Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,9 @@ tags:
|
|
| 12 |
|
| 13 |
The model combines the local geometric awareness of **Equivariant Graph Neural Networks (EGNNs)** with the global, pairwise reasoning capabilities of **Evoformer blocks** (inspired by AlphaFold 2), executed through a multi-step recycling mechanism.
|
| 14 |
|
|
|
|
|
|
|
|
|
|
| 15 |
## 🧬 Model Architecture
|
| 16 |
|
| 17 |
The architecture is explicitly designed to balance rich feature preservation (high hidden dimensionality) with controlled reasoning depth to prevent over-smoothing on 3D protein graphs.
|
|
|
|
| 12 |
|
| 13 |
The model combines the local geometric awareness of **Equivariant Graph Neural Networks (EGNNs)** with the global, pairwise reasoning capabilities of **Evoformer blocks** (inspired by AlphaFold 2), executed through a multi-step recycling mechanism.
|
| 14 |
|
| 15 |
+
## Usage
|
| 16 |
+
You can find everything related to this model at [GraphBind](https://github.com/Labrapuerta/GraphBind)
|
| 17 |
+
|
| 18 |
## 🧬 Model Architecture
|
| 19 |
|
| 20 |
The architecture is explicitly designed to balance rich feature preservation (high hidden dimensionality) with controlled reasoning depth to prevent over-smoothing on 3D protein graphs.
|