Evaluation of the global performance of eight in silico skin sensitization models using human data

Thumbnail Image
Date
2021
Authors
Golden, Emily
Macmillan, Donna S.
Dameron, Greg
Kern, Petra
Maertens, Alexandra
Editors
Contact
Journal ISSN
Electronic ISSN
ISBN
Bibliographical data
Publisher
Series
DOI (citable link)
ArXiv-ID
International patent number
Link to the license
EU project number
681002
Project
EUToxRisk21
Open Access publication
Collections
Restricted until
Title in another language
Research Projects
Organizational Units
Journal Issue
Publication type
Journal article
Publication status
Published
Published in
Alternatives to Animal Experimentation : ALTEX ; 38 (2021), 1. - pp. 33-48. - Springer Spektrum. - ISSN 0946-7785. - eISSN 1868-8551
Abstract
Allergic contact dermatitis, or the clinical manifestation of skin sensitization, is a leading occupational hazard. Several testing approaches exist to assess skin sensitization, but in silico models are perhaps the most advantageous due to their high speed and low-cost results. Many in silico skin sensitization models exist, though many have only been tested against results from animal studies (e.g., LLNA); this creates uncertainty in human skin sensitization assessments in both a screening and regulatory context. This project’s aim was to evaluate the accuracy of eight in silico skin sensitization models against two human data sets: one highly curated (Basketter et al., 2014) and one screening level (HSDB). The binary skin sen­sitization status of each chemical in each of the two data sets was compared to the prediction from eight in silico skin sensitization tools (Toxtree, PredSkin, OECD’s QSAR Toolbox, UL’s REACHAcross™, Danish QSAR Database, TIMES-SS, and Lhasa Limited’s Derek Nexus). Models were assessed for coverage, accuracy, sensitivity, and specificity, as well as optimization features (e.g., probability of accuracy, applicability domain, etc.), if available. While there was a wide range of sensitivity and specificity, the models generally performed comparably to the LLNA in predicting human skin sensitization status (i.e., approximately 70-80% accuracy). Additionally, the models did not mispredict the same com­pounds, suggesting there might be an advantage in combining models. In silico skin sensitization models offer accurate and useful insights in a screening context; however, further improvements are necessary so these models may be con­sidered fully reliable for regulatory applications.
Summary in another language
Subject (DDC)
570 Biosciences, Biology
Keywords
QSAR; read-across; skin sensitization; structural alerts
Conference
Review
undefined / . - undefined, undefined. - (undefined; undefined)
Cite This
ISO 690GOLDEN, Emily, Donna S. MACMILLAN, Greg DAMERON, Petra KERN, Thomas HARTUNG, Alexandra MAERTENS, 2021. Evaluation of the global performance of eight in silico skin sensitization models using human data. In: Alternatives to Animal Experimentation : ALTEX. Springer Spektrum. 38(1), pp. 33-48. ISSN 0946-7785. eISSN 1868-8551. Available under: doi: 10.14573/altex.1911261
BibTex
@article{Golden2021Evalu-57028,
  year={2021},
  doi={10.14573/altex.1911261},
  title={Evaluation of the global performance of eight in silico skin sensitization models using human data},
  number={1},
  volume={38},
  issn={0946-7785},
  journal={Alternatives to Animal Experimentation : ALTEX},
  pages={33--48},
  author={Golden, Emily and Macmillan, Donna S. and Dameron, Greg and Kern, Petra and Hartung, Thomas and Maertens, Alexandra}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/57028">
    <dcterms:issued>2021</dcterms:issued>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57028"/>
    <dc:contributor>Dameron, Greg</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57028/3/Hartung_2-1onbwkkrhgxdt1.pdf"/>
    <dc:contributor>Golden, Emily</dc:contributor>
    <dc:creator>Maertens, Alexandra</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/28"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Hartung, Thomas</dc:creator>
    <dc:language>eng</dc:language>
    <dc:creator>Dameron, Greg</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:abstract xml:lang="eng">Allergic contact dermatitis, or the clinical manifestation of skin sensitization, is a leading occupational hazard. Several testing approaches exist to assess skin sensitization, but in silico models are perhaps the most advantageous due to their high speed and low-cost results. Many in silico skin sensitization models exist, though many have only been tested against results from animal studies (e.g., LLNA); this creates uncertainty in human skin sensitization assessments in both a screening and regulatory context. This project’s aim was to evaluate the accuracy of eight in silico skin sensitization models against two human data sets: one highly curated (Basketter et al., 2014) and one screening level (HSDB). The binary skin sen­sitization status of each chemical in each of the two data sets was compared to the prediction from eight in silico skin sensitization tools (Toxtree, PredSkin, OECD’s QSAR Toolbox, UL’s REACHAcross™, Danish QSAR Database, TIMES-SS, and Lhasa Limited’s Derek Nexus). Models were assessed for coverage, accuracy, sensitivity, and specificity, as well as optimization features (e.g., probability of accuracy, applicability domain, etc.), if available. While there was a wide range of sensitivity and specificity, the models generally performed comparably to the LLNA in predicting human skin sensitization status (i.e., approximately 70-80% accuracy). Additionally, the models did not mispredict the same com­pounds, suggesting there might be an advantage in combining models. In silico skin sensitization models offer accurate and useful insights in a screening context; however, further improvements are necessary so these models may be con­sidered fully reliable for regulatory applications.</dcterms:abstract>
    <dc:contributor>Maertens, Alexandra</dc:contributor>
    <dc:creator>Golden, Emily</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-03-29T06:43:27Z</dc:date>
    <dc:creator>Kern, Petra</dc:creator>
    <dcterms:title>Evaluation of the global performance of eight in silico skin sensitization models using human data</dcterms:title>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-03-29T06:43:27Z</dcterms:available>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Kern, Petra</dc:contributor>
    <dc:contributor>Hartung, Thomas</dc:contributor>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57028/3/Hartung_2-1onbwkkrhgxdt1.pdf"/>
    <dc:contributor>Macmillan, Donna S.</dc:contributor>
    <dc:creator>Macmillan, Donna S.</dc:creator>
  </rdf:Description>
</rdf:RDF>
Internal note
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Contact
URL of original publication
Test date of URL
Examination date of dissertation
Method of financing
Comment on publication
Alliance license
Corresponding Authors der Uni Konstanz vorhanden
International Co-Authors
Bibliography of Konstanz
Yes
Refereed
Yes