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.
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.
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.
In the European regulatory context, rodent in vivo studies are the predominant source of neurotoxicity information. Although they form a cornerstone of neurotoxicological assessments, they are costly and the topic of ethical debate. While the public expects chemicals and products to be safe for the developing and mature nervous systems, considerable numbers of chemicals in commerce have not, or only to a limited extent, been assessed for their potential to cause neurotoxicity. As such, there is a societal push toward the replacement of animal models with in vitro or alternative methods. New approach methods (NAMs) can contribute to the regulatory knowledge base, increase chemical safety, and modernize chemical hazard and risk assessment. Provided they reach an acceptable level of regulatory relevance and reliability, NAMs may be considered as replacements for specific in vivo studies. The European Partnership for the Assessment of Risks from Chemicals (PARC) addresses challenges to the development and implementation of NAMs in chemical risk assessment. In collaboration with regulatory agencies, Project 5.2.1e (Neurotoxicity) aims to develop and evaluate NAMs for developmental neurotoxicity (DNT) and adult neurotoxicity (ANT) and to understand the applicability domain of specific NAMs for the detection of endocrine disruption and epigenetic perturbation. To speed up assay time and reduce costs, we identify early indicators of later-onset effects. Ultimately, we will assemble second-generation developmental neurotoxicity and first-generation adult neurotoxicity test batteries, both of which aim to provide regulatory hazard and risk assessors and industry stakeholders with robust, speedy, lower-cost, and informative next-generation hazard and risk assessment tools.
[This corrects the article DOI: 10.3389/ftox.2023.1212509.].
Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities of chemical and biological data to predict cardiotoxicity, using the recently released DICTrank data set from the United States FDA. We found that such data, including protein targets, especially those related to ion channels (e.g., hERG), physicochemical properties (e.g., electrotopological state), and peak concentration in plasma offer strong predictive ability for DICT. Compounds annotated with mechanisms of action such as cyclooxygenase inhibition could distinguish between most-concern and no-concern DICT. Cell Painting features for ER stress discerned most-concern cardiotoxic from nontoxic compounds. Models based on physicochemical properties provided substantial predictive accuracy (AUCPR = 0.93). With the availability of omics data in the future, using biological data promises enhanced predictability and deeper mechanistic insights, paving the way for safer drug development. All models from this study are available at https://broad.io/DICTrank_Predictor.
Cardiotoxicity , Drug Development , Humans , Cardiotoxicity/etiology , Cardiotoxicity/metabolism
Cell Painting assays generate morphological profiles that are versatile descriptors of biological systems and have been used to predict in vitro and in vivo drug effects. However, Cell Painting features extracted from classical software such as CellProfiler are based on statistical calculations and often not readily biologically interpretable. In this study, we propose a new feature space, which we call BioMorph, that maps these Cell Painting features with readouts from comprehensive Cell Health assays. We validated that the resulting BioMorph space effectively connected compounds not only with the morphological features associated with their bioactivity but with deeper insights into phenotypic characteristics and cellular processes associated with the given bioactivity. The BioMorph space revealed the mechanism of action for individual compounds, including dual-acting compounds such as emetine, an inhibitor of both protein synthesis and DNA replication. Overall, BioMorph space offers a biologically relevant way to interpret the cell morphological features derived using software such as CellProfiler and to generate hypotheses for experimental validation.
DNA Replication , Software , Phenotype
Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities of various chemical and biological data to predict cardiotoxicity, using the recently released Drug-Induced Cardiotoxicity Rank (DICTrank) dataset from the United States FDA. We analyzed a diverse set of data sources, including physicochemical properties, annotated mechanisms of action (MOA), Cell Painting, Gene Expression, and more, to identify indications of cardiotoxicity. We found that such data, including protein targets, especially those related to ion channels (such as hERG), physicochemical properties (such as electrotopological state) as well as peak concentration in plasma offer strong predictive ability as well as valuable insights into DICT. We also found compounds annotated with particular mechanisms of action, such as cyclooxygenase inhibition, could distinguish between most-concern and no-concern DICT compounds. Cell Painting features related to ER stress discern the most-concern cardiotoxic compounds from non-toxic compounds. While models based on physicochemical properties currently provide substantial predictive accuracy (AUCPR = 0.93), this study also underscores the potential benefits of incorporating more comprehensive biological data in future DICT predictive models. With the availability of - omics data in the future, using biological data promises enhanced predictability and delivers deeper mechanistic insights, paving the way for safer therapeutic drug development. All models and data used in this study are publicly released at https://broad.io/DICTrank_Predictor.
In past times, the analysis of endocrine disrupting properties of chemicals has mainly been focused on (anti-)estrogenic or (anti-)androgenic properties, as well as on aspects of steroidogenesis and the modulation of thyroid signaling. More recently, disruption of energy metabolism and related signaling pathways by exogenous substances, so-called metabolism-disrupting chemicals (MDCs) have come into focus. While general effects such as body and organ weight changes are routinely monitored in animal studies, there is a clear lack of mechanistic test systems to determine and characterize the metabolism-disrupting potential of chemicals. In order to contribute to filling this gap, one of the project within EU-funded Partnership for the Assessment of Risks of Chemicals (PARC) aims at developing novel in vitro methods for the detection of endocrine metabolic disruptors. Efforts will comprise projects related to specific signaling pathways, for example, involving mTOR or xenobiotic-sensing nuclear receptors, studies on hepatocytes, adipocytes and pancreatic beta cells covering metabolic and morphological endpoints, as well as metabolism-related zebrafish-based tests as an alternative to classic rodent bioassays. This paper provides an overview of the approaches and methods of these PARC projects and how this will contribute to the improvement of the toxicological toolbox to identify substances with endocrine disrupting properties and to decipher their mechanisms of action.
Fluorescence staining techniques, such as Cell Painting, together with fluorescence microscopy have proven invaluable for visualizing and quantifying the effects that drugs and other perturbations have on cultured cells. However, fluorescence microscopy is expensive, time-consuming, labor-intensive, and the stains applied can be cytotoxic, interfering with the activity under study. The simplest form of microscopy, brightfield microscopy, lacks these downsides, but the images produced have low contrast and the cellular compartments are difficult to discern. Nevertheless, by harnessing deep learning, these brightfield images may still be sufficient for various predictive purposes. In this study, we compared the predictive performance of models trained on fluorescence images to those trained on brightfield images for predicting the mechanism of action (MoA) of different drugs. We also extracted CellProfiler features from the fluorescence images and used them to benchmark the performance. Overall, we found comparable and largely correlated predictive performance for the two imaging modalities. This is promising for future studies of MoAs in time-lapse experiments for which using fluorescence images is problematic. Explorations based on explainable AI techniques also provided valuable insights regarding compounds that were better predicted by one modality over the other.
Image Processing, Computer-Assisted , Microscopy, Fluorescence/methods , Cells, Cultured , Image Processing, Computer-Assisted/methods
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.
Progressive multiple sclerosis (PMS) is currently diagnosed retrospectively. Here, we work toward a set of biomarkers that could assist in early diagnosis of PMS. A selection of cerebrospinal fluid metabolites (n = 15) was shown to differentiate between PMS and its preceding phenotype in an independent cohort (AUC = 0.93). Complementing the classifier with conformal prediction showed that highly confident predictions could be made, and that three out of eight patients developing PMS within three years of sample collection were predicted as PMS at that time point. Finally, this methodology was applied to PMS patients as part of a clinical trial for intrathecal treatment with rituximab. The methodology showed that 68% of the patients decreased their similarity to the PMS phenotype one year after treatment. In conclusion, the inclusion of confidence predictors contributes with more information compared to traditional machine learning, and this information is relevant for disease monitoring.
There is an ongoing aim to replace animal and in vitro laboratory models with in silico methods. Such replacement requires the successful validation and comparably good performance of the alternative methods. We have developed an in silico prediction system for human clinical pharmacokinetics, based on machine learning, conformal prediction and a new physiologically-based pharmacokinetic model, i.e. ANDROMEDA. The objectives of this study were: a) to evaluate how well ANDROMEDA predicts the human clinical pharmacokinetics of a previously proposed benchmarking data set comprising 24 physicochemically diverse drugs and 28 small drug molecules new to the market in 2021; b) to compare its predictive performance with that of laboratory methods; and c) to investigate and describe the pharmacokinetic characteristics of the modern drugs. Median and maximum prediction errors for the selected major parameters were ca 1.2 to 2.5-fold and 16-fold for both data sets, respectively. Prediction accuracy was on par with, or better than, the best laboratory-based prediction methods (superior performance for a vast majority of the comparisons), and the prediction range was considerably broader. The modern drugs have higher average molecular weight than those in the benchmarking set from 15 years earlier (ca 200 g/mol higher), and were predicted to (generally) have relatively complex pharmacokinetics, including permeability and dissolution limitations and significant renal, biliary and/or gut-wall elimination. In conclusion, the results were overall better than those obtained with laboratory methods, and thus serve to further validate the ANDROMEDA in silico system for the prediction of human clinical pharmacokinetics of modern and physicochemically diverse drugs.
Benchmarking , Models, Biological , Animals , Humans , Permeability , Pharmacokinetics , Pharmaceutical Preparations , Computer Simulation
Unreliable predictions can occur when an artificial intelligence (AI) system is presented with data it has not been exposed to during training. We demonstrate the use of conformal prediction to detect unreliable predictions, using histopathological diagnosis and grading of prostate biopsies as example. We digitized 7788 prostate biopsies from 1192 men in the STHLM3 diagnostic study, used for training, and 3059 biopsies from 676 men used for testing. With conformal prediction, 1 in 794 (0.1%) predictions is incorrect for cancer diagnosis (compared to 14 errors [2%] without conformal prediction) while 175 (22%) of the predictions are flagged as unreliable when the AI-system is presented with new data from the same lab and scanner that it was trained on. Conformal prediction could with small samples (N = 49 for external scanner, N = 10 for external lab and scanner, and N = 12 for external lab, scanner and pathology assessment) detect systematic differences in external data leading to worse predictive performance. The AI-system with conformal prediction commits 3 (2%) errors for cancer detection in cases of atypical prostate tissue compared to 44 (25%) without conformal prediction, while the system flags 143 (80%) unreliable predictions. We conclude that conformal prediction can increase patient safety of AI-systems.
Artificial Intelligence , Neoplasms , Male , Humans , Uncertainty , Prostate , Biopsy
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.
Biological Assay , Drug Discovery , Drug Discovery/methods , Gene Expression
Determining the levels of protein-protein interactions is essential for the analysis of signaling within the cell, characterization of mutation effects, protein function and activation in health and disease, among others. Herein, we describe MolBoolean - a method to detect interactions between endogenous proteins in various subcellular compartments, utilizing antibody-DNA conjugates for identification and signal amplification. In contrast to proximity ligation assays, MolBoolean simultaneously indicates the relative abundances of protein A and B not interacting with each other, as well as the pool of A and B proteins that are proximal enough to be considered an AB complex. MolBoolean is applicable both in fixed cells and tissue sections. The specific and quantifiable data that the method generates provide opportunities for both diagnostic use and medical research.
Protein Interaction Mapping , Proteins , Protein Interaction Mapping/methods , Proteins/metabolism , Signal Transduction
In vitro-in vivo prediction results for hepatic metabolic clearance (CLH) and intrinsic CLH (CLint) vary widely among studies. Reasons are not fully investigated and understood. The possibility to select favorable reference data for in vivo CLH and CLint and unbound fraction in plasma (fu) is among possible explanations. The main objective was to investigate how reference data selection influences log in vitro and in vivo CLint-correlations (r2). Another aim was to make a head-to-head comparison vs an in silico prediction method. Human hepatocyte CLint-data for 15 compounds from two studies were selected. These were correlated to in vivo CLint estimated using different reported CLH- and fu-estimates. Depending on the choice of reference data, r2 from two studies were 0.07 to 0.86 and 0.06 to 0.79. When using average reference estimates a r2 of 0.62 was achieved. Inclusion of two outliers in one of the studies resulted in a r2 of 0.38, which was lower than the predictive accuracy (q2) for the in silico method (0.48). In conclusion, the selection of reference data appears to play a major role for demonstrated predictions and the in silico method showed higher accuracy and wider range than hepatocytes for human in vivo CLint-predictions.
Hepatocytes , Liver , Hepatocytes/metabolism , Humans , Kinetics , Liver/metabolism , Metabolic Clearance Rate , Microsomes, Liver/metabolism
Objective: The aim of this project was to implement long-read sequencing for BCR-ABL1 TKI resistance mutation screening in a clinical setting for patients undergoing treatment for chronic myeloid leukemia. Materials and Methods: Processes were established for registering and transferring samples from the clinic to an academic sequencing facility for long-read sequencing. An automated analysis pipeline for detecting mutations was established, and an information system was implemented comprising features for data management, analysis and visualization. Clinical validation was performed by identifying BCR-ABL1 TKI resistance mutations by Sanger and long-read sequencing in parallel. The developed software is available as open source via GitHub at https://github.com/pharmbio/clamp. Results: The information system enabled traceable transfer of samples from the clinic to the sequencing facility, robust and automated analysis of the long-read sequence data, and communication of results from sequence analysis in a reporting format that could be easily interpreted and acted upon by clinical experts. In a validation study, all 17 resistance mutations found by Sanger sequencing were also detected by long-read sequencing. An additional 16 mutations were found only by long-read sequencing, all of them with frequencies below the limit of detection for Sanger sequencing. The clonal distributions of co-existing mutations were automatically resolved through the long-read data analysis. After the implementation and validation, the clinical laboratory switched their routine protocol from using Sanger to long-read sequencing for this application. Conclusions: Long-read sequencing delivers results with higher sensitivity compared to Sanger sequencing and enables earlier detection of emerging TKI resistance mutations. The developed processes, analysis workflow, and software components lower barriers for adoption and could be extended to other applications.
