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

Using supervised fuzzy clustering to predict protein structural classes.

Hong-Bin Shen1, Jie Yang, Xiao-Jun Liu

  • 1Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030, China.

Biochemical and Biophysical Research Communications
|July 19, 2005
PubMed
Summary

A new supervised fuzzy clustering approach improves protein classification accuracy. This method uses class labels during training to create predictive "if-then" rules, outperforming previous unsupervised methods for protein structural class prediction.

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

Benchmarking protein sequence and structure search methods for remote homology detection.

Genome biology·2026
Same author

BindRNAgen: Protein-binding RNA Sequence Generation Using Latent Diffusion Models.

Journal of molecular biology·2026
Same author

DrugDL: dual-modal deep learning framework for multi-property drug prediction and targeted therapy discovery.

Bioinformatics (Oxford, England)·2026
Same author

Reconstructing cell-cell interaction network in single-cell spatial transcriptomics via directed heterogeneous graph autoencoder.

Bioinformatics (Oxford, England)·2026
Same author

SMENET: A Multi-View Semantic Model for Multi-Level Enzyme Function Prediction.

IEEE transactions on computational biology and bioinformatics·2025
Same author

Ab-initio amino acid sequence design from protein text description with ProtDAT.

Nature communications·2025

Area of Science:

  • Protein Science
  • Bioinformatics
  • Computational Biology

Background:

  • Protein classification is crucial for understanding protein structure and function.
  • Accurate prediction of protein structural classes aids in various biological analyses.
  • Existing prediction methods can be enhanced with novel approaches.

Purpose of the Study:

  • To introduce a novel supervised fuzzy clustering approach for protein classification.
  • To extract predictive "if-then" fuzzy rules from training data.
  • To evaluate the performance of the new approach against existing methods.

Main Methods:

  • Developed a supervised fuzzy clustering algorithm that incorporates class label information during training.
  • Extracted a set of "if-then" fuzzy rules for predicting protein structural classes.

Related Experiment Videos

  • Validated the approach using two distinct working datasets.

    • Main Results:

    • The supervised fuzzy clustering approach achieved higher overall success prediction rates compared to unsupervised fuzzy c-means.
    • Demonstrated improved accuracy in predicting protein structural classes.
    • The novel predictor shows potential for complementary use with existing tools.

    Conclusions:

    • The supervised fuzzy clustering approach offers a more effective method for protein structural class prediction.
    • This technique enhances the accuracy of protein classification by leveraging training data labels.
    • The predictor can serve as a valuable addition to the suite of tools for protein attribute analysis.