Kirigami: large convolutional kernels improve deep learning-based RNA secondary structure prediction

Marc Harary, Chengxin Zhang
6/4/2024
q-bio.BMcs.AI

No official code found. Best implementation: marc-harary/kirigami (4 stars, MIT, last commit 2024-06-11).

Abstract

We introduce a novel fully convolutional neural network (FCN) architecture for predicting the secondary structure of ribonucleic acid (RNA) molecules. Interpreting RNA structures as weighted graphs, we employ deep learning to estimate the probability of base pairing between nucleotide residues. Unique to our model are its massive 11-pixel kernels, which we argue provide a distinct advantage for FCNs on the specialized domain of RNA secondary structures. On a widely adopted, standardized test set comprised of 1,305 molecules, the accuracy of our method exceeds that of current state-of-the-art (SOTA) secondary structure prediction software, achieving a Matthews Correlation Coefficient (MCC) over 11-40% higher than that of other leading methods on overall structures and 58-400% higher on pseudoknots specifically.

View on arXivView PDF

Code Implementations(1)

marc-harary/kirigamiCommunity100%
MIT

Kirigami: RNA secondary structure prediction via deep learning

41PythonJan 1, 20212 years agoMIT

Similar Papers

RNA Secondary Structure Prediction Using Transformer-Based Deep Learning Models

89% match2024

Comprehensive benchmarking of large language models for RNA secondary structure prediction

86% match1 repo152024

Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction

86% match2026

Scalable Deep Learning for RNA Secondary Structure Prediction

85% match1 repo432023

Rethinking Performance Measures of RNA Secondary Structure Problems

84% match2023

High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures

83% match1 repo222018

Cite this paper

@article{harary2024kirigami,
  title  = {Kirigami: large convolutional kernels improve deep learning-based RNA secondary structure prediction},
  author = {Marc Harary and Chengxin Zhang},
  year   = {2024},
  eprint = {2406.02381},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.02381v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.02381.svg)](https://codeofpaper.com/paper/2406.02381)

Discussion