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

Corrigendum to "Development and validation of a risk prediction model and prediction tools for post-thrombotic syndrome in patients with lower limb deep vein thrombosis" [Int. J. Med. Inform. 187 (2024) 105468].

International journal of medical informatics·2026
Same author

Rapid and Simple Detection of Enterocytozoon Bieneusi Using Lateral Flow Assay Based on Recombinase Polymerase Amplification or Nested PCR Combined with CRISPR-Cas12a.

Acta parasitologica·2026
Same author

Rapid and Simple Detection of <i>Mycobacterium avium</i> subsp. <i>paratuberculosis</i> Using a Lateral Flow Assay Based on CRISPR-Cas12a Combined with Recombinase Polymerase Amplification or Nested PCR.

Pathogens (Basel, Switzerland)·2026
Same author

Ligand-Controlled Cobalt-Catalyzed Regioselective Annulation: Divergent Synthesis of Indenols from <i>o</i>-Haloaromatic Ketones and Terminal Alkynes.

Organic letters·2025
Same author

MLWNNR: LncRNA-Disease Association Prediction with Multi-Kernel Learning-Driven Weighted Nuclear Norm Regularization.

Interdisciplinary sciences, computational life sciences·2025
Same author

Sheep challenged with sheep-derived type II Mycobacterium avium subsp. paratuberculosis: the first experimental model of paratuberculosis in China.

BMC veterinary research·2025

Related Experiment Video

Updated: Jul 1, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

749

4 mC site recognition algorithm based on pruned pre-trained DNABert-Pruning model and fused artificial feature

Guo-Bo Xie1, Yi Yu1, Zhi-Yi Lin1

  • 1Guangdong University of Technology, Guangzhou, 510000, China.

Analytical Biochemistry
|March 8, 2024
PubMed
Summary

A new algorithm, DNABert-4mC, enhances DNA 4mC site identification by fusing a pruned deep learning model with artificial features. This approach improves DNA sequence representation and accurately pinpoints 4mC sites.

Keywords:
4 mCDNABert-4mCFeature fusionPre-trainingPruning

More Related Videos

DNA Sequence Recognition by DNA Primase Using High-Throughput Primase Profiling
08:04

DNA Sequence Recognition by DNA Primase Using High-Throughput Primase Profiling

Published on: October 8, 2019

8.7K
Primer Extension Capture: Targeted Sequence Retrieval from Heavily Degraded DNA Sources
15:28

Primer Extension Capture: Targeted Sequence Retrieval from Heavily Degraded DNA Sources

Published on: September 3, 2009

20.2K

Related Experiment Videos

Last Updated: Jul 1, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

749
DNA Sequence Recognition by DNA Primase Using High-Throughput Primase Profiling
08:04

DNA Sequence Recognition by DNA Primase Using High-Throughput Primase Profiling

Published on: October 8, 2019

8.7K
Primer Extension Capture: Targeted Sequence Retrieval from Heavily Degraded DNA Sources
15:28

Primer Extension Capture: Targeted Sequence Retrieval from Heavily Degraded DNA Sources

Published on: September 3, 2009

20.2K

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • DNA 4mC is vital for genetic expression, but current deep learning models struggle with DNA sequence feature representation.
  • Accurate identification of DNA 4mC sites is crucial for understanding gene regulation.

Purpose of the Study:

  • To develop an advanced algorithm for identifying DNA 4mC sites with improved feature representation capabilities.
  • To address the limitations of existing deep learning methods in capturing complex DNA sequence information.

Main Methods:

  • Proposed DNABert-4mC algorithm, integrating a pruned DNABert-Pruning model with artificial feature encoding.
  • Developed the AFF-4mC fusion strategy to combine artificial features and the pruned model for enhanced DNA sequence representation.
  • Optimized feature extraction for 4mC sites and nucleotide importance within sequences.

Main Results:

  • The DNABert-4mC algorithm achieved a high average AUC of 93.81% across six independent test sets.
  • Demonstrated superior performance compared to seven other advanced algorithms, with significant improvements in identification accuracy.
  • The fusion strategy effectively enhanced multi-semantic space representation of DNA sequences.

Conclusions:

  • DNABert-4mC offers a more precise and accurate method for identifying DNA 4mC sites.
  • The integration of pruned deep learning models and artificial features represents a promising direction for bioinformatics tool development.
  • This algorithm advances the field of epigenomic analysis and gene expression studies.