Prediction of skin sensitization using machine learning

• Published in: Toxicology in vitro 2023-12, Vol.93, p.105690-105690, Article 105690
• Main Authors: Im, Jueng Eun, Lee, Jung Dae, Kim, Hyang Yeon, Kim, Hak Rim, Seo, Dong-Wan, Kim, Kyu-Bong
• Format: Article
• Language: English
• Subjects: Machine learning; Random forest; Skin sensitization; Surface tension
• ISSN: 0887-2333; 1879-3177
• DOI: 10.1016/j.tiv.2023.105690

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. •Random Forest model for the skin sensitization hazard of chemicals was developed.•Surface tension, melting point, and molecular weight were selected as model features.•45 allergens were successfully classified into GHS categories with an 82% f1-score.•Our model outperformed SVM, QSARs, and a linear model.•Validation results showed a similar tendency to DPRA (OECD 442E approved model).