Preprocessing of tandem mass spectrometric data based on decision tree classification

Genomics Proteomics Bioinformatics. 2005 Nov;3(4):231-7. doi: 10.1016/s1672-0229(05)03032-9.


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.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Amino Acid Sequence
  • Animals
  • Cattle
  • Computational Biology*
  • Databases, Protein
  • Decision Trees
  • Isotopes
  • Mass Spectrometry*
  • Peptides / analysis*
  • Peptides / chemistry
  • Peptides / metabolism
  • Proteins / analysis*
  • Proteins / chemistry
  • Proteins / metabolism
  • Sensitivity and Specificity
  • Serum Albumin, Bovine / chemistry
  • Trypsin / pharmacology


  • Isotopes
  • Peptides
  • Proteins
  • Serum Albumin, Bovine
  • Trypsin