{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T22:48:21Z","timestamp":1785710901244,"version":"3.56.0"},"reference-count":93,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Toxicol."],"abstract":"<jats:p>Computational models for skin sensitization prediction face critical challenges in handling activity cliffs, where structurally similar compounds exhibit different biological activities, limiting their regulatory applicability. This study systematically compared Random Forest (RF) and K\u2010Nearest Neighbors (KNN) models using five molecular fingerprint approaches integrated with structural alerts and physicochemical properties. Models were developed using 1174 chemicals and evaluated across progressive feature integration levels: fingerprints alone, fingerprints with structural alerts, and fully integrated models. Performance was assessed using standard classification metrics and chemical similarity analysis for compounds with \u226570% Tanimoto similarity but discordant experimental outcomes. RF consistently outperformed KNN across all fingerprint approaches, achieving 81% balanced accuracy compared to (74%) in fully integrated models on the test set. Critically, RF demonstrated superior handling of activity cliffs compared to KNN. Substructure\u2010based fingerprints (Avalon, PubChem and MACCS) consistently outperformed hash\u2010based approaches (Morgan, Atom Pair), with Avalon showing optimal performance across metrics. SHAP interpretability analysis identified vapor pressure (VP) as the most consistently important physicochemical predictor and identified key reactive structural features aligning with known sensitization mechanisms. These findings provide evidence\u2010based guidance for model selection when developing tools for skin sensitization and establish a systematic methodology for evaluating activity cliff performance that can be applied across other toxicological endpoints.<\/jats:p>","DOI":"10.3389\/ftox.2026.1739746","type":"journal-article","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T22:10:16Z","timestamp":1785708616000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing skin sensitization prediction across activity cliffs: a comparative analysis of K-nearest neighbours vs random Forest"],"prefix":"10.3389","volume":"8","author":[{"given":"Daniel C.","family":"Ukaegbu","sequence":"first","affiliation":[{"name":"Center for Alternatives to Animal Testing (CAAT), Johns Hopkins Bloomberg School of Public Health","place":["Baltimore, MD, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karolina","family":"Kopa\u0144ska","sequence":"additional","affiliation":[{"name":"Center for Alternatives to Animal Testing (CAAT), Johns Hopkins Bloomberg School of Public Health","place":["Baltimore, MD, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Ranslow","sequence":"additional","affiliation":[{"name":"Consortium for Environmental Risk Management (CERM)","place":["Hallowell, ME, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandra","family":"Maertens","sequence":"additional","affiliation":[{"name":"Center for Alternatives to Animal Testing (CAAT), Johns Hopkins Bloomberg School of Public Health","place":["Baltimore, MD, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-031-54513-9_9","article-title":"The economic impact of atopic dermatitis","volume-title":"Management of Atopic Dermatitis: Methods and Challenges","author":"Adamson","year":"2024"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1080\/07391102.2019.1633408","article-title":"Models for skin and brain penetration of major components from essential oils used in aromatherapy for dementia patients","volume":"38","author":"Agatonovic-Kustrin","year":"2020","journal-title":"J. Biomol. Struct. Dyn."},{"key":"B3","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.tiv.2015.09.028","article-title":"Prospective multicentre study of the U-SENS test method for skin sensitization testing","volume":"30","author":"Al\u00e9p\u00e9e","year":"2015","journal-title":"Toxicol. Vitro"},{"key":"B4","doi-asserted-by":"publisher","first-page":"4348","DOI":"10.1039\/C6GC01492E","article-title":"Alarms about structural alerts","volume":"18","author":"Alves","year":"2016","journal-title":"Green Chem."},{"key":"B5","doi-asserted-by":"publisher","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. and Eng."},{"key":"B6","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/j.tiv.2005.10.012","article-title":"Development of an in vitro skin sensitization test using human cell lines: the human cell line activation test (h-CLAT). I. Optimization of the h-CLAT protocol","volume":"20","author":"Ashikaga","year":"2006","journal-title":"Toxicol. Vitro An Int. J. Publ. Assoc. BIBRA"},{"key":"B7","first-page":"1","article-title":"Popularize artificial intelligence","volume":"1107","author":"Baldoni","year":"2013","journal-title":"CEUR Workshop Proc."},{"key":"B8","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.aca.2007.10.029","article-title":"Classification of multiway analytical data based on MOLMAP approach","volume":"605","author":"Ballabio","year":"2007","journal-title":"Anal. Chim. Acta"},{"key":"B93","doi-asserted-by":"publisher","DOI":"10.1515\/9781400874668","author":"Bellman","year":"1961","journal-title":"A guided tour"},{"key":"B92","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/3-540-49257-7_15","article-title":"When Is \u201cNearest Neighbor\u201d Meaningful?","author":"Beyer","year":"1999","journal-title":"Database Theory\u2014ICDT\u201999"},{"key":"B9","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1021\/acs.chemrestox.0c00186","article-title":"Pred-skin: a web portal for accurate prediction of human skin sensitizers","volume":"34","author":"Borba","year":"2021","journal-title":"Chem. Res. Toxicol."},{"key":"B10","first-page":"747","article-title":"Accounting for variance in machine learning benchmarks","volume-title":"Proceedings of Machine Learning and Systems","author":"Bouthillier","year":"2021"},{"key":"B11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"B12","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1021\/ci00046a002","article-title":"Atom pairs as molecular features in structure-activity studies: definition and applications","volume":"25","author":"Carhart","year":"1985","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"S5","DOI":"10.1186\/1752-153X-4-S1-S5","article-title":"Global QSAR models of skin sensitisers for regulatory purposes","author":"Chaudhry","year":"2010","journal-title":"Chem. Central J."},{"key":"B89","doi-asserted-by":"publisher","first-page":"11659","DOI":"10.3390\/ijms160511659","article-title":"Acute toxicity-supported chronic toxicity prediction: a k-nearest neighbor coupled read-across strategy","volume":"16","author":"Chavan","year":"2015","journal-title":"Int. J. Mol. Sci."},{"key":"B14","doi-asserted-by":"publisher","first-page":"4977","DOI":"10.1021\/jm4004285","article-title":"QSAR modeling: where have you been? Where are you going to?","volume":"57","author":"Cherkasov","year":"2014","journal-title":"J. Med. Chem."},{"key":"B15","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1093\/forestry\/cpaa034","article-title":"Comparison of linear regression, k-nearest neighbour and random forest methods in airborne laser-scanning-based prediction of growing stock","volume":"94","author":"Cosenza","year":"2021","journal-title":"For. An Int. J. For. Res."},{"key":"B16","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"B17","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s13321-023-00708-w","article-title":"Exploring QSAR models for activity-cliff prediction","volume":"15","author":"Dablander","year":"2023","journal-title":"J. Cheminformatics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4640","DOI":"10.3390\/molecules28124640","article-title":"Predictions of the biological effects of several acyclic monoterpenes as chemical constituents of essential oils extracted from plants","volume":"28","author":"Dascalu","year":"2023","journal-title":"Molecules"},{"key":"B19","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1021\/tx300465h","article-title":"Skin sensitization of epoxyaldehydes: importance of conjugation","volume":"26","author":"Delaine","year":"2013","journal-title":"Chem. Res. Toxicol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.1021\/tx500297d","article-title":"Epoxyalcohols: bioactivation and conjugation required for skin sensitization","volume":"27","author":"Delaine","year":"2014","journal-title":"Chem. Res. Toxicol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.chemolab.2017.10.006","article-title":"ChemBCPP: a freely available web server for calculating commonly used physicochemical properties","volume":"171","author":"Dong","year":"2017","journal-title":"Chemom. Intelligent Laboratory Syst."},{"key":"B22","article-title":"Understanding CLP","year":"2025","journal-title":"ECHA"},{"key":"B23","doi-asserted-by":"publisher","first-page":"783","DOI":"10.3109\/10408444.2011.598141","article-title":"A review of the electrophilic reaction chemistry involved in covalent protein binding relevant to toxicity","volume":"41","author":"Enoch","year":"2011","journal-title":"Crit. Rev. Toxicol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.rse.2014.07.028","article-title":"Importance of sample size, data type and prediction method for remote sensing-based estimations of aboveground forest biomass","volume":"154","author":"Fassnacht","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1924","DOI":"10.1021\/ci050413p","article-title":"QSAR \u2212 how good is it in practice? Comparison of descriptor sets on an unbiased cross section of corporate data sets","volume":"46","author":"Gedeck","year":"2006","journal-title":"J. Chem. Inf. Model."},{"key":"B26","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1053\/ac.2000.3191","article-title":"A skin sensitization risk assessment approach for evaluation of new ingredients and products","volume":"11","author":"Gerberick","year":"2000","journal-title":"Official J. Am. Contact Dermat. Soc."},{"key":"B27","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1111\/j.0105-1873.2004.00290.x","article-title":"A chemical dataset for evaluation of alternative approaches to skin-sensitization testing","volume":"50","author":"Gerberick","year":"2004","journal-title":"Contact Dermat."},{"key":"B28","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1111\/cod.13167","article-title":"Skin sensitization: uncertainties, challenges, and opportunities for improved risk assessment","volume":"80","author":"Gilmour","year":"2019","journal-title":"Contact Dermat."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/ci400572x","article-title":"Data set modelability by QSAR","volume":"54","author":"Golbraikh","year":"2014","journal-title":"J. Chem. Inf. Model."},{"key":"B30","doi-asserted-by":"publisher","first-page":"33","DOI":"10.14573\/altex.1911261","article-title":"Evaluation of the global performance of eight in silico skin sensitization models using human data","volume":"38","author":"Golden","year":"2021","journal-title":"ALTEX"},{"key":"B31","doi-asserted-by":"publisher","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":"B32","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.istruc.2022.10.004","article-title":"Bias-variance tradeoff in machine learning: theoretical formulation and implications to structural engineering applications","volume":"46","author":"Guan","year":"2022","journal-title":"Structures"},{"key":"B33","doi-asserted-by":"publisher","first-page":"10","DOI":"10.14573\/altex.2008.1.3","article-title":"Food for thought. On animal tests","volume":"25","author":"Hartung","year":"2008","journal-title":"Altern. Animal Exp."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.2-199.v1","article-title":"Advancing the activity cliff concept [version 1; peer review: 3 approved]","volume":"2","author":"Hu","year":"2013","journal-title":"F1000Research"},{"key":"B35","doi-asserted-by":"publisher","first-page":"105690","DOI":"10.1016\/j.tiv.2023.105690","article-title":"Prediction of skin sensitization using machine learning","volume":"93","author":"Im","year":"2023","journal-title":"Toxicol. Vitro"},{"key":"B36","doi-asserted-by":"publisher","first-page":"3797536","DOI":"10.1155\/2019\/3797536","article-title":"Impact of allergic contact dermatitis on the quality of life and work productivity","volume":"2019","author":"Kalboussi","year":"2019","journal-title":"Dermatology Res. Pract."},{"key":"B37","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1021\/tx7002239","article-title":"Allergic contact dermatitis\u2013Formation, structural requirements, and reactivity of skin sensitizers","volume":"21","author":"Karlberg","year":"2008","journal-title":"Chem. Res. Toxicol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1452065","DOI":"10.3389\/ftox.2024.1452065","article-title":"Fulfilling the criteria for CLP classification: the implications for substances under the EU chemicals legislation","volume":"6","author":"K\u00e4ttstr\u00f6m","year":"2024","journal-title":"Front. Toxicol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s13321-016-0163-1","article-title":"Similar compounds versus similar conformers: complementarity between PubChem 2-D and 3-D neighboring sets","volume":"8","author":"Kim","year":"2016","journal-title":"J. Cheminformatics"},{"key":"B40","doi-asserted-by":"publisher","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":"B41","doi-asserted-by":"publisher","first-page":"3671","DOI":"10.3390\/molecules26123671","article-title":"K-Nearest neighbor and random forest-based prediction of putative tyrosinase inhibitory peptides of Abalone Haliotis diversicolor","volume":"26","author":"Kongsompong","year":"2021","journal-title":"Mol. Basel, Switz."},{"key":"B42","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1016\/j.csbj.2025.08.001","article-title":"SbD4Skin by EosCloud: integrating multi-view molecular representation for predicting skin sensitization, irritation, and acute dermal toxicity","volume":"29","author":"Koutroumpa","year":"2025","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B43","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s13321-021-00506-2","article-title":"Analysis of the effects of related fingerprints on molecular similarity using an eigenvalue entropy approach","volume":"13","author":"Kuwahara","year":"2021","journal-title":"J. Cheminformatics"},{"key":"B44","doi-asserted-by":"publisher","first-page":"17304","DOI":"10.1038\/s41598-021-96812-8","article-title":"Evolutionary design of molecules based on deep learning and a genetic algorithm","volume":"11","author":"Kwon","year":"2021","journal-title":"Sci. Rep."},{"key":"B45","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1111\/j.1468-2494.2011.00646.x","article-title":"The influence of alkane chain length on the skin irritation potential of 1,2-alkanediols","volume":"33","author":"Lee","year":"2011","journal-title":"Int. J. Cosmet. Sci."},{"key":"B46","volume-title":"Growth Vs. Diversity: A Time-Evolution Analysis of the Chemical Space","author":"Lopez Perez","year":"2025"},{"key":"B47","doi-asserted-by":"publisher","first-page":"P26","DOI":"10.1186\/1758-2946-4-S1-P26","article-title":"A large scale classification of molecular fingerprints for the chemical space representation and SAR analysis","volume":"4","author":"L\u00f3pez-Vallejo","year":"2012","journal-title":"J. Cheminformatics"},{"key":"B48","doi-asserted-by":"publisher","first-page":"459","DOI":"10.14573\/altex.1710141","article-title":"Computational approaches to chemical hazard assessment","volume":"34","author":"Luechtefeld","year":"2017","journal-title":"ALTEX - Altern. Animal Exp."},{"key":"B49","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1002\/jat.3172","article-title":"Probabilistic hazard assessment for skin sensitization potency by dose-response modeling using feature elimination instead of quantitative structure-activity relationships","volume":"35","author":"Luechtefeld","year":"2015","journal-title":"J. Appl. Toxicol. JAT"},{"key":"B50","doi-asserted-by":"publisher","first-page":"111","DOI":"10.14573\/altex.1510054","article-title":"Analysis of public oral toxicity data from REACH registrations 2008-2014","volume":"33","author":"Luechtefeld","year":"2016","journal-title":"ALTEX"},{"key":"B51","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"B52","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1038\/jid.1969.42","article-title":"The identification of contact allergens by animal assay. The Guinea pig maximization test","volume":"52","author":"Magnusson","year":"1969","journal-title":"J. Investigative Dermatology"},{"key":"B53","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s13321-018-0263-1","article-title":"OPERA models for predicting physicochemical properties and environmental fate endpoints","volume":"10","author":"Mansouri","year":"2018","journal-title":"J. Cheminformatics"},{"key":"B54","volume-title":"Machine Learning: An Algorithmic Perspective","author":"Marsland","year":"2009"},{"key":"B55","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.yrtph.2018.11.002","article-title":"Molecular fingerprint-derived similarity measures for toxicological read-across: recommendations for optimal use","volume":"101","author":"Mellor","year":"2019","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"B56","doi-asserted-by":"crossref","first-page":"0","DOI":"10.1039\/9781849737920-00265","article-title":"Integrated approaches to safety testing: general principles and skin sensitization as test case","volume-title":"Reducing, Refining and Replacing the Use of Animals in Toxicity Testing","author":"Natsch","year":"2013"},{"key":"B57","doi-asserted-by":"publisher","first-page":"636","DOI":"10.14573\/altex.2201141","article-title":"Integrated skin sensitization assessment based on OECD methods (I): deriving a point of departure for risk assessment","volume":"39","author":"Natsch","year":"2022","journal-title":"ALTEX"},{"key":"B58","article-title":"Test guideline no. 406: skin sensitisation","volume":"4","year":"1992","journal-title":"OECD Guidel. Test. Chem."},{"key":"B59","unstructured":"Test no. 429: skin sensitisation\n          \n          \n          2010"},{"key":"B60","first-page":"1","article-title":"The adverse outcome pathway for skin sensitisation initiated by covalent binding to proteins part 1: scientific evidence","volume":"168","year":"2012","journal-title":"OECD Environ. Health Saf. Publ. Ser. Test. Assess."},{"key":"B61","unstructured":"The adverse outcome pathway for skin sensitisation initiated by covalent binding to proteins\n          \n          \n          2014"},{"key":"B62","volume-title":"256: Guidance Document on the Reporting of Defined Approaches and Individual Information Sources to be Used Within Integrated Approaches to Testing and Assessment (IATA) for Skin Sensitisation","author":"Oecd","year":"2016"},{"key":"B63","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1080\/10629360802083871","article-title":"An evaluation of the implementation of the cramer classification scheme in the toxtree software","volume":"19","author":"Patlewicz","year":"2008","journal-title":"SAR QSAR Environ. Res."},{"key":"B64","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B65","doi-asserted-by":"publisher","first-page":"2618","DOI":"10.1021\/acs.jcim.7b00274","article-title":"Interpretation of quantitative structure-activity relationship models: past, present, and future","volume":"57","author":"Polishchuk","year":"2017","journal-title":"J. Chem. Inf. Model."},{"key":"B66","doi-asserted-by":"publisher","first-page":"e18672","DOI":"10.7717\/peerj.18672","article-title":"Development of machine learning models for the prediction of the skin sensitization potential of cosmetic compounds","volume":"12","author":"Qiao","year":"2024","journal-title":"PeerJ"},{"key":"B67","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.1016\/j.tiv.2014.08.002","article-title":"LuSens: a keratinocyte based ARE reporter gene assay for use in integrated testing strategies for skin sensitization hazard identification","volume":"28","author":"Ramirez","year":"2014","journal-title":"Toxicol. Vitro An Int. J. Publ. Assoc. BIBRA"},{"key":"B90","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/0022-5193(82)90199-0","article-title":"The derivation of quantitative correlations between skin sensitisation and physio-chemical parameters for alkylating agents, and their application to experimental data for sultones","volume":"99","author":"Roberts","year":"1982","journal-title":"J. Theor. Biol."},{"key":"B91","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1002\/jat.1293","article-title":"Chemical reactivity indices and mechanism-based read-across for non-animal based assessment of skin sensitisation potential","volume":"28","author":"Roberts","year":"2008","journal-title":"J. Appl. Toxicol."},{"key":"B68","doi-asserted-by":"publisher","first-page":"25","DOI":"10.14573\/altex.1411011","article-title":"Integrated testing Strategies (ITS) for safety assessment","volume":"32","author":"Rovida","year":"2015","journal-title":"ALTEX"},{"key":"B69","doi-asserted-by":"publisher","first-page":"4156","DOI":"10.1021\/acs.jcim.0c00993","article-title":"Improving measures of chemical structural similarity using machine learning on chemical\u2013genetic interactions","volume":"61","author":"Safizadeh","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"B70","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1021\/ci500588j","article-title":"DataWarrior: an open-source program for chemistry aware data visualization and analysis","volume":"55","author":"Sander","year":"2015","journal-title":"J. Chem. Inf. Model."},{"key":"B71","doi-asserted-by":"publisher","first-page":"e0155419","DOI":"10.1371\/journal.pone.0155419","article-title":"Integrated computational solution for predicting skin sensitization potential of molecules","volume":"11","author":"Sarath Kumar","year":"2016","journal-title":"PLOS ONE"},{"key":"B72","doi-asserted-by":"publisher","first-page":"803","DOI":"10.3390\/toxics12110803","article-title":"A novel machine learning model and a web portal for predicting the human skin sensitization effects of chemical agents","volume":"12","author":"Scheufen Tieghi","year":"2024","journal-title":"Toxics"},{"key":"B73","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1021\/ci0503558","article-title":"Relationships between molecular complexity, biological activity, and structural diversity","volume":"46","author":"Schuffenhauer","year":"2006","journal-title":"J. Chem. Inf. Model."},{"key":"B74","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1021\/acs.chemrestox.5c00033","article-title":"Machine learning for toxicity prediction using chemical structures: pillars for success in the real world","volume":"38","author":"Seal","year":"2025","journal-title":"Chem. Res. Toxicol."},{"key":"B75","doi-asserted-by":"publisher","first-page":"tfae044","DOI":"10.1093\/toxres\/tfae044","article-title":"New approach methodologies (NAMs): identifying and overcoming hurdles to accelerated adoption","volume":"13","author":"Sewell","year":"2024","journal-title":"Toxicol. Res."},{"key":"B76","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1021\/acs.jcim.9b01067","article-title":"Experimental error, kurtosis, activity cliffs, and methodology: what limits the predictivity of quantitative structure\u2013activity relationship models?","volume":"60","author":"Sheridan","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"B77","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1021\/acs.jcim.8b00712","article-title":"In need of bias control: evaluating chemical data for machine learning in structure-based virtual screening","volume":"59","author":"Sieg","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"B78","doi-asserted-by":"publisher","first-page":"14360","DOI":"10.1021\/acsomega.9b02221","article-title":"Evolving concept of activity cliffs","volume":"4","author":"Stumpfe","year":"2019","journal-title":"ACS Omega"},{"key":"B79","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2021.655771","article-title":"In silico prediction of skin sensitization: quo vadis?","volume":"12","author":"Ta","year":"2021","journal-title":"Front. Pharmacol."},{"key":"B80","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/0169-7439(89)80086-3","article-title":"k-nearest neighbour method: the influence of data transformations and metrics","volume":"6","author":"Todeschini","year":"1989","journal-title":"Chemom. Intelligent Laboratory Syst."},{"key":"B81","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.yrtph.2014.12.008","article-title":"Assessing skin sensitization hazard in mice and men using non-animal test methods","volume":"71","author":"Urbisch","year":"2015","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"B82","doi-asserted-by":"publisher","first-page":"5938","DOI":"10.1021\/acs.jcim.2c01073","article-title":"Exposing the limitations of molecular machine learning with activity cliffs","volume":"62","author":"van Tilborg","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"B83","doi-asserted-by":"publisher","first-page":"616","DOI":"10.3390\/toxics12080616","article-title":"Limitations and modifications of skin sensitization NAMs for testing inorganic nanomaterials","volume":"12","author":"Wareing","year":"2024","journal-title":"Toxics"},{"key":"B84","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1002\/jat.2983","article-title":"Development and utilization of an ex vivo bromodeoxyuridine local lymph node assay protocol for assessing potential chemical sensitizers","volume":"35","author":"Williams","year":"2015","journal-title":"J. Appl. Toxicol."},{"key":"B85","doi-asserted-by":"publisher","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":"B86","doi-asserted-by":"publisher","first-page":"103356","DOI":"10.1016\/j.drudis.2022.103356","article-title":"Concepts and applications of chemical fingerprint for hit and lead screening","volume":"27","author":"Yang","year":"2022","journal-title":"Drug Discov. Today"},{"key":"B87","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1002\/jat.3424","article-title":"Prediction of skin sensitization potency using machine learning approaches","volume":"37","author":"Zang","year":"2017","journal-title":"J. Appl. Toxicol."},{"key":"B88","doi-asserted-by":"publisher","first-page":"18193","DOI":"10.1021\/acs.est.3c02198","article-title":"Count-based Morgan fingerprint: a more efficient and interpretable molecular representation in developing machine learning-based predictive regression models for water contaminants\u2019 activities and properties","volume":"57","author":"Zhong","year":"2023","journal-title":"Environ. Sci. and Technol."}],"container-title":["Frontiers in Toxicology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/ftox.2026.1739746\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T22:10:20Z","timestamp":1785708620000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/ftox.2026.1739746\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"references-count":93,"alternative-id":["10.3389\/ftox.2026.1739746"],"URL":"https:\/\/doi.org\/10.3389\/ftox.2026.1739746","relation":{},"ISSN":["2673-3080"],"issn-type":[{"value":"2673-3080","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"article-number":"1739746"}}