{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T06:46:11Z","timestamp":1792565171883,"version":"4.5.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Food and Chemical Toxicology"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.fct.2026.116422","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T16:05:25Z","timestamp":1791216325000},"page":"116422","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Artificial intelligence and machine learning in fragrance safety assessment: Current applications and future opportunities at RIFM"],"prefix":"10.1016","volume":"218","author":[{"given":"Yax","family":"Thakkar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danielle","family":"Botelho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne Marie","family":"Api","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.fct.2026.116422_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ces.2023.119086","article-title":"Machine learning methods for endocrine disrupting potential identification based on single-cell data","volume":"281","author":"Aghayev","year":"2023","journal-title":"Chem. Eng. Sci."},{"issue":"1","key":"10.1016\/j.fct.2026.116422_bib2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1006\/faat.1995.1144","article-title":"A multiple-path model of particle deposition in the rat lung","volume":"28","author":"Anjilvel","year":"1995","journal-title":"Fund. Appl. Toxicol."},{"issue":"9","key":"10.1016\/j.fct.2026.116422_bib3","doi-asserted-by":"crossref","first-page":"1420","DOI":"10.1021\/tx050075m","article-title":"Skin sensitization: reaction mechanistic applicability domains for structure\u2013activity relationships","volume":"18","author":"Aptula","year":"2005","journal-title":"Chem. Res. Toxicol."},{"issue":"5\u20136","key":"10.1016\/j.fct.2026.116422_bib4","article-title":"Predictive modeling for carcinogenicity using random forest-based QSAR","volume":"37","author":"Banerjee","year":"2018","journal-title":"Mol. Inf."},{"key":"10.1016\/j.fct.2026.116422_bib44","series-title":"Methods in Molecular Biology","isbn-type":"print","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-1-4939-7899-1_5","article-title":"Machine Learning Methods in Computational Toxicology","author":"Baskin","year":"2018","ISBN":"https:\/\/id.crossref.org\/isbn\/9781493978984"},{"key":"10.1016\/j.fct.2026.116422_bib5","first-page":"312","article-title":"Computational prediction of phototoxicity: current tools and future directions","volume":"98","author":"B\u00f6hm","year":"2024","journal-title":"Arch. Toxicol."},{"issue":"11","key":"10.1016\/j.fct.2026.116422_bib6","doi-asserted-by":"crossref","first-page":"3099","DOI":"10.1021\/ci300367a","article-title":"admetSAR: a comprehensive source and free tool for assessment of chemical ADMET properties","volume":"52","author":"Cheng","year":"2013","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.fct.2026.116422_bib7","doi-asserted-by":"crossref","DOI":"10.3389\/ftox.2022.981928","article-title":"Novel machine learning models to predict endocrine disruption activity for high-throughput chemical screening","volume":"4","author":"Collins","year":"2022","journal-title":"Frontiers in Toxicology"},{"key":"10.1016\/j.fct.2026.116422_bib9","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.yrtph.2017.05.017","article-title":"Integrating habits and practices data for soaps, cosmetics and air care products into an existing aggregate exposure model","volume":"88","author":"Comiskey","year":"2017","journal-title":"Regul. Toxicol. Pharmacol."},{"issue":"1","key":"10.1016\/j.fct.2026.116422_bib8","first-page":"99","article-title":"Integrating habits and practices data for soaps, cosmetics, and air care products into an aggregate exposure model","volume":"73","author":"Comiskey","year":"2015","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"10.1016\/j.fct.2026.116422_bib10","doi-asserted-by":"crossref","DOI":"10.1016\/j.comtox.2024.100338","article-title":"The predictivity of QSARs for toxicity: recommendations for improving model performance","volume":"33","author":"Cronin","year":"2025","journal-title":"Comput. Toxicol."},{"key":"10.1016\/j.fct.2026.116422_bib42","doi-asserted-by":"crossref","first-page":"109533","DOI":"10.1016\/j.cbi.2021.109533","article-title":"Application of artificial intelligence for detection of chemico-biological interactions associated with oxidative stress and DNA damage","volume":"345","author":"Davidovic","year":"2021","journal-title":"Chem. Biol. Interact."},{"key":"10.1016\/j.fct.2026.116422_bib12","article-title":"ToxMCP: guardrailed, auditable agentic workflows for computational toxicology via the model context protocol","author":"Djidrovski","year":"2026","journal-title":"bioRxiv"},{"key":"10.1016\/j.fct.2026.116422_bib13","article-title":"FAIR models in toxicology: principles, implementation and regulatory relevance","volume":"42","author":"Exner","year":"2025","journal-title":"ALTEX \u2014 Alternatives to Animal Experimentation"},{"key":"10.1016\/j.fct.2026.116422_bib14","series-title":"Steroids","author":"Fieser","year":"1959"},{"issue":"1","key":"10.1016\/j.fct.2026.116422_bib15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/minf.201501008","article-title":"Deep learning in drug discovery","volume":"35","author":"Gawehn","year":"2016","journal-title":"Mol. Inf."},{"key":"10.1016\/j.fct.2026.116422_bib16","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1021\/acs.chemrestox.2c00383","article-title":"The good, the bad, and the perplexing: structural alerts and read-across for predicting skin sensitization using human data","volume":"36","author":"Golden","year":"2023","journal-title":"Chem. Res. Toxicol."},{"key":"10.1016\/j.fct.2026.116422_bib17","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2023.1269932","article-title":"Artificial intelligence as the new frontier in chemical risk assessment","volume":"6","author":"Hartung","year":"2023","journal-title":"Front. Artif. Intell."},{"key":"10.1016\/j.fct.2026.116422_bib18","doi-asserted-by":"crossref","first-page":"85","DOI":"10.3389\/fenvs.2015.00085","article-title":"Tox21Challenge to build predictive models of nuclear receptor and stress response pathways as mediated by exposure to environmental chemicals and drugs","volume":"3","author":"Huang","year":"2016","journal-title":"Front. Environ. Sci."},{"key":"10.1016\/j.fct.2026.116422_bib19","first-page":"1","article-title":"The first eNanoMapper ontology-based data model and database for engineered nanomaterials","volume":"12","author":"Jeliazkova","year":"2021","journal-title":"Beilstein J. Nanotechnol."},{"key":"10.1016\/j.fct.2026.116422_bib20","doi-asserted-by":"crossref","DOI":"10.1016\/j.yrtph.2024.105752","article-title":"Incorporating Singaporean habits and practices for cosmetics and personal care products into a global consumer aggregate exposure model","volume":"156","author":"Juraimi","year":"2025","journal-title":"Regul. Toxicol. Pharmacol."},{"issue":"6","key":"10.1016\/j.fct.2026.116422_bib21","first-page":"941","article-title":"Exploratory data analysis by the self-organizing map: structures of welfare and poverty in the world and in Finland","volume":"19","author":"Kaski","year":"1996","journal-title":"Neural Netw."},{"issue":"13","key":"10.1016\/j.fct.2026.116422_bib23","first-page":"2424","article-title":"Classifying and segmenting microscopy images with deep neural networks","volume":"33","author":"Kraus","year":"2017","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/j.fct.2026.116422_bib45","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1093\/toxsci\/kfac075","article-title":"Machine Learning and Artificial Intelligence in Toxicological Sciences","volume":"189","author":"Lin","year":"2022","journal-title":"Toxicol. Sci."},{"key":"10.1016\/j.fct.2026.116422_bib24","doi-asserted-by":"crossref","DOI":"10.1111\/cts.70205","article-title":"Large language models and their applications in drug discovery and development: a primer","volume":"18","author":"Lu","year":"2025","journal-title":"Clin. Transl. Sci."},{"issue":"7","key":"10.1016\/j.fct.2026.116422_bib25","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1289\/ehp.1510267","article-title":"CERAPP: collaborative estrogen receptor activity prediction project","volume":"124","author":"Mansouri","year":"2016","journal-title":"Environ. Health Perspect."},{"key":"10.1016\/j.fct.2026.116422_bib26","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jaerosci.2016.01.018","article-title":"Improvements and additions to the multiple path particle dosimetry model","volume":"99","author":"Miller","year":"2016","journal-title":"J. Aerosol Sci."},{"key":"10.1016\/j.fct.2026.116422_bib27","article-title":"Test no. 498: in vitro phototoxicity \u2014 reconstructed human epidermis phototoxicity test method","year":"2019","journal-title":"OECD Guidel. Test. Chem."},{"key":"10.1016\/j.fct.2026.116422_bib28","article-title":"Practical guidance for implementing FAIR principles in computational toxicology model repositories","volume":"42","author":"Pawar","year":"2025","journal-title":"ALTEX \u2014 Alternatives to Animal Experimentation"},{"key":"10.1016\/j.fct.2026.116422_bib29","doi-asserted-by":"crossref","DOI":"10.1186\/s13321-018-0316-5","article-title":"JPlogP: an improved logP predictor trained using predicted data","author":"Plante","year":"2018","journal-title":"J. Cheminf."},{"key":"10.1016\/j.fct.2026.116422_bib43","series-title":"Ethics of Artificial Intelligence","isbn-type":"print","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1093\/oso\/9780190905033.003.0012","article-title":"Artificial Intelligence","author":"Russell","year":"2020","ISBN":"https:\/\/id.crossref.org\/isbn\/0190905034"},{"key":"10.1016\/j.fct.2026.116422_bib32","doi-asserted-by":"crossref","DOI":"10.1016\/j.yrtph.2023.105545","article-title":"Corrigendum to \"Use of an aggregate exposure model to estimate consumer exposure to fragrance ingredients in personal care and cosmetic products\"","volume":"147","author":"Safford","year":"2024","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"10.1016\/j.fct.2026.116422_bib31","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.yrtph.2017.02.021","article-title":"Application of the expanded creme RIFM consumer exposure model to fragrance ingredients in cosmetic, personal care and air care products","volume":"86","author":"Safford","year":"2017","journal-title":"Regul. Toxicol. Pharmacol."},{"issue":"3","key":"10.1016\/j.fct.2026.116422_bib30","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1016\/j.yrtph.2015.05.017","article-title":"Use of an aggregate exposure model to estimate consumer exposure to fragrance ingredients in personal care and cosmetic products","volume":"72","author":"Safford","year":"2015","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"10.1016\/j.fct.2026.116422_bib33","series-title":"Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World","author":"Seal","year":"2025"},{"issue":"9","key":"10.1016\/j.fct.2026.116422_bib34","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1021\/ci800151m","article-title":"Critical assessment of QSAR models of environmental toxicity against tetrahymena pyriformis: focusing on applicability domain and overfitting by variable selection","volume":"48","author":"Tetko","year":"2008","journal-title":"J. Chem. Inf. Model."},{"issue":"7","key":"10.1016\/j.fct.2026.116422_bib35","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1289\/ehp.1205784","article-title":"Improving the human hazard characterization of chemicals: a Tox21 update","volume":"121","author":"Tice","year":"2013","journal-title":"Environ. Health Perspect."},{"key":"10.1016\/j.fct.2026.116422_bib36","series-title":"Molecular Descriptors for Chemoinformatics","author":"Todeschini","year":"2009"},{"key":"10.1016\/j.fct.2026.116422_bib38","series-title":"Artificial Intelligence (AI) Program for Toxicology (AI4TOX)","year":"2024"},{"key":"10.1016\/j.fct.2026.116422_bib37","series-title":"EPI suite\u2122 (estimation programs interface) \u2013 estimating chemicals' physical\/chemical properties and environmental fate","year":"2026"},{"key":"10.1016\/j.fct.2026.116422_bib39","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR guiding principles for scientific data management and stewardship","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci. Data"},{"issue":"4","key":"10.1016\/j.fct.2026.116422_bib40","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1021\/ja01849a066","article-title":"Structure and the absorption spectra of \u03b1,\u03b2-unsaturated ketones","volume":"63","author":"Woodward","year":"1941","journal-title":"J. Am. Chem. Soc."},{"key":"10.1016\/j.fct.2026.116422_bib41","first-page":"111","article-title":"LD50 toxicity prediction using backpropagation neural networks and molecular descriptors","volume":"168","author":"Zhang","year":"2017","journal-title":"Chemosphere"}],"container-title":["Food and Chemical Toxicology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0278691526004977?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0278691526004977?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T06:19:57Z","timestamp":1792563597000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0278691526004977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":43,"alternative-id":["S0278691526004977"],"URL":"https:\/\/doi.org\/10.1016\/j.fct.2026.116422","relation":{},"ISSN":["0278-6915"],"issn-type":[{"value":"0278-6915","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Artificial intelligence and machine learning in fragrance safety assessment: Current applications and future opportunities at RIFM","name":"articletitle","label":"Article Title"},{"value":"Food and Chemical Toxicology","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.fct.2026.116422","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"116422"}}