feat(bcftools_mpileup): Removed bcftools_mpileup recipe and replace_i…

…upac sub - Keept bcftools mpileup program API
Clinical-Genomics · Nov 19, 2020 · e8c9c94 · e8c9c94
1 parent 5ea47e8
commit e8c9c94
Show file tree

Hide file tree

Showing 20 changed files with 67 additions and 1,005 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,13 +2,26 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
+## [10.0.0]
+- Removed support to run bcftools_mpileup as a variant caller
+- Added perl and MIP docker file and use it in recipes
+- Removed PATH check for proxy bins
+- Switched to using container manager instead of proxy bins in recipes
+- Removed support to run variant_integrity
+- Added deepvariant as variant caller and glnexus to merge samples to case vcf 
+
+**Tools**
+deepvariant: 1.0.0
+glnexus: v1.2.7
+
+
 ## [9.0.5]
 - Predicted gender from wgs samples are now used in the generated fam files.
 - Restrict plink analysis to intersected target capture kits for mixed wgs/wes cases
 - Update to chromograph in order to fix the renderering coverage images 
 
 **Tools**
-chromograph 0.3.1 -> 0.3.3
+chromograph: 0.3.1 -> 0.3.3
 
 ## [9.0.4]
 - Increased memory allocation for samtools_subsample_mt

diff --git a/definitions/rd_dna_initiation_map.yaml b/definitions/rd_dna_initiation_map.yaml
@@ -53,7 +53,6 @@ CHAIN_ALL:
   - CHAIN_MAIN:
     # PARALLEL chains, which inherit from MAIN in initiation, but are merged back to CHAIN_MAIN after execution
     - PARALLEL:
-      - bcftools_mpileup
       - CHAIN_DEEPVAR:
         - deepvariant
         - glnexus_merge

diff --git a/definitions/rd_dna_panel_parameters.yaml b/definitions/rd_dna_panel_parameters.yaml
@@ -244,12 +244,6 @@ picardtools_path:
     - picardtools_collectmultiplemetrics
   data_type: SCALAR
   type: path
-replace_iupac:
-  associated_recipe:
-    - mip
-  data_type: SCALAR
-  default: 0
-  type: mip
 ### Programs
 ## Gzip
 gzip_fastq:

diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml
@@ -56,7 +56,6 @@ expected_coverage:
 ## genomeAnalysisToolKitPath
 gatk_logging_level:
   associated_recipe:
-    - bcftools_mpileup
     - gatk_baserecalibration
     - gatk_combinevariantcallsets
     - gatk_gathervcfs
@@ -81,7 +80,6 @@ gatk_path:
 ## HumanGenomeReference
 human_genome_reference:
   associated_recipe:
-    - bcftools_mpileup
     - bwa_mem
     - bwa_mem2
     - cnvnator_ar
@@ -107,7 +105,6 @@ human_genome_reference:
   type: path
 human_genome_reference_file_endings:
   associated_recipe:
-    - bcftools_mpileup
     - bwa_mem
     - bwa_mem2
     - cnvnator_ar
@@ -137,7 +134,6 @@ recipe_core_number:
   data_type: HASH
   default:
     analysisrunstatus: 1
-    bcftools_mpileup: 16
     bwa_mem: 36
     bwa_mem2: 36
     cadd_ar: 13
@@ -253,7 +249,6 @@ recipe_time:
     analysisrunstatus: 1
     bwa_mem: 30
     bwa_mem2: 10
-    bcftools_mpileup: 40
     cadd_ar: 10
     chanjo_sexcheck: 2
     chromograph_cov: 1
@@ -339,12 +334,6 @@ picardtools_path:
     - sv_reformat
   data_type: SCALAR
   type: path
-replace_iupac:
-  associated_recipe:
-    - mip
-  data_type: SCALAR
-  default: 0
-  type: mip
 ### Programs
 split_fastq_file:
   analysis_mode: sample
@@ -1179,38 +1168,6 @@ sv_reformat_remove_genes_file:
   mandatory: no
   reference: reference_dir
   type: path
-## Bcftools
-bcftools_mpileup:
-  analysis_mode: case
-  associated_recipe:
-    - mip
-  data_type: SCALAR
-  default: 0
-  file_tag: _mpileup
-  program_executables:
-    - bcftools
-  recipe_type: variant_callers
-  outfile_suffix: ".vcf"
-  type: recipe
-  variant_caller: mpileup
-bcftools_mpileup_constrain:
-  associated_recipe:
-    - bcftools_mpileup
-  data_type: SCALAR
-  mandatory: no
-  type: recipe_argument
-bcftools_mpileup_filter_variant:
-  associated_recipe:
-    - bcftools_mpileup
-  data_type: SCALAR
-  default: 0
-  type: recipe_argument
-bcftools_mpileup_keep_unnormalised:
-  associated_recipe:
-    - bcftools_mpileup
-  data_type: SCALAR
-  default: 0
-  type: recipe_argument
 ## GATK Genotype
 gatk_haplotypecaller:
   analysis_mode: sample

diff --git a/documentation/Analysis.md b/documentation/Analysis.md
@@ -74,19 +74,19 @@ $ mip analyse rd_dna [case_id] --config_file [mip_config_rd_dna] --pr
 This will print a string with recipes in mode 2 (expect output) in chronological order (as far as possible, as some things are processed in parallel):
 
 ```Bash
-$ --split_fastq_file 2 --gzip_fastq 2 --fastqc_ar 2 --bwa_mem 2 --samtools_merge 2 --markduplicates 2 --gatk_baserecalibration 2 --chanjo_sexcheck 2 --sambamba_depth 2 --picardtools_collectmultiplemetrics 2 --picardtools_collecthsmetrics 2 --cnvnator_ar 2 --delly_call 2 --delly_reformat 2 --manta 2 --tiddit 2 --sv_combinevariantcallsets 2 --sv_varianteffectpredictor 2 --sv_vcfparser 2 --sv_rankvariant 2 --sv_reformat 2 --bcftools_mpileup 2 --gatk_haplotypecaller 2 --gatk_genotypegvcfs 2 --gatk_variantrecalibration 2 --gatk_combinevariantcallsets 2 --prepareforvariantannotationblock 2 --rhocall_ar 2 --vt_ar 2 --frequency_filter 2 --gatk_variantevalall 2 --gatk_variantevalexome 2 --varianteffectpredictor 2 --vcfparser 2 --peddy_ar 2 --plink 2 --rankvariant 2 --endvariantannotationblock 2 --qccollect_ar 2 --multiqc_ar 2 --analysisrunstatus 2 --sacct 2
+$ --split_fastq_file 2 --gzip_fastq 2 --fastqc_ar 2 --bwa_mem 2 --samtools_merge 2 --markduplicates 2 --gatk_baserecalibration 2 --chanjo_sexcheck 2 --sambamba_depth 2 --picardtools_collectmultiplemetrics 2 --picardtools_collecthsmetrics 2 --cnvnator_ar 2 --delly_call 2 --delly_reformat 2 --manta 2 --tiddit 2 --sv_combinevariantcallsets 2 --sv_varianteffectpredictor 2 --sv_vcfparser 2 --sv_rankvariant 2 --sv_reformat 2 --gatk_haplotypecaller 2 --gatk_genotypegvcfs 2 --gatk_variantrecalibration 2 --gatk_combinevariantcallsets 2 --prepareforvariantannotationblock 2 --rhocall_ar 2 --vt_ar 2 --frequency_filter 2 --gatk_variantevalall 2 --gatk_variantevalexome 2 --varianteffectpredictor 2 --vcfparser 2 --peddy_ar 2 --plink 2 --rankvariant 2 --endvariantannotationblock 2 --qccollect_ar 2 --multiqc_ar 2 --analysisrunstatus 2 --sacct 2
 ```
 
 Thus you will always have the actual recipe names that are supported facilitating starting from any step in the analysis for instance updating qc_sample_info.yaml and rerunning some recipes, but skipping markduplicates:
 
 ```Bash
-$ mip analyse rd_dna [case_id] --config_file [mip_config_rd_dna] --split_fastq_file 2 --gzip_fastq 2 --fastqc_ar 2 --bwa_mem 2 --samtools_merge 2 --markduplicates 0 --gatk_baserecalibration 1 --chanjo_sexcheck 2 --sambamba_depth 2 --picardtools_collectmultiplemetrics 2 --picardtools_collecthsmetrics 2 --cnvnator_ar 2 --delly_call 2 --delly_reformat 2 --manta 2 --tiddit 2 --sv_combinevariantcallsets 2 --sv_varianteffectpredictor 2 --sv_vcfparser 2 --sv_rankvariant 2 --sv_reformat 2 --bcftools_mpileup 2 --gatk_haplotypecaller 2 --gatk_genotypegvcfs 2 --gatk_variantrecalibration 2 --gatk_combinevariantcallsets 2 --prepareforvariantannotationblock 2 --rhocall_ar 2 --vt_ar 2 --frequency_filter 2 --gatk_variantevalall 2 --gatk_variantevalexome 2 --varianteffectpredictor 2 --vcfparser 2 --peddy_ar 2 --plink 2 --rankvariant 2 --endvariantannotationblock 2 --qccollect_ar 2 --multiqc 2 --analysisrunstatus 2 --sacct 2
+$ mip analyse rd_dna [case_id] --config_file [mip_config_rd_dna] --split_fastq_file 2 --gzip_fastq 2 --fastqc_ar 2 --bwa_mem 2 --samtools_merge 2 --markduplicates 0 --gatk_baserecalibration 1 --chanjo_sexcheck 2 --sambamba_depth 2 --picardtools_collectmultiplemetrics 2 --picardtools_collecthsmetrics 2 --cnvnator_ar 2 --delly_call 2 --delly_reformat 2 --manta 2 --tiddit 2 --sv_combinevariantcallsets 2 --sv_varianteffectpredictor 2 --sv_vcfparser 2 --sv_rankvariant 2 --sv_reformat 2 --gatk_haplotypecaller 2 --gatk_genotypegvcfs 2 --gatk_variantrecalibration 2 --gatk_combinevariantcallsets 2 --prepareforvariantannotationblock 2 --rhocall_ar 2 --vt_ar 2 --frequency_filter 2 --gatk_variantevalall 2 --gatk_variantevalexome 2 --varianteffectpredictor 2 --vcfparser 2 --peddy_ar 2 --plink 2 --rankvariant 2 --endvariantannotationblock 2 --qccollect_ar 2 --multiqc 2 --analysisrunstatus 2 --sacct 2
 ```
 
 You can of course start or skip any number of recipes as long as it is sane to do so (MIP will not check this but just execute)
 
 ### You can also modulate the mode of '--pr' using --prm:
 ```	  
 $ mip analyse rd_dna [case_id] --config_file [mip_config_rd_dna] --pr --prm 1
-$ --split_fastq_file 1 --gzip_fastq 1 --fastqc_ar 1 --bwa_mem 1 --samtools_merge 1 --markduplicates 1 --gatk_baserecalibration 1 --chanjo_sexcheck 1 --sambamba_depth 1 --picardtools_collectmultiplemetrics 1 --picardtools_collecthsmetrics 1 --cnvnator_ar 1 --delly_call 1 --delly_reformat 1 --manta 1 --tiddit 1 --sv_combinevariantcallsets 1 --sv_varianteffectpredictor 1 --sv_vcfparser 1 --sv_rankvariant 1 --sv_reformat 1 --bcftools_mpileup 1 --gatk_haplotypecaller 1 --gatk_genotypegvcfs 1 --gatk_variantrecalibration 1 --gatk_combinevariantcallsets 1 --prepareforvariantannotationblock 1 --rhocall_ar 1 --vt_ar 1 --frequency_filter 1 --gatk_variantevalall 1 --gatk_variantevalexome 1 --varianteffectpredictor 1 --vcfparser 1 --peddy_ar 1 --plink 1 --rankvariant 1 --endvariantannotationblock 1 --qccollect_ar 1 --multiqc 1 --analysisrunstatus 1 --sacct 1
+$ --split_fastq_file 1 --gzip_fastq 1 --fastqc_ar 1 --bwa_mem 1 --samtools_merge 1 --markduplicates 1 --gatk_baserecalibration 1 --chanjo_sexcheck 1 --sambamba_depth 1 --picardtools_collectmultiplemetrics 1 --picardtools_collecthsmetrics 1 --cnvnator_ar 1 --delly_call 1 --delly_reformat 1 --manta 1 --tiddit 1 --sv_combinevariantcallsets 1 --sv_varianteffectpredictor 1 --sv_vcfparser 1 --sv_rankvariant 1 --sv_reformat 1 --gatk_haplotypecaller 1 --gatk_genotypegvcfs 1 --gatk_variantrecalibration 1 --gatk_combinevariantcallsets 1 --prepareforvariantannotationblock 1 --rhocall_ar 1 --vt_ar 1 --frequency_filter 1 --gatk_variantevalall 1 --gatk_variantevalexome 1 --varianteffectpredictor 1 --vcfparser 1 --peddy_ar 1 --plink 1 --rankvariant 1 --endvariantannotationblock 1 --qccollect_ar 1 --multiqc 1 --analysisrunstatus 1 --sacct 1
 ```
diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm b/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm
@@ -16,7 +16,7 @@ use Moose::Util::TypeConstraints;
 ## MIPs lib
 use MIP::Main::Analyse qw{ mip_analyse };
 
-our $VERSION = 1.62;
+our $VERSION = 1.63;
 
 extends(qw{ MIP::Cli::Mip::Analyse });
 
@@ -270,14 +270,6 @@ q{gatk_baserecalibration_known_sites, gatk_haplotypecaller_snp_known_set, gatk_v
         )
     );
 
-    option(
-        q{replace_iupac} => (
-            documentation => q{Replace IUPAC code in alternative alleles with N},
-            is            => q{rw},
-            isa           => Bool,
-        )
-    );
-
     option(
         q{split_fastq_file} => (
             cmd_tags      => [q{Analysis recipe switch}],
@@ -1093,42 +1085,6 @@ q{Default: hgvs, symbol, numbers, sift, polyphen, humdiv, domains, protein, ccds
         )
     );
 
-    option(
-        q{bcftools_mpileup} => (
-            cmd_tags      => [q{Analysis recipe switch}],
-            documentation => q{Variant calling using bcftools mpileup},
-            is            => q{rw},
-            isa           => enum( [ 0, 1, 2 ] ),
-        )
-    );
-
-    option(
-        q{bcftools_mpileup_constrain} => (
-            cmd_flag      => q{bcftools_mpileup_constrain},
-            documentation => q{Use contrain in trio calling},
-            is            => q{rw},
-            isa           => Bool,
-        )
-    );
-
-    option(
-        q{bcftools_mpileup_filter_variant} => (
-            cmd_flag      => q{bcftools_mpileup_fil_var},
-            documentation => q{Use standard bcftools filters},
-            is            => q{rw},
-            isa           => Bool,
-        )
-    );
-
-    option(
-        q{bcftools_mpileup_keep_unnormalised} => (
-            cmd_flag      => q{bcftools_mpileup_keep_unn},
-            documentation => q{Do not normalise variants},
-            is            => q{rw},
-            isa           => Bool,
-        )
-    );
-
     option(
         q{gatk_haplotypecaller} => (
             cmd_tags      => [q{Analysis recipe switch}],

diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_dna_panel.pm b/lib/MIP/Cli/Mip/Analyse/Rd_dna_panel.pm
@@ -271,14 +271,6 @@ q{gatk_baserecalibration_known_sites, gatk_haplotypecaller_snp_known_set, gatk_v
         )
     );
 
-    option(
-        q{replace_iupac} => (
-            documentation => q{Replace IUPAC code in alternative alleles with N},
-            is            => q{rw},
-            isa           => Bool,
-        )
-    );
-
     option(
         q{gzip_fastq} => (
             cmd_tags      => [q{Analysis recipe switch}],

diff --git a/lib/MIP/Program/Perl.pm b/lib/MIP/Program/Perl.pm