“…In addition to hazard identification, information on skin sensitizer potency is imperative in order to allow quantitative risk assessment and to define exposure limits. Approaches for the prediction of skin sensitizer potency have been published and were recently reviewed by Ezendam et al (2016), such as assays targeting KE2 (epidermal equivalent sensitizer potency assay (Teunis et al, 2014), SENS-IS (Cottrez et al, 2015)) and the U-SENS assay modelling KE3 (Piroird et al, 2015). Furthermore, in silico models, often combining information from several in vitro methods, have been described, for example QSAR (Dearden et al, 2015), artificial neural networks (Tsujita-Inoue et al, 2014), probabilistic models and integrated testing strategy (ITS) approaches including a Bayesian model (Jaworska et al, 2013(Jaworska et al, , 2015Luechtefeld et al, 2015;Natsch et al, 2015).…”