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

Improved K-means clustering algorithm for exploring local protein sequence motifs representing common structural

Wei Zhong1, Gulsah Altun, Robert Harrison

  • 1Computer Science Department, Georgia State University, Atlanta, GA 30303-4110, USA. jetzhong@yahoo.com

IEEE Transactions on Nanobioscience
|October 14, 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

Post-Acute COVID Among California Workers' Compensation Claims Filed in 2020-2022.

Journal of occupational and environmental medicine·2026
Same author

Comparative Diagnostic Performance of Metabolic Scoring Indices for Ultrasonographic Hepatic Steatosis: Development and Validation of a Novel Composite Score in 1204 Consecutive Patients.

Journal of clinical medicine·2026
Same author

Home improvement programs and deadly countertops: the need to protect workers.

Annals of the American Thoracic Society·2026
Same author

Baseline Serum Albumin for Long-Term Risk Stratification in Maintenance Hemodialysis Patients: A Retrospective Cohort Study.

Journal of clinical medicine·2026
Same author

Creatinine Decline Rate as a Predictor of Renal Recovery After Acute Kidney Injury: A Retrospective Cohort Study.

Diagnostics (Basel, Switzerland)·2025
Same author

Cytotoxic Effects of Sorafenib, Lapatinib, and Bevacizumab, Alone and in Combination, on Medullary Thyroid Carcinoma Cells.

Current oncology (Toronto, Ont.)·2025

An improved K-means clustering algorithm enhances protein sequence motif discovery by identifying subtle, biologically meaningful patterns. This method reveals universally conserved sequence motifs across protein families, improving structural similarity analysis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • Protein sequence motifs are crucial for understanding conserved regions, protein structure, and function.
  • Existing methods for motif discovery may miss subtle or weak sequence patterns.

Purpose of the Study:

  • To explore recurring protein sequence motifs using an improved K-means clustering algorithm.
  • To evaluate the relationship between identified sequence motifs and their structures.
  • To introduce a novel greedy initialization method for K-means clustering.

Main Methods:

  • Application of an improved K-means clustering algorithm with a greedy initialization method.
  • Analysis of a new, updated dataset of protein sequences.
  • Study of structural similarity within recurring sequence clusters.

Related Experiment Videos

Main Results:

  • The improved K-means algorithm significantly increases the proportion of sequence segments in clusters with high structural similarity.
  • The enhanced algorithm successfully identifies weak and subtle sequence motifs missed by traditional K-means.
  • Discovered motifs are biologically meaningful, universally conserved across protein families, and represent common structures.

Conclusions:

  • The improved K-means algorithm offers a more effective approach to discovering detailed and biologically relevant protein sequence motifs.
  • This method enhances the analysis of conserved protein regions and their structural implications.
  • The algorithm shows potential for broader applications in bioinformatics for exploring data relationships.