PubChem Compounds Tested In Primary And Confirmatory Assays, 437,257 Compounds

Pubchem Compounds Tested In Primary And Confirmatory Assays contains 437,257 chemical compounds assembled from the PubChem BioAssay collection. The dataset was compiled by Swarit Jasial at the University of Bonn and includes compound identifiers, assay counts, and activity annotations. Each compound was tested in both primary and confirmatory assays.

Use Cases

• Train models to predict compound activity based on assay annotations.
• Analyze the relationship between primary and confirmatory assay results for specific compounds.
• Identify frequently tested compounds for benchmarking virtual screening algorithms.
• Study assay data consistency across the PubChem BioAssay collection.

Strengths

• Contains 437,257 compounds, providing a substantial sample size.
• Includes activity annotations for each compound, a key feature for supervised learning.
• Compounds were tested in both primary and confirmatory assays, enabling consistency analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.
• Row count is known, but the specific features per row beyond the description are unclear.

Provenance

Source

PubChem BioAssay collection

Collection Method

Assembled from the PubChem BioAssay collection and deposited in an Excel file.