Merge branch 'release/1.5.0'

.gitignore

@@ -7,3 +7,5 @@
 /setup.log
 /perl/perltidy.LOG
 /perl/bin/cpanm
+/perl/MYMETA.json
+/perl/MYMETA.yml

README.md

@@ -1,46 +1,15 @@
-LICENCE
-=======
-Copyright (c) 2014 Genome Research Ltd.
-
-Author: Cancer Genome Project [email protected]
-
-This file is part of cgpBattenberg.
-
-cgpBattenberg is free software: you can redistribute it and/or modify it under
-the terms of the GNU Affero General Public License as published by the Free
-Software Foundation; either version 3 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 Affero General Public License for more
-details.
-
-You should have received a copy of the GNU Affero General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-1. The usage of a range of years within a copyright statement contained within
-this distribution should be interpreted as being equivalent to a list of years
-including the first and last year specified and all consecutive years between
-them. For example, a copyright statement that reads 'Copyright (c) 2005, 2007-
-2009, 2011-2012' should be interpreted as being identical to a statement that
-reads 'Copyright (c) 2005, 2007, 2008, 2009, 2011, 2012' and a copyright
-statement that reads "Copyright (c) 2005-2012' should be interpreted as being
-identical to a statement that reads 'Copyright (c) 2005, 2006, 2007, 2008,
-2009, 2010, 2011, 2012'."
-
-
 cgpBattenberg
 =============
 
 An installation helper, perl wrapper and the R program Battenberg which detects subclonality and copy number in matched NGS data.
 
 ## Installation
 
-Please install the following before attempting to run ``setup.sh <install_to_folder>``
+Please install the following before attempting to run ``setup.sh <install_to_folder> [X/lib/perl:Y/lib/perl]``
 
-1. [PCAP-core](https://github.com/ICGC-TCGA-PanCancer/PCAP-core/releases)
-2. [alleleCount](https://github.com/cancerit/alleleCount/releases)
+1. [PCAP-core v2.1.3+](https://github.com/ICGC-TCGA-PanCancer/PCAP-core/releases)
+2. [alleleCount v3.0.1+](https://github.com/cancerit/alleleCount/releases)
+3. [cgpVcf v2.0.1+](https://github.com/cancerit/cgpVcf/releases)
 
 All of the items listed here use the same install method.
 
@@ -69,3 +38,35 @@ For the most up to date usage instructions for the wrapper code please see the c
 
 
 
+----
+
+LICENCE
+=======
+Copyright (c) 2014-2016 Genome Research Ltd.
+
+Author: Cancer Genome Project [email protected]
+
+This file is part of cgpBattenberg.
+
+cgpBattenberg is free software: you can redistribute it and/or modify it under
+the terms of the GNU Affero General Public License as published by the Free
+Software Foundation; either version 3 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 Affero General Public License for more
+details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+1. The usage of a range of years within a copyright statement contained within
+this distribution should be interpreted as being equivalent to a list of years
+including the first and last year specified and all consecutive years between
+them. For example, a copyright statement that reads 'Copyright (c) 2005, 2007-
+2009, 2011-2012' should be interpreted as being identical to a statement that
+reads 'Copyright (c) 2005, 2007, 2008, 2009, 2011, 2012' and a copyright
+statement that reads "Copyright (c) 2005-2012' should be interpreted as being
+identical to a statement that reads 'Copyright (c) 2005, 2006, 2007, 2008,
+2009, 2010, 2011, 2012'."

perl/MANIFEST

@@ -26,5 +26,6 @@ share/battenberg/RunBAFLogR.R
 share/battenberg/RunGetHaplotypedBAFs.R
 share/battenberg/RunImpute.R
 share/battenberg/segmentBAFphased.R
+share/gender/GRCh37d5_Y.loci
 t/1_pm_compile.t
 t/2_pl_compile.t

perl/Makefile.PL

@@ -37,6 +37,7 @@ WriteMakefile(
   PREREQ_PM     => {
                      'Const::Fast' => 0.014,
                      'Try::Tiny' => 0.22,
+                     'Bio::DB::HTS' => 2.0,
                    }
 );
 

perl/bin/battenberg.pl

@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 
 ##########LICENCE##########
-# Copyright (c) 2014,2015 Genome Research Ltd.
+# Copyright (c) 2014-2016 Genome Research Ltd.
 #
 # Author: Cancer Genome Project [email protected]
 #
@@ -45,6 +45,7 @@
 															segmentphased fitcn subclones finalise );
 
 const my @VALID_PROTOCOLS => qw( WGS WXS RNA );
+const my @VALID_GENDERS => qw(XX XY L);
 
 const my $DEFAULT_ALLELE_COUNT_MBQ => 20;
 const my $DEFAULT_PLATFORM_GAMMA=>1;
@@ -135,7 +136,6 @@ sub setup {
 					'p|process=s' => \$opts{'process'},
 					'u|thousand-genomes-loc=s' => \$opts{'1kgenloc'},
 					'r|reference=s' => \$opts{'reference'},
-					's|is-male' => \$opts{'is_male'},
 					'e|impute-info=s' => \$opts{'impute_info'},
 					'c|prob-loci=s' => \$opts{'prob_loci'},
 					'g|logs=s' => \$opts{'lgs'},
@@ -157,11 +157,13 @@ sub setup {
           'pr|protocol=s' => \$opts{'protocol'},
           'pl|platform=s' => \$opts{'platform'},
           'a|allele-counts=s' => \$opts{'allele-counts'},
+          'ge|gender=s' => \$opts{'gender'},
+          'gl|genderloci=s' => \$opts{'genderloci'},
           'j|jobs' => \$opts{'jobs'},
 		) or pod2usage(2);
 
-	pod2usage(-message => Sanger::CGP::Battenberg::license, -verbose => 0) if(defined $opts{'h'});
-  pod2usage(-message => Sanger::CGP::Battenberg::license, -verbose => 2) if(defined $opts{'m'});
+	pod2usage(-verbose => 0, -exitval => 0) if(defined $opts{'h'});
+  pod2usage(-verbose => 2, -exitval => 0) if(defined $opts{'m'});
 
   # then check for no args:
   my $defined;
@@ -205,6 +207,16 @@ sub setup {
 	delete $opts{'process'} unless(defined $opts{'process'});
   delete $opts{'index'} unless(defined $opts{'index'});
 
+  if(defined $opts{'gender'}){
+    pod2usage(-message => 'unknown gender value: '.$opts{'gender'}, -verbose => 1) unless(first {$_ eq $opts{'gender'}} @VALID_GENDERS);
+    if($opts{'gender'} eq 'L') {
+      die "ERROR: Gender of XY/XX must be supplied when 'allele-counts' defined\n" if(defined $opts{'allele-counts'});
+      $opts{'gender'} = Sanger::CGP::Battenberg::Implement::determine_gender(\%opts);
+    }
+  } else {
+    pod2usage(-message => 'gender not set', -verbose => 1);
+  }
+
   if(exists $opts{'protocol'} && defined $opts{'protocol'}) {
     my $bad_prot = 1;
 		$bad_prot = 0 if(first { $_ eq $opts{'protocol'} } @VALID_PROTOCOLS);
@@ -269,7 +281,7 @@ sub setup {
 	make_path($logs) unless(-d $logs);
 	$opts{'logs'} = $logs;
 
-	if(exists($opts{'is_male'}) && defined($opts{'is_male'})){
+	if($opts{'gender'} eq 'XY'){
 		$opts{'is_male'} = 'TRUE';
 	}else{
 		$opts{'is_male'} = 'FALSE';
@@ -291,6 +303,7 @@ sub setup {
 
 	$opts{'protocol'} = $DEFAULT_PROTOCOL if(!exists($opts{'protocol'}) || !defined($opts{'protocol'}));
 	$opts{'platform'} = $DEFAULT_PLATFORM if(!exists($opts{'platform'}) || !defined($opts{'platform'}));
+
 	return \%opts;
 }
 
@@ -312,7 +325,7 @@ =head1 SYNOPSIS
                                  - when '-a' defined sample name
     -normbam               -nb  Path to normal bam file
                                  - when '-a' defined sample name
-    -is-male               -s   Flag, if the sample is male
+    -gender                -ge  Gender, XX, XY or L (see -gl)
     -impute-info           -e   Location of the impute info file
     -thousand-genomes-loc  -u   Location of the directory containing 1k genomes data
     -ignore-contigs-file   -ig  File containing contigs to ignore
@@ -336,6 +349,8 @@ =head1 SYNOPSIS
     -assembly              -ra  Reference assembly []
     -protocol              -pr  Sequencing protocol [WGS]
     -platform              -pl  Sequencing platfrom [ILLUMINA]
+    -genderloci            -gl  List of gender loci, required when '-ge L' [share/gender/GRCh37d5_Y.loci]
+                                - these are loci that will not present at all in a female sample
 
    Optional system related parameters:
     -threads           -t   Number of threads allowed on this machine (default 1)

perl/bin/battenberg_CN_to_VCF.pl

@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 
 ##########LICENCE##########
-# Copyright (c) 2014 Genome Research Ltd.
+# Copyright (c) 2014-2016 Genome Research Ltd.
 #
 # Author: David Jones <[email protected]>
 #
@@ -34,7 +34,7 @@ BEGIN
 use Getopt::Long;
 use Pod::Usage qw(pod2usage);
 
-use Bio::DB::Sam;
+use Bio::DB::HTS;
 use Try::Tiny;
 use PCAP::Cli;
 
@@ -69,6 +69,7 @@ BEGIN
   my $record_converter = new Sanger::CGP::Vcf::VCFCNConverter(
     -contigs => [values %$contigs]
   );
+  $record_converter->extended_cn(1);
 
   my ($input_loc,$output_loc,$IN_FH,$OUT_FH);
   try{
@@ -105,12 +106,19 @@ BEGIN
 
 
     #Iterate through input and create a record for each.
-    my $fai = Bio::DB::Sam::Fai->load($reference);
+    my $fai = Bio::DB::HTS::Fai->load($reference);
     while(<$IN_FH>){
       my $line = $_;
       chomp($line);
       next if($line =~ m/^\s+chr/);
-      my ($seg_no,$chr,$start,$end,$blank1,$blank2,$blank3,$blank4,$mt_cn_tot,$mt_cn_min,undef) = split('\s+',$line);
+      my ($seg_no, $chr, $start, $end, $mt_cn_tot, $mt_cn_min, $mt_frac, $mt_cn_tot_sec, $mt_cn_min_sec, $mt_frac_sec) = (split('\s+',$line))[0,1,2,3,8,9,10,11,12,13];
+
+      my $extended = {  'mt_fcf' => $mt_frac eq 'NA' ? '.' : $mt_frac,
+                        'mt_tcs' => $mt_cn_tot_sec eq 'NA' ? '.' : $mt_cn_tot_sec,
+                        'mt_mcs' => $mt_cn_min_sec eq 'NA' ? '.' : $mt_cn_min_sec,
+                        'mt_fcs' => $mt_frac_sec eq 'NA' ? '.' : $mt_frac_sec,
+                      };
+
       my $wt_cn_tot = 2;
       my $wt_cn_min = 1;
       $start--; # all symbolic ALTs require preceeding base padding
@@ -125,7 +133,7 @@ BEGIN
                                                                       && defined($mt_cn_min));
 
       my $start_allele = $fai->fetch("$chr:$start-$start");
-      print $OUT_FH $record_converter->generate_record($chr,$start,$end,$start_allele,$wt_cn_tot,$wt_cn_min,$mt_cn_tot,$mt_cn_min);
+      print $OUT_FH $record_converter->generate_record($chr,$start,$end,$start_allele,$wt_cn_tot,$wt_cn_min,$mt_cn_tot,$mt_cn_min, $extended);
     }
 
   }catch{
@@ -172,7 +180,7 @@ sub parse_samples {
     $param_mod = 'w';
   }
   if(defined $opts->{'sb'.$param_mod}) {
-    $sam = Bio::DB::Sam->new(-bam => $opts->{'sb'.$param_mod}, -fasta => $reference);
+    $sam = Bio::DB::HTS->new(-bam => $opts->{'sb'.$param_mod}, -fasta => $reference);
     $samp_ref = Sanger::CGP::Vcf::BamUtil->parse_samples($sam->header->text,
                                                           $opts->{$param_mod.'ss'},
                                                           $opts->{$param_mod.'sq'},
@@ -249,7 +257,6 @@ sub setup{
   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'});