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.

A development of a graph-based ensemble machine learning model for skin sensitization hazard and potency assessment.

Many defined approaches (DAs) for skin sensitization assessment based on the adverse outcome pathway (AOP) have been developed to replace animal testing because the European Union has banned animal testing for cosmetic ingredients. Several DAs have demonstrated that machine learning models are beneficial. In this study, we have developed an ensemble prediction model utilizing the graph convolutional network (GCN) and machine learning approach to assess skin sensitization. The model integrates in silico parameters and data from alternatives to animal testing of well-defined AOP to improve DA predictivity. Multiple ensemble models were created using the probability produced by the GCN with six physicochemical properties, direct peptide reactivity assay, KeratinoSens™, and human cell line activation test (h-CLAT), using a multilayer perceptron approach. Models were evaluated by predicting the testing set's human hazard class and three potency classes (strong, weak, and non-sensitizer). When the GCN feature was used, 11 models out of 16 candidates showed the same or improved accuracy in the testing set. The ensemble model with the feature set of GCN, KeratinoSens™, and h-CLAT produced the best results with an accuracy of 88% for assessing human hazards. The best three-class potency model was created with the feature set of GCN and all three assays, resulting in 64% accuracy. These results from the ensemble approach indicate that the addition of the GCN feature could provide an improved predictivity of skin sensitization hazard and potency assessment.

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 different skin sensitization potentials of irritants and allergens as single substances and in combination using the KeratinoSens assay.

BACKGROUND: People are exposed to mixtures containing allergens and irritants often causing contact dermatitis. Therefore, regulatory authorities require systematic information on the effects of mixtures on the sensitization threshold. In this study a moderate (cinnamal) and a weak (ethylene glycol dimethacrylate) allergen were combined with irritants covering different mechanisms of action (sodium dodecyl sulfate, salicylic acid, and α-pinene). For a systematic approach, the single substances were initially tested using the KeratinoSens assay. Thereafter, each allergen was combined with noncytotoxic concentrations of the irritants. METHOD: The KeratinoSens assay was applied for the single substances according to OECD (Organisation for Economic Co-operation and Development) Test Guideline 442D. Based on these results, three noncytotoxic concentrations of the irritants were selected and applied simultaneously with 12 concentrations of the allergens to the KeratinoSens cells. Sensitization threshold and cytotoxicity were measured and compared with the individual testing. RESULTS: The combinations of allergens and irritants differed from the effects of the single substances and lowered the sensitization threshold. The quantitative approach allowed a clear description of the changes which varied by factors between 1.1 and 10.3. CONCLUSIONS: Overall, the allergen was the prominent compound in the mixture and its nature appeared to determine the degree of the response.

REACH alternative testing strategy for skin sensitization in practice: Fact or fiction?

From October 2016 the REACH Regulation requires an alternative testing strategy for skin sensitization. The current paper describes our experience when putting into practice the REACH alternative testing strategy with a modification for 50 industrial chemicals in total, including mono-constituents, multi-constituents and UVCBs. For mono- and multi-constituents, a tiered approach was followed starting with an in silico (Derek Nexus) assessment, DPRA and KeratinoSens™ assay, followed by a weight of evidence conclusion based on the generated data, or further testing using the U-SENS™ assay. For UVCBs testing started with the KeratinoSens™ assay followed by the U-SENS™ assay if additional relevant information could be gained for an overall conclusion. From the 50 substances tested, for 46% a conclusion on skin sensitization potential and potency could be drawn based on the non-animal testing strategy; however, 54% of the substances still needed to be studied in vivo due to discordant results from non-animal testing or the need for reliable potency data. Important issues with the currently available, validated non-animal methods are the lack or comparability of skin metabolism and lack of potency indication, which is present in the in vivo assays. Skin sensitization testing for UVCBs and multi-constituents is still in a grey area, as neither the in chemico, in vitro assays, and in vivo LLNA have been validated for UVCBs and multi-constituents.

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.

Effect of Fluorination on Skin Sensitization Potential and Fragrant Properties of Cinnamyl Compounds.

A series of three α- and three ß-fluorinated representatives of the family of cinnamate-derived odorants (cinnamaldehyde (1), cinnamyl alcohol (2), and ethyl cinnamate (3)) as used as fragrance ingredients is described. Olfactive evaluation shows that the fluorinated compounds exhibit a similar odor profile to their parent compounds, but the olfactive detection thresholds are clearly higher. In vitro evaluation of the skin sensitizing properties with three different assays indicates that α-fluorination of Michael acceptor systems 1 and 3 slightly improves the skin sensitization profile. α-Fluorocinnamyl alcohol 2b is a weaker skin sensitizer than cinnamyl alcohol 2a by in vitro tests and the fluorinated product drops below the sensitization threshold of the KeratinoSens® assay. On the other hand, ß-fluorination of compounds 1 - 3 results in highly reactive products which display a worsened in vitro skin sensitization profile.

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.

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.

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.

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.

Application of the KeratinoSens™ assay for assessing the skin sensitization potential of agrochemical active ingredients and formulations.

Assessment of skin sensitization potential is an important component of the safety evaluation process for agrochemical products. Recently, non-animal approaches including the KeratinoSens™ assay have been developed for predicting skin sensitization potential. Assessing the utility of the KeratinoSens™ assay for use with multi-component mixtures such as agrochemical formulations has not been previously evaluated and is a significant need. This study was undertaken to evaluate the KeratinoSens™ assay prediction potential for agrochemical formulations. The assay was conducted for 8 agrochemical active ingredients (AIs) including 3 sensitizers (acetochlor, meptyldinocap, triclopyr), 5 non-sensitizers (aminopyralid, clopyralid, florasulam, methoxyfenozide, oxyfluorfen) and 10 formulations for which in vivo sensitization data were available. The KeratinoSens™ correctly predicted the sensitization potential of all the AIs. For agrochemical formulations it was necessary to modify the standard assay procedure whereby the formulation was assumed to have a common molecular weight. The resultant approach correctly predicted the sensitization potential for 3 of 4 sensitizing formulations and all 6 non-sensitizing formulations when compared to in vivo data. Only the meptyldinocap-containing formulation was misclassified, as a result of high cytotoxicity. These results demonstrate the promising utility of the KeratinoSens™ assay for evaluating the skin sensitization potential of agrochemical AIs and formulations.

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.

Predicting points of departure and potency categories for fragrance ingredients by integrating OECD in vitro models.

Continuous potency assessment is crucial for conducting quantitative risk assessment (QRA) of sensitizers. Quantitative regression models, based on in vitro methods, have been developed to calculate points of departure for use in skin sensitization QRA. These models calculate a point of departure as a predicted value for Local Lymph Node Assay (LLNA) EC3 or potency value (PV), integrating data from the kinetic Direct Peptide Reactivity Assay (kDPRA), KeratinoSens (KS) assay, and human Cell Line Activation Test (h-CLAT). The goal of this study was to determine how in vitro predicted EC3s and PVs compare to published reference data. In vitro data were combined in point of departure regression models to predict EC3s and PVs. These points of departure were then grouped into sensitization potency categories, such as extreme, strong, moderate, weak, very weak, or non-sensitizer, as previously described. Trends in potency distribution and high concordance between predicted EC3 and PV categories and published potency categories were observed. Furthermore, the median absolute fold-misprediction ranged between 1.8 and 2.5 for models predicting EC3 and between 1.7 and 3.4 for those predicting PVs. These regression models are a promising animal alternative for determining sensitization quantitative potency for fragrance ingredients, thereby facilitating QRA.