IJPAM: Volume 76, No. 3 (2012)

FUZZY SUPPORT VECTOR MACHINES BASED ALGORITHM
FOR PEPTIDE IDENTIFICATION FROM
TANDEM MASS SPECTRA

Ling Jian$^1$, Zunquan Xia$^2$
$^{1,2}$School of Mathematical Sciences
Dalian University of Technology
Dalian, 116024, P.R. CHINA
$^1$College of Science
University of Petroleum
Qingdao, 266555, P.R. CHINA


Abstract. Shotgun tandem mass spectrometry-based peptide sequencing using programs such as SEQUEST allows high-throughput identification of peptides, which in turn allows identification of corresponding proteins. This paper present a novel machine learning method based on Fuzzy Support Vector Machines (Fuzzy SVMs) to discriminate between correct and incorrect identified peptides using SEQUEST search results. Through incorporating fuzzy membership this method can reduce the effect of noise in data points. Experiments show that this approach outperforms the traditional SVMs based technique, and it's an promising algorithm for peptide identification task.

Received: February 20, 2012

AMS Subject Classification: 92B05

Key Words and Phrases: peptide identification, SEQUEST, fuzzy support vector machines, mass spectrometry

Download paper from here.



Source: International Journal of Pure and Applied Mathematics
ISSN printed version: 1311-8080
ISSN on-line version: 1314-3395
Year: 2012
Volume: 76
Issue: 3