BAM_EDIT field missing from VCF output

aparton · Nov 23, 2017 · d1204cc · d1204cc
1 parent 0cbb384
commit d1204cc
Show file tree

Hide file tree

Showing 7 changed files with 12 additions and 2 deletions.
diff --git a/modules/Bio/EnsEMBL/VEP/CacheDir.pm b/modules/Bio/EnsEMBL/VEP/CacheDir.pm
@@ -410,6 +410,7 @@ sub info {
     if($info->{bam} && !$self->param('use_given_ref')) {
       $self->status_msg("INFO: BAM-edited cache detected, enabling --use_transcript_ref; use --use_given_ref to override this\n");
       $self->param('use_transcript_ref', 1);
+      $self->param('bam_edited', 1);
     }
 
     ## NOT CURRENTLY BEING USED, COMMENTED OUT AS NO UNIT TEST

diff --git a/modules/Bio/EnsEMBL/VEP/Config.pm b/modules/Bio/EnsEMBL/VEP/Config.pm
@@ -356,6 +356,7 @@ our @OPTION_SETS = (
     flags => ['bam'],
     set   => {
       use_transcript_ref => 1,
+      bam_edited => 1,
     }
   },
 

diff --git a/modules/Bio/EnsEMBL/VEP/Constants.pm b/modules/Bio/EnsEMBL/VEP/Constants.pm
@@ -87,7 +87,7 @@ our @FLAG_FIELDS = (
   { flag => 'refseq',          fields => ['REFSEQ_MATCH'] },
   { flag => 'merged',          fields => ['REFSEQ_MATCH', 'SOURCE'] },
   { flag => 'use_transcript_ref', fields => ['GIVEN_REF', 'USED_REF']},
-  { flag => 'bam',             fields => ['BAM_EDIT']},
+  { flag => 'bam_edited',      fields => ['BAM_EDIT']},
   { flag => 'custom',          fields => ['SOURCE'] },
   { flag => 'gene_phenotype',  fields => ['GENE_PHENO'] },
   { flag => 'nearest',         fields => ['NEAREST'] },

diff --git a/t/OutputFactory.t b/t/OutputFactory.t
@@ -1008,14 +1008,14 @@ $ib = get_annotated_buffer({
   species => 'homo_sapiens',
   dir => $test_cfg->{cache_root_dir},
   refseq => 1,
+  fasta => $test_cfg->{fasta},
 });
 
 $vfoa = $of->get_all_VariationFeatureOverlapAlleles($ib->buffer->[0])->[0];
 
 is_deeply(
   $of->BaseTranscriptVariationAllele_to_output_hash($vfoa)->{REFSEQ_MATCH},
   [
-    'rseq_ens_match_cds',
     'rseq_mrna_nonmatch',
     'rseq_cds_mismatch'
   ],

diff --git a/t/OutputFactory_VCF.t b/t/OutputFactory_VCF.t
@@ -70,6 +70,13 @@ is_deeply(
   'headers - plugin'
 );
 
+$headers = get_runner({refseq => 1, fasta => $test_cfg->{fasta}, quiet => 1, input_file => $test_cfg->{test_vcf}, vcf => 1})->get_OutputFactory->headers;
+is(
+  $headers->[-2],
+  '##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence annotations from Ensembl VEP. Format: Allele|Consequence|IMPACT|SYMBOL|Gene|Feature_type|Feature|BIOTYPE|EXON|INTRON|HGVSc|HGVSp|cDNA_position|CDS_position|Protein_position|Amino_acids|Codons|Existing_variation|DISTANCE|STRAND|FLAGS|SYMBOL_SOURCE|HGNC_ID|REFSEQ_MATCH|GIVEN_REF|USED_REF|BAM_EDIT">',
+  'headers - BAM_EDIT'
+);
+
 is_deeply(
   $of->fields,
   [

diff --git a/t/testdata/cache/homo_sapiens_refseq/84_GRCh38/21/25000001-26000000.gz b/t/testdata/cache/homo_sapiens_refseq/84_GRCh38/21/25000001-26000000.gz
diff --git a/t/testdata/cache/homo_sapiens_refseq/84_GRCh38/info.txt b/t/testdata/cache/homo_sapiens_refseq/84_GRCh38/info.txt
@@ -7,6 +7,7 @@ host	ens-variation3
 variation_cols	chr,variation_name,failed,somatic,start,end,allele_string,strand,minor_allele,minor_allele_freq,clin_sig,phenotype_or_disease,pubmed,AFR,AMR,EAS,EUR,SAS,AA,EA,ExAC,ExAC_AFR,ExAC_AMR,ExAC_Adj,ExAC_EAS,ExAC_FIN,ExAC_NFE,ExAC_OTH,ExAC_SAS
 port	3306
 build	all
+bam	interim_GRCh38.p10_knownrefseq_alignments_2017-01-13.bam
 polyphen	b
 regulatory	1
 assembly	GRCh38