Prediction of skin sensitization potency using machine learning approaches

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.

Integration of the Natural Language Processing of Structural Information Simplified Molecular-Input Line-Entry System Can Improve the In Vitro Prediction of Human Skin Sensitizers

Natural language processing (NLP) technology has recently used to predict substance properties based on their Simplified Molecular-Input Line-Entry System (SMILES). We aimed to develop a model predicting human skin sensitizers by integrating text features derived from SMILES with in vitro test outcomes. The dataset on SMILES, physicochemical properties, in vitro tests (DPRA, KeratinoSensTM, h-CLAT, and SENS-IS assays), and human potency categories for 122 substances sourced from the Cosmetics Europe database. The ChemBERTa model was employed to analyze the SMILES of substances. The last hidden layer embedding of ChemBERTa was tested with other features. Given the modest dataset size, we trained five XGBoost models using subsets of the training data, and subsequently employed bagging to create the final model. Notably, the features computed from SMILES played a pivotal role in the model for distinguishing sensitizers and non-sensitizers. The final model demonstrated a classification accuracy of 80% and an AUC-ROC of 0.82, effectively discriminating sensitizers from non-sensitizers. Furthermore, the model exhibited an accuracy of 82% and an AUC-ROC of 0.82 in classifying strong and weak sensitizers. In summary, we demonstrated that the integration of NLP of SMILES with in vitro test results can enhance the prediction of health hazard associated with chemicals.

Prediction of skin sensitization using machine learning

As global awareness of animal welfare spreads, the development of alternative animal test models is increasingly necessary. The purpose of this study was to develop a practical machine-learning model for skin sensitization using three physicochemical properties of the chemicals: surface tension, melting point, and molecular weight. In this study, a total of 482 chemicals with local lymph node assay results were collected, and 297 datasets with 6 physico-chemical properties were used to develop Random Forest (RF) model for skin sensitization. The developed model was validated with 45 fragrance allergens announced by European Commission. The validation results showed that RF achieved better or similar classification performance with f1-scores of 54% for penal, 82% for ternary, and 96% for binary compared with Support Vector Machine (SVM) (penal, 41%; ternary, 81%; binary, 93%), QSARs (ChemTunes, 72% for ternary; OECD Toolbox, 89% for binary), and a linear model (Kim et al., 2020) (41% for penal), and we recommend the ternary classification based on Global Harmonized System providing more detailed and precise information. In the further study, the proposed model results were experimentally validated with the Direct Peptide Reactivity Assay (DPRA, OECD TG 442C approved model), and the results showed a similar tendency. We anticipate that this study will help to easily and quickly screen chemical sensitization hazards.

In Silico Prediction of Human Organ Toxicity via Artificial Intelligence Methods

Unpredicted human organ level toxicity remains one of the major reasons for drug clinical failure. There is a critical need for cost-efficient strategies in the early stages of drug development for human toxicity assessment. At present, artificial intelligence methods are popularly regarded as a promising solution in chemical toxicology. Thus, we provided comprehensive in silico prediction models for eight significant human organ level toxicity end points using machine learning, deep learning, and transfer learning algorithms. In this work, our results showed that the graph-based deep learning approach was generally better than the conventional machine learning models, and good performances were observed for most of the human organ level toxicity end points in this study. In addition, we found that the transfer learning algorithm could improve model performance for skin sensitization end point using source domain of in vivo acute toxicity data and in vitro data of the Tox21 project. It can be concluded that our models can provide useful guidance for the rapid identification of the compounds with human organ level toxicity for drug discovery.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

Development of a 96-Well Electrophilic Allergen Screening Assay for Skin Sensitization Using a Measurement Science Approach

The Electrophilic Allergen Screening Assay (EASA) has emerged as a promising in chemico method to detect the first key event in the adverse outcome pathway (AOP) for skin sensitization. This assay functions by assessing the depletion of one of two probe molecules (4-nitrobenzenethiol (NBT) and pyridoxylamine (PDA)) in the presence of a test compound (TC). The initial development of EASA utilized a cuvette format resulting in multiple measurement challenges such as low throughput and the inability to include adequate control measurements. In this study, we describe the redesign of EASA into a 96-well plate format that incorporates in-process control measurements to quantify key sources of variability each time the assay is run. The data from the analysis of 67 TCs using the 96-well format had 77% concordance with animal data from the local lymph node assay (LLNA), a result consistent with that for the direct peptide reactivity assay (DPRA), an OECD test guideline (442C) protein binding assay. Overall, the measurement science approach described here provides steps during assay development that can be taken to increase confidence of in chemico assays by attempting to fully characterize the sources of variability and potential biases and incorporate in-process control measurements into the assay.

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.

Assessment of the skin sensitization potential of fragrance ingredients using the U-SENS™ assay

The U-SENS™ assay was developed to address the third key event of the skin sensitization adverse outcome pathway (AOP) and is described in OECD test guideline 442E, Annex II. A dataset of 68 fragrance ingredients comprised of 7 non-sensitizers and 61 sensitizers was tested in the U-SENS™ assay. The potential for fragrance ingredients to activate dendritic cells, measured by U-SENS™, was compared to the sensitization potential determined by weight of evidence (WoE) from historical data. Of the non-sensitizers, 4 induced CD86 cell surface marker ≥1.5-fold while 3 did not. Of the sensitizers, 50 were predicted to be positive in U-SENS™, while the remaining 11 were negative. Positive and negative predictive values (PPV and NPV) of U-SENS™ were 93% and 21%, respectively. No specific chemical property evaluated could account for misclassified ingredients. Assessment of parent and metabolite protein binding alerts in silico suggests that parent chemical metabolism may play a role in CD86 activation in U-SENS™. Combining the U-SENS™ assay in a "2 out of 3" defined approach with the direct peptide reactivity assay (DPRA) and KeratinoSens™ predicted sensitization hazard with PPV and NPV of 97% and 24%, respectively. Combining complementary in silico and in vitro methods to the U-SENS™ assay should be integrated to define the hazard classification of fragrance ingredients, since a single NAM cannot replace animal-based methods.

Evaluation of facial skin age based on biophysical properties in vivo

OBJECTIVE

The evaluation of skin age, reflecting overall facial characteristics, has not been established. Previous studies focused on visual assessment or individual-specific feature such as wrinkles or skin color. We studied the evaluation model of skin age index (SAI) including the overall aging features including wrinkles, skin color, pigmentation, elasticity, and hydration.

METHODS

Total 300 healthy women aged between 20 and 69 years included in this study. Pearson correlation analysis performed to identify the key factors among the biophysical properties with aging and developed the prediction model of SAI. Statistical regression analysis and machine learning technique applied to build the prediction model using the coefficient of determination (R² ) and root mean square error (RMSE). Validation study of the SAI model performed on 24 women for 6 weeks application with anti-aging product.

RESULTS

Prediction model of SAI consisted of skin elasticity, wrinkles, skin color (brightness, Pigmented spot, and Uv spot), and hydration, which are major features for aging. The cforest model to assess a SAI using machine learning identified the highest R² and lowest RMSE compared to other models, such as svmRadial, gaussprRadial, blackboost, rpart, and statistical regression formula. The cforest prediction model confirmed a significant decrease of predicted SAI after 6 weeks of application of anti-aging product.

CONCLUSION

We developed a prediction model to evaluate a SAI using machine learning, and led to accurate predicted age for overall clinical aging. This model can a good standard index for evaluating facial skin aging and anti-aging products.

Semi-correlations as a tool to model for skin sensitization

Semi-correlation specifically assesses the correlation between a binary variable and a continuous variable. Semi-correlations were applied to develop binary models for various endpoints. We applied the semi-correlation to develop models of two kinds of skin sensitization one related to animals (local lymph node assay LLNA) and one to human beings (direct peptide reactivity assay DPRA and/or human cell line activation test h-CLAT). The models refer to binary classification for a two-level strategy: the first level (analysis of all compounds) is used in the format "sensitizer or non-sensitizer", and the second level (only sensitizers) is a further classification in the format "strong or weak sensitizer". The ranges of statistical characteristics of the models depend on the endpoint, LLNA or DPRA/h-CLAT: for the first level, sensitivity: 0.69-0.88, specificity: 0.75-0.89, accuracy: 0.77-0.87, Matthew's correlation coefficient (MCC): 0.54-0.57 and for the second level, sensitivity: 0.70-1.0, specificity: 0.78-0.83, accuracy: 0.77-0.87, MCC: 0.54-0.76. Thus, the described approach can be applied to building up models of the skin sensitization potency.

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.

Implementation of the principles of the 3Rs of animal testing at CDER: Past, present and future

The safety testing of pharmaceutical candidates has traditionally relied on data gathered from studies in animals, and these sources of information remain a vital component of the safety assessment for new drug and biologic products. However, there are clearly ethical implications that attend the use of animals for safety testing, and FDA fully supports the principles of the 3Rs, as it relates to animal usage; these being to replace, reduce and refine. We provide an overview of some of the events and activities (legal and programmatic) that have had, and continue to have, the greatest impact on animal use in pharmaceutical development, and highlight some ongoing efforts to further meet the challenge of achieving our mission as humanely as possible.

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.

[Artificial intelligence to support telemedicine in Africa]

Telemedizin findet seit Jahrzehnten Anwendung im Alltag von Dermatologen. Insbesondere in afrikanischen Ländern mit begrenzter medizinischer Versorgung, zu überbrückenden geografischen Distanzen und einem zwischenzeitlich relativ gut ausgebauten Telekommunikationssektor liegen die Vorteile auf der Hand. Nationale und internationale Arbeitsgruppen unterstützen den Aufbau von teledermatologischen Projekten und bedienen sich in den letzten Jahren zunehmend KI(künstliche Intelligenz)-gestützter Technologien, um Ärzte vor Ort zu unterstützen. Vor diesem Hintergrund stellen ethnische Variationen eine besondere Herausforderung in der Entwicklung automatisierter Algorithmen dar. Um die Genauigkeit der Systeme weiter zu verbessern und globalisieren zu können, ist es wichtig, die Zahl der verfügbaren klinischen Daten zu erhöhen. Dies kann nur mit der aktiven Beteiligung der lokalen Gesundheitsversorger sowie der dermatologischen Gemeinschaft gelingen und muss stets im Interesse des einzelnen Patienten erfolgen.

Evaluating Skin Sensitization Via Soft and Hard Multivariate Modeling

Allergic contact dermatitis is the most frequent manifestation of immunotoxicity in humans with a prevalence rate of 15% to 20% over general population. Skin sensitization is a complex end point that was for a long time being evaluated using animal testing. Great efforts have been made to completely substitute the use of animals and replace them by integrating data from in vitro and in chemico assays with in silico calculated parameters. However, it remains undefined how to make the best use of the cumulative data in such a way that information gain is maximized and accomplished with the fewest number of tests possible. In this work, 3 skin sensitization prediction models were considered: one to discriminate sensitizers from non-sensitizers, considering a 2-level scale; one according to the GHS, considering a 3-level scale; and the other to categorize potency in a 6-level scale, according to available human data. We used a data set of known human skin allergens for which in vitro, in chemico, and in silico descriptors where available to build classifiers based on soft and hard multivariate modeling. Model building, optimization, and refinement resulted in 100% accuracy in distinguishing between sensitizers and non-sensitizers. The same model was able to perform the characterization, in 3 and 6 levels, respectively, with 98.8 and 97.5% accuracy. Combining data from in vitro and in chemico tests with in silico descriptors is relatively simple to implement and some predictors are fitting the adverse outcome pathway for skin sensitization.

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

Artificial intelligence (AI) has become a progressively prevalent Research Topic in medicine and is increasingly being applied to dermatology. There is a need to understand this technology's progress to help guide and shape the future for medical care providers and recipients. We reviewed the literature to evaluate the types of publications on the subject, the specific dermatological topics addressed by AI, and the most challenging barriers to its implementation. A substantial number of original articles and commentaries have been published to date and only few detailed reviews exist. Most AI applications focus on differentiating between benign and malignant skin lesions, however; others exist pertaining to ulcers, inflammatory skin diseases, allergen exposure, dermatopathology, and gene expression profiling. Applications commonly analyze and classify images, however, other tools such as risk assessment calculators are becoming increasingly available. Although many applications are technologically feasible, important implementation barriers have been identified including systematic biases, difficulty of standardization, interpretability, and acceptance by physicians and patients alike. This review provides insight into future research needs and possibilities. There is a strong need for clinical investigation in dermatology providing evidence of success overcoming the identified barriers. With these research goals in mind, an appropriate role for AI in dermatology may be achieved in not so distant future.

Skin sensitisation testing in practice: Applying a stacking meta model to cosmetic ingredients

Recently, several non-animal approaches contributing to the identification of skin sensitisation hazard have been introduced. Their validation and acceptance has largely been directed towards regulatory classification. Considering the driving force for replacement of in vivo tests centred on cosmetics, it is reasonable to ask how well the new approaches perform in this respect. In the present study, 219 substances, largely cosmetic raw materials (including dyes, preservatives and fragrances), have been evaluated in our Defined Approach integrating a stacking meta model (version 5), incorporating the individual outcomes of 3 in vitro validated methods (Direct Peptide Reactivity Assay, Keratinosens™, U-SENS™), 2 in silico tools (TIMES SS, TOXTREE) and physicochemical parameters (volatility, pH). Stacking meta model outcomes were compared with existing local lymph node assay (LLNA) data. Non-sensitisers comprised 68/219; 86 were weak/moderate and 65 were stronger sensitisers. The model version revision demonstrate the gain to discriminate sensitizers to non-sensitiser when the in silico TIMES model is incorporated as input parameter. The 85% to 91% accuracy for the cosmetics categories, indicates the stacking meta model offers value for the next generation risk assessment framework. These results pinpoint the power of the stacking meta model relying on a confidence based on the probability given in any individual prediction.

Systematic review of machine learning for diagnosis and prognosis in dermatology

Background: Software systems using artificial intelligence for medical purposes have been developed in recent years. The success of deep neural networks (DNN) in 2012 in the image recognition challenge ImageNet LSVRC 2010 fueled expectations of the potential for using such systems in dermatology.Objective: To evaluate the ways in which machine learning has been utilized in dermatology to date and provide an overview of the findings in current literature on the subject.Methods: We conducted a systematic review of existing literature, identifying the literature through a systematic search of the PubMed database. Two doctors assessed screening and eligibility with respect to pre-determined inclusion and exclusion criteria.Results: A total of 2175 publications were identified, and 64 publications were included. We identified eight major categories where machine learning tools were tested in dermatology. Most systems involved image recognition tools that were primarily aimed at binary classification of malignant melanoma (MM). Short system descriptions and results of all included systems are presented in tables.Conclusions: We present a complete overview of artificial intelligence implemented in dermatology. Impressive outcomes were reported in all of the identified eight categories, but head-to-head comparison proved difficult. The many areas of dermatology where we identified machine learning tools indicate the diversity of machine learning.

The 21st Century movement within the area of skin sensitization assessment: From the animal context towards current human-relevant in vitro solutions

In a regulatory context, skin sensitization hazard and risk evaluations of manufactured products and their ingredients (e.g. cosmetics) are mandatory in several regions. Great efforts have been made within the field of 21st Century Toxicology to provide non-animal testing approaches to assess the skin allergy potential of materials (e.g. chemicals, mixtures, nanomaterials, particles). Mechanistic understanding of skin sensitization process through the adverse outcome pathway (AOP) has promoted the development of in vitro methods, demonstrating accuracies superior to the traditional animal testing. These in vitro testing approaches are based on one of the four AOP key events (KE) of skin sensitization: formation of immunogenic hapten-protein complexes (KE-1 or the molecular initiating event, MIE), inflammatory keratinocyte responses (KE-2), dendritic cell activation (KE-3), and T-lymphocyte activation and proliferation (KE-4). This update provides an overview of the historically used in vivo methods as well as the current in chemico and in cell methods with and without OECD guideline designations to analyze the progress towards human-relevant in vitro test methods for safety assessment of the skin allergenicity potential of materials. Here our focus is to review 96 in vitro testing approaches directed to the KEs of the skin sensitization AOP.

Skin toxicology and 3Rs-Current challenges for public health protection

Driven by the fast paced development of complex test systems in vitro, mass spectrometry and omics, we finally have the tools to unravel the molecular events that underlie toxicological adversity. Yet, timely regulatory adaptation of these new tools continues to pose major challenges even for organs readily accessible such as skin. The reasons for this encompass a need for conservatism as well as the need of tests to serve an existing regulatory framework rather than to produce scientific knowledge. It is important to be aware of this in order to align regulatory skin toxicity with the 3R principles more readily. While most chemical safety testing is still based on animal data, regulatory frameworks have seen a strong push towards non-animal approaches. The endpoints corrosion, irritation, sensitisation, absorption and phototoxicity, for example, can now be covered in vitro with the corresponding test guidelines (TGs) being made available by the OECD. However, in vitro approaches tend to be more reductionist. Hence, a combination of several tests is usually preferable to achieve satisfying predictivity. Moreover, the test systems and their combined use need to be standardised and are therefore subject not only to validation but also to the ongoing development of so-called integrated approaches to testing and assessment (IATAs). Concomitantly, skin models are being refined to deliver the complexity required for increased applicability and predictivity. Given the importance of regulatory applicability for 3R-derived approaches to have a long-lasting impact, this review examines the state of regulatory implementation and perspectives, respectively.

Skin Sensitization Testing-What's Next?

There is an increasing demand for alternative in vitro methods to replace animal testing, and, to succeed, new methods are required to be at least as accurate as existing in vivo tests. However, skin sensitization is a complex process requiring coordinated and tightly regulated interactions between a variety of cells and molecules. Consequently, there is considerable difficulty in reproducing this level of biological complexity in vitro, and as a result the development of non-animal methods has posed a major challenge. However, with the use of a relevant biological system, the high information content of whole genome expression, and comprehensive bioinformatics, assays for most complex biological processes can be achieved. We propose that the Genomic Allergen Rapid Detection (GARD™) assay, developed to create a holistic data-driven in vitro model with high informational content, could be such an example. Based on the genomic expression of a mature human dendritic cell line and state-of-the-art machine learning techniques, GARD™ can today accurately predict skin sensitizers and correctly categorize skin sensitizing potency. Consequently, by utilizing advanced processing tools in combination with high information genomic or proteomic data, we can take the next step toward alternative methods with the same predictive accuracy as today’s in vivo methods—and beyond.

Contact Allergy to Fragrances: In Vitro Opportunities for Safety Assessment

The majority of cosmetic products contain fragrances to make products more pleasant to the consumer, as we all like goods that smell nice. Unfortunately, contact allergy to fragrance compounds is among the most frequent findings in patients with suspected allergic contact dermatitis. In order to revert this and to reduce contact allergy to cosmetics, it is imperative to improve safety assessment of cosmetic products for skin sensitization. In the era of animal ban for cosmetic ingredients, this represents a challenge. Luckily, in the last decades, substantial progress has been made in the understanding of the mechanism of chemical-induced contact allergy and several in vitro methods are available for hazard identification. The purpose of this manuscript is to explore the possibility of non-animal testing for quantitative risk assessment of fragrance-induced contact allergy, essential for cosmetic products, which cannot be tested on animals.

Chemical-induced contact allergy: from mechanistic understanding to risk prevention

Chemical allergens are small molecules able to form a sensitizing complex once they bound to proteins. One of the most frequent manifestations of chemical allergy is contact hypersensitivity, which can have serious impact on quality of life. Allergic contact dermatitis is a predominantly CD8 + T cell-mediated immune disease, resulting in erythema and eczema. Chemical allergy is of considerable importance to the toxicologist, who has the responsibility of identifying and characterizing the allergenic potential of chemicals, and estimating the risk they pose to human health. This review aimed at exploring the phenomena of chemical-induced contact allergy starting from a mechanistic understanding, immunoregulatory mechanisms, passing through the potency of contract allergen until the hazard identification, pointing out the in vitro models for assessing contact allergen-induced cell activation and the risk prevention.

Integrated Approaches to Testing and Assessment

The concept of Integrated Approaches to Testing and Assessment (IATA) has been advanced by the Organisation for Economic Cooperation and Development (OECD) member countries to enable a progressive shift from traditional chemical assessments largely based on the observation of the adverse effect in animal models, using individual methods or predefined batteries of standard toxicity tests, to assessment strategies integrating diverse lines of evidence. The flexible nature of IATA allows the inclusion of mechanistic data generated with non-animal methods and with new technologies (e.g. high-throughput and high content methods). The assessment process within IATA is typically conducted through weight-of-evidence which inevitably includes the elements of subjective expert judgement. For these reasons, IATA cannot be fully harmonized across sectors and countries. Nevertheless, some of the IATA components, such as defined approaches, which consist of a fixed data interpretation procedure (DIP) applied to data generated with a defined set of information sources, can be harmonized. The focus of this MiniReview is to provide an illustration of the differences between the IATA developed so far in the areas of regulatory toxicology, and ongoing activities related to the international harmonization of defined approaches that rely on multiple non-animal information sources.

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.

Challenges for Integrating Immunotoxicology into the Twenty-First-Century Toxicology Testing Paradigm

An emerging emphasis on mechanism-focused and human-relevant alternatives to animal use in toxicology underlies the toxicology testing in the twenty-first-century initiative. Herein we describe in vitro high-throughput screening programs seeking to address this goal, as well as strategies established to integrate assay results to build weight of evidence in support of hazard assessment. Furthermore, we discuss unique challenges facing the application of such alternatives for assessing immunotoxicity given the complexity of immune responses. Addressing these challenges will require the development of novel in vitro assays that evaluate well-characterized biochemical processes involved in immune response to help inform on putative adverse outcomes in vivo.