comparison gomwu_b.pl @ 1:f7287f82602f draft

"planemo upload commit 486235d6560c9e95bd42152ad19bf7c3941cdc1b"

0:91261b42c07e

#!/usr/bin/env perl

my $usage= "

gomwu_b.pl  (v. Feb 2015):

";

my $gen2go=shift;
my $measure=shift;
my $div=shift or die "$usage\nNot enough arguments for gomwu_b.pl\n";

my $clfile="cl_dissim0_".$div."_".$gen2go; 
open CLF, $clfile or die "cannot locate primary clustering file $clfile\n";
my %clgo={};
my $go;
my $cl;

	push @{$clgo{$cl}},$go;
}
close CLF;

unlink $clfile;
unlink "dissim0_".$div."_".$gen2go; 

opendir THISDIR, ".";
my @donealready=grep /$gen2go/, readdir THISDIR;
my $dones=" "."@donealready"." ";
#print "DONE: $dones\n";

my $inname2=$measure.".".$div.".tmp";
open TAB, $inname2 or die "go_nrify: cannot open input table $inname2\n";
<TAB>;
my %level={};
my %desc={};
my %value={};

	@{$nrgenes{$goos}}=@nrgens;	
	$gcount+=$#nrgens+1;
}

print $#nrgos+1," non-redundant GO categories of good size\n-------------\n"; 
$outname=$div."_".$measure;
open OUT, ">$outname" or die "gomwu_b: cannot create output $outname\n";
print {OUT} "name\tterm\tlev\tseq\tvalue\n";

foreach $go (@nrgos) {
	foreach $gene (@{$nrgenes{$go}}){

my %dnds;

####################
# building dissimilarity matrix

my $inname4="dissim_".$div."_".$measure."_".$gen2go;
my $inname3=$div."_".$measure;

#if($dones!~/ $inname4 /) { 

	use List::Util qw[min max];
	open TAB, $inname3 or die "go_cluster: cannot open input table $inname3\n";
	<TAB>;

	my $des;
	my $go; 
	my $l;
	my $gn;
	my $val;
	my @gos=();
	my %genes={};
	my %gosi={};

	print"\nSecondary clustering:\ncalculating similarities....\n";
	while (<TAB>){
		chomp;

1:f7287f82602f

#!/usr/bin/env perl

use File::Basename;

my $usage= "

gomwu_b.pl  (v. Feb 2015):

";

my $gen2go=shift;
my $measure=shift;
($mname,$mdir,$mext) = fileparse($measure,'\..*');
($aname,$adir,$aext) = fileparse($gen2go,'\..*');
my $div=shift or die "$usage\nNot enough arguments for gomwu_b.pl\n";

my $clfile=$mdir."cl_dissim0_".$div."_".$aname.$aext; 
open CLF, $clfile or die "cannot locate primary clustering file $clfile\n";
my %clgo={};
my $go;
my $cl;

	push @{$clgo{$cl}},$go;
}
close CLF;

unlink $clfile;
unlink $mdir."dissim0_".$div."_".$aname.$aext; 

opendir THISDIR, $mdir;
my @donealready=grep /$gen2go/, readdir THISDIR;
my $dones=" "."@donealready"." ";
#print "DONE: $dones\n";

my $inname2=$mdir.$mname.".".$div.".tmp";
open TAB, $inname2 or die "go_nrify: cannot open input table $inname2\n";
<TAB>;
my %level={};
my %desc={};
my %value={};

	@{$nrgenes{$goos}}=@nrgens;	
	$gcount+=$#nrgens+1;
}

print $#nrgos+1," non-redundant GO categories of good size\n-------------\n"; 
$outname=$mdir.$mname."_".$div.".tsv";
print("creating $outname");
open OUT, ">$outname" or die "gomwu_b: cannot create output $outname\n";
print {OUT} "name\tterm\tlev\tseq\tvalue\n";

foreach $go (@nrgos) {
	foreach $gene (@{$nrgenes{$go}}){

my %dnds;

####################
# building dissimilarity matrix

my $inname4=$mdir."dissim_".$div."_".$mname."_".$aname.$aext;
my $inname3=$mdir.$mname."_".$div.".tsv";

#if($dones!~/ $inname4 /) { 

	use List::Util qw[min max];
	open TAB, $inname3 or die "go_cluster: cannot open input table $inname3\n";
	<TAB>;

	# my $des;
	# my $go; 
	# my $l;
	# my $gn;
	# my $val;
	# my @gos=();
	# my %genes={};
	my %gosi={};

	print"\nSecondary clustering:\ncalculating similarities....\n";
	while (<TAB>){
		chomp;