{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T03:27:37Z","timestamp":1791084457442,"version":"4.1.0"},"reference-count":44,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2019,9,28]],"date-time":"2019-09-28T00:00:00Z","timestamp":1569628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006475","name":"Bergens Forskningsstiftelse","doi-asserted-by":"publisher","award":["BFS2017TMT01"],"award-info":[{"award-number":["BFS2017TMT01"]}],"id":[{"id":"10.13039\/501100006475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>The ability to predict the skin sensitization potential of small organic molecules is of high importance to the development and safe application of cosmetics, drugs and pesticides. One of the most widely accepted methods for predicting this hazard is the local lymph node assay (LLNA). The goal of this work was to develop in silico models for the prediction of the skin sensitization potential of small molecules that go beyond the state of the art, with larger LLNA data sets and, most importantly, a robust and intuitive definition of the applicability domain, paired with additional indicators of the reliability of predictions. We explored a large variety of molecular descriptors and fingerprints in combination with random forest and support vector machine classifiers. The most suitable models were tested on holdout data, on which they yielded competitive performance (Matthews correlation coefficients up to 0.52; accuracies up to 0.76; areas under the receiver operating characteristic curves up to 0.83). The most favorable models are available via a public web service that, in addition to predictions, provides assessments of the applicability domain and indicators of the reliability of the individual predictions.<\/jats:p>","DOI":"10.3390\/ijms20194833","type":"journal-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T05:58:33Z","timestamp":1569823113000},"page":"4833","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Skin Doctor: Machine Learning Models for Skin Sensitization Prediction that Provide Estimates and Indicators of Prediction Reliability"],"prefix":"10.3390","volume":"20","author":[{"given":"Anke","family":"Wilm","sequence":"first","affiliation":[{"name":"Center for Bioinformatics, Universit\u00e4t Hamburg, 20146 Hamburg, Germany"},{"name":"HITeC e.V, 22527 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5499-742X","authenticated-orcid":false,"given":"Conrad","family":"Stork","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Universit\u00e4t Hamburg, 20146 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6035-6944","authenticated-orcid":false,"given":"Christoph","family":"Bauer","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Bergen, 5020 Bergen, Norway"},{"name":"Computational Biology Unit (CBU), University of Bergen, 5020 Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5258-3605","authenticated-orcid":false,"given":"Andreas","family":"Schepky","sequence":"additional","affiliation":[{"name":"Front End Innovation, Beiersdorf AG, 20253 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8421-9381","authenticated-orcid":false,"given":"Jochen","family":"K\u00fchnl","sequence":"additional","affiliation":[{"name":"Front End Innovation, Beiersdorf AG, 20253 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2667-5877","authenticated-orcid":false,"given":"Johannes","family":"Kirchmair","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Universit\u00e4t Hamburg, 20146 Hamburg, Germany"},{"name":"Department of Chemistry, University of Bergen, 5020 Bergen, Norway"},{"name":"Computational Biology Unit (CBU), University of Bergen, 5020 Bergen, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,9,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"S238","DOI":"10.1093\/toxsci\/kfq346","article-title":"Chemical allergy: Translating biology into hazard characterization","volume":"120","author":"Kimber","year":"2011","journal-title":"Toxicol. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1111\/j.1600-0536.2007.01220.x","article-title":"The epidemiology of contact allergy in the general population\u2014prevalence and main findings","volume":"57","author":"Thyssen","year":"2007","journal-title":"Contact Dermat."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1111\/j.1396-0296.2004.04032.x","article-title":"Occupational contact dermatitis","volume":"17","author":"Lushniak","year":"2004","journal-title":"Dermatol. Ther."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Anderson, S.E., Siegel, P.D., and Meade, B.J. (2011). The LLNA: A brief review of recent advances and limitations. J. Allergy, 2011.","DOI":"10.1155\/2011\/424203"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.comtox.2018.06.001","article-title":"Principles underpinning the use of new methodologies in the risk assessment of cosmetic ingredients","volume":"7","author":"Dent","year":"2018","journal-title":"Comput. Toxicol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1007\/s00204-012-0867-6","article-title":"Non-animal test methods for predicting skin sensitization potentials","volume":"86","author":"Mehling","year":"2012","journal-title":"Arch. Toxicol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.tiv.2014.10.018","article-title":"Systematic evaluation of non-animal test methods for skin sensitisation safety assessment","volume":"29","author":"Reisinger","year":"2015","journal-title":"Toxicol. In Vitro"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1007\/s00204-016-1842-4","article-title":"State of the art in non-animal approaches for skin sensitization testing: From individual test methods towards testing strategies","volume":"90","author":"Ezendam","year":"2016","journal-title":"Arch. Toxicol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1111\/j.1600-0536.2011.02004_2.x","article-title":"The critical review of methodologies and approaches to assess the inherent skin sensitization potential (skin allergies) of chemicals. Part I","volume":"66","author":"Thyssen","year":"2012","journal-title":"Contact Dermat."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1080\/10408444.2018.1528207","article-title":"Computational approaches for skin sensitization prediction","volume":"48","author":"Wilm","year":"2018","journal-title":"Crit. Rev. Toxicol."},{"key":"ref_11","unstructured":"ECHA (European Chemicals Agency) (2019, July 10). The Use of Alternatives to Testing on Animals for the REACH Regulation, Third Report under Article 117(3) of the REACH Regulation. Available online: https:\/\/echa.europa.eu\/documents\/10162\/13639\/alternatives_test_animals_2017_en.pdf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1080\/10408444.2018.1429386","article-title":"Non-animal methods to predict skin sensitization (II): An assessment of defined approaches","volume":"48","author":"Kleinstreuer","year":"2018","journal-title":"Crit. Rev. Toxicol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1093\/toxsci\/kfy152","article-title":"Machine learning of toxicological big data enables read-across structure activity relationships (RASAR) outperforming animal test reproducibility","volume":"165","author":"Luechtefeld","year":"2018","journal-title":"Toxicol. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1039\/c8tx00051d","article-title":"Big-data and machine learning to revamp computational toxicology and its use in risk assessment","volume":"7","author":"Luechtefeld","year":"2018","journal-title":"Toxicol. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1093\/toxsci\/kfy286","article-title":"Oy vey! A comment on \u201cMachine learning of toxicological big data enables read-across structure activity relationships outperforming animal test reproducibility\u201d","volume":"167","author":"Alves","year":"2019","journal-title":"Toxicol. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1093\/toxsci\/kfy287","article-title":"Missing the difference between big data and artificial intelligence in RASAR versus traditional QSAR","volume":"167","author":"Luechtefeld","year":"2019","journal-title":"Toxicol. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1007\/s00204-019-02420-x","article-title":"Transfer learning for predicting human skin sensitizers","volume":"93","author":"Tung","year":"2019","journal-title":"Arch. Toxicol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.yrtph.2018.03.015","article-title":"Making reliable negative predictions of human skin sensitisation using an in silico fragmentation approach","volume":"95","author":"Chilton","year":"2018","journal-title":"Regul. Toxicol. Pharm."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1021\/acs.jcim.7b00194","article-title":"Pred-Skin: A fast and reliable web application to assess skin sensitization effect of chemicals","volume":"57","author":"Braga","year":"2017","journal-title":"J. Chem. Inf. Model."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1080\/15287394.2019.1616437","article-title":"Quantitative structure\u2013activity and quantitative structure\u2013property relationship approaches as alternative skin sensitization risk assessment methods","volume":"82","author":"Kim","year":"2019","journal-title":"J. Toxicol. Environ. Health"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1080\/1062936X.2019.1615547","article-title":"Idealization of correlations between optimal simplified molecular input-line entry system-based descriptors and skin sensitization","volume":"30","author":"Toropov","year":"2019","journal-title":"SAR QSAR Environ. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.tiv.2019.01.004","article-title":"Prediction of the skin sensitising potential and potency of compounds via mechanism-based binary and ternary classification models","volume":"59","author":"Di","year":"2019","journal-title":"Toxicol. In Vitro"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.taap.2014.12.014","article-title":"Predicting chemically-induced skin reactions. Part I: QSAR models of skin sensitization and their application to identify potentially hazardous compounds","volume":"284","author":"Alves","year":"2015","journal-title":"Toxicol. Appl. Pharmacol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s10822-011-9472-7","article-title":"Fragment-based prediction of skin sensitization using recursive partitioning","volume":"25","author":"Lu","year":"2011","journal-title":"J. Comput. Aided Mol. Des."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"S5","DOI":"10.1186\/1752-153X-4-S1-S5","article-title":"Global QSAR models of skin sensitisers for regulatory purposes","volume":"4","author":"Chaudhry","year":"2010","journal-title":"Chem. Cent. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1021\/tx4000655","article-title":"Predicting skin sensitization potency for Michael acceptors in the LLNA using quantum mechanics calculations","volume":"26","author":"Enoch","year":"2013","journal-title":"Chem. Res. Toxicol."},{"key":"ref_27","first-page":"379","article-title":"LLNA variability: An essential ingredient for a comprehensive assessment of non-animal skin sensitization test methods and strategies","volume":"32","author":"Hoffmann","year":"2015","journal-title":"ALTEX"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.1021\/acssuschemeng.7b04220","article-title":"A perspective and a new integrated computational strategy for skin sensitization assessment","volume":"6","author":"Alves","year":"2018","journal-title":"ACS Sustain. Chem. Eng."},{"key":"ref_29","unstructured":"Apt Systemst Ltd. (2019, July 10). Aptsys.net OASIS. QSAR Toolbox 4.3. Available online: http:\/\/oasis-lmc.org\/products\/software\/toolbox.aspx."},{"key":"ref_30","unstructured":"(2019, April 26). Chembench|Home. Available online: https:\/\/chembench.mml.unc.edu."},{"key":"ref_31","unstructured":"(2019, April 26). CosIng\u2014Cosmetics\u2014GROWTH\u2014European Commission. Available online: http:\/\/ec.europa.eu\/growth\/tools-databases\/cosing\/index.cfm?fuseaction=search.simple."},{"key":"ref_32","unstructured":"(2019, May 07). DrugBank Version 5.1.2. Available online: https:\/\/www.drugbank.ca."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: A major update to the DrugBank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref_34","unstructured":"(2019, February 25). EU Pesticides Database\u2014European Commission. Available online: http:\/\/ec.europa.eu\/food\/plant\/pesticides\/eu-pesticides-database\/public\/?event=activesubstance.selection&language=EN."},{"key":"ref_35","unstructured":"(2019, February 25). Chemical Identifier Resolver, Available online: https:\/\/cactus.nci.nih.gov\/chemical\/structure."},{"key":"ref_36","unstructured":"(2019, June 12). Chemical Computing Group Molecular Operating Environment (MOE)|MOEsaic|PSILO. Available online: https:\/\/www.chemcomp.com\/Products.htm."},{"key":"ref_37","unstructured":"(2019, May 10). PaDEL-Descriptor. Available online: http:\/\/www.yapcwsoft.com\/dd\/padeldescriptor\/."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1002\/jcc.21707","article-title":"PaDEL-Descriptor: An open source software to calculate molecular descriptors and fingerprints","volume":"32","author":"Yap","year":"2011","journal-title":"J. Comput. Chem."},{"key":"ref_39","unstructured":"Landrum, G. (2019, April 26). RDKit. Available online: http:\/\/www.rdkit.org."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","article-title":"Comparison of the predicted and observed secondary structure of T4 phage lysozyme","volume":"405","author":"Matthews","year":"1975","journal-title":"Biochim. Biophys. Acta Protein Struct."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Stork, C., Embruch, G., \u0160\u00edcho, M., de Bruyn Kops, C., Chen, Y., Svozil, D., and Kirchmair, J. (2019). NERDD: A web portal providing access to in silico tools for drug discovery. Bioinformatics.","DOI":"10.1093\/bioinformatics\/btz695"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1002\/cmdc.201700673","article-title":"Hit Dexter: A machine-learning model for the prediction of frequent hitters","volume":"13","author":"Stork","year":"2018","journal-title":"Chem. Med. Chem."},{"key":"ref_43","unstructured":"MolVs (2019, April 26). MolVs Version 0.1.1. Available online: https:\/\/github.com\/mcs07\/MolVS."},{"key":"ref_44","unstructured":"(2019, May 10). Scikit-Learn: Machine Learning in Python\u2014Scikit-Learn 0.21.0 Documentation. Available online: https:\/\/scikit-learn.org\/stable\/."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/20\/19\/4833\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:25:37Z","timestamp":1760189137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/20\/19\/4833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,28]]},"references-count":44,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2019,10]]}},"alternative-id":["ijms20194833"],"URL":"https:\/\/doi.org\/10.3390\/ijms20194833","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,28]]}}}