Nonparametric Models for Peak Identification and
Quantification in MALDI-TOF Mass Spectroscopy

Leanna L. House, Merlise A. Clyde and Robert L. Wolpert

Duke University

Decenber 2006

We present a novel nonparametric Bayesian model using Lévy random field priors for identifying the presence and abundance of proteins from mass spectrometry data. Informed prior distributions, based on expert opinion and on preliminary laboratory experiments, help distinguish true peaks from background noise and help resolve uncertainty about peak multiplicity.

Keywords: Bayes; Kernel Regression; Lévy random fields

The manuscript is available in PostScript (2.82Mb) and PDF (1.36Mb) formats.

Cite as:

@TechReport{Hous:Clyd:Wolp:2006,
      Author = "Leanna L. House and Merlise A. Clyde and Robert L. Wolpert",
       Title = "Nonparametric Models for Peak Identification and
                Quantification in Mass Spectroscopy with Application to
                {MALDI-TOF}",
        Year = 2006,
 Institution = "Duke University Department of Statistical Science",
        Type = "Discussion Paper",
      Number = "2006-24",
         URL = "www.stat.duke.edu/ftp/pub/WorkingPapers/06-24.html",
}