Homework 6. In a multi-sequence FASTA file, produce statistics such as sequence number, average seq length, GC content, AT content, etc
It is Myeongji`s idea
#!/usr/bin/perl
use strict;
use warnings;
my$DNA1="TRET.txt";
open(fileHandle, $DNA1);
my@allLines1=<fileHandle>;
chomp(@allLines1);
my@protein1 = splice @allLines1, 1;
close(fileHandle);
my$DNA2="VEGFA.txt";
open(fileHandle, $DNA2);
my@allLines2=<fileHandle>;
chomp(@allLines2);
my@protein2 = splice @allLines2, 1;
close(fileHandle);
my$DNA3="Propreinsulin.txt";
open(fileHandle, $DNA3);
my@allLines3=<fileHandle>;
chomp(@allLines3);
my@protein3 = splice @allLines3, 1;
close(fileHandle);
my$pro1 = join "",@protein1;
print "TRET : ", $pro1, "\n";
my$pro2 = join "",@protein2;
print "VEGFA : ", $pro2, "\n";
my$pro3 = join "",@protein3;
print "Propreinsulin : ", $pro3, "\n";
print "\n";
my$length1=length$pro1;
print "The length of TRET sequence : $length1.\n";
my$length2=length$pro2;
print "The length of VEGFA sequence : $length2.\n";
my$length3=length$pro3;
print "The length of Propreinsulin sequence : $length3.\n";
my$average=($length1+$length2+$length3)/3;
print "The average length of multi-sequences : $average.\n";
print "\n";
# =~tr/AT/BC/ : A를 B로, T를 C로 교환 (1:1)
my $i;
for($i=1; $i<=3; $i++)
{
if($i == 1)
{
my$pro = $pro1;
my$a=($pro=~tr/A/A/);
my$b=($pro=~tr/C/C/);
my$c=($pro=~tr/G/G/);
my$d=($pro=~tr/T/T/);
my$Total=$a+$b+$c+$d;
print"<protein", $i, ">\n";
print"The number of A is $a.\n";
print"The number of C is $b.\n";
print"The number of G is $c.\n";
print"The number of T is $d.\n";
print"Total bases in DNA : $Total.\n";
#count of GC
#=~s:search, /이걸/이걸로/ 치환 (1:1아님), g:글로벌 매칭(스트링 전체를 훑고 매칭하는 것), 치환한 갯수를 결과로 나타냄
my$GC=($pro=~s/GC/GC/g);
print"The total number of dinucleotide GC in DNA : $GC.\n";
#count of AT
my$AT=($pro=~s/AT/AT/g);
print"The total number of dinucleotide AT in DNA : $AT.\n";
#percentage of GC & AT
my$GCper=($GC/($Total)*100);
print"The percentage of GC: $GCper%.\n";
my$ATper=($AT/($Total)*100);
print"The percentage of AT: $ATper%.\n";
print "\n";
};
if($i == 2)
{
my$pro = $pro2;
my$a=($pro=~tr/A/A/);
my$b=($pro=~tr/C/C/);
my$c=($pro=~tr/G/G/);
my$d=($pro=~tr/T/T/);
my$Total=$a+$b+$c+$d;
print"<protein", $i, ">\n";
print"The number of A is $a.\n";
print"The number of C is $b.\n";
print"The number of G is $c.\n";
print"The number of T is $d.\n";
print"Total bases in DNA : $Total.\n";
#count of GC
#=~s:search, /이걸/이걸로/ 치환 (1:1아님), g:글로벌 매칭(스트링 전체를 훑고 매칭하는 것), 치환한 갯수를 결과로 나타냄
my$GC=($pro=~s/GC/GC/g);
print"The total number of dinucleotide GC in DNA : $GC.\n";
#count of AT
my$AT=($pro=~s/AT/AT/g);
print"The total number of dinucleotide AT in DNA : $AT.\n";
#percentage of GC & AT
my$GCper=($GC/($Total)*100);
print"The percentage of GC: $GCper%.\n";
my$ATper=($AT/($Total)*100);
print"The percentage of AT: $ATper%.\n";
print "\n";
};
if($i == 3)
{
my$pro = $pro3;
my$a=($pro=~tr/A/A/);
my$b=($pro=~tr/C/C/);
my$c=($pro=~tr/G/G/);
my$d=($pro=~tr/T/T/);
my$Total=$a+$b+$c+$d;
print"<protein", $i, ">\n";
print"The number of A is $a.\n";
print"The number of C is $b.\n";
print"The number of G is $c.\n";
print"The number of T is $d.\n";
print"Total bases in DNA : $Total.\n";
#count of GC
#=~s:search, /이걸/이걸로/ 치환 (1:1아님), g:글로벌 매칭(스트링 전체를 훑고 매칭하는 것), 치환한 갯수를 결과로 나타냄
my$GC=($pro=~s/GC/GC/g);
print"The total number of dinucleotide GC in DNA : $GC.\n";
#count of AT
my$AT=($pro=~s/AT/AT/g);
print"The total number of dinucleotide AT in DNA : $AT.\n";
#percentage of GC & AT
my$GCper=($GC/($Total)*100);
print"The percentage of GC: $GCper%.\n";
my$ATper=($AT/($Total)*100);
print"The percentage of AT: $ATper%.\n";
print "\n";
};
};
exit;
my $file = <FASTA>;
my @R = split "",$file;
my $A =0;
foreach my $nuc (@R) {
if ($nuc eq 'A') {
$A = $A+1;
}
}
