Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Classification of Systems-II01:31

Classification of Systems-II

119
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
119
Classification of Systems-I01:26

Classification of Systems-I

156
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
156
Antibody Structure and Classes01:25

Antibody Structure and Classes

647
Antibodies, also known as immunoglobulins, are produced by B cells in response to foreign substances, such as bacteria and viruses. These proteins are critical for recognizing and neutralizing these substances, protecting the body from potential harm.
The basic structure of an antibody consists of four protein chains: two identical heavy chains and two identical light chains. These chains are held together by disulfide bonds and other non-covalent interactions, forming a Y-shaped structure.
647
Protein Organization01:13

Protein Organization

135.6K
Overview
135.6K
Aggregates Classification01:29

Aggregates Classification

289
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
289
Protein Folding01:22

Protein Folding

116.6K
Overview
116.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Stereotactic centralized ablative radiation therapy: a framework for ultra-heterogeneous radiotherapy of bulky tumors.

Frontiers in oncology·2026
Same author

Preliminary Comparative Analysis of Circulatory Glycosaminoglycan Concentrations and Disaccharide Profiles in Diabetic and Healthy Subjects.

The Eurasian journal of medicine·2026
Same author

SpliceSelectNet: a hierarchical Transformer-based deep learning model for splice site prediction.

Nucleic acids research·2026
Same author

Continuation of anti-tuberculosis therapy after Clostridioides difficile infection: a retrospective cohort study.

Journal of infection and chemotherapy : official journal of the Japan Society of Chemotherapy·2026
Same author

Drinking water temperatures modulate gut microbiota-L-cysteine axis to enhance adipose thermogenesis and alleviate obesity-related metabolic disorders in mice.

Life sciences·2026
Same author

PhenoNMF: A novel multi-layer matrix factorization framework for age-stratified comprehensive phenotypic similarity analysis.

BMC medical informatics and decision making·2026

Related Experiment Video

Updated: May 10, 2025

RNA Secondary Structure Prediction Using High-throughput SHAPE
13:42

RNA Secondary Structure Prediction Using High-throughput SHAPE

Published on: May 31, 2013

31.3K

RNA secondary structure prediction by conducting multi-class classifications.

Jiyuan Yang1, Kengo Sato2, Martin Loza3

  • 1Department of Computer Science, the Graduate School of Information Science and Technology, the University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, 113-8656, Tokyo, Japan.

Computational and Structural Biotechnology Journal
|April 21, 2025
PubMed
Summary

This study presents a simpler deep learning approach for RNA secondary structure prediction, avoiding complex post-processing steps. The new method achieves valid predictions and improved performance, with additional techniques enhancing accuracy across different RNA families.

Keywords:
Deep learningMulti-class classificationPost-processingRNA secondary structure

More Related Videos

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

68.4K
The ITS2 Database
16:17

The ITS2 Database

Published on: March 12, 2012

30.5K

Related Experiment Videos

Last Updated: May 10, 2025

RNA Secondary Structure Prediction Using High-throughput SHAPE
13:42

RNA Secondary Structure Prediction Using High-throughput SHAPE

Published on: May 31, 2013

31.3K
A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

68.4K
The ITS2 Database
16:17

The ITS2 Database

Published on: March 12, 2012

30.5K

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Genomics

Background:

  • Predicting RNA secondary structures is crucial for understanding RNA function but remains a significant computational challenge.
  • Existing deep learning methods often require complex post-processing to ensure prediction validity, potentially limiting accuracy.
  • These post-processing steps add complexity and may hinder the overall performance of RNA structure prediction models.

Purpose of the Study:

  • To develop a simplified deep learning method for RNA secondary structure prediction that eliminates the need for post-processing.
  • To evaluate the efficacy of a novel approach treating RNA secondary structure prediction as multiple multi-class classifications.
  • To introduce and assess auxiliary methods, including data augmentation and cross-family evaluation improvements, to boost model performance.

Main Methods:

  • RNA secondary structure prediction framed as a series of multi-class classification tasks.
  • Implementation of a deep learning model incorporating an attention mechanism and a convolutional neural network.
  • Development of data augmentation strategies for enhanced within-RNA-family prediction.
  • Introduction of a technique to mitigate performance degradation in cross-RNA-family predictions.

Main Results:

  • The proposed method successfully generates valid RNA secondary structure predictions without complex post-processing.
  • The model achieved improved performance compared to existing methods that rely on post-processing adjustments.
  • Data augmentation and cross-family evaluation methods demonstrated significant benefits for prediction accuracy.
  • The study confirmed the effectiveness of the simplified classification approach and additional performance-enhancing techniques.

Conclusions:

  • A novel, simplified deep learning framework enables valid RNA secondary structure prediction without complex post-processing.
  • The attention mechanism and convolutional neural network model, combined with classification, offer a robust prediction strategy.
  • Additional methods for data augmentation and cross-family generalization are effective in improving prediction accuracy.
  • This research provides a more efficient and potentially higher-performing approach to RNA secondary structure prediction.