The Community for Technology Leaders
2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops (2012)
Philadelphia, USA USA
Oct. 4, 2012 to Oct. 7, 2012
ISBN: 978-1-4673-2746-6
pp: 602-609
Xijun Liang , School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China
Zhonghang Xia , Dept. of Computer Science, Western Kentucky University, Bowling Green, KY 42101, USA
Xinnan Niu , Dept. of Pathology, Microbiology and Immunology, Vanderbilt University School of Medicine, Nashville, TN 37232
Andrew J. Link , Dept. of Pathology, Microbiology and Immunology, Vanderbilt University School of Medicine, Nashville, TN 37232
Liping Pang , School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China
Fangxiang Wu , Division of Biomedical Engineering, University of Saskatchewan, 57 Campus Dr., Saskatoon, SK S7N 5A9, Canada
Hongwei Zhang , School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China
ABSTRACT
Peptide identification is a critical step to understand the proteome in cells and tissue. Typically, high-throughput peptide spectra generated in the MS/MS procedure are searched against real protein sequences by peptide matching. Although a number of automated algorithms have been developed to help identifying those high quality of peptide spectrum matches (PSMs), lack of trustworthy target PSMs remains an open problem. In this paper, we design the FC-Ranker algorithm to calculate the score of each target PSM. A nonnegative weight is assigned to each target PSM to indicate its likelihood of being correct. Particularly, we proposed a fuzzy SVM classification model and a fuzzy silhouette index for iteratively updating the scores of target PSMs. Furthermore, FC-Ranker provides a framework for tackling the problem of uncertainty of target PSMs, and it can be easily adjusted to adapt new datasets.
INDEX TERMS
fuzzy support vector machine (SVM), peptide identification, peptide spectrum matches (PSMs), fuzzy clustering
CITATION

X. Liang et al., "A fuzzy cluster-based algorithm for peptide identification," 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops(BIBMW), Philadelphia, USA USA, 2012, pp. 602-609.
doi:10.1109/BIBMW.2012.6470208
89 ms
(Ver 3.3 (11022016))