Skip to main content

Table 2 Description of features selected for the classifiers built for the two datasets.

From: Prediction of peptides observable by mass spectrometry applied at the experimental set level

Avian Bursa Dataset
Number of prolines
Percent glycine
Percent alanine
Percent leucine
Percent polar amino acids
Percent hydrophobic amino acids
Percent positive amino acids
Percent negative
Size (Dawson, 1972)
Optimized transfer energy parameter (Oobatake et al., 1985)
Weights for beta-sheet at the window position of 5 (Qian-Sejnowski, 1988)
Transfer free energy from oct to wat (Radzicka-Wolfenden, 1988)
Information measure for C-terminal turn (Robson-Suzuki, 1976)
Amphiphilicity index (Mitaku et al., 2002)
Hodgkin's Lymphoma Model Dataset
Number of cytosienes
Signal sequence helical potential (Argos et al., 1982)
Transer free energy to surface (Bull-Breese, 1974)
Normalized relative frequency of alpha-helix (Isogai et al., 1980)
Normalized relative frequence of double bend (Isogai et al., 1980)
Distance between C-alpha and centroid fo side chain (Levitt, 1976)
Retention coefficient in NAH2PO4 (Meek-Rossetti, 1981)
Interior composition of amino acids intracellular proteins (Fukuchi-Nishikawa, 2001)
Linker propensity from 1-linker dataset (George-Heringa, 2003)