cpLogD: RDF Version of a Confidence Predictor for LogD

An RDF version of the cpLogD dataset, which likely contains data for predicting the distribution coefficient (LogD) of chemical compounds. The dataset was created by Maris Lapins of Uppsala University and is available in RDF HDT and Turtle formats. The specific size, row count, and temporal coverage of the data are not provided in the description.

Use Cases

• Training confidence-aware machine learning models for LogD prediction based on the dataset's RDF structure.
• Benchmarking conformal regression methods using the provided molecular property data.
• Evaluating support vector machine performance on chemical property prediction tasks.
• Developing semantic web applications for cheminformatics using the RDF representation.

Strengths

• Available in two structured RDF formats (HDT and Turtle), facilitating semantic querying.
• Authored by a researcher from Uppsala University, suggesting an academic origin.

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

Uppsala University

Collection Method

Derived from the original cpLogD dataset, converted to RDF.