Publish OFoldX pipeline artifacts

53e3071 verified 2 months ago

6.61 kB

library_name: ofoldx
tags:
  - biology
  - biomolecular-design
  - protein
  - rna
  - dna
  - model
  - proteinmpnn
  - design-generation
  - protein-design
artifact_kind: model
repo_id: oteam/proteinmpnn-noise002
license: mit
pipeline_tag: other
task: design_generation
model-index:
  - name: proteinmpnn-noise002
    results: []
widget:
  - pipeline_tag: other
    task: design_generation
    example_title: Backbone sequence design
    text: |-
      input_structure: backbone.cif
      design_chains: A
    input_format: structure_path
  - pipeline_tag: other
    task: design_generation
    example_title: Binder design
    text: |-
      target_structure: target.cif
      target_chains: A
      design_chains: B
    input_format: structure_path

proteinmpnn-noise002

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

Disclaimer

This model card was generated by the OFoldX team for an OFoldX model 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 ProteinMPNN-family sequence-design checkpoint for fixed-backbone inverse folding.

Model Provenance

Upstream Project: ProteinMPNN / LigandMPNN release
Source Checkpoint: proteinmpnn_v_48_002.pt
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

Field	Value
Repository	`oteam/proteinmpnn-noise002`
Artifact Kind	`model`
Task	`design_generation`
Architecture	`proteinmpnn`
Entrypoint	`ofoldx.models.proteinmpnn.model.ProteinMPNNDesignGenerator`
Config	`config.json`
Weights	`model.safetensors`
Source Checkpoint	`proteinmpnn_v_48_002.pt`
Checkpoint Variant	`proteinmpnn_v_48_002`
k-Neighbors	`48`
Node Feature Size	`0`
Training Noise	`0.02 Angstrom`

Source checkpoint: proteinmpnn_v_48_002.pt; the public repo suffix records the upstream Gaussian noise variant (0.02 Angstrom).

Usage

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

pip install ofoldx

Pipeline Usage

Load the artifact from oteam/proteinmpnn-noise002 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-noise002")
output = pipeline(...)

from ofoldx import AutoModel

model = AutoModel.from_pretrained("oteam/proteinmpnn-noise002")

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: model
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

ProteinMPNN was trained for fixed-backbone protein sequence design on PDB biounits with a 2021-08-02 data snapshot. OFoldX does not redistribute the training set.

Training Procedure

Upstream ProteinMPNN trains graph-neural inverse-folding models with 48-neighbor checkpoints and multiple Gaussian backbone-noise variants. OFoldX converts released ProteinMPNN-family checkpoints into model.safetensors; it does not run ProteinMPNN 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 ProteinMPNN / LigandMPNN release 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.

oteam
/

proteinmpnn-noise002