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

Automated protein classification using consensus decision.

Tolga Can1, Orhan Camoğlu, Ambuj K Singh

  • 1Department of Computer Science, University of California at Santa Barbara, 93106, USA. tcan@cs.ucsb.edu

Proceedings. IEEE Computational Systems Bioinformatics Conference
|February 2, 2006
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

Comparative transcriptome profiling reveals molecular mechanisms of freezing stress responses in cultivated and wild Cicer species.

Scientific reports·2025
Same author

Phosphorylation of SNAP-25 at Ser187 is enhanced following its cleavage by Botulinum Neurotoxin Serotype A, promoting the dominant-negative effect of the resulting fragment.

PLoS pathogens·2025
Same author

E2-regulated transcriptome complexity revealed by long-read direct RNA sequencing: from isoform discovery to truncated proteins.

RNA biology·2025
Same author

Effective primer design for genotype and subtype detection of highly divergent viruses in large scale genome datasets.

BMC bioinformatics·2025
Same author

Sleep deprivation modulates pain sensitivity through alterations in lncRNA and mRNA expression in the nucleus accumbens and ventral midbrain.

Neuropharmacology·2025
Same author

Probabilistic memory auto-encoding network for abnormal behavior detection in surveillance video.

Neural networks : the official journal of the International Neural Network Society·2025
Same journal

A Two-Step Approach for Clustering Proteins based on Protein Interaction Profile.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2008
Same journal

Proceedings of 2005 IEEE Computational Systems Bioinformatics Conference. August 8-11, 2005. Stanford, California, USA.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2007
Same journal

Fractal genomics modeling: a new approach to genomic analysis and biomarker discovery.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2006
Same journal

Gene Ontology friendly biclustering of expression profiles.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2006
Same journal

Comparative analysis of gene sets in the Gene Ontology space under the multiple hypothesis testing framework.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2006
Same journal

AZuRE, a scalable system for automated term disambiguation of gene and protein names.

Proceedings. IEEE Computational Systems Bioinformatics Conference·2006
See all related articles

We developed a machine learning method to automatically classify protein structures using the Structural Classification of Proteins (SCOP) database. This ensemble classifier significantly improves accuracy over individual methods.

Area of Science:

  • Structural bioinformatics
  • Computational biology
  • Machine learning applications

Background:

  • Accurate protein structure classification is crucial for understanding protein function and evolution.
  • Existing methods for protein classification have limitations in accuracy and scope.
  • The Structural Classification of Proteins (SCOP) database provides a hierarchical framework for protein classification.

Purpose of the Study:

  • To develop a novel, highly accurate technique for automated SCOP classification of protein structures.
  • To leverage machine learning, specifically ensemble methods, to enhance classification performance.
  • To improve upon the accuracy of individual sequence- and structure-comparison tools.

Main Methods:

  • Utilized a committee (ensemble) classifier combining decisions from multiple component classifiers.

Related Experiment Videos

  • Employed two sequence-comparison and three structure-comparison tools as component classifiers.
  • Developed a joint hypothesis to first determine if a protein belongs to an existing SCOP category.
  • Applied a consensus classifier for family, superfamily, and fold level classification for predicted members.

    • Main Results:

    • The ensemble classifier significantly improved classification accuracy compared to individual component classifiers.
    • Achieved error rate reductions of 3-12 times at the family level.
    • Demonstrated error rate reductions of 1.5-4.5 times at the superfamily level.
    • Showed error rate reductions of 1.1-2.4 times at the fold level.

    Conclusions:

    • The proposed ensemble machine learning technique provides a robust and accurate method for automated protein structure classification within the SCOP hierarchy.
    • Combining multiple comparison tools through an ensemble approach effectively overcomes limitations of individual methods.
    • This approach offers a significant advancement in the field of structural bioinformatics, enabling more precise protein categorization.