Proteinmpnn Membrane Global Noise020

Model Details

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

Converted membrane ProteinMPNN checkpoint with a global soluble/membrane label.

Model Provenance

• Upstream Project: Membrane ProteinMPNN
• Source Release: https://github.com/dauparas/LigandMPNN
• Primary Paper: Robust deep learning-based protein sequence design using ProteinMPNN
• Upstream License: MIT for upstream ProteinMPNN and LigandMPNN code/model parameters

Model Specification

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

Links

• Hub repository: oteam/proteinmpnn-membrane-global-noise020
• Upstream paper: Robust deep learning-based protein sequence design using ProteinMPNN
• Upstream repository: Membrane ProteinMPNN
• Source checkpoint release: https://github.com/dauparas/LigandMPNN
• Code: ofoldx/pipelines/design.py
• Project repository: https://github.com/OTeam-AI4S/OFoldX
• Issues: https://github.com/OTeam-AI4S/OFoldX/issues

Usage

The artifact depends on the ofoldx library. Install it with pip:

pip install ofoldx

Pipeline Usage

Load the artifact from oteam/proteinmpnn-membrane-global-noise020 with the OFoldX task pipeline. Use AutoModel or AutoProcessor only when you need lower-level control:

from ofoldx.pipelines import Pipeline

pipeline = Pipeline.from_pretrained("oteam/proteinmpnn-membrane-global-noise020")

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

This checkpoint is distributed in the LigandMPNN parameter release. The global-label model adds a binary soluble/membrane feature to the ProteinMPNN-style input representation. OFoldX does not redistribute the training set.

Training Procedure

Upstream training follows the ProteinMPNN fixed-backbone inverse-folding setup with a global membrane label and a 0.20 Angstrom noisy-backbone checkpoint. OFoldX only converts the released checkpoint.

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 Membrane ProteinMPNN work for the source checkpoint. If OFoldX supports your work, please also cite or link the OFoldX project repository.

@article{dauparas2022robust,
author = {Dauparas, Justas and Anishchenko, Ivan and Bennett, Nathaniel and Bai, Hua and Ragotte, Robert J. and Milles, Lukas F. and Wicky, Basile I. M. and Courbet, Alexis and de Haas, Rob J. and Bethel, Neville and others},
title = {Robust deep learning-based protein sequence design using ProteinMPNN},
journal = {Science},
volume = {378},
number = {6615},
pages = {49--56},
year = {2022},
doi = {10.1126/science.add2187}
}

Contact

Please use OFoldX GitHub 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.