RNA Feature Vector Similarity

Compare RNA structures using cosine similarity of 10-dim feature vectors.

License: ViennaRNA is licensed under Custom (ViennaRNA Package License) and may require explicit attribution when utilized. Please refer to the license for full terms.

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.

---

Tools Used Tools Used Source Source Cite Cite

Go to Tool Page

proto-bio/proto-language/proto_language/constraint/rna_secondary_structure/structure_similarity_constraint.py

View source

@article{lorenz2011viennarna,
  title={ViennaRNA Package 2.0},
  author={Lorenz, Ronny and Bernhart, Stephan H and H{\"o}ner zu Siederdissen, Christian and Tafer, Hakim and Flamm, Christoph and Stadler, Peter F and Hofacker, Ivo L},
  journal={Algorithms for Molecular Biology},
  volume={6},
  number={1},
  pages={26},
  year={2011},
  publisher={BioMed Central},
  doi={10.1186/1748-7188-6-26}
}

Copy citation

Construct 10-dim feature vectors and compare using cosine similarity.

Returns (1 - similarity) / 2, scaling cosine similarity from [-1, 1] to [0, 1].

API Reference

ConfigRNAFeatureSimilarityConfig Source

Configuration for feature vector similarity constraint.

Compares 10-dimensional structural feature vectors using cosine similarity. Features include: length, number of pairs, pairing ratio, stem statistics (avg, max, count), loop statistics, MFE, MFE per nucleotide, and hairpin count.

Inherits from RNAStructureConstraintBaseConfig.

reference_sequence · string · required

Reference RNA/DNA sequence to compare against

temperature · number · default: "37.0"

Folding temperature in Celsius

ReturnsConstraintOutput

Per-proposal score ((1 - cosine) / 2) with metadata for the reference/candidate feature vectors, predicted structure, and candidate MFE.

Usage

python

from proto_language.core import Constraint
from proto_language.constraint import rna_feature_similarity_constraint, RNAFeatureSimilarityConfig

constraint = Constraint(
    inputs=[segment],
    function=rna_feature_similarity_constraint,
    function_config=RNAFeatureSimilarityConfig(
        # Configure parameters here
    ),
)

scores = constraint.evaluate()

Metadata

Property	Value
Key	rna-feature-similarity
Function	rna_feature_similarity_constraint
Category	rna_secondary_structure
Mode	discrete
Uses GPU	False
Supported Types	dna, rna