Pharmaceutical Sciences Faculty Publications
Analysis of Mass Spectral Serum Profiles for Biomarker Selection
Document Type
Article
Publication Date
9-13-2005
Journal Title
Bioinformatics
Volume
21
Issue
21
First Page
4039
Last Page
4045
DOI
10.1093/bioinformatics/bti670
Abstract
Motivation: Mass spectrometric profiles of peptides and proteins obtained by current technologies are characterized by complex spectra, high dimensionality and substantial noise. These characteristics generate challenges in the discovery of proteins and protein-profiles that distinguish disease states, e.g. cancer patients from healthy individuals. We present low-level methods for the processing of mass spectral data and a machine learning method that combines support vector machines, with particle swarm optimization for biomarker selection.
Results: The proposed method identified mass points that achieved high prediction accuracy in distinguishing liver cancer patients from healthy individuals in SELDI-QqTOF profiles of serum.
Availability: MATLAB scripts to implement the methods described in this paper are available from the HWR's lab website http://lombardi.georgetown.edu/labpage
Contact:hwr@georgetown.edu
Keywords
Biomarker, mass spectrometry, peptides, proteins, spectrum, serum
Recommended Citation
Ressom, Habtom W.; Varghese, Rency S.; Abdel-Hamid, Mohamed; Abdel-Latif Eissa, Sohair; Saha, Daniel; Goldman, Lenka; Petricoin, Emanuel F.; Conrads, Thomas P.; Veenstra, Timothy D.; Loffredo, Christopher A.; and et al, "Analysis of Mass Spectral Serum Profiles for Biomarker Selection" (2005). Pharmaceutical Sciences Faculty Publications. 418.
https://digitalcommons.cedarville.edu/pharmaceutical_sciences_publications/418