Life Cycle Thinking in Drug Discovery: Acute Oral Toxicity Predictions for 1150 Compounds

A dataset of 1150 compounds used to develop and validate machine learning models for predicting acute oral toxicity across six drug scaffolds. The models, including QSAR, q-RASAR, and deep learning methods, were applied to virtually screen over 23,000 untested molecules. The dataset was authored by Jianing Xu and last updated on June 2, 2026.

Use Cases

• Training interpretable ML models for acute oral toxicity prediction based on quantitative structure–activity relationships (QSAR) described in the dataset.
• Virtual screening of large chemical libraries to prioritize low-toxicity drug leads based on the validated computational workflow.
• Analyzing structure–toxicity relationships to guide the de novo design of safer chemicals as mentioned in the description.
• Benchmarking deep learning algorithms for global toxicity modeling across multiple drug scaffolds.

Strengths

• Dataset is based on 1150 compounds, providing a foundation for model development.
• Models achieved external validation coefficients (R²) ranging from 0.7674 to 0.8980, indicating robust predictive performance.
• The computational workflow was applied to screen over 23,000 untested molecules, demonstrating scalability.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the primary dataset is unknown, which may limit suitability assessment.
• Data may reflect bias inherent to the specific compounds and scaffolds studied.

Provenance

Source

figshare

Collection Method

Likely compiled for research on in silico toxicity prediction in drug discovery.

Freshness

Last updated 2026-06-02 12:15:41; freshness should be verified.