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

Clustering time-varying gene expression profiles using scale-space signals.

Tanveer Syeda-Mahmood1

  • 1IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA. stf@almaden.ibm.com

Proceedings. IEEE Computer Society Bioinformatics Conference
|February 3, 2006
PubMed
Summary

This study introduces a novel pattern recognition method to analyze gene expression dynamics. It captures gene similarity by detecting significant changes in time-varying expression patterns, offering new insights into biological processes and disease.

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

CNN-based detection of pediatric lymphoma on whole body [<sup>18</sup>F]FDG-PET/MRI.

American journal of nuclear medicine and molecular imaging·2026
Same author

HNOSeg-XS: Extremely Small Hartley Neural Operator for Efficient and Resolution-Robust 3D Image Segmentation.

IEEE transactions on medical imaging·2025
Same author

Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects.

International journal of computer vision·2024
Same author

Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology.

Nature machine intelligence·2024
Same author

Digital twins for health: a scoping review.

NPJ digital medicine·2024
Same author

Modelling-based joint embedding of histology and genomics using canonical correlation analysis for breast cancer survival prediction.

Artificial intelligence in medicine·2024

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Gene expression patterns are crucial for organismal function.
  • Traditional gene expression analysis often overlooks time-varying dynamics, focusing on intensity alone.
  • Understanding temporal gene expression is key to deciphering gene regulation and disease mechanisms.

Purpose of the Study:

  • To develop a pattern recognition approach for analyzing time-varying gene expression data.
  • To capture gene similarity by identifying salient changes in temporal expression profiles.
  • To improve the clustering and retrieval of functionally similar genes based on dynamic expression patterns.

Main Methods:

  • Utilizing scale-space analysis to detect significant twists and bends in higher-dimensional curves formed from gene expression time series.

Related Experiment Videos

  • Developing a shape similarity measure based on the strength of these detected changes.
  • Implementing a clustering algorithm that employs scale-space distance as a similarity metric.

    • Main Results:

    • Demonstrated that dissimilarity in time series is effectively revealed by sharp changes in their higher-dimensional representations.
    • Established a novel scale-space distance metric for clustering gene expression profiles.
    • Showcased the utility of multi-dimensional curves as cluster prototypes for retrieving functionally similar genes.

    Conclusions:

    • The proposed pattern recognition approach effectively captures temporal gene expression similarities missed by traditional methods.
    • Scale-space analysis provides a robust metric for identifying biologically relevant changes in gene expression dynamics.
    • This method enhances the ability to cluster and retrieve functionally related genes, aiding in the understanding of gene regulation and disease onset.