Prediction of drug-induced liver injury and cardiotoxicity using chemical structure and in vitro assay data.

Drug-induced liver injury (DILI) and cardiotoxicity (DICT) are major adverse effects triggered by many clinically important drugs. To provide an alternative to in vivo toxicity testing, the U.S. Tox21 consortium has screened a collection of ∼10K compounds, including drugs in clinical use, against >70 cell-based assays in a quantitative high-throughput screening (qHTS) format. In this study, we compiled reference compound lists for DILI and DICT and compared the potential of Tox21 assay data with chemical structure information in building prediction models for human in vivo hepatotoxicity and cardiotoxicity. Models were built with four different machine learning algorithms (e.g., Random Forest, Naïve Bayes, eXtreme Gradient Boosting, and Support Vector Machine) and model performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC-ROC). Chemical structure-based models showed reasonable predictive power for DILI (best AUC-ROC = 0.75 ± 0.03) and DICT (best AUC-ROC = 0.83 ± 0.03), while Tox21 assay data alone only showed better than random performance. DILI and DICT prediction models built using a combination of assay data and chemical structure information did not have a positive impact on model performance. The suboptimal predictive performance of the assay data is likely due to insufficient coverage of an adequately predictive number of toxicity mechanisms. The Tox21 consortium is currently expanding coverage of biological response space with additional assays that probe toxicologically important targets and under-represented pathways that may improve the prediction of in vivo toxicity such as DILI and DICT.

Using in vitro ADME data for lead compound selection: An emphasis on PAMPA pH 5 permeability and oral bioavailability.

Membrane permeability plays an important role in oral drug absorption. Caco-2 and Madin-Darby Canine Kidney (MDCK) cell culture systems have been widely used for assessing intestinal permeability. Since most drugs are absorbed passively, Parallel Artificial Membrane Permeability Assay (PAMPA) has gained popularity as a low-cost and high-throughput method in early drug discovery when compared to high-cost, labor intensive cell-based assays. At the National Center for Advancing Translational Sciences (NCATS), PAMPA pH 5 is employed as one of the Tier I absorption, distribution, metabolism, and elimination (ADME) assays. In this study, we have developed a quantitative structure activity relationship (QSAR) model using our ∼6500 compound PAMPA pH 5 permeability dataset. Along with ensemble decision tree-based methods such as Random Forest and eXtreme Gradient Boosting, we employed deep neural network and a graph convolutional neural network to model PAMPA pH 5 permeability. The classification models trained on a balanced training set provided accuracies ranging from 71% to 78% on the external set. Of the four classifiers, the graph convolutional neural network that directly operates on molecular graphs offered the best classification performance. Additionally, an ∼85% correlation was obtained between PAMPA pH 5 permeability and in vivo oral bioavailability in mice and rats. These results suggest that data from this assay (experimental or predicted) can be used to rank-order compounds for preclinical in vivo testing with a high degree of confidence, reducing cost and attrition as well as accelerating the drug discovery process. Additionally, experimental data for 486 compounds (PubChem AID: 1645871) and the best models have been made publicly available (https://opendata.ncats.nih.gov/adme/).

Drug Repurposing Screen for Compounds Inhibiting the Cytopathic Effect of SARS-CoV-2.

Drug repurposing is a rapid approach to identifying therapeutics for the treatment of emerging infectious diseases such as COVID-19. To address the urgent need for treatment options, we carried out a quantitative high-throughput screen using a SARS-CoV-2 cytopathic assay with a compound collection of 8,810 approved and investigational drugs, mechanism-based bioactive compounds, and natural products. Three hundred and nineteen compounds with anti-SARS-CoV-2 activities were identified and confirmed, including 91 approved drug and 49 investigational drugs. Among these confirmed compounds, the anti-SARS-CoV-2 activities of 230 compounds, including 38 approved drugs, have not been previously reported. Chlorprothixene, methotrimeprazine, and piperacetazine were the three most potent FDA approved drugs with anti-SARS-CoV-2 activities. These three compounds have not been previously reported to have anti-SARS-CoV-2 activities, although their antiviral activities against SARS-CoV and Ebola virus have been reported. These results demonstrate that this comprehensive data set of drug repurposing screen for SARS-CoV-2 is useful for drug repurposing efforts including design of new drug combinations for clinical trials.

An OpenData portal to share COVID-19 drug repurposing data in real time.

The National Center for Advancing Translational Sciences (NCATS) has developed an online open science data portal for its COVID-19 drug repurposing campaign - named OpenData - with the goal of making data across a range of SARS-CoV-2 related assays available in real-time. The assays developed cover a wide spectrum of the SARS-CoV-2 life cycle, including both viral and human (host) targets. In total, over 10,000 compounds are being tested in full concentration-response ranges from across multiple annotated small molecule libraries, including approved drug, repurposing candidates and experimental therapeutics designed to modulate a wide range of cellular targets. The goal is to support research scientists, clinical investigators and public health officials through open data sharing and analysis tools to expedite the development of SARS-CoV-2 interventions, and to prioritize promising compounds and repurposed drugs for further development in treating COVID-19.

Drug Repurposing Screen for Compounds Inhibiting the Cytopathic Effect of SARS-CoV-2.

Drug repurposing is a rapid approach to identify therapeutics for the treatment of emerging infectious diseases such as COVID-19. To address the urgent need for treatment options, we carried out a quantitative high-throughput screen using a SARS-CoV-2 cytopathic assay with a compound collection of 8,810 approved and investigational drugs, mechanism-based bioactive compounds, and natural products. Three hundred and nineteen compounds with anti-SARS-CoV-2 activities were identified and confirmed, including 91 approved drugs and 49 investigational drugs. The anti-SARS-CoV-2 activities of 230 of these confirmed compounds, of which 38 are approved drugs, have not been previously reported. Chlorprothixene, methotrimeprazine, and piperacetazine were the three most potent FDA-approved drugs with anti-SARS-CoV-2 activities. These three compounds have not been previously reported to have anti-SARS-CoV-2 activities, although their antiviral activities against SARS-CoV and Ebola virus have been reported. These results demonstrate that this comprehensive data set is a useful resource for drug repurposing efforts, including design of new drug combinations for clinical trials for SARS-CoV-2.

Novel Consensus Architecture To Improve Performance of Large-Scale Multitask Deep Learning QSAR Models.

Advances in the development of high-throughput screening and automated chemistry have rapidly accelerated the production of chemical and biological data, much of them freely accessible through literature aggregator services such as ChEMBL and PubChem. Here, we explore how to use this comprehensive mapping of chemical biology space to support the development of large-scale quantitative structure-activity relationship (QSAR) models. We propose a new deep learning consensus architecture (DLCA) that combines consensus and multitask deep learning approaches together to generate large-scale QSAR models. This method improves knowledge transfer across different target/assays while also integrating contributions from models based on different descriptors. The proposed approach was validated and compared with proteochemometrics, multitask deep learning, and Random Forest methods paired with various descriptors types. DLCA models demonstrated improved prediction accuracy for both regression and classification tasks. The best models together with their modeling sets are provided through publicly available web services at https://predictor.ncats.io .

The NCATS Pharmaceutical Collection: a 10-year update.

The National Center for Advancing Translational Sciences (NCATS) Pharmaceutical Collection (NPC), a comprehensive collection of clinically approved drugs, was made a public resource in 2011. Over the past decade, the NPC has been systematically profiled for activity across an array of pathways and disease models, generating an unparalleled amount of data. These data have not only enabled the identification of new repurposing candidates with several in clinical trials, but also uncovered new biological insights into drug targets and disease mechanisms. This retrospective provides an update on the NPC in terms of both successes and lessons learned. We also report our efforts in bringing the NPC up-to-date with drugs approved in recent years.

The NCATS BioPlanet - An Integrated Platform for Exploring the Universe of Cellular Signaling Pathways for Toxicology, Systems Biology, and Chemical Genomics.

Chemical genomics aims to comprehensively define, and ultimately predict, the effects of small molecule compounds on biological systems. Chemical activity profiling approaches must consider chemical effects on all pathways operative in mammalian cells. To enable a strategic and maximally efficient chemical profiling of pathway space, we have created the NCATS BioPlanet, a comprehensive integrated pathway resource that incorporates the universe of 1,658 human pathways sourced from publicly available, manually curated sources, which have been subjected to thorough redundancy and consistency cross-evaluation. BioPlanet supports interactive browsing, retrieval, and analysis of pathways, exploration of pathway connections, and pathway search by gene targets, category, and availability of corresponding bioactivity assay, as well as visualization of pathways on a 3-dimensional globe, in which the distance between any two pathways is proportional to their degree of gene component overlap. Using this resource, we propose a strategy to identify a minimal set of 362 biological assays that can interrogate the universe of human pathways. The NCATS BioPlanet is a public resource, which will be continually expanded and updated, for systems biology, toxicology, and chemical genomics, available at http://tripod.nih.gov/bioplanet/.

Expanding biological space coverage enhances the prediction of drug adverse effects in human using in vitro activity profiles.

In vitro assay data have recently emerged as a potential alternative to traditional animal toxicity studies to aid in the prediction of adverse effects of chemicals on humans. Here we evaluate the data generated from a battery of quantitative high-throughput screening (qHTS) assays applied to a large and diverse collection of chemicals, including approved drugs, for their capacity in predicting human toxicity. Models were built with animal in vivo toxicity data, in vitro human cell-based assay data, as well as in combination with chemical structure and/or drug-target information to predict adverse effects observed for drugs in humans. Interestingly, we found that the models built with the human cell-based assay data performed close to those of the models based on animal in vivo toxicity data. Furthermore, expanding the biological space coverage of assays by including additional drug-target annotations was shown to significantly improve model performance. We identified a small set of targets, which, when added to the current suite of in vitro human cell-based assay data, result in models that greatly outperform those built with the existing animal toxicity data. Assays can be developed for this set of targets to screen compounds for construction of robust models for human toxicity prediction.

Canvass: A Crowd-Sourced, Natural-Product Screening Library for Exploring Biological Space.

Natural products and their derivatives continue to be wellsprings of nascent therapeutic potential. However, many laboratories have limited resources for biological evaluation, leaving their previously isolated or synthesized compounds largely or completely untested. To address this issue, the Canvass library of natural products was assembled, in collaboration with academic and industry researchers, for quantitative high-throughput screening (qHTS) across a diverse set of cell-based and biochemical assays. Characterization of the library in terms of physicochemical properties, structural diversity, and similarity to compounds in publicly available libraries indicates that the Canvass library contains many structural elements in common with approved drugs. The assay data generated were analyzed using a variety of quality control metrics, and the resultant assay profiles were explored using statistical methods, such as clustering and compound promiscuity analyses. Individual compounds were then sorted by structural class and activity profiles. Differential behavior based on these classifications, as well as noteworthy activities, are outlined herein. One such highlight is the activity of (-)-2(S)-cathafoline, which was found to stabilize calcium levels in the endoplasmic reticulum. The workflow described here illustrates a pilot effort to broadly survey the biological potential of natural products by utilizing the power of automation and high-throughput screening.

Modelling the Tox21 10 K chemical profiles for in vivo toxicity prediction and mechanism characterization.

Target-specific, mechanism-oriented in vitro assays post a promising alternative to traditional animal toxicology studies. Here we report the first comprehensive analysis of the Tox21 effort, a large-scale in vitro toxicity screening of chemicals. We test ∼ 10,000 chemicals in triplicates at 15 concentrations against a panel of nuclear receptor and stress response pathway assays, producing more than 50 million data points. Compound clustering by structure similarity and activity profile similarity across the assays reveals structure-activity relationships that are useful for the generation of mechanistic hypotheses. We apply structural information and activity data to build predictive models for 72 in vivo toxicity end points using a cluster-based approach. Models based on in vitro assay data perform better in predicting human toxicity end points than animal toxicity, while a combination of structural and activity data results in better models than using structure or activity data alone. Our results suggest that in vitro activity profiles can be applied as signatures of compound mechanism of toxicity and used in prioritization for more in-depth toxicological testing.

Profiling of the Tox21 10K compound library for agonists and antagonists of the estrogen receptor alpha signaling pathway.

The U.S. Tox21 program has screened a library of approximately 10,000 (10K) environmental chemicals and drugs in three independent runs for estrogen receptor alpha (ERα) agonist and antagonist activity using two types of ER reporter gene cell lines, one with an endogenous full length ERα (ER-luc; BG1 cell line) and the other with a transfected partial receptor consisting of the ligand binding domain (ER-bla; ERα ß-lactamase cell line), in a quantitative high-throughput screening (qHTS) format. The ability of the two assays to correctly identify ERα agonists and antagonists was evaluated using a set of 39 reference compounds with known ERα activity. Although both assays demonstrated adequate (i.e. >80%) predictivity, the ER-luc assay was more sensitive and the ER-bla assay more specific. The qHTS assay results were compared with results from previously published ERα binding assay data and showed >80% consistency. Actives identified from both the ER-bla and ER-luc assays were analyzed for structure-activity relationships (SARs) revealing known and potentially novel ERα active structure classes. The results demonstrate the feasibility of qHTS to identify environmental chemicals with the potential to interact with the ERα signaling pathway and the two different assay formats improve the confidence in correctly identifying these chemicals.