Merge 333cbcd into 4802f52

Clinical-Genomics · Apr 12, 2021 · 6d47af4 · 6d47af4
2 parents 4802f52 + 333cbcd
commit 6d47af4
Show file tree

Hide file tree

Showing 7 changed files with 61 additions and 13 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -21,18 +21,18 @@ This project adheres to [Semantic Versioning](http://semver.org/).
 
 arriba: v1.2.0 -> v2.1.0
 bedtools: 2.29.0 -> 2.30.0
-bcftools: 1.10.2-hd2cd319_0 -> 1.11-h7c999a4_0
+bcftools: 1.10.2-hd2cd319_0 -> 1.12=h45bccc9_1
 bwa-mem2 2.0 -> 2.2
 chanjo: 4.2.0 -> 4.6
 cyrius: v1.0 -> v1.1
 deepvariant: 1.0.0
 delly: 0.8.1 -> 0.8.7
 gatk: v4.1.8.1 -> v4.2.0.0
 glnexus: v1.3.1
-htslib: 1.10.2-h78d89cc_0 -> 1.11-hd3b49d5_2
+htslib: 1.10.2-h78d89cc_0 -> 1.12=h9093b5e_1
 pdfmerger: v1.0
 picardtools: 2.23.4 -> 2.25.0
-samtools: 1.10-h9402c20_2 -> 1.11-h6270b1f_0
+samtools: 1.10-h9402c20_2 -> 1.12=h9aed4be_1
 smncopynumbercaller: 4b2c1ad -> v1.1.1
 star: 2.7.4a -> 2.7.8a
 stranger: 0.7 -> 0.7.1

diff --git a/containers/htslib/Dockerfile b/containers/htslib/Dockerfile
@@ -5,15 +5,15 @@ FROM clinicalgenomics/mip_base:2.1
 ################## METADATA ######################
 
 LABEL base_image="clinicalgenomics/mip_base:2.1"
-LABEL version="3"
+LABEL version="4"
 LABEL software="htslib"
-LABEL software.version="1.11"
+LABEL software.version="1.12"
 LABEL extra.binaries="bcftools, bgzip, samtools, tabix"
 LABEL maintainer="Clinical-Genomics/MIP"
 
-RUN conda install bcftools=1.11=h7c999a4_0 htslib=1.11=hd3b49d5_2 samtools=1.11=h6270b1f_0
+RUN conda install bcftools=1.12=h45bccc9_1 htslib=1.12=h9093b5e_1 samtools=1.12=h9aed4be_1
 
 ## Clean up after conda
-RUN /opt/conda/bin/conda clean -tipsy
+RUN /opt/conda/bin/conda clean -ya
 
 WORKDIR /data/
diff --git a/documentation/Setup.md b/documentation/Setup.md
@@ -54,7 +54,7 @@ You can speed up, for instance, the Readonly module by also installing the compa
 - [GENMOD] (version: 3.7.3)
 - [Gffcompare] (version: 0.11.2)
 - [Glnexus] (version: 1.3.1)
-- [Htslib] (version: 1.11)
+- [Htslib] (version: 1.12)
 - [Manta] (version: 1.6.0)
 - [Megafusion] (version: cc6676c)
 - [MultiQC] (version: 1.9)

diff --git a/lib/MIP/Program/Bcftools.pm b/lib/MIP/Program/Bcftools.pm
@@ -16,7 +16,7 @@ use autodie qw{ :all };
 use Readonly;
 
 ## MIPs lib/
-use MIP::Constants qw{ $COMMA $DOUBLE_QUOTE $NEWLINE $PIPE $SPACE };
+use MIP::Constants qw{ $ASTERISK $BACKWARD_SLASH $COMMA $DOUBLE_QUOTE $DOT $NEWLINE $PIPE $SPACE };
 use MIP::Environment::Executable qw{ get_executable_base_command };
 use MIP::Unix::Standard_streams qw{ unix_standard_streams };
 use MIP::Unix::Write_to_file qw{ unix_write_to_file };
@@ -1124,10 +1124,13 @@ sub bcftools_norm {
 
 ## Function : Perl wrapper for writing bcftools norm recipe to $filehandle or return commands array. Based on bcftools 1.6.
 ## Returns  : @commands
-## Arguments: $filehandle             => Filehandle to write to
+## Arguments: $atomize                => Decompose complex variants e.g. split MNVs into consecutive SNVs
+##          : $atom_overlaps          => Use "." or "*" for missing allele when decomposing complex varaiants
+##          : $filehandle             => Filehandle to write to
 ##          : $infile_path            => Infile path to read from
 ##          : $multiallelic           => To split/join multiallelic calls or not
 ##          : $multiallelic_type      => Type of multiallelic to split/join {OPTIONAL}
+##          : $old_rec_tag            => Annotate the decomposed records with the orignal record
 ##          : $outfile_path           => Outfile path to write to
 ##          : $output_type            => 'b' compressed BCF; 'u' uncompressed BCF; 'z' compressed VCF; 'v' uncompressed VCF [v]
 ##          : $reference_check        => Controls how to treat incorrect reference alleles - 's' fix; 'w' warn; 'x' exclude; 'e' exit
@@ -1144,9 +1147,12 @@ sub bcftools_norm {
     my ($arg_href) = @_;
 
     ## Flatten argument(s)
+    my $atomize;
+    my $atom_overlaps;
     my $filehandle;
     my $infile_path;
     my $multiallelic;
+    my $old_rec_tag;
     my $outfile_path;
     my $reference_check;
     my $reference_path;
@@ -1164,6 +1170,16 @@ sub bcftools_norm {
     my $output_type;
 
     my $tmpl = {
+        atomize => {
+            allow       => [ undef, 0, 1 ],
+            store       => \$atomize,
+            strict_type => 1,
+        },
+        atom_overlaps => {
+            allow       => [ undef, $DOT, $BACKWARD_SLASH . $ASTERISK ],
+            store       => \$atom_overlaps,
+            strict_type => 1,
+        },
         filehandle   => { store => \$filehandle, },
         infile_path  => { store => \$infile_path, strict_type => 1, },
         multiallelic => {
@@ -1177,6 +1193,11 @@ sub bcftools_norm {
             store       => \$multiallelic_type,
             strict_type => 1,
         },
+        old_rec_tag => {
+            allow       => [ undef, 0, 1 ],
+            store       => \$old_rec_tag,
+            strict_type => 1,
+        },
         outfile_path => {
             store       => \$outfile_path,
             strict_type => 1,
@@ -1237,11 +1258,26 @@ sub bcftools_norm {
         }
     );
 
+    if ($atomize) {
+
+        push @commands, q{--atomize};
+    }
+
+    if ($atom_overlaps) {
+
+        push @commands, q{--atom_overlaps} . $SPACE . $atom_overlaps;
+    }
+
     if ($multiallelic) {
 
         push @commands, q{--multiallelics} . $SPACE . $multiallelic . $multiallelic_type;
     }
 
+    if ($old_rec_tag) {
+
+        push @commands, q{--old-rec-tag};
+    }
+
     if ($reference_check) {
 
         push @commands, q{--check-ref} . $SPACE . $reference_check;

diff --git a/t/bcftools_norm.t b/t/bcftools_norm.t
@@ -20,7 +20,7 @@ use Readonly;
 
 ## MIPs lib/
 use lib catdir( dirname($Bin), q{lib} );
-use MIP::Constants qw{ $COMMA $SPACE };
+use MIP::Constants qw{ $ASTERISK $BACKWARD_SLASH $COMMA $SPACE };
 use MIP::Test::Commands qw{ test_function };
 
 BEGIN {
@@ -80,6 +80,14 @@ my %required_argument = (
 );
 
 my %specific_argument = (
+    atomize => {
+        input           => 1,
+        expected_output => q{--atomize},
+    },
+    atom_overlaps => {
+        input           => $BACKWARD_SLASH . $ASTERISK,
+        expected_output => q{--atom_overlaps} . $SPACE . $BACKWARD_SLASH . $ASTERISK,
+    },
     infile_path => {
         input           => q{infile.test},
         expected_output => q{infile.test},
@@ -88,6 +96,10 @@ my %specific_argument = (
         input           => q{snps},
         expected_output => q{--multiallelics +snps},
     },
+    old_rec_tag => {
+        input           => 1,
+        expected_output => q{--old-rec-tag},
+    },
     output_type => {
         input           => q{v},
         expected_output => q{--output-type v},

diff --git a/t/data/test_data/miptest_install_config.yaml b/t/data/test_data/miptest_install_config.yaml
@@ -105,7 +105,7 @@ container:
       bgzip:
       samtools:
       tabix:
-    uri: docker.io/clinicalgenomics/htslib:1.11
+    uri: docker.io/clinicalgenomics/htslib:1.12
   manta:
     executable:
       configManta.py:

diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml
@@ -104,7 +104,7 @@ container:
       bgzip:
       samtools:
       tabix:
-    uri: docker.io/clinicalgenomics/htslib:1.11
+    uri: docker.io/clinicalgenomics/htslib:1.12
   manta:
     executable:
       configManta.py: