A phenomics approach for antiviral drug discovery

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.

Discovery Phase Agrochemical Predictive Safety Assessment Using High Content In Vitro Data to Estimate an In Vivo Toxicity Point of Departure

Utilization of in vitro (cellular) techniques, like Cell Painting and transcriptomics, could provide powerful tools for agrochemical candidate sorting and selection in the discovery process. However, using these models generates challenges translating in vitro concentrations to the corresponding in vivo exposures. Physiologically based pharmacokinetic (PBPK) modeling provides a framework for quantitative in vitro to in vivo extrapolation (IVIVE). We tested whether in vivo (rat liver) transcriptomic and apical points of departure (PODs) could be accurately predicted from in vitro (rat hepatocyte or human HepaRG) transcriptomic PODs or HepaRG Cell Painting PODs using PBPK modeling. We compared two PBPK models, the ADMET predictor and the httk R package, and found httk to predict the in vivo PODs more accurately. Our findings suggest that a rat liver apical and transcriptomic POD can be estimated utilizing a combination of in vitro transcriptome-based PODs coupled with PBPK modeling for IVIVE. Thus, high content in vitro data can be translated with modest accuracy to in vivo models of ultimate regulatory importance to help select agrochemical analogs in early stage discovery program.

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.

Current challenges in the discovery of treatments against Mayaro fever

INTRODUCTION

Mayaro fever is an emerging viral disease that manifests as an acute febrile illness. The disease is self-limiting, however joint pain can persist for months leading to chronic arthralgia. There is no specific treatment available, which ultimately leads to socioeconomic losses in populations at risk as well as strains to the public health systems.

AREAS COVERED

We reviewed the candidate treatments proposed for Mayaro virus (MAYV) infection and disease, including antiviral compounds targeting viral or host mechanisms, and pathways involved in disease development and pathogenicity. We assessed compound screening technologies and experimental infection models used in these studies and indicated the advantages and limitations of available technologies and intended therapeutic strategies.

EXPERT OPINION

Although several compounds have been suggested as candidate treatments against MAYV infection, notably those with antiviral activity, most compounds were assessed only in vitro. Compounds rarely progress toin vivo or preclinical studies, and such difficulty may be associated with limited experimental models. MAYV biology is largely inferred from related alphaviruses and reflected by few studies focusing on target proteins or mechanisms of action for MAYV. Therapeutic strategies targeting pathogenic inflammatory responses have shown potential against MAYV-induced disease in vivo, which might reduce long-term sequelae.

A flexible, image-based, high-throughput platform encompassing in-depth cell profiling to identify broad-spectrum coronavirus antivirals with limited off-target effects

The recent pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) posed a major threat to global health. Although the World Health Organization ended the public health emergency status, antiviral drugs are needed to address new variants of SARS-CoV-2 and future pandemics. To identify novel broad-spectrum coronavirus drugs, we developed a high-content imaging platform compatible with high-throughput screening. The platform is broadly applicable as it can be adapted to include various cell types, viruses, antibodies, and dyes. We demonstrated that the antiviral activity of compounds against SARS-CoV-2 variants (Omicron BA.5 and Omicron XBB.1.5), SARS-CoV, and human coronavirus 229E could easily be assessed. The inclusion of cellular dyes and immunostaining in combination with in-depth image analysis enabled us to identify compounds that induced undesirable phenotypes in host cells, such as changes in cell morphology or in lysosomal activity. With the platform, we screened ∼900K compounds and triaged hits, thereby identifying potential candidate compounds carrying broad-spectrum activity with limited off-target effects. The flexibility and early-stage identification of compounds with limited host cell effects provided by this high-content imaging platform can facilitate coronavirus drug discovery. We anticipate that its rapid deployability and fast turnaround can also be applied to combat future pandemics.

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

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

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.

Semantic Segmentation of Cell Painted Organelles using DeepLabv3plus Model

Cell painting based high content fluorescence imaging technique offers deep insight into the functional and biological changes in subcellular structures. However, advanced instrumentation and the limited availability of suitable fluorescent dyes restricts the tool to comprehensively characterize the cell morphology. Therefore, generating fluorescent specific organelle images using transmitted light microscopy provides an alternative solution for clinical applications. In this work, the utility of semantic segmentation deep network for predicting the Endoplasmic Reticulum (ER), cytoplasm and nuclei from a composite image is investigated. To perform this study, a public dataset consisting of 3456 composite images are considered from Broad Bioimage Benchmark collection. The pixel wise labeling is carried out with the generated binary masks for ER, cytoplasm and nuclei. DeepLabv3plus architecture with Atrous Spatial Pyramid Pooling (ASPP) and depth wise separable convolution is used as a learning model to perform semantic segmentation. The accuracy and loss function at different learning rates are analyzed and the segmentation results are validated using Jaccard index, mean Boundary F (BF) score and dice index. The trained model achieved 97.86% accuracy with a loss of 0.07 at the learning rate of 0.01. Mean BF score, dice index and Jaccard index for nuclei, ER and cytoplasm are (0.98, 0.94, 0.88), (0.97, 0.82, 0.7) and (0.95, 0.88, 0.66) respectively. The obtained results indicate that the adopted methodology could delineate the subcellular structures by accurately detecting sharp object boundaries. Therefore, this study could be useful for predicting the cell painted images from transmitted light microscopy without the requirement of fluorescent labeling.

Identification of Z-Tyr-Ala-CHN2, a Cathepsin L Inhibitor with Broad-Spectrum Cell-Specific Activity against Coronaviruses, including SARS-CoV-2

The ongoing COVID-19 pandemic, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is partly under control by vaccination. However, highly potent and safe antiviral drugs for SARS-CoV-2 are still needed to avoid development of severe COVID-19. We report the discovery of a small molecule, Z-Tyr-Ala-CHN2, which was identified in a cell-based antiviral screen. The molecule exerts sub-micromolar antiviral activity against SARS-CoV-2, SARS-CoV-1, and human coronavirus 229E. Time-of-addition studies reveal that Z-Tyr-Ala-CHN2 acts at the early phase of the infection cycle, which is in line with the observation that the molecule inhibits cathepsin L. This results in antiviral activity against SARS-CoV-2 in VeroE6, A549-hACE2, and HeLa-hACE2 cells, but not in Caco-2 cells or primary human nasal epithelial cells since the latter two cell types also permit entry via transmembrane protease serine subtype 2 (TMPRSS2). Given their cell-specific activity, cathepsin L inhibitors still need to prove their value in the clinic; nevertheless, the activity profile of Z-Tyr-Ala-CHN2 makes it an interesting tool compound for studying the biology of coronavirus entry and replication.

A Novel Nanosafety Approach Using Cell Painting, Metabolomics, and Lipidomics Captures the Cellular and Molecular Phenotypes Induced by the Unintentionally Formed Metal-Based (Nano)Particles

Additive manufacturing (AM) or industrial 3D printing uses cutting-edge technologies and materials to produce a variety of complex products. However, the effects of the unintentionally emitted AM (nano)particles (AMPs) on human cells following inhalation, require further investigations. The physicochemical characterization of the AMPs, extracted from the filter of a Laser Powder Bed Fusion (L-PBF) 3D printer of iron-based materials, disclosed their complexity, in terms of size, shape, and chemistry. Cell Painting, a high-content screening (HCS) assay, was used to detect the subtle morphological changes elicited by the AMPs at the single cell resolution. The profiling of the cell morphological phenotypes, disclosed prominent concentration-dependent effects on the cytoskeleton, mitochondria, and the membranous structures of the cell. Furthermore, lipidomics confirmed that the AMPs induced the extensive membrane remodeling in the lung epithelial and macrophage co-culture cell model. To further elucidate the biological mechanisms of action, the targeted metabolomics unveiled several inflammation-related metabolites regulating the cell response to the AMP exposure. Overall, the AMP exposure led to the internalization, oxidative stress, cytoskeleton disruption, mitochondrial activation, membrane remodeling, and metabolic reprogramming of the lung epithelial cells and macrophages. We propose the approach of integrating Cell Painting with metabolomics and lipidomics, as an advanced nanosafety methodology, increasing the ability to capture the cellular and molecular phenotypes and the relevant biological mechanisms to the (nano)particle exposure.

Deep learning in image-based phenotypic drug discovery

Modern drug discovery approaches often use high-content imaging to systematically study the effect on cells of large libraries of chemical compounds. By automatically screening thousands or millions of images to identify specific drug-induced cellular phenotypes, for example, altered cellular morphology, these approaches can reveal 'hit' compounds offering therapeutic promise. In the past few years, artificial intelligence (AI) methods based on deep learning (DL) [a family of machine learning (ML) techniques] have disrupted virtually all image analysis tasks, from image classification to segmentation. These powerful methods also promise to impact drug discovery by accelerating the identification of effective drugs and their modes of action. In this review, we highlight applications and adaptations of ML, especially DL methods for cell-based phenotypic drug discovery (PDD).

Optimization of N-Piperidinyl-Benzimidazolone Derivatives as Potent and Selective Inhibitors of 8-Oxo-Guanine DNA Glycosylase 1

8-oxo Guanine DNA Glycosylase 1 is the initiating enzyme within base excision repair and removes oxidized guanines from damaged DNA. Since unrepaired 8-oxoG could lead to G : C→T : A transversion, base removal is of utmost importance for cells to ensure genomic integrity. For cells with elevated levels of reactive oxygen species this dependency is further increased. In the past we and others have validated OGG1 as a target for inhibitors to treat cancer and inflammation. Here, we present the optimization campaign that led to the broadly used tool compound TH5487. Based on results from a small molecule screening campaign, we performed hit to lead expansion and arrived at potent and selective substituted N-piperidinyl-benzimidazolones. Using X-ray crystallography data, we describe the surprising binding mode of the most potent member of the class, TH8535. Here, the N-Piperidinyl-linker adopts a chair instead of a boat conformation which was found for weaker analogues. We further demonstrate cellular target engagement and efficacy of TH8535 against a number of cancer cell lines.

Integrating cell morphology with gene expression and chemical structure to aid mitochondrial toxicity detection

Mitochondrial toxicity is an important safety endpoint in drug discovery. Models based solely on chemical structure for predicting mitochondrial toxicity are currently limited in accuracy and applicability domain to the chemical space of the training compounds. In this work, we aimed to utilize both -omics and chemical data to push beyond the state-of-the-art. We combined Cell Painting and Gene Expression data with chemical structural information from Morgan fingerprints for 382 chemical perturbants tested in the Tox21 mitochondrial membrane depolarization assay. We observed that mitochondrial toxicants differ from non-toxic compounds in morphological space and identified compound clusters having similar mechanisms of mitochondrial toxicity, thereby indicating that morphological space provides biological insights related to mechanisms of action of this endpoint. We further showed that models combining Cell Painting, Gene Expression features and Morgan fingerprints improved model performance on an external test set of 244 compounds by 60% (in terms of F1 score) and improved extrapolation to new chemical space. The performance of our combined models was comparable with dedicated in vitro assays for mitochondrial toxicity. Our results suggest that combining chemical descriptors with biological readouts enhances the detection of mitochondrial toxicants, with practical implications in drug discovery.

Morphological profiling of environmental chemicals enables efficient and untargeted exploration of combination effects

Environmental chemicals are commonly studied one at a time, and there is a need to advance our understanding of the effect of exposure to their combinations. Here we apply high-content microscopy imaging of cells stained with multiplexed dyes (Cell Painting) to profile the effects of Cetyltrimethylammonium bromide (CTAB), Bisphenol A (BPA), and Dibutyltin dilaurate (DBTDL) exposure on four human cell lines; both individually and in all combinations. We show that morphological features can be used with multivariate data analysis to discern between exposures from individual compounds, concentrations, and combinations. CTAB and DBTDL induced concentration-dependent morphological changes across the four cell lines, and BPA exacerbated morphological effects when combined with CTAB and DBTDL. Combined exposure to CTAB and BPA induced changes in the ER, Golgi apparatus, nucleoli and cytoplasmic RNA in one of the cell lines. Different responses between cell lines indicate that multiple cell types are needed when assessing combination effects. The rapid and relatively low-cost experiments combined with high information content make Cell Painting an attractive methodology for future studies of combination effects. All data in the study is made publicly available on Figshare.

Image-Based Annotation of Chemogenomic Libraries for Phenotypic Screening

Phenotypical screening is a widely used approach in drug discovery for the identification of small molecules with cellular activities. However, functional annotation of identified hits often poses a challenge. The development of small molecules with narrow or exclusive target selectivity such as chemical probes and chemogenomic (CG) libraries, greatly diminishes this challenge, but non-specific effects caused by compound toxicity or interference with basic cellular functions still pose a problem to associate phenotypic readouts with molecular targets. Hence, each compound should ideally be comprehensively characterized regarding its effects on general cell functions. Here, we report an optimized live-cell multiplexed assay that classifies cells based on nuclear morphology, presenting an excellent indicator for cellular responses such as early apoptosis and necrosis. This basic readout in combination with the detection of other general cell damaging activities of small molecules such as changes in cytoskeletal morphology, cell cycle and mitochondrial health provides a comprehensive time-dependent characterization of the effect of small molecules on cellular health in a single experiment. The developed high-content assay offers multi-dimensional comprehensive characterization that can be used to delineate generic effects regarding cell functions and cell viability, allowing an assessment of compound suitability for subsequent detailed phenotypic and mechanistic studies.