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

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.

Development, External Validation, and Visualization of Machine Learning Models for Predicting Occurrence of Acute Kidney Injury after Cardiac Surgery

Background

Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication that results in short- and long-term mortality among patients. Here, we adopted machine learning algorithms to build prediction models with the overarching goal of identifying patients who are at a high risk of such unfavorable kidney outcomes.

Methods

A total of 1686 patients (development cohort) and 422 patients (validation cohort), with 126 pre- and intra-operative variables, were recruited from the First Medical Centre and the Sixth Medical Centre of Chinese PLA General Hospital in Beijing, China, respectively. Analyses were performed using six machine learning techniques, namely K-nearest neighbor, logistic regression, decision tree, random forest (RF), support vector machine, and neural network, and the APPROACH score, a previously established risk score for CSA-AKI. For model tuning, optimal hyperparameter was achieved by using GridSearch with 5-fold cross-validation from the scikit-learn library. Model performance was externally assessed via the receiver operating characteristic (ROC) and decision curve analysis (DCA). Explainable machine learning was performed using the Python SHapley Additive exPlanation (SHAP) package and Seaborn library, which allow the calculation of marginal contributory SHAP value.

Results

637 patients (30.2%) developed CSA-AKI within seven days after surgery. In the external validation, the RF classifier exhibited the best performance among the six machine learning techniques, as shown by the ROC curve and DCA, while the traditional APPROACH risk score showed a relatively poor performance. Further analysis found no specific causative factor contributing to the development of CSA-AKI; rather, the development of CSA-AKI appeared to be a complex process resulting from a complex interplay of multiple risk factors. The SHAP summary plot illustrated the positive or negative contribution of RF-top 20 variables and extrapolated risk of developing CSA-AKI at individual levels. The Seaborn library showed the effect of each single feature on the model output of the RF prediction.

Conclusions

Efficient machine learning approaches were successfully established to predict patients with a high probability of developing acute kidney injury after cardiac surgery. These findings are expected to help clinicians to optimize treatment strategies and minimize postoperative complications.

Clinical Trial Registration

The study protocol was registered at the ClinicalTrials Registration System (https://www.clinicaltrials.gov/, #NCT04966598) on July 26, 2021.

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.

Cell segmentation in images without structural fluorescent labels

High-content screening (HCS) provides an excellent tool to understand the mechanism of action of drugs on disease-relevant model systems. Careful selection of fluorescent labels (FLs) is crucial for successful HCS assay development. HCS assays typically comprise (a) FLs containing biological information of interest, and (b) additional structural FLs enabling instance segmentation for downstream analysis. However, the limited number of available fluorescence microscopy imaging channels restricts the degree to which these FLs can be experimentally multiplexed. In this article, we present a segmentation workflow that overcomes the dependency on structural FLs for image segmentation, typically freeing two fluorescence microscopy channels for biologically relevant FLs. It consists in extracting structural information encoded within readouts that are primarily biological, by fine-tuning pre-trained state-of-the-art generalist cell segmentation models for different combinations of individual FLs, and aggregating the respective segmentation results together. Using annotated datasets that we provide, we confirm our methodology offers improvements in performance and robustness across several segmentation aggregation strategies and image acquisition methods, over different cell lines and various FLs. It thus enables the biological information content of HCS assays to be maximized without compromising the robustness and accuracy of computational single-cell profiling.

Optimizing the Cell Painting assay for image-based profiling

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

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.

Unbiased single-cell morphology with self-supervised vision transformers

Accurately quantifying cellular morphology at scale could substantially empower existing single-cell approaches. However, measuring cell morphology remains an active field of research, which has inspired multiple computer vision algorithms over the years. Here, we show that DINO, a vision-transformer based, self-supervised algorithm, has a remarkable ability for learning rich representations of cellular morphology without manual annotations or any other type of supervision. We evaluate DINO on a wide variety of tasks across three publicly available imaging datasets of diverse specifications and biological focus. We find that DINO encodes meaningful features of cellular morphology at multiple scales, from subcellular and single-cell resolution, to multi-cellular and aggregated experimental groups. Importantly, DINO successfully uncovers a hierarchy of biological and technical factors of variation in imaging datasets. The results show that DINO can support the study of unknown biological variation, including single-cell heterogeneity and relationships between samples, making it an excellent tool for image-based biological discovery.

Leveraging Cell Painting Images to Expand the Applicability Domain and Actively Improve Deep Learning Quantitative Structure-Activity Relationship Models

The search for chemical hit material is a lengthy and increasingly expensive drug discovery process. To improve it, ligand-based quantitative structure-activity relationship models have been broadly applied to optimize primary and secondary compound properties. Although these models can be deployed as early as the stage of molecule design, they have a limited applicability domain─if the structures of interest differ substantially from the chemical space on which the model was trained, a reliable prediction will not be possible. Image-informed ligand-based models partly solve this shortcoming by focusing on the phenotype of a cell caused by small molecules, rather than on their structure. While this enables chemical diversity expansion, it limits the application to compounds physically available and imaged. Here, we employ an active learning approach to capitalize on both of these methods' strengths and boost the model performance of a mitochondrial toxicity assay (Glu/Gal). Specifically, we used a phenotypic Cell Painting screen to build a chemistry-independent model and adopted the results as the main factor in selecting compounds for experimental testing. With the additional Glu/Gal annotation for selected compounds we were able to dramatically improve the chemistry-informed ligand-based model with respect to the increased recognition of compounds from a 10% broader chemical space.

Multisite assessment of reproducibility in high-content cell migration imaging data

High-content image-based cell phenotyping provides fundamental insights into a broad variety of life science disciplines. Striving for accurate conclusions and meaningful impact demands high reproducibility standards, with particular relevance for high-quality open-access data sharing and meta-analysis. However, the sources and degree of biological and technical variability, and thus the reproducibility and usefulness of meta-analysis of results from live-cell microscopy, have not been systematically investigated. Here, using high-content data describing features of cell migration and morphology, we determine the sources of variability across different scales, including between laboratories, persons, experiments, technical repeats, cells, and time points. Significant technical variability occurred between laboratories and, to lesser extent, between persons, providing low value to direct meta-analysis on the data from different laboratories. However, batch effect removal markedly improved the possibility to combine image-based datasets of perturbation experiments. Thus, reproducible quantitative high-content cell image analysis of perturbation effects and meta-analysis depend on standardized procedures combined with batch correction.

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

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

Sequence enrichment profiles enable target-agnostic antibody generation for a broad range of antigens

Phenotypic drug discovery (PDD) enables the target-agnostic generation of therapeutic drugs with novel mechanisms of action. However, realizing its full potential for biologics discovery requires new technologies to produce antibodies to all, a priori unknown, disease-associated biomolecules. We present a methodology that helps achieve this by integrating computational modeling, differential antibody display selection, and massive parallel sequencing. The method uses the law of mass action-based computational modeling to optimize antibody display selection and, by matching computationally modeled and experimentally selected sequence enrichment profiles, predict which antibody sequences encode specificity for disease-associated biomolecules. Applied to a phage display antibody library and cell-based antibody selection, ∼10⁵ antibody sequences encoding specificity for tumor cell surface receptors expressed at 10³-10⁶ receptors/cell were discovered. We anticipate that this approach will be broadly applicable to molecular libraries coupling genotype to phenotype and to the screening of complex antigen populations for identification of antibodies to unknown disease-associated targets.

Morphological Profiling Identifies the Motor Protein Eg5 as Cellular Target of Spirooxindoles

Oxindoles and iso-oxindoles are natural product-derived scaffolds that provide inspiration for the design and synthesis of novel biologically relevant compound classes. Notably, the spirocyclic connection of oxindoles with iso-oxindoles has not been explored by nature but promises to provide structurally related compounds endowed with novel bioactivity. Therefore, methods for their efficient synthesis and the conclusive discovery of their cellular targets are highly desirable. We describe a selective RhIII -catalyzed scaffold-divergent synthesis of spirooxindole-isooxindoles and spirooxindole-oxindoles from differently protected diazooxindoles and N-pivaloyloxy aryl amides which includes a functional group-controlled Lossen rearrangement as key step. Unbiased morphological profiling of a corresponding compound collection in the Cell Painting assay efficiently identified the mitotic kinesin Eg5 as the cellular target of the spirooxindoles, defining a unique Eg5 inhibitor chemotype.

Rapid and Accurate Identification of Cell Phenotypes of Different Drug Mechanisms by Using Single-Cell Fluorescence Images Via Deep Learning

Identification of a drug mechanism is vital for drug development. However, it often resorts to the expensive and cumbersome omics methods along with complex data analysis. Herein, we developed a methodology to analyze organelle staining images of single cells using a deep learning algorithm (TL-ResNet50) for rapid and accurate identification of different drug mechanisms. Based on the organelle-related cell morphological changes caused by drug action, the constructed deep learning model can fast predict the drug mechanism with a high accuracy of 92%. Further analysis reveals that drug combination at different ratios can enhance a certain mechanism or generate a new mechanism. This work would highly facilitate clinical medication and drug screening.

Single-cell subcellular protein localisation using novel ensembles of diverse deep architectures

Unravelling protein distributions within individual cells is vital to understanding their function and state and indispensable to developing new treatments. Here we present the Hybrid subCellular Protein Localiser (HCPL), which learns from weakly labelled data to robustly localise single-cell subcellular protein patterns. It comprises innovative DNN architectures exploiting wavelet filters and learnt parametric activations that successfully tackle drastic cell variability. HCPL features correlation-based ensembling of novel architectures that boosts performance and aids generalisation. Large-scale data annotation is made feasible by our AI-trains-AI approach, which determines the visual integrity of cells and emphasises reliable labels for efficient training. In the Human Protein Atlas context, we demonstrate that HCPL is best performing in the single-cell classification of protein localisation patterns. To better understand the inner workings of HCPL and assess its biological relevance, we analyse the contributions of each system component and dissect the emergent features from which the localisation predictions are derived.

Morphological profiling by high-throughput single-cell biophysical fractometry

Complex and irregular cell architecture is known to statistically exhibit fractal geometry, i.e., a pattern resembles a smaller part of itself. Although fractal variations in cells are proven to be closely associated with the disease-related phenotypes that are otherwise obscured in the standard cell-based assays, fractal analysis with single-cell precision remains largely unexplored. To close this gap, here we develop an image-based approach that quantifies a multitude of single-cell biophysical fractal-related properties at subcellular resolution. Taking together with its high-throughput single-cell imaging performance (~10,000 cells/sec), this technique, termed single-cell biophysical fractometry, offers sufficient statistical power for delineating the cellular heterogeneity, in the context of lung-cancer cell subtype classification, drug response assays and cell-cycle progression tracking. Further correlative fractal analysis shows that single-cell biophysical fractometry can enrich the standard morphological profiling depth and spearhead systematic fractal analysis of how cell morphology encodes cellular health and pathological conditions.

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

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

Application of cell painting for chemical hazard evaluation in support of screening-level chemical assessments

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

Predicting compound activity from phenotypic profiles and chemical structures

Predicting assay results for compounds virtually using chemical structures and phenotypic profiles has the potential to reduce the time and resources of screens for drug discovery. Here, we evaluate the relative strength of three high-throughput data sources-chemical structures, imaging (Cell Painting), and gene-expression profiles (L1000)-to predict compound bioactivity using a historical collection of 16,170 compounds tested in 270 assays for a total of 585,439 readouts. All three data modalities can predict compound activity for 6-10% of assays, and in combination they predict 21% of assays with high accuracy, which is a 2 to 3 times higher success rate than using a single modality alone. In practice, the accuracy of predictors could be lower and still be useful, increasing the assays that can be predicted from 37% with chemical structures alone up to 64% when combined with phenotypic data. Our study shows that unbiased phenotypic profiling can be leveraged to enhance compound bioactivity prediction to accelerate the early stages of the drug-discovery process.

The evolving role of investigative toxicology in the pharmaceutical industry

For decades, preclinical toxicology was essentially a descriptive discipline in which treatment-related effects were carefully reported and used as a basis to calculate safety margins for drug candidates. In recent years, however, technological advances have increasingly enabled researchers to gain insights into toxicity mechanisms, supporting greater understanding of species relevance and translatability to humans, prediction of safety events, mitigation of side effects and development of safety biomarkers. Consequently, investigative (or mechanistic) toxicology has been gaining momentum and is now a key capability in the pharmaceutical industry. Here, we provide an overview of the current status of the field using case studies and discuss the potential impact of ongoing technological developments, based on a survey of investigative toxicologists from 14 European-based medium-sized to large pharmaceutical companies.

Artificial intelligence and machine learning disciplines with the potential to improve the nanotoxicology and nanomedicine fields: a comprehensive review

The use of nanomaterials in medicine depends largely on nanotoxicological evaluation in order to ensure safe application on living organisms. Artificial intelligence (AI) and machine learning (MI) can be used to analyze and interpret large amounts of data in the field of toxicology, such as data from toxicological databases and high-content image-based screening data. Physiologically based pharmacokinetic (PBPK) models and nano-quantitative structure-activity relationship (QSAR) models can be used to predict the behavior and toxic effects of nanomaterials, respectively. PBPK and Nano-QSAR are prominent ML tool for harmful event analysis that is used to understand the mechanisms by which chemical compounds can cause toxic effects, while toxicogenomics is the study of the genetic basis of toxic responses in living organisms. Despite the potential of these methods, there are still many challenges and uncertainties that need to be addressed in the field. In this review, we provide an overview of artificial intelligence (AI) and machine learning (ML) techniques in nanomedicine and nanotoxicology to better understand the potential toxic effects of these materials at the nanoscale.

Host Cell Targets for Unconventional Antivirals against RNA Viruses

The recent COVID-19 crisis has highlighted the importance of RNA-based viruses. The most prominent members of this group are SARS-CoV-2 (coronavirus), HIV (human immunodeficiency virus), EBOV (Ebola virus), DENV (dengue virus), HCV (hepatitis C virus), ZIKV (Zika virus), CHIKV (chikungunya virus), and influenza A virus. With the exception of retroviruses which produce reverse transcriptase, the majority of RNA viruses encode RNA-dependent RNA polymerases which do not include molecular proofreading tools, underlying the high mutation capacity of these viruses as they multiply in the host cells. Together with their ability to manipulate the immune system of the host in different ways, their high mutation frequency poses a challenge to develop effective and durable vaccination and/or treatments. Consequently, the use of antiviral targeting agents, while an important part of the therapeutic strategy against infection, may lead to the selection of drug-resistant variants. The crucial role of the host cell replicative and processing machinery is essential for the replicative cycle of the viruses and has driven attention to the potential use of drugs directed to the host machinery as therapeutic alternatives to treat viral infections. In this review, we discuss small molecules with antiviral effects that target cellular factors in different steps of the infectious cycle of many RNA viruses. We emphasize the repurposing of FDA-approved drugs with broad-spectrum antiviral activity. Finally, we postulate that the ferruginol analog (18-(phthalimide-2-yl) ferruginol) is a potential host-targeted antiviral.

Selection of Optimal Cell Lines for High-Content Phenotypic Screening

High-content microscopy offers a scalable approach to screen against multiple targets in a single pass. Prior work has focused on methods to select "optimal" cellular readouts in microscopy screens. However, methods to select optimal cell line models have garnered much less attention. Here, we provide a roadmap for how to select the cell line or lines that are best suited to identify bioactive compounds and their mechanism of action (MOA). We test our approach on compounds targeting cancer-relevant pathways, ranking cell lines in two tasks: detecting compound activity ("phenoactivity") and grouping compounds with similar MOA by similar phenotype ("phenosimilarity"). Evaluating six cell lines across 3214 well-annotated compounds, we show that optimal cell line selection depends on both the task of interest (e.g., detecting phenoactivity vs inferring phenosimilarity) and distribution of MOAs within the compound library. Given a task of interest and a set of compounds, we provide a systematic framework for choosing optimal cell line(s). Our framework can be used to reduce the number of cell lines required to identify hits within a compound library and help accelerate the pace of early drug discovery.

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

The cytoplasmic dynein-1 (dynein) motor plays a key role in cellular organisation by transporting a wide variety of cellular constituents towards the minus ends of microtubules. However, relatively little is known about how the biosynthesis, assembly and functional diversity of the motor is 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 guide RNA library targeting 18,253 genes, 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 generated from multiplexed images revealed co-functional genes involved in many cellular processes, including several candidate novel regulators of core dynein functions. Mechanistic analysis of one of these proteins, the RNA-binding protein SUGP1, provides evidence that it promotes cargo trafficking by sustaining functional expression of the dynein activator LIS1. Our dataset represents a rich source of new hypotheses for investigating microtubule-based transport, as well as several other aspects of cellular organisation that were captured by our high-content imaging.

Linking chemicals, genes and morphological perturbations to diseases

The progress in image-based high-content screening technology has facilitated high-throughput phenotypic profiling notably the quantification of cell morphology perturbation by chemicals. However, understanding the mechanism of action of a chemical and linking it to cell morphology and phenotypes remains a challenge in drug discovery. In this study, we intended to integrate molecules that induced transcriptomic perturbations and cellular morphological changes into a biological network in order to assess chemical-phenotypic relationships in humans. Such a network was enriched with existing disease information to suggest molecular and cellular profiles leading to phenotypes. Two datasets were used for this study. Firstly, we used the "Cell Painting morphological profiling assay" dataset, composed of 30,000 compounds tested on human osteosarcoma cells (named U2OS). Secondly, we used the "L1000 mRNA profiling assay" dataset, a collection of transcriptional expression data from cultured human cells treated with approximately 20,000 bioactive small molecules from the Library of Integrated Network-based Cellular Signatures (LINCS). Furthermore, pathways, gene ontology terms and disease enrichments were performed on the transcriptomics data. Overall, our study makes it possible to develop a biological network combining chemical-gene-pathway-morphological perturbation and disease relationships. It contains an ensemble of 9989 chemicals, 732 significant morphological features and 12,328 genes. Through diverse examples, we demonstrated that some drugs shared similar genes, pathways and morphological profiles that, taken together, could help in deciphering chemical-phenotype observations.

Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence

Only around 20% of the human proteome is considered to be druggable with small-molecule antagonists. This leaves some of the most compelling therapeutic targets outside the reach of ligand discovery. The concept of targeted protein degradation (TPD) promises to overcome some of these limitations. In brief, TPD is dependent on small molecules that induce the proximity between a protein of interest (POI) and an E3 ubiquitin ligase, causing ubiquitination and degradation of the POI. In this perspective, we want to reflect on current challenges in the field, and discuss how advances in multiomics profiling, artificial intelligence, and machine learning (AI/ML) will be vital in overcoming them. The presented roadmap is discussed in the context of small-molecule degraders but is equally applicable for other emerging proximity-inducing modalities.

Prediction of inotropic effect based on calcium transients in human iPSC-derived cardiomyocytes and machine learning

Functional changes to cardiomyocytes are undesirable during drug discovery and identifying the inotropic effects of compounds is hence necessary to decrease the risk of cardiovascular adverse effects in the clinic. Recently, approaches leveraging calcium transients in human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) have been developed to detect contractility changes, induced by a variety of mechanisms early during drug discovery projects. Although these approaches have been able to provide some predictive ability, we hypothesised that using additional waveform parameters could offer improved insights, as well as predictivity. In this study, we derived 25 parameters from each calcium transient waveform and developed a modified Random Forest method to predict the inotropic effects of the compounds. In total annotated data for 48 compounds were available for modelling, out of which 31 were inotropes. The results show that the Random Forest model with a modified purity criterion performed slightly better than an unmodified algorithm in terms of the Area Under the Curve, giving values of 0.84 vs 0.81 in a cross-validation, and outperformed the ToxCast Pipeline model, for which the highest value was 0.76 when using the best-performing parameter, PW10. Our study hence demonstrates that more advanced parameters derived from waveforms, in combination with additional machine learning methods, provide improved predictivity of cardiovascular risk associated with inotropic effects.

Selection of optimal cell lines for high-content phenotypic screening

High-content microscopy offers a scalable approach to screen against multiple targets in a single pass. Prior work has focused on methods to select "optimal" cellular readouts in microscopy screens. However, methods to select optimal cell line models have garnered much less attention. Here, we provide a roadmap for how to select the cell line or lines that are best suited to identify bioactive compounds and their mechanism of action (MOA). We test our approach on compounds targeting cancer-relevant pathways, ranking cell lines in two tasks: detecting compound activity ("phenoactivity") and grouping compounds with similar MOA by similar phenotype ("phenosimilarity"). Evaluating six cell lines across 3214 well-annotated compounds, we show that optimal cell line selection depends on both the task of interest (e.g. detecting phenoactivity vs. inferring phenosimilarity) and distribution of MOAs within the compound library. Given a task of interest and set of compounds, we provide a systematic framework for choosing optimal cell line(s). Our framework can be used to reduce the number of cell lines required to identify hits within a compound library and help accelerate the pace of early drug discovery.

Using chemical and biological data to predict drug toxicity

Various sources of information can be used to better understand and predict compound activity and safety-related endpoints, including biological data such as gene expression and cell morphology. In this review, we first introduce types of chemical, in vitro and in vivo information that can be used to describe compounds and adverse effects. We then explore how compound descriptors based on chemical structure or biological perturbation response can be used to predict safety-related endpoints, and how especially biological data can help us to better understand adverse effects mechanistically. Overall, the described applications demonstrate how large-scale biological information presents new opportunities to anticipate and understand the biological effects of compounds, and how this can support predictive toxicology and drug discovery projects.

Virtual Screening-Based Drug Development for the Treatment of Nervous System Diseases

The incidence rate of nervous system diseases has increased in recent years. Nerve injury or neurodegenerative diseases usually cause neuronal loss and neuronal circuit damage, which seriously affect motor nerve and autonomic nervous function. Therefore, safe and effective treatment is needed. As traditional drug research becomes slower and more expensive, it is vital to enlist the help of cutting- edge technology. Virtual screening (VS) is an attractive option for the identification and development of promising new compounds with high efficiency and low cost. With the assistance of computer- aided drug design (CADD), VS is becoming more and more popular in new drug development and research. In recent years, it has become a reality to transform non-neuronal cells into functional neurons through small molecular compounds, which provides a broader application prospect than transcription factor-mediated neuronal reprogramming. This review mainly summarizes related theory and technology of VS and the drug research and development using VS technology in nervous system diseases in recent years, and focuses more on the potential application of VS technology in neuronal reprogramming, thus facilitating new drug design for both prevention and treatment of nervous system diseases.

Application of Machine Learning in Spatial Proteomics

Spatial proteomics is an interdisciplinary field that investigates the localization and dynamics of proteins, and it has gained extensive attention in recent years, especially the subcellular proteomics. Numerous evidence indicate that the subcellular localization of proteins is associated with various cellular processes and disease progression. Mass spectrometry (MS)-based and imaging-based experimental approaches have been developed to acquire large-scale spatial proteomic data. To allow the reliable analysis of increasingly complex spatial proteomics data, machine learning (ML) methods have been widely used in both MS-based and imaging-based spatial proteomic data analysis pipelines. Here, we comprehensively survey the applications of ML in spatial proteomics from following aspects: (1) data resources for spatial proteome are comprehensively introduced; (2) the roles of different ML algorithms in data analysis pipelines are elaborated; (3) successful applications of spatial proteomics and several analytical tools integrating ML methods are presented; (4) challenges existing in modern ML-based spatial proteomics studies are discussed. This review provides guidelines for researchers seeking to apply ML methods to analyze spatial proteomic data and can facilitate insightful understanding of cell biology as well as the future research in medical and drug discovery communities.

Patient-by-Patient Deep Transfer Learning for Drug-Response Profiling Using Confocal Fluorescence Microscopy of Pediatric Patient-Derived Tumor-Cell Spheroids

Image-based phenotypic drug profiling is receiving increasing attention in drug discovery and precision medicine. Compared to classical end-point measurements quantifying drug response, image-based profiling enables both the quantification of drug response and characterization of disease entities and drug-induced cell-death phenotypes. Here, we aim to quantify image-based drug responses in patient-derived 3D spheroid tumor cell cultures, tackling the challenges of a lack of single-cell-segmentation methods and limited patient-derived material. Therefore, we investigate deep transfer learning with patient-by-patient fine-tuning for cell-viability quantification. We fine-tune a convolutional neural network (pre-trained on ImageNet) with 210 control images specific to a single training cell line and 54 additional screen -specific assay control images. This method of image-based drug profiling is validated on 6 cell lines with known drug sensitivities, and further tested with primary patient-derived samples in a medium-throughput setting. Network outputs at different drug concentrations are used for drug-sensitivity scoring, and dense-layer activations are used in t-distributed stochastic neighbor embeddings of drugs to visualize groups of drugs with similar cell-death phenotypes. Image-based cell-line experiments show strong correlation to metabolic results ( R ≈ 0.7 ) and confirm expected hits, indicating the predictive power of deep learning to identify drug-hit candidates for individual patients. In patient-derived samples, combining drug sensitivity scoring with phenotypic analysis may provide opportunities for complementary combination treatments. Deep transfer learning with patient-by-patient fine-tuning is a promising, segmentation-free image-analysis approach for precision medicine and drug discovery.

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

Cells can be perturbed by various chemical and genetic treatments and the impact on gene expression and morphology can be measured via transcriptomic profiling and image-based assays, respectively. The patterns observed in these high-dimensional profile data can power a dozen applications in drug discovery and basic biology research, but both types of profiles are rarely available for large-scale experiments. Here, we provide a collection of four datasets with both gene expression and morphological profile data useful for developing and testing multimodal methodologies. Roughly a thousand features are measured for each of the two data types, across more than 28,000 chemical and genetic perturbations. We define biological problems that use the shared and complementary information in these two data modalities, provide baseline analysis and evaluation metrics for multi-omic applications, and make the data resource publicly available ( https://broad.io/rosetta/ ).

The phenotypic landscape of essential human genes

Understanding the basis for cellular growth, proliferation, and function requires determining the roles of essential genes in diverse cellular processes, including visualizing their contributions to cellular organization and morphology. Here, we combined pooled CRISPR-Cas9-based functional screening of 5,072 fitness-conferring genes in human HeLa cells with microscopy-based imaging of DNA, the DNA damage response, actin, and microtubules. Analysis of >31 million individual cells identified measurable phenotypes for >90% of gene knockouts, implicating gene targets in specific cellular processes. Clustering of phenotypic similarities based on hundreds of quantitative parameters further revealed co-functional genes across diverse cellular activities, providing predictions for gene functions and associations. By conducting pooled live-cell screening of ∼450,000 cell division events for 239 genes, we additionally identified diverse genes with functional contributions to chromosome segregation. Our work establishes a resource detailing the consequences of disrupting core cellular processes that represents the functional landscape of essential human genes.

Morphology and gene expression profiling provide complementary information for mapping cell state

Morphological and gene expression profiling can cost-effectively capture thousands of features in thousands of samples across perturbations by disease, mutation, or drug treatments, but it is unclear to what extent the two modalities capture overlapping versus complementary information. Here, using both the L1000 and Cell Painting assays to profile gene expression and cell morphology, respectively, we perturb human A549 lung cancer cells with 1,327 small molecules from the Drug Repurposing Hub across six doses, providing a data resource including dose-response data from both assays. The two assays capture both shared and complementary information for mapping cell state. Cell Painting profiles from compound perturbations are more reproducible and show more diversity but measure fewer distinct groups of features. Applying unsupervised and supervised methods to predict compound mechanisms of action (MOAs) and gene targets, we find that the two assays not only provide a partially shared but also a complementary view of drug mechanisms. Given the numerous applications of profiling in biology, our analyses provide guidance for planning experiments that profile cells for detecting distinct cell types, disease phenotypes, and response to chemical or genetic perturbations.

Morphological signatures of actin organization in single cells accurately classify genetic perturbations using CNNs with transfer learning

The actin cytoskeleton plays essential roles in countless cell processes, from cell division to migration to signaling. In cancer cells, cytoskeletal dynamics, cytoskeletal filament organization, and overall cell morphology are known to be altered substantially. We hypothesize that actin fiber organization and cell shape may carry specific signatures of genetic or signaling perturbations. We used convolutional neural networks (CNNs) on a small fluorescence microscopy image dataset of retinal pigment epithelial (RPE) cells and triple-negative breast cancer (TNBC) cells for identifying morphological signatures in cancer cells. Using a transfer learning approach, CNNs could be trained to accurately distinguish between normal and oncogenically transformed RPE cells with an accuracy of about 95% or better at the single cell level. Furthermore, CNNs could distinguish transformed cell lines differing by an oncogenic mutation from each other and could also detect knockdown of cofilin in TNBC cells, indicating that each single oncogenic mutation or cytoskeletal perturbation produces a unique signature in actin morphology. Application of the Local Interpretable Model-Agnostic Explanations (LIME) method for visually interpreting the CNN results revealed features of the global actin structure relevant for some cells and classification tasks. Interestingly, many of these features were supported by previous biological observation. Actin fiber organization is thus a sensitive marker for cell identity, and identification of its perturbations could be very useful for assaying cell phenotypes, including disease states.

Modulating biomolecular condensates: a novel approach to drug discovery

In the past decade, membraneless assemblies known as biomolecular condensates have been reported to play key roles in many cellular functions by compartmentalizing specific proteins and nucleic acids in subcellular environments with distinct properties. Furthermore, growing evidence supports the view that biomolecular condensates often form by phase separation, in which a single-phase system demixes into a two-phase system consisting of a condensed phase and a dilute phase of particular biomolecules. Emerging understanding of condensate function in normal and aberrant cellular states, and of the mechanisms of condensate formation, is providing new insights into human disease and revealing novel therapeutic opportunities. In this Perspective, we propose that such insights could enable a previously unexplored drug discovery approach based on identifying condensate-modifying therapeutics (c-mods), and we discuss the strategies, techniques and challenges involved.

Microfluidics for long-term single-cell time-lapse microscopy: Advances and applications

Cells are inherently dynamic, whether they are responding to environmental conditions or simply at equilibrium, with biomolecules constantly being made and destroyed. Due to their small volumes, the chemical reactions inside cells are stochastic, such that genetically identical cells display heterogeneous behaviors and gene expression profiles. Studying these dynamic processes is challenging, but the development of microfluidic methods enabling the tracking of individual prokaryotic cells with microscopy over long time periods under controlled growth conditions has led to many discoveries. This review focuses on the recent developments of one such microfluidic device nicknamed the mother machine. We overview the original device design, experimental setup, and challenges associated with this platform. We then describe recent methods for analyzing experiments using automated image segmentation and tracking. We further discuss modifications to the experimental setup that allow for time-varying environmental control, replicating batch culture conditions, cell screening based on their dynamic behaviors, and to accommodate a variety of microbial species. Finally, this review highlights the discoveries enabled by this technology in diverse fields, such as cell-size control, genetic mutations, cellular aging, and synthetic biology.

TNTdetect.AI: A Deep Learning Model for Automated Detection and Counting of Tunneling Nanotubes in Microscopy Images

Simple Summary

Microscopy is central to many areas of biomedical science research, including cancer research, and is critical for understanding basic pathophysiology, mechanisms of action, and treatment response. However, analysis of the numerous images generated from microscopy readouts is usually performed manually, a process that is tedious and time-consuming. Moreover, manual analysis of microscopy images may limit both accuracy and reproducibility. Here, we used an artificial intelligence approach to analyze tunnelling nanotubes (TNTs), a feature of cancer cells that may contribute to their aggressiveness, but which are hard to identify and count. Our approach labeled and detected TNTs and cancer cells from microscopy images and generated TNT-to-cell ratios comparable to those of human experts. Continued refinement of this process will provide a new approach to the analysis of TNTs. Additionally, this approach has the potential to enhance drug screens intended to assess therapeutic efficacy of experimental agents and to reproducibly assess TNTs as a potential biomarker of response to cancer therapy.

Abstract

Background: Tunneling nanotubes (TNTs) are cellular structures connecting cell membranes and mediating intercellular communication. TNTs are manually identified and counted by a trained investigator; however, this process is time-intensive. We therefore sought to develop an automated approach for quantitative analysis of TNTs. Methods: We used a convolutional neural network (U-Net) deep learning model to segment phase contrast microscopy images of both cancer and non-cancer cells. Our method was composed of preprocessing and model development. We developed a new preprocessing method to label TNTs on a pixel-wise basis. Two sequential models were employed to detect TNTs. First, we identified the regions of images with TNTs by implementing a classification algorithm. Second, we fed parts of the image classified as TNT-containing into a modified U-Net model to estimate TNTs on a pixel-wise basis. Results: The algorithm detected 49.9% of human expert-identified TNTs, counted TNTs, and calculated the number of TNTs per cell, or TNT-to-cell ratio (TCR); it detected TNTs that were not originally detected by the experts. The model had 0.41 precision, 0.26 recall, and 0.32 f-1 score on a test dataset. The predicted and true TCRs were not significantly different across the training and test datasets (p = 0.78). Conclusions: Our automated approach labeled and detected TNTs and cells imaged in culture, resulting in comparable TCRs to those determined by human experts. Future studies will aim to improve on the accuracy, precision, and recall of the algorithm.

Orthogonally-tunable and ER-targeting fluorophores detect avian influenza virus early infection

Cell-based assays can monitor virus infection at a single-cell level with high sensitivity and cost-efficiency. For this purpose, it is crucial to develop molecular probes that respond selectively to physiological changes in live cells. We report stimuli-responsive light-emitters built on a T-shaped benzimidazole platform, and consecutive borylation reactions to produce a library of homologs displaying systematic changes in fluorescence quantum yield and environmental sensitivity. We find that certain fluorophores localize selectively at the endoplasmic reticulum, and interact with proteins involved in the stress signaling pathways. Notably, the mono-borylated compound responds selectively to the stress conditions by enhancing fluorescence, and detects avian influenza virus infection at the single-cell level. Our findings demonstrate the unprecedented practical utility of the stress-responsive molecular probes to differentiate cellular states for early diagnosis.

Methods to detect and distinguish the early stage of viral infection often involve complicated and time-consuming protocols. Here, the authors disclose a class of fluorescent molecules that enable fast detection of avian influenza virus infection by selectively localizing at the endoplasmic reticulum in the cell.