Skip to navigation Skip to content
  • Woodruff
  • Business
  • Health Sciences
  • Law
  • MARBL
  • Oxford College
  • Theology
  • Schools
    • Undergraduate

      • Emory College
      • Oxford College
      • Business School
      • School of Nursing

      Community

      • Emory College
      • Oxford College
      • Business School
      • School of Nursing
    • Graduate

      • Business School
      • Graduate School
      • School of Law
      • School of Medicine
      • School of Nursing
      • School of Public Health
      • School of Theology
  • Libraries
    • Libraries

      • Robert W. Woodruff
      • Business
      • Chemistry
      • Health Sciences
      • Law
      • MARBL
      • Music & Media
      • Oxford College
      • Theology
    • Library Tools

      • Course Reserves
      • Databases
      • Digital Scholarship (ECDS)
      • discoverE
      • eJournals
      • Electronic Dissertations
      • EmoryFindingAids
      • EUCLID
      • ILLiad
      • OpenEmory
      • Research Guides
  • Resources
    • Resources

      • Administrative Offices
      • Emory Healthcare
      • Academic Calendars
      • Bookstore
      • Campus Maps
      • Shuttles and Parking
      • Athletics: Emory Eagles
      • Arts at Emory
      • Michael C. Carlos Museum
      • Emory News Center
      • Emory Report
    • Resources

      • Emergency Contacts
      • Information Technology (IT)
      • Outlook Web Access
      • Office 365
      • Blackboard
      • OPUS
      • PeopleSoft Financials: Compass
      • Careers
      • Human Resources
      • Emory Alumni Association
  • Browse
    • Works by Author
    • Works by Journal
    • Works by Subject
    • Works by Dept
    • Faculty by Dept
  • For Authors
    • How to Submit
    • Deposit Advice
    • Author Rights
    • Publishing Your Data
    • FAQ
    • Emory Open Access Policy
    • Open Access Fund
  • About OpenEmory
    • About OpenEmory
    • About Us
    • Citing Articles
    • Contact Us
    • Privacy Policy
    • Terms of Use
 
Contact Us

Filter Results:

Year

  • 2008 (1)

Author

  • Cho, Hyun-Woo (1)
  • Jeong, Myong K. (1)
  • Jones, Dean P (1)
  • Kim, Seoung Bum (1)
  • Park, Youngja (1)
  • Ziegler, Thomas R (1)

Subject

  • Engineering, Biomedical (1)
  • Health Sciences, Medicine and Surgery (1)

Journal

  • International Journal of Data Mining and Bioinformatics (1)

Keyword

  • analysi (1)
  • correct (1)
  • featur (1)
  • metabolom (1)
  • multivari (1)
  • nmr (1)
  • nuclear (1)
  • orthogon (1)
  • osc (1)
  • reson (1)
  • select (1)
  • signal (1)
  • statist (1)

Author department

  • Medicine: Endocrinology (1)

Search Results for all work with filters:

  • Gletsu-Miller, Nana
  • magnet
  • Medicine: Pulmonary

Work 1 of 1

Sorted by relevance

Article

Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra

by Hyun-Woo Cho; Seoung Bum Kim; Myong K. Jeong; Youngja Park; Nana Gletsu-Miller; Thomas R Ziegler; Dean P Jones

2008

Subjects
  • Health Sciences, Medicine and Surgery
  • Engineering, Biomedical
  • File Download
  • View on PubMed Central
  • View Abstract

Abstract:Close

High-resolution Nuclear Magnetic Resonance (NMR) spectroscopy in combination with multivariate statistical methods has been widely used to investigate metabolic fluctuations in biological systems. This study presents three feature selection methods for identifying the metabolite features that contribute to the distinction of spectral samples among varying nutritional conditions in human plasma. Loading vectors of Principal Component Analysis (PCA), the optimal discriminant direction of Fisher discriminant analysis, and index values of the Variable Importance in Projection (VIP) in a Partial Least Square Discriminant Analysis (PLS-DA) were used to calculate the importance of individual metabolite feature in spectra. In addition, an Orthogonal Signal Correction (OSC) filter was used to eliminate unnecessary variations in NMR spectra and its effectiveness was demonstrated through PCA and kernel PCA. For the evaluation of presented feature selection methods, we compared the ability of classification based on the metabolite features selected by each method. The results have shown that the best classification was achieved using VIP values from an OSC-PLS-DA model.
Site Statistics
  • 16,941
  • Total Works
  • 3,667,698
  • Downloads
  • 1,143,609
  • Downloads This Year
  • 6,807
  • Faculty Profiles

Copyright © 2016 Emory University - All Rights Reserved
540 Asbury Circle, Atlanta, GA 30322-2870
(404) 727-6861
Privacy Policy | Terms & Conditions

v2.2.8-dev

Contact Us Recent and Popular Items
Download now