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

GMHCC: high-throughput analysis of biomolecular data using graph-based multiple hierarchical consensus clustering.

Yifu Lu1, Zhuohan Yu1, Yunhe Wang1

  • 1School of Artificial Intelligence, Jilin University, Changchun 130012, China.

Bioinformatics (Oxford, England)
|April 22, 2022
PubMed
Summary

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

Establishing quality management system for biomonitoring laboratory network: based on element internal exposures in China national human biomonitoring.

Environment international·2026
Same author

The ratio of GABA/Glu as a biomarker in children with attention deficit hyperactivity disorder.

Physiology & behavior·2026
Same author

ARISE: RNA-anchored shared-edge topology and hierarchical fusion for spatial multi-omics integration.

Bioinformatics (Oxford, England)·2026
Same author

Risk stratification of 1-year atrial tachyarrhythmia recurrence after ablation in patients with persistent atrial fibrillation: ALADS-AF score.

BMC cardiovascular disorders·2026
Same author

<i>Aspergillus neoalliaceus</i> MR-86 Promotes the Growth of <i>Saposhnikovia divaricata</i> by Regulating the Rhizosphere Microbiome.

Plants (Basel, Switzerland)·2026
Same author

Cellular water-potential sensing through biomolecular condensation.

Nature·2026

This study introduces a novel Graph-based Multiple Hierarchical Consensus Clustering (GMHCC) method for analyzing complex biomolecular data. GMHCC effectively clusters subtypes, revealing insights into cell lineages and characterization mechanisms.

Area of Science:

  • Genomics
  • Molecular Biology
  • Bioinformatics

Background:

  • High-throughput sequencing generates massive biomolecular data, necessitating effective subtype clustering for analysis.
  • Existing computational clustering methods face limitations with high dimensionality, data heterogeneity, and noise.

Purpose of the Study:

  • To develop a novel Graph-based Multiple Hierarchical Consensus Clustering (GMHCC) method for biomolecular data.
  • To address limitations of existing clustering approaches in handling complex biological datasets.

Main Methods:

  • Developed an unsupervised graph-based feature ranking (FR) model to rank features.
  • Generated multiple diverse feature subsets for robust basic partitions (BPs).
  • Employed a graph-based linking method to refine clusters and explore hierarchical structures.

Related Experiment Videos

Main Results:

  • GMHCC demonstrated effectiveness on 35 cancer gene expression and eight single-cell RNA-seq datasets.
  • Validated superior performance compared to state-of-the-art consensus clustering methods.
  • Differential gene, gene ontology, and KEGG pathway analyses provided novel biological insights.

Conclusions:

  • GMHCC offers an effective approach for clustering diverse biomolecular data.
  • The method provides valuable insights into cellular mechanisms and developmental processes.
  • The developed software and code are publicly available for research use.