Skip to main content
NA-MPNN Motif Specificity
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/protein_structure/dna_motif_specificity_constraint.py
View source
Constraint contributors
Specificity score from NA-MPNN predicted base-preference matrices. Predicts (or reuses) a protein-DNA complex for each candidate, predicts a per-position base PPM with NA-MPNN, and scores the specificity advantage of the target motif over the best off-target relative to desired_margin (using the configured scoring_mode).

​
API Reference

ConfigNAMPNNMotifSpecificityConfig Source
Config for the na-mpnn-motif-specificity constraint.
​
NAMPNNSpecificityConfig
Tool config for na-mpnn-specificity predictions.
​
enum
default:"alphafold3"
Predictor for the protein-DNA complex; must be DNA-capable (alphafold3/boltz2/protenix).Options: esmfold, esmfold2, alphafold3, boltz2, chai1, protenix, alphafold2, alphafold2_binder
​
ESMFoldConfig
Configuration for ESMFold structure prediction.
​
ESMFold2Config
Configuration for ESMFold2 structure prediction.
​
AlphaFold3Config
Configuration for AlphaFold3 structure prediction.
​
Boltz2Config
Configuration for Boltz2 structure prediction.
​
Chai1Config
Configuration for Chai1 structure prediction.
​
ProtenixConfig
Configuration for Protenix structure prediction.
​
AlphaFold2Config
Configuration for the general AlphaFold2 multimer structure predictor.
​
AlphaFold2BinderStructureConfig
Configuration for the AF2 binder-design backend.
​
string
required
Target DNA motif in A/C/G/T alphabet.
​
List[string]
required
Off-target motifs used for the specificity margin.
​
List[integer]
0-based DNA indices mapped to motif positions (required only when scoring_mode=‘cross_entropy’).
​
number
default:"1.0"
Specificity advantage satisfying the term; scale follows scoring_mode (CE or log-prob).
​
integer
default:"0"
Canonical DNA chain label for motif indexing when multiple DNA chains exist (fwd strand 0).
​
enum
default:"sliding_logprob"
Motif scoring: fixed-index cross_entropy or sliding-window log-prob.Options: cross_entropy, sliding_logprob
ReturnsConstraintOutput
One result per candidate; score 0.0 (best) when the target beats every off-target by desired_margin, 1.0 (worst) otherwise. Metadata carries the target/off-target scores and advantage.

​
Usage

python

​
Metadata