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

You might also read

Related Articles

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

Sort by
Same author

Fourier Kolmogorov-Arnold Network integrated into BioBERT-based model for Biomedical Named Entity Recognition.

NPJ digital medicine·2026
Same author

A hybrid machine learning model with attention mechanism and multidimensional multivariate feature coding for essential gene prediction.

BMC biology·2025
Same author

Predicting lncRNA-protein interactions using a hybrid deep learning model with dinucleotide-codon fusion feature encoding.

BMC genomics·2024
Same author

Ensemble learning based on bi-directional gated recurrent unit and convolutional neural network with word embedding module for bioactive peptide prediction.

Food chemistry·2024
Same author

A miRNA-disease association prediction model based on tree-path global feature extraction and fully connected artificial neural network with multi-head self-attention mechanism.

BMC cancer·2024
Same author

Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network.

PLoS computational biology·2023

Related Experiment Video

Updated: Sep 15, 2025

Methodology for Accurate Detection of Mitochondrial DNA Methylation
12:11

Methodology for Accurate Detection of Mitochondrial DNA Methylation

Published on: May 20, 2018

13.5K

DNA Methylation Recognition Using Hybrid Deep Learning with Dual Nucleotide Visualization Fusion Feature Encoding.

Li Tan1, Li Mengshan2, Li Yelin1

  • 1College of Physics and Electronic Information, Gannan Normal University, Ganzhou, 341000, China.

Interdisciplinary Sciences, Computational Life Sciences
|July 16, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces DeepDNA-DNVFF, a novel method for predicting DNA methylation. Its advanced feature encoding and deep learning model improve accuracy and offer insights into gene regulation and disease biomarkers.

More Related Videos

Targeted DNA Methylation Analysis by Next-generation Sequencing
08:38

Targeted DNA Methylation Analysis by Next-generation Sequencing

Published on: February 24, 2015

37.3K
Methyl-binding DNA capture Sequencing for Patient Tissues
08:40

Methyl-binding DNA capture Sequencing for Patient Tissues

Published on: October 31, 2016

8.7K

Related Experiment Videos

Last Updated: Sep 15, 2025

Methodology for Accurate Detection of Mitochondrial DNA Methylation
12:11

Methodology for Accurate Detection of Mitochondrial DNA Methylation

Published on: May 20, 2018

13.5K
Targeted DNA Methylation Analysis by Next-generation Sequencing
08:38

Targeted DNA Methylation Analysis by Next-generation Sequencing

Published on: February 24, 2015

37.3K
Methyl-binding DNA capture Sequencing for Patient Tissues
08:40

Methyl-binding DNA capture Sequencing for Patient Tissues

Published on: October 31, 2016

8.7K

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Current machine and deep learning methods for DNA methylation prediction have limitations in feature extraction from DNA sequences.
  • Existing models often focus on single methylation types, lacking universality and robustness.
  • There is a need for advanced methods to fully leverage sequence information for accurate DNA methylation prediction.

Purpose of the Study:

  • To propose a novel and efficient method, DeepDNA-DNVFF, for universal DNA methylation prediction.
  • To develop an improved feature encoding technique that extracts more potential information from DNA sequences.
  • To enhance the prediction accuracy and capture long-range dependencies in DNA sequences.

Main Methods:

  • Developed a new dual nucleotide visual fusion feature encoding (DNVFF) method by integrating 2D DNA visualization techniques.
  • Employed a hybrid deep learning model combining Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and an attention mechanism.
  • Evaluated DeepDNA-DNVFF against traditional encoding methods and state-of-the-art approaches across multiple species datasets.

Main Results:

  • The DNVFF encoding method demonstrated superior extraction of latent feature information from DNA sequences compared to traditional methods.
  • DeepDNA-DNVFF outperformed existing advanced methods on 10 out of 17 species datasets.
  • Achieved a maximum Matthews correlation coefficient approximately 1.24% higher than the state-of-the-art, indicating improved prediction performance.

Conclusions:

  • DeepDNA-DNVFF provides an effective approach for predicting DNA methylation sites.
  • The method offers valuable insights for understanding gene regulatory mechanisms.
  • The findings suggest potential applications in identifying disease biomarkers through accurate DNA methylation prediction.