Merge pull request #2054 from Clinical-Genomics/release/12.0.1

jemten · web-flow · commit ef074abfeb2b · 2023-10-09T10:30:21.000+02:00
Release/12.0.1
diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS
@@ -2,4 +2,4 @@
 # the repo. Unless a later match takes precedence,
 # @global-owner1 and @global-owner2 will be requested for
 # review when someone opens a pull request.
-*   @henrikstranneheim @jemten @ramprasadn
+* @henrikstranneheim @Clinical-Genomics/rare-disease
diff --git a/643594-miptest_metrics_deliverables.yaml b/643594-miptest_metrics_deliverables.yaml
@@ -0,0 +1,3 @@
+---
+metrics: []
+
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,12 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
+## [12.0.1]
+
+- Adds loqudb and gnomad frequencies to vcf2cytosure filtering
+- Store PCT_PF_READS_IMPROPER_PAIRS in qc file
+- Evaluate and fail analysis where PCT_PF_READS_IMPROPER_PAIRS is above 5 %
+
 ## [12.0.0]
 
 - Set overlap requirement for merging two SVs to 0.8, down from the 0.95 default
diff --git a/definitions/rd_dna_panel_parameters.yaml b/definitions/rd_dna_panel_parameters.yaml
@@ -1183,7 +1183,7 @@ qccollect_eval_metric_file:
   associated_recipe:
     - qccollect_ar
   data_type: SCALAR
-  default: qc_eval_metric_-v1.3-.yaml
+  default: qc_eval_metric_-v1.4-.yaml
   exists_check: file
   is_reference: 1
   reference: reference_dir
diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml
@@ -1057,7 +1057,7 @@ vcf2cytosure_exclude_filter:
   associated_recipe:
     - vcf2cytosure_ar
   data_type: SCALAR
-  default: "'clingen_ngiAF > 0.1 || swegenAF > 0.05 || clinical_genomics_mipAF > 0.05 || decipherAF > 0.1'"
+  default: "'clingen_ngiAF > 0.1 || swegenAF > 0.05 || clinical_genomics_mipAF > 0.05 || decipherAF > 0.1 || clinical_genomics_loqusFrq > 0.05 || gnomad_svAF > 0.05'"
   type: recipe_argument
 vcf2cytosure_freq:
   associated_recipe:
@@ -1069,7 +1069,7 @@ vcf2cytosure_freq_tag:
   associated_recipe:
     - vcf2cytosure_ar
   data_type: SCALAR
-  default: FRQ
+  default: clinical_genomics_loqusFrq
   type: recipe_argument
 vcf2cytosure_maxbnd:
   associated_recipe:
@@ -2309,7 +2309,7 @@ qccollect_eval_metric_file:
   associated_recipe:
     - qccollect_ar
   data_type: SCALAR
-  default: qc_eval_metric_-v1.3-.yaml
+  default: qc_eval_metric_-v1.4-.yaml
   exists_check: file
   is_reference: 1
   reference: reference_dir
diff --git a/definitions/rd_rna_parameters.yaml b/definitions/rd_rna_parameters.yaml
@@ -1095,7 +1095,7 @@ qccollect_eval_metric_file:
   associated_recipe:
     - qccollect_ar
   data_type: SCALAR
-  default: qc_eval_metric_-v1.3-.yaml
+  default: qc_eval_metric_-v1.4-.yaml
   exists_check: file
   is_reference: 1
   reference: reference_dir
diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm
@@ -82,7 +82,7 @@ Readonly our %ANALYSIS => (
 );
 
 ## Set MIP version
-Readonly our $MIP_VERSION => q{12.0.0};
+Readonly our $MIP_VERSION => q{12.0.1};
 
 ## Cli
 Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160;
diff --git a/lib/MIP/Main/Qccollect.pm b/lib/MIP/Main/Qccollect.pm
@@ -555,7 +555,7 @@ sub parse_limit_qc_output {
 
     return if not $limit_qc_output;
 
-    Readonly my @SKIP_QC_METRICS => qw{ collectmultiplemetrics variantevalall variantevalexome };
+    Readonly my @SKIP_QC_METRICS => qw{ variantevalall variantevalexome };
 
     foreach my $delete_metric_key (@SKIP_QC_METRICS) {
 
diff --git a/lib/MIP/Qccollect.pm b/lib/MIP/Qccollect.pm
@@ -455,7 +455,7 @@ sub define_evaluate_metric {
 
 sub evaluate_analysis {
 
-## Function  : Read in aevaluate metrics and evaluate on sample and case level
+## Function  : Read in evaluation metrics and evaluate on sample and case level
 ## Returns   :
 ## Arguments : eval_metric_file  => File with evaluation metrics
 ##           : qc_data_href      => QC data {REF}
@@ -896,7 +896,6 @@ sub parse_sample_qc_metric {
                       $evaluate_metric_href->{$sample_id}{$recipe_name}{$metric},
                 }
             );
-            next METRIC;
         }
     }
     return 1;
diff --git a/lib/MIP/Recipes/Install/Mip_scripts.pm b/lib/MIP/Recipes/Install/Mip_scripts.pm
@@ -88,7 +88,7 @@ sub install_mip_scripts {
               mip_rd_dna_vcf_rerun_config.yaml
               mip_rd_rna_config.yaml
               program_test_cmds.yaml
-              qc_eval_metric_-v1.3-.yaml
+              qc_eval_metric_-v1.4-.yaml
               qc_regexp_-v1.26-.yaml
               rank_model_-v1.34-.ini
               svrank_model_-v1.9-.ini
diff --git a/lib/MIP/Store.pm b/lib/MIP/Store.pm
@@ -149,6 +149,10 @@ sub define_qc_metrics_to_store {
             analysis_mode => q{sample},
             recipe_name   => q{collecthsmetrics},
         },
+        PCT_PF_READS_IMPROPER_PAIRS => {
+            analysis_mode => q{sample},
+            recipe_name => q{collectmultiplemetrics},
+        },
         PCT_TARGET_BASES_10X => {
             analysis_mode => q{sample},
             recipe_name   => q{collecthsmetrics},
diff --git a/t/data/references/qc_eval_metric_-v1.4-.yaml b/t/data/references/qc_eval_metric_-v1.4-.yaml
@@ -28,6 +28,8 @@ wgs:
   collectmultiplemetrics:
     PCT_PF_READS_ALIGNED:
       lt: 0.95
+    PCT_PF_READS_IMPROPER_PAIRS:
+      gt: 0.05
     PCT_ADAPTER:
       gt: 0.0005
   markduplicates:
diff --git a/t/define_evaluate_metric.t b/t/define_evaluate_metric.t
@@ -47,8 +47,9 @@ diag(   q{Test define_evaluate_metric from Qccollect.pm}
       . $SPACE
       . $EXECUTABLE_NAME );
 
-Readonly my $PCT_ADAPTER          => 0.0005;
-Readonly my $PCT_PF_READS_ALIGNED => 0.95;
+Readonly my $PCT_ADAPTER                 => 0.0005;
+Readonly my $PCT_PF_READS_ALIGNED        => 0.95;
+Readonly my $PCT_PF_READS_IMPROPER_PAIRS => 0.05;
 
 my $log = test_log( { no_screen => 1, } );
 
@@ -59,7 +60,7 @@ my %sample_info = test_mip_hashes(
 );
 
 ## Given a file with evaluation metrics
-my $eval_metric_file = catfile( dirname($Bin), qw{ t data references qc_eval_metric_-v1.3-.yaml} );
+my $eval_metric_file = catfile( dirname($Bin), qw{ t data references qc_eval_metric_-v1.4-.yaml} );
 
 ## When defining the evaluation metrics based on the analysis
 my %evaluate_metric = define_evaluate_metric(
@@ -83,6 +84,9 @@ my %expected = (
             PCT_PF_READS_ALIGNED => {
                 lt => $PCT_PF_READS_ALIGNED,
             },
+            PCT_PF_READS_IMPROPER_PAIRS => {
+                gt => $PCT_PF_READS_IMPROPER_PAIRS,
+            },
         },
     },
     ADM1059A2 => {
@@ -98,6 +102,9 @@ my %expected = (
             PCT_PF_READS_ALIGNED => {
                 lt => $PCT_PF_READS_ALIGNED,
             },
+            PCT_PF_READS_IMPROPER_PAIRS => {
+                gt => $PCT_PF_READS_IMPROPER_PAIRS,
+            },
         },
     },
     ADM1059A3 => {
diff --git a/t/evaluate_analysis.t b/t/evaluate_analysis.t
@@ -69,7 +69,7 @@ my %sample_info = test_mip_hashes(
     }
 );
 
-my $eval_metric_file = catfile( dirname($Bin), qw{ t data references qc_eval_metric_-v1.3-.yaml} );
+my $eval_metric_file = catfile( dirname($Bin), qw{ t data references qc_eval_metric_-v1.4-.yaml} );
 
 ## Then set the relevant evaluation metrics for the analysis
 my $is_ok = evaluate_analysis(
diff --git a/t/mip_qccollect.test b/t/mip_qccollect.test
@@ -32,7 +32,7 @@ our $USAGE = build_usage( {} );
 my $VERBOSE = 1;
 ## Set paths
 my $cluster_constant_path = catdir( dirname($Bin), qw{ t data} );
-my $eval_metric_file      = catfile( dirname($Bin), qw{ templates qc_eval_metric_-v1.3-.yaml } );
+my $eval_metric_file      = catfile( dirname($Bin), qw{ templates qc_eval_metric_-v1.4-.yaml } );
 my $mip_path              = catfile( dirname($Bin), q{mip} );
 my $log_file_path         = catfile( cwd(),         q{qc_metrics_qccollect.log} );
 my $test_reference_path   = catdir( $cluster_constant_path, q{references} );
diff --git a/t/parse_limit_qc_output.t b/t/parse_limit_qc_output.t
@@ -47,7 +47,7 @@ my %qc_data = (
     sample => {
         sample_id => {
             recipe_output_file => {
-                collectmultiplemetrics => {
+                variantevalall => {
                     header => q{data},
                 },
             },
@@ -68,7 +68,7 @@ parse_limit_qc_output(
     }
 );
 
-## Then remove key collectmultiplemetrics
+## Then remove key variantevalall
 my %expected_qc_data = (
     sample => {
         sample_id => {
diff --git a/t/parse_sample_qc_metric.t b/t/parse_sample_qc_metric.t
@@ -49,20 +49,20 @@ diag(   q{Test parse_sample_qc_metric from Qccollect.pm}
 
 ## Constants
 Readonly my $PCT_TARGET_BASES_10X         => 0.95;
+Readonly my $FAIL_PCT_TARGET_BASES_10X    => 0.90;
 Readonly my $PERCENTAGE_MAPPED_READS_EVAL => 95;
 Readonly my $PERCENTAGE_MAPPED_READS_PASS => 99;
 
 ## Given sample qc data when metric lacks a header
-my $infile    = q{an_infile};
-my $metric    = q{percentage_mapped_reads};
+my $infile        = q{an_infile};
+my $metric        = q{percentage_mapped_reads};
 my $header_recipe = q{collecthsmetrics};
 my $header_metric = q{PCT_TARGET_BASES_10X};
-my $recipe    = q{bamstats};
-my $sample_id = q{ADM1059A1};
-my %qc_data   = (
+my $recipe        = q{bamstats};
+my $sample_id     = q{ADM1059A1};
+my %qc_data       = (
     sample => {
-        $sample_id =>
-          { $infile => { $recipe => { $metric => $PERCENTAGE_MAPPED_READS_PASS }, }, },
+        $sample_id => { $infile => { $recipe => { $metric => $PERCENTAGE_MAPPED_READS_PASS }, }, },
     }
 );
 
@@ -104,9 +104,13 @@ my $is_ok = parse_sample_qc_metric(
 );
 ok( $is_ok, q{Parsed sample qc data metrics} );
 
-## Given sample qc data when metric has a header
-my $data_header   = q{first_of_pair};
-$qc_data{sample}{$sample_id}{$infile}{$header_recipe}{header}{$data_header}{$header_metric} = $PCT_TARGET_BASES_10X;
+## Given sample qc data when metric has headers
+my $data_header = q{first_of_pair};
+$qc_data{sample}{$sample_id}{$infile}{$header_recipe}{header}{$data_header}{$header_metric} =
+  $PCT_TARGET_BASES_10X;
+my $second_data_header = q{second_of_pair};
+$qc_data{sample}{$sample_id}{$infile}{$header_recipe}{header}{$second_data_header}{$header_metric}
+  = $FAIL_PCT_TARGET_BASES_10X;
 
 ## Alias
 my $qc_data_header_recipe_href =
@@ -121,6 +125,14 @@ $is_ok = parse_sample_qc_metric(
         sample_id            => $sample_id,
     }
 );
+
+## Then parses format OK...
 ok( $is_ok, q{Parsed sample qc data header metrics} );
 
+## ... and fails qc check for the second header
+my $failed_evaluation =
+  q{FAILED:collecthsmetrics_PCT_TARGET_BASES_10X:} . $FAIL_PCT_TARGET_BASES_10X;
+is( $qc_data{evaluation}{collecthsmetrics}[0],
+    $failed_evaluation, q{Fails qc on second data header} );
+
 done_testing();
diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml
@@ -125,7 +125,7 @@ container:
   mip:
     executable:
       mip:
-    uri: docker.io/clinicalgenomics/mip:v12.0.0
+    uri: docker.io/clinicalgenomics/mip:v12.0.1
   multiqc:
     executable:
       multiqc:
diff --git a/templates/qc_eval_metric_-v1.4-.yaml b/templates/qc_eval_metric_-v1.4-.yaml
@@ -28,6 +28,8 @@ wgs:
   collectmultiplemetrics:
     PCT_PF_READS_ALIGNED:
       lt: 0.95
+    PCT_PF_READS_IMPROPER_PAIRS:
+      gt: 0.05
     PCT_ADAPTER:
       gt: 0.0005
   markduplicates:

Original file line number	Diff line number	Diff line change
`@@ -455,7 +455,7 @@ sub define_evaluate_metric {`
`455`	`455`
`456`	`456`	`sub evaluate_analysis {`
`457`	`457`
`458`		`-## Function : Read in aevaluate metrics and evaluate on sample and case level`
	`458`	`+## Function : Read in evaluation metrics and evaluate on sample and case level`
`459`	`459`	`## Returns :`
`460`	`460`	`## Arguments : eval_metric_file => File with evaluation metrics`
`461`	`461`	`## : qc_data_href => QC data {REF}`
`@@ -896,7 +896,6 @@ sub parse_sample_qc_metric {`
`896`	`896`	`$evaluate_metric_href->{$sample_id}{$recipe_name}{$metric},`
`897`	`897`	`}`
`898`	`898`	`);`
`899`		`- next METRIC;`
`900`	`899`	`}`
`901`	`900`	`}`
`902`	`901`	`return 1;`