Article ID: | iaor2009352 |
Country: | United Kingdom |
Volume: | 23 |
Start Page Number: | 619 |
End Page Number: | 626 |
Publication Date: | Jan 2007 |
Journal: | Bioinformatics |
Authors: | Ressom H.W., Varghese R.S., Drake S.K., Hortin G.L., Abdel-Hamid M., Loffredo C.A., Goldman R. |
Keywords: | heuristics: ant systems |
Due to the large number of peaks in mass spectra of low-molecular-weight enriched sera, a systematic method is needed to select a parsimonious set of peaks to facilitate biomarker identification. We present computational methods for matrix-assisted laser desorption/ionization time-of-flight spectral data preprocessing and peak selection. In particular, we propose a novel method that combines ant colony optimization with support vector machines to select a small set of useful peaks.