High-Throughput Screening to Advance In Vitro Toxicology: Accomplishments, Challenges, and Future Directions.

Traditionally, chemical toxicity is determined by in vivo animal studies, which are low throughput, expensive, and sometimes fail to predict compound toxicity in humans. Due to the increasing number of chemicals in use and the high rate of drug candidate failure due to toxicity, it is imperative to develop in vitro, high-throughput screening methods to determine toxicity. The Tox21 program, a unique research consortium of federal public health agencies, was established to address and identify toxicity concerns in a high-throughput, concentration-responsive manner using a battery of in vitro assays. In this article, we review the advancements in high-throughput robotic screening methodology and informatics processes to enable the generation of toxicological data, and their impact on the field; further, we discuss the future of assessing environmental toxicity utilizing efficient and scalable methods that better represent the corresponding biological and toxicodynamic processes in humans.

Prediction of chemical-induced acute toxicity using in vitro assay data and chemical structure.

Exposure to various chemicals found in the environment and in the context of drug development can cause acute toxicity. To provide an alternative to in vivo animal toxicity testing, the U.S. Tox21 consortium developed in vitro assays to test a library of approximately 10,000 drugs and environmental chemicals (Tox21 10 K compound library) in a quantitative high-throughput screening (qHTS) approach. In this study, we assessed the utility of Tox21 assay data in comparison with chemical structure information in predicting acute systemic toxicity. Prediction models were developed using four machine learning algorithms, namely Random Forest, Naïve Bayes, eXtreme Gradient Boosting, and Support Vector Machine, and their performance was assessed using the area under the receiver operating characteristic curve (AUC-ROC). The chemical structure-based models as well as the Tox21 assay data demonstrated good predictive power for acute toxicity, achieving AUC-ROC values ranging from 0.83 to 0.93 and 0.73 to 0.79, respectively. We applied the models to predict the acute toxicity potential of the compounds in the Tox21 10 K compound library, most of which were found to be non-toxic. In addition, we identified the Tox21 assays that contributed the most to acute toxicity prediction, such as acetylcholinesterase (AChE) inhibition and p53 induction. Chemical features including organophosphates and carbamates were also identified to be significantly associated with acute toxicity. In conclusion, this study underscores the utility of in vitro assay data in predicting acute toxicity.

Evaluating the Utility of the MSTI Assay in Predicting Compound Promiscuity and Cytotoxicity.

Nonspecific reactive chemicals often interfere with the interpretation of high-throughput assay results because of their promiscuity and/or cytotoxicity. Using a high-throughput assay to identify such compounds is necessary to efficiently rule out potential assay artifacts. The MSTI, (E)-2-(4-mercaptostyryl)-1,3,3-trimethyl-3H-indol-1-ium, assay uses a thiol-containing fluorescent probe to screen for electrophile reactivity and could potentially be used to determine nonspecific reactive compounds. The Tox21 10K compound library was previously screened against a panel of ∼80 cell-based and biochemical assays, including the biochemical MSTI assay. In this study, we compared the MSTI assay activity of the Tox21 10K compounds with their promiscuity and cytotoxicity as reflected by their activities across the Tox21 assay panel to determine: (1) if this assay is predictive of a compound's promiscuity and cytotoxicity and (2) what chemical features create inconsistent results between the MSTI assay activity and promiscuity/cytotoxicity (false negatives and false positives). We found that the MSTI assay can predict a chemical's promiscuity/cytotoxicity with a 0.55 sensitivity and 0.97 specificity. Out of 3,407 unique compounds evaluated, we identified 92 false positive and 227 false negative results. Several structural features such as carboxamides and alkyl halides were found to be apparent in 53% (p = 2.4 × 10-07) and 19% (p = 4.3 × 10-06) of the false positives and negatives, respectively. The results of this analysis will help identify the potential challenges of this high-throughput assay and allow researchers to identify if a compound will be cytotoxic or promiscuous in an efficient manner.

Decoding the κ Opioid Receptor (KOR): Advancements in Structural Understanding and Implications for Opioid Analgesic Development.

The opioid crisis in the United States is a significant public health issue, with a nearly threefold increase in opioid-related fatalities between 1999 and 2014. In response to this crisis, society has made numerous efforts to mitigate its impact. Recent advancements in understanding the structural intricacies of the κ opioid receptor (KOR) have improved our knowledge of how opioids interact with their receptors, triggering downstream signaling pathways that lead to pain relief. This review concentrates on the KOR, offering crucial structural insights into the binding mechanisms of both agonists and antagonists to the receptor. Through comparative analysis of the atomic details of the binding site, distinct interactions specific to agonists and antagonists have been identified. These insights not only enhance our understanding of ligand binding mechanisms but also shed light on potential pathways for developing new opioid analgesics with an improved risk-benefit profile.

In vitro profiling of pesticides within the Tox21 10K compound library for bioactivity and potential toxicity.

Pesticides include a diverse class of toxic chemicals, often having numerous modes of actions when used in agriculture against targeted organisms to control insect infestation, halt unwanted vegetation, and prevent the spread of disease. In this study, the in vitro assay activity of pesticides within the Tox21 10K compound library were examined. The assays in which pesticides showed significantly more activities than non-pesticide chemicals revealed potential targets and mechanisms of action for pesticides. Furthermore, pesticides that showed promiscuous activity against many targets and cytotoxicity were identified, which warrant further toxicological evaluation. Several pesticides were shown to require metabolic activation, demonstrating the importance of introducing metabolic capacity to in vitro assays. Overall, the activity profiles of pesticides highlighted in this study can contribute to the knowledge gaps surrounding pesticide mechanisms and to the better understanding of the on- and off-target organismal effects of pesticides.

Identification of Potent and Selective Acetylcholinesterase/Butyrylcholinesterase Inhibitors by Virtual Screening.

Acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) play important roles in human neurodegenerative disorders such as Alzheimer's disease. In this study, machine learning methods were applied to develop quantitative structure-activity relationship models for the prediction of novel AChE and BChE inhibitors based on data from quantitative high-throughput screening assays. The models were used to virtually screen an in-house collection of ∼360K compounds. The optimal models achieved good performance with area under the receiver operating characteristic curve values ranging from 0.83 ± 0.03 to 0.87 ± 0.01 for the prediction of AChE/BChE inhibition activity and selectivity. Experimental validation showed that the best-performing models increased the assay hit rate by several folds. We identified 88 novel AChE and 126 novel BChE inhibitors, 25% (AChE) and 53% (BChE) of which showed potent inhibitory effects (IC50 < 5 µM). In addition, structure-activity relationship analysis of the BChE inhibitors revealed scaffolds for chemistry design and optimization. In conclusion, machine learning models were shown to efficiently identify potent and selective inhibitors against AChE and BChE and novel structural series for further design and development of potential therapeutics against neurodegenerative disorders.

Predictive Models for Human Cytochrome P450 3A7 Selective Inhibitors and Substrates.

Inappropriate use of prescription drugs is potentially more harmful in fetuses/neonates than in adults. Cytochrome P450 (CYP) 3A subfamily undergoes developmental changes in expression, such as a transition from CYP3A7 to CYP3A4 shortly after birth, which provides a potential way to distinguish medication effects on fetuses/neonates and adults. The purpose of this study was to build first-in-class predictive models for both inhibitors and substrates of CYP3A7/CYP3A4 using chemical structure analysis. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The performance varied for each CYP3A7/CYP3A4 inhibitor/substrate model depending on the data set type, model type, rebalancing method, and specific feature set. For the active inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.77 ± 0.01 to 0.84 ± 0.01. For the selective inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.72 ± 0.02 to 0.79 ± 0.04. The predictive power of the optimal models was validated by compounds with known potencies as CYP3A7/CYP3A4 inhibitors or substrates. In addition, we identified structural features significant for CYP3A7/CYP3A4 selective or common inhibitors and substrates. In summary, the top performing models can be further applied as a tool to rapidly evaluate the safety and efficacy of new drugs separately for fetuses/neonates and adults. The significant structural features could guide the design of new therapeutic drugs as well as aid in the optimization of existing medicine for fetuses/neonates.

Three-Dimensional Structural Insights Have Revealed the Distinct Binding Interactions of Agonists, Partial Agonists, and Antagonists with the µ Opioid Receptor.

The United States is experiencing the most profound and devastating opioid crisis in history, with the number of deaths involving opioids, including prescription and illegal opioids, continuing to climb over the past two decades. This severe public health issue is difficult to combat as opioids remain a crucial treatment for pain, and at the same time, they are also highly addictive. Opioids act on the opioid receptor, which in turn activates its downstream signaling pathway that eventually leads to an analgesic effect. Among the four types of opioid receptors, the µ subtype is primarily responsible for the analgesic cascade. This review describes available 3D structures of the µ opioid receptor in the protein data bank and provides structural insights for the binding of agonists and antagonists to the receptor. Comparative analysis on the atomic details of the binding site in these structures was conducted and distinct binding interactions for agonists, partial agonists, and antagonists were observed. The findings in this article deepen our understanding of the ligand binding activity and shed some light on the development of novel opioid analgesics which may improve the risk benefit balance of existing opioids.

Identification of nonmonotonic concentration-responses in Tox21 high-throughput screening estrogen receptor assays.

Environmental endocrine-disrupting chemicals (EDCs) interfere with the metabolism and actions of endogenous hormones. It has been well documented in numerous in vivo and in vitro studies that EDCs can exhibit nonmonotonic dose response (NMDR) behaviors. Not conforming to the conventional linear or linear-no-threshold response paradigm, these NMDR relationships pose practical challenges to the risk assessment of EDCs. In the meantime, the endocrine signaling pathways and biological mechanisms underpinning NMDR remain incompletely understood. The US Tox21 program has conducted in vitro cell-based high-throughput screening assays for estrogen receptors (ER), androgen receptors, and other nuclear receptors, and screened the 10 K-compound library for potential endocrine activities. Using 15 concentrations across several orders of magnitude of concentration range and run in both agonist and antagonist modes, these Tox21 assay datasets contain valuable quantitative information that can be explored to evaluate the nonlinear effects of EDCs and may infer potential mechanisms. In this study we analyzed the concentration-response curves (CRCs) in all 8 Tox21 ERα and ERß assays by developing clustering and classification algorithms customized to the datasets to identify various shapes of CRCs. After excluding NMDR curves likely caused by cytotoxicity, luciferase inhibition, or autofluorescence, hundreds of compounds were identified to exhibit Bell or U-shaped CRCs. Bell-shaped CRCs are about 7 times more frequent than U-shaped ones in the Tox21 ER assays. Many compounds exhibit NMDR in at least one assay, and some EDCs well-known for their NMDRs in the literature were also identified, suggesting their nonmonotonic effects may originate at cellular levels involving transcriptional ER signaling. The developed computational methods for NMDR identification in ER assays can be adapted and applied to other high-throughput bioassays.

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.

Retro Drug Design: From Target Properties to Molecular Structures.

To deliver more therapeutics to more patients more quickly and economically is the ultimate goal of pharmaceutical researchers. The advent and rapid development of artificial intelligence (AI), in combination with other powerful computational methods in drug discovery, makes this goal more practical than ever before. Here, we describe a new strategy, retro drug design, or RDD, to create novel small-molecule drugs from scratch to meet multiple predefined requirements, including biological activity against a drug target and optimal range of physicochemical and ADMET properties. The molecular structure was represented by an atom typing based molecular descriptor system, optATP, which was further transformed to the space of loading vectors from principal component analysis. Traditional predictive models were trained over experimental data for the target properties using optATP and shallow machine learning methods. The Monte Carlo sampling algorithm was then utilized to find the solutions in the space of loading vectors that have the target properties. Finally, a deep learning model was employed to decode molecular structures from the solutions. To test the feasibility of the algorithm, we challenged RDD to generate novel kinase inhibitors from random numbers with five different ADMET properties optimized at the same time. The best Tanimoto similarity score between the generated valid structures and the available 4,314 kinase inhibitors was < 0.50, indicating a high extent of novelty of the generated compounds. From the 3,040 structures that met all six target properties, 20 were selected for synthesis and experimental measurement of inhibition activity over 97 representative kinases and the ADMET properties. Fifteen and eight compounds were determined to be hits or strong hits, respectively. Five of the six strong kinase inhibitors have excellent experimental ADMET properties. The results presented in this paper illustrate that RDD has the potential to significantly improve the current drug discovery process.

AZD8055 enhances in vivo efficacy of afatinib in chordomas.

Chordomas are primary bone tumors that arise in the cranial base, mobile spine, and sacrococcygeal region, affecting patients of all ages. Currently, there are no approved agents for chordoma patients. Here, we evaluated the anti-tumor efficacy of small molecule inhibitors that target oncogenic pathways in chordoma, as single agents and in combination, to identify novel therapeutic approaches with the greatest translational potential. A panel of small molecule compounds was screened in vivo against patient-derived xenograft (PDX) models of chordoma, and potentially synergistic combinations were further evaluated using chordoma cell lines and xenograft models. Among the tested agents, inhibitors of EGFR (BIBX 1382, erlotinib, and afatinib), c-MET (crizotinib), and mTOR (AZD8055) significantly inhibited tumor growth in vivo but did not induce tumor regression. Co-inhibition of EGFR and c-MET using erlotinib and crizotinib synergistically reduced cell viability in chordoma cell lines but did not result in enhanced in vivo activity. Co-inhibition of EGFR and mTOR pathways using afatinib and AZD8055 synergistically reduced cell viability in chordoma cell lines. Importantly, this dual inhibition completely suppressed tumor growth in vivo, showing improved tumor control. Together, these data demonstrate that individual inhibitors of EGFR, c-MET, and mTOR pathways suppress chordoma growth both in vitro and in vivo. mTOR inhibition increased the efficacy of EGFR inhibition on chordoma growth in several preclinical models. The insights gained from our study potentially provide a novel combination therapeutic strategy for patients with chordoma. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Improving the solubility and antileukemia activity of Wnt/ß-catenin signaling inhibitors by disrupting molecular planarity.

Leukemia cells depend on the Wnt/ß-catenin signaling pathway for their growth. Pyrvinium, a known Wnt signaling inhibitor, has demonstrated promising efficacy in the treatment of the aggressive blast phase chronic myeloid leukemia (BP-CML). We previously developed potent inhibitors 1-2 for the Wnt/ß-catenin signaling pathway. However, the further application of these compounds as anti-leukemia agents is limited by their modest anti-leukemia activity in cells and poor aqueous solubility, due to the high molecular planarity of the chemical scaffold. Here, we reported our efforts in the synthesis and in vitro evaluation of 18 new compounds (4a-r) that have been designed to disrupt the molecular planarity of the chemical scaffold. Several compounds of the series showed significantly improved anti-leukemia activity and aqueous solubility. As a highlight, compounds 4c not only maintained excellent inhibitory potency (IC50 = 1.3 nM) for Wnt signaling but also demonstrated good anti-leukemia potency (IC50 = 0.9 µM) in the CML K562 cells. Moreover, compound 4c had an aqueous solubility of 5.9 µg/mL, which is over 50-fold enhanced compared to its parents 1-2.

Identification of environmental chemicals that activate p53 signaling after in vitro metabolic activation.

Currently, approximately 80,000 chemicals are used in commerce. Most have little-to-no toxicity information. The U.S. Toxicology in the 21st Century (Tox21) program has conducted a battery of in vitro assays using a quantitative high-throughput screening (qHTS) platform to gain toxicity information on environmental chemicals. Due to technical challenges, standard methods for providing xenobiotic metabolism could not be applied to qHTS assays. To address this limitation, we screened the Tox21 10,000-compound (10K) library, with concentrations ranging from 2.8 nM to 92 µM, using a p53 beta-lactamase reporter gene assay (p53-bla) alone or with rat liver microsomes (RLM) or human liver microsomes (HLM) supplemented with NADPH, to identify compounds that induce p53 signaling after biotransformation. Two hundred and seventy-eight compounds were identified as active under any of these three conditions. Of these 278 compounds, 73 gave more potent responses in the p53-bla assay with RLM, and 2 were more potent in the p53-bla assay with HLM compared with the responses they generated in the p53-bla assay without microsomes. To confirm the role of metabolism in the differential responses, we re-tested these 75 compounds in the absence of NADPH or with heat-attenuated microsomes. Forty-four compounds treated with RLM, but none with HLM, became less potent under these conditions, confirming the role of RLM in metabolic activation. Further evidence of biotransformation was obtained by measuring the half-life of the parent compounds in the presence of microsomes. Together, the data support the use of RLM in qHTS for identifying chemicals requiring biotransformation to induce biological responses.

A Universal and High-Throughput Proteomics Sample Preparation Platform.

Major advances have been made to improve the sensitivity of mass analyzers, spectral quality, and speed of data processing enabling more comprehensive proteome discovery and quantitation. While focus has recently begun shifting toward robust proteomics sample preparation efforts, a high-throughput proteomics sample preparation is still lacking. We report the development of a highly automated universal 384-well plate sample preparation platform with high reproducibility and adaptability for extraction of proteins from cells within a culture plate. Digestion efficiency was excellent in comparison to a commercial digest peptide standard with minimal sample loss while improving sample preparation throughput by 20- to 40-fold (the entire process from plated cells to clean peptides is complete in ∼300 min). Analysis of six human cell types, including two primary cell samples, identified and quantified ∼4,000 proteins for each sample in a single high-performance liquid chromatography (HPLC)-tandem mass spectrometry injection with only 100-10K cells, thus demonstrating universality of the platform. The selected protein was further quantified using a developed HPLC-multiple reaction monitoring method for HeLa digests with two heavy labeled internal standard peptides spiked in. Excellent linearity was achieved across different cell numbers indicating a potential for target protein quantitation in clinical research.

Development of Robust Quantitative Structure-Activity Relationship Models for CYP2C9, CYP2D6, and CYP3A4 Catalysis and Inhibition.

Cytochrome P450 enzymes are responsible for the metabolism of >75% of marketed drugs, making it essential to identify the contributions of individual cytochromes P450 to the total clearance of a new candidate drug. Overreliance on one cytochrome P450 for clearance levies a high risk of drug-drug interactions; and considering that several human cytochrome P450 enzymes are polymorphic, it can also lead to highly variable pharmacokinetics in the clinic. Thus, it would be advantageous to understand the likelihood of new chemical entities to interact with the major cytochrome P450 enzymes at an early stage in the drug discovery process. Typical screening assays using human liver microsomes do not provide sufficient information to distinguish the specific cytochromes P450 responsible for clearance. In this regard, we experimentally assessed the metabolic stability of ∼5000 compounds for the three most prominent xenobiotic metabolizing human cytochromes P450, i.e., CYP2C9, CYP2D6, and CYP3A4, and used the data sets to develop quantitative structure-activity relationship models for the prediction of high-clearance substrates for these enzymes. Screening library included the NCATS Pharmaceutical Collection, comprising clinically approved low-molecular-weight compounds, and an annotated library consisting of drug-like compounds. To identify inhibitors, the library was screened against a luminescence-based cytochrome P450 inhibition assay; and through crossreferencing hits from the two assays, we were able to distinguish substrates and inhibitors of these enzymes. The best substrate and inhibitor models (balanced accuracies ∼0.7), as well as the data used to develop these models, have been made publicly available (https://opendata.ncats.nih.gov/adme) to advance drug discovery across all research groups. SIGNIFICANCE STATEMENT: In drug discovery and development, drug candidates with indiscriminate cytochrome P450 metabolic profiles are considered advantageous, since they provide less risk of potential issues with cytochrome P450 polymorphisms and drug-drug interactions. This study developed robust substrate and inhibitor quantitative structure-activity relationship models for the three major xenobiotic metabolizing cytochromes P450, i.e., CYP2C9, CYP2D6, and CYP3A4. The use of these models early in drug discovery will enable project teams to strategize or pivot when necessary, thereby accelerating drug discovery research.

Resources for Developing Reliable and Reproducible In Vitro Toxicological Test Methods.

A broad range of in vitro test methods have been developed given their numerous potential advantages over in vivo tests. We describe here key resources and tools to increase the reliability and reproducibility of in vitro toxicological test methods.

Systematic Identification of Molecular Targets and Pathways Related to Human Organ Level Toxicity.

The mechanisms leading to organ level toxicities are poorly understood. In this study, we applied an integrated approach to deduce the molecular targets and biological pathways involved in chemically induced toxicity for eight common human organ level toxicity end points (carcinogenicity, cardiotoxicity, developmental toxicity, hepatotoxicity, nephrotoxicity, neurotoxicity, reproductive toxicity, and skin toxicity). Integrated analysis of in vitro assay data, molecular targets and pathway annotations from the literature, and toxicity-molecular target associations derived from text mining, combined with machine learning techniques, were used to generate molecular targets for each of the organ level toxicity end points. A total of 1516 toxicity-related genes were identified and subsequently analyzed for biological pathway coverage, resulting in 206 significant pathways (p-value <0.05), ranging from 3 (e.g., developmental toxicity) to 101 (e.g., skin toxicity) for each toxicity end point. This study presents a systematic and comprehensive analysis of molecular targets and pathways related to various in vivo toxicity end points. These molecular targets and pathways could aid in understanding the biological mechanisms of toxicity and serve as a guide for the design of suitable in vitro assays for more efficient toxicity testing. In addition, these results are complementary to the existing adverse outcome pathway (AOP) framework and can be used to aid in the development of novel AOPs. Our results provide abundant testable hypotheses for further experimental validation.

Predictive Models to Identify Small Molecule Activators and Inhibitors of Opioid Receptors.

Opioid receptors (OPRs) are the main targets for the treatment of pain and related disorders. The opiate compounds that activate these receptors are effective analgesics but their use leads to adverse effects, and they often are highly addictive drugs of abuse. There is an urgent need for alternative chemicals that are analgesics and to reduce/avoid the unwanted effects in order to relieve the public health crisis of opioid addiction. Here, we aim to develop computational models to predict the OPR activity of small molecule compounds based on chemical structures and apply these models to identify novel OPR active compounds. We used four different machine learning algorithms to build models based on quantitative high throughput screening (qHTS) data sets of three OPRs in both agonist and antagonist modes. The best performing models were applied to virtually screen a large collection of compounds. The model predicted active compounds were experimentally validated using the same qHTS assays that generated the training data. Random forest was the best classifier with the highest performance metrics, and the mu OPR (OPRM)-agonist model achieved the best performance measured by AUC-ROC (0.88) and MCC (0.7) values. The model predicted actives resulted in hit rates ranging from 2.3% (delta OPR-agonist) to 15.8% (OPRM-agonist) after experimental confirmation. Compared to the original assay hit rate, all models enriched the hit rate by ≥2-fold. Our approach produced robust OPR prediction models that can be applied to prioritize compounds from large libraries for further experimental validation. The models identified several novel potent compounds as activators/inhibitors of OPRs that were confirmed experimentally. The potent hits were further investigated using molecular docking to find the interactions of the novel ligands in the active site of the corresponding OPR.

Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure.

Traditional toxicity testing reliant on animal models is costly and low throughput, posing a significant challenge with the increasing numbers of chemicals that humans are exposed to in the environment. The purpose of this investigation was to build optimal prediction models for various human in vivo/organ-level toxicity end points (extracted from ChemIDPlus) using chemical structure and Tox21 in vitro quantitative high-throughput screening (qHTS) bioactivity assay data. Several supervised machine learning algorithms were applied to model 14 human toxicity end points pertaining to vascular, kidney, ureter and bladder, and liver organ systems. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The top four models, with AUC-ROC values >0.8, were derived for endocrine (0.90 ± 0.00), musculoskeletal (0.88 ± 0.02), peripheral nerve and sensation (0.85 ± 0.01), and brain and coverings (0.83 ± 0.02) toxicities, whereas the best model AUC-ROC values were >0.7 for the remaining 10 toxicities. Model performance was found to be dependent on the specific data set, model type, and feature selection method used. In addition, chemical structure and assay data showed different levels of contribution to the prediction of different toxicity end points. Although in vitro assay data, when combined with chemical structure, slightly improved the predictive accuracy for most end points (11 out of 14), a noteworthy finding was the near equal success of the structure-only models, which do not require Tox21 qHTS screening data, and the relatively poor performance of assay-only models. Thus, the top-performing structure-only models from this study could be applied for hazard screening of large sets of chemicals for potential human toxicity, whereas the largest assay contributions to models (i.e., cellular targets) could be used, along with the top-contributing structural features, to provide insight into toxicity mechanisms.