From fb5fcff844914394ddf40174050d3bda71439ea1 Mon Sep 17 00:00:00 2001
From: Erika Villa <Erika.Villa@utsouthwestern.edu>
Date: Fri, 6 Jul 2018 09:41:31 -0500
Subject: [PATCH] cbioportal
---
alignment/filter_genefusions.pl | 12 ++++++------
genect_rnaseq/cBioPortal_documents.pl | 12 ++++++------
variants/filter_cnvkit.pl | 6 +++++-
3 files changed, 17 insertions(+), 13 deletions(-)
diff --git a/alignment/filter_genefusions.pl b/alignment/filter_genefusions.pl
index cc6481c..0786670 100755
--- a/alignment/filter_genefusions.pl
+++ b/alignment/filter_genefusions.pl
@@ -5,7 +5,6 @@ use Getopt::Long qw(:config no_ignore_case no_auto_abbrev);
my %opt = ();
my $results = GetOptions (\%opt,'fusion|f=s','prefix|p=s','help|h');
-
my %entrez;
open ENT, "</project/shared/bicf_workflow_ref/gene_info.human.txt" or die $!;
my $headline = <ENT>;
@@ -36,7 +35,7 @@ print OUT join("\t","FusionName","LeftGene","RightGene","LefttBreakpoint",
print OUTIR join("\t","Hugo_Symbol","Entrez_Gene_Id","Center","Tumor_Sample_Barcode",
"Fusion","DNA_support","RNA_support","Method","Frame"),"\n";
-my $sname = (split(/_DNA_panel1385/,$opt{prefix}))[0];
+my $sname = $opt{prefix};
open FUSION, "<$opt{fusion}" or die $!;
my $header = <FUSION>;
@@ -62,15 +61,16 @@ while (my $line = <FUSION>) {
$hash{SumRNAReads} += $hash{JunctionReadCount}+$hash{SpanningFragCount};
my $fname = join("--",$hash{LeftGene},$hash{RightGene});
my $fname2 = join("--",sort {$a cmp $b} $hash{LeftGene},$hash{RightGene});
- my $ename = join("--",$entrez{$hash{LeftGene}},$entrez{$hash{RightGene}});
- my ($dna_support,$rna_support)=("no","no");
+ my ($dna_support,$rna_support)=("no") x 2;
if ($known{$fname2} && ($hash{SumRNAReads} >= 3)|| ($hash{SumRNAReads} >= 5)) {
$rna_support = "yes";
print OUT join("\t",$fname,$hash{LeftGene},$hash{RightGene},
$hash{LeftBreakpoint},$hash{RightBreakpoint},$hash{LeftStrand},
$hash{RightStrand},$hash{SumRNAReads},0),"\n";
- print OUTIR join("\t",$fname,$ename,"UTSW NGS Clinical Sequencing Lab",$sname,$fname." fusion",
- 0,$rna_support,"STAR 2.5.2b","N/A"),"\n";
+ print OUTIR join("\t",$hash{LeftGene},$entrez{$hash{LeftGene}},"UTSW",$sname,$fname." fusion",
+ $dna_support,$rna_support,"STAR Fusion","N/A"),"\n";
+ print OUTIR join("\t",$hash{RightGene},$entrez{$hash{RightGene}},"UTSW",$sname,$fname." fusion",
+ $dna_support,$rna_support,"STAR Fusion","N/A"),"\n";
}
}
diff --git a/genect_rnaseq/cBioPortal_documents.pl b/genect_rnaseq/cBioPortal_documents.pl
index 7f1fe0c..fd0a8ba 100644
--- a/genect_rnaseq/cBioPortal_documents.pl
+++ b/genect_rnaseq/cBioPortal_documents.pl
@@ -35,28 +35,28 @@ close ENT_ENS;
if($opt{fpkm}){
open FPKM, "<$opt{fpkm}" or die $!;
- open OUTF, ">$opt{prefix}\.data_expression_median_fpkm.txt" or die $!;
+ open OUTF, ">$opt{prefix}\.data_fpkm.cbioportal.txt" or die $!;
print OUTF join("\t","Entrez_Gene_Id",$opt{prefix}),"\n";
my %fpkm;
my $fpkm_header = <FPKM>;
while(my $line = <FPKM>){
chomp $line;
- my @row = split(/\t/,$line);
- my $ensembl = (split(/\./,$row[0]))[0];
+ my ($id,$gene,$ref,$strand,$start,$end,$coverage,$fpkm,$tpm) = split(/\t/,$line);
+ my $ensembl = (split(/\./,$id))[0];
if ($entrez{$ensembl}) {
$entrezid = $entrez{$ensembl};
}else {
- $entrezid = $entrez{$row[1]};
+ $entrezid = $entrez{$gene};
}
next unless ($entrezid);
- print OUTF join("\t",$entrezid,$row[7]),"\n";
+ print OUTF join("\t",$entrezid,$fpkm),"\n";
}
close OUTF;
}
if($opt{logcpm}){
open IN, "<$opt{logcpm}" or die $!;
- open OUTL, ">$opt{prefix}\.cBioPortal.logCPM.txt" or die $!;
+ open OUTL, ">$opt{prefix}\.data_logCPM.cbioportal.txt" or die $!;
print OUTL join("\t","Entrez_Gene_Id",$opt{prefix}),"\n";
$fname = basename($opt{logcpm});
my $sample = (split(/\./,$fname))[0];
diff --git a/variants/filter_cnvkit.pl b/variants/filter_cnvkit.pl
index 596ec22..ddcf170 100644
--- a/variants/filter_cnvkit.pl
+++ b/variants/filter_cnvkit.pl
@@ -30,9 +30,11 @@ my $file = shift @ARGV;
my $prefix = (split(/\./,(split(/\//,$file))[0]))[0];
open OUT, ">$prefix\.cnvcalls.txt" or die $!;
-open BIO, ">$prefix\.data_cna_cbioportal.txt" or die $!;
+open BIO, ">$prefix\.data_cna_discrete.cbioportal.txt" or die $!;
+open BIO2, ">$prefix\.data_cna_continuous.cbioportal.txt" or die $!;
print OUT join("\t","Gene","Chromosome","Start","End","Abberation Type","CN","Score"),"\n";
print BIO join("\t","Hugo_Symbol","Entrez_Gene_Id",$prefix),"\n";
+print BIO2 join("\t","Hugo_Symbol","Entrez_Gene_Id",$prefix),"\n";
open IN, "<$file" or die $!;
my $header = <IN>;
@@ -56,9 +58,11 @@ while (my $line = <IN>) {
$cn_cbio = $cn -2;
$cn_cbio = 2 if ($cn > 4);
print BIO join("\t",$gene,$entrez{$gene},$cn_cbio),"\n";
+ print BIO2 join("\t",$gene,$entrez{$gene},$log2),"\n";
print OUT join("\t",$gene,$chr,$start,$end,$abtype,$cn,$weight),"\n";
}
}
close IN;
close OUT;
close BIO;
+close BIO2;
--
GitLab