Predictive Tests for Irritants and Allergens and Their Use in Quantitative Risk Assessment

Validation of Quantitative Structure-Activity Relationship (QSAR) and Quantitative Structure-Property Relationship (QSPR) approaches as alternatives to skin sensitization risk assessment

The aim of this study was conducted to validate the physicochemical properties of a total of 362 chemicals [305 skin sensitizers (212 in the previous study + 93 additional new chemicals), 57 non-skin sensitizers (38 in the previous study + 19 additional new chemicals)] for skin sensitization risk assessment using quantitative structure-activity relationship (QSAR)/quantitative structure-property relationship (QSPR) approaches. The average melting point (MP), surface tension (ST), and density (DS) of the 305 skin sensitizers and 57 non-sensitizers were used to determine the cutoff values distinguishing positive and negative sensitization, and correlation coefficients were employed to derive effective 3-fold concentration (EC3 (%)) values. QSAR models were also utilized to assess skin sensitization. The sensitivity, specificity, and accuracy were 80, 15, and 70%, respectively, for the Toxtree QSAR model; 88, 46, and 81%, respectively, for Vega; and 56, 61, and 56%, respectively, for Danish EPA QSAR. Surprisingly, the sensitivity, specificity, and accuracy were 60, 80, and 64%, respectively, when MP, ST, and DS (MP+ST+DS) were used in this study. Further, MP+ST+DS exhibited a sensitivity of 77%, specificity 57%, and accuracy 73% when the derived EC3 values were classified into local lymph node assay (LLNA) skin sensitizer and non-sensitizer categories. Thus, MP, ST, and DS may prove useful in predicting EC3 values as not only an alternative approach to animal testing but also for skin sensitization risk assessment.

Alternative skin sensitization prediction and risk assessment using proinflammatory biomarkers, interleukin-1 beta (IL-1β) and inducible nitric oxide synthase (iNOS)

As an alternative to animal tests for skin sensitization potency and risk assessment, cell viability and biomarkers related to skin sensitization were analyzed in THP-1 human monocytic leukemia cells. Cell viabilities of 90% (CV90) and 75% (CV75) were determined for 24 selected test chemicals. Further biomarkers related to skin sensitization were also determined under equivalent comparative conditions. In cell viability analyses, potent skin sensitizers exhibited high cytotoxicity, but non-sensitizers did not display this tendency. In biomarker analyses, interleukin-I beta (IL-1β), inducible nitric oxide synthase (iNOS), IL-1β+iNOS, and THP-1 IL-1β+Raw 264.7 IL-1β were found to be suitable for prediction of skin sensitization potency following classification as either skin sensitizers or non-sensitizers (accuracies of 91.7%, 87.5%, 83.3%, and 82.6%, respectively). A significant positive correlation was found between biomarkers and skin sensitization potency, with a correlation coefficient (R) of 0.7 or more (correlation coefficients of 0.77, 0.72, 0.7, and 0.84, respectively). Finally, the skin sensitization potency effective threefold concentration (EC) 3% was predicted using a biomarker equation, with resulting prediction rates (match rate with actual data) of 58.3%, 54.2%, 62.5%, and 60.9%, respectively. The prediction accuracy for the EC3 value obtained from animal data was calculated as 83.3%, 79.2%, 79.2%, and 73.9%, respectively. Thus, these biomarkers, IL-1β and iNOS, may be alternatively used to predict skin sensitization potency and risk assessment.

IL-1α and IL-1β as alternative biomarkers for risk assessment and the prediction of skin sensitization potency

Potential biomarkers of skin sensitization in RAW264.7 mouse macrophages were investigated as alternatives to animal experiments and risk assessment. The concentrations that resulted in a cell viability of 90% (CV90) and 75% (CV75) were calculated by using a water-soluble tetrazolium salt (WST)-1 assay and used to analyze the skin sensitization potency of 23 experimental materials under equivalent treatment conditions. In addition, the expression of interleukin (IL)-1α, IL-1β, IL-31, tumor necrosis factor (TNF)-α, inducible nitric oxide synthase (iNOS), prostaglandin E2 (PGE2), and cyclooxygenase-2 (COX-2) was analyzed utilizing Western blotting. In the cell viability analysis, skin sensitizers were generally more cytotoxic and exhibited increased skin sensitization potency. However, nonsensitizers did not show any marked cytotoxic tendency. Biomarker analysis demonstrated that IL-1α, IL-1β, and the combination of IL-1α and IL-1β (IL-1α + IL-1β) predicted reliably skin sensitization potential (1) sensitivities of 94.4%, 83.3%, and 83.3%, specificities of 100%, 100%, and 100%, and (2) accuracies of 95.7%, 87%, and 87%, respectively. These observations correlated most reliably as indicators for skin sensitization potency. Data suggest that IL-1α and IL-1β may serve as potential biomarkers for skin sensitization and provide an alternative method to animal experiments for prediction of skin sensitization potency and risk assessment.

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.

Predictive performance for human skin sensitizing potential of the human cell line activation test (h-CLAT)

BACKGROUND

Recent changes in regulatory restrictions and social opposition to animal toxicology experiments have driven the need for reliable in vitro tests for predicting the skin sensitizing potentials of a wide variety of industrial chemicals. Previously, we developed the human cell line activation test (h-CLAT) as a cell-based assay to predict the skin sensitizing potential of chemicals, and showed the correspondence between the h-CLAT and the murine local lymph node assay results.

OBJECTIVES

This study was conducted to investigate the predictive performance of the h-CLAT for human skin sensitizing potential.

MATERIALS/METHODS

We selected a total of 66 test chemicals with known human sensitizing potential, and tested all chemicals with the h-CLAT. We then evaluated the performance of the h-CLAT in predicting human sensitizing potential.

RESULTS AND CONCLUSION

Forty-five of 51 tested sensitizers were positive in the h-CLAT, indicating relatively high sensitivity. Also, 10 of 15 non-sensitizers were correctly detected as negative. The overall agreement between human data and h-CLAT outcome was 83%. Furthermore, the h-CLAT could accurately predict the human sensitizing potential of 23 tested chemicals that were amines, heterocyclic compounds, or sulfur compounds. Our data indicate the utility of the h-CLAT for predicting the human skin sensitizing potential of a variety of chemicals.

The human repeated insult patch test in the 21st century: a commentary

The human repeated insult patch test (HRIPT) is over half a century old, but is still used in several countries as a confirmatory test in the safety evaluation of skin sensitizers. This is despite the criticism it receives from an ethical perspective and regarding the scientific validity of such testing. In this commentary, the HRIPT is reviewed, with emphasis on ethical aspects and where the test can, and cannot, contribute in a scientifically meaningful manner to safety evaluation. It is concluded that where there is a specific rationale for testing, for example, to substantiate a no-effect level for a sensitizing chemical or to ensure that matrix effects are not making an unexpected contribution to sensitizing potency, then rigorous independent review may confirm that an HRIPT is ethical and scientifically justifiable. The possibility that sensitization may be induced in volunteers dictates that HRIPTs should be conducted rarely and in cases where the benefits overwhelmingly outweigh the risk. However, for the very large majority of HRIPTs conducted concerning the risk of skin sensitization, there is neither scientific justification nor any other merit.

The local lymph node assay and the assessment of relative potency: status of validation

For the prediction of skin sensitization potential, the local lymph node assay (LLNA) is a fully validated alternative to guinea-pig tests. More recently, information from LLNA dose-response analyses has been used to assess the relative potency of skin sensitizing chemicals. These data are then deployed for risk assessment and risk management. In this commentary, the utility and validity of these relative potency measurements are reviewed. It is concluded that the LLNA does provide a valuable assessment of relative sensitizing potency in the form of the estimated concentration of a chemical required to produce a threefold stimulation of draining lymph node cell proliferation compared with concurrent controls (EC3 value) and that all reasonable validation requirements have been addressed successfully. EC3 measurements are reproducible in both intra- and interlaboratory evaluations and are stable over time. It has been shown also, by several independent groups, that EC3 values correlate closely with data on relative human skin sensitization potency. Consequently, the recommendation made here is that LLNA EC3 measurements should now be regarded as a validated method for the determination of the relative potency of skin sensitizing chemicals, a conclusion that has already been reached by a number of independent expert groups.

Information derived from sensitization test methods: test sensitivity, false positives and false negatives

Predictive toxicology tests for the prospective identification of skin-sensitizing chemicals are well known and have been used for many years. However, of these, only the local lymph node assay (LLNA) has actually undergone formal independent assessment to determine the accuracy of the predictions, particularly with respect to the likelihood of false positives and false negatives. Often, efforts to increase the sensitivity of a test (reducing false negatives) tend to increase the number of false positives. In this short review, these issues are discussed in particular relation to the 3 predictive tests available in regulatory toxicology, the guinea-pig maximization test, the occluded patch test of Buehler and the LLNA. A key perspective is that no predictive test is without limitations; having a good appreciation of these limitations is necessary for making the best use of the information derived from these methods.

Identification and classification of skin sensitizers: identifying false positives and false negatives

The first step in regulatory evaluation of substances involves the identification of their intrinsic hazards, including the potential for skin sensitization. This is, quite properly, entirely different from assessment of the risks to human health, which might arise from incorporation of substances in products. EU guidance on regulations concerning the classification of skin sensitizers suggests a range of sources of information be deployed in the hazard identification process. These include chemical structure, predictive animal tests, and various types of human data. Where the information is clear-cut, then uncertainties rarely arise. However, for some materials, discordant information arises, perhaps because the substance is on the borderline of test sensitivity and classification (sensitizing materials of insufficient potency do not classified according to the EU scheme), due to conflicting results in predictive tests or for other reasons. In this study, we review data on a number of substances where a classification decision is complicated by such discordances and seek to use these examples to demonstrate how best to make a weight of evidence decision on whether a substance should, or should not, be classified as a skin sensitizer.