Annotated Compound Data Sets for Chemoinformatics and Medicinal Chemistry

Annotated compound data sets are part of a freely available database and software tool collection developed at the University of Bonn. The original release was described in a 2012 F1000Research article, with an updated version described in a forthcoming data note. The data is provided by author Ye Hu.

Use Cases

• Train compound property prediction models based on annotated chemical structures.
• Benchmark chemoinformatics algorithms based on the provided compound data sets.
• Perform virtual screening for drug discovery based on annotated compound libraries.

Strengths

• Data is freely available and described in peer-reviewed F1000Research articles.
• Data sets are annotated, which likely provides labels for machine learning tasks.

Limitations

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

Provenance

Source

University of Bonn laboratory

Collection Method

Developed in a laboratory for chemoinformatics and computational medicinal chemistry.

Time Range

Original release in 2012, with an updated version forthcoming.

Freshness

Last updated is unknown.

Geography

null