Commit
·
648f3e9
1
Parent(s):
51a9333
update readme
Browse files- README.md +9 -12
- assets/images/architecture.png +0 -0
- assets/images/homology_detection.png +0 -0
- assets/images/reconstruction.png +0 -0
- assets/images/structure_prediction.png +0 -0
- assets/images/structure_tokenizer/launch_protein_viewer.png +0 -0
- assets/images/structure_tokenizer/select_files.png +0 -0
- assets/images/structure_tokenizer/visualize_reconstruction.png +0 -0
README.md
CHANGED
|
@@ -14,12 +14,12 @@ AIDO.StructureTokenizer is a VQ-VAE-based tokenizer designed for protein structu
|
|
| 14 |
|
| 15 |
## Model Description
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
**AIDO.StructureTokenizer** is built on a Vector Quantized Variational Autoencoder (VQ-VAE) architecture with the following components:
|
| 20 |
-
- Equivariant Encoder: Encodes backbone structures into a latent space that maintains rotational and translational symmetries using the Equiformer architecture.
|
| 21 |
- Discrete Codebook: Maps continuous latent vectors into 512 discrete structural tokens.
|
| 22 |
-
- Invariant Decoder: Reconstructs full 3D structures, including side chains, from the structural tokens using an architecture adapted from ESMFold.
|
| 23 |
|
| 24 |
This model strikes a balance between reconstruction fidelity and structural locality, optimizing its suitability for downstream tasks such as structure prediction, homology detection, and multimodal protein modeling.
|
| 25 |
|
|
@@ -30,17 +30,14 @@ This model strikes a balance between reconstruction fidelity and structural loca
|
|
| 30 |
- Reconstructing Structures (See [below](#reconstructing-structures))
|
| 31 |
- Structure Prediction (See [this section](https://huggingface.co/genbio-ai/AIDO.Protein2StructureToken-16B/blob/main/README.md#structure-prediction) in genbio-ai/AIDO.Protein2StructureToken-16B)
|
| 32 |
|
| 33 |
-
### Hyperparameters
|
| 34 |
-
|
| 35 |
-
TODO
|
| 36 |
-
|
| 37 |
-
### Training details
|
| 38 |
-
|
| 39 |
-
TODO
|
| 40 |
-
|
| 41 |
## Results
|
| 42 |
|
| 43 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
## How to Use
|
| 46 |
Please see `experiments/AIDO.StructureTokenizer` in [Model Generator](https://github.com/genbio-ai/modelgenerator) for more details.
|
|
|
|
| 14 |
|
| 15 |
## Model Description
|
| 16 |
|
| 17 |
+

|
| 18 |
|
| 19 |
**AIDO.StructureTokenizer** is built on a Vector Quantized Variational Autoencoder (VQ-VAE) architecture with the following components:
|
| 20 |
+
- Equivariant Encoder (6M): Encodes backbone structures into a latent space that maintains rotational and translational symmetries using the Equiformer architecture.
|
| 21 |
- Discrete Codebook: Maps continuous latent vectors into 512 discrete structural tokens.
|
| 22 |
+
- Invariant Decoder (300M): Reconstructs full 3D structures, including side chains, from the structural tokens using an architecture adapted from ESMFold.
|
| 23 |
|
| 24 |
This model strikes a balance between reconstruction fidelity and structural locality, optimizing its suitability for downstream tasks such as structure prediction, homology detection, and multimodal protein modeling.
|
| 25 |
|
|
|
|
| 30 |
- Reconstructing Structures (See [below](#reconstructing-structures))
|
| 31 |
- Structure Prediction (See [this section](https://huggingface.co/genbio-ai/AIDO.Protein2StructureToken-16B/blob/main/README.md#structure-prediction) in genbio-ai/AIDO.Protein2StructureToken-16B)
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
## Results
|
| 34 |
|
| 35 |
+
### Reconstructing Structures
|
| 36 |
+

|
| 37 |
+
### Homology Detection
|
| 38 |
+

|
| 39 |
+
### Structure Prediction
|
| 40 |
+

|
| 41 |
|
| 42 |
## How to Use
|
| 43 |
Please see `experiments/AIDO.StructureTokenizer` in [Model Generator](https://github.com/genbio-ai/modelgenerator) for more details.
|
assets/images/architecture.png
ADDED
|
assets/images/homology_detection.png
ADDED
|
assets/images/reconstruction.png
ADDED
|
assets/images/structure_prediction.png
ADDED
|
assets/images/structure_tokenizer/launch_protein_viewer.png
ADDED
|
assets/images/structure_tokenizer/select_files.png
ADDED
|
assets/images/structure_tokenizer/visualize_reconstruction.png
ADDED
|