Traditionally, the skin sensitization potential of chemicals has been assessed using animal models. However, the preferred animal testing for chemical safety assessment has shown major drawbacks, such as poor correlation with human response, high cost and slow outcome rate. Moreover, due to growing ethical, political, and financial concerns, sustainable alternatives to animal testing need to be developed. As publicly available skin sensitization data continues to grow, computational approaches are expected to reduce or replace animal testing for the prediction of human skin sensitization potential. Here, we report on new comprehensive computational approach for predicting human skin sensitization that integrates multiple Quantitative Structure-Activity Relationship (QSAR) models developed on <i>in vitro</i>, <i>in chemico</i>, animal, and human data, into a final Naïve Bayes model. QSAR models were generated using human repeat insult patch tests (HRIPTs), human maximization tests (HMTs), as well as mouse Local Lymph Node Assay (LLNA) data for skin sensitization. In addition, we also include data for three validated alternative methods, named Direct Peptide Reactivity Assay (DPRA), KeratinoSens, and the human Cell Line Activation Test (h-CLAT). Models were developed and rigorously validated according to the best practices of QSAR modeling using open-source tools. Predictions obtained from these models were then used to build a Naïve Bayes model for predicting human skin sensitization with high externally estimated predictivity: balanced accuracy (89%), sensitivity (94%), positive predicted value (91%), specificity (84%), and negative predicted value (89%). All the developed models could be accessed at Pred-Skin 2.0 Web-portal at: http://5.189.141.142:5002/.

Comprehensive computational approach for predicting human skin sensitization as suggested alternative to animal testing

2019 Spring National Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.