Merge branch 'develop' into release/11.2.1

CHANGELOG.md

@@ -3,11 +3,43 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
+## [Develop]
+
+- Increased memory allocation for salmon and picardtools_mergersamfiles (RNA)
+- Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update
+- New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf.
+- Remove the RSeQC read duplication analysis as it often fails.
+- Increased run time allocation for gatk_asereadcounter.
+- Increased the default required length for a trimmed rna read to be retained from 20 bp to 40 bp. Configurable via CLI or config.
+- Fixed a bug where gnomad SV version 2.0 instead of version 2.1 was used to annotate SVs
+- One-pass instead of two-pass mapping with STAR-Fusion, as recommended for STAR-Fusion 1.12
+
+### Tools
+
+- Arriba 2.3.0 -> 2.4.0
+- DeepVariant 1.4.0 -> 1.5.0
+- FastQC: 0.11.9 -> 0.12.1
+- GATK: 4.2.6.1 -> 4.4.0.0
+- Gffcompare 0.11.2 -> 0.12.6
+- Htslib 1.15.1 -> 1.16
+- MegaFusion 66a3a80 -> d3feacf
+- Picard 2.27.2 -> 2.27.5
+- STAR-Fusion 1.11.0 -> 1.12.0
+- SVDB: 2.7.0 -> 2.8.1
+- Tiddit 3.3.2 -> 3.4.0
+
+### Databases
+
+clinvar: 20220829 -> 20230218
+loqusdb snapshot: 20230208 -> 20230214
+hmtvar: oct2022
+
 ## [11.2.1]
 
 - Patching of gens pre processing container to solve an issue with incomplete bed files.
 
 ### Tools
+
 gens_preproc 1.0.2 -> 1.0.8
 
 ## [11.2.0]
@@ -79,7 +111,7 @@ gens_preproc 1.0.2 -> 1.0.8
 - dbnsfp: 4.1a -> 4.3a (grch38 only)
 - gnomad: r3.1.1 -> r3.1.2 (grch38 only)
 - giab: 3.3.2 -> 4.2.1
-- loqusdb dump: 20210921 -> 20220905
+- loqusdb dump: 20210921 -> c
 - nist: v3.3.2 -> v4.2.1
 - vcf2cytosure blacklist: 200520
 

containers/fastqc/Dockerfile

@@ -5,15 +5,13 @@ FROM clinicalgenomics/mip_base:2.1
 ################## METADATA ######################
 
 LABEL base_image="clinicalgenomics/mip_base:2.1"
-LABEL version="2"
+LABEL version="3"
 LABEL software="fastqc"
-LABEL software.version="0.11.9"
+LABEL software.version="0.12.1"
 LABEL extra.binaries="fastqc"
 LABEL maintainer="Clinical-Genomics/MIP"
 
-RUN conda install fastqc=0.11.9=0
-
-## Clean up after conda
-RUN /opt/conda/bin/conda clean -tipsy
+RUN conda install fastqc=0.12.1 && \
+    /opt/conda/bin/conda clean -ya
 
 WORKDIR /data/

containers/hmtnote/Dockerfile

@@ -5,15 +5,15 @@ FROM clinicalgenomics/mip_base:2.1
 ################## METADATA ######################
 
 LABEL base-image="clinicalgenomics/mip_base:2.1"
-LABEL version="1"
+LABEL version="2"
 LABEL software="HmtNote"
 LABEL software.version="0.7.2"
-LABEL extra.binaries="HmtNote"
+LABEL extra.binaries="HmtNote, hmtvar_oct2022"
 LABEL maintainer="Clinical-Genomics/MIP"
 
 ## Conda env installation + clean up
 RUN conda install pip python=3.7 && \
-    /opt/conda/bin/conda clean -tipsy
+    /opt/conda/bin/conda clean -ya
 
 # Install HmtNote
 RUN pip install --no-cache-dir hmtnote==0.7.2 && \

containers/htslib/Dockerfile

@@ -5,13 +5,13 @@ FROM clinicalgenomics/mip_base:2.1
 ################## METADATA ######################
 
 LABEL base-image="clinicalgenomics/mip_base:2.1"
-LABEL version="7"
+LABEL version="8"
 LABEL software="htslib"
-LABEL software.version="1.15.1"
+LABEL software.version="1.16"
 LABEL extra.binaries="bcftools, bgzip, samtools, tabix"
 LABEL maintainer="Clinical-Genomics/MIP"
 
-RUN conda install bcftools=1.15.1 htslib=1.15.1 samtools=1.15.1 && \
+RUN conda install bcftools=1.16 htslib=1.16 samtools=1.16.1 && \
     /opt/conda/bin/conda clean -ya
 
 WORKDIR /data/

containers/megafusion/Dockerfile

@@ -7,7 +7,7 @@ FROM clinicalgenomics/mip_base:2.1
 LABEL base_image="clinicalgenomics/mip_base:2.1"
 LABEL version="4"
 LABEL software="MegaFusion"
-LABEL software.version="66a3a80"
+LABEL software.version="d3feacf"
 LABEL extra.binaries="MegaFusion.py"
 LABEL maintainer="Clinical-Genomics/MIP"
 
@@ -25,5 +25,5 @@ RUN git clone https://github.com/J35P312/MegaFusion.git /opt/conda/share/MegaFus
 WORKDIR /opt/conda/share/MegaFusion
 
 ## Make sure we're on the right commit
-RUN git reset --hard 66a3a80
+RUN git reset --hard d3feacf
 

definitions/rd_dna_parameters.yaml

@@ -1015,7 +1015,7 @@ sv_svdb_query_overlap:
   associated_recipe:
     - sv_annotate
   data_type: SCALAR
-  default: 0.5
+  default: 0.8
   type: recipe_argument
 sv_vcfanno_config:
   associated_recipe:

definitions/rd_rna_parameters.yaml

@@ -146,7 +146,7 @@ recipe_time:
     dna_vcf_reformat: 1
     fastqc_ar: 1
     fusion_report: 8
-    gatk_asereadcounter: 3
+    gatk_asereadcounter: 8
     gatk_baserecalibration: 5
     gatk_haplotypecaller: 12
     gatk_splitncigarreads: 16
@@ -191,10 +191,10 @@ recipe_memory:
     merge_fusion_reports: 8
     multiqc_ar: 10
     picardtools_collectrnaseqmetrics: 10
-    picardtools_mergesamfiles: 5
+    picardtools_mergesamfiles: 8
     preseq_ar: 8
     rseqc: 40
-    salmon_quant: 2
+    salmon_quant: 4
     star_aln: 5
     star_fusion: 25
     stringtie_ar: 2
@@ -301,6 +301,13 @@ trim_galore_ar:
   program_executables:
     - trim_galore
   type: recipe
+trim_min_length:
+  associated_recipe:
+    - trim_galore_ar
+  data_type: SCALAR
+  default: 40
+  mandatory: no
+  type: recipe_argument
 ## Salmon
 salmon_quant:
   analysis_mode: sample

documentation/Setup.md

@@ -78,7 +78,7 @@ You can speed up, for instance, the Readonly module by also installing the compa
 - [StringTie] (version: 2.1.3b)
 - [Svdb] (version: 2.4.0)
 - [Telomerecat] (version: 3.4.0)
-- [Tiddit] (version: 2.12.1)
+- [Tiddit] (version: 3.4.0)
 - [Upd] (version: 0.1.1)
 - [Varg] (version: 1.2.0)
 - [Vcf2cytosure] (version: 0.5.1)

lib/MIP/Cli/Mip/Analyse/Rd_rna.pm

@@ -976,6 +976,14 @@ q{Regular expression file containing the regular expression to be used for each
         )
     );
 
+    option(
+        q{trim_min_length} => (
+            documentation => q{Discard trimmed reads shorter than this},
+            is            => q{rw},
+            isa           => Int,
+        )
+    );
+
     option(
         q{vcfparser_ar} => (
             cmd_tags      => [q{Analysis recipe switch}],

lib/MIP/Program/Trim_galore.pm

@@ -37,6 +37,7 @@ sub trim_galore {
 ##          : $filehandle             => Filehandle to write to
 ##          : $gzip_output            => Gzip output fastq file
 ##          : $infile_paths_ref       => Infile paths {REF}
+##          : $length                 => Minimum length of trimmed read to retain
 ##          : $outdir_path            => Outdirectory path
 ##          : $paired_reads           => Do paired end trimming
 ##          : $stderrfile_path        => Stderrfile path
@@ -50,6 +51,7 @@ sub trim_galore {
     my $cores;
     my $filehandle;
     my $infile_paths_ref;
+    my $length;
     my $outdir_path;
     my $paired_reads;
     my $stderrfile_path;
@@ -88,6 +90,11 @@ sub trim_galore {
             store       => \$infile_paths_ref,
             strict_type => 1,
         },
+        length => {
+            allow       => [ undef, qr/\A \d+ \z/xms ],
+            store       => \$length,
+            strict_type => 1,
+        },
         outdir_path => {
             store       => \$outdir_path,
             strict_type => 1,
@@ -137,6 +144,10 @@ sub trim_galore {
         push @commands, q{--paired};
     }
 
+    if ($length) {
+        push @commands, q{--length} . $SPACE . $length;
+    }
+
     push @commands, join $SPACE, @{$infile_paths_ref};
 
     push @commands,

lib/MIP/Recipes/Analysis/Rseqc.pm

@@ -292,16 +292,6 @@ sub analysis_rseqc {
     );
     say {$filehandle} $NEWLINE;
 
-    say {$filehandle} q{## Rseqc read_duplication};
-    rseqc_read_duplication(
-        {
-            filehandle           => $filehandle,
-            infile_path          => $infile_path,
-            outfiles_path_prefix => $outfile_path_prefix . $UNDERSCORE . q{read_duplication},
-        }
-    );
-    say {$filehandle} $NEWLINE;
-
     close $filehandle;
 
     if ( $recipe{mode} == 1 ) {

lib/MIP/Recipes/Analysis/Star_aln.pm

@@ -1037,8 +1037,9 @@ sub analysis_star_fusion_aln {
             outfile_name_prefix                    => $outfile_path_prefix . $DOT,
             pe_overlap_mmp                         => $PE_OVERLAP_MMP,
             pe_overlap_nbases_min                  => $PE_OVERLAP_NBASES_MIN,
+            quant_mode                             => q{GeneCounts},
             thread_number                          => $recipe{core_number},
-            two_pass_mode                          => q{Basic},
+            two_pass_mode                          => q{None},
         },
     );
     say {$filehandle} $NEWLINE;
@@ -1053,21 +1054,6 @@ sub analysis_star_fusion_aln {
     );
     say {$filehandle} $NEWLINE;
 
-    ## Remove intermediary files
-  FILE_TAG:
-    foreach my $file_tag (qw{ _STARgenome _STARpass1 }) {
-
-        gnu_rm(
-            {
-                filehandle  => $filehandle,
-                force       => 1,
-                infile_path => $outfile_path_prefix . $DOT . $file_tag,
-                recursive   => 1,
-            }
-        );
-        print {$filehandle} $NEWLINE;
-    }
-
     ## Close filehandle
     close $filehandle or $log->logcroak(q{Could not close filehandle});
 

lib/MIP/Recipes/Analysis/Trim_galore.pm

@@ -278,6 +278,7 @@ sub analysis_trim_galore {
                 cores            => $process_core_number,
                 filehandle       => $filehandle,
                 infile_paths_ref => \@fastq_files,
+                length           => $active_parameter_href->{trim_min_length},
                 outdir_path      => $outsample_directory,
                 paired_reads     => $paired_reads,
                 stderrfile_path  => $stderrfile_path,

lib/MIP/Recipes/Download/Gnomad.pm

@@ -201,7 +201,7 @@ sub download_gnomad {
             },
             method => \&_annotate,
         },
-        q{r2.1.1_sv} => {
+        q{r2.1_sv} => {
             arg_href => {
                 info_keys_ref => [qw{ INFO/AC INFO/AF INFO/POPMAX_AF }],
             },
@@ -723,7 +723,7 @@ sub _build_af_file {
             strict_type => 1,
         },
         reference_version => {
-            allow       => [qw{ r2.0.1 r2.1.1 r2.1.1_sv r3.1.1 r3.1.2 }],
+            allow       => [qw{ r2.0.1 r2.1.1 r2.1_sv r3.1.1 r3.1.2 }],
             required    => 1,
             store       => \$reference_version,
             strict_type => 1,
@@ -737,7 +737,7 @@ sub _build_af_file {
     use MIP::Program::Htslib qw{ htslib_bgzip htslib_tabix };
 
     ## Don't build file for SV:s
-    return if ( $reference_version eq q{r2.1.1_sv} );
+    return if ( $reference_version eq q{r2.1_sv} );
 
     my $outfile_no_suffix = remove_file_path_suffix(
         {

t/trim_galore.t

@@ -23,16 +23,13 @@ use lib catdir( dirname($Bin), q{lib} );
 use MIP::Constants qw{ $COMMA $SPACE };
 use MIP::Test::Commands qw{ test_function };
 
-
 BEGIN {
 
     use MIP::Test::Fixtures qw{ test_import };
 
 ### Check all internal dependency modules and imports
 ## Modules with import
-    my %perl_module = (
-        q{MIP::Program::Trim_galore} => [qw{ trim_galore }],
-);
+    my %perl_module = ( q{MIP::Program::Trim_galore} => [qw{ trim_galore }], );
 
     test_import( { perl_module_href => \%perl_module, } );
 }
@@ -47,7 +44,8 @@ diag(   q{Test trim_galore from Trim_galore.pm}
       . $SPACE
       . $EXECUTABLE_NAME );
 
-Readonly my $CORES => 12;
+Readonly my $CORES      => 12;
+Readonly my $MIN_LENGTH => 30;
 
 ## Base arguments
 my @function_base_commands = qw{ trim_galore };
@@ -97,6 +95,10 @@ my %specific_argument = (
         inputs_ref      => [qw{ file_1.fastq file_2.fastq }],
         expected_output => q{file_1.fastq} . $SPACE . q{file_2.fastq},
     },
+    length => {
+        input           => $MIN_LENGTH,
+        expected_output => q{--length} . $SPACE . $MIN_LENGTH,
+    },
     outdir_path => {
         input           => catdir(qw{ output dir }),
         expected_output => q{--output_dir} . $SPACE . catdir(qw{ output dir }),