
License: This constraint can use multiple tools, each under its own license. See the Tools Used tab and each tool’s page for license details.
This constraint 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.
API Reference
Configuration for structure-conditioned MPNN sequence-probability scoring.
enum
default:"ligandmpnn"
Structure-conditioned model used to score the sequence.Options:
ligandmpnn, proteinmpnnenum
default:"configured_structure_inputs"
Use configured structure_inputs or each proposal’s attached structure for MPNN scoring.Options:
configured_structure_inputs, proposal_structurearray
Structures for MPNN scoring; optional when using proposal structures.
string
Structure chain corresponding to the scored input sequence.
enum
default:"probability_loss"
Return 1-exp(avg_log_likelihood), mean NLL, or perplexity.Options:
probability_loss, nll, perplexityenum
default:"model"
Compute MPNN probability with the model or read pmpnn from proposal generator metadata.Options:
model, proposal_metadatastring
Generator metadata namespace to read for pmpnn when score_source=‘proposal_metadata’.
enum
default:"proteinmpnn"
ProteinMPNN weights used when model=‘proteinmpnn’.Options:
proteinmpnn, v_48_002, v_48_010, v_48_030, abmpnn, solubleboolean
default:"False"
Whether LigandMPNN scoring conditions on fixed-residue sidechain atoms.
number
default:"8.0"
Ligand-residue distance cutoff (Å) used by LigandMPNN scoring.
enum
default:"ligand_mpnn"
LigandMPNN implementation used for scoring: Foundry-backed ligand_mpnn or original LigandMPNN.Options:
ligand_mpnn, originalstring
Optional explicit LigandMPNN checkpoint path.
integer
Seed for MPNN scoring. None lets proto-tools choose its default seed behavior.
string
default:"cuda"
Device for MPNN scoring.
boolean
default:"False"
Whether to print MPNN scoring progress.
Usage
python

