Fix ref matching for long indels

mskcc · Sep 29, 2016 · 735c1f7 · 735c1f7
1 parent 8560b97
commit 735c1f7
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/maf2vcf.pl b/maf2vcf.pl
@@ -101,7 +101,9 @@
 push( @regions_split, [ splice( @regions, 0, 100000 ) ] ) while @regions;
 map{ my $loci = join( " ", @{$_} ); $lines .= `$samtools faidx $ref_fasta $loci` } @regions_split;
 foreach my $line ( grep( length, split( ">", $lines ))) {
-    my ( $locus, $bps ) = split( "\n", $line );
+    # Carefully split this FASTA entry, properly chomping newlines for long indels
+    my ( $locus, $bps ) = split( "\n", $line, 2 );
+    $bps =~ s/\r|\n//g;
     if( $bps ){
         $bps = uc( $bps );
         $flanking_bps{$locus} = $bps;

diff --git a/vcf2maf.pl b/vcf2maf.pl
@@ -248,7 +248,9 @@ sub GetBiotypePriority {
 push( @regions_split, [ splice( @regions, 0, 100000 ) ] ) while @regions;
 map{ my $loci = join( " ", @{$_} ); $lines .= `$samtools faidx $ref_fasta $loci` } @regions_split;
 foreach my $line ( grep( length, split( ">", $lines ))) {
-    my ( $locus, $bps ) = split( "\n", $line );
+    # Carefully split this FASTA entry, properly chomping newlines for long indels
+    my ( $locus, $bps ) = split( "\n", $line, 2 );
+    $bps =~ s/\r|\n//g;
     if( $bps ){
         $bps = uc( $bps );
         $flanking_bps{$locus} = $bps;