetic mapping, and potentially, predictive value for in vivo experimentation in genetically matched individuals. To explore this further, we derived a panel of fibroblast lines from a genetic reference population of laboratory mice (the Diversity Outbred, DO). We then used high-content imaging to capture hundreds of cell morphology traits in cells exposed to the oxidative stress-inducing arsenic metabolite monomethylarsonous acid (MMAIII). We employed dose-response modeling to capture latent parameters of response and we then used these parameters to identify several hundred cell morphology quantitative trait loci (cmQTL). Response cmQTL encompass genes with established associations with cellular responses to arsenic exposure, including Abcc4 and Txnrd1, as well as novel gene candidates like Xrcc2. Moreover, baseline trait cmQTL highlight the influence of natural variation on fundamental aspects of nuclear morphology. We show that the natural variants influencing response include both coding and non-coding variation, and that cmQTL haplotypes can be used to predict response in orthogonal cell lines. Our study sheds light on the major molecular initiating events of oxidative stress that are under genetic regulation, including the NRF2-mediated antioxidant response, cellular detoxification pathways, DNA damage repair response, and cell death trajectories.

DICTrank: The largest reference list of 1318 human drugs ranked by risk of drug-induced cardiotoxicity using FDA labeling

Drug-induced cardiotoxicity (DICT) is a leading cause of drug trial failure and discontinuation. Current drug annotations for cardiotoxicity largely focus on individual outcomes or mechanisms. Considering the broad spectrum of adverse cardiac events, we developed Drug-Induced Cardiotoxicity Rank (DICTrank) using FDA labeling and comprehensively classified 1318 human drugs into four categories: Most-DICT-Concern (n = 341), Less-DICT-Concern (n = 528), No-DICT-Concern (n = 343), and Ambiguous-DICT-Concern (n = 106). Notably, DICTrank covers diverse therapeutic categories, of which several were enriched with Most-DICT-Concern drugs, such as antineoplastic agents, sex hormones, anti-inflammatory drugs, beta-blockers, and cardiac therapy. DICTrank currently presents the largest drug list of DICT annotation, and it could contribute to the development of new approach methods, including AI models for early identification of DICT risk during drug development and beyond.

Reversing pathological cell states: the road less travelled can extend the therapeutic horizon

Acquisition of omics data advances at a formidable pace. Yet, our ability to utilize these data to control cell phenotypes and design interventions that reverse pathological states lags behind. Here, we posit that cell states are determined by core networks that control cell-wide networks. To steer cell fate decisions, core networks connecting genotype to phenotype must be reconstructed and understood. A recent method, cell state transition assessment and regulation (cSTAR), applies perturbation biology to quantify causal connections and mechanistically models how core networks influence cell phenotypes. cSTAR models are akin to digital cell twins enabling us to purposefully convert pathological states back to physiologically normal states. While this capability has a range of applications, here we discuss reverting oncogenic transformation.

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.

Optimizing the Cell Painting assay for image-based profiling

In image-based profiling, software extracts thousands of morphological features of cells from multi-channel fluorescence microscopy images, yielding single-cell profiles that can be used for basic research and drug discovery. Powerful applications have been proven, including clustering chemical and genetic perturbations on the basis of their similar morphological impact, identifying disease phenotypes by observing differences in profiles between healthy and diseased cells and predicting assay outcomes by using machine learning, among many others. Here, we provide an updated protocol for the most popular assay for image-based profiling, Cell Painting. Introduced in 2013, it uses six stains imaged in five channels and labels eight diverse components of the cell: DNA, cytoplasmic RNA, nucleoli, actin, Golgi apparatus, plasma membrane, endoplasmic reticulum and mitochondria. The original protocol was updated in 2016 on the basis of several years' experience running it at two sites, after optimizing it by visual stain quality. Here, we describe the work of the Joint Undertaking for Morphological Profiling Cell Painting Consortium, to improve upon the assay via quantitative optimization by measuring the assay's ability to detect morphological phenotypes and group similar perturbations together. The assay gives very robust outputs despite various changes to the protocol, and two vendors' dyes work equivalently well. We present Cell Painting version 3, in which some steps are simplified and several stain concentrations can be reduced, saving costs. Cell culture and image acquisition take 1-2 weeks for typically sized batches of ≤20 plates; feature extraction and data analysis take an additional 1-2 weeks.This protocol is an update to Nat. Protoc. 11, 1757-1774 (2016): https://doi.org/10.1038/nprot.2016.105.

Optimized cell type signatures revealed from single-cell data by combining principal feature analysis, mutual information, and machine learning

Machine learning techniques are excellent to analyze expression data from single cells. These techniques impact all fields ranging from cell annotation and clustering to signature identification. The presented framework evaluates gene selection sets how far they optimally separate defined phenotypes or cell groups. This innovation overcomes the present limitation to objectively and correctly identify a small gene set of high information content regarding separating phenotypes for which corresponding code scripts are provided. The small but meaningful subset of the original genes (or feature space) facilitates human interpretability of the differences of the phenotypes including those found by machine learning results and may even turn correlations between genes and phenotypes into a causal explanation. For the feature selection task, the principal feature analysis is utilized which reduces redundant information while selecting genes that carry the information for separating the phenotypes. In this context, the presented framework shows explainability of unsupervised learning as it reveals cell-type specific signatures. Apart from a Seurat preprocessing tool and the PFA script, the pipeline uses mutual information to balance accuracy and size of the gene set if desired. A validation part to evaluate the gene selection for their information content regarding the separation of the phenotypes is provided as well, binary and multiclass classification of 3 or 4 groups are studied. Results from different single-cell data are presented. In each, only about ten out of more than 30000 genes are identified as carrying the relevant information. The code is provided in a GitHub repository at https://github.com/AC-PHD/Seurat_PFA_pipeline.

Merging bioactivity predictions from cell morphology and chemical fingerprint models using similarity to training data

The applicability domain of machine learning models trained on structural fingerprints for the prediction of biological endpoints is often limited by the lack of diversity of chemical space of the training data. In this work, we developed similarity-based merger models which combined the outputs of individual models trained on cell morphology (based on Cell Painting) and chemical structure (based on chemical fingerprints) and the structural and morphological similarities of the compounds in the test dataset to compounds in the training dataset. We applied these similarity-based merger models using logistic regression models on the predictions and similarities as features and predicted assay hit calls of 177 assays from ChEMBL, PubChem and the Broad Institute (where the required Cell Painting annotations were available). We found that the similarity-based merger models outperformed other models with an additional 20% assays (79 out of 177 assays) with an AUC > 0.70 compared with 65 out of 177 assays using structural models and 50 out of 177 assays using Cell Painting models. Our results demonstrated that similarity-based merger models combining structure and cell morphology models can more accurately predict a wide range of biological assay outcomes and further expanded the applicability domain by better extrapolating to new structural and morphology spaces.

Application of Cell Painting for chemical hazard evaluation in support of screening-level chemical assessments

'Cell Painting' is an imaging-based high-throughput phenotypic profiling (HTPP) method in which cultured cells are fluorescently labeled to visualize subcellular structures (i.e., nucleus, nucleoli, endoplasmic reticulum, cytoskeleton, Golgi apparatus / plasma membrane and mitochondria) and to quantify morphological changes in response to chemicals or other perturbagens. HTPP is a high-throughput and cost-effective bioactivity screening method that detects effects associated with many different molecular mechanisms in an untargeted manner, enabling rapid in vitro hazard assessment for thousands of chemicals. Here, 1201 chemicals from the ToxCast library were screened in concentration-response up to ∼100 μM in human U-2 OS cells using HTPP. A phenotype altering concentration (PAC) was estimated for chemicals active in the tested range. PACs tended to be higher than lower bound potency values estimated from a broad collection of targeted high-throughput assays, but lower than the threshold for cytotoxicity. In vitro to in vivo extrapolation (IVIVE) was used to estimate administered equivalent doses (AEDs) based on PACs for comparison to human exposure predictions. AEDs for 18/412 chemicals overlapped with predicted human exposures. Phenotypic profile information was also leveraged to identify putative mechanisms of action and group chemicals. Of 58 known nuclear receptor modulators, only glucocorticoids and retinoids produced characteristic profiles; and both receptor types are expressed in U-2 OS cells. Thirteen chemicals with profile similarity to glucocorticoids were tested in a secondary screen and one chemical, pyrene, was confirmed by an orthogonal gene expression assay as a novel putative GR modulating chemical. Most active chemicals demonstrated profiles not associated with a known mechanism-of-action. However, many structurally related chemicals produced similar profiles, with exceptions such as diniconazole, whose profile differed from other active conazoles. Overall, the present study demonstrates how HTPP can be applied in screening-level chemical assessments through a series of examples and brief case studies.

Toward a systems-level probing of tumor clonality

Cancer has been described as a genetic disease that clonally evolves in the face of selective pressures imposed by cell-intrinsic and extrinsic factors. Although classical models based on genetic data predominantly propose Darwinian mechanisms of cancer evolution, recent single-cell profiling of cancers has described unprecedented heterogeneity in tumors providing support for alternative models of branched and neutral evolution through both genetic and non-genetic mechanisms. Emerging evidence points to a complex interplay between genetic, non-genetic, and extrinsic environmental factors in shaping the evolution of tumors. In this perspective, we briefly discuss the role of cell-intrinsic and extrinsic factors that shape clonal behaviors during tumor progression, metastasis, and drug resistance. Taking examples of pre-malignant states associated with hematological malignancies and esophageal cancer, we discuss recent paradigms of tumor evolution and prospective approaches to further enhance our understanding of this spatiotemporally regulated process.

Using Transcriptomics and Cell Morphology Data in Drug Discovery: The Long Road to Practice

Gene expression and cell morphology data are high-dimensional biological readouts of much recent interest for drug discovery. They are able to describe biological systems in different states (e.g., healthy and diseased), as well as biological systems before and after compound treatment, and they are hence useful for matching both spaces (e.g., for drug repurposing) as well as for characterizing compounds with respect to efficacy and safety endpoints. This Microperspective describes recent advances in this direction with a focus on applied drug discovery and drug repurposing, as well as outlining what else is needed to advance further, with a particular focus on better understanding the applicability domain of readouts and their relevance for decision making, which is currently often still unclear.

Computational drug repurposing by exploiting large-scale gene expression data: Strategy, methods and applications

De novo drug development is an extremely complex, time-consuming and costly task. Urgent needs for therapies of various diseases have greatly accelerated searches for more effective drug development methods. Luckily, drug repurposing provides a new and effective perspective on disease treatment. Rapidly increased large-scale transcriptome data paints a detailed prospect of gene expression during disease onset and thus has received wide attention in the field of computational drug repurposing. However, how to efficiently mine transcriptome data and identify new indications for old drugs remains a critical challenge. This review discussed the irreplaceable role of transcriptome data in computational drug repurposing and summarized some representative databases, tools and strategies. More importantly, it proposed a practical guideline through establishing the correspondence between three gene expression data types and five strategies, which would facilitate researchers to adopt appropriate strategies to deeply mine large-scale transcriptome data and discover more effective therapies.