Merge pull request #2033 from Clinical-Genomics/release/11.2.0

Release/11.2.0

CHANGELOG.md

@@ -3,6 +3,18 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
+## [11.2.0]
+
+- Adds retroseq for mobile element detection
+
+### Databases
+
+- expansionhunter variant catalog: v4.0.2 -> v5.0.0
+
+### Tools
+
+- RetroSeq: 9d4f3b5
+
 ## [11.1.3]
 
 - Adds Gens' bed index file to deliverables

containers/retroseq/Dockerfile

@@ -0,0 +1,30 @@
+################## BASE IMAGE ######################
+
+FROM clinicalgenomics/mip_base:2.1
+
+################## METADATA ######################
+
+LABEL base_image="clinicalgenomics/mip_base:2.1"
+LABEL version="1"
+LABEL software="retroseq"
+LABEL software.version="1.5_9d4f3b5"
+LABEL extra.binaries="retroseq"
+LABEL maintainer="Clinical-Genomics/MIP"
+
+RUN apt-get update --fix-missing && \
+    apt-get install -y --no-install-recommends \
+        ca-certificates && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+RUN conda install samtools exonerate bedtools bcftools && \
+    /opt/conda/bin/conda clean -ya
+
+RUN git clone https://github.com/tk2/RetroSeq.git /opt/conda/share/RetroSeq
+
+WORKDIR /opt/conda/share/RetroSeq
+
+## Remove samtool check
+## Make sure we're on the right commit and remove samtools check
+RUN git reset --hard 9d4f3b5 && \
+    sed -i '/RetroSeq::Utilities::checkBinary( q\[samtools\].*/d' ./bin/retroseq.pl

definitions/install_parameters.yaml

@@ -93,6 +93,7 @@ rd_dna:
     - picard
     - plink
     - python
+    - retroseq
     - rhocall
     - rtg-tools
     - sambamba

definitions/rd_dna_initiation_map.yaml

@@ -49,6 +49,13 @@ CHAIN_ALL:
       - sv_rankvariant
       - sv_reformat
       - vcf2cytosure_ar
+    - CHAIN_MOBILE_ELEMENTS:
+      - me_merge_bam
+      - retroseq
+      - me_merge_vcfs
+      - me_annotate
+      - me_varianteffectpredictor
+      - me_filter
   - CHAIN_MAIN:
     # PARALLEL chains, which inherit from MAIN in initiation, but are merged back to CHAIN_MAIN after execution
     - PARALLEL:

definitions/rd_dna_parameters.yaml

@@ -226,6 +226,11 @@ recipe_core_number:
     gzip_fastq: 0
     manta: 36
     markduplicates: 13
+    me_annotate: 2
+    me_filter: 2
+    me_merge_bam: 5
+    me_merge_vcfs: 2
+    me_varianteffectpredictor: 4
     mitodel: 1
     mt_annotation: 1
     multiqc_ar: 1
@@ -234,6 +239,7 @@ recipe_core_number:
     picardtools_collectmultiplemetrics: 1
     plink: 1
     qccollect_ar: 1
+    retroseq: 2
     rhocall_ar: 13
     rhocall_viz: 1
     rtg_vcfeval: 36
@@ -301,6 +307,7 @@ recipe_memory:
     picardtools_collecthsmetrics: 8
     picardtools_collectmultiplemetrics: 8
     plink: 10
+    retroseq: 5
     rhocall_ar: 2
     rhocall_viz: 5
     sambamba_depth: 10
@@ -355,6 +362,11 @@ recipe_time:
     gzip_fastq: 2
     manta: 30
     markduplicates: 20
+    me_annotate: 2
+    me_filter: 1
+    me_merge_bam: 5
+    me_merge_vcfs: 2
+    me_varianteffectpredictor: 3
     mitodel: 2
     mt_annotation: 1
     multiqc_ar: 5
@@ -365,6 +377,7 @@ recipe_time:
     prepareforvariantannotationblock: 5
     qccollect_ar: 1
     rankvariant: 10
+    retroseq: 5
     rhocall_ar: 5
     rhocall_viz: 1
     rtg_vcfeval: 1
@@ -405,6 +418,7 @@ picardtools_path:
     - markduplicates
     - picardtools_collecthsmetrics
     - picardtools_collectmultiplemetrics
+    - retroseq
     - sv_reformat
   data_type: SCALAR
   type: path
@@ -866,7 +880,7 @@ expansionhunter_variant_catalog_file_path:
   associated_recipe:
     - expansionhunter
   data_type: SCALAR
-  default: grch37_expansionhunter_variant_catalog_-4.0.2-.json
+  default: grch37_expansionhunter_variant_catalog_-5.0.0-.json
   exists_check: file
   is_reference: 1
   reference: reference_dir
@@ -1250,6 +1264,129 @@ sv_reformat_remove_genes_file:
   mandatory: no
   reference: reference_dir
   type: path
+## Mobile element chain
+me_merge_bam:
+  analysis_mode: sample
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: "_all"
+  program_executables:
+    - samtools
+  outfile_suffix: ".bam"
+  type: recipe
+retroseq:
+  analysis_mode: sample
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: _me
+  outfile_suffix: ".vcf.gz"
+  program_executables:
+    - bcftools
+    - picard
+    - retroseq.pl
+    - tabix
+  type: recipe
+mobile_element_reference:
+  associated_recipe:
+    - retroseq
+  data_type: HASH
+  is_reference: 1
+  reference: reference_dir
+  type: path
+me_merge_vcfs:
+  analysis_mode: case
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: _me
+  outfile_suffix: ".vcf.gz"
+  program_executables:
+    - bgzip
+    - svdb
+    - tabix
+  type: recipe
+me_merge_vcfs_overlap:
+  associated_recipe:
+    - me_merge_vcfs
+  data_type: SCALAR
+  default: 0.5
+  type: recipe_argument
+me_merge_vcfs_bnd_distance:
+  associated_recipe:
+    - me_merge_vcfs
+  data_type: SCALAR
+  default: 150
+  type: recipe_argument
+me_annotate:
+  analysis_mode: case
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: _ann
+  outfile_suffix: ".vcf.gz"
+  program_executables:
+    - bcftools
+    - svdb
+    - tabix
+  type: recipe
+me_annotate_query_files:
+  associated_recipe:
+    - me_annotate
+  data_type: HASH
+  exists_check: file
+  is_reference: 1
+  reference: reference_dir
+  type: path
+me_annotate_query_overlap:
+  associated_recipe:
+    - me_annotate
+  data_type: SCALAR
+  default: -1
+  type: recipe_argument
+me_annotate_query_bnd_distance:
+  associated_recipe:
+    - me_annotate
+  data_type: SCALAR
+  default: 150
+  type: recipe_argument
+me_varianteffectpredictor:
+  analysis_mode: case
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: _vep
+  outfile_suffix: ".vcf.gz"
+  program_executables:
+    - bcftools
+    - tabix
+    - vep
+  type: recipe
+me_filter:
+  analysis_mode: case
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: _filter
+  outfile_suffix: ".vcf.gz"
+  program_executables:
+    - bcftools
+    - mip
+    - tabix
+  type: recipe
+me_filter_frequency_threshold:
+  associated_recipe:
+    - me_filter
+  data_type: SCALAR
+  default: 0.1
+  type: recipe_argument
 ## GATK CollectReadCounts
 gatk_collectreadcounts:
   analysis_mode: sample

documentation/Setup.md

@@ -64,6 +64,7 @@ You can speed up, for instance, the Readonly module by also installing the compa
 - [PicardTools] (version: 2.27.2)
 - [PLINK] (version: 1.90b3x35)
 - [Preseq] (version: 3.1.2)
+- [RetroSeq] (version: 9d4f3b5)
 - [Rhocall] (version: 0.5.1)
 - [RSeQC] (version: 4.0.0)
 - [rtg-tools] (version: 3.12)
@@ -195,6 +196,7 @@ Corresponding MIP references:
 [PicardTools]: http://broadinstitute.github.io/picard/
 [PLINK]: https://www.cog-genomics.org/plink2
 [Preseq]: http://smithlabresearch.org/software/preseq/
+[RetroSeq]: https://github.com/tk2/RetroSeq
 [Rhocall]: https://github.com/dnil/rhocall
 [RSeQC]: http://rseqc.sourceforge.net/
 [rtg-tools]: https://github.com/RealTimeGenomics/rtg-tools

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

@@ -1156,6 +1156,115 @@ q{Default: hgvs, symbol, numbers, sift, polyphen, humdiv, domains, protein, ccds
         )
     );
 
+    option(
+        q{me_merge_bam} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Prepare bam files for RetroSeq},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{retroseq} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Discover mobile elements using RetroSeq},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{me_merge_vcfs} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Merge sample vcfs from RetroSeq},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{me_merge_vcfs_bnd_distance} => (
+            cmd_tags      => [q{Default: 150}],
+            documentation => q{Maximum distance between two similar BNDs},
+            is            => q{rw},
+            isa           => Num,
+        )
+    );
+
+    option(
+        q{me_merge_vcfs_overlap} => (
+            cmd_tags      => [q{Default: }],
+            documentation => q{Overlap required to merge two events},
+            is            => q{rw},
+            isa           => Num,
+        )
+    );
+
+    option(
+        q{mobile_element_reference} => (
+            cmd_tags      => [q{file.vcf=TE_type}],
+            documentation => q{Database file(s) for mobile element iscovery},
+            is            => q{rw},
+            isa           => HashRef,
+        )
+    );
+
+    option(
+        q{me_annotate} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Annotate mobile elememnt},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{me_annotate_query_bnd_distance} => (
+            cmd_tags      => [q{Default: 150}],
+            documentation => q{Maximum distance between two similar BNDs},
+            is            => q{rw},
+            isa           => Num,
+        )
+    );
+
+    option(
+        q{me_annotate_query_overlap} => (
+            cmd_tags      => [q{Default: }],
+            documentation => q{Overlap required to annotate},
+            is            => q{rw},
+            isa           => Num,
+        )
+    );
+
+    option(
+        q{me_varianteffectpredictor} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Annotate mobile elements with VEP},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{me_filter} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Filter mobile elements},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{me_filter_frequency_threshold} => (
+            cmd_tags      => [q{Default: 0.1}],
+            documentation =>
+              q{Threshold frequency for variants to be filtered out, set to 0 to disable},
+            is  => q{rw},
+            isa => Num,
+        )
+    );
+
     option(
         q{gatk_haplotypecaller} => (
             cmd_tags      => [q{Analysis recipe switch}],