conservation_stats.sh

#!/bin/bash
for a in *;do;
  echo $a;cd $a;
  for i in *.faa;do;
    j=`echo $i | cut -d. -f1`;
    for k in *.faa;do;
      l=`echo $k | cut -d. -f1`;
      water -asequence $i -bsequence $k -datafile EBLOSUM60 -gapopen 10 -gapextend 0.5 -outfile  $j.$l -nobrief > /dev/null 2>&1;
      sed -i s/\#//g $j.$l;
      awk 'FNR == 19{printf $2" "}; FNR==26{print $2" "}; FNR==20{printf $2" "}' $j.$l | tr -d '()' | sed s'|/| |'g > $j.$l.tmp;
      awk '{print(($3/$4))}' $j.$l.tmp >> out; 
      done;
    done;
  awk '{for(i=1;i<=NF;i++) {sum[i] += $i; sumsq[i] += ($i)^2}} END {for (i=1;i<=NF;i++) {print sum[i]/NR, sqrt((sumsq[i]-sum[i]^2/NR)/NR)}}' out;
  cd ../;
done