From 47b225a367b264060dc1c845cad8be829c627fd8 Mon Sep 17 00:00:00 2001
From: Brandi Cantarel <brandi.cantarel@utsouthwestern.edu>
Date: Fri, 13 Sep 2019 13:38:06 -0500
Subject: [PATCH] confounding symbols on multiple chrs

---
 genect_rnaseq/concat_fpkm.pl | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/genect_rnaseq/concat_fpkm.pl b/genect_rnaseq/concat_fpkm.pl
index c3be1e3..18ee999 100755
--- a/genect_rnaseq/concat_fpkm.pl
+++ b/genect_rnaseq/concat_fpkm.pl
@@ -15,7 +15,7 @@ while (my $line = <SYM>) {
     chomp($line);
     my ($chrom,$start,$end,$ensembl,$symbol,$type) = split(/\t/,$line);
     $ensembl = (split(/\./,$ensembl))[0];
-    $names{$ensembl} = {symbol=>$symbol,type=>$type};
+    $names{$ensembl} = {chr=>$chrom,symbol=>$symbol,type=>$type};
 }
 
 my @files = @ARGV;
@@ -32,8 +32,13 @@ foreach $file (@files) {
     while (my $line = <IN>) {
 	chomp($line);
 	my ($ensid,$gene,$chr,$strand,$start,$end,$cov,$fpkm,$tmp) = split(/\t/,$line);
-	my ($ens,$version) = split(/\./,$ensid);
-	$cts{$ens}{$sample} = $fpkm;
+	my $ens = $ensid;
+	$ens =~ s/\.\d+//;
+	if ($chr eq $names{$ens}{chr}) {
+	    $cts{$ens}{$sample} = $fpkm;
+	}else {
+	    warn "unable to map to genenames\n";
+	}
     }
     close IN;
 }
-- 
GitLab