Bioinformatics Advance Access originally published online on June 24, 2004
Bioinformatics 2004 20(17):3128-3136; doi:10.1093/bioinformatics/bth372
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Bioinformatics vol. 20 issue 17 © Oxford University Press 2004; all rights reserved.
Standardization and denoising algorithms for mass spectra to classify whole-organism bacterial specimens
1 Division of Laboratory Science, National Center for Environmental Health, Centers for Disease Control and Prevention, Atlanta, GA 30341, USA, 2 Department of Statistics, University of Georgia, Athens, GA 30602, USA and 3 Division of Bacterial and Mycotic Diseases, National Center for Infectious Diseases, Centers for Disease Control and Prevention, Atlanta, GA 30333, USA
Received on February 13, 2004; revised on June 9, 2004; accepted on June 15, 2004
Advance Access Publication June 23, 2004
Motivation: Application of mass spectrometry in proteomics is a breakthrough in high-throughput analyses. Early applications have focused on protein expression profiles to differentiate among various types of tissue samples (e.g. normal versus tumor). Here our goal is to use mass spectra to differentiate bacterial species using whole-organism samples. The raw spectra are similar to spectra of tissue samples, raising some of the same statistical issues (e.g. non-uniform baselines and higher noise associated with higher baseline), but are substantially noisier. As a result, new preprocessing procedures are required before these spectra can be used for statistical classification.
Results: In this study, we introduce novel preprocessing steps that can be used with any mass spectra. These comprise a standardization step and a denoising step. The noise level for each spectrum is determined using only data from that spectrum. Only spectral features that exceed a threshold defined by the noise level are subsequently used for classification. Using this approach, we trained the Random Forest program to classify 240 mass spectra into four bacterial types. The method resulted in zero prediction errors in the training samples and in two test datasets having 240 and 300 spectra, respectively.
Availability: Fortran code for standardization and denoising is available at the supplementary information website.
Supplementary information: http://www.stat.uga.edu/~datta/Massspec/supp.html
Contact: gsatten{at}cdc.gov
* To whom correspondence should be addressed.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  Y. M. Williamson, H. Moura, A. R. Woolfitt, J. L. Pirkle, J. R. Barr, M. D. G. Carvalho, E. P. Ades, G. M. Carlone, and J. S. Sampson Differentiation of Streptococcus pneumoniae Conjunctivitis Outbreak Isolates by Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry Appl. Envir. Microbiol., October 1, 2008; 74(19): 5891 - 5897. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 D. Mantini, F. Petrucci, P. Del Boccio, D. Pieragostino, M. Di Nicola, A. Lugaresi, G. Federici, P. Sacchetta, C. Di Ilio, and A. Urbani Independent component analysis for the extraction of reliable protein signal profiles from MALDI-TOF mass spectra Bioinformatics, January 1, 2008; 24(1): 63 - 70. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 P. Larranaga, B. Calvo, R. Santana, C. Bielza, J. Galdiano, I. Inza, J. A. Lozano, R. Armananzas, G. Santafe, A. Perez, et al. Machine learning in bioinformatics Brief Bioinform, March 1, 2006; 7(1): 86 - 112. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 J. Listgarten and A. Emili Statistical and Computational Methods for Comparative Proteomic Profiling Using Liquid Chromatography-Tandem Mass Spectrometry Mol. Cell. Proteomics, April 1, 2005; 4(4): 419 - 434. [Abstract] [Full Text] [PDF]
|
|