SVM model for quality assessment of medium resolution mass spectra from 18O-water labeling experiments

Alexey V. Nefedov, Miroslaw J. Gilski, Rovshan G. Sadygov

Research output: Contribution to journalArticle

6 Scopus citations

Abstract

We describe a method for assessing the quality of mass spectra and improving reliability of relative ratio estimations from 18O-water labeling experiments acquired from low resolution mass spectrometers. The mass profiles of heavy and light peptide pairs are often affected by artifacts, including coeluting contaminant species, noise signal, instrumental fluctuations in measuring ion position and abundance levels. Such artifacts distort the profiles, leading to erroneous ratio estimations, thus reducing the reliability of ratio estimations in high throughput quantification experiments. We used support vector machines (SVMs) to filter out mass spectra that deviated significantly from expected theoretical isotope distributions. We built an SVM classifier with a decision function that assigns a score to every mass profile based on such spectral features as mass accuracy, signal-to-noise ratio, and differences between experimental and theoretical isotopic distributions. The classifier was trained using a data set obtained from samples of mouse renal cortex. We then tested it on protein samples (bovine serum albumin) mixed in five different ratios of labeled and unlabeled species. We demonstrated that filtering the data using our SVM classifier results in as much as a 9-fold reduction in the coefficient of variance of peptide ratios, thus significantly improving the reliability of ratio estimations.

Original languageEnglish (US)
Pages (from-to)2095-2103
Number of pages9
JournalJournal of Proteome Research
Volume10
Issue number4
DOIs
StatePublished - Apr 1 2011

Keywords

  • Support vector machines
  • isotope distribution
  • mass accuracy
  • signal-to-noise ratio
  • stable-isotope labeling

ASJC Scopus subject areas

  • Biochemistry
  • Chemistry(all)

Fingerprint Dive into the research topics of 'SVM model for quality assessment of medium resolution mass spectra from <sup>18</sup>O-water labeling experiments'. Together they form a unique fingerprint.

  • Cite this