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

Combing ontologies and dipeptide composition for predicting DNA-binding proteins.

Loris Nanni1, Alessandra Lumini

  • 1DEIS, IEIIT-CNR, Università di Bologna, Viale Risorgimento 2, 40136 Bologna, Italy. loris.nanni@unibo.it

Amino Acids
|January 5, 2008
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

Ensemble Deep Learning Models on Raw DNA Sequences for Viral Genome Identification in Human Samples.

Sensors (Basel, Switzerland)·2026
Same author

Matrix-based vector representations in neural networks for classifying molecular biology data.

Bioinformatics advances·2025
Same author

Entropy-Regularized Attention for Explainable Histological Classification with Convolutional and Hybrid Models.

Entropy (Basel, Switzerland)·2025
Same author

Advancing Precision: A Comprehensive Review of MRI Segmentation Datasets from BraTS Challenges (2012-2025).

Sensors (Basel, Switzerland)·2025
Same author

Deep Ensembling of Multiband Images for Earth Remote Sensing and Foramnifera Data.

Sensors (Basel, Switzerland)·2025
Same author

Postprocessing for Skin Detection.

Journal of imaging·2024
Same journal

Author Correction: Novel octapeptide containing the RGD sequence as a potential anti-SARS-CoV-2 agent: design, synthesis, and theoretical studies.

Amino acids·2026
Same journal

Polyamines in CNS malignancies: positively charged culprits in the hijacking of neural and immune signaling pathways.

Amino acids·2026
Same journal

The effects of glutamine supplementation on inflammatory and oxidative stress indices in chronic diseases: a systematic review.

Amino acids·2026
Same journal

Reprogramming parasitic signatures into anticancer peptide candidates: in silico discovery of Leishmania major-derived peptides.

Amino acids·2026
Same journal

Effects of taurine on skeletal muscle in senescence-accelerated mice and C2C12 myoblasts and myotubes.

Amino acids·2026
Same journal

Dual functions of thermospermine in plant growth and stress responses.

Amino acids·2026
See all related articles

Identifying DNA-binding proteins is crucial for understanding gene regulation. Our novel fusion method combines gene ontology and dipeptide features, achieving high accuracy (0.97 MCC) and outperforming existing approaches.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • DNA-binding proteins play a critical role in regulating gene expression.
  • Accurate identification of DNA-binding proteins is essential for biological research.

Purpose of the Study:

  • To develop a novel computational method for predicting DNA-binding proteins.
  • To enhance prediction accuracy by fusing features from Gene Ontology (GO) and dipeptide composition.

Main Methods:

  • A parallel fusion approach combining two classifiers: one using GO features and another using dipeptide composition.
  • Support Vector Machine (SVM) and 1-nearest neighbor algorithms were employed as classifiers.
  • Jackknife cross-validation was used for performance evaluation.

Related Experiment Videos

Main Results:

  • The proposed fusion method achieved a Matthews's correlation coefficient (MCC) of approximately 0.97, surpassing the literature benchmark of 0.924.
  • The Area Under the ROC Curve (AUC) reached 0.995, indicating excellent discriminatory power.
  • The fusion method demonstrated a low error rate with 5% false negatives and 0% false positives.

Conclusions:

  • The parallel fusion of GO and dipeptide features significantly improves DNA-binding protein prediction accuracy.
  • Gene Ontology data alone is insufficient for reliable prediction, highlighting the value of feature fusion.
  • The tested feature extraction methods are partially independent, supporting the efficacy of their combined use.