Screening Allergenic Potencies of Skin-Contact Products Using the Human-Derived THP-1 Cell Activation Test.

With the prevalence of allergic contact dermatitis (ACD) from the usage of skin-contact products, like wearable, skin care, and hair care products, screening their skin sensitizing potential is necessary, for the sake of alleviating the consequent public health impact. In the present study, a total of 77 skin-contact products classified by four categories, watch bands (WBs), skin care products (SCPs), hair care products (HCPs), and rubber gloves (RGs), were investigated, using an optimized in vitro assay of human cell line activation test (h-CLAT). Extracting the products using neutral artificial sweat simulated well the practical usage scenarios, and testing the extracts showed that 26 of them were allergy test positive, including nine WBs, six SCPs, two HCPs, and nine RGs. The allergenic response was mainly characterized by the induction of CD54 expression, and diverse paradigms of CD54 and CD86 levels were observed by analyzing dose-response curves, which could also be influenced by the compromised viability of the THP-1 cells. The data implicated the intricate regulation by different contributors to suspicious ingredients in the test samples. Altogether, a promising methodology for testing skin allergy potential was well established for commonly used commodities by neutral artificial sweat extraction coupled with h-CLAT screening. The findings would be of great help in tracing the potential allergens in practical products and improving their qualities.

Plant extracts, polymers and new approach methods: Practical experience with skin sensitization assessment.

Over the last decade, research into methodologies to identify skin sensitization hazards has led to the adoption of several non-animal methods as OECD test guidelines. However, predictive accuracy beyond the chemical domains of the individual validation studies remains largely untested. In the present study, skin sensitization test results from in vitro and in chemico methods for 12 plant extracts and 15 polymeric materials are reported and compared to available in vivo skin sensitization data. Eight plant extracts were tested in the DPRA and h-CLAT, with the 2 out of 3 approach resulting in a balanced accuracy of 50%. The balanced accuracy for the 11 plant extracts assessed in the SENS-IS was 88%. Excluding 5 polymers inconclusive in vitro, the remainder, assessed using the 2 out of 3 approach, resulted in 63% balanced accuracy. The SENS-IS method, excluding one polymeric material due to technical inapplicability, showed 68% balanced accuracy. Although based on limited numbers, the results presented here indicate that some substance subgroups may not be in the applicability domains of the method used and careful analysis is required before positive or negative results can be accepted.

Sensitization properties of acetophenone azine, a new skin sensitizer identified in textile.

BACKGROUND: Acetophenone azine (CAS no. 729-43-1) present in sports equipment (shoes, socks and shin pads) has been suspected to induce skin allergies. Twelve case reports of allergy in children and adults from Europe and North America were published between 2016 and 2021. OBJECTIVES: The objective of this study was to confirm that acetophenone azine is indeed a skin sensitizer based on in vitro/ in vivo testings derived from the Adverse Outcome Pathway (AOP) built for skin sensitization by OECD in 2012. METHODS: Acetophenone azine was tested in vitro according to the human cell line activation test (h-CLAT) and the ARE-Nrf2 Luciferase Test (KeratinoSens) and in vivo using the Local Lymph Nodes Assay (LLNA). RESULTS: Both the h-CLAT and the KeratinoSens were positive whereas the LLNA performed at 5, 2.5 and 1% (wt/vol) of acetophenone azine, was negative. CONCLUSION: Based on these results, acetophenone azine was considered as a skin sensitizer. This was recently confirmed by its classification under the CLP regulation.

Development of an In Vitro Sensitisation Test Using a Coculture System of Human Bronchial Epithelium and Immune Cells.

Chemical respiratory sensitisation is a serious health problem. However, to date, there are no validated test methods available for identifying respiratory sensitisers. The aim of this study was to develop an in vitro sensitisation test by modifying the human cell line activation test (h-CLAT) to detect respiratory sensitisers and distinguish them from skin sensitisers. THP-1 cells were exposed to the test chemicals (two skin sensitisers and six respiratory sensitisers), either as monocultures or as cocultures with air-liquid interface-cultured reconstructed human bronchial epithelium. The responses were analysed by measuring the expression levels of surface markers on THP-1 cells (CD86, CD54 and OX40L) and the concentrations of cytokines in the culture media (interleukin (IL)-8, IL-33 and thymic stromal lymphopoietin (TSLP)). The cocultures exhibited increased CD54 expression on THP-1 cells; moreover, in the cocultures but not in the monocultures, exposure to two uronium salts (i.e. respiratory sensitisers) increased CD54 expression on THP-1 cells to levels above the criteria for a positive h-CLAT result. Additionally, exposure to the respiratory sensitiser abietic acid, significantly increased IL-8 concentration in the culture medium, but only in the cocultures. Although further optimisation of the method is needed to distinguish respiratory from skin sensitisers by using these potential markers (OX40L, IL-33 and TSLP), the coculture of THP-1 cells with bronchial epithelial cells offers a potentially useful approach for the detection of respiratory sensitisers.

The Monocytic Cell Line THP-1 as a Validated and Robust Surrogate Model for Human Dendritic Cells.

We have implemented an improved, cost-effective, and highly reproducible protocol for a simple and rapid differentiation of the human leukemia monocytic cell line THP-1 into surrogates for immature dendritic cells (iDCs) or mature dendritic cells (mDCs). The successful differentiation of THP-1 cells into iDCs was determined by high numbers of cells expressing the DC activation markers CD54 (88%) and CD86 (61%), and the absence of the maturation marker CD83. The THP-1-derived mDCs are characterized by high numbers of cells expressing CD54 (99%), CD86 (73%), and the phagocytosis marker CD11b (49%) and, in contrast to THP-1-derived iDCs, CD83 (35%) and the migration marker CXCR4 (70%). Treatment of iDCs with sensitizers, such as NiSO4 and DNCB, led to high expression of CD54 (97%/98%; GMFI, 3.0/3.2-fold induction) and CD86 (64%/96%; GMFI, 4.3/3.2-fold induction) compared to undifferentiated sensitizer-treated THP-1 (CD54, 98%/98%; CD86, 55%/96%). Thus, our iDCs are highly suitable for toxicological studies identifying potential sensitizing or inflammatory compounds. Furthermore, the expression of CD11b, CD83, and CXCR4 on our iDC and mDC surrogates could allow studies investigating the molecular mechanisms of dendritic cell maturation, phagocytosis, migration, and their use as therapeutic targets in various disorders, such as sensitization, inflammation, and cancer.

Characterization of dermal sensitization potential for industrial or agricultural chemicals with EpiSensA.

The regulatory community is transitioning to the use of nonanimal methods for dermal sensitization assessments; however, some in vitro assays have limitations in their domain of applicability depending on the properties of chemicals being tested. This study explored the utility of epidermal sensitization assay (EpiSensA) to evaluate the sensitization potential of complex and/or "difficult to test" chemicals. Assay performance was evaluated by testing a set of 20 test chemicals including 10 methacrylate esters, 5 silicone-based compounds, 3 crop protection formulations, and 2 surfactant mixtures; each had prior in vivo data plus some in silico and in vitro data. Using the weight of evidence (WoE) assessments by REACH Lead Registrants, 14 of these chemicals were sensitizers and, six were nonsensitizers based on in vivo studies (local lymph node assay [LLNA] and/or guinea pig studies). The EpiSensA correctly predicted 16/20 materials with three test materials as false positive and one silane as false negative. This silane, classified as weak sensitizer via LLNA, also gave a "false negative" result in the KeratinoSens™ assay. Overall, consistent with prior evaluations, the EpiSensA demonstrated an accuracy level of 80% relative to available in vivo WoE assessments. In addition, potency classification based on the concentration showing positive marker gene expression of EpiSensA was performed. The EpiSensA correctly predicted the potency for all seven sensitizing methacrylates classified as weak potency via LLNA (EC3 ≥ 10%). In summary, EpiSensA could identify dermal sensitization potential of these test substances and mixtures, and continues to show promise as an in vitro alternative method for dermal sensitization.

Assessment of the skin sensitisation hazard of functional polysiloxanes and silanes in the SENS-IS assay.

In the context of a larger testing programme that aimed at assessing the skin sensitisation potential of functional polysiloxanes and silanes, this investigation complements the available in vitro and in vivo data with data in the SENS-IS assay, a human in vitro 3D skin-based model. The SENS-IS assay allowed testing of all functional polysiloxanes and silanes without any solubility issues or limitations related to the multiconstituent nature of the commercial grade test substances. It appeared to encompass skin metabolism, a factor which we considered important for the skin sensitisation hazard assessment particularly of aminofunctionalised siloxanes and silanes. These three technical aspects posed significant challenges in the first part of the in vitro programme with the OECD-validated in vitro assays. The SENS-IS assay delivered promising results for this group of substances. On its own, it was the best performing model, as it did not pose any technical issues with the assay and it matched all in vivo outcomes. Considering its performance and avoidance of any limitations due to lack of solubility or chemical composition aspects, we concluded that the SENS-IS assay to be a suitable starting point for an integrated testing strategy for skin sensitisation for the group of functional polysiloxanes and silanes.

Development of an artificial neural network model for risk assessment of skin sensitization using human cell line activation test, direct peptide reactivity assay, KeratinoSens™ and in silico structure alert parameter.

It is important to predict the potential of cosmetic ingredients to cause skin sensitization, and in accordance with the European Union cosmetic directive for the replacement of animal tests, several in vitro tests based on the adverse outcome pathway have been developed for hazard identification, such as the direct peptide reactivity assay, KeratinoSens™ and the human cell line activation test. Here, we describe the development of an artificial neural network (ANN) prediction model for skin sensitization risk assessment based on the integrated testing strategy concept, using direct peptide reactivity assay, KeratinoSens™, human cell line activation test and an in silico or structure alert parameter. We first investigated the relationship between published murine local lymph node assay EC3 values, which represent skin sensitization potency, and in vitro test results using a panel of about 134 chemicals for which all the required data were available. Predictions based on ANN analysis using combinations of parameters from all three in vitro tests showed a good correlation with local lymph node assay EC3 values. However, when the ANN model was applied to a testing set of 28 chemicals that had not been included in the training set, predicted EC3s were overestimated for some chemicals. Incorporation of an additional in silico or structure alert descriptor (obtained with TIMES-M or Toxtree software) in the ANN model improved the results. Our findings suggest that the ANN model based on the integrated testing strategy concept could be useful for evaluating the skin sensitization potential.

Non-animal assessment of skin sensitization hazard: Is an integrated testing strategy needed, and if so what should be integrated?

There is an expectation that to meet regulatory requirements, and avoid or minimize animal testing, integrated approaches to testing and assessment will be needed that rely on assays representing key events (KEs) in the skin sensitization adverse outcome pathway. Three non-animal assays have been formally validated and regulatory adopted: the direct peptide reactivity assay (DPRA), the KeratinoSens™ assay and the human cell line activation test (h-CLAT). There have been many efforts to develop integrated approaches to testing and assessment with the "two out of three" approach attracting much attention. Here a set of 271 chemicals with mouse, human and non-animal sensitization test data was evaluated to compare the predictive performances of the three individual non-animal assays, their binary combinations and the "two out of three" approach in predicting skin sensitization potential. The most predictive approach was to use both the DPRA and h-CLAT as follows: (1) perform DPRA - if positive, classify as sensitizing, and (2) if negative, perform h-CLAT - a positive outcome denotes a sensitizer, a negative, a non-sensitizer. With this approach, 85% (local lymph node assay) and 93% (human) of non-sensitizer predictions were correct, whereas the "two out of three" approach had 69% (local lymph node assay) and 79% (human) of non-sensitizer predictions correct. The findings are consistent with the argument, supported by published quantitative mechanistic models that only the first KE needs to be modeled. All three assays model this KE to an extent. The value of using more than one assay depends on how the different assays compensate for each other's technical limitations. Copyright © 2017 John Wiley & Sons, Ltd.

Binary test battery with KeratinoSens™ and h-CLAT as part of a bottom-up approach for skin sensitization hazard prediction.

Skin sensitization is one of the key safety endpoints for chemicals applied directly to the skin. Several integrated testing strategies (ITS) using multiple non-animal test methods have been developed to accurately evaluate the sensitizing potential of chemicals, but there is no regulatory-accepted ITS to classify a chemical as a non-sensitizer. In this study, the predictive performance of a binary test battery with KeratinoSens™ and h-CLAT compared to the local lymph node assay (LLNA) and human data was examined using comprehensive dataset of 203 chemicals. When two negative results indicate a non-sensitizer, the binary test battery provided sensitivity of 93.4% or 94.4% compared with the LLNA or human data. Taking into account the predictive limitations (i.e. high log Kow, pre-/pro-haptens and acyl transfer agents (or amine-reactive)), the binary test battery had extremely high sensitivity comparable to that of the 3 out of 3 ITS where three negative results of the DPRA, KeratinoSens™ and h-CLAT indicate a non-sensitizer. Therefore, the data from KeratinoSens™ or h-CLAT may provide partly redundant information on the molecular initiating event derived from DPRA. Taken together, the binary test battery of KeratinoSens™ and h-CLAT could be used as part of a bottom-up approach for skin sensitization hazard prediction.

Evaluation of in vitro assays for the assessment of the skin sensitization hazard of functional polysiloxanes and silanes.

The skin sensitization potential of chemicals has traditionally been evaluated in vivo according to OECD testing guidelines in guinea pigs or the mouse local lymph node assay. There has lately been a great emphasis on establishing in vitro test methods reflecting the key biological events in the adverse outcome pathway (AOP) for skin sensitization as published by the OECD. Against this background, a group of 8 polysiloxanes and silanes, seven of them aminofunctionalised, for which in vivo data were already available, has been tested in vitro in the direct peptide reactivity assay (DPRA), the KeratinoSens™ and the human cell line activation test (h-CLAT) and in the modified myeloid U937 skin sensitization test (mMUSST) as far as technically feasible. The main objective of the programme was to determine the utility of these systems for this heterogeneous group of silicone-based substances, recognizing that some substances are outside the assays applicability domains. The presented data provided some interesting mechanistical insights into the performance of these assays for functionalised siloxanes and silanes. The data also allow for a preliminary evaluation of proposed integrated testing strategies (ITS) to determine the skin sensitization potential of chemicals which were not considered in the training sets of the respective ITS.

In chemico, in vitro and in vivo comparison of the skin sensitizing potential of eight unsaturated and one saturated lipid compounds.

The applicability of the Direct Peptide Reactivity Assay (DPRA), the KeratinoSens™ assay and the human cell line activation test (OECD Test Guidelines 442C, 442D, 442E) in predicting the skin sensitising potential of nine lipid (bio)chemicals was investigated. The results from the three assays were integrated using a published prediction model (PM), by which skin sensitisation is predicted if at least two of the three assays yield positive results. Of the eight test substances that were classified as non-sensitisers using available Guinea Pig Maximisation Test (GPMT) data, only five were correctly predicted as 'negative' in the PM. (However, only two were correctly predicted as 'negative' in the murine Local Lymph Node Assay.) The one lipid (bio)chemical that tested positive in the GPMT was also positive applying the PM. Based upon the outcome of the present study, lipid (bio)chemicals with a log Kow up to 7-8 appear amenable to the three assays. However, solubility problems, that were not evident initially, affected the performance of the DPRA. Further investigations are merited to address the conclusiveness of negative test results with concurrent lack of cytotoxicity in the in vitro assays, to evaluate if poorly soluble substances come into contact with the cells.

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.

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.

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.

Can currently available non-animal methods detect pre and pro-haptens relevant for skin sensitization?

Predictive testing to characterize substances for their skin sensitization potential has historically been based on animal tests such as the Local Lymph Node Assay (LLNA). In recent years, regulations in the cosmetics and chemicals sectors have provided strong impetus to develop non-animal alternatives. Three test methods have undergone OECD validation: the direct peptide reactivity assay (DPRA), the KeratinoSens™ and the human Cell Line Activation Test (h-CLAT). Whilst these methods perform relatively well in predicting LLNA results, a concern raised is their ability to predict chemicals that need activation to be sensitizing (pre- or pro-haptens). This current study reviewed an EURL ECVAM dataset of 127 substances for which information was available in the LLNA and three non-animal test methods. Twenty eight of the sensitizers needed to be activated, with the majority being pre-haptens. These were correctly identified by 1 or more of the test methods. Six substances were categorized exclusively as pro-haptens, but were correctly identified by at least one of the cell-based assays. The analysis here showed that skin metabolism was not likely to be a major consideration for assessing sensitization potential and that sensitizers requiring activation could be identified correctly using one or more of the current non-animal methods.

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.

Assessing skin sensitization hazard in mice and men using non-animal test methods.

Sensitization, the prerequisite event in the development of allergic contact dermatitis, is a key parameter in both hazard and risk assessments. The pathways involved have recently been formally described in the OECD adverse outcome pathway (AOP) for skin sensitization. One single non-animal test method will not be sufficient to fully address this AOP and in many cases the use of a battery of tests will be necessary. A number of methods are now fully developed and validated. In order to facilitate acceptance of these methods by both the regulatory and scientific communities, results of the single test methods (DPRA, KeratinoSens, LuSens, h-CLAT, (m)MUSST) as well for a the simple '2 out of 3' ITS for 213 substances have been compiled and qualitatively compared to both animal and human data. The dataset was also used to define different mechanistic domains by probable protein-binding mechanisms. In general, the non-animal test methods exhibited good predictivities when compared to local lymph node assay (LLNA) data and even better predictivities when compared to human data. The '2 out of 3' prediction model achieved accuracies of 90% or 79% when compared to human or LLNA data, respectively and thereby even slightly exceeded that of the LLNA.

Test battery with the human cell line activation test, direct peptide reactivity assay and DEREK based on a 139 chemical data set for predicting skin sensitizing potential and potency of chemicals.

To develop a testing strategy incorporating the human cell line activation test (h-CLAT), direct peptide reactivity assay (DPRA) and DEREK, we created an expanded data set of 139 chemicals (102 sensitizers and 37 non-sensitizers) by combining the existing data set of 101 chemicals through the collaborative projects of Japan Cosmetic Industry Association. Of the additional 38 chemicals, 15 chemicals with relatively low water solubility (log Kow > 3.5) were selected to clarify the limitation of testing strategies regarding the lipophilic chemicals. Predictivities of the h-CLAT, DPRA and DEREK, and the combinations thereof were evaluated by comparison to results of the local lymph node assay. When evaluating 139 chemicals using combinations of three methods based on integrated testing strategy (ITS) concept (ITS-based test battery) and a sequential testing strategy (STS) weighing the predictive performance of the h-CLAT and DPRA, overall similar predictivities were found as before on the 101 chemical data set. An analysis of false negative chemicals suggested a major limitation of our strategies was the testing of low water-soluble chemicals. When excluded the negative results for chemicals with log Kow > 3.5, the sensitivity and accuracy of ITS improved to 97% (91 of 94 chemicals) and 89% (114 of 128). Likewise, the sensitivity and accuracy of STS to 98% (92 of 94) and 85% (111 of 129). Moreover, the ITS and STS also showed good correlation with local lymph node assay on three potency classifications, yielding accuracies of 74% (ITS) and 73% (STS). Thus, the inclusion of log Kow in analysis could give both strategies a higher predictive performance.

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

The skin sensitization potential of chemicals has been determined with the use of the murine local lymph node assay (LLNA). However, in recent years public concern about animal welfare has led to a requirement for non-animal risk assessment systems for the prediction of skin sensitization potential, to replace LLNA. Selection of an appropriate in vitro test or in silico model descriptors is critical to obtain good predictive performance. Here, we investigated the utility of artificial neural network (ANN) prediction models using various combinations of descriptors from several in vitro sensitization tests. The dataset, collected from published data and from experiments carried out in collaboration with the Japan Cosmetic Industry Association (JCIA), consisted of values from the human cell line activation test (h-CLAT), direct peptide reactivity assay (DPRA), SH test and antioxidant response element (ARE) assay for chemicals whose LLNA thresholds have been reported. After confirming the relationship between individual in vitro test descriptors and the LLNA threshold (e.g. EC3 value), we used the subsets of chemicals for which the requisite test values were available to evaluate the predictive performance of ANN models using combinations of h-CLAT/DPRA (N = 139 chemicals), the DPRA/ARE assay (N = 69), the SH test/ARE assay (N = 73), the h-CLAT/DPRA/ARE assay (N = 69) and the h-CLAT/SH test/ARE assay (N = 73). The h-CLAT/DPRA, h-CLAT/DPRA/ARE assay and h-CLAT/SH test/ARE assay combinations showed a better predictive performance than the DPRA/ARE assay and the SH test/ARE assay. Our data indicates that the descriptors evaluated in this study were all useful for predicting human skin sensitization potential, although combinations containing h-CLAT (reflecting dendritic cell-activating ability) were most effective for ANN-based prediction.