Article Preprocessing of Tandem Mass Spectrometric Data Based on Decision Tree Classif ication

In this study, we present a preprocessing method for quadrupole time-of-f light (Q-TOF) tandem mass spectra to increase the accuracy of database searching for peptide (protein) identif ication. Based on the natural isotopic information inher-ent 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 iden-tif ication process. The experimental results show that this preprocessing method increases the search speed and the reliability of peptide identif ication. Key words: peptide identif ication, Q-TOF tandem mass spectra, feature selection, decision tre