Merge 1681e6c into 9e67ba4

Clinical-Genomics · Feb 23, 2024 · c434e40 · c434e40
2 parents 9e67ba4 + 1681e6c
commit c434e40
Show file tree

Hide file tree

Showing 28 changed files with 1,282 additions and 57 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,21 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
+## [12.1.0]
+
+- Adds optional trimming of reads with Fastp for the DNA workflow, turned on by default
+- Adds automatic fail in analaysisrunstatus for cases where the peddy detects errors in the pedigree
+- Adds automatic fail in analaysisrunstatus for cases where the peddy detects a discrepancy between the given and calculated gender
+
+### Tools
+
+- Fastp: 0.23.4
+
+### Databases
+
+clinvar: 20231203 -> 20240215
+loqusdb snapshot: 20231204 -> 20240220
+
 ## [12.0.3]
 
 - Updates genmod to version 3.8.2 to introduce normalized rankscore, [#2055](https://github.com/Clinical-Genomics/MIP/issues/2055)

diff --git a/definitions/install_parameters.yaml b/definitions/install_parameters.yaml
@@ -76,6 +76,7 @@ rd_dna:
     - deeptrio
     - delly
     - expansionhunter
+    - fastp
     - fastqc
     - gatk
     - gatk4

diff --git a/definitions/rd_dna_initiation_map.yaml b/definitions/rd_dna_initiation_map.yaml
@@ -6,6 +6,7 @@ CHAIN_ALL:
   - CHAIN_FASTQ:
     - fastqc_ar
   - CHAIN_MAIN:
+    - fastp_ar
     - bwa_mem
     - bwa_mem2
     - samtools_merge

diff --git a/definitions/rd_dna_panel_parameters.yaml b/definitions/rd_dna_panel_parameters.yaml
@@ -1198,7 +1198,7 @@ qccollect_regexp_file:
   associated_recipe:
     - qccollect_ar
   data_type: SCALAR
-  default: qc_regexp_-v1.27-.yaml
+  default: qc_regexp_-v1.28-.yaml
   exists_check: file
   is_reference: 1
   reference: reference_dir

diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml
@@ -209,6 +209,7 @@ recipe_core_number:
     endvariantannotationblock: 1
     expansionhunter: 3
     fastqc_ar: 0
+    fastp_ar: 12
     variant_annotation: 13
     frequency_filter: 13
     gatk_baserecalibration: 13
@@ -345,6 +346,7 @@ recipe_time:
     endvariantannotationblock: 2
     expansionhunter: 3
     fastqc_ar: 10
+    fastp_ar: 3
     variant_annotation: 3
     frequency_filter: 2
     gatk_baserecalibration: 20
@@ -445,6 +447,48 @@ fastqc_ar:
   program_executables:
     - fastqc
   type: recipe
+## Fastp
+fastp_ar:
+  analysis_mode: sample
+  associated_recipe:
+    - mip
+  data_type: SCALAR
+  default: 1
+  file_tag: _fastp
+  outfile_suffix: ".fastq.gz"
+  program_executables:
+    - fastp
+  type: recipe
+fastp_detect_pe_adapter:
+  associated_recipe:
+    - fastp_ar
+  data_type: SCALAR
+  default: 1
+  type: recipe_argument
+fastp_length_required:
+  associated_recipe:
+    - fastp_ar
+  data_type: SCALAR
+  default: 25
+  type: recipe_argument
+fastp_low_complexity_filter:
+  associated_recipe:
+    - fastp_ar
+  data_type: SCALAR
+  default: 1
+  type: recipe_argument
+fastp_overrepresentation_analysis:
+  associated_recipe:
+    - fastp_ar
+  data_type: SCALAR
+  default: 1
+  type: recipe_argument
+fastp_trim_poly_g:
+  associated_recipe:
+    - fastp_ar
+  data_type: SCALAR
+  default: 1
+  type: recipe_argument
 ## BWA
 bwa_mem:
   analysis_mode: sample
@@ -2329,7 +2373,7 @@ qccollect_regexp_file:
   associated_recipe:
     - qccollect_ar
   data_type: SCALAR
-  default: qc_regexp_-v1.27-.yaml
+  default: qc_regexp_-v1.28-.yaml
   exists_check: file
   is_reference: 1
   reference: reference_dir

diff --git a/definitions/rd_rna_parameters.yaml b/definitions/rd_rna_parameters.yaml
@@ -1110,7 +1110,7 @@ qccollect_regexp_file:
   associated_recipe:
     - qccollect_ar
   data_type: SCALAR
-  default: qc_regexp_-v1.27-.yaml
+  default: qc_regexp_-v1.28-.yaml
   exists_check: file
   is_reference: 1
   reference: reference_dir

diff --git a/documentation/README.md b/documentation/README.md
@@ -235,4 +235,4 @@ MIP will place any generated data files in the output data directory specified b
 [Perl]:https://www.perl.org/
 [Rank model file]: https://github.com/Clinical-Genomics/MIP/blob/master/templates/rank_model_-v1.34-.ini
 [SV rank model file]: https://github.com/Clinical-Genomics/MIP/blob/master/templates/svrank_model_-v1.9-.ini
-[Qc regexp file]: https://github.com/Clinical-Genomics/MIP/blob/master/templates/qc_regexp_-v1.26-.yaml
+[Qc regexp file]: https://github.com/Clinical-Genomics/MIP/blob/master/templates/qc_regexp_-v1.28-.yaml
diff --git a/documentation/Setup.md b/documentation/Setup.md
@@ -47,6 +47,7 @@ You can speed up, for instance, the Readonly module by also installing the compa
 - [Cnvnator] (version: 0.4.1)
 - [Cyrius] (version: v1.1.1)
 - [Expansionhunter] (version 5.0.0)
+- [Fastp] (version: 0.23.4)
 - [FastQC] (version: 0.11.9)
 - [Deeptrio] (version: 1.4.0)
 - [Deepvariant] (version: 1.4.0)
@@ -181,6 +182,7 @@ Corresponding MIP references:
 [Delly]: https://github.com/dellytools/delly
 [Deepvariant]: https://github.com/google/deepvariant
 [Expansionhunter]: https://github.com/Illumina/ExpansionHunter
+[Fastp]: https://github.com/OpenGene/fastp
 [FastQC]: http://www.bioinformatics.babraham.ac.uk/projects/fastqc/
 [GATK]: http://www.broadinstitute.org/gatk/
 [GENMOD]: https://github.com/moonso/genmod/

diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm b/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm
@@ -301,6 +301,55 @@ q{gatk_baserecalibration_known_sites, gatk_haplotypecaller_snp_known_set, gatk_v
         )
     );
 
+    option(
+        q{fastp} => (
+            cmd_tags      => [q{Analysis recipe switch}],
+            documentation => q{Sequence quality trimming using FastP},
+            is            => q{rw},
+            isa           => enum( [ 0, 1, 2 ] ),
+        )
+    );
+
+    option(
+        q{fastp_detect_pe_adapter} => (
+            documentation => q{Automatically detect paired end adapters},
+            is            => q{rw},
+            isa           => Bool,
+        )
+    );
+
+    option(
+        q{fastp_length_required} => (
+            documentation => q{Required length to keep trimmed read pair},
+            is            => q{rw},
+            isa           => Int,
+        )
+    );
+
+    option(
+        q{fastp_low_complexity_filter} => (
+            documentation => q{Apply Fastp low complexity filter},
+            is            => q{rw},
+            isa           => Bool,
+        )
+    );
+
+    option(
+        q{fastp_overrepresentation_analysis} => (
+            documentation => q{Do an overrepresentation analysis on the fastq files},
+            is            => q{rw},
+            isa           => Bool,
+        )
+    );
+
+    option(
+        q{fastp_trim_poly_g} => (
+            documentation => q{Trim poly g sequences from fastq files},
+            is            => q{rw},
+            isa           => Bool,
+        )
+    );
+
     option(
         q{bwa_mem} => (
             cmd_tags      => [q{Analysis recipe switch}],
@@ -2061,7 +2110,7 @@ q{Default: hgvs, symbol, numbers, sift, polyphen, humdiv, domains, protein, ccds
 
     option(
         q{qccollect_regexp_file} => (
-            cmd_tags      => [q{Default: qc_regexp_-v1.25-.yaml}],
+            cmd_tags      => [q{Default: qc_regexp_-v1.28-.yaml}],
             documentation =>
 q{Regular expression file containing the regular expression to be used for each program},
             is  => q{rw},

diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_dna_panel.pm b/lib/MIP/Cli/Mip/Analyse/Rd_dna_panel.pm
@@ -1197,7 +1197,7 @@ q{Default: hgvs, symbol, numbers, sift, polyphen, humdiv, domains, protein, ccds
 
     option(
         q{qccollect_regexp_file} => (
-            cmd_tags      => [q{Default: qc_regexp_-v1.25-.yaml}],
+            cmd_tags      => [q{Default: qc_regexp_-v1.28-.yaml}],
             documentation =>
 q{Regular expression file containing the regular expression to be used for each program},
             is  => q{rw},

diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_rna.pm b/lib/MIP/Cli/Mip/Analyse/Rd_rna.pm
@@ -817,7 +817,7 @@ q{Default: BaseQualityRankSumTest, ChromosomeCounts, Coverage, DepthPerAlleleByS
 
     option(
         q{qccollect_regexp_file} => (
-            cmd_tags      => [q{Default: qc_regexp_-v1.25-.yaml}],
+            cmd_tags      => [q{Default: qc_regexp_-v1.28-.yaml}],
             documentation =>
 q{Regular expression file containing the regular expression to be used for each program},
             is  => q{rw},

diff --git a/lib/MIP/Cli/Mip/Install.pm b/lib/MIP/Cli/Mip/Install.pm
@@ -141,7 +141,7 @@ sub _build_usage {
                 enum(
                     [
                         qw{ arriba bedtools blobfish bootstrapann bwa bwakit bwa-mem2 cadd chanjo
-                          chromograph cnvnator cyrius deeptrio deepvariant delly expansionhunter fastqc gatk
+                          chromograph cnvnator cyrius deeptrio deepvariant delly expansionhunter fastp fastqc gatk
                           gatk4 genmod gens_preproc gffcompare glnexus hmtnote htslib manta megafusion mip mip_scripts multiqc
                           pdfmerger perl peddy picard plink preseq python retroseq rhocall rseqc rtg-tools salmon sambamba
                           smncopynumbercaller star star-fusion stranger stringtie svdb telomerecat tiddit
@@ -174,7 +174,7 @@ q{Save singularity images to sif and update run instructions for offline mip exe
                 enum(
                     [
                         qw{ arriba bedtools blobfish bootstrapann bwa bwakit bwa-mem2 cadd chanjo
-                          chromograph cnvnator cyrius deeptrio deepvariant delly expansionhunter fastqc gatk
+                          chromograph cnvnator cyrius deeptrio deepvariant delly expansionhunter fastp fastqc gatk
                           gatk4 genmod gens_preproc gffcompare glnexus hmtnote htslib manta megafusion mip mip_scripts multiqc
                           pdfmerger perl peddy picard plink preseq python retroseq rhocall rseqc rtg-tools salmon sambamba
                           smncopynumbercaller star star-fusion stranger stringtie svdb telomerecat tiddit

diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm
@@ -82,7 +82,7 @@ Readonly our %ANALYSIS => (
 );
 
 ## Set MIP version
-Readonly our $MIP_VERSION => q{12.0.3};
+Readonly our $MIP_VERSION => q{12.1.0};
 
 ## Cli
 Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160;

diff --git a/lib/MIP/Environment/Executable.pm b/lib/MIP/Environment/Executable.pm
@@ -339,6 +339,11 @@ q?'my ($version) = /Version:\s+(.*)/xms; if($version) {chomp $version;print $ver
             version_cmd    => q{--version},
             version_regexp => q?'chomp;print $_;last;'?,
         },
+        fastp => {
+            version_cmd => q{--version 2>&1 >/dev/null},
+            version_regexp =>
+              q?'my ($version) = /fastp\s(\S+)/xms; if($version) {print $version;last;}'?,
+        },
         fastqc => {
             version_cmd    => q{--version},
             version_regexp =>