Skip to main content

Table 1 Pattern features for net 1 and net 2

From: Identification of b-/y-ions in MS/MS spectra using a two stage neural network

net 1 pattern features net 2 pattern features
feature value feature value
intensity N, D intensity N, D
strong peak B strong peak B
local intensity rank N local intensity rank N
global intensity rank N global intensity rank N
relative cleavage position N, D relative cleavage position N, D
random peak hypothesis P random peak hypothesis P
principal isotope H principal isotope H
isotopologue B isotopologue B
complement N complement P n e t 1
H2O neutral loss N, D H2O neutral loss N, D
NH3 neutral loss N, D NH3 neutral loss N, D
H2O-H2O neutral loss N, D H2O-H2O neutral loss N, D
H2O-NH3 neutral loss N, D H2O-NH3 neutral loss N, D
CO neutral loss (a-ion) N, D CO neutral loss (a-ion) N, D
   N-term flanking ion P n e t 1
   C-term flanking ion P n e t 1
  1. N specifies a normalized quantity, D specifies a discretized quantity, B indicates a binary value, H indicates a histogram value, N indicates a value sampled from a normal distribution, and P indicates a probability. All peaks are processed first by net 1 and and then by net 2. net 2 features are influenced by the preceding characterization of peaks by net 1.