Multivariate models for prediction of human skin sensitization hazard. Issue 3 (2nd August 2016)

• Record Type: Journal Article
• Authors: Strickland, Judy; Zang, Qingda; Paris, Michael; Lehmann, David M.; Allen, David; Choksi, Neepa; Matheson, Joanna; Jacobs, Abigail; Casey, Warren; Kleinstreuer, Nicole
• Is Part Of: Journal of applied toxicology. Volume 37:Issue 3(2017)
• Page Start: 347
• Page End: 360
• Publication Date: 2016-08-02
• Subjects: Skin sensitization -- allergic contact dermatitis (ACD) -- integrated decision strategy -- machine learning -- LLNA -- DPRA -- KeratinoSens -- h‐CLAT; Toxicology -- Periodicals; Industrial toxicology -- Periodicals; Environmentally induced diseases -- Periodicals; Toxicology -- Periodicals; 615.9005
• DOI: 10.1002/jat.3366
• Languages: English
• ISSNs: 0260-437X

Abstract

Abstract: One of the Interagency Coordinating Committee on the Validation of Alternative Method's (ICCVAM) top priorities is the development and evaluation of non‐animal approaches to identify potential skin sensitizers. The complexity of biological events necessary to produce skin sensitization suggests that no single alternative method will replace the currently accepted animal tests. ICCVAM is evaluating an integrated approach to testing and assessment based on the adverse outcome pathway for skin sensitization that uses machine learning approaches to predict human skin sensitization hazard. We combined data from three in chemico or in vitro assays – the direct peptide reactivity assay (DPRA), human cell line activation test (h‐CLAT) and KeratinoSens™ assay – six physicochemical properties and an in silico read‐across prediction of skin sensitization hazard into 12 variable groups. The variable groups were evaluated using two machine learning approaches, logistic regression and support vector machine, to predict human skin sensitization hazard. Models were trained on 72 substances and tested on an external set of 24 substances. The six models (three logistic regression and three support vector machine) with the highest accuracy (92%) used: (1) DPRA, h‐CLAT and read‐across; (2) DPRA, h‐CLAT, read‐across and KeratinoSens; or (3) DPRA, h‐CLAT, read‐across, KeratinoSens and log P. The models performed better at predicting human skin sensitization hazard than the murine local lymph node assay (accuracy 88%), any of the alternative methods alone (accuracy 63–79%) or test batteries combining data from the individual methods (accuracy 75%). These results suggest that computational methods are promising tools to identify effectively the potential human skin sensitizers without animal testing. Published 2016. This article has been contributed to by US Government employees and their work is in the public domain in the USA. Abstract : The Interagency Coordinating Committee on the Validation of Alternative Methods evaluated a non‐animal decision strategy using machine learning approaches to integrate in vitro, in chemico and in silico data and physicochemical properties to predict human skin sensitization hazard for 96 substances. The six most accurate models used different combinations of variables and outperformed the local lymph node assay and individual non‐animal methods. Results of this evaluation suggest that computational approaches are promising tools to integrate data effectively to identify potential sensitizers without animal testing.