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

Unsupervised learning from complex data: the matrix incision tree algorithm.

J H Kim1, L Ohno-Machado, I S Kohane

  • 1Children's Hospital Informatics Program, Children's Hospital, Harvard Medical School, 300 Longwood Avenue, Boston, MA 02115, USA. juhan_kim@harvard.edu

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|March 27, 2001
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

The phenotypical implications of immune dysregulation in fragile X syndrome.

European journal of neurology·2020
Same author

Computer-based Patient Records.

Yearbook of medical informatics·2016
Same author

Absence of evidence for increase in risk for autism or attention-deficit hyperactivity disorder following antidepressant exposure during pregnancy: a replication study.

Translational psychiatry·2016
Same author

Prenatal antidepressant exposure is associated with risk for attention-deficit hyperactivity disorder but not autism spectrum disorder in a large health system.

Molecular psychiatry·2014
Same author

Peripheral blood gene expression signature differentiates children with autism from unaffected siblings.

Neurogenetics·2013
Same author

Comparative RNA editing in autistic and neurotypical cerebella.

Molecular psychiatry·2012

This study introduces a new algorithm to organize complex gene expression data. The matrix incision tree method reveals hierarchical structures in high-dimensional data for better knowledge discovery.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Data Mining

Background:

  • Large-scale gene expression data analysis necessitates advanced methods for knowledge discovery and predictive modeling.
  • Organizing high-dimensional data, such as DNA microarray datasets, into meaningful structures is crucial for biological insights.
  • Current methods may lack efficiency in uncovering the inherent hierarchical organization within complex biological datasets.

Purpose of the Study:

  • To present a novel algorithm for organizing complex high-dimensional data spaces.
  • To reveal the hierarchical structural organization of observed data without prior knowledge.
  • To facilitate knowledge discovery and predictive model building from large-scale gene expression datasets.

Main Methods:

  • The proposed method organizes high-dimensional data into successive lower-dimensional spaces.

Related Experiment Videos

  • It utilizes the geometric properties of the data structure.
  • The matrix incision tree algorithm identifies successive hyperplanes for optimal data separation.

    • Main Results:

    • The matrix incision tree algorithm successfully reveals hierarchical structures in complex datasets.
    • The method demonstrates the ability to organize high-dimensional data effectively.
    • Promising results were obtained when tested against published datasets.

    Conclusions:

    • The matrix incision tree algorithm offers a novel approach to analyzing high-dimensional biological data.
    • This method enhances the understanding of data structure and facilitates knowledge discovery.
    • The algorithm shows potential for improving predictive modeling and clustering in genomics research.