featureCKSAAP: Feature Coding by k-spaced Aminoacids/Base Pairs
In BioSeqClass: Classification for Biological Sequences

Description Usage Arguments Details Author(s) Examples

Protein sequences are coded based on the frequency of k-spaced aminoacids/base pairs.

1	featureCKSAAP(seq,g,class=elements("aminoacid"))

`seq`	a string vector for the protein, DNA, or RNA sequences.
`g`	an integer indicating the distance between two aminoacids/bases (g>=0).
`class`	a list for the class of biological properties. It can be produced by `elements` and `aaClass`.

featureCKSAAP returns a matrix with (g+1)*M\^2 columns. Each row represented features of one sequence coding by a (g+1)*M\^2 dimension numeric vector. Each column is the number of k-spaced aminoacids/base pair (0<=k<=g).

Hong Li

if(interactive()){
  file = file.path(path.package("BioSeqClass"), "example", "acetylation_K.pos40.pep")
  seq = as.matrix(read.csv(file,header=F,sep="\t",row.names=1))[,1]
    
  CKSAAP0 = featureCKSAAP(seq,0,elements("aminoacid"))
  CKSAAP2 = featureCKSAAP(seq,2,elements("aminoacid"))  
}