A weighted classification model for peptide identification

Author

Xijun Liang ; Zhonghang Xia ; Xinnan Niu ; Link, A.

Author_Institution

Coll. of Sci., China Univ. of Pet., Qingdao, China

fYear

2014

fDate

2-4 June 2014

Firstpage

1

Lastpage

2

Abstract

Although a number of sequence database search tools and post-database search algorithms for filtering target PSMs have been developed, the discrepancy among the output PSMs is usually significant, remaining a few disputable PSMs. We employ a SVM-based learning model to search the optimal weight for each target PSM and develop a new score system, C-Ranker, to rank all target PSMs. Compared with PeptideProphet and Percolator, CRanker has identified more PSMs under similar false discover rates over different datasets.

Keywords

biochemistry; bioinformatics; classification; data mining; learning (artificial intelligence); mass spectra; molecular biophysics; molecular configurations; optimisation; pattern matching; query formulation; sequences; sorting; spectral analysis; support vector machines; C-Ranker; PSM identification; PSM output discrepancy; PeptideProphet; Percolator; SVM-based learning model; false discover rates; optimal weight search; peptide identification; post-database search algorithms; score system; sequence database search tools; target PSM filtering; target PSM ranking; weighted classification model; Databases; Educational institutions; Electronic mail; Peptides; Proteins; Support vector machines; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Advances in Bio and Medical Sciences (ICCABS), 2014 IEEE 4th International Conference on

Conference_Location

Miami, FL

Print_ISBN

978-1-4799-5786-6

Type

conf

DOI

10.1109/ICCABS.2014.6863913

Filename

6863913