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

Fast model-based protein homology detection without alignment.

Sepp Hochreiter1, Martin Heusel, Klaus Obermayer

  • 1Institute of Bioinformatics, Johannes Kepler Universität Linz, 4040 Linz, Austria. hochreit@bioinf.jku.at

Bioinformatics (Oxford, England)
|May 10, 2007
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

Polarity-dependent modulation of sleep oscillations and cortical excitability in aging.

Frontiers in aging neuroscience·2026
Same author

VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification.

Journal of cheminformatics·2025
Same author

On the robustness of the emergent spatiotemporal dynamics in biophysically realistic and phenomenological whole-brain models at multiple network resolutions.

Frontiers in network physiology·2025
Same author

Mean arterial pressure is all you need in a machine learning model for mean arterial pressure prediction.

European journal of anaesthesiology·2025
Same author

Neural dynamics underlying the cue validity effect in target conflict resolution.

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

A robotics-inspired scanpath model reveals the importance of uncertainty and semantic object cues for gaze guidance in dynamic scenes.

Journal of vision·2025
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

Long Short-Term Memory (LSTM) offers a faster, model-based approach for protein homology detection. This recurrent neural network achieves state-of-the-art classification performance while significantly reducing computation time compared to existing methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Increasing demand for rapid gene classification in genomics.
  • Limitations of current homology detection methods: time-consuming sequence alignments, SVMs, and PSSMs.
  • Need for model-based approaches that capture class properties for better protein function insights.

Purpose of the Study:

  • Introduce a fast, model-based recurrent neural network for protein homology detection.
  • Develop a method that automatically extracts indicative patterns and correlations for classification.
  • Enhance protein classification speed and accuracy.

Main Methods:

  • Application of Long Short-Term Memory (LSTM), a recurrent neural network, for protein homology detection.
  • Utilizing LSTM's capability to automatically extract local and global sequence statistics and patterns.

Related Experiment Videos

  • Testing LSTM on remote protein homology detection benchmarks (SCOP superfamilies and PROSITE classes).

    • Main Results:

    • LSTM achieves state-of-the-art classification performance, comparable to PSI-BLAST and HMM-based methods.
    • LSTM is significantly faster than alignment-based methods, SVMs, and profile methods.
    • LSTM successfully extracted known PROSITE motifs and generated improved alternative motifs for better classification.

    Conclusions:

    • LSTM provides a computationally efficient and highly accurate method for protein homology detection.
    • LSTM's model-based approach offers advantages over traditional alignment methods.
    • The algorithm demonstrates potential for discovering new protein functional insights through pattern analysis.