Archives of Toxicology

, Volume 89, Issue 12, pp 2355–2383

Bayesian integrated testing strategy (ITS) for skin sensitization potency assessment: a decision support system for quantitative weight of evidence and adaptive testing strategy

  • Joanna S. Jaworska
  • Andreas Natsch
  • Cindy Ryan
  • Judy Strickland
  • Takao Ashikaga
  • Masaaki Miyazawa
In vitro systems

DOI: 10.1007/s00204-015-1634-2

Cite this article as:
Jaworska, J.S., Natsch, A., Ryan, C. et al. Arch Toxicol (2015) 89: 2355. doi:10.1007/s00204-015-1634-2


The presented Bayesian network Integrated Testing Strategy (ITS-3) for skin sensitization potency assessment is a decision support system for a risk assessor that provides quantitative weight of evidence, leading to a mechanistically interpretable potency hypothesis, and formulates adaptive testing strategy for a chemical. The system was constructed with an aim to improve precision and accuracy for predicting LLNA potency beyond ITS-2 (Jaworska et al., J Appl Toxicol 33(11):1353–1364, 2013) by improving representation of chemistry and biology. Among novel elements are corrections for bioavailability both in vivo and in vitro as well as consideration of the individual assays’ applicability domains in the prediction process. In ITS-3 structure, three validated alternative assays, DPRA, KeratinoSens and h-CLAT, represent first three key events of the adverse outcome pathway for skin sensitization. The skin sensitization potency prediction is provided as a probability distribution over four potency classes. The probability distribution is converted to Bayes factors to: 1) remove prediction bias introduced by the training set potency distribution and 2) express uncertainty in a quantitative manner, allowing transparent and consistent criteria to accept a prediction. The novel ITS-3 database includes 207 chemicals with a full set of in vivo and in vitro data. The accuracy for predicting LLNA outcomes on the external test set (n = 60) was as follows: hazard (two classes)—100 %, GHS potency classification (three classes)—96 %, potency (four classes)—89 %. This work demonstrates that skin sensitization potency prediction based on data from three key events, and often less, is possible, reliable over broad chemical classes and ready for practical applications.


Integrated testing strategy Skin sensitization Bayesian network LLNA potency class 

Supplementary material

204_2015_1634_MOESM1_ESM.xlsx (47 kb)
Supplementary material 1 (XLSX 47 kb)
204_2015_1634_MOESM2_ESM.xlsx (29 kb)
Supplementary material 2 (XLSX 28 kb)
204_2015_1634_MOESM3_ESM.xlsx (65 kb)
Supplementary material 3 (XLSX 65 kb)

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Joanna S. Jaworska
    • 1
  • Andreas Natsch
    • 2
  • Cindy Ryan
    • 3
  • Judy Strickland
    • 4
  • Takao Ashikaga
    • 5
  • Masaaki Miyazawa
    • 6
  1. 1.Procter and Gamble CompanyStrombeek-BeverBelgium
  2. 2.Givaudan Schweiz AGDuebendorfSwitzerland
  3. 3.Procter and Gamble CompanyMasonUSA
  4. 4.ILS/Contractor Supporting NICEATMResearch Triangle ParkUSA
  5. 5.Shisheido Company LimitedTokyoJapan
  6. 6.Kao Corporation, R&D Safety Science ResearchTochigiJapan

Personalised recommendations