Calculate ATGC percentage in parallel with perl
By Jit 2640 days ago
#!/usr/bin/perl
use strict;
use Parallel::ForkManager;
use Bio::SeqIO;
#usage: perl testParallel.pl <multi fasta infile>
my %sequences;
my $seqio = Bio::SeqIO->new(-file => "$ARGV[0]", -format => "fasta");
while(my$seqobj = $seqio->next_seq) {
my $id = $seqobj->display_id; # there's your key
my $seq = $seqobj->seq; # and there's your value
$sequences{$id} = $seq;
}
my $max_procs = 5;
my @names = keys %sequences;
# hash to resolve PID's back to child specific information
my $pm = new Parallel::ForkManager($max_procs);
# Setup a callback for when a child finishes up so we can
# get it's exit code
$pm->run_on_finish (
sub { my ($pid, $exit_code, $ident) = @_;
#print "** $ident just got out of the pool ".
"with PID $pid and exit code: $exit_code\n";
}
);
$pm->run_on_start(
sub { my ($pid,$ident)=@_;
#print "** $ident started, pid: $pid\n";
}
);
$pm->run_on_wait(
sub {
#print "** Have to wait for one children ...\n"
},
0.5
);
NAMES:
foreach my $child ( 0 .. $#names ) {
my $pid = $pm->start($names[$child]) and next NAMES;
checkATCG($names[$child]);
$pm->finish($child); # pass an exit code to finish
}
print "Waiting for Children...\n";
$pm->wait_all_children;
print "Everybody is out of the pool!\n";
sub checkATCG {
my $name=shift;
my $DNA=$sequences{$name};
my $length=length $DNA;
my $a=($DNA=~tr/A//);
my $b=($DNA=~tr/C//);
my $c=($DNA=~tr/G//);
my $d=($DNA=~tr/T//);
my $Total=$a+$b+$c+$d;
my $GC=($DNA=~s/GC/GC/g);
my $AT=($DNA=~s/AT/AT/g);
my $GCper=($GC/($Total)*100);
print"$name\t$Total\t$AT\t$GC\t$GCper:\n";
}
