The aim of the current study was to develop an in silico model to predict the sensitizing potential of cosmetic ingredients based on their physicochemical characteristics and to compare the predictions with historical animal data and results from “omics”-based in vitro studies. An in silico model was developed with the use of WEKA machine learning software fed with physicochemical and structural descriptors of haptens and trained with data from published epidemiological studies compiled into estimated odds ratio (eOR) and estimated attributable risk (eAR) indices. The outcome classification was compared to the results of animal studies and in vitro tests. Of all the models tested, the best results were obtained for the Naive Bayes classifier trained with 24 physicochemical descriptors and eAR, which yielded an accuracy of 86%, sensitivity of 80%, and specificity of 90%. This model was subsequently used to predict the sensitizing potential of 15 emerging and less-studied haptens, of which 7 were classified as sensitizers: cyclamen aldehyde, N,N-dimethylacrylamide, dimethylthiocarbamyl benzothiazole sulphide, geraniol hydroperoxide, isobornyl acrylate, neral, and prenyl caffeate. The best-performing model (NaiveBayes eAR, 24 parameters), along with an alternative model based on eOR (Random Comittee eOR, 17 parameters), are available for further tests by interested readers. In conclusion, the proposed infotechnomics approach allows for a prediction of the sensitizing potential of cosmetic ingredients (and possibly also other haptens) with accuracy comparable to historical animal tests and in vitro tests used nowadays. In silico models consume little resources, are free of ethical concerns, and can provide results for multiple chemicals almost instantly; therefore, the proposed approach seems useful in the safety assessment of cosmetics.

Introduction:The use of cosmetics and skin care products is on a steady increase, especially in developed countries. Despite increasingly strict regulations, ingredients with irritant potential are still widely used in cosmetic products. On patch tests, irritant reactions may be mistaken for allergic reactions, leading to misdiagnoses.Aim: To compile and analyze available data on irritant reactions to cosmetic ingredients from patch test studies in humans. Material and methods: Data on irritant reactions to cosmetic ingredients in patch tests were extracted from published patch test studies indexed in PubMed, Embase, Web of Science or Google Scholar. The available data were pooled to assess the frequency and create a ranking list of irritant cosmetic ingredients. Results: Data on the prevalence of irritant reactions among people undergoing patch testing (routine or experimental) were available for 47 cosmetic ingredients. Among ingredients routinely tested in the European Baseline Series, the highest rates of irritant reactions were reported for Myroxylon pereirae resin (balsam of Peru, irritant reactions in 3.40% of patch test patients), followed by Fragrance mix II (2.83%), Fragrance mix I (2.34%), colophonium (1.14%), p-phenylenediamine 1% (0.99%), hydroxyisohexyl 3-cyclohexene carboxaldehyde (0.70%), Paraben mix (0.48%) and Quaternium 15 (0.29%). Conclusions: A range of widely used cosmetic ingredients possess irritative properties, which may contribute to irritant contact dermatitis in the consumers. In routine patch testing, irritant reactions to cosmetic ingredients may emerge in as many as one in ten patients. As irritant reactions to cosmetic ingredients in patch tests may contribute to false diagnosis of allergic contact dermatitis, doctors should be aware of the risk and able to single out such reactions.

No abstract

No abstract

No abstract