Source commit

CNAG-Biomedical-Informatics · Aug 7, 2024 · 79ccf7b · 79ccf7b
1 parent 264ef71
commit 79ccf7b
Show file tree

Hide file tree

Showing 6 changed files with 56 additions and 12 deletions.
diff --git a/lib/Pheno/Ranker.pm b/lib/Pheno/Ranker.pm
@@ -465,6 +465,9 @@ sub run {
 "Sorry, <$target_file> does not contain primary_key <$primary_key>. Are you using the right config file?\n"
           unless exists $tar_data->{$primary_key};
 
+        # Re-structure interpretations if PXF
+        restructure_pxf_interpretations($tar_data, $self);
+
         # We store {primary_key} as a variable as it might be deleted from $tar_data (--exclude-terms id)
         my $tar_data_id = $tar_data->{$primary_key};
 
@@ -479,9 +482,6 @@ sub run {
             )
         };
 
-        # Re-structure interpretations if PXF
-        restructure_pxf_interpretations($tar_data, $self);
-
         # *** IMPORTANT ***
         # The target binary is created from matches to $glob_hash
         # Thus, it does not include variables ONLY present in TARGET

diff --git a/lib/Pheno/Ranker/IO.pm b/lib/Pheno/Ranker/IO.pm
@@ -11,6 +11,7 @@ use List::Util qw(any);
 use Hash::Util qw(lock_hash);
 use YAML::XS qw(LoadFile DumpFile);
 use JSON::XS;
+#use Data::Dumper;
 
 #use Sort::Naturally qw(nsort);
 use Exporter 'import';
@@ -350,9 +351,14 @@ sub restructure_pxf_interpretations {
     # Premature return if the format is not 'PXF'
     return unless $self->{format} eq 'PXF';
 
+    # Premature return if "interpretations" is excluded
+    return if (grep { $_ eq 'interpretations' } @{ $self->{exclude_terms} });
+
+    say "Restructuring <interpretations> in PXFs..." if defined $self->{verbose};
+
     # Function to restructure individual interpretation
     my $restructure_interpretation = sub {
-        my $interpretation   = shift;
+        my $interpretation     = shift;
         my $disease_id         = $interpretation->{diagnosis}{disease}{id};
         my $new_interpretation = {
             progressStatus         => $interpretation->{progressStatus},
@@ -366,17 +372,35 @@ sub restructure_pxf_interpretations {
             my $interpretation_data;
 
             if ( exists $genomic_interpretation->{variantInterpretation} ) {
-                $gene_id = $genomic_interpretation->{variantInterpretation}{variationDescriptor}{geneContext}{valueId};
-                $interpretation_data =
+                my $variant_interpretation =
                   $genomic_interpretation->{variantInterpretation};
+
+                # Check if geneContext with valueId exists
+                if (
+                    exists $variant_interpretation->{variationDescriptor}
+                    {geneContext}{valueId} )
+                {
+                    $gene_id = $variant_interpretation->{variationDescriptor}
+                      {geneContext}{valueId};
+                }
+
+                # Check if id within variationDescriptor exists as an alternative
+                elsif (
+                    exists $variant_interpretation->{variationDescriptor}{id} )
+                {
+                    $gene_id =
+                      $variant_interpretation->{variationDescriptor}{id};
+                }
+
+                $interpretation_data = $variant_interpretation;
             }
             elsif ( exists $genomic_interpretation->{geneDescriptor} ) {
                 $gene_id = $genomic_interpretation->{geneDescriptor}{valueId};
                 $interpretation_data =
                   $genomic_interpretation->{geneDescriptor};
             }
 
-            $new_interpretation->{genomicInterpretations}->{$gene_id} = {
+            $new_interpretation->{genomicInterpretations}{$gene_id} = {
                 interpretationStatus =>
                   $genomic_interpretation->{interpretationStatus},
                 (
@@ -398,7 +422,8 @@ sub restructure_pxf_interpretations {
         my $new_data = {};
 
         foreach my $interpretation ( @{ $data->{interpretations} } ) {
-            my ( $disease_id, $new_interpretation ) = $restructure_interpretation->($interpretation);
+            my ( $disease_id, $new_interpretation ) =
+              $restructure_interpretation->($interpretation);
             $new_data->{$disease_id} = $new_interpretation;
         }
 

diff --git a/t/cli.t b/t/cli.t
@@ -342,7 +342,7 @@ SKIP: {
     my $input_file = catfile( 't', 'interpretations_pxf.json' );
 
     # The reference file to compare the output with
-    my $reference_file = catfile( 't', 'matrix_interpretations_pxf.txt' );
+    my $reference_file = catfile( 't', 'matrix_ref_interpretations_pxf.txt' );
 
     # The generated output file
     my ( undef, $tmp_file ) =

diff --git a/t/interpretations_pxf.json b/t/interpretations_pxf.json
@@ -53,6 +53,25 @@
                 "valueId": "HGNC:12345",
                 "symbol": "GENE1"
               }
+            },
+            {
+              "subjectOrBiosampleId": "Subject_2",
+              "interpretationStatus": "CAUSATIVE",
+              "variantInterpretation": {
+                "variationDescriptor": {
+                  "id": "var_vUsarphuwufsiYwRzWVTDjIRF",
+                  "label": "telomeric 11q deletion",
+                  "moleculeContext": "genomic",
+                  "structuralType": {
+                    "id": "SO:1000029",
+                    "label": "chromosomal_deletion"
+                  },
+                  "allelicState": {
+                    "id": "GENO:0000135",
+                    "label": "heterozygous"
+                  }
+                }
+              }
             }
           ]
         }

diff --git a/t/matrix_interpretations_pxf.txt b/t/matrix_interpretations_pxf.txt
diff --git a/t/matrix_ref_interpretations_pxf.txt b/t/matrix_ref_interpretations_pxf.txt
@@ -0,0 +1,3 @@
+	Sample_1	Sample_2
+Sample_1	0	15
+Sample_2	15	0