Changes in rejoin_vf; Fix unit tests

Ensembl · Dec 4, 2024 · df56c61 · df56c61
1 parent d3d655c
commit df56c61
Show file tree

Hide file tree

Showing 7 changed files with 41 additions and 9 deletions.
diff --git a/modules/Bio/EnsEMBL/VEP/InputBuffer.pm b/modules/Bio/EnsEMBL/VEP/InputBuffer.pm
@@ -663,7 +663,8 @@ sub split_variants {
           $first->{original_allele_string} = $original_vf->{allele_string};
           $first->{original_start}         = $original_vf->{start};
           $first->{original_end}           = $original_vf->{end};
-          $first->{minimised}              = 1
+          $first->{minimised}              = 1;
+          $first->{first}              = 1;
         }
 
         push @tmp, $new_vf;

diff --git a/modules/Bio/EnsEMBL/VEP/OutputFactory.pm b/modules/Bio/EnsEMBL/VEP/OutputFactory.pm
@@ -2194,7 +2194,8 @@ sub rejoin_variants_in_InputBuffer {
   foreach my $vf(@{$buffer->buffer}) {
 
     # reset original one
-    if(defined($vf->{original_allele_string})) {
+    # check $vf->{first} to get first $vf in split_variants
+    if(defined($vf->{first})) {
 
       # do consequence stuff
       $self->get_all_output_hashes_by_VariationFeature($vf);

diff --git a/t/InputBuffer.t b/t/InputBuffer.t
@@ -72,6 +72,7 @@ is_deeply($vfs->[0], bless( {
   'variation_name' => 'rs142513484',
   'map_weight' => 1,
   'allele_string' => 'C/T',
+  'nontrimmed_allele_string' => 'C/T',
   'end' => 25585733,
   'start' => 25585733,
   'seq_region_end' => 25585733,
@@ -90,6 +91,7 @@ is_deeply($vfs->[0], bless( {
   'variation_name' => 'rs148490508',
   'map_weight' => 1,
   'allele_string' => 'A/G',
+  'nontrimmed_allele_string' => 'A/G',
   'end' => 25592911,
   'start' => 25592911,
   'seq_region_end' => 25592911,
@@ -418,7 +420,9 @@ is_deeply($ib->buffer, [
     'chr' => '1',
     'minimised' => 1,
     'original_allele_string' => 'CAGAAGAAAG/TAGAAGAAAG/C',
+    'nontrimmed_allele_string' => 'CAGAAGAAAG/TAGAAGAAAG/C',
     'original_end' => 10,
+    'first' => 1,
     'end' => 1,
     'original_start' => 1,
     'strand' => 1,
@@ -439,7 +443,10 @@ is_deeply($ib->buffer, [
     'variation_name' => '.',
     'alt_allele' => '-',
     'map_weight' => 1,
+    'minimised' => 1,
     'allele_string' => 'AGAAGAAAG/-',
+    'original_allele_string' => 'CAGAAGAAAG/TAGAAGAAAG/C',
+    'nontrimmed_allele_string' => 'CAGAAGAAAG/TAGAAGAAAG/C',
     'start' => 2,
     'seq_region_start' => 2,
     'seq_region_end' => 10,
@@ -470,7 +477,10 @@ is_deeply(
     'strand' => 1,
     'variation_name' => '.',
     'map_weight' => 1,
+    'minimised' => 1,
     'allele_string' => 'CAG/TAG/T',
+    'original_allele_string' => 'CAG/TAG/T',
+    'nontrimmed_allele_string' => 'CAG/TAG/T',
     'end' => 3,
     'start' => 1,
     'seq_region_start' => 1,

diff --git a/t/OutputFactory.t b/t/OutputFactory.t
@@ -1678,7 +1678,9 @@ $ib = get_annotated_buffer({
 
 is(scalar @{$ib->buffer}, 2, 'minimal - expanded count');
 is($ib->buffer->[0]->allele_string, 'C/T', 'minimal - expanded first allele string');
-
+# print("Before rejoin\n");
+# use Data::Dumper;
+# print(Dumper($ib->buffer));
 $of->rejoin_variants_in_InputBuffer($ib);
 
 is(scalar @{$ib->buffer}, 1, 'minimal - rejoined count');

diff --git a/t/OutputFactory_JSON.t b/t/OutputFactory_JSON.t
@@ -532,7 +532,7 @@ SKIP: {
       'cdna_start' => 2347,
       'transcript_id' => 'NM_000484.3',
       'gene_id' => '351',
-      'uploaded_allele' => '-/A',
+      'uploaded_allele' => 'G/GA',
       'cds_start' => 2147,
       'protein_start' => 716,
       'refseq_match' => [

diff --git a/t/Parser_Region.t b/t/Parser_Region.t
@@ -127,7 +127,9 @@ is_deeply($vf, bless( {
   'strand' => '1',
   'variation_name' => '21:25587759-25587758:1/A',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => '-/A',
+  'original_allele_string' => '-/A',
   'end' => '25587758',
   'start' => '25587759',
   'seq_region_end' => '25587758',

diff --git a/t/Parser_VCF.t b/t/Parser_VCF.t
@@ -215,15 +215,17 @@ is_deeply($vf, bless( {
   'strand' => 1,
   'variation_name' => 'test',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => 'A/C/GG',
+  'nontrimmed_allele_string' => 'A/C/GG',
   'original_allele_string' => 'A/C/GG',
   'end' => 25587759,
   'start' => 25587759,
   'seq_region_end' => 25587759,
   'seq_region_start' => 25587759
 }, 'Bio::EnsEMBL::Variation::VariationFeature' ), 'mixed types - different first base');
 
-# mixed types - different first base
+# mixed types - same first base
 $vf = Bio::EnsEMBL::VEP::Parser::VCF->new({
   config => $cfg,
   file => $test_cfg->create_input_file([qw(21 25587759 test G GC,GT . . .)]),
@@ -235,8 +237,10 @@ is_deeply($vf, bless( {
   'strand' => 1,
   'variation_name' => 'test',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => '-/C/T',
-  'original_allele_string' => 'A/C/GG',
+  'original_allele_string' => 'G/GC/GT',
+  'nontrimmed_allele_string' => 'G/GC/GT',
   'end' => 25587759,
   'start' => 25587760,
   'seq_region_end' => 25587759,
@@ -322,8 +326,10 @@ is_deeply($vf, bless( {
   'strand' => 1,
   'variation_name' => 'test',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => 'G/C/<DEL:*>',
   'original_allele_string' => 'G/C/<DEL:*>',
+  'nontrimmed_allele_string' => 'G/C/<DEL:*>',
   'end' => 25587759,
   'start' => 25587759,
   'seq_region_end' => 25587759,
@@ -342,8 +348,10 @@ is_deeply($vf, bless( {
   'strand' => 1,
   'variation_name' => 'test',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => 'C/-/*',
   'original_allele_string' => 'GC/G/*',
+  'nontrimmed_allele_string' => 'GC/G/*',
   'end' => 25587760,
   'start' => 25587760,
   'seq_region_end' => 25587760,
@@ -362,8 +370,10 @@ is_deeply($vf, bless( {
   'strand' => 1,
   'variation_name' => 'test',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => '-/C/*',
   'original_allele_string' => 'G/GC/*',
+  'nontrimmed_allele_string' => 'G/GC/*',
   'end' => 25587759,
   'start' => 25587760,
   'seq_region_end' => 25587759,
@@ -382,6 +392,7 @@ is_deeply($vf, bless( {
   'chr' => '21',
   'minimised' => 1,
   'original_allele_string' => 'CAT/CCT',
+  'nontrimmed_allele_string' => 'CAT/CCT',
   'original_end' => 25587760,
   'end' => 25587759,
   'seq_region_end' => 25587759,
@@ -406,8 +417,10 @@ is_deeply($vf, bless( {
   'strand' => 1,
   'variation_name' => 'test',
   'map_weight' => 1,
+  'minimised' => 1,
   'allele_string' => 'C/T/CAA',
   'original_allele_string' => 'C/T/CAA',
+  'nontrimmed_allele_string' => 'C/T/CAA',
   'end' => 25587758,
   'start' => 25587758,
   'seq_region_end' => 25587758,
@@ -944,7 +957,8 @@ is_deeply($tandem_RUC, bless( {
     'end' => 25587769,
     'seq_region_start' => 25587760,
     'seq_region_end' => 25587769,
-    'map_weight' => 1
+    'map_weight' => 1,
+    'minimised' => 1
   },
   'Bio::EnsEMBL::Variation::VariationFeature' ) ,
   'VariationFeature - tandem repeat using RUC');
@@ -963,7 +977,8 @@ is_deeply($tandem, bless( {
     'end' => 25587769,
     'seq_region_start' => 25587760,
     'seq_region_end' => 25587769,
-    'map_weight' => 1
+    'map_weight' => 1,
+    'minimised' => 1
   },
   'Bio::EnsEMBL::Variation::VariationFeature' ) ,
   'VariationFeature - tandem repeat with missing sequence');
@@ -987,7 +1002,8 @@ is_deeply($tandem, bless( {
     'end' => 25587760,
     'seq_region_start' => 25587760,
     'seq_region_end' => 25587760,
-    'map_weight' => 1
+    'map_weight' => 1,
+    'minimised' => 1
   },
   'Bio::EnsEMBL::Variation::VariationFeature' ) ,
   'VariationFeature - tandem repeat with missing END and SVLEN');