Skip to main content
Protein Nearest-Neighbor Gap Gini
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_quality/protein_nearest_neighbor_gap_gini_constraint.py
View source
Constraint contributors
Require low gap Gini against the nearest reference protein.

API Reference

ConfigProteinNearestNeighborGapGiniConfig Source
Configuration for gap Gini against nearest protein neighbors.
string
required
Path to MMseqs2 target database (FASTA file or MMseqs2 createdb output).
string
required
FASTA file used to recover top-hit sequences by target ID.
number
default:"0.1"
Maximum acceptable gap Gini (0-1, inclusive) against the nearest reference protein.
boolean
default:"True"
If True, proposals with no MMseqs2 hit pass as novel sequences.
boolean
default:"True"
Center-crop the pairwise alignment and strip end gaps before computing gap Gini.
Mmseqs2SearchProteinsConfig
Advanced MMseqs2 protein search configuration.
MafftConfig
Advanced MAFFT pairwise alignment configuration.
ReturnsConstraintOutput
One output per proposal. A score of 0.0 passes and 1.0 fails. Metadata contains the nearest target ID, nearest hit sequence, and computed gap Gini.

Usage

python

Metadata