genomewalker
1/22/2016 - 8:05 AM

fa2sto.sh

#!/bin/bash

# We need one fasta file export with the aligned sequences and another with the SS SAI filter
ALIGN=${1}
OFILE=${1/.fasta/.stk}

# Creating the first part of the file
# we need to linearize the fasta file
awk '
BEGIN{
 RS=">"
 print "# STOCKHOLM 1.0"
}
{
 if ($0 ~ /HelBacte/)
  {
   exit
  }
}
{
      sub("\n","\t");
      gsub("\n","");
      gsub(" ","");
      gsub("\t"," "); 
      print $0
      }
' ${ALIGN} > ${OFILE}

# We linearize the SS SAI and add to the converted file
awk 'BEGIN{RS="HelBacte"}NR>1{sub("\n","\t"); gsub("\n",""); gsub(" ",""); gsub("\t"," "); print $0}' ${ALIGN} |awk '{print "#=GC SS_cons"$0"\n//"}' >> ${OFILE}