| --- |
| tags: |
| - Biology |
| - Protein |
| - RNA |
| - DNA |
| - Structure Prediction |
| license: agpl-3.0 |
| library_name: ofoldx |
| pipeline_tag: other |
| --- |
| |
| # Protenix |
|
|
| Pre-trained model for all-atom structure prediction of proteins, nucleic acids, small molecules, and their complexes. |
|
|
| ## Disclaimer |
|
|
| This is an UNOFFICIAL implementation of the [Protenix - Advancing Structure Prediction Through a Comprehensive AlphaFold3 Reproduction](https://doi.org/10.1101/2025.01.08.631967) by Xinshi Chen, Yuxuan Zhang, et al. |
|
|
| The OFFICIAL repository of Protenix is at [bytedance/Protenix](https://github.com/bytedance/Protenix). |
|
|
| **The team releasing Protenix did not write this model card for this model so this model card has been written by the OFoldX team.** |
|
|
| ## Model Details |
|
|
| Protenix combines atom and token embeddings with an MSA-conditioned recycled Pairformer trunk, EDM coordinate |
| diffusion, and distogram and confidence heads. Template, structure-conditioned, and constraint variants provide |
| additional structural evidence; the constraint model supports atom contacts, token contacts, pockets, and substructures. |
|
|
| Please refer to the [Training Details](#training-details) section for more information on the training process. |
|
|
| ### Variants |
|
|
| - **[oteam/protenix](https://huggingface.co/oteam/protenix)**: The default v1.0 all-atom structure predictor. |
| - **[oteam/protenix-20250630](https://huggingface.co/oteam/protenix-20250630)**: The v1.0 model trained on a later data cutoff. |
| - **[oteam/protenix-v0.5](https://huggingface.co/oteam/protenix-v0.5)**: The v0.5 base model, also available as |
| [oteam/protenix-base](https://huggingface.co/oteam/protenix-base). |
| - **[oteam/protenix-constraint](https://huggingface.co/oteam/protenix-constraint)**: The v0.5 model with constraint conditioning. |
| - **[oteam/protenix-mini-tmpl](https://huggingface.co/oteam/protenix-mini-tmpl)**: The v0.5 mini model with structure conditioning. |
| - **Protenix-v2**: The larger template-conditioned model, using locally converted parameters. Select the `protenix-v2` checkpoint identifier when converting its weights. |
|
|
| ### Model Specification |
|
|
| | Variant | Pairformer Blocks | MSA Stages | Single Size | Pair Size | Recycling Steps | Num Parameters (M) | |
| | ------------------------ | ----------------- | ---------- | ----------- | --------- | --------------- | ------------------ | |
| | Base v0.5 | 48 | 4 | 384 | 128 | 10 | 368.123 | |
| | Constraint v0.5 | 48 | 4 | 384 | 128 | 10 | 368.339 | |
| | Template v1 | 48 | 4 | 384 | 128 | 10 | 368.549 | |
| | Mini v0.5 | 16 | 1 | 384 | 128 | 4 | 134.102 | |
| | Mini ESM / ISM v0.5 | 16 | 1 | 384 | 128 | 4 | 2967.899 | |
| | Structure condition v0.5 | 16 | 1 | 384 | 128 | 4 | 134.212 | |
| | Tiny v0.5 | 8 | 1 | 384 | 128 | 4 | 109.535 | |
| | Protenix-v2 | 48 | 4 | 384 | 256 | 10 | 464.535 | |
|
|
| The Mini ESM and ISM counts include the frozen ESM2 encoder. |
|
|
| ### Links |
|
|
| - **Code**: [ofoldx.models.protenix](https://github.com/OTeam-AI4S/OFoldX/tree/main/ofoldx/models/protenix) |
| - **Paper**: |
| [Protenix - Advancing Structure Prediction Through a Comprehensive AlphaFold3 Reproduction](https://doi.org/10.1101/2025.01.08.631967) |
| - **Developed by**: Xinshi Chen, Yuxuan Zhang, Chan Lu, Wenzhi Ma, Jiaqi Guan, Chengyue Gong, Jincai Yang, Hanyu Zhang, |
| Ke Zhang, Shenghao Wu, Kuangqi Zhou, Yanping Yang, Zhenyu Liu, Lan Wang, Bo Shi, Shaochen Shi, and Wenzhi Xiao |
| - **Model type**: Pairformer-based all-atom biomolecular structure predictor with optional learned constraints |
| - **Original Repository**: [bytedance/Protenix](https://github.com/bytedance/Protenix) |
|
|
| ## 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/protenix") |
| result = pipeline(structure, seed=7) |
| ``` |
|
|
| The result contains predicted structures and confidence values. Atoms must have known elements and formal charges. |
|
|
| ### Downstream Use |
|
|
| #### Chemical Guidance |
|
|
| You can enable training-free chemical guidance during sampling: |
|
|
| ```python |
| import ofoldx |
| from ofoldx.io import read_structure |
| from ofoldx.models.protenix import ProtenixTfgGuidance |
| |
| structure, report = read_structure("input.cif") |
| pipeline = ofoldx.pipeline("fold", model="oteam/protenix") |
| result = pipeline(structure, tfg_guidance=ProtenixTfgGuidance(), seed=7) |
| ``` |
|
|
| Guidance is disabled by default and can be configured through `ProtenixTfgGuidance`. |
|
|
| Template repositories accept `templates=`. Structure-conditioned repositories accept `structure_condition=` with an |
| in-memory structure. Constraint repositories accept `atom_contacts`, `token_contacts`, `pocket`, and `substructure=`. |
| The mini template checkpoint uses the structure-conditioned graph, rather than the ordinary template graph. |
|
|
| ## Training Details |
|
|
| Protenix is trained with coordinate, geometric, distogram, and confidence objectives in a staged training program. |
|
|
| ### Training Data |
|
|
| The Protenix training data includes biomolecular structures from the [PDB](https://www.rcsb.org/) and AlphaFold 2 |
| predictions used for distillation. The [upstream training guide](https://github.com/bytedance/Protenix/blob/main/docs/training_inference_instructions.md) |
| describes data preparation. |
|
|
| ### Training Procedure |
|
|
| Protenix is trained in stages with coordinate denoising, geometric, distogram, and confidence objectives. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @article{protenix2025advancing, |
| author = {ByteDance AML AI4Science Team and Chen, Xinshi and Zhang, Yuxuan and others}, |
| title = {Protenix - Advancing Structure Prediction Through a Comprehensive AlphaFold3 Reproduction}, |
| year = {2025}, |
| doi = {10.1101/2025.01.08.631967}, |
| journal = {bioRxiv} |
| } |
| ``` |
|
|
| > [!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 [Protenix paper](https://doi.org/10.1101/2025.01.08.631967) 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 |
| ``` |
|
|
