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 Experiment Videos

Kernel-based machine learning protocol for predicting DNA-binding proteins.

Nitin Bhardwaj1, Robert E Langlois, Guijun Zhao

  • 1Bioinformatics Program, Department of Bioengineering, University of Illinois at Chicago, Chicago, IL 60607, USA.

Nucleic Acids Research
|November 15, 2005
PubMed
Summary
This summary is machine-generated.

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

Elucidating metabolites and biosynthetic pathways during musk maturation: insights from forest musk deer.

Frontiers in pharmacology·2025
Same author

Multiomics analysis provides insights into musk secretion in muskrat and musk deer.

GigaScience·2025
Same author

Efficacy and safety of YOXINTINE for depression: A double-blinded, randomized, placebo-controlled, phase 2 clinical trial.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2024
Same author

Preliminary exploration of the musk biosynthetic mechanism by transcriptomic sequencing in muskrats.

Scientific reports·2024
Same author

Chemical composition and microbiota changes across musk secretion stages of forest musk deer.

Frontiers in microbiology·2024
Same author

Deleterious variant in FAM71D cause male infertility with asthenoteratospermia.

Molecular genetics and genomics : MGG·2024
Same journal

Correction to 'New origin firing is inhibited by APC/CCdh1 activation in S-phase after severe replication stress'.

Nucleic acids research·2026
Same journal

VeloRM: disentangling pre- and post-splicing RNA modification dynamics at single-cell resolution.

Nucleic acids research·2026
Same journal

Accessibility of telomeric overhangs to stabilizing small-molecule ligands.

Nucleic acids research·2026
Same journal

Multivalent interactions mediate SNAIL transcription factor stimulation of the nucleosome deacetylase activity of the CoREST complex.

Nucleic acids research·2026
Same journal

Genome-wide mapping of DNA G-quadruplexes in Trypanosoma brucei chromatin reveals enrichment in coding regions and transcription start sites.

Nucleic acids research·2026
Same journal

Correction to 'The Gene Ontology knowledgebase in 2026'.

Nucleic acids research·2026
See all related articles

This study introduces a machine learning model using Support Vector Machines (SVMs) to accurately predict DNA-binding proteins (DNA-BPs). The novel approach achieves high accuracy without relying on sequence or structural homology, aiding in the discovery of new DNA-binding proteins.

Area of Science:

  • Biochemistry
  • Computational Biology
  • Bioinformatics

Background:

  • DNA-binding proteins (DNA-BPs) are crucial for cellular processes like DNA replication and gene regulation.
  • Existing methods for identifying DNA-BPs using sequence and structure have moderate accuracy.
  • Accurate identification of DNA-BPs is essential for understanding cellular functions.

Purpose of the Study:

  • To develop a machine learning protocol for predicting DNA-binding proteins (DNA-BPs).
  • To achieve higher prediction accuracy than existing methods.
  • To create a tool that can identify DNA-BPs irrespective of their homology to known proteins.

Main Methods:

  • Utilized Support Vector Machines (SVMs) as the classification algorithm.
  • Extracted features from protein characteristics including surface composition, overall charge, and positive potential patches.

Related Experiment Videos

  • Trained and evaluated the model on a dataset of 121 DNA-BPs and 238 non-binding proteins.

    • Main Results:

    • Achieved 100% accuracy in self-consistency tests.
    • Reported 90% accuracy for cross-validation and 86.3% for leave-one-pair-out evaluation.
    • Demonstrated 85.8% accuracy on a dataset with less than 20% sequence identity, and correctly predicted all seven unbounded DNA-BPs tested.

    Conclusions:

    • The developed SVM-based protocol significantly improves the accuracy of DNA-binding protein prediction.
    • The method's independence from sequence or structural homology allows for the identification of novel DNA-BPs.
    • This approach offers a powerful tool for discovering proteins with DNA-binding functions.