ADMET-AI
Predict ADMET properties swiftly and accurately using machine learning.
ADMET-AI is a machine learning model designed to predict Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties of chemical compounds. Utilizing a graph neural network architecture, Chemprop-RDKit, trained on 41 datasets from the Therapeutics Data Commons, ADMET-AI offers rapid and accurate evaluations of large-scale chemical libraries. It provides a user-friendly web interface for batch predictions, facilitating efficient drug discovery processes.
Estimated resource cost: 0.000062
Categories: Ligand/Drug Design & Screening
Tags: ADMET Molecular Descriptors Toxicity
Key Capabilities
- Employs Chemprop-RDKit, a graph neural network architecture, for precise ADMET property predictions.
- Trained on 41 ADMET datasets from the Therapeutics Data Commons, ensuring comprehensive coverage.
- Outperforms existing ADMET prediction tools in both speed and accuracy.
- Provides contextualized predictions by comparing results with a reference set of approved drugs.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 5 |
| runtime_median | 4 |
| runtime_std | 3 |
| runtime_90th_percentile | 10 |
| runtime_max | 76 |
Similar Tools
- ChemBounce
- eTox Drug Toxicity Prediction
- Free Wilson Analysis
- Mordred Molecular Descriptor Calculator
Ready to submit your job?
Review your configuration, then confirm the estimated credit cost before you run the job. Note that credit estimates are not guaranteed and runtime can vary depending on inputs and settings.
Estimated Credits: 0.000062
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.