Artificial Intelligence That Predicts Sensitizing Potential of Cosmetic Ingredients with Accuracy Comparable to Animal and In Vitro Tests—How Does the Infotechnomics Compare to Other “Omics” in the Cosmetics Safety Assessment?

Abstract

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.

Evaluation of the Safety of Cosmetic Ingredients and Their Skin Compatibility through In Silico and In Vivo Assessments of a Newly Developed Eye Serum

“…Nowadays, NAMs are widely applied for the risk evaluation of skin sensitizers [7,60]. In this sense, a very interesting research study was performed and presented by Kalicinska et al, describing an in silico model for the prediction of the sensitizing potential of cosmetic ingredients, especially haptens [63]. According to the values provided by the SpheraCosmolife software, considering the product type and the concentrations used of LMW-and MMW-HA, low skin sensitization was evidenced.…”

Diseases from the Spectrum of Dermatitis and Eczema: Can “Omics” Sciences Help with Better Systematics and More Accurate Differential Diagnosis?

“…As a result of haptenization, the spatial conformation of endogenous proteins becomes distorted by the covalent bonds with haptens to such extent that they no longer are recognized as self-antigens and can provoke an immune response like any non-self-antigen [ 85 ]. The sensitizing potential of a hapten is determined by its physicochemical properties [ 86 , 87 ]. The most frequent causes of ACD are metals and cosmetic ingredients, mainly fragrances and preservatives.…”

“…People are constantly exposed to environmental chemicals, and chemical processes of hapten activation and the haptenization of autologous proteins into non-self-antigens are constantly ongoing in everyone’s bodies. Significant effort has been invested into the early identification of emerging haptens (e.g., new cosmetic ingredients, drugs and industrial chemicals) which have considerable potential to cause a CA and ACD [ 87 , 99 , 100 ]. However, the fact that only a minority of people will ultimately develop a CA to one or a few of the hundreds of haptens they are constantly exposed to makes it clear that the prerequisites for the development of a CA are individual predispositions in combination with other co-factors, e.g., inflammation on the site of hapten penetration [ 101 , 102 , 103 ].…”