Transformers
Safetensors
English
esmfold2
biology
esm
protein
protein-structure-prediction
structure-prediction
protein-design
3d-structure
confidence-estimation
molecular-dynamics
Instructions to use biohub/ESMFold2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use biohub/ESMFold2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("biohub/ESMFold2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ ESMfold2 was evaluated against state-of-the-art single-sequence and MSA-based st
|
|
| 42 |
|
| 43 |
![][image1]
|
| 44 |
|
| 45 |
-
Refer to the [paper](https://biohub.ai/papers/
|
| 46 |
|
| 47 |
### Usage
|
| 48 |
|
|
@@ -142,9 +142,7 @@ protein = ProteinInput(
|
|
| 142 |
)
|
| 143 |
ligand = LigandInput(id="L", ccd=["ATP"])
|
| 144 |
|
| 145 |
-
|
| 146 |
-
# once the Biohub Platform inference server announces it.
|
| 147 |
-
client = esmfold2_client(model="esmc-fold-flash-2604", token=os.environ["ESM_API_KEY"])
|
| 148 |
|
| 149 |
spi = StructurePredictionInput(sequences=[protein, ligand])
|
| 150 |
result = client.fold_all_atom(
|
|
|
|
| 42 |
|
| 43 |
![][image1]
|
| 44 |
|
| 45 |
+
Refer to the [paper](https://biohub.ai/papers/esm_protein.pdf) for details on additional performance metrics.
|
| 46 |
|
| 47 |
### Usage
|
| 48 |
|
|
|
|
| 142 |
)
|
| 143 |
ligand = LigandInput(id="L", ccd=["ATP"])
|
| 144 |
|
| 145 |
+
client = esmfold2_client(model="esmfold2-fast-2026-05", token=os.environ["ESM_API_KEY"])
|
|
|
|
|
|
|
| 146 |
|
| 147 |
spi = StructurePredictionInput(sequences=[protein, ligand])
|
| 148 |
result = client.fold_all_atom(
|