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

Motif-based protein sequence classification using neural networks.

Konstantinos Blekas1, Dimitrios I Fotiadis, Aristidis Likas

  • 1Department of Computer Science and Biomedical Research Institute-FORTH, University of Ioannina, GR-45110 Ioannina, Greece. kblekas@cs.uoi.gr

Journal of Computational Biology : a Journal of Computational Molecular Cell Biology
|February 24, 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

From challenge to innovation: a narrative review on innovation in nephrology and hemodialysis randomized trials.

Journal of nephrology·2026
Same author

Hemodiafiltration beyond the CONVINCE trial.

Clinical kidney journal·2026
Same author

The effect of dietetic counseling combined with digital tools intervention on hemodynamic markers in Greek adults: The GATEKEEPER Study.

Nutrition, metabolism, and cardiovascular diseases : NMCD·2026
Same author

A machine learning approach predicts improvement of physical exercise capacity based on pulse wave analysis in coronary artery disease patients.

Journal of sport and health science·2026
Same author

Prognostic Model Development for Continuous Carotid Intima-Media Thickness: A Graph-Driven Self-Supervised Learning Approach.

IEEE journal of biomedical and health informatics·2025
Same author

Development of Machine Learning Models for Predicting Effectiveness and Adherence in Cardiac Rehabilitation.

IEEE journal of biomedical and health informatics·2025
Same journal

GMSA: A Graph Matching and Point Cloud Registration-Based Method for Spatial Transcriptomics Data Alignment.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Investigations on Multiple Protein Scaffold Filling.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Cell Type Prediction for Single-Cell RNA Sequencing Utilizing Unsupervised Domain Adaptation and Semi-Supervised Learning.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

PPIGAN: Prediction of Protein-Protein Interactions Using Generative Adversarial Networks.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Deep Structure-Enhanced Cell Clustering Model for Single-Cell RNA Sequencing Data.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Asymmetric Drug-Drug Interaction Prediction Based on Generative Adversarial Networks and Knowledge Graph.

Journal of computational biology : a journal of computational molecular cell biology·2026
See all related articles

This study introduces a novel neural network system for protein classification. It efficiently encodes protein sequences using conserved motifs, outperforming existing methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Accurate protein classification is crucial for understanding biological function.
  • Existing neural network approaches face challenges with protein sequence encoding.
  • Developing effective feature representation is key for protein classification systems.

Purpose of the Study:

  • To propose and evaluate a novel neural network-based system for multi-class protein classification.
  • To address the challenge of protein sequence encoding for neural network input.
  • To compare different motif identification strategies and assess the impact of background features.

Main Methods:

  • Mapping protein sequences into a numerical feature space using matching scores to conserved patterns (motifs).

Related Experiment Videos

  • Investigating two distinct methods for motif identification in feature generation.
  • Incorporating background features (2-grams) to enhance the neural system's performance.
  • Comparative evaluation of proposed methods against established protein classification techniques.

    • Main Results:

    • The proposed motif-based feature mapping significantly improves protein classification accuracy.
    • Comparative analysis reveals the strengths of different motif identification schemes.
    • Inclusion of 2-gram background features positively impacts neural system performance.
    • Experimental results demonstrate the high efficiency and superiority of the developed system.

    Conclusions:

    • The developed neural network system offers a highly efficient and superior approach to multi-class protein classification.
    • Motif-based sequence encoding provides an effective solution for feeding protein data into neural networks.
    • The method demonstrates significant advantages over existing protein classification techniques.