Skip to main content
. Author manuscript; available in PMC: 2008 Mar 17.
Published in final edited form as: J Proteome Res. 2008 Jan 12;7(2):603–610. doi: 10.1021/pr0705237

Figure 4.

Figure 4

Frequency of occurrence of the top 10 peptide peaks (A) and top 10 glycan peaks (B) selected in 10 runs by randomly splitting the entire spectra into labeled and blinded sets. Note that the top 10 peptide and 10 glycan peaks in each run were found through 100 ACO-SVM iterations by randomly splitting the labeled set into training and validation sets at each iteration. The 10 most frequent m/z windows are listed.