Chemical Functional Uses with ToxPrint and EPI Suite Properties

The dataset contains chemical functional use data, associated ToxPrint descriptors, and EPI Suite properties, supporting a 2017 publication on high-throughput screening for functional substitutes. It includes 729 ToxPrint descriptors per chemical and model outputs such as confusion matrices and bioactivity indices. The data was compiled by the U.S. Environmental Protection Agency for research on chemical alternatives.

Use Cases

• Predict functional use categories for chemicals using the 729 ToxPrint descriptors as features in classification models.
• Analyze the relationship between EPI Suite properties and bioactivity index values to identify potential chemical substitutes.
• Validate model performance using the provided confusion matrix values and similarity thresholds for each prediction.
• Classify Tox21 chemicals as poor predictions, functional substitutes, or candidate alternatives based on their functional use prediction and bioactivity index.

Strengths

• Includes 729 ToxPrint descriptors per chemical, enabling detailed structural analysis.
• Provides multiple data components: functional uses, chemical properties, and model evaluation metrics.
• Associated with a peer-reviewed publication in Green Chemistry (2017), ensuring academic relevance.

Limitations

• The number of chemicals and total rows is unknown, making it difficult to assess dataset scale.
• Data is from 2017 and may not reflect the latest chemical inventories or regulatory standards.
• File format is XLS, which may require conversion for use with modern data science tools.

Provenance

Source

U.S. Environmental Protection Agency

Collection Method

Compiled for high-throughput screening research, incorporating ToxPrint descriptors and EPI Suite properties.

Time Range

Associated with research published in 2017.

Freshness

Last updated in November 2020, but the core data is associated with a 2017 publication.