{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T10:19:34Z","timestamp":1785406774554,"version":"3.56.0"},"reference-count":45,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["SNF_10000358"],"award-info":[{"award-number":["SNF_10000358"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"award":["SNF_10000358"],"award-info":[{"award-number":["SNF_10000358"]}],"id":[{"id":"https:\/\/ror.org\/00yjd3n13","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Molecules"],"abstract":"<jats:p>New psychoactive substances (NPS) are a heterogeneous group of recreational drugs that mimic the actions and psychoactive effects of existing pharmaceutical products or recreational drugs. As NPS can be highly potent, even exceeding their template compound\u2019s potency, there are frequent reports of non-fatal and fatal intoxications. One principal target for hallucinogenic and psychedelic drugs, including NPS, is the 5-hydroxytryptamine receptor 2A (5-HT2A). Since NPS are designed to evade legal restrictions, this drug market is quickly evolving, and researchers are playing catch-up, investigating these novel compounds for their toxicological and pharmacological properties. Receptor binding affinity (Ki) is an important property describing ligand\u2013receptor interactions and is a prerequisite for receptor activation. Competitive in vitro assays can be used to assess Ki; this is a resource-intensive process. We used publicly available Ki data for the 5-HT2A, calculated molecular descriptors and fingerprints, and trained five classification machine learning models. The predictive performance of the models had precisions and recalls up to 93% and 92%, respectively. We used explainable artificial intelligence, i.e., SHAP values and similarity maps, for model interpretation. The results are in line with previous experiments and support its suitability to predict the binding affinities of possible 5-HT2A ligands.<\/jats:p>","DOI":"10.3390\/molecules31111888","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:19:42Z","timestamp":1780316382000},"page":"1888","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Artificial Intelligence (xAI) for 5-HT2A Receptor Binding Affinity of New Psychoactive Substances"],"prefix":"10.3390","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2105-326X","authenticated-orcid":false,"given":"Verena","family":"Sch\u00f6ning","sequence":"first","affiliation":[{"name":"Clinical Pharmacology & Toxicology, Department of Internal Medicine, University Hospital Bern, 3010 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3647-7455","authenticated-orcid":false,"given":"Katharina Elisabeth","family":"Grafinger","sequence":"additional","affiliation":[{"name":"Institute of Forensic Medicine Bern, Forensic Toxicology and Chemistry, University of Bern, 3008 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Pasin","sequence":"additional","affiliation":[{"name":"Hyperion Data, Griffith, NSW 2680, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7126-348X","authenticated-orcid":false,"given":"Christophe P.","family":"Stove","sequence":"additional","affiliation":[{"name":"Laboratory of Toxicology, Department of Bioanalysis, Faculty of Pharmaceutical Sciences, Ghent University, 9000 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8659-1304","authenticated-orcid":false,"given":"Wolfgang","family":"Weinmann","sequence":"additional","affiliation":[{"name":"Institute of Forensic Medicine Bern, Forensic Toxicology and Chemistry, University of Bern, 3008 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0658-9330","authenticated-orcid":false,"given":"Felix","family":"Hammann","sequence":"additional","affiliation":[{"name":"Clinical Pharmacology & Toxicology, Department of Internal Medicine, University Hospital Bern, 3010 Bern, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2045125320967197","DOI":"10.1177\/2045125320967197","article-title":"New psychoactive substances: A review and updates","volume":"10","author":"Shafi","year":"2020","journal-title":"Ther. Adv. Psychopharmacol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1685","DOI":"10.1111\/j.1360-0443.2010.02934.x","article-title":"Legal highs and the challenges for policy makers","volume":"105","author":"Winstock","year":"2010","journal-title":"Addiction"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.drugpo.2016.11.002","article-title":"Assessing the \u2018added value\u2019 of European policy on new psychoactive substances","volume":"40","author":"Chatwin","year":"2017","journal-title":"Int. J. Drug Policy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"285","DOI":"10.3390\/psychoactives3020018","article-title":"New Psychoactive Substances: Health and Legal Challenges","volume":"3","author":"Santos","year":"2024","journal-title":"Psychoactives"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ferrari J\u00fanior, E., Leite, B.H.M., Gomes, E.B., Vieira, T.M., Sepulveda, P., and Caldas, E.D. (2022). Fatal cases involving new psychoactive substances and trends in analytical techniques. Front. Toxicol., 4.","DOI":"10.3389\/ftox.2022.1033733"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100016","DOI":"10.1016\/j.etdah.2021.100016","article-title":"Mortality involving New Psychoactive Substances across Europe, 2016\u20132017","volume":"1","author":"Vicente","year":"2021","journal-title":"Emerg. Trends Drugs Addict. Health"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Webb, L., Shi, X., Goodair, C., and Cheeta, S. (2022). Trends in Mortality From Novel Psychoactive Substances as \u201cLegal Highs\u201d: Gender Differences in Manner of Death and Implications for Risk Differences for Women. Front. Psychiatry, 13.","DOI":"10.3389\/fpsyt.2022.890840"},{"key":"ref_8","unstructured":"European Monitoring Centre for Drugs and Drug Addiction (EMCDDA) (2014). European Drug Report 2014\u2014Trends and Developments, Publications Office."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/s11419-018-0415-z","article-title":"Pharmacological evaluation of new constituents of \u201cSpice\u201d: Synthetic cannabinoids based on indole, indazole, benzimidazole and carbazole scaffolds","volume":"36","author":"Schoeder","year":"2018","journal-title":"Forensic Toxicol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/978-1-61779-909-9_3","article-title":"Radioligand binding assays and their analysis","volume":"897","author":"Maguire","year":"2012","journal-title":"Methods Mol. Biol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1021\/acsptsci.2c00222","article-title":"Receptor Binding Profiles for Tryptamine Psychedelics and Effects of 4-Propionoxy-N,N-dimethyltryptamine in Mice","volume":"6","author":"Glatfelter","year":"2023","journal-title":"ACS Pharmacol. Transl. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.neuropharm.2017.07.012","article-title":"Monoamine receptor interaction profiles of 4-thio-substituted phenethylamines (2C-T drugs)","volume":"134","author":"Luethi","year":"2018","journal-title":"Neuropharmacology"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/j.neuropharm.2015.08.034","article-title":"Receptor interaction profiles of novel N-2-methoxybenzyl (NBOMe) derivatives of 2,5-dimethoxy-substituted phenethylamines (2C drugs)","volume":"99","author":"Rickli","year":"2015","journal-title":"Neuropharmacology"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, A. (2007). Serotonin 2A (5-HT2A) Receptor Function: Ligand-Dependent Mechanisms and Pathways. Serotonin Receptors in Neurobiology, CRC Press\/Taylor & Francis.","DOI":"10.1201\/9781420005752-11"},{"key":"ref_15","first-page":"45","article-title":"Hallucinogens and Serotonin 5-HT(2A) Receptor-Mediated Signaling Pathways","volume":"36","year":"2018","journal-title":"Curr. Top. Behav. Neurosci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1056\/NEJMra041867","article-title":"The serotonin syndrome","volume":"352","author":"Boyer","year":"2005","journal-title":"N. Engl. J. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1002\/wmts.42","article-title":"Structure\u2013activity relationships of serotonin 5-HT2A agonists","volume":"1","author":"Nichols","year":"2012","journal-title":"Wiley Interdiscip. Rev. Membr. Transp. Signal."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s11030-017-9729-8","article-title":"Practical application of the Average Information Content Maximization (AIC-MAX) algorithm: Selection of the most important structural features for serotonin receptor ligands","volume":"21","author":"Warszycki","year":"2017","journal-title":"Mol. Divers."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"349","DOI":"10.3390\/pharmaceutics16030349","article-title":"Integrated QSAR Models for Prediction of Serotonergic Activity: Machine Learning Unveiling Activity and Selectivity Patterns of Molecular Descriptors","volume":"16","author":"Mendyk","year":"2024","journal-title":"Pharmaceutics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"14587","DOI":"10.1039\/D1RA01335A","article-title":"Machine learning vs. field 3D-QSAR models for serotonin 2A receptor psychoactive substances identification","volume":"11","author":"Floresta","year":"2021","journal-title":"RSC Adv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2150","DOI":"10.1021\/acs.jcim.3c01517","article-title":"SerotoninAI: Serotonergic System Focused, Artificial Intelligence-Based Application for Drug Discovery","volume":"64","author":"Mendyk","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kerns, E.H., and Di, L. (2008). Drug-Like Properties: Concepts, Structure Design and Methods: From ADME to Toxicity Optimization, Elsevier.","DOI":"10.1016\/B978-012369520-8.50018-8"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1021\/acs.chemrev.6b00177","article-title":"GPCR Dynamics: Structures in Motion","volume":"117","author":"Latorraca","year":"2017","journal-title":"Chem. Rev."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e6","DOI":"10.5210\/jbc.v41i1.7309","article-title":"The Science Behind G Protein-Coupled Receptors (GPCRs) and Their Accurate Visual Representation in Scientific Research","volume":"41","author":"Sojka","year":"2017","journal-title":"J. Biocommun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4661","DOI":"10.1016\/j.bmc.2008.02.033","article-title":"The role of lipophilicity in determining binding affinity and functional activity for 5-HT2A receptor ligands","volume":"16","author":"Parker","year":"2008","journal-title":"Bioorg Med. Chem."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"\u0141api\u0144ska, N., Szl\u0119k, J., Pac\u0142awski, A., and Mendyk, A. (2025). Machine Learning Tool for New Selective Serotonin and Serotonin\u2013Norepinephrine Reuptake Inhibitors. Molecules, 30.","DOI":"10.3390\/molecules30030637"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1016\/0006-2952(91)90178-8","article-title":"Differential interactions of dimethyltryptamine (DMT) with 5-HT1A and 5-HT2 receptors","volume":"41","author":"Deliganis","year":"1991","journal-title":"Biochem. Pharmacol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/0028-3908(90)90001-8","article-title":"Differential interactions of indolealkylamines with 5-hydroxytryptamine receptor subtypes","volume":"29","author":"McKenna","year":"1990","journal-title":"Neuropharmacology"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1324","DOI":"10.1021\/acs.jcim.8b00825","article-title":"Interpretation of QSAR Models by Coloring Atoms According to Changes in Predicted Activity: How Robust Is It?","volume":"59","author":"Sheridan","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1038\/s41586-025-10061-7","article-title":"Psychedelics elicit their effects by 5-HT2A receptor-mediated Gi signalling","volume":"651","author":"Xu","year":"2026","journal-title":"Nature"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2727","DOI":"10.1021\/acschemneuro.3c00267","article-title":"Structure\u2013Activity Assessment and In-Depth Analysis of Biased Agonism in a Set of Phenylalkylamine 5-HT2A Receptor Agonists","volume":"14","author":"Pottie","year":"2023","journal-title":"ACS Chem. Neurosci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"114251","DOI":"10.1016\/j.bcp.2020.114251","article-title":"Identification of psychedelic new psychoactive substances (NPS) showing biased agonism at the 5-HT2AR through simultaneous use of \u03b2-arrestin 2 and miniG\u03b1q bioassays","volume":"182","author":"Pottie","year":"2020","journal-title":"Biochem. Pharmacol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1111\/bcp.16152","article-title":"Management of serotonin syndrome (toxicity)","volume":"91","author":"Chiew","year":"2025","journal-title":"Br. J. Clin. Pharmacol."},{"key":"ref_34","doi-asserted-by":"crossref","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":"ref_35","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1038\/s41529-025-00713-4","article-title":"Gaining scientific understanding with small data machine learning: Explainable molecule representations and their consensus","volume":"9","author":"Sahlmann","year":"2025","journal-title":"npj Mater. Degrad."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity Fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"ref_37","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_38","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1093\/bioinformatics\/btn479","article-title":"Chemical substructures that enrich for biological activity","volume":"24","author":"Klekota","year":"2008","journal-title":"Bioinformatics"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1002\/qsar.200290002","article-title":"Identification of Diverse Database Subsets using Property-Based and Fragment-Based Molecular Descriptions","volume":"21","author":"Ashton","year":"2002","journal-title":"Quant. Struct.-Act. Relatsh."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1021\/ci700157b","article-title":"y-Randomization and Its Variants in QSPR\/QSAR","volume":"47","author":"Meringer","year":"2007","journal-title":"J. Chem. Inf. Model."},{"key":"ref_41","unstructured":"Molnar, C. (2025). Interpretable Machine Learning. A Guide for Making Black Box Models Explainable, LeanPub. [3rd ed.]."},{"key":"ref_42","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/1758-2946-5-43","article-title":"Similarity maps\u2014A visualization strategy for molecular fingerprints and machine-learning methods","volume":"5","author":"Riniker","year":"2013","journal-title":"J. Cheminform."},{"key":"ref_44","unstructured":"Rossum, G.V., and Drake, F.L. (2009). Python 3 Reference Manual, CreateSpace."},{"key":"ref_45","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Molecules"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1420-3049\/31\/11\/1888\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:20:52Z","timestamp":1780316452000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1420-3049\/31\/11\/1888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":45,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["molecules31111888"],"URL":"https:\/\/doi.org\/10.3390\/molecules31111888","relation":{},"ISSN":["1420-3049"],"issn-type":[{"value":"1420-3049","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]}}}