Preprocessing of Tandem Mass Spectrometric Data Based on Decision Tree Classification
- Author:
Zhang JING-FEN
1
;
He SI-MIN
;
Cai JIN-JIN
;
Cao XING-JUN
;
Sun RUI-XIANG
;
Fu YAN
;
Zeng RONG
;
Gao WEN
Author Information
1. 中国科学院计算技术研究所
- Keywords:
peptide identification;
Q-TOF tandem mass spectra;
feature selection;
decision tree
- From:
Genomics, Proteomics & Bioinformatics
2005;3(4):231-237
- CountryChina
- Language:Chinese
-
Abstract:
In this study, we present a preprocessing method for quadrupole time-of-flight(Q-TOF) tandem mass spectra to increase the accuracy of database searching for peptide (protein) identification. Based on the natural isotopic information inherent in tandem mass spectra, we construct a decision tree after feature selection to classify the noise and ion peaks in tandem spectra. Furthermore, we recognize overlapping peaks to find the monoisotopic masses of ions for the following identification process. The experimental results show that this preprocessing method increases the search speed and the reliability of peptide identification.
