CB1 Receptor Affinity and Potency Data for New Psychoactive Substances

Data Sheet 1 contains compiled public data on the binding affinity and functional potency of synthetic cannabinoid receptor agonists at the cannabinoid 1 receptor (CB1). The dataset was used to train machine learning models with molecular descriptors and fingerprints, achieving high performance metrics. It was authored by Verena Schöning and last updated on 2026-05-20.

Use Cases

• Training classification models to predict CB1 receptor binding affinity based on molecular descriptors.
• Training classification models to predict CB1 receptor functional potency based on Extended Connectivity Fingerprints.
• Applying explainable AI (SHAP) to identify structural features impacting high affinity and potency.
• Analyzing the distinct molecular drivers of affinity (lipophilicity) versus potency (lipophilicity, shape, branching, electronics).

Strengths

• Models described achieved recall, precision, and F1 scores greater than 90%.
• Analysis includes explainable AI (SHAP) to interpret feature importance.
• Data is publicly available under a CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The primary file format is a PDF (1.2 MB), which may require extraction to access structured data.

Provenance

Source

figshare, authored by Verena Schöning.

Collection Method

Compiled from publicly available data on CB1 affinity and potency.

Time Range

null

Freshness

Last updated 2026-05-20 05:23:40; freshness should be verified.

Geography

null