Image-based profiling for drug discovery: due for a machine-learning upgrade?

Decoding phenotypic screening: A comparative analysis of image representations

Biomedical imaging techniques such as high content screening (HCS) are valuable for drug discovery, but high costs limit their use to pharmaceutical companies. To address this issue, The JUMP-CP consortium released a massive open image dataset of chemical and genetic perturbations, providing a valuable resource for deep learning research. In this work, we aim to utilize the JUMP-CP dataset to develop a universal representation model for HCS data, mainly data generated using U2OS cells and CellPainting protocol, using supervised and self-supervised learning approaches. We propose an evaluation protocol that assesses their performance on mode of action and property prediction tasks using a popular phenotypic screening dataset. Results show that the self-supervised approach that uses data from multiple consortium partners provides representation that is more robust to batch effects whilst simultaneously achieving performance on par with standard approaches. Together with other conclusions, it provides recommendations on the training strategy of a representation model for HCS images.

In-cell chemical construction of a photoswitchable CENP-E using a photochromic covalent inhibitor

An arylazopyrazole-based covalent inhibitor targeting the mitotic motor protein of centromere-associated protein E (CENP-E) was developed. Using this photoswitchable inhibitor, a photoswitchable CENP-E was chemically constructed in cells, which enabled to local control of mitotic cell division with light illumination.

Embedded monitoring system and teaching of artificial intelligence online drug component recognition

Drug testing has many test elements. It aims to prevent unqualified drugs from entering the market and ensure drug safety. The existing artificial intelligence (AI) online monitoring system identifies active ingredients in the process of use. Owing to their openness, data are easy to be lost, failing to meet user needs and inducing a specific impact on the use of the monitoring system. With the continuous development of computer and measurement technologies, various biochemical data are increasing at an unprecedented speed, and numerous databases are emerging. Extracting patterns from considerable known data and experimental facts is an essential task for a wide range of biological and chemical workers. Pattern recognition is one of the essential technologies for data mining. It is widely used in industry, agriculture, national defense, biomedicine, meteorology, astronomy, and other fields. To improve the effect of the online drug ingredient recognition system, this study used AI to design an online drug ingredient recognition-embedded monitoring system and applied AI to the teaching field to improve teaching efficiency. First, this study constructed the framework of the AI online drug ingredient recognition-embedded monitoring system and introduced the process of online drug ingredient recognition. Then, it introduced the pattern recognition method, constructed the pattern recognition system, and presented the pattern recognition algorithm and the algorithm evaluation index. Afterward, it used pattern recognition to conduct a qualitative analysis of the infrared spectrum of drug components and introduced the overall process of the qualitative analysis. In addition, this study employed AI to implement changes to the embedded system instruction in colleges and universities, summarizing the current issues. The impact of drug component recognition and the educational impact of embedded systems were investigated in the experimental portion. The experimental findings demonstrated the excellent accuracy, sensitivity, specificity, and Matthew correlation coefficient of the online drug component recognition-integrated monitoring system in this work. Compared with that of other systems, its average drug component recognition accuracy was above 0.85. Students in five majors reported high levels of satisfaction with the embedded system teaching, which is better for delivering college instruction.

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.

Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations

The identification of genetic and chemical perturbations with similar impacts on cell morphology can elucidate compounds' mechanisms of action or novel regulators of genetic pathways. Research on methods for identifying such similarities has lagged due to a lack of carefully designed and well-annotated image sets of cells treated with chemical and genetic perturbations. Here we create such a Resource dataset, CPJUMP1, in which each perturbed gene's product is a known target of at least two chemical compounds in the dataset. We systematically explore the directionality of correlations among perturbations that target the same protein encoded by a given gene, and we find that identifying matches between chemical and genetic perturbations is a challenging task. Our dataset and baseline analyses provide a benchmark for evaluating methods that measure perturbation similarities and impact, and more generally, learn effective representations of cellular state from microscopy images. Such advancements would accelerate the applications of image-based profiling of cellular states, such as uncovering drug mode of action or probing functional genomics.

Artificial intelligence for high content imaging in drug discovery

Artificial intelligence (AI) and high-content imaging (HCI) are contributing to advancements in drug discovery, propelled by the recent progress in deep neural networks. This review highlights AI's role in analysis of HCI data from fixed and live-cell imaging, enabling novel label-free and multi-channel fluorescent screening methods, and improving compound profiling. HCI experiments are rapid and cost-effective, facilitating large data set accumulation for AI model training. However, the success of AI in drug discovery also depends on high-quality data, reproducible experiments, and robust validation to ensure model performance. Despite challenges like the need for annotated compounds and managing vast image data, AI's potential in phenotypic screening and drug profiling is significant. Future improvements in AI, including increased interpretability and integration of multiple modalities, are expected to solidify AI and HCI's role in drug discovery.

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.

Genome-scale requirements for dynein-based transport revealed by a high-content arrayed CRISPR screen

The microtubule motor dynein plays a key role in cellular organization. However, little is known about how dynein's biosynthesis, assembly, and functional diversity are orchestrated. To address this issue, we have conducted an arrayed CRISPR loss-of-function screen in human cells using the distribution of dynein-tethered peroxisomes and early endosomes as readouts. From a genome-wide gRNA library, 195 validated hits were recovered and parsed into those impacting multiple dynein cargoes and those whose effects are restricted to a subset of cargoes. Clustering of high-dimensional phenotypic fingerprints revealed co-functional proteins involved in many cellular processes, including several candidate novel regulators of core dynein functions. Further analysis of one of these factors, the RNA-binding protein SUGP1, indicates that it promotes cargo trafficking by sustaining functional expression of the dynein activator LIS1. Our data represent a rich source of new hypotheses for investigating microtubule-based transport, as well as several other aspects of cellular organization captured by our high-content imaging.

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.

Image-based profiling and deep learning reveal morphological heterogeneity of colorectal cancer organoids

Patient-derived organoids have proven to be a highly relevant model for evaluating of disease mechanisms and drug efficacies, as they closely recapitulate in vivo physiology. Colorectal cancer organoids, specifically, exhibit a diverse range of morphologies, which have been analyzed with image-based profiling. However, the relationship between morphological subtypes and functional parameters of the organoids remains underexplored. Here, we identified two distinct morphological subtypes ("cystic" and "solid") across 31360 bright field images using image-based profiling, which correlated differently with viability and apoptosis level of colorectal cancer organoids. Leveraging object detection neural networks, we were able to categorize single organoids achieving higher viability scores as "cystic" than "solid" subtype. Furthermore, a deep generative model was proposed to predict apoptosis intensity based on a apoptosis-featured dataset encompassing over 17000 bright field and matched fluorescent images. Notably, a significant correlation of 0.91 between the predicted value and ground truth was achived, underscoring the feasibility of this generative model as a potential means for assessing organoid functional parameters. The underlying cellular heterogeneity of the organoids, i.e., conserved colonic cell types and rare immune components, was also verified with scRNA sequencing, implying a compromised tumor microenvironment. Additionally, the "cystic" subtype was identified as a relapse phenotype featuring intestinal stem cell signatures, suggesting that this visually discernible relapse phenotype shows potential as a novel biomarker for colorectal cancer diagnosis and prognosis. In summary, our findings demonstrate that the morphological heterogeneity of colorectal cancer organoids explicitly recapitulate the association of phenotypic features and exogenous perturbations through the image-based profiling, providing new insights into disease mechanisms.

Facts and Hopes in Using Omics to Advance Combined Immunotherapy Strategies

The field of oncology has been transformed by immune checkpoint inhibitors (ICI) and other immune-based agents; however, many patients do not receive a durable benefit. While biomarker assessments from pivotal ICI trials have uncovered certain mechanisms of resistance, results thus far have only scraped the surface. Mechanisms of resistance are as complex as the tumor microenvironment (TME) itself, and the development of effective therapeutic strategies will only be possible by building accurate models of the tumor-immune interface. With advancement of multi-omic technologies, high-resolution characterization of the TME is now possible. In addition to sequencing of bulk tumor, single-cell transcriptomic, proteomic, and epigenomic data as well as T-cell receptor profiling can now be simultaneously measured and compared between responders and nonresponders to ICI. Spatial sequencing and imaging platforms have further expanded the dimensionality of existing technologies. Rapid advancements in computation and data sharing strategies enable development of biologically interpretable machine learning models to integrate data from high-resolution, multi-omic platforms. These models catalyze the identification of resistance mechanisms and predictors of benefit in ICI-treated patients, providing scientific foundation for novel clinical trials. Moving forward, we propose a framework by which in silico screening, functional validation, and clinical trial biomarker assessment can be used for the advancement of combined immunotherapy strategies.

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.

A versatile information retrieval framework for evaluating profile strength and similarity

In profiling assays, thousands of biological properties are measured in a single test, yielding biological discoveries by capturing the state of a cell population, often at the single-cell level. However, for profiling datasets, it has been challenging to evaluate the phenotypic activity of a sample and the phenotypic consistency among samples, due to profiles' high dimensionality, heterogeneous nature, and non-linear properties. Existing methods leave researchers uncertain where to draw boundaries between meaningful biological response and technical noise. Here, we developed a statistical framework that uses the well-established mean average precision (mAP) as a single, data-driven metric to bridge this gap. We validated the mAP framework against established metrics through simulations and real-world data applications, revealing its ability to capture subtle and meaningful biological differences in cell state. Specifically, we used mAP to assess both phenotypic activity for a given perturbation (or a sample) as well as consistency within groups of perturbations (or samples) across diverse high-dimensional datasets. We evaluated the framework on different profile types (image, protein, and mRNA profiles), perturbation types (CRISPR gene editing, gene overexpression, and small molecules), and profile resolutions (single-cell and bulk). Our open-source software allows this framework to be applied to identify interesting biological phenomena and promising therapeutics from large-scale profiling data.

Morphological profiling in human neural progenitor cells classifies hits in a pilot drug screen for Alzheimer's disease

Alzheimer's disease accounts for 60-70% of dementia cases. Current treatments are inadequate and there is a need to develop new approaches to drug discovery. Recently, in cancer, morphological profiling has been used in combination with high-throughput screening of small-molecule libraries in human cells in vitro. To test feasibility of this approach for Alzheimer's disease, we developed a cell morphology-based drug screen centred on the risk gene, SORL1 (which encodes the protein SORLA). Increased Alzheimer's disease risk has been repeatedly linked to variants in SORL1, particularly those conferring loss or decreased expression of SORLA, and lower SORL1 levels are observed in post-mortem brain samples from individuals with Alzheimer's disease. Consistent with its role in the endolysosomal pathway, SORL1 deletion is associated with enlarged endosomes in neural progenitor cells and neurons. We, therefore, hypothesized that multi-parametric, image-based cell phenotyping would identify features characteristic of SORL1 deletion. An automated morphological profiling method (Cell Painting) was adapted to neural progenitor cells and used to determine the phenotypic response of SORL1-/- neural progenitor cells to treatment with compounds from a small internationally approved drug library (TargetMol, 330 compounds). We detected distinct phenotypic signatures for SORL1-/- neural progenitor cells compared to isogenic wild-type controls. Furthermore, we identified 16 compounds (representing 14 drugs) that reversed the mutant morphological signatures in neural progenitor cells derived from three SORL1-/- induced pluripotent stem cell sub-clones. Network pharmacology analysis revealed the 16 compounds belonged to five mechanistic groups: 20S proteasome, aldehyde dehydrogenase, topoisomerase I and II, and DNA synthesis inhibitors. Enrichment analysis identified DNA synthesis/damage/repair, proteases/proteasome and metabolism as key pathways/biological processes. Prediction of novel targets revealed enrichment in pathways associated with neural cell function and Alzheimer's disease. Overall, this work suggests that (i) a quantitative phenotypic metric can distinguish induced pluripotent stem cell-derived SORL1-/- neural progenitor cells from isogenic wild-type controls and (ii) phenotypic screening combined with multi-parametric high-content image analysis is a viable option for drug repurposing and discovery in this human neural cell model of Alzheimer's disease.

Computational model for drug research

This special issue focuses on computational model for drug research regarding drug bioactivity prediction, drug-related interaction prediction, modelling for immunotherapy and modelling for treatment of a specific disease, as conveyed by the following six research and four review articles. Notably, these 10 papers described a wide variety of in-depth drug research from the computational perspective and may represent a snapshot of the wide research landscape.

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.

Pooled CRISPR screening of high-content cellular phenotypes using ghost cytometry

Recent advancements in image-based pooled CRISPR screening have facilitated the mapping of diverse genotype-phenotype associations within mammalian cells. However, the rapid enrichment of cells based on morphological information continues to pose a challenge, constraining the capacity for large-scale gene perturbation screening across diverse high-content cellular phenotypes. In this study, we demonstrate the applicability of multimodal ghost cytometry-based cell sorting, including both fluorescent and label-free high-content phenotypes, for rapid pooled CRISPR screening within vast cell populations. Using the high-content cell sorter operating in fluorescence mode, we successfully executed kinase-specific CRISPR screening targeting genes influencing the nuclear translocation of RelA. Furthermore, using the multiparametric, label-free mode, we performed large-scale screening to identify genes involved in macrophage polarization. Notably, the label-free platform can enrich target phenotypes without requiring invasive staining, preserving untouched cells for downstream assays and expanding the potential for screening cellular phenotypes even when suitable markers are absent.

From pixels to phenotypes: Integrating image-based profiling with cell health data as BioMorph features improves interpretability

Cell Painting assays generate morphological profiles that are versatile descriptors of biological systems and have been used to predict in vitro and in vivo drug effects. However, Cell Painting features extracted from classical software such as CellProfiler are based on statistical calculations and often not readily biologically interpretable. In this study, we propose a new feature space, which we call BioMorph, that maps these Cell Painting features with readouts from comprehensive Cell Health assays. We validated that the resulting BioMorph space effectively connected compounds not only with the morphological features associated with their bioactivity but with deeper insights into phenotypic characteristics and cellular processes associated with the given bioactivity. The BioMorph space revealed the mechanism of action for individual compounds, including dual-acting compounds such as emetine, an inhibitor of both protein synthesis and DNA replication. Overall, BioMorph space offers a biologically relevant way to interpret the cell morphological features derived using software such as CellProfiler and to generate hypotheses for experimental validation.

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.

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.

Natural products in osteoarthritis treatment: bridging basic research to clinical applications

Osteoarthritis (OA) is the most prevalent degenerative musculoskeletal disease, severely impacting the function of patients and potentially leading to disability, especially among the elderly population. Natural products (NPs), obtained from components or metabolites of plants, animals, microorganisms etc., have gained significant attention as important conservative treatments for various diseases. Recently, NPs have been well studied in preclinical and clinical researches, showing promising potential in the treatment of OA. In this review, we summed up the main signaling pathways affected by NPs in OA treatment, including NF-κB, MAPKs, PI3K/AKT, SIRT1, and other pathways, which are related to inflammation, anabolism and catabolism, and cell death. In addition, we described the therapeutic effects of NPs in different OA animal models and the current clinical studies in OA patients. At last, we discussed the potential research directions including in-depth analysis of the mechanisms and new application strategies of NPs for the OA treatment, so as to promote the basic research and clinical transformation in the future. We hope that this review may allow us to get a better understanding about the potential bioeffects and mechanisms of NPs in OA therapy, and ultimately improve the effectiveness of NPs-based clinical conservative treatment for OA patients.

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.

Is fragment-based graph a better graph-based molecular representation for drug design? A comparison study of graph-based models

Graph Neural Networks (GNNs) have gained significant traction in various sectors of AI-driven drug design. Over recent years, the integration of fragmentation concepts into GNNs has emerged as a potent strategy to augment the efficacy of molecular generative models. Nonetheless, challenges such as symmetry breaking and potential misrepresentation of intricate cycles and undefined functional groups raise questions about the superiority of fragment-based graph representation over traditional methods. In our research, we undertook a rigorous evaluation, contrasting the predictive prowess of eight models-developed using deep learning algorithms-across 12 benchmark datasets that span a range of properties. These models encompass established methods like GCN, AttentiveFP, and D-MPNN, as well as innovative fragment-based representation techniques. Our results indicate that fragment-based methodologies, notably PharmHGT, significantly improve model performance and interpretability, particularly in scenarios characterized by limited data availability. However, in situations with extensive training, fragment-based molecular graph representations may not necessarily eclipse traditional methods. In summation, we posit that the integration of fragmentation, as an avant-garde technique in drug design, harbors considerable promise for the future of AI-enhanced drug design.

High-Content Image-Based Screening and Deep Learning for the Detection of Anti-Inflammatory Drug Leads

We developed a high-content image-based screen that utilizes the pro-inflammatory stimulus lipopolysaccharide (LPS) and murine macrophages (RAW264.7) with the goal of enabling the identification of novel anti-inflammatory lead compounds. We screened 2,259 bioactive compounds with annotated mechanisms of action (MOA) to identify compounds that block the LPS-induced phenotype in macrophages. We utilized a set of seven fluorescence microscopy probes to generate images that were used to train and optimize a deep neural network classifier to distinguish between unstimulated and LPS-stimulated macrophages. The top hits from the deep learning classifier were validated using a linear classifier trained on individual cells and subsequently investigated in a multiplexed cytokine secretion assay. All 12 hits significantly modulated the expression of at least one cytokine upon LPS stimulation. Seven of these were allosteric inhibitors of the mitogen-activated protein kinase kinase (MEK1/2) and showed similar effects on cytokine expression. This deep learning morphological assay identified compounds that modulate the innate immune response to LPS and may aid in identifying new anti-inflammatory drug leads.

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.

Advanced optical imaging for the rational design of nanomedicines

Despite the enormous potential of nanomedicines to shape the future of medicine, their clinical translation remains suboptimal. Translational challenges are present in every step of the development pipeline, from a lack of understanding of patient heterogeneity to insufficient insights on nanoparticle properties and their impact on material-cell interactions. Here, we discuss how the adoption of advanced optical microscopy techniques, such as super-resolution optical microscopies, correlative techniques, and high-content modalities, could aid the rational design of nanocarriers, by characterizing the cell, the nanomaterial, and their interaction with unprecedented spatial and/or temporal detail. In this nanomedicine arena, we will discuss how the implementation of these techniques, with their versatility and specificity, can yield high volumes of multi-parametric data; and how machine learning can aid the rapid advances in microscopy: from image acquisition to data interpretation.

Investigation of normalization procedures for transcriptome profiles of compounds oriented toward practical study design

The transcriptome profile is a representative phenotype-based descriptor of compounds, widely acknowledged for its ability to effectively capture compound effects. However, the presence of batch differences is inevitable. Despite the existence of sophisticated statistical methods, many of them presume a substantial sample size. How should we design a transcriptome analysis to obtain robust compound profiles, particularly in the context of small datasets frequently encountered in practical scenarios? This study addresses this question by investigating the normalization procedures for transcriptome profiles, focusing on the baseline distribution employed in deriving biological responses as profiles. Firstly, we investigated two large GeneChip datasets, comparing the impact of different normalization procedures. Through an evaluation of the similarity between response profiles of biological replicates within each dataset and the similarity between response profiles of the same compound across datasets, we revealed that the baseline distribution defined by all samples within each batch under batch-corrected condition is a good choice for large datasets. Subsequently, we conducted a simulation to explore the influence of the number of control samples on the robustness of response profiles across datasets. The results offer insights into determining the suitable quantity of control samples for diminutive datasets. It is crucial to acknowledge that these conclusions stem from constrained datasets. Nevertheless, we believe that this study enhances our understanding of how to effectively leverage transcriptome profiles of compounds and promotes the accumulation of essential knowledge for the practical application of such profiles.

High-Throughput 3D Imaging Flow Cytometry of Suspended Adherent 3D Cell Cultures

3D cell cultures are indispensable in recapitulating in vivo environments. Among the many 3D culture methods, culturing adherent cells on hydrogel beads to form spheroid-like structures is a powerful strategy for maintaining high cell viability and functions in the adherent states. However, high-throughput, scalable technologies for 3D imaging of individual cells cultured on the hydrogel scaffolds are lacking. This study reports the development of a high throughput, scalable 3D imaging flow cytometry platform for analyzing spheroid models. This platform is realized by integrating a single objective fluorescence light-sheet microscopy with a microfluidic device that combines hydrodynamic and acoustofluidic focusing techniques. This integration enabled unprecedentedly high-throughput and scalable optofluidic 3D imaging, processing 1310 spheroids consisting of 28 117 cells min-1 . The large dataset obtained enables precise quantification and comparison of the nuclear morphology of adhering and suspended cells, revealing that the adhering cells have smaller nuclei with less rounded surfaces. This platform's high throughput, robustness, and precision for analyzing the morphology of subcellular structures in 3D culture models hold promising potential for various biomedical analyses, including image-based phenotypic screening of drugs with spheroids or organoids.

A semiconductor 96-microplate platform for electrical-imaging based high-throughput phenotypic screening

High-content imaging for compound and genetic profiling is popular for drug discovery but limited to endpoint images of fixed cells. Conversely, electronic-based devices offer label-free, live cell functional information but suffer from limited spatial resolution or throughput. Here, we introduce a semiconductor 96-microplate platform for high-resolution, real-time impedance imaging. Each well features 4096 electrodes at 25 µm spatial resolution and a miniaturized data interface allows 8× parallel plate operation (768 total wells) for increased throughput. Electric field impedance measurements capture >20 parameter images including cell barrier, attachment, flatness, and motility every 15 min during experiments. We apply this technology to characterize 16 cell types, from primary epithelial to suspension cells, and quantify heterogeneity in mixed co-cultures. Screening 904 compounds across 13 semiconductor microplates reveals 25 distinct responses, demonstrating the platform's potential for mechanism of action profiling. The scalability and translatability of this semiconductor platform expands high-throughput mechanism of action profiling and phenotypic drug discovery applications.

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.

Small-Molecule Probes as Pharmacological Tools for the Bone Morphogenetic Protein Signaling Pathway

The bone morphogenetic protein (BMP) pathway is highly conserved and plays central roles in health and disease. The quality and quantity of its signaling outputs are regulated at multiple levels, offering pharmacological options for targeted modulation. Both target-centric and phenotypic drug discovery (PDD) approaches were applied to identify small-molecule BMP inhibitors and stimulators. In this Review, we accumulated and systematically classified the different reported chemotypes based on their targets as well as modes-of-action, and herein we illustrate the discovery history of selected candidates. A comprehensive summary of available biochemical, cellular, and in vivo activities is provided for the most relevant BMP modulators, along with recommendations on their preferred use as chemical probes to study BMP-related (patho)physiological processes. There are a number of high-quality probes used as BMP inhibitors that potently and selectively interrogate the kinase activities of distinct type I (16 chemotypes available) and type II receptors (3 chemotypes available). In contrast, only a few high-quality BMP stimulator modalities have been introduced to the field due to a lack of profound target knowledge. FK506-derived macrolides such as calcineurin-sparing FKBP12 inhibitors currently represent the best-characterized chemical tools for direct activation of BMP-SMAD signaling at the receptor level. However, several PDD campaigns succeeded in expanding the druggable space of BMP stimulators. Albeit the majority of them do not entirely fulfill the strict chemical probe criteria, many chemotypes exhibit unique and unrecognized mechanisms as pathway potentiators or synergizers, serving as valuable pharmacological tools for BMP perturbation.

Transcriptomics and cell painting analysis reveals molecular and morphological features associated with fed-batch production performance in CHO recombinant clones

Stable, highly productive mammalian cells are critical for manufacturing affordable and effective biological medicines. Establishing a rational design of optimal biotherapeutic expression systems requires understanding how cells support the high demand for efficient biologics production. To that end, we performed transcriptomics and high-throughput imaging studies to identify putative genes and morphological features that underpin differences in antibody productivity among clones from a Chinese hamster ovary cell line. During log phase growth, we found that the expression of genes involved in biological processes related to cellular morphology varied significantly between clones with high specific productivity (qP > 35 pg/cell/day) and low specific productivity (qP < 20 pg/cell/day). At Day 10 of a fed-batch production run, near peak viable cell density, differences in gene expression related to metabolism, epigenetic regulation, and proliferation became prominent. Furthermore, we identified a subset of genes whose expression predicted overall productivity, including glutathione synthetase (Gss) and lactate dehydrogenase A (LDHA). Finally, we demonstrated the feasibility of cell painting coupled with high-throughput imaging to assess the morphological properties of intracellular organelles in relation to growth and productivity in fed-batch production. Our efforts lay the groundwork for systematic elucidation of clone performance using a multiomics approach that can guide future process design strategies.

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.

Genetically engineered bacteria: a new frontier in targeted drug delivery

Genetically engineered bacteria (GEB) have shown significant promise to revolutionize modern medicine. These engineered bacteria with unique properties such as enhanced targeting, versatility, biofilm disruption, reduced drug resistance, self-amplification capabilities, and biodegradability represent a highly promising approach for targeted drug delivery and cancer theranostics. This innovative approach involves modifying bacterial strains to function as drug carriers, capable of delivering therapeutic agents directly to specific cells or tissues. Unlike synthetic drug delivery systems, GEB are inherently biodegradable and can be naturally eliminated from the body, reducing potential long-term side effects or complications associated with residual foreign constituents. However, several pivotal challenges such as safety and controllability need to be addressed. Researchers have explored novel tactics to improve their capabilities and overcome existing challenges, including synthetic biology tools (e.g., clustered regularly interspaced short palindromic repeats (CRISPR) and bioinformatics-driven design), microbiome engineering, combination therapies, immune system interaction, and biocontainment strategies. Because of the remarkable advantages and tangible progress in this field, GEB may emerge as vital tools in personalized medicine, providing precise and controlled drug delivery for various diseases (especially cancer). In this context, future directions include the integration of nanotechnology with GEB, the focus on microbiota-targeted therapies, the incorporation of programmable behaviors, the enhancement in immunotherapy treatments, and the discovery of non-medical applications. In this way, careful ethical considerations and regulatory frameworks are necessary for developing GEB-based systems for targeted drug delivery. By addressing safety concerns, ensuring informed consent, promoting equitable access, understanding long-term effects, mitigating dual-use risks, and fostering public engagement, these engineered bacteria can be employed as promising delivery vehicles in bio- and nanomedicine. In this review, recent advances related to the application of GEB in targeted drug delivery and cancer therapy are discussed, covering crucial challenging issues and future perspectives.

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.

MSC.sensor: Capturing cancer cell interactions with stroma for functional profiling

Mesenchymal stromal cells (MSCs) contribute to the microenvironment regulating normal and malignant hematopoiesis, and thus may support subpopulations of cancer cells to escape therapeutic pressure. Here, we engineered bone marrow MSCs to express a synthetic CD19-sensor receptor to detect and display interacting primary CD19+ leukemia cells in coculture. This implementation provides a versatile platform facilitating ex vivo drug response profiling of primary CD19+ leukemia cells in coculture with high-sensitivity and scalability.

Use of Deep-Learning Assisted Assessment of Cardiac Parameters in Zebrafish to Discover Cyanidin Chloride as a Novel Keap1 Inhibitor Against Doxorubicin-Induced Cardiotoxicity

Doxorubicin-induced cardiomyopathy (DIC) brings tough clinical challenges as well as continued demand in developing agents for adjuvant cardioprotective therapies. Here, a zebrafish phenotypic screening with deep-learning assisted multiplex cardiac functional analysis using motion videos of larval hearts is established. Through training the model on a dataset of 2125 labeled ventricular images, ZVSegNet and HRNet exhibit superior performance over previous methods. As a result of high-content phenotypic screening, cyanidin chloride (CyCl) is identified as a potent suppressor of DIC. CyCl effectively rescues cardiac cell death and improves heart function in both in vitro and in vivo models of Doxorubicin (Dox) exposure. CyCl shows strong inhibitory effects on lipid peroxidation and mitochondrial damage and prevents ferroptosis and apoptosis-related cell death. Molecular docking and thermal shift assay further suggest a direct binding between CyCl and Keap1, which may compete for the Keap1-Nrf2 interaction, promote nuclear accumulation of Nrf2, and subsequentially transactivate Gpx4 and other antioxidant factors. Site-specific mutation of R415A in Keap1 significantly attenuates the protective effects of CyCl against Dox-induced cardiotoxicity. Taken together, the capability of deep-learning-assisted phenotypic screening in identifying promising lead compounds against DIC is exhibited, and new perspectives into drug discovery in the era of artificial intelligence are provided.

Application of colloidal photonic crystals in study of organoids

As alternative disease models, other than 2D cell lines and patient-derived xenografts, organoids have preferable in vivo physiological relevance. However, both endogenous and exogenous limitations impede the development and clinical translation of these organoids. Fortunately, colloidal photonic crystals (PCs), which benefit from favorable biocompatibility, brilliant optical manipulation, and facile chemical decoration, have been applied to the engineering of organoids and have achieved the desirable recapitulation of the ECM niche, well-defined geometrical onsets for initial culture, in situ multiphysiological parameter monitoring, single-cell biomechanical sensing, and high-throughput drug screening with versatile functional readouts. Herein, we review the latest progress in engineering organoids fabricated from colloidal PCs and provide inputs for future research.

Recent Advances in High-Content Imaging and Analysis in iPSC-Based Modelling of Neurodegenerative Diseases

In the field of neurodegenerative pathologies, the platforms for disease modelling based on patient-derived induced pluripotent stem cells (iPSCs) represent a valuable molecular diagnostic/prognostic tool. Indeed, they paved the way for the in vitro recapitulation of the pathological mechanisms underlying neurodegeneration and for characterizing the molecular heterogeneity of disease manifestations, also enabling drug screening approaches for new therapeutic candidates. A major challenge is related to the choice and optimization of the morpho-functional study designs in human iPSC-derived neurons to deeply detail the cell phenotypes as markers of neurodegeneration. In recent years, the specific combination of high-throughput screening with subcellular resolution microscopy for cell-based high-content imaging (HCI) screening allowed in-depth analyses of cell morphology and neurite trafficking in iPSC-derived neuronal cells by using specific cutting-edge microscopes and automated computational assays. The present work aims to describe the main recent protocols and advances achieved with the HCI analysis in iPSC-based modelling of neurodegenerative diseases, highlighting technical and bioinformatics tips and tricks for further uses and research. To this end, microscopy requirements and the latest computational pipelines to analyze imaging data will be explored, while also providing an overview of the available open-source high-throughput automated platforms.

Machine learning for cross-scale microscopy of viruses

Despite advances in virological sciences and antiviral research, viruses continue to emerge, circulate, and threaten public health. We still lack a comprehensive understanding of how cells and individuals remain susceptible to infectious agents. This deficiency is in part due to the complexity of viruses, including the cell states controlling virus-host interactions. Microscopy samples distinct cellular infection stages in a multi-parametric, time-resolved manner at molecular resolution and is increasingly enhanced by machine learning and deep learning. Here we discuss how state-of-the-art artificial intelligence (AI) augments light and electron microscopy and advances virological research of cells. We describe current procedures for image denoising, object segmentation, tracking, classification, and super-resolution and showcase examples of how AI has improved the acquisition and analyses of microscopy data. The power of AI-enhanced microscopy will continue to help unravel virus infection mechanisms, develop antiviral agents, and improve viral vectors.

Integrating inflammatory biomarker analysis and artificial-intelligence-enabled image-based profiling to identify drug targets for intestinal fibrosis

Intestinal fibrosis, often caused by inflammatory bowel disease, can lead to intestinal stenosis and obstruction, but there are no approved treatments. Drug discovery has been hindered by the lack of screenable cellular phenotypes. To address this, we used a scalable image-based morphology assay called Cell Painting, augmented with machine learning algorithms, to identify small molecules that could reverse the activated fibrotic phenotype of intestinal myofibroblasts. We then conducted a high-throughput small molecule chemogenomics screen of approximately 5,000 compounds with known targets or mechanisms, which have achieved clinical stage or approval by the FDA. By integrating morphological analyses and AI using pathologically relevant cells and disease-relevant stimuli, we identified several compounds and target classes that are potentially able to treat intestinal fibrosis. This phenotypic screening platform offers significant improvements over conventional methods for identifying a wide range of drug targets.

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.

Discovering the mechanism of action of drugs with a sparse explainable network

BACKGROUND

Although Deep Neural Networks (DDNs) have been successful in predicting the efficacy of cancer drugs, the lack of explainability in their decision-making process is a significant challenge. Previous research proposed mimicking the Gene Ontology structure to allow for interpretation of each neuron in the network. However, these previous approaches require huge amount of GPU resources and hinder its extension to genome-wide models.

METHODS

We developed SparseGO, a sparse and interpretable neural network, for predicting drug response in cancer cell lines and their Mechanism of Action (MoA). To ensure model generalization, we trained it on multiple datasets and evaluated its performance using three cross-validation schemes. Its efficiency allows it to be used with gene expression. In addition, SparseGO integrates an eXplainable Artificial Intelligence (XAI) technique, DeepLIFT, with Support Vector Machines to computationally discover the MoA of drugs.

FINDINGS

SparseGO's sparse implementation significantly reduced GPU memory usage and training speed compared to other methods, allowing it to process gene expression instead of mutations as input data. SparseGO using expression improved the accuracy and enabled its use on drug repositioning. Furthermore, gene expression allows the prediction of MoA using 265 drugs to train it. It was validated on understudied drugs such as parbendazole and PD153035.

INTERPRETATION

SparseGO is an effective XAI method for predicting, but more importantly, understanding drug response.

FUNDING

The Accelerator Award Programme funded by Cancer Research UK [C355/A26819], Fundación Científica de la AECC and Fondazione AIRC, Project PIBA_2020_1_0055 funded by the Basque Government and the Synlethal Project (RETOS Investigacion, Spanish Government).

Prediction of mechanistic subtypes of Parkinson's using patient-derived stem cell models

Parkinson's disease is a common, incurable neurodegenerative disorder that is clinically heterogeneous: it is likely that different cellular mechanisms drive the pathology in different individuals. So far it has not been possible to define the cellular mechanism underlying the neurodegenerative disease in life. We generated a machine learning-based model that can simultaneously predict the presence of disease and its primary mechanistic subtype in human neurons. We used stem cell technology to derive control or patient-derived neurons, and generated different disease subtypes through chemical induction or the presence of mutation. Multidimensional fluorescent labelling of organelles was performed in healthy control neurons and in four different disease subtypes, and both the quantitative single-cell fluorescence features and the images were used to independently train a series of classifiers to build deep neural networks. Quantitative cellular profile-based classifiers achieve an accuracy of 82%, whereas image-based deep neural networks predict control and four distinct disease subtypes with an accuracy of 95%. The machine learning-trained classifiers achieve their accuracy across all subtypes, using the organellar features of the mitochondria with the additional contribution of the lysosomes, confirming the biological importance of these pathways in Parkinson's. Altogether, we show that machine learning approaches applied to patient-derived cells are highly accurate at predicting disease subtypes, providing proof of concept that this approach may enable mechanistic stratification and precision medicine approaches in the future.

A semiconductor 96-microplate platform for electrical-imaging based high-throughput phenotypic screening

Profiling compounds and genetic perturbations via high-content imaging has become increasingly popular for drug discovery, but the technique is limited to endpoint images of fixed cells. In contrast, electronic-based devices offer label-free, functional information of live cells, yet current approaches suffer from low-spatial resolution or single-well throughput. Here, we report a semiconductor 96-microplate platform designed for high-resolution real-time impedance "imaging" at scale. Each well features 4,096 electrodes at 25 µm spatial resolution while a miniaturized data interface allows 8× parallel plate operation (768 total wells) within each incubator for enhanced throughputs. New electric field-based, multi-frequency measurement techniques capture >20 parameter images including tissue barrier, cell-surface attachment, cell flatness, and motility every 15 min throughout experiments. Using these real-time readouts, we characterized 16 cell types, ranging from primary epithelial to suspension, and quantified heterogeneity in mixed epithelial and mesenchymal co-cultures. A proof-of-concept screen of 904 diverse compounds using 13 semiconductor microplates demonstrates the platform's capability for mechanism of action (MOA) profiling with 25 distinct responses identified. The scalability of the semiconductor platform combined with the translatability of the high dimensional live-cell functional parameters expands high-throughput MOA profiling and phenotypic drug discovery applications.