Perl Working On Two Hash References - perl

Question

I would like to compare the values of two hash references.
The data dumper of my first hash is this:
$VAR1 = {
'42-MG-BA' => [
{
'chromosome' => '19',
'position' => '35770059',
'genotype' => 'TC'
},
{
'chromosome' => '2',
'position' => '68019584',
'genotype' => 'G'
},
{
'chromosome' => '16',
'position' => '9561557',
'genotype' => 'G'
},
And the second hash is similar to this but with more hashes in the array. I would like to compare the genotype of my first and second hash if the position and the choromosome matches.
map {print "$_= $cave_snp_list->{$_}->[0]->{chromosome}\n"}sort keys %$cave_snp_list;
map {print "$_= $geno_seq_list->{$_}->[0]->{chromosome}\n"}sort keys %$geno_seq_list;
I could do that for the first array of the hashes.
Could you help me in how to work for all the arrays?
This is my actual code in full
#!/software/bin/perl
use strict;
use warnings;
use Getopt::Long;
use Benchmark;
use Config::Config qw(Sequenom.ini);
useDatabase::Conn;
use Data::Dumper;
GetOptions("sam=s" => \my $sample);
my $geno_seq_list = getseqgenotypes($sample);
my $cave_snp_list = getcavemansnpfile($sample);
#print Dumper($geno_seq_list);
print scalar %$geno_seq_list, "\n";
foreach my $sam (keys %{$geno_seq_list}) {
my $seq_used = $geno_seq_list->{$sam};
my $cave_used = $cave_snp_list->{$sam};
print scalar(#$geno_seq_list->{$_}) if sort keys %$geno_seq_list, "\n";
print scalar(#$cave_used), "\n";
#foreach my $seq2com (# {$seq_used } ){
# foreach my $cave2com( # {$cave_used} ){
# print $seq2com->{chromosome},":" ,$cave2com->{chromosome},"\n";
# }
#}
map { print "$_= $cave_snp_list->{$_}->[0]->{chromosome}\n" } sort keys %$cave_snp_list;
map { print "$_= $geno_seq_list->{$_}->[0]->{chromosome}\n" } sort keys %$geno_seq_list;
}
sub getseqgenotypes {
my $snpconn;
my $gen_list = {};
$snpconn = Database::Conn->new('live');
$snpconn->addConnection(DBI->connect('dbi:Oracle:pssd.world', 'sn', 'ss', { RaiseError => 1, AutoCommit => 0 }),
'pssd');
#my $conn2 =Database::Conn->new('live');
#$conn2->addConnection(DBI->connect('dbi:Oracle:COSI.world','nst_owner','nst_owner', {RaiseError =>1 , AutoCommit=>0}),'nst');
my $id_ind = $snpconn->execute('snp::Sequenom::getIdIndforExomeSample', $sample);
my $genotype = $snpconn->executeArrRef('snp::Sequenom::getGenotypeCallsPosition', $id_ind);
foreach my $geno (#{$genotype}) {
push #{ $gen_list->{ $geno->[1] } }, {
chromosome => $geno->[2],
position => $geno->[3],
genotype => $geno->[4],
};
}
return ($gen_list);
} #end of sub getseqgenotypes
sub getcavemansnpfile {
my $nstconn;
my $caveman_list = {};
$nstconn = Database::Conn->new('live');
$nstconn->addConnection(
DBI->connect('dbi:Oracle:CANP.world', 'nst_owner', 'NST_OWNER', { RaiseError => 1, AutoCommit => 0 }), 'nst');
my $id_sample = $nstconn->execute('nst::Caveman::getSampleid', $sample);
#print "IDSample: $id_sample\n";
my $file_location = $nstconn->execute('nst::Caveman::getCaveManSNPSFile', $id_sample);
open(SNPFILE, "<$file_location") || die "Error: Cannot open the file $file_location:$!\n";
while (<SNPFILE>) {
chomp;
next if /^>/;
my #data = split;
my ($nor_geno, $tumor_geno) = split /\//, $data[5];
# array of hash
push #{ $caveman_list->{$sample} }, {
chromosome => $data[0],
position => $data[1],
genotype => $nor_geno,
};
} #end of while loop
close(SNPFILE);
return ($caveman_list);
}

Answer 1

The problem that I see is that you're constructing a tree for generic storage of data, when what you want is a graph, specific to the task. While you are constructing the record, you could also be constructing the part that groups data together. Below is just one example.
my %genotype_for;
my $record
= { chromosome => $data[0]
, position => $data[1]
, genotype => $nor_geno
};
push #{ $gen_list->{ $geno->[1] } }, $record;
# $genotype_for{ position }{ chromosome }{ name of array } = genotype code
$genotype_for{ $data[1] }{ $data[0] }{ $sample } = $nor_geno;
...
return ( $caveman_list, \%genotype_for );
In the main line, you receive them like so:
my ( $cave_snp_list, $geno_lookup ) = getcavemansnpfile( $sample );
This approach at least allows you to locate similar position and chromosome values. If you're going to do much with this, I might suggest an OO approach.
Update
Assuming that you wouldn't have to store the label, we could change the lookup to
$genotype_for{ $data[1] }{ $data[0] } = $nor_geno;
And then the comparison could be written:
foreach my $pos ( keys %$small_lookup ) {
next unless _HASH( my $sh = $small_lookup->{ $pos } )
and _HASH( my $lh = $large_lookup->{ $pos } )
;
foreach my $chrom ( keys %$sh ) {
next unless my $sc = $sh->{ $chrom }
and my $lc = $lh->{ $chrom }
;
print "$sc:$sc";
}
}
However, if you had limited use for the larger list, you could construct the specific case
and pass that in as a filter when creating the longer list.
Thus, in whichever loop creates the longer list, you could just go
...
next unless $sample{ $position }{ $chromosome };
my $record
= { chromosome => $chromosome
, position => $position
, genotype => $genotype
};
...