QSAR Fish Toxicity: Acute Toxicity Data for Fathead Minnow

A QSAR dataset for regression modeling of acute chemical toxicity towards the fathead minnow (Pimephales promelas). The data was originally published in 2015 by Cassotti et al. and was curated for the TabArena Tabular ML IID Study. The dataset is licensed under CC BY 4.0.

Use Cases

• Regression modeling of acute toxicity based on molecular descriptors.
• Evaluating machine learning models for independent and identically distributed (IID) tabular data.
• Studying the relationship between chemical structure and aquatic toxicity.
• Benchmarking model performance on datasets with a known high rate of duplicate feature vectors.

Strengths

• Dataset is licensed under CC BY 4.0, permitting broad reuse.
• Original source and reference are clearly cited for traceability.
• Curation notes highlight a specific anomaly: 15% duplicate rows when ignoring the target feature.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, sample data, and file formats are unknown, which limits suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

https://doi.org/10.24432/C5JG7B; Cassotti, Matteo, et al. 'A similarity-based QSAR model for predicting acute toxicity towards the fathead minnow (Pimephales promelas).' SAR and QSAR in Environmental Research 26.3 (2015): 217-243.

Collection Method

Curated from the original source for the TabArena Tabular ML IID Study.

Time Range

2015

Freshness

Dataset Year is 2015; last updated date is unknown.

Geography

null