Related Experiment Video
Updated: Sep 10, 2025

RNA Secondary Structure Prediction Using High-throughput SHAPE
Published on: May 31, 2013
ECSFinder: optimized prediction of evolutionarily conserved RNA secondary structures from genome sequences.
Vanda Gaonac'h-Lovejoy1,2,3, John S Mattick4,5, Martin Sauvageau1,3,6
1Department of Biochemistry and Molecular Medicine, Université de Montréal, Montreal, QC H3T 1J4, Canada.
Predicting conserved RNA secondary structures is key for understanding long noncoding RNA (lncRNA) function. A new machine learning tool, ECSFinder, integrates strengths of existing methods to improve accuracy in identifying these structures genome-wide.
Area of Science:
- Genomics
- Bioinformatics
- Molecular Biology
Background:
- Accurate prediction of RNA secondary structures is crucial for understanding the evolutionary conservation and functional roles of long noncoding RNAs (lncRNAs).
- Existing tools like SISSIz and R-scape have limitations in identifying evolutionarily conserved RNA structures (ECSs).
Purpose of the Study:
- To benchmark SISSIz and R-scape for predicting ECSs using experimental frameworks.
- To develop an improved method for identifying ECSs by integrating the strengths of existing tools.
- To implement this improved method in a new tool for large-scale applications.
Main Methods:
- Benchmarking SISSIz and R-scape against mitochondrial RNA structures and simulated Rfam structures.
- Evaluating interpretable machine learning approaches to combine thermodynamic stability and covariation metrics.
- Developing a random forest classifier integrating RNALalifold, SISSIz, and R-scape features.
Main Results:
- SISSIz and R-scape showed similar overall performance but with distinct detection preferences.
- A machine learning classifier significantly outperformed individual tools in ECS identification.
- The developed classifier successfully integrated thermodynamic stability and covariation metrics.
Conclusions:
- A novel machine learning approach, implemented in ECSFinder, enhances the accuracy of identifying conserved RNA secondary structures.
- ECSFinder offers robust, genome-wide identification of RNA structures, providing insights into lncRNA evolution and function.
- This tool is valuable for large-scale comparative genomics and understanding lncRNA modular elements.
Related Concept Videos
RNA Structure
Different Types of RNA Have the Same Basic Structure
There are three main types of ribonucleic acid (RNA) involved in protein synthesis: messenger RNA (mRNA), transfer RNA (tRNA), and ribosomal RNA (rRNA). All three...
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
RNA Stability
Evolutionary Relationships through Genome Comparisons
Gene Evolution - Fast or Slow?
In contrast, regions which code...
Conservation of Protein Domains Over Different Proteins
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...

