{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:50:49Z","timestamp":1780710649692,"version":"3.54.1"},"reference-count":28,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T00:00:00Z","timestamp":1658275200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100019266","name":"Korea Medical Device Development Fund","doi-asserted-by":"publisher","award":["1711138228, RS\u20102020\u2010KD000123"],"award-info":[{"award-number":["1711138228, RS\u20102020\u2010KD000123"]}],"id":[{"id":"10.13039\/100019266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019266","name":"Korea Medical Device Development Fund","doi-asserted-by":"publisher","award":["1711139088, RS\u20102021\u2010KD000006"],"award-info":[{"award-number":["1711139088, RS\u20102021\u2010KD000006"]}],"id":[{"id":"10.13039\/100019266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["analyticalsciencejournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J of Applied Toxicology"],"published-print":{"date-parts":[[2022,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Many defined approaches (DAs) for skin sensitization assessment based on the adverse outcome pathway (AOP) have been developed to replace animal testing because the European Union has banned animal testing for cosmetic ingredients. Several DAs have demonstrated that machine learning models are beneficial. In this study, we have developed an ensemble prediction model utilizing the graph convolutional network (GCN) and machine learning approach to assess skin sensitization. The model integrates in silico parameters and data from alternatives to animal testing of well\u2010defined AOP to improve DA predictivity. Multiple ensemble models were created using the probability produced by the GCN with six physicochemical properties, direct peptide reactivity assay, KeratinoSens\u2122, and human cell line activation test (h\u2010CLAT), using a multilayer perceptron approach. Models were evaluated by predicting the testing set's human hazard class and three potency classes (strong, weak, and non\u2010sensitizer). When the GCN feature was used, 11 models out of 16 candidates showed the same or improved accuracy in the testing set. The ensemble model with the feature set of GCN, KeratinoSens\u2122, and h\u2010CLAT produced the best results with an accuracy of 88% for assessing human hazards. The best three\u2010class potency model was created with the feature set of GCN and all three assays, resulting in 64% accuracy. These results from the ensemble approach indicate that the addition of the GCN feature could provide an improved predictivity of skin sensitization hazard and potency assessment.<\/jats:p>","DOI":"10.1002\/jat.4361","type":"journal-article","created":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T08:38:54Z","timestamp":1657096734000},"page":"1832-1842","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["A development of a graph\u2010based ensemble machine learning model for skin sensitization hazard and potency assessment"],"prefix":"10.1002","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0127-6490","authenticated-orcid":false,"given":"Byoungjun","family":"Jeon","sequence":"first","affiliation":[{"name":"Interdisciplinary Program in Bioengineering, Graduate School Seoul National University  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min Hyuk","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering Seoul National University Hospital  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae Hyun","family":"Choi","sequence":"additional","affiliation":[{"name":"Thenevus Plastic Surgery Clinic  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeong\u2010Cheol","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Experimental Animal Research, Biomedical Research Institute Seoul National University Hospital  Seoul South Korea"},{"name":"Graduate School of Translational Medicine Seoul National University College of Medicine  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-849X","authenticated-orcid":false,"given":"Sungwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering Seoul National University College of Medicine  Seoul South Korea"},{"name":"Institute of Bioengineering Seoul National University  Seoul South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,7,20]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/cod.13119"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci9803381"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2018.01.039"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3558"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3105"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/10408444.2018.1429385"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00204-015-1634-2"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00479-8"},{"key":"e_1_2_8_10_1","volume-title":"Concepts and applications of molecular similarity","author":"Johnson M. A.","year":"1990"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/10408444.2018.1429386"},{"key":"e_1_2_8_12_1","unstructured":"OECD. (2010).Test No. 429: Skin Sensitisation."},{"key":"e_1_2_8_13_1","unstructured":"OECD. (2018a).Test No. 442D:In Vitro Skin Sensitisation."},{"key":"e_1_2_8_14_1","unstructured":"OECD. (2018b).Test No. 442E:In Vitro Skin Sensitisation."},{"key":"e_1_2_8_15_1","unstructured":"OECD. (2021a).Guideline No. 497: Defined Approaches on Skin Sensitisation."},{"key":"e_1_2_8_16_1","unstructured":"OECD. (2021b).Test No. 442C:In Chemico Skin Sensitisation."},{"key":"e_1_2_8_17_1","first-page":"2825","article-title":"Scikit\u2010learn: Machine learning in python","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_2_8_18_1","unstructured":"Ramsundar B. Eastman P. Walters P. &Pande V.(2019).Deep learning for the life sciences: applying deep learning to genomics microscopy drug discovery and more: O'Reilly Media."},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yrtph.2018.04.022"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-021-00271-4"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3281"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3572"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3366"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3127"},{"key":"e_1_2_8_25_1","first-page":"59","article-title":"Regulation (EC) no. 1223\/2009 of the European parliament and of the council","volume":"342","author":"UNION, P","year":"2009","journal-title":"Official Journal of the European Union"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.11.009"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/jat.3424"}],"container-title":["Journal of Applied Toxicology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jat.4361","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jat.4361","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jat.4361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T15:42:53Z","timestamp":1760542973000},"score":1,"resource":{"primary":{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/10.1002\/jat.4361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,20]]},"references-count":28,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["10.1002\/jat.4361"],"URL":"https:\/\/doi.org\/10.1002\/jat.4361","archive":["Portico"],"relation":{},"ISSN":["0260-437X","1099-1263"],"issn-type":[{"value":"0260-437X","type":"print"},{"value":"1099-1263","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,20]]},"assertion":[{"value":"2022-04-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}