Differences

This shows you the differences between two versions of the page.

--- genetica:preproc_models [2013/05/16 15:55] – [Alternativa a Fisher: Barnard Test] osotolongo
+++ genetica:preproc_models [2020/08/04 10:58] (current) – external edit 127.0.0.1
@@ Line 6: / Line 6: @@
 <code>
-$ plink plink --bfile archivo --model --allow-no-sex --out archivo
+$ plink --bfile archivo --model --allow-no-sex --out archivo
 </code>
@@ Line 37: / Line 37: @@
 # Copyright 2013 O. Sotolongo <osotolongo@fundacioace.com>
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
 use strict; use warnings;
 use File::Slurp qw(read_file);
@@ Line 47: / Line 57: @@
 my $ofile = $plist;
-$ofile =~ s/(.*)\.(.*)/$1\.$model\.recalc\.$2/;
+$ofile =~ s/(.*)\.(.*)/$1\.$model\.recalc2\.$2/;
+# cambiar a clustering con (?:PATTERN)
-my %input_data = reverse map {/^(.*\s+(rs\d+)\s+.*)$/} grep {/^(.*\s+$model\s+.*)$/} read_file $plist;
+my %input_data = reverse map {/^(\s*\d+\s+(\S+)\s+[A,T,C,G]+\s+[A,T,C,G]+\s+$model\s+.*)$/} grep {/^(.*\s+$model\s+.*)$/} read_file $plist;
-my %bim_data = map {/^\d+\s+(rs\d+)\s+\d+\.*\d*\s+(\d+)\s+[A,T,C,G]+\s+[A,T,C,G]+\s*$/} grep {/.*rs\d+.*/} read_file $bimfile;
+my %bim_data = map {/^\d+\s+(.*)\s+\d+\.*\d*\s+(\d+)\s+[A,T,C,G]+\s+[A,T,C,G]+\s*$/} read_file $bimfile;
 my %cells;
 foreach my $marker (sort keys %input_data){
-	(@{$cells{$marker}} {qw/chr allele1 allele2 affa1 affa2 unaffa1 unaffa2 chi2 df pval0/}) = $input_data{$marker} =~ /^\s*(\d+)\s+rs\d+\s+([A,T,C,G])+\s+([A,T,C,G])+\s+$model\s+(\d+)\/(\d+)\s+(\d+)\/(\d+)\s+(\d+\.*\d*e*-*\d*|NA)\s+(\d+\.*\d*e*-*\d*|NA)\s+(\d+\.*\d*e*-*\d*|NA)\s*$/;
+	(@{$cells{$marker}} {qw/chr allele1 allele2 affa1 affa2 unaffa1 unaffa2 chi2 df pval0/}) = $input_data{$marker} =~ /^\s*(\d+)\s+$marker\s+([A,T,C,G])+\s+([A,T,C,G])+\s+$model\s+(\d+)\/(\d+)\s+(\d+)\/(\d+)\s+(\d+\.*\d*e*-*\d*|NA)\s+(\d+\.*\d*e*-*\d*|NA)\s+(\d+\.*\d*e*-*\d*|NA)\s*$/;
 	if(exists($cells{$marker}{affa1}) && exists($cells{$marker}{affa2}) && exists($cells{$marker}{unaffa1}) && exists($cells{$marker}{unaffa2})){
 		my $affa1 = $cells{$marker}{affa1};
@@ Line 79: / Line 89: @@
 foreach my $marker (sort {($cells{$a}->{chr} <=> $cells{$b}->{chr}) or ($a cmp $b)} keys %input_data){
-	print ODF "$cells{$marker}{chr}\t$marker\t$bim_data{$marker}\t$cells{$marker}{allele1}\t$cells{$marker}{allele2}\t$cells{$marker}{afreq}\t$cells{$marker}{ufreq}\t$cells{$marker}{chi2}\t$cells{$marker}{df}\t$cells{$marker}{pval0}\t$cells{$marker}{oddsratio}\t$cells{$marker}{stderr}\t$cells{$marker}{pvalue}\n";
+	if(exists($bim_data{$marker})){
+		print ODF "$cells{$marker}{chr}\t$marker\t$bim_data{$marker}\t$cells{$marker}{allele1}\t$cells{$marker}{allele2}\t$cells{$marker}{afreq}\t$cells{$marker}{ufreq}\t$cells{$marker}{chi2}\t$cells{$marker}{df}\t$cells{$marker}{pval0}\t$cells{$marker}{oddsratio}\t$cells{$marker}{stderr}\t$cells{$marker}{pvalue}\n";
+	}
 }
@@ Line 145: / Line 157: @@
 $cells{$marker}{pvalue} = shit->get('x');
 </code>
+**OJO:** Esto demora muchisimo. Despues de 5 días de calculo sobre una base de datos y modelo dominate tuve que para la ejecucion. Lo lanzare cuando tenga tiempo y la base de datos a usar este definida.