Sign in to access this content
Model
DSMBind is an energy-based model that has been trained on protein-ligand complexes to predict binding affinities. The model produces comparative values that are useful for ranking protein-ligand binding affinities.
Sign in to access this content
| Field | Response |
|---|---|
| Intended Application(s) & Domain(s): | Protein-Ligand Binding Affinity Prediction |
| Model Type: | Structural Biology for Drug Discovery |
| Intended Users: | This model is intended for developers or researchers who want to study protein-ligand binding. |
| Outputs: | A scalar value indicating the binding affinity |
| Describe how the model works: | This model takes a 3D protein-ligand complex structure as input and produces a scalar value with the learned model weights. |
| Technical Limitations: | This model produces only comparative values instead of absolute binding energy and may perform less well on non-crystal structures. |
| Verified to have met prescribed NVIDIA standards: | Yes |
| Performance Metrics: | Pearson correlation between the prediction values and ground truth binding affinities |
| Potential Known Risks: | Output value could lead to incorrect inference on binding affinity of a complex |
| Licensing: | https://www.apache.org/licenses/LICENSE-2.0 |