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

Self-organizing hierarchic networks for pattern recognition in protein sequence

J Hanke1, G Beckmann, P Bork

  • 1Max-Delbrück-Center for Molecular Medicine, Department of Bioinformatics, Berlin-Buch, Germany. hanke@bioinf.mdc-berlin.de

Protein Science : a Publication of the Protein Society
|January 1, 1996
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

An IMU and sEMG dataset of induced stumble events during treadmill walking in transfemoral amputees.

Scientific data·2026
Same author

Alterations of oral microbiota and impact on the gut microbiome in type 1 diabetes mellitus revealed by integrated multi-omic analyses.

Microbiome·2022
Same author

[The gut microbiome in Parkinson's disease].

Der Nervenarzt·2018
Same author

The gut microbiome is associated with behavioural task in honey bees.

Insectes sociaux·2018
Same author

Significantly enhanced lung metastasis and reduced organ NK cell functions in diet-induced obese rats.

BMC obesity·2017
Same author

Erratum to: Functional implications of microbial and viral gut metagenome changes in early stage L-DOPA-naïve Parkinson's disease patients.

Genome medicine·2017
Same journal

Macromolecular crowding inhibits degradation of alpha-synuclein amyloid fibrils induced by cathepsins and MMP9.

Protein science : a publication of the Protein Society·2026
Same journal

Sequence-encoded differences in the conformational ensembles of CITED transcriptional activation domains impact coactivator binding.

Protein science : a publication of the Protein Society·2026
Same journal

The phospholipid biosynthesis enzyme PlsB contains three distinct domains for membrane association, lysophosphatidic acid synthesis, and dimerization.

Protein science : a publication of the Protein Society·2026
Same journal

Structural basis of ligand selectivity in FAD/NAD(P)H-dependent dehydrogenases: insights from trypanothione reductase and type II NADH dehydrogenase.

Protein science : a publication of the Protein Society·2026
Same journal

Achieving protease substrate-specific inhibition by mAb dual functional selections.

Protein science : a publication of the Protein Society·2026
Same journal

How important are quantum mechanical effects in controlling biological functions: Enzymes, electron transfer and bird navigation.

Protein science : a publication of the Protein Society·2026
See all related articles

This study introduces a novel hierarchical self-organizing maps (SOMs) method for automatic protein sequence pattern recognition. The approach efficiently identifies conserved motifs in unaligned sequences, outperforming existing methods.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Protein sequence analysis is crucial for understanding protein function and evolution.
  • Existing methods for pattern recognition often require prealigned sequences and can be sensitive to data redundancy.
  • Unsupervised learning offers a promising avenue for discovering novel patterns in biological data.

Purpose of the Study:

  • To develop an automatic, unsupervised method for recognizing patterns in unaligned protein sequences.
  • To improve the sensitivity and efficiency of pattern identification in large sequence databases.
  • To demonstrate the method's effectiveness on challenging biological recognition problems.

Main Methods:

  • Utilized hierarchical self-organizing maps (SOMs), a type of unsupervised neural network.

Related Experiment Videos

  • Employed a three-stage training process: feature extraction, feature recognition refinement, and feature positional learning.
  • Developed a definition of 'feature' as conserved ungapped sequence segments.

    • Main Results:

    • The method successfully identified patterns in unaligned protein sequences without prior alignment.
    • It demonstrated robustness against training set redundancy and effectiveness with small datasets.
    • The approach achieved sensitive and efficient pattern identification in sequence databases.
    • Successfully applied to recognize helix-turn-helix motifs, CUB domains, and ribokinases.

    Conclusions:

    • Hierarchical SOMs provide a powerful, automatic approach for protein sequence pattern discovery.
    • The method is versatile and effective for various challenging biological recognition tasks.
    • This unsupervised technique can uncover patterns not evident in all sequences within a learning set.