Going All In: A Strategic Investment in In Silico Toxicology

Multi-Endpoint Acute Toxicity Assessment of Organic Compounds Using Large-Scale Machine Learning Modeling

In recent years, alternative animal testing methods such as computational and machine learning approaches have become increasingly crucial for toxicity testing. However, the complexity and scarcity of available biomedical data challenge the development of predictive models. Combining nonlinear machine learning together with multicondition descriptors offers a solution for using data from various assays to create a robust model. This work applies multicondition descriptors (MCDs) to develop a QSTR (Quantitative Structure-Toxicity Relationship) model based on a large toxicity data set comprising more than 80,000 compounds and 59 different end points (122,572 data points). The prediction capabilities of developed single-task multi-end point machine learning models as well as a novel data analysis approach with the use of Convolutional Neural Networks (CNN) are discussed. The results show that using MCDs significantly improves the model and using them with CNN-1D yields the best result (R2train = 0.93, R2ext = 0.70). Several structural features showed a high level of contribution to the toxicity, including van der Waals surface area (VSA), number of nitrogen-containing fragments (nN+), presence of S-P fragments, ionization potential, and presence of C-N fragments. The developed models can be very useful tools to predict the toxicity of various compounds under different conditions, enabling quick toxicity assessment of new compounds.

Making the Case for Quantum Mechanics in Predictive Toxicology─Nearly 100 Years Too Late?

The use of quantum mechanics (QM) has long been the norm to study covalent-binding phenomena in chemistry and biochemistry. The pharmaceutical industry leverages QM models explicitly in covalent drug discovery and implicitly to characterize short-range interactions in noncovalent binding. Predictive toxicology has resisted widespread adoption of QM, including in the pharmaceutical industry, despite its obvious relevance to the metabolic processes in the upstream of adverse outcome pathways and advances in both QM methods and computational resources, which support fit-for-purpose applications in reasonable timeframes. Here, we make the case for embracing QM as an indispensable part of a toxicologist's toolkit. We argue that QM provides the necessary orthogonality to alert-based expert systems and traditional QSARs, consistent with calls for animal-free integrated testing strategies for safety assessments of commercial chemicals. We outline existing roadblocks to this transition, including the need to train model developers in QM and the shift toward service-based toxicity models that utilize high-performance computing clusters. Lastly, we describe recent examples of successful implementations of QM in hazard assessments and propose how in silico toxicology can be further advanced by integrating QM with artificial intelligence.

Toward Property-Based Regulation

An expanding web of adverse impacts on people and the environment has been steadily linked to anthropogenic chemicals and their proliferation. Central to this web are the regulatory structures intended to protect human and environmental health through the control of new molecules. Through chronically insufficient and inefficient action, the current chemical-by-chemical regulatory approach, which considers regulation at the level of chemical identity, has enabled many adverse impacts to develop and persist. Recognizing the link between fundamental physicochemical properties and hazards, we describe a new paradigm─property-based regulation. By regulating physicochemical properties, we show how governments can delineate and enforce safe chemical spaces, increasing the scalability of chemical assessments, reducing the time and resources to regulate a substance, and providing transparency for chemical designers. We highlight sparse existing property-based approaches and demonstrate their applicability using bioaccumulation as an example. Finally, we present a path to implementation in the United States, prescribing roles and steps for government, nongovernmental organizations, and industry to accelerate this transition, to the benefit of all.

Quantum-Mechanical Approach to Predicting the Carcinogenic Potency of N-Nitroso Impurities in Pharmaceuticals

N-Nitroso contaminants in medicinal products are of concern due to their high carcinogenic potency; however, not all these compounds are created equal, and some are relatively benign chemicals. Understanding the structure-activity relationships (SARs) that drive hazards in one molecule versus another is key to both protecting human health and alleviating costly and sometimes inaccurate animal testing. Here, we report on an extension of the CADRE (computer-aided discovery and REdesign) platform, which is used broadly by the pharmaceutical and personal care industries to assess environmental and human health endpoints, to predict the carcinogenic potency of N-nitroso compounds. The model distinguishes compounds in three potency categories with 77% accuracy in external testing, which surpasses the reproducibility of rodent cancer bioassays and constraints imposed by limited (high-quality) data. The robustness of predictions for more complex pharmaceuticals is maximized by capturing key SARs using quantum mechanics, that is, by hinging the model on the underlying chemistry versus chemicals in the training set. To this end, the present approach can be leveraged in a quantitative hazard assessment and to offer qualitative guidance using electronic structure comparisons between well-studied analogues and unknown contaminants.

Computer-Aided Discovery and Redesign for Respiratory Sensitization: A Tiered Mechanistic Model to Deliver Robust Performance Across a Diverse Chemical Space

Asthma is among the most common occupational diseases with considerable public health and economic costs. Chemicals that induce hypersensitivity in the airways can cause respiratory distress and comorbidities with respiratory infections such as COVID. Robust predictive models for this end point are still elusive due to the lack of an experimental benchmark and the over-reliance of existing in silico tools on structural alerts and structural (vs chemical) similarities. The Computer-Aided Discovery and REdesign (CADRE) platform is a proven strategy for providing robust computational predictions for hazard end points using a tiered hybrid system of expert rules, molecular simulations, and quantum mechanics calculations. The recently developed CADRE model for respiratory sensitization is based on a highly curated data set of structurally diverse chemicals with high-fidelity biological data. The model evaluates absorption kinetics in lung mucosa using Monte Carlo simulations, assigns reactive centers in a molecule and possible biotransformations via expert rules, and determines subsequent reactivity with cell proteins via quantum-mechanics calculations using a multi-tiered regression. The model affords an accuracy above 0.90, with a series of external validations based on literature data in the range of 0.88-0.95. The model is applicable to all low-molecular-weight organics and can inform not only chemical substitution but also chemical redesign to advance development of safer alternatives.

An Evaluation of the Occupational Health Hazards of Peptide Couplers

Peptide couplers (also known as amide bond-forming reagents or coupling reagents) are broadly used in organic chemical syntheses, especially in the pharmaceutical industry. Yet, occupational health hazards associated with this chemical class are largely unexplored, which is disconcerting given the intrinsic reactivity of these compounds. Several case studies involving occupational exposures reported adverse respiratory and dermal health effects, providing initial evidence of chemical sensitization. To address the paucity of toxicological data, a pharmaceutical cross-industry task force was formed to evaluate and assess the potential of these compounds to cause eye and dermal irritation as well as corrosivity and dermal sensitization. The goal of our work was to inform health and safety professionals as well as pharmaceutical and organic chemists of the occupational health hazards associated with this chemical class. To that end, 25 of the most commonly used peptide couplers and five hydrolysis products were selected for in vivo, in vitro, and in silico testing. Our findings confirmed that dermal sensitization is a concern for this chemical class with 21/25 peptide couplers testing positive for dermal sensitization and 15 of these being strong/extreme sensitizers. We also found that dermal corrosion and irritation (8/25) as well as eye irritation (9/25) were health hazards associated with peptide couplers and their hydrolysis products (4/5 were dermal irritants or corrosive and 4/5 were eye irritants). Resulting outcomes were synthesized to inform decision making in peptide coupler selection and enable data-driven hazard communication to workers. The latter includes harmonized hazard classifications, appropriate handling recommendations, and accurate safety data sheets, which support the industrial hygiene hierarchy of control strategies and risk assessment. Our study demonstrates the merits of an integrated, in vivo -in silico analysis, applied here to the skin sensitization endpoint using the Computer-Aided Discovery and REdesign (CADRE) and Derek Nexus programs. We show that experimental data can improve predictive models by filling existing data gaps while, concurrently, providing computational insights into key initiating events and elucidating the chemical structural features contributing to adverse health effects. This interactive, interdisciplinary approach is consistent with Green Chemistry principles that seek to improve the selection and design of less hazardous reagents in industrial processes and applications.

Structure-to-process design framework for developing safer pesticides

Rational design of pesticides with tunable degradation properties and minimal ecotoxicity is among the grand challenges of green chemistry. While computational approaches have gained traction in predictive toxicology, current methods lack the necessary multifaceted approach and design-vectoring tools needed for system-based chemical development. Here, we report a tiered computational framework, which integrates kinetics and thermodynamics of indirect photodegradation with predictions of ecotoxicity and performance, based on cutoff values in mechanistically derived physicochemical properties and electronic parameters. Extensively validated against experimental data and applied to 700 pesticides on the U.S. Environmental Protection Agency's registry, our simple yet powerful approach can be used to screen existing molecules to identify application-ready candidates with desirable characteristics. By linking structural attributes to process-based outcomes and by quantifying trade-offs in safety, depletion, and performance, our method offers a user-friendly roadmap to rational design of novel pesticides.

Revealing Adverse Outcome Pathways from Public High-Throughput Screening Data to Evaluate New Toxicants by a Knowledge-Based Deep Neural Network Approach

Traditional experimental testing to identify endocrine disruptors that enhance estrogenic signaling relies on expensive and labor-intensive experiments. We sought to design a knowledge-based deep neural network (k-DNN) approach to reveal and organize public high-throughput screening data for compounds with nuclear estrogen receptor α and β (ERα and ERβ) binding potentials. The target activity was rodent uterotrophic bioactivity driven by ERα/ERβ activations. After training, the resultant network successfully inferred critical relationships among ERα/ERβ target bioassays, shown as weights of 6521 edges between 1071 neurons. The resultant network uses an adverse outcome pathway (AOP) framework to mimic the signaling pathway initiated by ERα and identify compounds that mimic endogenous estrogens (i.e., estrogen mimetics). The k-DNN can predict estrogen mimetics by activating neurons representing several events in the ERα/ERβ signaling pathway. Therefore, this virtual pathway model, starting from a compound's chemistry initiating ERα activation and ending with rodent uterotrophic bioactivity, can efficiently and accurately prioritize new estrogen mimetics (AUC = 0.864-0.927). This k-DNN method is a potential universal computational toxicology strategy to utilize public high-throughput screening data to characterize hazards and prioritize potentially toxic compounds.

In silico Prediction of Skin Sensitization: Quo vadis?

Skin direct contact with chemical or physical substances is predisposed to allergic contact dermatitis (ACD), producing various allergic reactions, namely rash, blister, or itchy, in the contacted skin area. ACD can be triggered by various extremely complicated adverse outcome pathways (AOPs) remains to be causal for biosafety warrant. As such, commercial products such as ointments or cosmetics can fulfill the topically safe requirements in animal and non-animal models including allergy. Europe, nevertheless, has banned animal tests for the safety evaluations of cosmetic ingredients since 2013, followed by other countries. A variety of non-animal in vitro tests addressing different key events of the AOP, the direct peptide reactivity assay (DPRA), KeratinoSens™, LuSens and human cell line activation test h-CLAT and U-SENS™ have been developed and were adopted in OECD test guideline to identify the skin sensitizers. Other methods, such as the SENS-IS are not yet fully validated and regulatorily accepted. A broad spectrum of in silico models, alternatively, to predict skin sensitization have emerged based on various animal and non-animal data using assorted modeling schemes. In this article, we extensively summarize a number of skin sensitization predictive models that can be used in the biopharmaceutics and cosmeceuticals industries as well as their future perspectives, and the underlined challenges are also discussed.

Quantifying Uncertainty in Ecotoxicological Risk Assessment: MUST, a Modular Uncertainty Scoring Tool

Whether conducting a risk, hazard, or alternatives assessment, one invariably struggles with the task of reconciling multiple available values of toxicological thresholds into a single outcome. When combining multiple pieces of evidence from many different sources, it is important to consider the role of data uncertainty. Uncertainty is inherent to all scientific data. However, in toxicological assessments, controversies and uncertainties are typically understated; they lack methodological transparency; or they poorly integrate qualitative and quantitative sources of information. Similarly, in model development, data curation is rarely performed with sufficient rigor, particularly when applying big data statistics. To overcome the hurdles of a decision process that must reconcile divergent data, we developed an uncertainty scoring tool that can be trained to reproduce specific decision-making paradigms and ensure consistency in the practitioner's judgment across complex scenarios. While designed to aid with ecotoxicological assessments and predictive model development, the tool's applicability extends to any decision-making process that calls for synthesis of incongruent data. Here, we highlight the development process, as well as demonstrate the method's utility in several prototypical ecotoxicological case studies.

Toxicology Advances for 21st Century Chemical Pollution

Pollution represents a leading threat to global health and ecosystems. Systems-based initiatives, including Planetary Health, EcoHealth, and One Health, require theoretical and translational platforms to address chemical pollution. Comparative and predictive toxicology are providing integrative approaches for identifying problematic contaminants, designing less hazardous alternatives, and reducing the impacts of chemical pollution.