Advanced

Predicting skin sensitizers with confidence — Using conformal prediction to determine applicability domain of GARD

Forreryd, Andy LU ; Norinder, Ulf; Lindberg, Tim LU and Lindstedt, Malin LU (2018) In Toxicology in Vitro 48. p.179-187
Abstract

GARD — Genomic Allergen Rapid Detection is a cell based alternative to animal testing for identification of skin sensitizers. The assay is based on a biomarker signature comprising 200 genes measured in an in vitro model of dendritic cells following chemical stimulations, and consistently reports predictive performances ~90% for classification of external test sets. Within the field of in vitro skin sensitization testing, definition of applicability domain is often neglected by test developers, and assays are often considered applicable across the entire chemical space. This study complements previous assessments of model performance with an estimate of confidence in individual classifications, as well as a statistically valid... (More)

GARD — Genomic Allergen Rapid Detection is a cell based alternative to animal testing for identification of skin sensitizers. The assay is based on a biomarker signature comprising 200 genes measured in an in vitro model of dendritic cells following chemical stimulations, and consistently reports predictive performances ~90% for classification of external test sets. Within the field of in vitro skin sensitization testing, definition of applicability domain is often neglected by test developers, and assays are often considered applicable across the entire chemical space. This study complements previous assessments of model performance with an estimate of confidence in individual classifications, as well as a statistically valid determination of the applicability domain for the GARD assay. Conformal prediction was implemented into current GARD protocols, and a large external test dataset (n = 70) was classified at a confidence level of 85%, to generate a valid model with a balanced accuracy of 88%, with none of the tested chemical reactivity domains identified as outside the applicability domain of the assay. In conclusion, results presented in this study complement previously reported predictive performances of GARD with a statistically valid assessment of uncertainty in each individual prediction, thus allowing for classification of skin sensitizers with confidence.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Applicability domain, Conformal prediction, GARD, In vitro assay, Skin sensitization
in
Toxicology in Vitro
volume
48
pages
9 pages
publisher
Elsevier
external identifiers
  • scopus:85041459100
ISSN
0887-2333
DOI
10.1016/j.tiv.2018.01.021
language
English
LU publication?
yes
id
fffa1098-3fb4-4449-ab8f-4658473ddda7
date added to LUP
2018-02-20 10:13:54
date last changed
2018-11-18 05:03:07
@article{fffa1098-3fb4-4449-ab8f-4658473ddda7,
  abstract     = {<p>GARD — Genomic Allergen Rapid Detection is a cell based alternative to animal testing for identification of skin sensitizers. The assay is based on a biomarker signature comprising 200 genes measured in an in vitro model of dendritic cells following chemical stimulations, and consistently reports predictive performances ~90% for classification of external test sets. Within the field of in vitro skin sensitization testing, definition of applicability domain is often neglected by test developers, and assays are often considered applicable across the entire chemical space. This study complements previous assessments of model performance with an estimate of confidence in individual classifications, as well as a statistically valid determination of the applicability domain for the GARD assay. Conformal prediction was implemented into current GARD protocols, and a large external test dataset (n = 70) was classified at a confidence level of 85%, to generate a valid model with a balanced accuracy of 88%, with none of the tested chemical reactivity domains identified as outside the applicability domain of the assay. In conclusion, results presented in this study complement previously reported predictive performances of GARD with a statistically valid assessment of uncertainty in each individual prediction, thus allowing for classification of skin sensitizers with confidence.</p>},
  author       = {Forreryd, Andy and Norinder, Ulf and Lindberg, Tim and Lindstedt, Malin},
  issn         = {0887-2333},
  keyword      = {Applicability domain,Conformal prediction,GARD,In vitro assay,Skin sensitization},
  language     = {eng},
  month        = {04},
  pages        = {179--187},
  publisher    = {Elsevier},
  series       = {Toxicology in Vitro},
  title        = {Predicting skin sensitizers with confidence — Using conformal prediction to determine applicability domain of GARD},
  url          = {http://dx.doi.org/10.1016/j.tiv.2018.01.021},
  volume       = {48},
  year         = {2018},
}