Merge pull request wtsi-npg#795 from wtsi-npg/devel

pull from devel to master to create release 66.0.0
mgcam · Aug 15, 2023 · 2f3d471 · 2f3d471
2 parents 5ca4ea3 + f853904
commit 2f3d471
Show file tree

Hide file tree

Showing 4 changed files with 16 additions and 5 deletions.
diff --git a/Changes b/Changes
@@ -1,6 +1,11 @@
 LIST OF CHANGES
 ---------------
 
+release 66.0.0
+ - small tweak to seq_alignment so GbS samples with no study ref do not fail
+ - switch off spatial filter for NovaSeqX
+ - for NovaSeqX, default RNA analysis should be STAR
+
 release 65.1.0
  - ensure per-product archival for NovaSeqX data
  - runs with data analysed on-board are not deletable

diff --git a/lib/npg_pipeline/function/seq_alignment.pm b/lib/npg_pipeline/function/seq_alignment.pm
@@ -301,7 +301,7 @@ sub _alignment_command { ## no critic (Subroutines::ProhibitExcessComplexity)
     push @{$p4_ops->{prune}}, 'ssfqc_tee_ssfqc:subsample-';
   }
 
-  if($self->platform_NovaSeq) {  # skip spatial filter
+  if($self->platform_NovaSeq or $self->platform_NovaSeqX) {  # skip spatial filter
     $p4_param_vals->{spatial_filter_switch} = q[off];
   }
 
@@ -440,7 +440,7 @@ sub _alignment_command { ## no critic (Subroutines::ProhibitExcessComplexity)
     $p4_param_vals->{markdup_method} = $do_gbs_plex ? q[none] : $self->markdup_method($dp);
     $p4_param_vals->{markdup_optical_distance_value} = ($uses_patterned_flowcell? $PFC_MARKDUP_OPT_DIST: $NON_PFC_MARKDUP_OPT_DIST);
 
-    if($p4_param_vals->{markdup_method} eq q[none]) {
+    if(!$do_gbs_plex && ($p4_param_vals->{markdup_method} eq q[none])) {
       $skip_target_markdup_metrics = 1;
 
       if(my $pcb=npg_pipeline::cache::reference->instance->get_primer_panel_bed_file($dp, $self->repository)) {
@@ -491,6 +491,7 @@ sub _alignment_command { ## no critic (Subroutines::ProhibitExcessComplexity)
 
   my $p4_local_assignments = {};
   if($do_gbs_plex){
+     $p4_param_vals->{primer_clip_method} = q[no_clip];
      $p4_param_vals->{bwa_executable}   = q[bwa0_6];
      $p4_param_vals->{bsc_executable}   = q[bamsort];
      $p4_param_vals->{alignment_method} = $bwa;
@@ -499,7 +500,8 @@ sub _alignment_command { ## no critic (Subroutines::ProhibitExcessComplexity)
      $skip_target_markdup_metrics = 1;
   }
   elsif($do_rna) {
-    my $rna_analysis = $self->_analysis($l->reference_genome, $rpt_list) // $DEFAULT_RNA_ANALYSIS;
+    my $rna_analysis = $self->_analysis($l->reference_genome, $rpt_list) // ($self->platform_NovaSeqX? q[star]:$DEFAULT_RNA_ANALYSIS);
+
     if (none {$_ eq $rna_analysis} @RNA_ANALYSES){
         $self->info($l->to_string . qq[- Unsupported RNA analysis: $rna_analysis - running $DEFAULT_RNA_ANALYSIS instead]);
         $rna_analysis = $DEFAULT_RNA_ANALYSIS;

diff --git a/t/20-function-seq_alignment.t b/t/20-function-seq_alignment.t
@@ -1277,7 +1277,7 @@ subtest 'chromium' => sub {
 };
 
 subtest 'miseq' => sub {
-  plan tests => 23;
+  plan tests => 24;
 
   my $runfolder = q{171020_MS5_24135_A_MS5476963-300V2};
   my $runfolder_path = join q[/], $dir, $runfolder;
@@ -1311,6 +1311,10 @@ subtest 'miseq' => sub {
   my $dp1 = npg_pipeline::product->new(lims => $l1, rpt_list => q[24135:1:1],);
   ok ($ms_gen->can_run_gbs($dp1), 'can run gbs pipeline on 24135:1:1');
 
+  my $l2 = st::api::lims->new(id_run => 24135, position => 1, tag_index =>2);
+  my $dp2 = npg_pipeline::product->new(lims => $l2, rpt_list => q[24135:1:2],);
+  ok ($ms_gen->can_run_gbs($dp2), 'can run gbs pipeline on 24135:1:2 (no study ref)');
+
   my $l3 = st::api::lims->new(id_run => 24135, position => 1, tag_index => 3);
   my $dp3 = npg_pipeline::product->new(lims => $l3, rpt_list => q[24135:1:3],);
   ok (! $ms_gen->can_run_gbs($dp3), 'cannot run gbs pipeline on 24135:1:3');

diff --git a/t/data/miseq/samplesheet_24135_gbs.csv b/t/data/miseq/samplesheet_24135_gbs.csv
@@ -1,7 +1,7 @@
 [Data],,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
 Sample_ID,Sample_Name,GenomeFolder,Index,Index2,bait_name,default_library_type,default_tag_sequence,default_tagtwo_sequence,email_addresses,email_addresses_of_followers,email_addresses_of_managers,email_addresses_of_owners,is_control,is_pool,lane_id,lane_priority,library_name,organism,organism_taxon_id,project_cost_code,project_id,project_name,purpose,qc_state,request_id,required_insert_size_range,sample_accession_number,sample_cohort,sample_common_name,sample_consent_withdrawn,sample_description,sample_donor_id,sample_id,sample_name,sample_public_name,sample_reference_genome,sample_supplier_name,spiked_phix_tag_index,study_accession_number,study_alignments_in_bam,study_contains_nonconsented_human,study_contains_nonconsented_xahuman,study_description,study_id,study_name,study_reference_genome,study_separate_y_chromosome_data,study_title,tag_index,gbs_plex_name,
 20314922,mxPCR7155682,,ATCACGTT,AGGCGAAG,,GbS standard,ATCACGTT,AGGCGAAG,[email protected] [email protected],[email protected],[email protected],[email protected],0,0,20315681,0,20314922,,,S0910,,,standard,,,from:100 to:1000,,,,0,,mxPCR7155682,3373451,mxPCR7155682,,,HAPMAP5265538,,EGAS00001002541,1,0,0,This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F%0D%0A,4825,Multiplex PCR R%26D for Agena%2FFluidigm replacement,Homo_sapiens (GRCh38_15),0,Flexible multiplex PCR for genotyping-by-sequencing,1,Hs_MajorQC,
-20314923,mxPCR7155683,,CGATGTTT,AGGCGAAG,,GnT MDA,CGATGTTT,AGGCGAAG,[email protected] [email protected],[email protected],[email protected],[email protected],0,0,20315681,0,20314923,,,S0910,,,standard,,,from:100 to:1000,,,,0,,mxPCR7155683,3373452,mxPCR7155683,,,HAPMAP5265539,,EGAS00001002541,1,0,0,This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F%0D%0A,4825,Multiplex PCR R%26D for Agena%2FFluidigm replacement,Homo_sapiens (GRCh38_15),0,Flexible multiplex PCR for genotyping-by-sequencing,2,Hs_MajorQC,
+20314923,mxPCR7155683,,CGATGTTT,AGGCGAAG,,GnT MDA,CGATGTTT,AGGCGAAG,[email protected] [email protected],[email protected],[email protected],[email protected],0,0,20315681,0,20314923,,,S0910,,,standard,,,from:100 to:1000,,,,0,,mxPCR7155683,3373452,mxPCR7155683,,,HAPMAP5265539,,EGAS00001002541,1,0,0,This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F%0D%0A,4825,Multiplex PCR R%26D for Agena%2FFluidigm replacement, ,0,Flexible multiplex PCR for genotyping-by-sequencing,2,Hs_MajorQC,
 20314924,mxPCR7155684,,CGATGTTT,AGGCGAAG,,GBS,TTAGGCAT,AGGCGAAG,[email protected] [email protected],[email protected],[email protected],[email protected],0,0,20315681,0,20314922,,,S0910,,,standard,,,from:100 to:1000,,,,0,,mxPCR7155684,3373452,mxPCR7155684,,,HAPMAP5265539,,EGAS00001002541,1,0,0,This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F%0D%0A,3597,Blah,Homo_sapiens (GRCh38_15),0,Blah,3,Hs_MajorQC,
 20314925,mxPCR7155685,,TGACCACT,AGGCGAAG,,GBS,TGACCACT,AGGCGAAG,[email protected] [email protected],[email protected],[email protected],[email protected],0,0,20315681,0,20314923,,,S0910,,,standard,,,from:100 to:1000,,,,0,,mxPCR7155685,3373454,mxPCR7155685,,,HAPMAP5265540,,EGAS00001002543,1,0,0,This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F%0D%0A,2410,Blah,Homo_sapiens (GRCh38_15),0,Blah,4,Hs_MajorQC,
 20314926,mxPCR7155686,,ACAGTGGT,AGGCGAAG,,GBS,ACAGTGGT,AGGCGAAG,[email protected] [email protected],[email protected],[email protected],[email protected],0,0,20315681,0,20314923,,,S0910,,,standard,,,from:100 to:1000,,,,0,,mxPCR7155686,3373455,mxPCR7155686,,,HAPMAP5265540,,EGAS00001002543,1,0,0,This data is part of a pre-publication release. For information on the proper use of pre-publication data shared by the Wellcome Trust Sanger Institute (including details of any publication moratoria)%2C please see http%3A%2F%2Fwww.sanger.ac.uk%2Fdatasharing%2F%0D%0A,3597,Blah,Homo_sapiens (GRCh38_15),0,Blah,5,Not_stored,