Abhimanyu Singh
A bioinformatics beginner
Our Sponsors
Perl script to extract sequence by Ids from multifasta file !
By Abhimanyu Singh 2093 days ago
#!/usr/bin/perl -w
use strict;
my $idsfile = "$ARGV[0]";
my $seqfile = "$ARGV[1]";
my %ids = ();
open FILE, $idsfile;
while(<FILE>) {
chomp;
$ids{$_} += 1;
}
close FILE;
local $/ = "\n>"; # read by FASTA record
open FASTA, $seqfile;
while (<FASTA>) {
chomp;
my $seq = $_;
my ($id) = $seq =~ /^>*(\S+)/; # parse ID as first word in FASTA header
if (exists($ids{$id})) {
$seq =~ s/^>*.+\n//; # remove FASTA header
$seq =~ s/\n//g; # remove endlines
print ">$id\n$seq\n";
}
}
close FASTA;
