LigandMPNN
Pre-trained model for protein sequence design and scoring conditioned on a backbone and non-protein atomic context.
Disclaimer
This is an UNOFFICIAL implementation of the Atomic context-conditioned protein sequence design using LigandMPNN by Justas Dauparas, et al.
The OFFICIAL repository of LigandMPNN is at dauparas/LigandMPNN.
The team releasing LigandMPNN did not write this model card for this model so this model card has been written by the OFoldX team.
Model Details
LigandMPNN is an autoregressive inverse-folding model for protein sequence design with explicit atomic context. In addition to the protein backbone, it embeds nearby ligand, nucleic-acid, metal, and other non-protein atoms. This local chemical context conditions sequence generation around interfaces and binding sites.
Please refer to the Training Details section for more information on the training process.
Variants
- oteam/ligandmpnn-noise005: 0.05 Å training coordinate noise.
- oteam/ligandmpnn-noise010: 0.10 Å training coordinate noise; also available as oteam/ligandmpnn.
- oteam/ligandmpnn-noise020: 0.20 Å training coordinate noise.
- oteam/ligandmpnn-noise030: 0.30 Å training coordinate noise.
Model Specification
| Hidden Size | Encoder Blocks | Atom-Context Blocks | Context Blocks | Decoder Blocks | Neighbors | Context Atoms | Num Parameters (M) |
|---|---|---|---|---|---|---|---|
| 128 | 3 | 2 | 2 | 3 | 32 | 25 | 2.632 |
Links
- Code: ofoldx.models.ligandmpnn
- Paper: Atomic context-conditioned protein sequence design using LigandMPNN
- Developed by: Justas Dauparas, Gyu Rie Lee, Robert Pecoraro, Linna An, Ivan Anishchenko, Cameron Glasscock, and David Baker
- Model type: Atomic-context autoregressive message-passing neural network for protein sequence design
- Original Repository: dauparas/LigandMPNN
Usage
The model file depends on the ofoldx library. You can install it using pip:
pip install ofoldx
Direct Use
Sequence Design
You can use this model directly with a pipeline for sequence design with non-protein atomic context:
import ofoldx
from ofoldx.io import read_structure
structure, _ = read_structure("complex.cif")
pipeline = ofoldx.pipeline("design", model="oteam/ligandmpnn")
result = pipeline(structure)
Each candidate contains the designed molecular target and named sequence scores.
Sequence Scoring
You can use this model directly with a pipeline for sequence scoring with non-protein atomic context:
import ofoldx
from ofoldx.io import read_structure
structure, _ = read_structure("complex.cif")
pipeline = ofoldx.pipeline("score", model="oteam/ligandmpnn")
result = pipeline(structure, num_decoding_orders=8, seed=7)
The result contains designed and global sequence NLL in nats per residue.
Downstream Use
Design and Packing
Combine a designer and an independently loaded MPNN Packer with
LigandMpnnDesignAndPackPipeline to generate side-chain
coordinates after sequence design. See the pipeline guide for composition.
Training Details
LigandMPNN is trained to recover protein sequences from backbone geometry and non-protein atomic context.
Training Data
LigandMPNN was trained on protein assemblies from the PDB available by 16 December 2022, including structures with ligands, nucleic acids, and metals. Protein sequences were clustered at 30% identity.
Training Procedure
LigandMPNN uses autoregressive sequence recovery with coordinate perturbations for robustness.
Citation
@article{dauparas2025atomic,
author = {Dauparas, Justas and Lee, Gyu Rie and Pecoraro, Robert and others},
title = {Atomic context-conditioned protein sequence design using LigandMPNN},
journal = {Nature Methods},
year = {2025},
doi = {10.1038/s41592-025-02626-1}
}
The artifacts distributed in this repository are part of the OFoldX project. If OFoldX supports your research, please cite the OFoldX project as follows:
@software{chen2026ofoldx,
author = {Chen, Zhiyuan},
title = {OFoldX},
year = {2026},
url = {https://github.com/OTeam-AI4S/OFoldX},
}
Contact
Please use GitHub issues of OFoldX for any questions or comments on the model implementation or model card.
Please contact the authors of the LigandMPNN paper 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.
For additional terms and clarifications, please refer to our License FAQ.
SPDX-License-Identifier: AGPL-3.0-or-later