Explainable Artificial Intelligence (xAI) for 5-HT2A Receptor Binding Affinity of New Psychoactive Substances
Molecules · 01.06.2026 · 31 (11) · 1888
DOI: 10.3390/molecules31111888 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecules, online erschienen am 01.06.2026. Verfasst von Verena Schöning und 5 weiteren Autor:innen. Beteiligte Einrichtung: Clinical Pharmacology & Toxicology, Department of Internal Medicine, University Hospital Bern, 3010 Bern, Switzerland. Hauptthemen laut MEDLINE: Receptor, Serotonin, 5-HT2A, Artificial Intelligence, Psychotropic Drugs. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss National Science Foundation.
Abstract (Originalsprache)
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’s 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–receptor 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Clinical Pharmacology & Toxicology, Department of Internal Medicine, University Hospital Bern, 3010 Bern, Switzerland.
- Institute of Forensic Medicine Bern, Forensic Toxicology and Chemistry, University of Bern, 3008 Bern, Switzerland.
- Hyperion Data, Griffith, NSW 2680, Australia.
- Laboratory of Toxicology, Department of Bioanalysis, Faculty of Pharmaceutical Sciences, Ghent University, 9000 Ghent, Belgium.
ORCID-Profile: Verena Schöning, Katharina Elisabeth Grafinger, Christophe P Stove, Wolfgang Weinmann, Felix Hammann
Förderung
- Swiss National Science Foundation
Zitieren
APA
Schöning, V., Grafinger, K. E., Pasin, D., Stove, C. P., Weinmann, W., & Hammann, F. (2026). Explainable Artificial Intelligence (xAI) for 5-HT2A Receptor Binding Affinity of New Psychoactive Substances. Molecules, 31(11), 1888. https://doi.org/10.3390/molecules31111888
Vancouver
Schöning V, Grafinger KE, Pasin D, Stove CP, Weinmann W, Hammann F. Explainable Artificial Intelligence (xAI) for 5-HT2A Receptor Binding Affinity of New Psychoactive Substances. Molecules. 2026;31(11):1888. doi:10.3390/molecules31111888
BibTeX
@article{Schning2026,
author = {Schöning, Verena and Grafinger, Katharina Elisabeth and Pasin, Daniel and Stove, Christophe P and Weinmann, Wolfgang and Hammann, Felix},
title = {Explainable Artificial Intelligence (xAI) for 5-HT2A Receptor Binding Affinity of New Psychoactive Substances},
journal = {Molecules},
year = {2026},
volume = {31},
number = {11},
pages = {1888},
doi = {10.3390/molecules31111888}
}
EUVIMED