Update README.md
Browse files
README.md
CHANGED
|
@@ -50,7 +50,7 @@ The MolCRAFT series addresses critical challenges in generative models for SBDD,
|
|
| 50 |
|
| 51 |
### MolJO (Molecule Joint Optimization)
|
| 52 |
|
| 53 |
-
|
| 54 |
|
| 55 |
* **Description**: MolJO is a gradient-based SBMO framework that leverages a continuous and differentiable space derived through Bayesian inference. It facilitates **joint guidance signals across different modalities** (continuous coordinates and discrete atom types) while preserving SE(3)-equivariance. MolJO introduces a novel backward correction strategy for an effective trade-off between exploration and exploitation.
|
| 56 |
* **Key Contributions**:
|
|
@@ -62,7 +62,7 @@ The MolCRAFT series addresses critical challenges in generative models for SBDD,
|
|
| 62 |
|
| 63 |
### MolPilot (How to Pilot the Aircraft)
|
| 64 |
|
| 65 |
-
|
| 66 |
|
| 67 |
* **Description**: MolPilot addresses challenges in geometric structure modeling by focusing on the **twisted probability path of multi-modalities** (continuous 3D positions and discrete 2D topologies). It proposes a VLB-Optimal Scheduling (VOS) strategy, optimizing the Variational Lower Bound as a path integral for SBDD. MolPilot significantly enhances molecular geometries and interaction modeling.
|
| 68 |
* **Key Contributions**:
|
|
@@ -76,7 +76,7 @@ Official implementation of ICML 2024 ["MolCRAFT: Structure-Based Drug Design in
|
|
| 76 |
|
| 77 |
🎉 Our demo is now available [here](http://61.241.63.126:8000). Welcome to have a try!
|
| 78 |
|
| 79 |
-
|
| 80 |
|
| 81 |
## Environment
|
| 82 |
It is highly recommended to install via docker if a Linux server with NVIDIA GPU is available.
|
|
|
|
| 50 |
|
| 51 |
### MolJO (Molecule Joint Optimization)
|
| 52 |
|
| 53 |
+
<!--  -->
|
| 54 |
|
| 55 |
* **Description**: MolJO is a gradient-based SBMO framework that leverages a continuous and differentiable space derived through Bayesian inference. It facilitates **joint guidance signals across different modalities** (continuous coordinates and discrete atom types) while preserving SE(3)-equivariance. MolJO introduces a novel backward correction strategy for an effective trade-off between exploration and exploitation.
|
| 56 |
* **Key Contributions**:
|
|
|
|
| 62 |
|
| 63 |
### MolPilot (How to Pilot the Aircraft)
|
| 64 |
|
| 65 |
+
<!--  -->
|
| 66 |
|
| 67 |
* **Description**: MolPilot addresses challenges in geometric structure modeling by focusing on the **twisted probability path of multi-modalities** (continuous 3D positions and discrete 2D topologies). It proposes a VLB-Optimal Scheduling (VOS) strategy, optimizing the Variational Lower Bound as a path integral for SBDD. MolPilot significantly enhances molecular geometries and interaction modeling.
|
| 68 |
* **Key Contributions**:
|
|
|
|
| 76 |
|
| 77 |
🎉 Our demo is now available [here](http://61.241.63.126:8000). Welcome to have a try!
|
| 78 |
|
| 79 |
+
<!--  -->
|
| 80 |
|
| 81 |
## Environment
|
| 82 |
It is highly recommended to install via docker if a Linux server with NVIDIA GPU is available.
|