Related Experiment Video
Updated: Jun 6, 2026

Methods for the Discovery of Novel Compounds Modulating a Gamma-Aminobutyric Acid Receptor Type A Neurotransmission
Published on: August 16, 2018
Predicting affinity and potency of new psychoactive substances at cannabinoid 1 receptor with explainable artificial
Verena Schöning1, Gaia Alluisetti2,3, Katharina Elisabeth Grafinger2
1Clinical Pharmacology and Toxicology, Department of Internal Medicine, University Hospital Bern, Bern, Switzerland.
Machine learning models accurately predict cannabinoid receptor 1 (CB1) affinity and potency for new psychoactive substances (NPS). Lipophilicity drives affinity, while potency involves a wider range of molecular features, aiding in the regulation of recreational drugs.
Area of Science:
- Pharmacology and Cheminformatics
- Drug Discovery and Regulation
Background:
- Binding affinity and functional potency are key ligand-receptor interaction properties.
- Understanding molecular features is crucial for regulating new psychoactive substances (NPS), like synthetic cannabinoid receptor agonists.
- Synthetic cannabinoid receptor agonists are often full agonists of the cannabinoid 1 receptor (CB1).
Purpose of the Study:
- To develop machine learning models predicting CB1 receptor affinity and potency.
- To identify molecular features driving these interactions in NPS.
- To aid in the regulation of recreational drugs by understanding structure-activity relationships.
Main Methods:
- Compiled publicly available data on CB1 affinity and potency.
- Employed molecular descriptors and fingerprints for machine learning model training.
- Utilized explainable AI (SHAP values) to analyze feature importance for affinity and potency.
Main Results:
- XGBoost and Random Forest models achieved >90% recall, precision, and F1 scores for predicting both affinity and potency.
- Models utilizing molecular descriptors and Extended Connectivity Fingerprints (ECFP) showed superior performance.
- SHAP analysis highlighted key structural features influencing CB1 affinity and potency in NPS.
Conclusions:
- Lipophilicity and membrane-partitioning are primary drivers of CB1 receptor affinity.
- Potency is influenced by a combination of lipophilicity, shape, branching, and electronic descriptors.
- These findings provide valuable insights for the design and regulation of synthetic cannabinoids and other NPS.
Related Concept Videos
Structure-Activity Relationships and Drug Design
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence its...
The Two-State Receptor Model
The binding affinity of a drug determines its interaction with one...
Drug-Receptor Interactions
Several parameters, such as the drug's affinity for its receptor and its efficacy, which is its ability to activate the receptor, determine the drug's effect on the tissue.
Drug-Receptor Interaction: Agonist
Agonists can bind to receptors in different ways. Some agonists bind directly to the receptor's active site, mimicking the endogenous ligand's action.
Quantitative Aspects of Drug-Receptor Interaction
CNS Stimulants: Cocaine, Amphetamines and Cannabinoids