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

Dynamic model-based clustering for time-course gene expression data.

Fang-Xiang Wu1, W J Zhang, Anthony J Kusalik

  • 1Division of Biomedical Engineering, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5A9, Canada. faw341@mail.usask.ca

Journal of Bioinformatics and Computational Biology
|August 4, 2005
PubMed
Summary

This study introduces a novel dynamic model-based clustering method to analyze time-course gene expression data. The approach effectively captures data dynamics, improving clustering quality for genomic applications.

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

IIC-DTI: A Contrastive Learning Enhanced Inter-Intra Molecular Fusing Framework for Drug-Target Interaction Prediction.

Interdisciplinary sciences, computational life sciences·2026
Same author

Graph convolution network based on meta-paths and mutual information for drug-target interaction prediction.

BMC bioinformatics·2025
Same author

The study of the variation of mineral distribution and relative concentration on varieties of oat using synchrotron-based X-ray fluorescence imaging.

Food research international (Ottawa, Ont.)·2025
Same author

Predicting miRNA-Drug Interactions Based on Multi-source Feature Fusion of Heterogeneous Network.

Interdisciplinary sciences, computational life sciences·2025
Same author

Low-Count PET Image Reconstruction With Generalized Sparsity Priors via Unrolled Deep Networks.

IEEE journal of biomedical and health informatics·2025
Same author

Unraveling bladder cancer-related circRNA biomarkers: a hybrid model combining deep learning and statistics.

Health information science and systems·2025

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Microarray technology generates extensive time-course gene expression data crucial for genomic disease diagnosis and drug design.
  • Existing clustering techniques often fail to capture the inherent dynamics of time-series gene expression data, limiting analytical insights.
  • High-quality clustering requires methods that explicitly consider the temporal characteristics of gene expression patterns.

Purpose of the Study:

  • To propose and evaluate a novel dynamic model-based clustering method for analyzing time-course gene expression data.
  • To address the limitations of static and correlation-based methods in capturing temporal dependencies in gene expression.
  • To enhance the accuracy and utility of clustering for uncovering biologically relevant patterns in dynamic gene expression datasets.

Related Experiment Videos

Main Methods:

  • A dynamic model-based clustering approach is proposed, treating gene expression datasets as time series generated by stochastic processes.
  • Each cluster is defined by an autoregressive model, with parameters identified using a relocation-iteration algorithm.
  • Posterior probabilities are used for gene assignment, and bootstrapping with the average adjusted Rand index (AARI) assesses clustering quality.

Main Results:

  • The proposed dynamic clustering method demonstrates superior performance compared to traditional methods like k-means on synthetic and real gene expression datasets.
  • The method effectively captures the temporal dynamics, leading to higher quality and more meaningful clusters.
  • Computational experiments validate the method's ability to extract useful information from time-course gene expression data.

Conclusions:

  • The dynamic model-based clustering method offers a powerful and effective tool for analyzing time-course gene expression data.
  • By incorporating temporal dynamics, this approach improves upon existing clustering techniques for genomic applications.
  • This method facilitates a deeper understanding of gene regulation and biological processes over time.