README.md

---
library_name: "ofoldx"
tags:
  - "biology"
  - "biomolecular-design"
  - "protein"
  - "rna"
  - "dna"
  - "pipeline"
  - "proteinmpnn"
  - "design-generation"
  - "protein-design"
artifact_kind: "pipeline"
repo_id: "oteam/solublempnn-noise030"
license: "mit"
pipeline_tag: "other"
task: "design_generation"
model-index:
  - name: "solublempnn-noise030"
    results:
      []
widget:
  - pipeline_tag: "other"
    task: "design_generation"
    example_title: "Backbone sequence design"
    text: "input_structure: backbone.cif\ndesign_chains: A"
    input_format: "structure_path"
  - pipeline_tag: "other"
    task: "design_generation"
    example_title: "Binder design"
    text: "target_structure: target.cif\ntarget_chains: A\ndesign_chains: B"
    input_format: "structure_path"
---

# solublempnn-noise030

OFoldX `pipeline` artifact for biomolecular design generation, using the `proteinmpnn` architecture.

## Disclaimer

This model card was generated by the OFoldX team for an OFoldX `pipeline` artifact.
The upstream model authors did not write this card unless explicitly stated otherwise.

OFoldX is pre-alpha research software. Check the source checkpoint, upstream release, and local validation
before using the artifact for scientific or operational decisions.

## Model Details

ProteinMPNN sequence-design model for protein backbones, including soluble and membrane variants.

Converted SolubleMPNN sequence-design checkpoint for soluble protein backbones.

### Model Provenance

- **Upstream Project**: SolubleMPNN
- **Source Release**: [https://github.com/dauparas/LigandMPNN](https://github.com/dauparas/LigandMPNN)
- **Primary Paper**: [Computational design of soluble and functional membrane protein analogues](https://doi.org/10.1038/s41586-024-07601-y)
- **Upstream License**: MIT for upstream ProteinMPNN and LigandMPNN code/model parameters

### Model Specification

| Field | Value |
| ----- | ----- |
| Repository | `oteam/solublempnn-noise030` |
| Artifact Kind | `pipeline` |
| Task | `design_generation` |
| Architecture | `proteinmpnn` |
| Entrypoint | `ofoldx.pipelines.design.DesignPipeline` |

> [!NOTE]
> Checkpoint metadata: `k_neighbors=48`; the `noiseXXX` suffix identifies the training-noise variant.

### Links

- **Hub repository**: [oteam/solublempnn-noise030](https://huggingface.co/oteam/solublempnn-noise030)
- **Upstream paper**: [Computational design of soluble and functional membrane protein analogues](https://doi.org/10.1038/s41586-024-07601-y)
- **Upstream repository**: [SolubleMPNN](https://github.com/dauparas/ProteinMPNN/tree/main/soluble_model_weights)
- **Source checkpoint release**: [https://github.com/dauparas/LigandMPNN](https://github.com/dauparas/LigandMPNN)
- **Code**: [`ofoldx/pipelines/design.py`](https://github.com/OTeam-AI4S/OFoldX/tree/main/ofoldx/pipelines/design.py)
- **Project repository**: [https://github.com/OTeam-AI4S/OFoldX](https://github.com/OTeam-AI4S/OFoldX)
- **Issues**: [https://github.com/OTeam-AI4S/OFoldX/issues](https://github.com/OTeam-AI4S/OFoldX/issues)

## Usage

The artifact depends on the [`ofoldx`](https://github.com/OTeam-AI4S/OFoldX) library. Install it with pip:

```bash
pip install ofoldx
```

### Pipeline Usage

Load the artifact from `oteam/solublempnn-noise030` with the OFoldX task pipeline. Use `AutoModel` or `AutoProcessor` only when you need lower-level control:

```python
from ofoldx.pipelines import Pipeline

pipeline = Pipeline.from_pretrained("oteam/solublempnn-noise030")
```

When a matching processor is available, load it with `AutoProcessor.from_pretrained(...)` and pass the
processed batch to the model.

### Interface

- **Task**: `design_generation`
- **Artifact kind**: `pipeline`
- **Architecture**: `proteinmpnn`
- **Runtime files**: `manifest.json`, `config.json`, and `model.safetensors` when present

## Training Details

OFoldX did not train these weights. This repository contains a converted checkpoint and OFoldX runtime
metadata for loading it.

### Training Data

The SolubleMPNN work trains like ProteinMPNN on PDB assemblies as of 2021-08-02, filtered to X-ray/cryo-EM structures better than 3.5 A and fewer than 10,000 residues, while excluding annotated transmembrane PDB entries. OFoldX does not redistribute the training set.

### Training Procedure

Upstream SolubleMPNN follows ProteinMPNN-style fixed-backbone inverse-folding training with 48-neighbor noisy-backbone checkpoint variants. OFoldX converts released SolubleMPNN checkpoints into `model.safetensors`; it does not run SolubleMPNN training.

## Evaluation

OFoldX conversion reports and contract tests validate artifact structure and checkpoint loading. Task-level
scientific evaluation should be checked against the corresponding upstream model release or paper.

## Limitations

- This artifact is distributed for research use.
- Inputs must match the model-specific processor and expected biomolecular representation.
- OFoldX is pre-alpha, so APIs and artifact metadata may still change before a stable release.

## Citation

Please cite the upstream SolubleMPNN work for the source checkpoint. If OFoldX supports your work, please also cite or link the OFoldX project repository.

```bibtex
@article{solublempnn2024membrane,
  title = {Computational design of soluble and functional membrane protein analogues},
  journal = {Nature},
  year = {2024},
  doi = {10.1038/s41586-024-07601-y}
}
```

## Contact

Please use [OFoldX GitHub issues](https://github.com/OTeam-AI4S/OFoldX/issues) for questions or comments about this model card.

## License

The Hub `license` metadata, when present, reflects the source checkpoint or upstream project license. The OFoldX project license is not yet finalized.
The source checkpoint is associated with the upstream license noted above: MIT for upstream ProteinMPNN and LigandMPNN code/model parameters. Review both OFoldX and upstream terms before redistribution or production use.