boltz2 / README.md

Publish OFoldX pipeline artifacts

f752d18 verified 1 day ago

6.12 kB

library_name: ofoldx
tags:
  - biology
  - biomolecular-design
  - protein
  - rna
  - dna
  - pipeline
  - boltz2
  - structure-prediction
  - protein-structure
artifact_kind: pipeline
repo_id: oteam/boltz2
license: mit
base_model: boltz-community/boltz-2
pipeline_tag: other
task: structure_prediction
model-index:
  - name: boltz2
    results: []
widget:
  - pipeline_tag: other
    task: structure_prediction
    example_title: Single-chain protein
    text: |-
      >A
      MKTAYIAKQRQISFVKSHFSRQDILD
    input_format: fasta
  - pipeline_tag: other
    task: structure_prediction
    example_title: Protein complex
    text: |-
      >A
      MKTAYIAKQRQISFVKSHFSRQDILD
      >B
      GSHMRYFVTAVSRPGRGEPRFI
    input_format: fasta

boltz2

OFoldX pipeline artifact for biomolecular structure prediction, using the boltz2 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

Boltz-2-shaped structure-prediction model converted for the OFoldX runtime.

Converted Boltz-2 structure-prediction checkpoint for biomolecular interaction modeling.

Model Provenance

Upstream Project: Boltz-2
Source Checkpoint: boltz2_conf_final.ckpt
Source Release: https://huggingface.co/boltzgen/boltzgen-1
Primary Paper: Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction
Upstream License: MIT for upstream Boltz code and weights

Model Specification

Field	Value
Repository	`oteam/boltz2`
Artifact Kind	`pipeline`
Task	`structure_prediction`
Architecture	`boltz2`
Entrypoint	`ofoldx.pipelines.structure_prediction.StructurePredictionPipeline`
Source Checkpoint	`boltz2_conf_final.ckpt`

Source checkpoint: boltz2_conf_final.ckpt.

Usage

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

pip install ofoldx

Pipeline Usage

Load the artifact from oteam/boltz2 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/boltz2")

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

Interface

Task: structure_prediction
Artifact kind: pipeline
Architecture: boltz2
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 Boltz-2 report describes structure data from PDB structures before 2023-06-01, experimental NMR collections, MD trajectory datasets, AF2 monomer distillation, Boltz-1 complex distillation, and affinity data from PubChem, ChEMBL, BindingDB, and related filtered assay sources. OFoldX does not redistribute the training set.

Training Procedure

Upstream Boltz-2 training is staged across structure, confidence, and affinity objectives. This OFoldX artifact converts a released checkpoint into model.safetensors plus an OFoldX manifest; it does not run Boltz-2 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 Boltz-2 work for the source checkpoint. If OFoldX supports your work, please also cite or link the OFoldX project repository.

@article{passaro2025boltz2,
  author = {Passaro, Saro and Corso, Gabriele and Wohlwend, Jeremy and Reveiz, Mateo and Thaler, Stephan and Somnath, Vignesh Ram and Getz, Noah and Portnoi, Tally and Roy, Julien and Stark, Hannes and Kwabi-Addo, David and Beaini, Dominique and Jaakkola, Tommi and Barzilay, Regina},
  title = {Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction},
  year = {2025},
  doi = {10.1101/2025.06.14.659707},
  journal = {bioRxiv}
}

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 Boltz code and weights. Review both OFoldX and upstream terms before redistribution or production use.

oteam
/

boltz2