QSAR_TID_11: Drug Potency Data with Molecular Fingerprints

An openml dataset containing drugs and their potency. Features are FCFP 1024-bit molecular fingerprints generated from SMILES strings using the Pipeline Pilot program. The dataset is in the public domain under a us-pd license.

Use Cases

• Predicting drug potency (MEDIAN_PXC50) based on molecular fingerprint features.
• Training QSAR models for molecular toxicity or chemical property analysis.
• Benchmarking fingerprint-based machine learning algorithms in cheminformatics.

Strengths

• Includes a target feature (MEDIAN_PXC50) for potency prediction.
• Features are standardized 1024-bit FCFP molecular fingerprints.
• Data is in the public domain, facilitating unrestricted use.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

openml

Collection Method

Molecular fingerprints generated from SMILES strings using Dassault Systemes BIOVIA Pipeline Pilot.

Time Range

Temporal coverage is unknown.

Freshness

Last updated date is unknown.

Geography

Spatial coverage is unknown.