> ## Documentation Index > Fetch the complete documentation index at: https://proto.evodesign.org/docs/llms.txt > Use this file to discover all available pages before exploring further. # MPNN Sequence Probability > Score sequence compatibility with a structure-conditioned MPNN model.
MPNN Sequence Probability
**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.

evo-design/proto-language/proto\_language/constraint/sequence\_scoring/mpnn\_sequence\_probability\_constraint.py
View source
Constraint contributors
Score proposals by MPNN probability; lower is better. ## API Reference
ConfigMPNNSequenceProbabilityConfig Source
Configuration for structure-conditioned MPNN sequence-probability scoring. Structure-conditioned model used to score the sequence. Options: `ligandmpnn`, `proteinmpnn` Use configured structure\_inputs or each proposal's attached structure for MPNN scoring. Options: `configured_structure_inputs`, `proposal_structure` Structures for MPNN scoring; optional when using proposal structures. Structure chain corresponding to the scored input sequence. Return 1-exp(avg\_log\_likelihood), mean NLL, or perplexity. Options: `probability_loss`, `nll`, `perplexity` Compute MPNN probability with the model or read pmpnn from proposal generator metadata. Options: `model`, `proposal_metadata` Generator metadata namespace to read for pmpnn when score\_source='proposal\_metadata'. ProteinMPNN weights used when model='proteinmpnn'. Options: `proteinmpnn`, `v_48_002`, `v_48_010`, `v_48_030`, `abmpnn`, `soluble` Whether LigandMPNN scoring conditions on fixed-residue sidechain atoms. Ligand-residue distance cutoff (Å) used by LigandMPNN scoring. LigandMPNN implementation used for scoring: Foundry-backed ligand\_mpnn or original LigandMPNN. Options: `ligand_mpnn`, `original` Optional explicit LigandMPNN checkpoint path. Seed for MPNN scoring. None lets proto-tools choose its default seed behavior. Device for MPNN scoring. Whether to print MPNN scoring progress.
## Usage ```python python icon="python" theme={null} from proto_language.core import Constraint from proto_language.constraint import mpnn_sequence_probability_constraint, MPNNSequenceProbabilityConfig constraint = Constraint( inputs=[segment], function=mpnn_sequence_probability_constraint, function_config=MPNNSequenceProbabilityConfig( # Configure parameters here ), ) scores = constraint.evaluate() ``` ## Metadata | Property | Value | | --------------- | -------------------------------------- | | Key | `mpnn-sequence-probability` | | Function | `mpnn_sequence_probability_constraint` | | Category | `sequence_scoring` | | Mode | `discrete` | | Uses GPU | `True` | | Supported Types | `protein` |