Skip to main content
LigandMPNN Inverse Folding
License: LigandMPNN is open source and free for academic and commercial use under an MIT license. Please refer to the license for full terms.

This generator is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.

Go to Tool Page
evo-design/proto-language/proto_language/generator/ligandmpnn_generator.py
View source
Copy citation
Generator contributors
Protein sequence generator using LigandMPNN inverse folding model. This generator uses LigandMPNN to design protein sequences that are predicted to fold into a given 3D backbone structure while considering ligand context. Unlike ProteinMPNN, LigandMPNN is aware of non-protein atoms (ligands, cofactors, metal ions) in the structure. LigandMPNN is particularly effective for:
  • Designing enzymes with specific active site geometries
  • Optimizing binding pockets around ligands
  • Creating sequences for cofactor-dependent proteins
  • Redesigning protein-ligand interfaces

​
API Reference

ConfigLigandMPNNGeneratorConfig Source
Configuration object for LigandMPNNGenerator.This class defines configuration parameters for the LigandMPNN generator, which uses the LigandMPNN inverse folding model to design protein sequences conditioned on a given 3D backbone structure and ligand context.LigandMPNN extends ProteinMPNN to be aware of non-protein atoms (ligands, cofactors, metal ions), making it particularly effective for:
  • Enzyme active site design
  • Binding pocket optimization
  • Cofactor-dependent protein design
​
array
Structure(s) with optional chains_to_redesign and fixed_positions constraints.
​
enum
default:"ligand_mpnn"
LigandMPNN implementation: Foundry-backed ligand_mpnn or original LigandMPNN.Options: ligand_mpnn, original
​
number
default:"0.1"
Randomness of sampling (0-1). Near 0 is deterministic; near 1 is proportional to model probs.
​
array
Single-letter amino-acid codes to forbid in the designed sequence.
​
boolean
default:"False"
Whether LigandMPNN conditions on fixed-residue sidechain atoms.
​
number
default:"8.0"
Ligand-residue distance cutoff (Å) used by LigandMPNN.
​
string
Optional explicit LigandMPNN checkpoint path.
​
integer
Optional seed passed directly to the LigandMPNN tool; None uses Proto’s derived seed stream.
​
integer
default:"1"
Number of sequences to process simultaneously on GPU
​
string
default:"cuda"
GPU device for inference (e.g. ‘cuda’ or ‘cuda:0’).
​
boolean
default:"False"
Whether to print status messages during execution.

​
Usage

python

​
Metadata