VPTMdb: a viral post-translational modification database

Yujia Xiang; Quan Zou; Lilin Zhao

. CTD clusters 20 amino acids into three groups: hydrophobic, neutral and polar. The CTD composition (CTD-C) calculates the composition values of hydrophobic, neutral and polar groups for a given sequence. The CTD transition (CTD-T) represents the percentage frequency of an amino acid of one particular property followed by an amino acid of another property. The CTD distribution (CTD-D) represents the distribution of each property for a given sequence. Each property has five distribution descriptors, which are the first residue, 25% residues, 50% residues, 75% residues, and 100% residues in the whole sequence of a given specific property. In this research, CTD-C, CTD-T, and CTD-D were used to encoded protein sequences and yielded 39, 39, and 195 features, respectively. More detailed information about CTD can be found in the literature (Govindan and Nair, 2011) .