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

Effective DNA binding protein prediction by using key features via Chou's general PseAAC.

Sheikh Adilina1, Dewan Md Farid1, Swakkhar Shatabda1

  • 1Department of Computer Science and Engineering, United International University, Plot 2, United City, Madani Avenue, Satarkul, Badda, Dhaka 1212, Bangladesh.

Journal of Theoretical Biology
|October 15, 2018
PubMed
Summary

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

Trainable clustering framework for spatial transcriptomics.

Bioinformatics advances·2026
Same author

TextEconomizer: Enhancing lossy text compression with denoising transformers and entropy coding.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

A deep reinforcement based echo state network for network intrusion classification.

PloS one·2026
Same author

The good, the bad, and the ugly: opportunities, challenges, and pitfalls in spatial proteomics modeling.

Briefings in bioinformatics·2026
Same author

Spatial information matters: are traditional imputation methods effective for spatial transcriptomics data?

Briefings in bioinformatics·2026
Same author

Comprehensive retail network dataset for bangladesh: Shop-level sales and location data.

Data in brief·2026

This study improves DNA-binding protein (DBP) prediction using sequence-based features and feature selection, enhancing accuracy on independent test sets by reducing overfitting.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Proteomics

Background:

  • DNA-binding proteins (DBPs) are crucial for cellular functions, including immunity and oxygen transport.
  • Existing supervised machine learning methods for DBP classification often overfit, showing degraded performance on independent test sets.

Purpose of the Study:

  • To develop an improved prediction method for DNA-binding proteins by reducing overfitting.
  • To enhance the performance of DBP classification using sequence-derived features and rigorous feature selection.

Main Methods:

  • Extracted sequence-based features solely from protein sequences.
  • Applied two distinct feature selection techniques to identify optimal predictive features.
  • Utilized supervised machine learning for DBP classification.
Keywords:
Classification algorithmDNA binding proteinsFeature selectionHandling overfittingIndependent test setSequence based features

Related Experiment Videos

Main Results:

  • Achieved comparable performance on training sets.
  • Demonstrated significantly improved accuracy on independent test sets, reaching 82.26% (a 1.62% increase over prior state-of-the-art).
  • Reported enhanced sensitivity (0.95) and area under the ROC curve (0.823) on the independent test set.

Conclusions:

  • The proposed feature extraction and selection approach effectively mitigates overfitting in DBP prediction.
  • This method offers a more robust and accurate way to classify DNA-binding proteins based on sequence information.