Rather than using manifest variables for accumulating results you can use a hash keyed by chromosome:
use strict;
use warnings;
my %chroms;
# Count frequency of start sited in the column-2.
while (<DATA>) {
next if /^#/; #ignore comments in the input file
chomp(my $line = $_);
my ($chr, $start, $end, $strand) = (split /\t/, $line)[0, 1, 2, 5]
+;
my $startPoint;
if ($strand eq '+') {
$startPoint = $start;
$chroms{$chr}{startPoints_plusStrand}{$startPoint}++;
} elsif ($strand eq '-') {
$startPoint = $end;
$chroms{$chr}{startPoints_minusStrand}{$startPoint}++;
} else {
die "Goofy BED Data on line $.:\n$_";
}
}
print "#Plus Strand BedGraph:\n";
for my $chromKey (keys %chroms) {
my $chrom = $chroms{$chromKey};
print "--- $chromKey\n";
for my $key (sort {$a <=> $b} keys %{$chrom->{startPoints_plusStra
+nd}}) {
print $key + 1, "\t", "+", "$chrom->{startPoints_plusStrand}{$
+key}\n";
}
}
__DATA__
#chromosome start end position col-5 strand
chr7 127471196 127472363 Pos1 0 +
chr7 127471196 127472363 Pos1 0 +
chr7 127471196 127472363 Pos1 0 +
chr7 127471196 127472363 Pos1 0 +
chr7 127471196 127472363 Pos1 0 +
chr7 127472363 127473530 Pos2 0 +
chr7 127473530 127474697 Pos3 0 -
chr7 127474697 127475864 Pos4 0 -
chr8 40000 40500 Pos5 0 +
chr8 40000 40600 Pos5 0 +
chr8 40000 40650 Pos5 0 +
chr8 41000 41200 Pos6 0 -
Optimising for fewest key strokes only makes sense transmitting to Pluto or beyond