#RAW data
chr1q21 na S100A3 S100A6 HRNR DRD5P2 .......
HSA04910_INSULIN_SIGNALING_PATHWAY na XRCC5 HRAS ....
V$YY1_02 na B3GALT6 DZIP1 RAB1B SART3 FLJ20309 ..
MORF_EIF3S2 na HCCS XRCC3 LDHB LDHA OXA1L RPL14 ...
module_486 na CYP3A7 C14orf179 JAG2 INTS1 RBM6 ..
CATABOLIC_PROCESS na PGD HNRPD USE1 RNF217 RNASEH1
#second word can be eleminated
####
#Map data
XRCC5 SNP_A-1966881 1
EFNA1 SNP_A-1877994 9
HRNR SNP_A-1919060 2
XRCC5 SNP_A-1966884 1
XRCC5 SNP_A-1966882 1
HRNR SNP_A-1829030 1
####
chr1q21
HRNR SNP_A-1829030 1
HRNR SNP_A-1919060 2
EFNA1 SNP_A-1877994 9
HSA04910_INSULIN_SIGNALING_PATHWAY
XRCC5 SNP_A-1966884 1
XRCC5 SNP_A-1966882 1
XRCC5 SNP_A-1966881 1
.......
####
#Actually is a subroutine which is a part of my other program:
sub parseGeneEntry { ##purpose of this function is to return everything from the second tab onwards (these are the genes)
$genesList = $_[0];
#print $genesList."\n";
#print "STARTING PARSING \n";
@genes;
@genes = split(/\t/,$genesList);
shift(@genes); ##removes first entry of array
#print $#genes." "; ##for debugging only
shift(@genes);
#print $#genes." ";
#@genes;
$toReturn = "";
$counter = 0;
foreach $element(@genes){
if ($counter == 0){
$toReturn = $toReturn.$element;
$counter++;
}
else{
$toReturn = $toReturn."\t".$element;
}
}
#$toReturn = $toReturn."\n";
#print length($toReturn)." ".$toReturn."\n\n";
return($toReturn);
}