biohub
/

ESMFold2

@@ -1,19 +1,34 @@
 ---
 license: mit
 ---
 # Model Card for ESMFold2
 ## Model Details
-ESMFold2 is a state-of-the-art protein structure prediction model that combines ESMC (6B parameter) language model representations with a diffusion-based structure prediction architecture inspired by AlphaFold3.
 The model predicts high-resolution, all-atom 3D protein structures directly from amino acid sequences, with optional multiple sequence alignment (MSA) input for enhanced accuracy on challenging targets. The model outputs comprehensive structural information including all-atom coordinates (backbone and side chains), confidence metrics (pLDDT, pAE, pTM, iPTM), and optional distogram predictions for detailed analysis of predicted structures. Unlike ESMFold, ESMCFold is able to predict structures for all biomolecules, including small molecules, DNA, RNA, and modified amino acids.
-ESMFold2 is capable of either single-sequence or MSA conditioned structure prediction for improved accuracy on difficult targets
-For additional information, visit the [Biohub Platform](https://biohub.ai) for no-code tools, step-by-step tutorial notebooks, and detailed information on the models.
-## System Requirements
 * Compute Requirements: GPU
 * PyTorch environment with GPU support recommended.
@@ -22,6 +37,10 @@ For additional information, visit the [Biohub Platform](https://biohub.ai) for n
 Coming soon
 ### Model Architecture
 The architecture consists of an input embedder, which includes the ESMC language model embeddings, a pairwise folding block trunk, an atom diffusion module, an optional MSA encoder, and a confidence head.
@@ -76,8 +95,8 @@ This hybrid architecture combines the representational power of large-scale prot
 | Model | MSA Conditioning | Description | Data Cutoff |
 | :---- | :---- | :---- | :---- |
-| [esmfold2](https://huggingface.co/biohub/esmfold2-fast) | No | Inference optimized single-sequence structure prediction model | June 2025, older cutoff is Sept 2021 |
-| [esmfold2-fast](https://huggingface.co/biohub/esmfold2) | Yes | Large model, capable of either single-sequence or MSA conditioned structure prediction for improved accuracy on difficult targets | June 2025, older cutoff is Sept 2021 |
 **Confidence Head (optional, for inference):**
@@ -157,9 +176,6 @@ Refer to the [paper](https://biohub.ai/papers/esmc.pdf) for details on additiona
 Do not use the model for the following purposes:
-- Clinical diagnosis or treatment recommendations.
-- Any use that violates applicable laws, regulations (including trade compliance laws), or third-party rights such as privacy or intellectual property rights.
-- Any use that is prohibited by the [model license](https://github.com/Biohub/esm/blob/main/LICENSE.md).
 - Any use that is prohibited by the [Acceptable Use Policy](https://biohub.org/acceptable-use-policy/).
 ### Caveats and Recommendations
@@ -176,3 +192,4 @@ Should you have any security or privacy issues or questions related to this mode
 Many people on the Biohub AI Research team and prior EvolutionaryScale team contributed to the development of this model. It would not have been possible without them.

 ---
 license: mit
+language:
+- en
+tags:
+- biology
+- esm
+- protein
+- protein-structure-prediction
+- structure-prediction
+- protein-design
+- 3d-structure
+- confidence-estimation
+- molecular-dynamics
+- transformers
 ---
 # Model Card for ESMFold2
 ## Model Details
+ESMFold2 is a state-of-the-art model for protein structure prediction and design that defines a new frontier for speed and accuracy. The model achieves unprecedented success rates for protein binder and antibody generation, validated through biophysical and functional characterization.
 The model predicts high-resolution, all-atom 3D protein structures directly from amino acid sequences, with optional multiple sequence alignment (MSA) input for enhanced accuracy on challenging targets. The model outputs comprehensive structural information including all-atom coordinates (backbone and side chains), confidence metrics (pLDDT, pAE, pTM, iPTM), and optional distogram predictions for detailed analysis of predicted structures. Unlike ESMFold, ESMCFold is able to predict structures for all biomolecules, including small molecules, DNA, RNA, and modified amino acids.
+ESMFold2 is capable of either single-sequence or MSA conditioned structure prediction for improved accuracy on difficult targets.
+To run this model with the Biohub Platform API, visit the [Biohub Platform](https://biohub.ai/).
+Read more about ESMFold2 in our paper [here](https://biohub.ai/papers/esmc.pdf).
+### System Requirements
 * Compute Requirements: GPU
 * PyTorch environment with GPU support recommended.
 Coming soon
+### Citation
+Coming soon.
 ### Model Architecture
 The architecture consists of an input embedder, which includes the ESMC language model embeddings, a pairwise folding block trunk, an atom diffusion module, an optional MSA encoder, and a confidence head.
 | Model | MSA Conditioning | Description | Data Cutoff |
 | :---- | :---- | :---- | :---- |
+| [esmfold2-fast](https://huggingface.co/biohub/esmfold2-fast) | No | Inference optimized single-sequence structure prediction model | June 2025, older cutoff is Sept 2021 |
+| [esmfold2](https://huggingface.co/biohub/esmfold2) | Yes | Large model, capable of either single-sequence or MSA conditioned structure prediction for improved accuracy on difficult targets | June 2025, older cutoff is Sept 2021 |
 **Confidence Head (optional, for inference):**
 Do not use the model for the following purposes:
 - Any use that is prohibited by the [Acceptable Use Policy](https://biohub.org/acceptable-use-policy/).
 ### Caveats and Recommendations
 Many people on the Biohub AI Research team and prior EvolutionaryScale team contributed to the development of this model. It would not have been possible without them.