| --- |
| tags: |
| - Biology |
| - Protein |
| - Structure Prediction |
| license: agpl-3.0 |
| library_name: ofoldx |
| pipeline_tag: other |
| --- |
| |
| # ESMFold2 |
|
|
| Pre-trained models for all-atom structure prediction and gradient-based protein binder design. |
|
|
| ## Disclaimer |
|
|
| This is an UNOFFICIAL implementation of the [Language Modeling Materializes a World Model of Protein Biology](https://biohub.ai/papers/esm_protein.pdf) by Salvatore Candido, et al. |
|
|
| The OFFICIAL repository of ESMFold2 is at [Biohub/esm](https://github.com/Biohub/esm). |
|
|
| **The team releasing ESMFold2 did not write this model card for this model so this model card has been written by the OFoldX team.** |
|
|
| ## Model Details |
|
|
| ESMFold2 uses a frozen ESMC language model to supply sequence representations to a recurrent folding trunk. |
| A diffusion head generates atomic coordinates, and distogram and confidence heads score the prediction. Supported |
| checkpoints also accept protein MSA evidence. Experimental variants expose differentiable inversion for protein binder |
| sequence design. |
|
|
| Please refer to the [Training Details](#training-details) section for more information on the training process. |
|
|
| ### Variants |
|
|
| - **[oteam/esmfold2](https://huggingface.co/oteam/esmfold2)**: The full 48-block folding model with optional MSA conditioning. |
| - **[oteam/esmfold2-fast](https://huggingface.co/oteam/esmfold2-fast)**: The 24-block single-sequence folding model. |
| - **[oteam/esmfold2-experimental](https://huggingface.co/oteam/esmfold2-experimental)**: The binder-design workflow. |
| - **[oteam/esmfold2-experimental-fast](https://huggingface.co/oteam/esmfold2-experimental-fast)**: The experimental fast model used for binder sequence optimization. |
|
|
| ### Model Specification |
|
|
| | Variant | Folding Blocks | MSA | ESMC | Single Size | Pair Size | Atom Size | Token Size | Recurrent Updates | Sampling Steps | Num Parameters (M) | |
| | ----------------- | -------------- | --- | ---- | ----------- | --------- | --------- | ---------- | ----------------- | -------------- | ------------------ | |
| | ESMFold2 | 48 | yes | 6B | 384 | 256 | 128 | 768 | 4 | 14 | 6579.742 | |
| | ESMFold2 Fast | 24 | no | 6B | 384 | 256 | 128 | 768 | 4 | 14 | 6533.723 | |
| | Experimental | 48 | yes | 6B | 384 | 256 | 128 | 768 | 4 | 14 | 6577.328 | |
| | Experimental Fast | 24 | no | 6B | 384 | 256 | 128 | 768 | 4 | 14 | 6530.863 | |
|
|
| Parameter counts include the frozen ESMC encoder. |
|
|
| ### Links |
|
|
| - **Code**: [ofoldx.models.esmfold2](https://github.com/OTeam-AI4S/OFoldX/tree/main/ofoldx/models/esmfold2) |
| - **Paper**: [Language Modeling Materializes a World Model of Protein Biology](https://biohub.ai/papers/esm_protein.pdf) |
| - **Developed by**: Salvatore Candido, Thomas Hayes, Alexander Derry, Roshan Rao, Zeming Lin, Robert Verkuil, Bryan Wu, |
| Jin Sub Lee, Elise S. Bruguera, Jehan A. Keval, Mykhailo Kopylov, John E. Pak, Wesley Wu, Neil Thomas, Samson |
| Mataraso, Alvin Hsu, Ashton C. Trotman-Grant, Kilian Fatras, Allan dos Santos Costa, Rohil Badkundri, Halil Akın, |
| Deniz Oktay, Jonathan Deaton, Elizabeth Montabana, Hrishita Sitwala, Yue Yu, Marius Wiggert, Dylan Alexander Carlin, |
| Anthony W. Goering, Tomasz Blazejewski, McCullen Sandora, Michael Hla, Tina Z. Jia, Leon H. Kloker, Nicholas J. |
| Sofroniew, Masatoshi Uehara, Jassi Pannu, Sharrol Bachas, Daniel S. Liu, Tom Sercu, and Alexander Rives |
| - **Model type**: ESMC-conditioned recurrent all-atom folding model with diffusion coordinate generation |
| - **Original Repository**: [Biohub/esm](https://github.com/Biohub/esm) |
|
|
| ## Usage |
|
|
| The model file depends on the [`ofoldx`](https://ofoldx.valtech.ai/) library. You can install it using pip: |
|
|
| ```bash |
| pip install ofoldx |
| ``` |
|
|
| ### Direct Use |
|
|
| #### Structure Prediction |
|
|
| You can use this model directly with a pipeline for all-atom structure prediction: |
|
|
| ```python |
| import ofoldx |
| from ofoldx.io import read_structure |
| |
| structure, report = read_structure("input.cif") |
| pipeline = ofoldx.pipeline("fold", model="oteam/esmfold2") |
| result = pipeline(structure, seed=7) |
| ``` |
|
|
| The result contains predicted structures and confidence values. The standard and Fast models share the frozen |
| [MultiMolecule ESMC-6B checkpoint](https://huggingface.co/multimolecule/esmc-6b); its exact revision is recorded in the |
| model configuration and downloaded through the Hugging Face cache. Protein sequences are also accepted directly. |
|
|
| #### Binder Design |
|
|
| You can use this model directly with a pipeline for experimental binder sequence optimization: |
|
|
| ```python |
| import ofoldx |
| |
| pipeline = ofoldx.pipeline("design", model="oteam/esmfold2-experimental") |
| result = pipeline("MKTAYIAKQRQISFVKSHFSRQ", num_binder_residues=80, seed=7) |
| ``` |
|
|
| The workflow optimizes binder sequences with gradients and ranks candidates using folding predictions. It requires the |
| full experimental repository, including when scaling critics are disabled. Antibody designs are detected automatically |
| unless `is_antibody` is specified. |
| Antibody detection and CDR scoring use ANARCI and require HMMER's `hmmscan` executable on `PATH`. |
|
|
| ## Training Details |
|
|
| ESMFold2 combines pretrained folding models with learned confidence and scaling components for structure prediction. |
|
|
| ### Training Data |
|
|
| Biohub reports training on Protein Data Bank (PDB) and AlphaFold DB (AFDB) data, with a September 2021 cutoff for |
| ESMFold2 and ESMFold2-Fast. ESMC was pretrained separately; consult its model card for the sequence corpus. |
|
|
| ### Training Procedure |
|
|
| ESMFold2 is trained with diffusion, distogram, and confidence objectives for all-atom structure prediction. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{candido2026language, |
| title = {Language Modeling Materializes a World Model of Protein Biology}, |
| author = {Candido, Salvatore and Hayes, Thomas and Derry, Alexander and others}, |
| year = {2026}, |
| url = {https://biohub.ai/papers/esm_protein.pdf}, |
| note = {Preprint} |
| } |
| ``` |
|
|
| > [!NOTE] |
| > The artifacts distributed in this repository are part of the OFoldX project. |
| > If OFoldX supports your research, please cite the OFoldX project as follows: |
|
|
| ```bibtex |
| @software{chen2026ofoldx, |
| author = {Chen, Zhiyuan}, |
| title = {OFoldX}, |
| year = {2026}, |
| url = {https://github.com/OTeam-AI4S/OFoldX}, |
| } |
| ``` |
|
|
| ## Contact |
|
|
| Please use GitHub issues of [OFoldX](https://github.com/OTeam-AI4S/OFoldX/issues) for any questions or comments on the model implementation or model card. |
|
|
| Please contact the authors of the [ESMFold2 paper](https://biohub.ai/papers/esm_protein.pdf) for questions or comments on the paper/model. |
|
|
| ## License |
|
|
| The model weights, implementation, configuration, and documentation distributed by OFoldX are licensed under the |
| [GNU Affero General Public License](https://github.com/OTeam-AI4S/OFoldX/blob/main/license.md). |
|
|
| For additional terms and clarifications, please refer to our |
| [License FAQ](https://github.com/OTeam-AI4S/OFoldX/blob/main/license-faq.md). |
|
|
| ```spdx |
| SPDX-License-Identifier: AGPL-3.0-or-later |
| ``` |
|
|
