\name{featurePSSM}
\alias{featurePSSM}
\title{Feature Coding}
\description{
  A set of functions for extract features from biological sequences, and coding 
  features by numeric vector.
}
\usage{
  featurePSSM(seq, start.pos, stop.pos, psiblast.path, database.path)  
}
\arguments{    
  \item{seq}{a string vector for the protein, DNA, or RNA sequences.} 
  \item{start.pos}{a integer vector denoting the start position of the fragment window.}  
  \item{stop.pos}{a integer vector denoting the stop position of the fragment window.}
  \item{psiblast.path}{a string for the path of blastpgp program. 
    blastpgp will be employed to do PSI-BLAST and get Position-Specific 
    Scoring Matrix.}
  \item{database.path}{a string for the path of a formated reference database.
    Database can be formated by "formatdb" program.}
}
\details{  
  \code{\link{featurePSSM}} returns a matrix with 20*N+N columns. Each row 
  represented features of one sequence coding by a 20*N+N dimension numeric 
  vector generated by PSI-BLAST. It contains two kinds of fatures: normalized 
  position-specific score of PSSM (Position-Specific Scoring Matrix), Shannon 
  entropy for each position of WOP (weighted observed percentages). Program 
  PSI-BLAST and formatted NCBI non-redundant protein database are needed.  
}
\author{Hong Li}
\examples{
if(interactive()){
  file = file.path(.path.package("BioSeqClass"), "example", "acetylation_K.fasta")  
  tmp = readFASTA(file) 
  proteinSeq = sapply(tmp,function(x){x[["seq"]]})
  names(proteinSeq) = sapply(tmp,function(x){x[["desc"]]})
   
  ## Need "blastpgp" program and a formated database. Database can be formated by "formatdb" program.
  PSSM1 = featurePSSM(proteinSeq[1:2], start.pos=rep(1,2), stop.pos=rep(10,2), psiblast.path="blastpgp", database.path="./result1.fasta")  
}
}