Merge branch 'hotfix/v2.1.3'

cancerit · May 23, 2016 · 02fa689 · 02fa689
2 parents e606c12 + 613eadc
commit 02fa689
Show file tree

Hide file tree

Showing 6 changed files with 19 additions and 17 deletions.
diff --git a/perl/bin/ascatCnToVCF.pl b/perl/bin/ascatCnToVCF.pl
@@ -184,9 +184,6 @@ sub setup{
   PCAP::Cli::file_for_reading('sbw', $opts{'sbw'});
   PCAP::Cli::file_for_reading('r', $opts{'r'});
 
-  # required: direct input
-  pod2usage(-message  => "\nERROR: rs|reference-species must be defined.\n", -verbose => 1,  -output => \*STDERR) unless($opts{'rs'});
-
   pod2usage(-message  => "\nERROR: msq|sample-sequencing-protocol-mut must be defined.\n", -verbose => 1,  -output => \*STDERR) if(exists $opts{'msq'} && ! defined $opts{'msq'});
   pod2usage(-message  => "\nERROR: wsq|sample-sequencing-protocol-norm must be defined.\n", -verbose => 1,  -output => \*STDERR) if(exists $opts{'wsq'} && ! defined $opts{'wsq'});
 

diff --git a/perl/bin/utilities/ascatSnpPanelFromVcfs.pl b/perl/bin/utilities/ascatSnpPanelFromVcfs.pl
@@ -91,8 +91,6 @@
 my $result = evaluate_set($cluster, \%sample_dist);
 print $result if($result);
 
-warn Dumper(\%sample_dist);
-
 sub evaluate_set {
   my ($cluster, $sample_dist) = @_;
   my $retval;

diff --git a/perl/docs.tar.gz b/perl/docs.tar.gz
diff --git a/perl/lib/Sanger/CGP/Ascat.pm b/perl/lib/Sanger/CGP/Ascat.pm
@@ -26,7 +26,7 @@ use strict;
 use Const::Fast qw(const);
 use base 'Exporter';
 
-our $VERSION = '2.1.2';
+our $VERSION = '2.1.3';
 our @EXPORT = qw($VERSION);
 
 const my $LICENSE =>

diff --git a/perl/lib/Sanger/CGP/Ascat/Implement.pm b/perl/lib/Sanger/CGP/Ascat/Implement.pm
@@ -149,6 +149,8 @@ sub ascat {
     PCAP::Threaded::touch_success(File::Spec->catdir($tmp, 'progress'), 'merge_counts_wt', 0);
   }
 
+  my $core_chrs = snpLociChrs($options);
+
   my $command = "cd $ascat_out; "._which('Rscript');
 
   my $mod_path = dirname(abs_path($0)).'/../share';
@@ -166,6 +168,7 @@ sub ascat {
   $command .= ' '.$options->{'normal_name'};
   $command .= ' '.$normcountfile;
   $command .= ' '.$options->{'gender'};
+  $command .= ' '.$core_chrs;
   $command .= ' '.$rdata;
 
   if(defined($options->{'ploidy'}) && defined($options->{'purity'})){
@@ -245,13 +248,12 @@ sub finalise {
   $command .= " -msp $options->{platform} -wsp $options->{platform}" if(defined $options->{'platform'});
 
   my $vcf_gz = $new_vcf.'.gz';
-  my $bgzip = _which('bgzip');
-  $bgzip .= sprintf ' -c %s > %s', $new_vcf, $vcf_gz;
+  my $sort_gz = sprintf q{(grep '^#' %s ; grep -v '^#' %s | sort -k 1,1 -k 2,2n) | %s -c > %s}, $new_vcf, $new_vcf, _which('bgzip'), $vcf_gz;
 
   my $tabix = _which('tabix');
   $tabix .= sprintf ' -p vcf %s', $vcf_gz;
 
-  push @commands, $command, $bgzip, $tabix;
+  push @commands, $command, $sort_gz, $tabix;
 
   PCAP::Threaded::external_process_handler(File::Spec->catdir($tmp, 'logs'), \@commands, 0);
 

diff --git a/perl/share/ascat/runASCAT.R b/perl/share/ascat/runASCAT.R
@@ -35,18 +35,21 @@ if(length(args)==0){
 	normal_sample = args[6]
 	normal_count_file = args[7]
 	gender = args[8]
-  rdat_out = args[9]
-  purity = as.numeric(args[10])
-  ploidy = as.numeric(args[11])
-  refchrs = args[12]
+	chrCount = as.numeric(args[9])
+  rdat_out = args[10]
+  purity = as.numeric(args[11])
+  ploidy = as.numeric(args[12])
+  refchrs = args[13]
 
-  refCN = ifelse(args[13]=="NA",NA,as.numeric(args[13]))
+  refCN = ifelse(args[14]=="NA",NA,as.numeric(args[14]))
   if(is.na(refchrs)||refchrs=="NA") {
   	refchrs = NA
 	}
 
 }
 
+cat(chrCount,' : chr Count \n')
+
 ## checkpointing: if the RData file exists, only rerun the last step of ASCAT
 if(length(dir(pattern=rdat_out))==0) {
 
@@ -76,8 +79,9 @@ if(length(dir(pattern=rdat_out))==0) {
     ## This gives every SNP a name (to be able to do GC correction)
     SNPposWithNames = read.table(SNP_pos_with_names,sep="\t",header=T,row.names=1)
 
-    ctrans = 1:24
-    names(ctrans)=c(1:22,"X","Y")
+    ctrans = 1:chrCount
+    nonGenderChrs = chrCount - 2
+    names(ctrans)=c(1:nonGenderChrs,"X","Y")
     newnames = ctrans[as.vector(SNPposWithNames[,1])]*1000000000+SNPposWithNames[,2]
     newnamesSEQ = ctrans[as.vector(SNPpos[,1])]*1000000000+as.numeric(SNPpos[,2])
 
@@ -213,7 +217,8 @@ if(!is.null(ascat.output$nA)) {
   colnames(gCN) = c("Chromosome","Position","Log R", "segmented LogR", "BAF", "segmented BAF", "Copy number", "Minor allele", "Raw copy number")
   gCN[,1]=as.vector(ascat.bc$SNPpos[,1])
   gCN[,2]=ascat.bc$SNPpos[,2]
-  gCN[gCN[,1]=="X",1]=23
+  # X chr is the first one after the main, all includes X+Y
+  gCN[gCN[,1]=="X",1]=chrCount-1
   gCN[,3]=ascat.bc$Tumor_LogR[,1]
   gCN[,4]=ascat.bc$Tumor_LogR_segmented[,1]
   gCN[,5]=ascat.bc$Tumor_BAF[,1]