Evaluation of combinations of in vitro sensitization test descriptors for the artificial neural network-based risk assessment model of skin sensitization

In Silico Prediction of Skin Sensitization for Compounds via Flexible Evidence Combination Based on Machine Learning and Dempster-Shafer Theory

Skin sensitization is increasingly becoming a significant concern in the development of drugs and cosmetics due to consumer safety and occupational health problems. In silico methods have emerged as alternatives to traditional in vivo animal testing due to ethical and economic considerations. In this study, machine learning methods were used to build quantitative structure-activity relationship (QSAR) models on five skin sensitization data sets (GPMT, LLNA, DPRA, KeratinoSens, and h-CLAT), achieving effective predictive accuracies (correct classification rates of 0.688-0.764 on test sets). To address the complex mechanisms of human skin sensitization, the Dempster-Shafer theory was applied to merge multiple QSAR models, resulting in an evidence-based integrated decision model. Various evidence combinations and combination rules were explored, with the self-defined Q3 rule showing superior balance. The combination of evidence such as GPMT and KeratinoSens and h-CLAT achieved a correct classification rate (CCR) of 0.880 and coverage of 0.893 while maintaining the competitiveness of other combinations. Additionally, the Shapley additive explanations (SHAP) method was used to interpret important features and substructures related to skin sensitization. A comparative analysis of an external human test set demonstrated the superior performance of the proposed method. Finally, to enhance accessibility, the workflow was implemented into a user-friendly software named HSkinSensDS.

Development of a hierarchical support vector regression-based in silico model for the prediction of the cysteine depletion in DPRA

Topical and transdermal treatments have been dramatically growing recently and it is crucial to consider skin sensitization during the drug discovery and development process for these administration routes. Various tests, including animal and non-animal approaches, have been devised to assess the potential for skin sensitization. Furthermore, numerous in silico models have been created, providing swift and cost-effective alternatives to traditional methods such as in vivo, in vitro, and in chemico methods for categorizing compounds. In this study, a quantitative structure-activity relationship (QSAR) model was developed using the innovative hierarchical support vector regression (HSVR) scheme. The aim was to quantitatively predict the potential for skin sensitization by analyzing the percent of cysteine depletion in Direct Peptide Reactivity Assay (DPRA). The results demonstrated accurate, consistent, and robust predictions in the training set, test set, and outlier set. Consequently, this model can be employed to estimate skin sensitization potential of novel or virtual compounds.

Application of Defined Approaches to Assess Skin Sensitization Potency of Isothiazolinone Compounds

INTRODUCTION

Isothiazolinones (ITs) are widely used as antimicrobial preservatives in cosmetics and as additives for preservation of consumer and industrial products to control bacteria, fungi, and algae. Although they are effective biocides, they have the potential to produce skin irritation and sensitization, which poses a human health hazard. In this project, we evaluated nonanimal defined approaches (DAs) for skin sensitization that can provide point-of-departure estimates for use in quantitative risk assessment for ITs.

MATERIALS AND METHODS

The skin sensitization potential of six ITs was evaluated using three internationally harmonized nonanimal test methods: the direct peptide reactivity assay, KeratinoSens™, and the human cell line activation test. Results from these test methods were then applied to two versions of the Shiseido Artificial Neural Network DA.

RESULTS

Sensitization hazard or potency predictions were compared with those of the in vivo murine local lymph node assay (LLNA). The nonanimal methods produced skin sensitization hazard and potency classifications concordant with those of the LLNA. EC3 values (the estimated concentration needed to produce a stimulation index of three, the threshold positive response) generated by the DAs had less variability than LLNA EC3 values, and confidence limits from the DAs overlapped those of the LLNA EC3 for most substances.

CONCLUSION

The application of in silico models to in chemico and in vitro skin sensitization data is a promising data integration procedure for DAs to support hazard and potency classification and quantitative risk assessment.

Skin Sensitization Testing: The Ascendancy of Non-Animal Methods

A century ago, toxicology was an empirical science identifying substance hazards in surrogate mammalian models. Over several decades, these models improved, evolved to reduce animal usage, and recently have begun the process of dispensing with animals entirely. However, despite good hazard identification, the translation of hazards into adequately assessed risks to human health often has presented challenges. Unfortunately, many skin sensitizers known to produce contact allergy in humans, despite being readily identified as such in the predictive assays, continue to cause this adverse health effect. Increasing the rigour of hazard identification is inappropriate. Regulatory action has only proven effective via complete bans of individual substances. Since the problem applies to a broad range of substances and industry categories, and since generic banning of skin sensitizers would be an economic catastrophe, the solution is surprisingly simple—they should be subject to rigorous safety assessment, with the risks thereby managed accordingly. The ascendancy of non-animal methods in skin sensitization is giving unparalleled opportunities in which toxicologists, risk assessors, and regulators can work in concert to achieve a better outcome for the protection of human health than has been delivered by the in vivo methods and associated regulations that they are replacing.

Weight of Evidence Approach for Skin Sensitization Potency Categorization of Fragrance Ingredients

Reliable human potency data are necessary for conducting quantitative risk assessments, as well as development and validation of new nonanimal methods for skin sensitization assessments. Previously, human skin sensitization potency of fragrance materials was derived primarily from human data or the local lymph node assay.

Improved performance of the SH test as an in vitro skin sensitization test with a new predictive model and decision tree

Demands for the elimination and replacement of animal experiments for cosmetic safety assessment have increased in recent years. Evaluation of skin sensitization, however, is a critical issue in cosmetic safety assessment. The SH test is an in vitro skin sensitization test method that evaluates protein binding of chemical substances, which is an important event in skin sensitization. We previously verified the technical transferability and between-laboratory reproducibility of the SH test, a domestic test method for which no scientific research has been conducted, and improved the protocol, but also noted some unresolved issues. Therefore, in the present study, we successfully improved the operational efficiency and clarity of the final judgment of the SH test by (i) developing a new decision-making system that can make a final judgment without statistical processing, (ii) changing the statistical method, and (iii) evaluating and determining the maximum number of repetitions necessary for optimal efficiency. The improved SH test was verified by comparing it with existing test methods already adopted by the Organization for Economic Cooperation and Development. The results of this study demonstrated excellent performance of the improved SH test, with high reproducibility, reliable predictability, and good operational efficiency. The predictive performance of the improved method does not differ significantly from that of the conventional method, although it is clearer and more efficient. Therefore, the results of the present improved method are consistent with those obtained using the conventional method, with higher efficiency.

Amino Reactivity of Glutardialdehyde and Monoaldehydes─Chemoassay Profile vs Skin Sensitization Potency

Chemoassay profiling of organic electrophiles through the direct peptide reactivity assay has become an OECD-accepted nonanimal component in the REACH evaluation of potential skin sensitizers. For aldehydes forming imines (Schiff bases), however, existing chemoassays yielded inconclusive results, indicating issues with their NH₂ sensitivity and the reversibility of the reaction. In the present study, a new kinetic chemoassay employing the N terminus of glycine-para-nitroanilide, Gly-pNA, as a model nucleophile for protein NH₂ groups is introduced and applied to nine aliphatic monoaldehydes and glutardialdehyde (1,5-pentanedial) that have log K_ow (octanol/water partition coefficient) values from 0.63 to 3.99. The Gly-pNA second-order rate constants k₁ range from 8.56 to 150 L·mol^-1·min^-1 for the monoaldehydes. Interestingly, glutardialdehyde with a k₁ of 17 731 L·mol^-1·min^-1 is 170-fold more reactive than its monoaldehyde counterpart pentanal. This can be rationalized by hydration or tautomerization of the dialdehyde to monoaldehydic forms, now facilitating Schiff base formation through an intramolecular H bond. Comparison with murine local lymph node assay data from the literature reveals that adduct stability in terms of reaction thermodynamics (K = k₁/k_-1^pseudo) rather than formation kinetics (k₁) governs the skin sensitization potency of Schiff-base-forming aldehydes. The discussion includes analytically determined adduct patterns, and the impact of α- and β-carbon substitution as well as hydrophobicity on aldehyde reactivity.

Enhancing between-facility reproducibility of the SH test as an in vitro skin sensitization test by the improved test method

There has been an increased demand to eliminate animal experiments and to replace the experiments with alternative tests for assessing the safety of cosmetics. The SH test is an in vitro skin sensitization test that evaluates the protein binding abilities of a test substance. Skin sensitization must be evaluated by multiple test methods. The SH test uses the same cell line and measuring instruments as the human Cell-Line Activation Test (h-CLAT), which is one of the test methods used to evaluate different key events and is listed in the OECD test guidelines. There are cost advantages to usher the SH test into facilities that are already running the h-CLAT. The SH test is conducted only at a facility that has developed the SH test because studies on the between-facility reproducibility and validity have not been performed. Therefore, to verify the transferability of the SH test and the between-facilities reproducibility, we evaluated the reproducibility of the SH test results at three facilities, including the development facility. After an initial round of testing, the protocol was refined as follows to improve reproducibility among the three facilities: i) determine the optimum pH range, ii) change the maximum applicable concentration of water-soluble substances, and iii) define the appropriate dispersion conditions for evaluating hydrophobic substances. These refinements markedly enhanced the between-facility reproducibility (from 76.0% to 96.0%) for the 25 substances evaluated in this study. This study confirmed that the SH test is an effective skin sensitization test method with high technical transferability and between-facility reproducibility.

Development of quantitative model of a local lymph node assay for evaluating skin sensitization potency applying machine learning CatBoost

The estimated concentrations for a stimulation index of 3 (EC3) in murine local lymph node assay (LLNA) is an important quantitative value for determining the strength of skin sensitization to chemicals, including cosmetic ingredients. However, animal testing bans on cosmetics in Europe necessitate the development of alternative testing methods to LLNA. A machine learning-based prediction method can predict complex toxicity risks from multiple variables. Therefore, we developed an LLNA EC3 regression model using CatBoost, a new gradient boosting decision tree, based on the reliable Cosmetics Europe database which included data for 119 substances. We found that a model using in chemico/in vitro tests, physical properties, and chemical information associated with key events of skin sensitization adverse outcome pathway as variables showed the best performance with a coefficient of determination (R²) of 0.75. In addition, this model can indicate the variable importance as the interpretation of the model, and the most important variable was associated with the human cell line activation test that evaluate dendritic cell activation. The good performance and interpretability of our LLNA EC3 predictable regression model suggests that it could serve as a useful approach for quantitative assessment of skin sensitization.

Safety Testing of Cosmetic Products: Overview of Established Methods and New Approach Methodologies (NAMs)

Cosmetic products need to have a proven efficacy combined with a comprehensive toxicological assessment. Before the current Cosmetic regulation N°1223/2009, the 7th Amendment to the European Cosmetics Directive has banned animal testing for cosmetic products and for cosmetic ingredients in 2004 and 2009, respectively. An increasing number of alternatives to animal testing has been developed and validated for safety and efficacy testing of cosmetic products and cosmetic ingredients. For example, 2D cell culture models derived from human skin can be used to evaluate anti-inflammatory properties, or to predict skin sensitization potential; 3D human skin equivalent models are used to evaluate skin irritation potential; and excised human skin is used as the gold standard for the evaluation of dermal absorption. The aim of this manuscript is to give an overview of the main in vitro and ex vivo alternative models used in the safety testing of cosmetic products with a focus on regulatory requirements, genotoxicity potential, skin sensitization potential, skin and eye irritation, endocrine properties, and dermal absorption. Advantages and limitations of each model in safety testing of cosmetic products are discussed and novel technologies capable of addressing these limitations are presented.

Current opinion on risk assessment of cosmetics

Risk assessment of cosmetic ingredients is a useful scientific method to characterize potential adverse effects resulting from using cosmetics. The process of risk assessment consists of four steps: hazard identification, dose-response assessment, exposure assessment, and risk characterization. Hazard identification of chemicals refers to the initial stage of risk assessment and generally utilizes animal studies to evaluate toxicity. Since 2013, however, toxicity studies of cosmetic ingredients using animals have not been permitted in the EU and alternative toxicity test methods for animal studies have momentum to be developed for cosmetic ingredients. In this paper, we briefly review the alternative test methods that are available for cosmetic ingredients including read-across, in silico, in chemico, and invitro methods. In addition, new technologies such as omics and artificial intelligence (AI) have been discussed to expand or improve the knowledge and hazard identification of cosmetic ingredients. Aggregate exposure of cosmetic ingredients is another safety issue and methods for its improvement were reviewed. There have been concerns over the safety of nano-cosmetics for a long time, but the risk of nano-cosmetics remains unclear. Therefore, current issues of cosmetic risk assessment are discussed and expert opinion will be provided for the safety of cosmetics.

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.

Mechanism-based integrated assay systems for the prediction of drug-induced liver injury

Drug-induced liver injury (DILI) can cause hepatic failure and result in drug withdrawal from the market. It has host-related and compound-dependent mechanisms. Preclinical prediction of DILI risk is very challenging and safety assessments based on animals inadequately forecast human DILI risk. In contrast, human-derived in vitro cell culture-based models could improve DILI risk prediction accuracy. Here, we developed and validated an innovative method to assess DILI risk associated with various compounds. Fifty-four marketed and withdrawn drugs classified as DILI risks of "most concern", "less concern", and "no concern" were tested using a combination of four assays addressing mitochondrial injury, intrahepatic lipid accumulation, inhibition of bile canalicular network formation, and bile acid accumulation. Using the inhibitory potencies of the drugs evaluated in these in vitro tests, an algorithm with the highest available DILI risk prediction power was built by artificial neural network (ANN) analysis. It had an overall forecasting accuracy of 73%. We excluded the intrahepatic lipid accumulation assay to avoid overfitting. The accuracy of the algorithm in terms of predicting DILI risks was 62% when it was constructed by ANN but only 49% when it was built by the point-added scoring method. The final algorithm based on three assays made no DILI risk prediction errors such as "most concern " instead of "no concern" and vice-versa. Our mechanistic approach may accurately predict DILI risks associated with numerous candidate drugs.

Non-animal methods to predict skin sensitization (II): an assessment of defined approaches *

Skin sensitization is a toxicity endpoint of widespread concern, for which the mechanistic understanding and concurrent necessity for non-animal testing approaches have evolved to a critical juncture, with many available options for predicting sensitization without using animals. Cosmetics Europe and the National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods collaborated to analyze the performance of multiple non-animal data integration approaches for the skin sensitization safety assessment of cosmetics ingredients. The Cosmetics Europe Skin Tolerance Task Force (STTF) collected and generated data on 128 substances in multiple in vitro and in chemico skin sensitization assays selected based on a systematic assessment by the STTF. These assays, together with certain in silico predictions, are key components of various non-animal testing strategies that have been submitted to the Organization for Economic Cooperation and Development as case studies for skin sensitization. Curated murine local lymph node assay (LLNA) and human skin sensitization data were used to evaluate the performance of six defined approaches, comprising eight non-animal testing strategies, for both hazard and potency characterization. Defined approaches examined included consensus methods, artificial neural networks, support vector machine models, Bayesian networks, and decision trees, most of which were reproduced using open source software tools. Multiple non-animal testing strategies incorporating in vitro, in chemico, and in silico inputs demonstrated equivalent or superior performance to the LLNA when compared to both animal and human data for skin sensitization.

Application of IATA - A case study in evaluating the global and local performance of a Bayesian network model for skin sensitization

The information characterizing key events in an Adverse Outcome Pathway (AOP) can be generated from in silico, in chemico, in vitro and in vivo approaches. Integration of this information and interpretation for decision making are known as integrated approaches to testing and assessment (IATA). One such IATA was published by Jaworska et al., which describes a Bayesian network model known as ITS-2. The current work evaluated the performance of ITS-2 using a stratified cross-validation approach. We also characterized the impact of replacing the most significant component of the network, output from the expert system TIMES-SS, with structural alert information from the OECD Toolbox and Toxtree. Lack of structural alerts or TIMES-SS predictions yielded a sensitization potential prediction of 79%. If the TIMES-SS prediction was replaced by a structural alert indicator, the network predictivity increased up to 87%. The original network's predictivity was 89%. The local applicability domain of the original ITS-2 network was also evaluated using reaction mechanistic domains to understand what types of chemicals ITS-2 was able to make the best predictions for. We found that the original network was successful at predicting which chemicals would be sensitizers, but not at predicting their potency.

How Adverse Outcome Pathways Can Aid the Development and Use of Computational Prediction Models for Regulatory Toxicology

Efforts are underway to transform regulatory toxicology and chemical safety assessment from a largely empirical science based on direct observation of apical toxicity outcomes in whole organism toxicity tests to a predictive one in which outcomes and risk are inferred from accumulated mechanistic understanding. The adverse outcome pathway (AOP) framework provides a systematic approach for organizing knowledge that may support such inference. Likewise, computational models of biological systems at various scales provide another means and platform to integrate current biological understanding to facilitate inference and extrapolation. We argue that the systematic organization of knowledge into AOP frameworks can inform and help direct the design and development of computational prediction models that can further enhance the utility of mechanistic and in silico data for chemical safety assessment. This concept was explored as part of a workshop on AOP-Informed Predictive Modeling Approaches for Regulatory Toxicology held September 24-25, 2015. Examples of AOP-informed model development and its application to the assessment of chemicals for skin sensitization and multiple modes of endocrine disruption are provided. The role of problem formulation, not only as a critical phase of risk assessment, but also as guide for both AOP and complementary model development is described. Finally, a proposal for actively engaging the modeling community in AOP-informed computational model development is made. The contents serve as a vision for how AOPs can be leveraged to facilitate development of computational prediction models needed to support the next generation of chemical safety assessment.

The adverse outcome pathway for skin sensitisation: Moving closer to replacing animal testing

This article outlines the work of the Organisation for Economic Co-operation and Development (OECD) that led to being jointly awarded the 2015 Lush Black Box Prize. The award-winning work centred on the development of 'The Adverse Outcome Pathway for Skin Sensitisation Initiated by Covalent Binding to Proteins'. This Adverse Outcome Pathway (AOP) has provided the mechanistic basis for the integration of skin sensitisation-related information. Recent developments in integrated approaches to testing and assessment, based on the AOP, are summarised. The impact of the AOP on regulatory policy and on the Three Rs are discussed. An overview of the next generation of the skin sensitisation AOP module in the OECD QSAR Toolbox, based on more-recent work at the Laboratory of Mathematical Chemistry, is also presented.

Prediction of skin sensitization potency using machine learning approaches

The replacement of animal use in testing for regulatory classification of skin sensitizers is a priority for US federal agencies that use data from such testing. Machine learning models that classify substances as sensitizers or non-sensitizers without using animal data have been developed and evaluated. Because some regulatory agencies require that sensitizers be further classified into potency categories, we developed statistical models to predict skin sensitization potency for murine local lymph node assay (LLNA) and human outcomes. Input variables for our models included six physicochemical properties and data from three non-animal test methods: direct peptide reactivity assay; human cell line activation test; and KeratinoSens™ assay. Models were built to predict three potency categories using four machine learning approaches and were validated using external test sets and leave-one-out cross-validation. A one-tiered strategy modeled all three categories of response together while a two-tiered strategy modeled sensitizer/non-sensitizer responses and then classified the sensitizers as strong or weak sensitizers. The two-tiered model using the support vector machine with all assay and physicochemical data inputs provided the best performance, yielding accuracy of 88% for prediction of LLNA outcomes (120 substances) and 81% for prediction of human test outcomes (87 substances). The best one-tiered model predicted LLNA outcomes with 78% accuracy and human outcomes with 75% accuracy. By comparison, the LLNA predicts human potency categories with 69% accuracy (60 of 87 substances correctly categorized). These results suggest that computational models using non-animal methods may provide valuable information for assessing skin sensitization potency. Copyright © 2017 John Wiley & Sons, Ltd.

Integrated decision strategies for skin sensitization hazard

One of the top priorities of the Interagency Coordinating Committee for the Validation of Alternative Methods (ICCVAM) is the identification and evaluation of non-animal alternatives for skin sensitization testing. Although skin sensitization is a complex process, the key biological events of the process have been well characterized in an adverse outcome pathway (AOP) proposed by the Organisation for Economic Co-operation and Development (OECD). Accordingly, ICCVAM is working to develop integrated decision strategies based on the AOP using in vitro, in chemico and in silico information. Data were compiled for 120 substances tested in the murine local lymph node assay (LLNA), direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT) and KeratinoSens assay. Data for six physicochemical properties, which may affect skin penetration, were also collected, and skin sensitization read-across predictions were performed using OECD QSAR Toolbox. All data were combined into a variety of potential integrated decision strategies to predict LLNA outcomes using a training set of 94 substances and an external test set of 26 substances. Fifty-four models were built using multiple combinations of machine learning approaches and predictor variables. The seven models with the highest accuracy (89-96% for the test set and 96-99% for the training set) for predicting LLNA outcomes used a support vector machine (SVM) approach with different combinations of predictor variables. The performance statistics of the SVM models were higher than any of the non-animal tests alone and higher than simple test battery approaches using these methods. These data suggest that computational approaches are promising tools to effectively integrate data sources to identify potential skin sensitizers without animal testing. Published 2016. This article has been contributed to by US Government employees and their work is in the public domain in the USA.

Multivariate models for prediction of human skin sensitization hazard

One of the Interagency Coordinating Committee on the Validation of Alternative Method's (ICCVAM) top priorities is the development and evaluation of non-animal approaches to identify potential skin sensitizers. The complexity of biological events necessary to produce skin sensitization suggests that no single alternative method will replace the currently accepted animal tests. ICCVAM is evaluating an integrated approach to testing and assessment based on the adverse outcome pathway for skin sensitization that uses machine learning approaches to predict human skin sensitization hazard. We combined data from three in chemico or in vitro assays - the direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT) and KeratinoSens™ assay - six physicochemical properties and an in silico read-across prediction of skin sensitization hazard into 12 variable groups. The variable groups were evaluated using two machine learning approaches, logistic regression and support vector machine, to predict human skin sensitization hazard. Models were trained on 72 substances and tested on an external set of 24 substances. The six models (three logistic regression and three support vector machine) with the highest accuracy (92%) used: (1) DPRA, h-CLAT and read-across; (2) DPRA, h-CLAT, read-across and KeratinoSens; or (3) DPRA, h-CLAT, read-across, KeratinoSens and log P. The models performed better at predicting human skin sensitization hazard than the murine local lymph node assay (accuracy 88%), any of the alternative methods alone (accuracy 63-79%) or test batteries combining data from the individual methods (accuracy 75%). These results suggest that computational methods are promising tools to identify effectively the potential human skin sensitizers without animal testing. Published 2016. This article has been contributed to by US Government employees and their work is in the public domain in the USA.

Chemical applicability domain of the Local Lymph Node Assay (LLNA) for skin sensitisation potency. Part 2. The biological variability of the murine Local Lymph Node Assay (LLNA) for skin sensitisation

The Local Lymph Node Assay (LLNA) is the most common in vivo regulatory toxicology test for skin sensitisation, quantifying potency as the EC3, the concentration of chemical giving a threefold increase in thymidine uptake in the local lymph node. Existing LLNA data can, along with clinical data, provide useful comparator information on the potency of sensitisers. Understanding of the biological variability of data from LLNA studies is important for those developing non-animal based risk assessment approaches for skin allergy. Here an existing set of 94 EC3 values for 12 chemicals, all tested at least three times in the same vehicle have been analysed by calculating standard deviations (SD) for logEC3 values. The SDs range from 0.08 to 0.22. The overall SD for the 94 logEC3 values is 0.147. Thus the 95% confidence limits (2xSD) for LLNA EC3 values are within a factor of 2, comparable to those for physico-chemical measurements such as partition coefficients and solubility. The residual SDs of Quantitative Mechanistic Models (QMMs) based on physical organic chemistry parameters are similar to the overall SD of the LLNA, indicating that QMMs of this type are unlikely to be bettered for predictive accuracy.

Analysis of the Local Lymph Node Assay (LLNA) variability for assessing the prediction of skin sensitisation potential and potency of chemicals with non-animal approaches

The knowledge of the biological mechanisms leading to the induction of skin sensitisation has favoured in recent years the development of alternative non-animal methods. During the formal validation process, results from the Local Lymph Node Assay (LLNA) are generally used as reference data to assess the predictive capacity of the non-animal tests. This study reports an analysis of the variability of the LLNA for a set of chemicals for which multiple studies are available and considers three hazard classification schemes: POS/NEG, GHS/CLP and ECETOC. As the type of vehicle used in a LLNA study is known to influence to some extent the results, two analyses were performed: considering the solvent used to test the chemicals and without considering the solvent. The results show that the number of discordant classifications increases when a chemical is tested in more than one solvent. Moreover, it can be concluded that study results leading to classification in the strongest classes (1A and EXT) seem to be more reliable than those in the weakest classes. This study highlights the importance of considering the variability of the reference data when evaluating non-animal tests.

Predicting skin sensitisation using a decision tree integrated testing strategy with an in silico model and in chemico/in vitro assays

There is a pressing need for non-animal methods to predict skin sensitisation potential and a number of in chemico and in vitro assays have been designed with this in mind. However, some compounds can fall outside the applicability domain of these in chemico/in vitro assays and may not be predicted accurately. Rule-based in silico models such as Derek Nexus are expert-derived from animal and/or human data and the mechanism-based alert domain can take a number of factors into account (e.g. abiotic/biotic activation). Therefore, Derek Nexus may be able to predict for compounds outside the applicability domain of in chemico/in vitro assays. To this end, an integrated testing strategy (ITS) decision tree using Derek Nexus and a maximum of two assays (from DPRA, KeratinoSens, LuSens, h-CLAT and U-SENS) was developed. Generally, the decision tree improved upon other ITS evaluated in this study with positive and negative predictivity calculated as 86% and 81%, respectively. Our results demonstrate that an ITS using an in silico model such as Derek Nexus with a maximum of two in chemico/in vitro assays can predict the sensitising potential of a number of chemicals, including those outside the applicability domain of existing non-animal assays.