Support vector machine with a Pearson VII function kernel for discriminating halophilic and non-halophilic proteins

- We defined the normalized amino acid composition and found halophilic proteins have fewer small residues.
- We introduced a novel kernel named Pearson VII function kernel and developed a support vector machine classifier to discriminate halophilic and non-halophilic proteins.
- The prediction accuracy was very encouraging and reached 91.7%.
- The reason of worse performance for small proteins may be related with the missing of some important residues.