Merge branch 'release/v1.1.0'

MANIFEST

@@ -29,6 +29,7 @@ docs/pod_html/Sanger/CGP/Grass/GenomeData/Transcript.html
 docs/pod_html/Sanger/CGP/Grass/VcfContigs.html
 docs/pod_html/Sanger/CGP/Grass/VcfConverter.html
 docs/reports_html/common.js
+docs/reports_html/cover.14
 docs/reports_html/cover.css
 docs/reports_html/coverage.html
 docs/reports_html/css.js

MYMETA.json

@@ -4,7 +4,7 @@
       "unknown"
    ],
    "dynamic_config" : 0,
-   "generated_by" : "ExtUtils::MakeMaker version 6.68, CPAN::Meta::Converter version 2.131560",
+   "generated_by" : "ExtUtils::MakeMaker version 6.68, CPAN::Meta::Converter version 2.142690",
    "license" : [
       "agpl_3"
    ],
@@ -45,5 +45,5 @@
       }
    },
    "release_status" : "stable",
-   "version" : "v1.0.1"
+   "version" : "v1.1.0"
 }

MYMETA.yml

@@ -3,28 +3,28 @@ abstract: unknown
 author:
   - unknown
 build_requires:
-  ExtUtils::MakeMaker: 0
+  ExtUtils::MakeMaker: '0'
 configure_requires:
-  ExtUtils::MakeMaker: 0
+  ExtUtils::MakeMaker: '0'
 dynamic_config: 0
-generated_by: 'ExtUtils::MakeMaker version 6.68, CPAN::Meta::Converter version 2.131560'
+generated_by: 'ExtUtils::MakeMaker version 6.68, CPAN::Meta::Converter version 2.142690'
 license: open_source
 meta-spec:
   url: http://module-build.sourceforge.net/META-spec-v1.4.html
-  version: 1.4
+  version: '1.4'
 name: Grass
 no_index:
   directory:
     - t
     - inc
 requires:
-  Attribute::Abstract: 1.02
-  Bio::DB::Sam: 1.39
-  Bio::Root::Version: 1.006923
-  Const::Fast: 0.014
-  Devel::Cover: 1.09
-  List::Util: 1.38
-  Pod::Coverage: 0.23
-  Sub::Exporter::Progressive: 0.001011
-  Try::Tiny: 0.19
-version: v1.0.1
+  Attribute::Abstract: '1.02'
+  Bio::DB::Sam: '1.39'
+  Bio::Root::Version: '1.006923'
+  Const::Fast: '0.014'
+  Devel::Cover: '1.09'
+  List::Util: '1.38'
+  Pod::Coverage: '0.23'
+  Sub::Exporter::Progressive: '0.001011'
+  Try::Tiny: '0.19'
+version: v1.1.0

lib/Sanger/CGP/Grass.pm

@@ -2,21 +2,21 @@ package Sanger::CGP::Grass;
 
 ##########LICENCE##########
 # Copyright (c) 2014 Genome Research Ltd.
-# 
+#
 # Author: Lucy Stebbings <cgpit@sanger.ac.uk>
-# 
+#
 # This file is part of grass.
-# 
+#
 # grass 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/>.
 ##########LICENCE##########
@@ -25,6 +25,6 @@ package Sanger::CGP::Grass;
 use strict;
 use Const::Fast qw(const);
 
-our $VERSION = '1.0.1';
+our $VERSION = '1.1.0';
 
 1;

lib/Sanger/CGP/Grass/FlankingBases.pm

@@ -82,7 +82,7 @@ sub new {
 
     if ($args{-infile})  { $self->infile($args{-infile}); }
     if ($args{-ref})     { $self->ref($args{-ref}); }
-    if ($args{-flip_strand}) { $self->{-flip_strand} = $args{-flip_strand}; }
+    if ($args{-flip_strand}) { $self->flip_strand($args{-flip_strand}); }
 
     return $self;
 }

lib/Sanger/CGP/Grass/VcfConverter.pm

@@ -77,7 +77,7 @@ sub new {
 
     if ($args{-infile})  { $self->infile($args{-infile}); }
     if ($args{-contigs}) { $self->{_contigs} = $args{-contigs}; }
-    if ($args{-flip_strand}) { $self->{-flip_strand} = $args{-flip_strand}; }
+    if ($args{-flip_strand}) { $self->flip_strand($args{-flip_strand}); }
 
     $self->{_format} = 'RC';
 
@@ -192,13 +192,14 @@ sub gen_header{
     {key => 'INFO', ID => 'RGN',       Number => 1, Type => 'String',   Description => 'Region where nucleotide variant (breakpoint) occurs in relation to a gene'},
     {key => 'INFO', ID => 'RGNNO',     Number => 1, Type => 'Integer',  Description => 'Number of intron/exon where nucleotide variant (breakpoint) occurs in relation to a gene'},
     {key => 'INFO', ID => 'RGNC',      Number => 1, Type => 'Integer',  Description => 'Count of total number of introns/exons in stated transcript'},
+    {key => 'INFO', ID => 'TSRDS',     Number => '.', Type => 'String',  Description => 'Reads from the tumour sample ('.$mt_sample->name.') that span to this rearrangement'},
+    {key => 'INFO', ID => 'NSRDS',     Number => '.', Type => 'String',  Description => 'Reads from the normal sample ('.$wt_sample->name.') that span to this rearrangement'},
     {key => 'INFO', ID => 'TRDS',      Number => '.', Type => 'String',  Description => 'Reads from the tumour sample ('.$mt_sample->name.') that contribute to this rearrangement'},
     {key => 'INFO', ID => 'NRDS',      Number => '.', Type => 'String',  Description => 'Reads from the normal sample ('.$wt_sample->name.') that contribute to this rearrangement'},
       ];
 
   # details info layout for the tumour and the normal column
   my $format = [
-#	{key => 'FORMAT', ID => 'GT', Number => 1, Type => 'String', Description => 'Genotype'},
     {key => 'FORMAT', ID => 'RC', Number => 1, Type => 'Integer', Description => 'Count of countributing reads'},
       ];
 
@@ -498,12 +499,17 @@ sub gen_record {
     $rec2 .= 'FL='.$firstlast2.';' if ($firstlast2);
   }
 
+  if($names) {
+    $rec1 .= 'TSRDS='.$names;
+    $rec2 .= 'TSRDS='.$names;
+  }
+
   # FORMAT FIELDS
   # in format put read counts for: normal, tumour
 
 	# FORMAT
-	$normal_count = q{} unless(defined $normal_count);
-	$tumour_count = q{} unless(defined $tumour_count);
+	$normal_count = q{0} unless(defined $normal_count);
+	$tumour_count = q{0} unless(defined $tumour_count);
 	$rec1 .= SEP.$self->{_format}.SEP.$normal_count.SEP.$tumour_count;
 	$rec2 .= SEP.$self->{_format}.SEP.$normal_count.SEP.$tumour_count;
 

t/grass.t

@@ -40,13 +40,25 @@ use FindBin qw($Bin);
 #my $genome_cache = '/lustre/scratch104/sanger/am3/vagrent/e74/Homo_sapiens.GRCh37.74.vagrent.cache.gz';
 my $genome_cache = "$Bin/../testData/vagrent.cache.gz";
 my $ref = "$Bin/../testData/genome.fa";
+if(exists $ENV{GRASS_GRCH37_FA}) {
+  $ref = $ENV{GRASS_GRCH37_FA};
+}
 
 my $script = $Bin.'/../bin/' . 'grass.pl';
 my $tmpdir = tempdir( CLEANUP => 1 );
-
-test_coord_input();
+note $tmpdir;
+
+SKIP: {
+  unless(-e $ref) {
+    my $message = "SKIPPING: Reference *.fa not found at '$ref', set ENV: GRASS_GRCH37_FA to enable these tests";
+    warn "$message\n";
+    skip $message, '3';
+  }
+  test_coord_input();
+  test_file_input_bedpe();
+}
 test_file_input();
-test_file_input_bedpe();
+
 
 #----------------------------------------------------------------------------------------#
 sub test_coord_input {
@@ -97,6 +109,8 @@ sub test_file_input_bedpe {
     my $testfile_out_vcf = "$tmpdir/testout_Brass_ann.vcf";
 
     ok(copy($infile, $testfile), 'setup files');
+
+    unless (-e $ref) { die "ERROR: ref file $ref does not exist. exiting\n"; }
     my $command = "$^X $script -genome_cache $genome_cache -file $testfile -ref $ref";
     note "$command\n";
     my ($out, $err, @result) = capture { system($command); };
@@ -116,14 +130,14 @@ sub test_file_input_bedpe {
 
     my $slurp_testfile_out = slurp_file($testfile_out);
     my $slurp_outfile = slurp_file($outfile);
-    is_deeply($slurp_testfile_out, $slurp_testfile_out, 'correct bedpe file created');
+    is_deeply($slurp_testfile_out, $slurp_outfile, 'correct bedpe file created');
 
     my $slurp_testfile_out_vcf = slurp_file($testfile_out_vcf);
     my $slurp_outfile_vcf = slurp_file($outfile_vcf);
 
     # path of reference file will differ so remove from comparison
-    splice(@{$slurp_testfile_out_vcf}, 3);
-    splice(@{$slurp_outfile_vcf}, 3);
+    splice(@{$slurp_testfile_out_vcf}, 3,1);
+    splice(@{$slurp_outfile_vcf}, 3,1);
 
     is_deeply($slurp_testfile_out_vcf, $slurp_outfile_vcf, 'correct vcf file created');
 }

testData/test_VcfConverterII_ann.vcf

@@ -1,6 +1,6 @@
 ##fileformat=VCFv4.1
 ##fileDate=20140512
-##source_20140512.1=VcfConverter.t_v1.0.1
+##source_20140512.1=VcfConverter.t_v1.1.0
 ##reference=/nfs/users/nfs_l/las/CGP_github/grass/t/../testData/genome.fa
 ##contig=<ID=1,assembly=GRC37,length=249250621,species=HUMAN>
 ##contig=<ID=2,assembly=GRC37,length=243199373,species=HUMAN>
@@ -54,10 +54,12 @@
 ##INFO=<ID=RGN,Number=1,Type=String,Description="Region where nucleotide variant (breakpoint) occurs in relation to a gene">
 ##INFO=<ID=RGNNO,Number=1,Type=Integer,Description="Number of intron/exon where nucleotide variant (breakpoint) occurs in relation to a gene">
 ##INFO=<ID=RGNC,Number=1,Type=Integer,Description="Count of total number of introns/exons in stated transcript">
+##INFO=<ID=TSRDS,Number=.,Type=String,Description="Reads from the tumour sample (PD1234a) that span to this rearrangement">
+##INFO=<ID=NSRDS,Number=.,Type=String,Description="Reads from the normal sample (PD1234b) that span to this rearrangement">
 ##INFO=<ID=TRDS,Number=.,Type=String,Description="Reads from the tumour sample (PD1234a) that contribute to this rearrangement">
 ##INFO=<ID=NRDS,Number=.,Type=String,Description="Reads from the normal sample (PD1234b) that contribute to this rearrangement">
 ##FORMAT=<ID=RC,Number=1,Type=Integer,Description="Count of countributing reads">
-##vcfProcessLog_20140512.1=<InputVCFSource=<VcfConverter.t>,InputVCFVer=<1.0.1>>
+##vcfProcessLog_20140512.1=<InputVCFSource=<VcfConverter.t>,InputVCFVer=<1.1.0>>
 ##SAMPLE=<ID=NORMAL,Description="Normal",Accession=45,Platform=HiSeq,Protocol=genomic,SampleName=PD1234b,Source=ID_SAMPLE_COSMIC,Study=12346>
 ##SAMPLE=<ID=TUMOUR,Description="Mutant",Accession=123,Platform=HiSeq,Protocol=genomic,SampleName=PD1234a,Source=ID_SAMPLE_COSMIC,Study=12345>
 #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NORMAL	TUMOUR