AllMetal3D
Identify likely metal and water binding sites from a protein structure.
Predict metal and water binding sites in proteins using 3D convolutional neural networks (AllMetal3D/Water3D).
Estimated resource cost: 0.0002945
Categories: Molecular Docking & Interactions
Tags: Binding Site Prediction Proteins
Key Capabilities
- Predicts metal-binding and water-binding sites directly from an input protein structure using 3D CNNs.
- Provides per-site probabilities for different metal ions and water occupancy.
- Uses a joint model of localization, identity, and coordination geometry to improve metal-site precision.
- Considers local 3D atomic environments rather than only sequence motifs, enabling detection of noncanonical sites.
- Can be applied to experimentally determined and predicted structures (such as AlphaFold models).
- Outputs machine-readable result files for downstream analysis and integration into custom workflows.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 0 |
| runtime_median | 0 |
| runtime_std | 0 |
| runtime_90th_percentile | 0 |
| runtime_max | 0 |
Similar Tools
- AF2Bind
- ScanNet Protein Binding Site Prediction
- ColabDock
- DockQ
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: 0.0002945
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.