Computational approaches for skin sensitization prediction

An Integrated Testing Strategy and Online Tool for Assessing Skin Sensitization of Agrochemical Formulations

Non-animal assessment of skin sensitization is a global trend. Recently, scientific efforts have been focused on the integration of multiple evidence for decision making with the publication of OECD Guideline No. 497 for defined approaches to skin sensitization. The integrated testing strategy (ITS) methods reported by the guideline integrates in chemico, in vitro, and in silico testing to assess both hazard and potency of skin sensitization. The incorporation of in silico methods achieved comparable performance with fewer experiments compared to the traditional two-out-of-three (2o3) method. However, the direct application of current ITSs to agrochemicals can be problematic due to the lack of agrochemicals in the training data of the incorporated in silico methods. To address the issue, we present ITS-SkinSensPred 2.0 for agrochemicals and agrochemical formulations using a reconfigured in silico model SkinSensPred for pesticides. Compared to ITSv2, the proposed ITS-SkinSensPred 2.0 achieved an 11% and 16% improvement in the accuracy and correct classification rate for hazard identification and potency classification, respectively. In addition, an online ITS tool was implemented and available on the SkinSensDB website. The tool is expected to be useful for evaluating skin sensitization of substances.

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

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

Development of a rapid screening method utilizing 2D LC for effect-directed analysis in the identification of environmental toxicants

Effect-directed analysis (EDA) is a crucial tool in environmental toxicology, effectively integrating toxicity testing with chemical analysis. The conventional EDA approach, however, presents challenges such as significant solvent consumption, extended analysis time, labor intensity, and potential contamination risks. In response, we introduce an innovative alternative to the conventional EDA. This method utilizes the MTT bioassay and online two-dimensional liquid chromatography (2D LC) coupled with high-resolution mass spectrometry (HR-MS), significantly reducing the fractionation steps and leveraging the enhanced sensitivity of the bioassay and automated chemical analysis. In the chemical analysis phase, a switching valve interface is employed for comprehensive analysis. We tested the performance of both the conventional and our online 2D LC-based methods using a household product. Both methods identified the same number of toxicants in the sample. Our alternative EDA is 22.5 times faster than the conventional method, fully automated, and substantially reduces solvent consumption. This novel approach offers ease, cost-effectiveness, and represents a paradigm shift in EDA methodologies. By integrating a sensitive bioassay with online 2D LC, it not only enhances efficiency but also addresses the challenges associated with traditional methods, marking a significant advancement in environmental toxicology research.

Strategy proposal using QSAR models to approach mutagenicity assessment of non intentionally added substances in recycled plastic resins

CONTEXT

Transition to the use of recycled plastics raises an issue concerning safety assessment of Non Intentionally Added Substances (NIAS). To assess the mutagenic potential of the recycled polyethylene impurities and to evaluate the need to perform in vitro assays on recycled resins, this study lies in identifying existing NIAS associated with recycled Low/High Density Polyethylene and assessing the mutagenicity data-gaps by employing in silico tools.

METHODS

Quantitative Structure-Activity Relationship (QSAR) models predicting Ames mutagenicity were selected from literature, then NIAS were run to 1/evaluate performances of each model, 2/apply a QSAR strategy on the NIAS molecular space and address data-gaps.

RESULTS

Among the 165 NIAS identified, experimental Ames results were not found for 50 substances while the substances with experimental data were predominantly negatives. No individual model was able to predict all NIAS due to applicability domain limitations. Taking into account 1/calculated performances, 2/availability of applicability domain, 3/description of the Training Set, an Integrated Strategy was founded including Sarpy, Consensus and Protox to extend the applicability domain.

CONCLUSION & PERSPECTIVES

Existing data and predictions generated by this strategy suggest a low mutagenic potential of NIAS. Further investigation is needed to explore other genotoxicity mechanisms.

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

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

Principles, applications, and future of artificial intelligence in dermatology

This paper provides an overview of artificial-intelligence (AI), as applied to dermatology. We focus our discussion on methodology, AI applications for various skin diseases, limitations, and future opportunities. We review how the current image-based models are being implemented in dermatology across disease subsets, and highlight the challenges facing widespread adoption. Additionally, we discuss how the future of AI in dermatology might evolve and the emerging paradigm of large language, and multi-modal models to emphasize the importance of developing responsible, fair, and equitable models in dermatology.

Perspectives of data science in preclinical safety assessment

The data landscape in preclinical safety assessment is fundamentally changing because of not only emerging new data types, such as human systems biology, or real-world data (RWD) from clinical trials, but also technological advancements in data-processing software and analytical tools based on deep learning approaches. The recent developments of data science are illustrated with use cases for the three factors: predictive safety (new in silico tools), insight generation (new data for outstanding questions); and reverse translation (extrapolating from clinical experience to resolve preclinical questions). Further advances in this field can be expected if companies focus on overcoming identified challenges related to a lack of platforms and data silos and assuring appropriate training of data scientists within the preclinical safety teams.

Naturally-Occurring Tyrosinase Inhibitors Classified by Enzyme Kinetics and Copper Chelation

Currently, there are three major assaying methods used to validate in vitro whitening activity from natural products: methods using mushroom tyrosinase, human tyrosinase, and dopachrome tautomerase (or tyrosinase-related protein-2, TRP-2). Whitening agent development consists of two ways, melanin synthesis inhibition in melanocytes and downregulation of melanocyte stimulation. For melanin levels, the melanocyte cell line has been used to examine melanin synthesis with the expression levels of TRP-1 and TRP-2. The proliferation of epidermal surfaced cells and melanocytes is stimulated by cellular signaling receptors, factors, or mediators including endothelin-1, α-melanocyte-stimulating hormone, nitric oxide, histamine, paired box 3, microphthalmia-associated transcription factor, pyrimidine dimer, ceramide, stem cell factors, melanocortin-1 receptor, and cAMP. In addition, the promoter region of melanin synthetic genes including tyrosinase is upregulated by melanocyte-specific transcription factors. Thus, the inhibition of growth and melanin synthesis in gene expression levels represents a whitening research method that serves as an alternative to tyrosinase inhibition. Many researchers have recently presented the bioactivity-guided fractionation, discovery, purification, and identification of whitening agents. Melanogenesis inhibition can be obtained using three different methods: tyrosinase inhibition, copper chelation, and melanin-related protein downregulation. There are currently four different types of inhibitors characterized based on their enzyme inhibition mechanisms: competitive, uncompetitive, competitive/uncompetitive mixed-type, and noncompetitive inhibitors. Reversible inhibitor types act as suicide substrates, where traditional inhibitors are classified as inactivators and reversible inhibitors based on the molecule-recognizing properties of the enzyme. In a minor role, transcription factors can also be downregulated by inhibitors. Currently, the active site copper iron-binding inhibitors such as kojic acid and chalcone exhibit tyrosinase inhibitory activity. Because the tyrosinase catalysis site structure is important for the mechanism determination of tyrosinase inhibitors, understanding the enzyme recognition and inhibitory mechanism of inhibitors is essential for the new development of tyrosinase inhibitors. The present review intends to classify current natural products identified by means of enzyme kinetics and copper chelation to exhibit tyrosinase enzyme inhibition.

The Skin Sensitisation of Cosmetic Ingredients: Review of Actual Regulatory Status

All cosmetics products must be safe under foreseeable conditions of use. Allergenic responses are one of the most frequent adverse reactions noted for cosmetics. Thus, the EU cosmetics legislation requires skin sensitisation assessment for all cosmetics ingredients, including the regulated ones (for which the full toxicological dossier needs to be analysed by the Scientific Committee on Consumer Safety (SCCS)) and those (perceived as less toxic) which are assessed by industrial safety assessors. Regardless of who performs the risk assessment, it should be carried out using scientifically and regulatory body-accepted methods. In the EU, reference methods for chemical toxicity testing are defined in the relevant Annexes (VII-X) of the Registration, Evaluation, Authorisation and Restriction of Chemicals (REACH) Regulation. Recommendations for Skin Sensitization (Skin Sens) testing are provided in Annex VII, and this particular endpoint information is required for all EU-registered chemicals. Historically, in vivo animal and human methods have been used. Both raise ethical doubts, and some of them cause practical problems in the objective analysis of skin sensitising potency. Previous decades of huge effort have resulted in the regulatory acceptance of the alternative Skin Sens IATA (Integrated Approaches to Testing and Assessment) and NGRA (Next Generation Risk Assessment). Regardless of the testing issues, a serious sociological problem are observed within the market: the consumer assumes the presence of strong sensitisers in cosmetics formulations and insufficient risk management tools used by the industry. The present review aims to provide an overview of methods for assessing skin sensitisation. Additionally, it aims to answer the following question: what are the most potent skin sensitisers used in cosmetics? The answer considers the mechanistic background along with the actual regulatory status of ingredients and practical examples of responsible industry solutions in the area of risk management.

Incorporating integrated testing strategy (ITSv1) defined approach into read-across (RAx) in predicting skin sensitization potency: ITSv1-based RAx

Recently, due to regulatory and ethical demands, new approach methodologies (NAMs), defined approaches (DAs), and read-across (RAx) have been used in the risk assessment of skin sensitization. Integrated testing strategy (ITS)v1 DA, adopted in OECD Guideline No. 497, can be used for skin sensitization potency categorization. However, ITSv1 DA alone is not used for further refinement of the potency prediction based on EC3 (the estimated concentration that produces a stimulation index of 3 in murine local lymph node assay) values. Moreover, there is no explicit approach to incorporating NAM/DA data into RAx to fill the data gap of EC3 values with high confidence. This study developed a strategy incorporating ITSv1 DA into RAx to predict skin sensitization potency: ITSv1-based RAx. To examine the reliability of this novel strategy, a case study with lilial, a fragrance material, was performed. Based on ITSv1-based RAx, the skin sensitization potency of lilial was determined by extrapolating the EC3 value of 9.5% for the suitable analogue bourgeonal, which was close to the historical EC3 value of 8.6%. The result suggested that the strategy can refine the prediction of EC3 values with high confidence and be useful for the risk assessment of skin sensitization.

Semiquantitative sensitization safety assessment of extractable and leachables associated with parenteral pharmaceutical products

Extractable and leachables (E&Ls) associated with parenteral pharmaceutical products should be assessed for patient safety. One essential safety endpoint is local or systemic sensitization. However, there are no regulatory guidelines for quantitative sensitization safety assessment of E&Ls. A semiquantitative sensitization safety assessment workflow is developed to refine the sensitization safety assessment of E&Ls associated with parenteral pharmaceutical products. The workflow is composed of two sequential steps: local skin sensitization and systemic sensitization safety assessment. The local skin sensitization step has four tiers. The output from this step is the acceptable exposure level for local sensitization (AEL_ls) and this safety threshold can be used for local sensitization safety assessment. From the derived AEL_ls, the systemic sensitization safety assessment at step 2 proceeds in 2 tiers. The output from this workflow is the derivation of acceptable exposure level for systemic sensitization (AEL_ss). When the estimated human daily exposure (HDE) is compared with the AEL_ss, the margin of exposure is calculated to determine the sensitization safety of E&Ls following parenteral administration. The current work represents an initial effort to develop a scientifically robust process for sensitization safety assessment of E&Ls associated with parenteral pharmaceutical products.

Alternative Methods for Skin-Sensitization Assessment

Skin sensitization is a term used to refer to the regulatory hazard known as allergic contact dermatitis (ACD) in humans or contact hypersensitivity in rodents, an important health endpoint considered in chemical hazard and risk assessments. Information on skin sensitization potential is required in various regulatory frameworks, such as the Directive of the European Parliament and the Council on Registration, Evaluation and Authorization of Chemicals (REACH). The identification of skin-sensitizing chemicals previously required the use of animal testing, which is now being replaced by alternative methods. Alternative methods in the field of skin sensitization are based on the measurement or prediction of key events (KE), i.e., (i) the molecular triggering event, i.e., the covalent binding of electrophilic substances to nucleophilic centers in skin proteins; (ii) the activation of keratinocytes; (iii) the activation of dendritic cells; (iv) the proliferation of T cells. This review article focuses on the current state of knowledge regarding the methods corresponding to each of the key events in skin sensitization and considers the latest trends in the development and modification of these methods.

Reconfiguring the online tool of SkinSensPred for predicting skin sensitization of pesticides

Adverse outcome pathway (AOP)-based computational models provide state-of-the-art prediction for human skin sensitizers and are promising alternatives to animal testing. However, little is known about their applicability to pesticides due to scarce pesticide data for evaluation. Moreover, pesticides traditionally have been tested on animals without human data, making validation difficult. Direct application of AOP-based models to pesticides may be inappropriate since their original applicability domains were designed to maximize reliability for human response prediction on diverse chemicals but not pesticides. This study proposed to identify a consensus chemical space with concordant human responses predicted by the SkinSensPred online tool and animal testing data to reduce animal testing. The identified consensus chemical space for non-sensitizers achieved high concordance of 85% and 100% for the cross-validation and independent test, respectively. The reconfigured SkinSensPred can be applied as the first-tier tool for identifying non-sensitizers to reduce. animal testing for pesticides by 19.6%.

SkinSensPred as a Promising in Silico Tool for Integrated Testing Strategy on Skin Sensitization

Skin sensitization is an important regulatory endpoint associated with allergic contact dermatitis. Recently, several adverse outcome pathway (AOP)-based alternative methods were developed to replace animal testing for evaluating skin sensitizers. The AOP-based assays were further integrated as a two-out-of-three method with good predictivity. However, the acquisition of experimental data is resource-intensive. In contrast, an integrated testing strategy (ITS) capable of maximizing the usage of laboratory data from AOP-based and in silico methods was developed as defined approaches (DAs) to both hazard and potency assessment. There are currently two in silico models, namely Derek Nexus and OECD QSAR Toolbox, evaluated in the OECD Testing Guideline No. 497. Since more advanced machine learning algorithms have been proposed for skin sensitization prediction, it is therefore desirable to evaluate their performance under the ITS framework. This study evaluated the performance of a new ITS DA (ITS-SkinSensPred) adopting a transfer learning-based SkinSensPred model. Results showed that the ITS-SkinSensPred has similar or slightly better performance compared to the other ITS models. SkinSensPred-based ITS is expected to be a promising method for assessing skin sensitization.

Implementation of a dermal sensitization threshold (DST) concept for risk assessment: structure-based DST and in vitro data-based DST

Skin sensitization resulting in allergic contact dermatitis represents an important toxicological endpoint as part of safety assessments. When available substance-specific sensitization data are inadequate, the dermal sensitization threshold (DST) concept has been proposed to set a skin exposure threshold to provide no appreciable risk of skin sensitization. Structure-based DSTs, which include non-reactive, reactive, and high potency category (HPC) DSTs, can be applied to substances with an identified chemical structures. An in vitro data-based "mixture DST" can be applied to mixtures based on data from in vitro test methods, such as KeratinoSens™ and the human Cell Line Activation Test. The purpose of this review article is to discuss the practical use of DSTs for conducting sound sensitization risk assessments to assure the safety of consumer products. To this end, several improvements are discussed in this review. For application of structure-based DSTs, an overall structural classification workflow was developed to exclude the possibility that "HPC but non-reactive" chemicals are misclassified as "non-reactive", because such chemicals should be classified as HPC chemicals considering that HPC rules have been based on the chemical structure of high potency sensitizers. Besides that, an extended application of the mixture DST principle to mixtures that either is cytotoxic or evaluated as positive was proposed. On a final note, we also developed workflows that integrate structure-based and in vitro-based mixture DST. The proposed workflows enable the application of the appropriate DST, which serves as a point of departure in the quantitative sensitization risk assessment.

Gradient boosting approaches can outperform logistic regression for risk prediction in cutaneous allergy

BACKGROUND

Contact allergy is a major clinical and public health challenge. It is important to identify individuals who are at risk and perform patch testing to identify relevant allergens. Predicting clinical risk on the basis of input parameters is common in clinical medicine and traditionally has been achieved with linear models.

OBJECTIVES

We hypothesized that the risk of a clinically relevant positive patch test could be predicted according to clinical and demographic parameters.

METHODS

We compared the predictive accuracy of logistic regression with more sophisticated machine learning approaches such as gradient boosting, in the prediction of patch testing results.

RESULTS

We found that both logistic regression and more sophisticated machine learning approaches were able to predict the risk of positive patch tests. For certain predictions, including the overall risk of a clinically relevant positive patch test, gradient boosting approaches can outperform logistic regression.

CONCLUSIONS

These findings suggest that complex nonlinear interactions between input variables are relevant in risk prediction. While a risk prediction model cannot replace the judgment of an experienced clinician, quantifying the risk of a clinically relevant positive patch test result has the potential to assist in decision making and to inform discussions with patients.

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

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

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.

Predicting the Skin Sensitization Potential of Small Molecules with Machine Learning Models Trained on Biologically Meaningful Descriptors

In recent years, a number of machine learning models for the prediction of the skin sensitization potential of small organic molecules have been reported and become available. These models generally perform well within their applicability domains but, as a result of the use of molecular fingerprints and other non-intuitive descriptors, the interpretability of the existing models is limited. The aim of this work is to develop a strategy to replace the non-intuitive features by predicted outcomes of bioassays. We show that such replacement is indeed possible and that as few as ten interpretable, predicted bioactivities are sufficient to reach competitive performance. On a holdout data set of 257 compounds, the best model (“Skin Doctor CP:Bio”) obtained an efficiency of 0.82 and an MCC of 0.52 (at the significance level of 0.20). Skin Doctor CP:Bio is available free of charge for academic research. The modeling strategies explored in this work are easily transferable and could be adopted for the development of more interpretable machine learning models for the prediction of the bioactivity and toxicity of small organic compounds.

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.

Inhibitory Effect of Avenanthramides (Avn) on Tyrosinase Activity and Melanogenesis in α-MSH-Activated SK-MEL-2 Cells: In Vitro and In Silico Analysis

Melanin causes melasma, freckles, age spots, and chloasma. Anti-melanogenic agents can prevent disease-related hyperpigmentation. In the present study, the dose-dependent tyrosinase inhibitory activity of Avenanthramide (Avn)-A-B-C was demonstrated, and 100 µM Avn-A-B-C produced the strongest competitive inhibition against inter-cellular tyrosinase and melanin synthesis. Avn-A-B-C inhibits the expression of melanogenesis-related proteins, such as TRP1 and 2. Molecular docking simulation revealed that AvnC (−7.6 kcal/mol) had a higher binding affinity for tyrosinase than AvnA (−7.3 kcal/mol) and AvnB (−6.8 kcal/mol). AvnC was predicted to interact with tyrosinase through two hydrogen bonds at Ser360 (distance: 2.7 Å) and Asn364 (distance: 2.6 Å). In addition, AvnB and AvnC were predicted to be skin non-sensitizers in mammals by the Derek Nexus Quantitative Structure–Activity Relationship system.

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.

Skin Doctor CP: Conformal Prediction of the Skin Sensitization Potential of Small Organic Molecules

Skin sensitization potential or potency is an important end point in the safety assessment of new chemicals and new chemical mixtures. Formerly, animal experiments such as the local lymph node assay (LLNA) were the main form of assessment. Today, however, the focus lies on the development of nonanimal testing approaches (i.e., in vitro and in chemico assays) and computational models. In this work, we investigate, based on publicly available LLNA data, the ability of aggregated, Mondrian conformal prediction classifiers to differentiate between non- sensitizing and sensitizing compounds as well as between two levels of skin sensitization potential (weak to moderate sensitizers, and strong to extreme sensitizers). The advantage of the conformal prediction framework over other modeling approaches is that it assigns compounds to activity classes only if a defined minimum level of confidence is reached for the individual predictions. This eliminates the need for applicability domain criteria that often are arbitrary in their nature and less flexible. Our new binary classifier, named Skin Doctor CP, differentiates nonsensitizers from sensitizers with a higher reliability-to-efficiency ratio than the corresponding nonconformal prediction workflow that we presented earlier. When tested on a set of 257 compounds at the significance levels of 0.10 and 0.30, the model reached an efficiency of 0.49 and 0.92, and an accuracy of 0.83 and 0.75, respectively. In addition, we developed a ternary classification workflow to differentiate nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers. Although this model achieved satisfactory overall performance (accuracies of 0.90 and 0.73, and efficiencies of 0.42 and 0.90, at significance levels 0.10 and 0.30, respectively), it did not obtain satisfying class-wise results (at a significance level of 0.30, the validities obtained for nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers were 0.70, 0.58, and 0.63, respectively). We argue that the model is, in consequence, unable to reliably identify strong to extreme sensitizers and suggest that other ternary models derived from the currently accessible LLNA data might suffer from the same problem. Skin Doctor CP is available via a public web service at https://nerdd.zbh.uni-hamburg.de/skinDoctorII/.

Comparison of the predictive nature of the Genomic Allergen Rapid Detection (GARD) assay with mammalian assays in determining the skin sensitisation potential of agrochemical active ingredients

Alternatives to mammalian testing are highly desirable to predict the skin sensitisation potential of agrochemical active ingredients (AI). The GARD assay, a stimulated, dendritic cell-like, cell line measuring genomic signatures, was evaluated using twelve AIs (seven sensitisers and five non-sensitisers) and the results compared with historical results from guinea pig or local lymph node assay (LLNA) studies. Initial GARD results suggested 11/12 AIs were sensitisers and six concurred with mammalian data. Conformal predictions changed one AI to a non-sensitiser. An AI identified as non-sensitising in the GARD assay was considered a potent sensitiser in the LLNA. In total 7/12 GARD results corresponded with mammalian data. AI chemistries might not be comparable to the GARD training set in terms of applicability domains. Whilst the GARD assay can replace mammalian tests for skin sensitisation evaluation for compounds including cosmetic ingredients, further work in agrochemical chemistries is needed for this assay to be a viable replacement to animal testing. The work conducted here is, however, considered exploratory research and the methodology needs further development to be validated for agrochemicals. Mammalian and other alternative assays for regulatory safety assessments of AIs must provide confidence to assign the appropriate classification for human health protection.

Application of the adverse outcome pathway framework for investigating skin sensitization potential of nanomaterials using new approach methods

BACKGROUND

Currently, considerable efforts to standardize methods for accurate assessment of properties and safety aspects of nanomaterials are being made. However, immunomodulation effects upon skin exposure to nanomaterial have not been explored.

OBJECTIVES

To investigate the immunotoxicity of single-wall carbon nanotubes, titanium dioxide, and fullerene using the current mechanistic understanding of skin sensitization by applying the concept of adverse outcome pathway (AOP).

METHODS

Investigation of the ability of nanomaterials to interact with skin proteins using the micro-direct peptide reactivity assay; the expression of CD86 cell surface marker using the U937 cell activation test (OECD No. 442E/2018); and the effects of nanomaterials on modulating inflammatory response through inflammatory cytokine release by U937 cells.

RESULTS

The nanomaterials easily internalized into keratinocytes cells, interacted with skin proteins, and triggered activation of U937 cells by increasing CD86 expression and modulating inflammatory cytokine production. Consequently, these nanomaterials were classified as skin sensitizers in vitro.

CONCLUSIONS

Our study suggests the potential immunotoxicity of nanomaterials and highlights the importance of studying the immunotoxicity and skin sensitization potential of nanomaterials to anticipate possible human health risks using standardized mechanistic nonanimal methods with high predictive accuracy. Therefore, it contributes toward the applicability of existing OECD (Organisation for Economic Co-operation and Development) testing guidelines for accurate assessment of nanomaterial skin sensitization potential.

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.

Going All In: A Strategic Investment in In Silico Toxicology

As vast numbers of new chemicals are introduced to market annually, we are faced with the grand challenge of protecting humans and the environment while minimizing economically and ethically costly animal testing. In silico models promise to be the solution we seek, but we find ourselves at crossroads of future development efforts that would ensure standalone applicability and reliability of these tools. A conscientious effort that prioritizes experimental testing to support the needs of in silico models (versus regulatory needs) is called for to achieve this goal. Using economic analogy in the title of this work, we argue that a prudent investment is to go all-in to support in silico model development, rather than gamble our future by keeping the status quo of a "balanced portfolio" of testing approaches. We discuss two paths to future in silico toxicology-one based on big-data statistics ("broadsword"), and the other based on direct modeling of molecular interactions ("scalpel")-and offer rationale that the latter approach is more transparent, is better aligned with our quest for fundamental knowledge, and has a greater potential to succeed if we are willing to transform our toxicity-testing paradigm.

Skin Doctor: Machine Learning Models for Skin Sensitization Prediction that Provide Estimates and Indicators of Prediction Reliability

The ability to predict the skin sensitization potential of small organic molecules is of high importance to the development and safe application of cosmetics, drugs and pesticides. One of the most widely accepted methods for predicting this hazard is the local lymph node assay (LLNA). The goal of this work was to develop in silico models for the prediction of the skin sensitization potential of small molecules that go beyond the state of the art, with larger LLNA data sets and, most importantly, a robust and intuitive definition of the applicability domain, paired with additional indicators of the reliability of predictions. We explored a large variety of molecular descriptors and fingerprints in combination with random forest and support vector machine classifiers. The most suitable models were tested on holdout data, on which they yielded competitive performance (Matthews correlation coefficients up to 0.52; accuracies up to 0.76; areas under the receiver operating characteristic curves up to 0.83). The most favorable models are available via a public web service that, in addition to predictions, provides assessments of the applicability domain and indicators of the reliability of the individual predictions.