Proteome Profiling without Selection Bias

Author

Barla, Annalisa ; Irler, Bettina ; Merler, Stefano ; Jurman, Giuseppe ; Paoli, Silvano ; Furlanello, Cesare

Author_Institution

ITC, Trento

fYear

0

fDate

0-0 0

Firstpage

941

Lastpage

946

Abstract

In this paper, we present a method for predictive profiling of mass spectrometry data. The method integrates a spectra preprocessing pipeline with a complete validation setup aimed at identifying the discriminating peaks and at providing an unbiased estimate of the predictive classification error, based on SVM classifiers and on entropy-based RFE procedure. A particular emphasis is placed upon avoiding selection bias effects throughout all the analysis steps, from preprocessing to peak importance ranking

Keywords

biology computing; entropy; mass spectroscopic chemical analysis; molecular biophysics; proteins; support vector machines; SVM classifiers; entropy-based RFE procedure; mass spectrometry; peak importance ranking; predictive classification error; predictive profiling; proteome profiling; selection bias; spectra preprocessing pipeline; Biomarkers; Data preprocessing; Grid computing; Ionization; Mass spectroscopy; Pipelines; Proposals; Proteomics; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2006. CBMS 2006. 19th IEEE International Symposium on

Conference_Location

Salt Lake City, UT

ISSN

1063-7125

Print_ISBN

0-7695-2517-1

Type

conf

DOI

10.1109/CBMS.2006.134

Filename

1647691