If I understood correctly, you want something like:
-
Read and parse the sequences file
- For each sequence, open a file that is named after the sequence header
- From that file, get the first number of each line
- Associate each letter in the sequence with those numbers
use strict;
use warnings;
my ($seqfile) = @ARGV;
#seqfile is the file with the sequences.
open my $seqfh, "<", $seqfile or die $!;
{
local $/ = "\n>";
while (my $nextseq = <$seqfh>){
chop $nextseq unless eof $seqfh;
substr ($nextseq,0,1,"") if $. == 1;
my ($name,@seq) = split /\n/,$nextseq;
my @aas = split //,join "",@seq;
my @coords = getCoords ($name);
print "$aas[$_] $coords[$_]\n" for(0..$#aas);
}
}
sub getCoords
{
my ($fname) = @_;
local $/="\n";
my @ns;
open my $fh, "<", $fname or die $!;
while (my $line = <$fh>){
chomp $line;
my @ff = split /\s+/,$line;
push @ns, (split /\s+/,$line)[0];
}
close $fh;
return @ns;
}