Document Detail

Leveraging latent information in NMR spectra for robust predictive models.
MedLine Citation:
PMID:  17990485     Owner:  NLM     Status:  MEDLINE    
A significant challenge in metabolomics experiments is extracting biologically meaningful data from complex spectral information. In this paper we compare two techniques for representing 1D NMR spectra: "Spectral Binning" and "Targeted Profiling". We use simulated 1D NMR spectra with specific characteristics to assess the quality of predictive multivariate statistical models built using both data representations. We also assess the effect of different variable scaling techniques on the two data representations. We demonstrate that models built using Targeted Profiling are not only more interpretable than Spectral Binning models, but are more robust with respect to compound overlap, and variability in solution conditions (such as pH and ionic strength). Our findings from the synthetic dataset were validated using a real-world dataset.
David Chang; Aalim Weljie; Jack Newton
Related Documents :
17666755 - Cisa: combined nmr resonance connectivity information determination and sequential assi...
20132595 - Improved discrimination between monocotyledonous and dicotyledonous plants for weed con...
9694395 - Experimental artefacts in 2d-mas exchange experiments: non-uniform mixing time within a...
23069915 - Comment on blasi et al.'s, (2011) "lipid nanoparticles for brain targeting i. formulati...
12750835 - Evolutionary and dynamic stability in continuous population games.
19679355 - An international meta-analysis of values of travel time savings.
Publication Detail:
Type:  Comparative Study; Journal Article    
Journal Detail:
Title:  Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing     Volume:  -     ISSN:  2335-6936     ISO Abbreviation:  Pac Symp Biocomput     Publication Date:  2007  
Date Detail:
Created Date:  2007-11-09     Completed Date:  2007-12-20     Revised Date:  2013-02-20    
Medline Journal Info:
Nlm Unique ID:  9711271     Medline TA:  Pac Symp Biocomput     Country:  Singapore    
Other Details:
Languages:  eng     Pagination:  115-26     Citation Subset:  IM    
Chenomx Inc., Edmonton, Alberta, Canada.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Brain Chemistry
Computational Biology
Databases, Factual
Magnetic Resonance Spectroscopy / statistics & numerical data*
Models, Biological
Multivariate Analysis
Rats, Sprague-Dawley

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Protein interactions and disease phenotypes in the ABC transporter superfamily.
Next Document:  Bioinformatics data profiling tools: a prelude to metabolic profiling.