From f8b0d2b5998e81fa4a0cf56db781caa3902fd4ee Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 28 Feb 2025 11:12:58 +0100
Subject: [PATCH 01/24] adding modern test
---
conf/test_modern.config | 57 +++++++++++++++++++++++++++++++++++++++++
nextflow.config | 1 +
2 files changed, 58 insertions(+)
create mode 100644 conf/test_modern.config
diff --git a/conf/test_modern.config b/conf/test_modern.config
new file mode 100644
index 00000000..53ff7f72
--- /dev/null
+++ b/conf/test_modern.config
@@ -0,0 +1,57 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/eager -profile test_modern,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+ resourceLimits = [
+ cpus: 4,
+ memory: '15.GB',
+ time: '1.h'
+ ]
+}
+
+params {
+ config_profile_name = 'Test modern profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
+ // Input data
+ // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
+ // TODO nf-core: Give any required params for the test so that command line flags are not needed
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
+
+ // Genome references
+ fasta = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
+
+
+ // Preprocessing
+ sequencing_qc_tool = 'falco'
+ preprocessing_tool = 'fastp'
+ convert_inputbam = true
+
+ // Mapping
+ mapping_tool = 'bwamem'
+
+ // BAM filtering
+ run_bamfiltering = true
+ bamfiltering_minreadlength = 30
+ bamfiltering_mappingquality = 37
+
+ // Metagenomics
+ run_metagenomics = true
+ metagenomics_complexity_tool = 'prinseq'
+ metagenomics_profiling_tool = 'kraken2'
+ metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/kraken/eager_test.tar.gz'
+ metagenomics_run_postprocessing = true
+
+ // Genotyping
+ genotyping_tool = 'hc'
+
+}
diff --git a/nextflow.config b/nextflow.config
index a5d4f694..d6cee232 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -393,6 +393,7 @@ profiles {
test_malt { includeConfig 'conf/test_malt.config' }
test_krakenuniq { includeConfig 'conf/test_krakenuniq.config'}
test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
+ test_modern { includeConfig 'conf/test_modern.config' }
}
// Load nf-core custom profiles from different Institutions
From e44842f0c048f7f90ada1fb2c78a1c18618d5322 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 28 Feb 2025 11:57:43 +0100
Subject: [PATCH 02/24] adding microbial genome test, but missing samplesheet
dsl2 to test
---
conf/test_microbial.config | 57 ++++++++++++++++++++++++++++++++++++++
conf/test_modern.config | 2 --
nextflow.config | 3 +-
3 files changed, 59 insertions(+), 3 deletions(-)
create mode 100644 conf/test_microbial.config
diff --git a/conf/test_microbial.config b/conf/test_microbial.config
new file mode 100644
index 00000000..48842532
--- /dev/null
+++ b/conf/test_microbial.config
@@ -0,0 +1,57 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/eager -profile test_microbial,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+ resourceLimits = [
+ cpus: 4,
+ memory: '15.GB',
+ time: '1.h'
+ ]
+}
+
+params {
+ config_profile_name = 'Test microbial profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
+ // Input data
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_PE_only.tsv'
+
+ // Genome references
+ fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
+
+
+ // Preprocessing
+ sequencing_qc_tool = 'falco'
+
+ // Mapping
+ mapping_tool = 'circularmapper'
+
+ // BAM filtering
+ deduplication_tool = "dedup"
+ run_bamfiltering = true
+ bamfiltering_minreadlength = 30
+ bamfiltering_mappingquality = 37
+
+ // Metagenomics
+ run_metagenomics = true
+ metagenomics_profiling_tool = 'krakenuniq'
+ metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/krakenuniq/testdb-krakenuniq.tar.gz'
+
+ // Manioulate Damage
+ run_mapdamage_rescaling = true
+ run_pmd_filtering = true
+
+ // Genotyping
+ genotyping_tool = 'freebayes'
+
+
+}
diff --git a/conf/test_modern.config b/conf/test_modern.config
index 53ff7f72..5add473c 100644
--- a/conf/test_modern.config
+++ b/conf/test_modern.config
@@ -23,8 +23,6 @@ params {
config_profile_description = 'Minimal test dataset to check pipeline function'
// Input data
- // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
- // TODO nf-core: Give any required params for the test so that command line flags are not needed
input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
// Genome references
diff --git a/nextflow.config b/nextflow.config
index d6cee232..45b23490 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -393,7 +393,8 @@ profiles {
test_malt { includeConfig 'conf/test_malt.config' }
test_krakenuniq { includeConfig 'conf/test_krakenuniq.config'}
test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
- test_modern { includeConfig 'conf/test_modern.config' }
+ test_modern { includeConfig 'conf/test_modern.config' }
+ test_microbial { includeConfig 'conf/test_microbial.config' }
}
// Load nf-core custom profiles from different Institutions
From 24cc1093620b67c91eb802deb442d799fd90f8ab Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 7 Mar 2025 10:39:50 +0100
Subject: [PATCH 03/24] adding short dna, still need the ncbi dir to be set
---
conf/test_shortdna.config | 56 +++++++++++++++++++++++++++++++++++++++
nextflow.config | 1 +
2 files changed, 57 insertions(+)
create mode 100644 conf/test_shortdna.config
diff --git a/conf/test_shortdna.config b/conf/test_shortdna.config
new file mode 100644
index 00000000..c1079fdd
--- /dev/null
+++ b/conf/test_shortdna.config
@@ -0,0 +1,56 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/eager -profile test_shortdna,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+ resourceLimits = [
+ cpus: 4,
+ memory: '15.GB',
+ time: '1.h'
+ ]
+}
+
+params {
+ config_profile_name = 'Test very short DNA profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
+ // Input data
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
+
+ // Genome references
+ fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
+
+
+ // Preprocessing
+ sequencing_qc_tool = 'falco'
+
+ // Mapping
+ // TO DO: Change when mapAD is there.
+ // mapping_tool = 'mapad'
+
+
+ // Metagenomics
+ run_metagenomics = true
+ metagenomics_complexity_tool = 'bbduk'
+ metagenomics_profiling_tool = 'malt'
+ metagenomics_profiling_database = params.pipelines_testdata_base_path + '/eager/databases/malt/eager_test.tar.gz'
+ metagenomics_run_postprocessing = true
+ metagenomics_maltextract_taxonlist = params.pipelines_testdata_base_path + '/eager/testdata/Mammoth/maltextract/MaltExtract_list.txt'
+ metagenomics_maltextract_ncbidir = 'https://github.com/rhuebler/HOPS/raw/external/Resources/'
+
+ // Manioulate Damage
+ run_pmd_filtering = true
+
+ // Genotyping
+ genotyping_tool = 'angsd'
+
+
+}
diff --git a/nextflow.config b/nextflow.config
index 45b23490..1e96ef98 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -395,6 +395,7 @@ profiles {
test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
test_modern { includeConfig 'conf/test_modern.config' }
test_microbial { includeConfig 'conf/test_microbial.config' }
+ test_shortdna { includeConfig 'conf/test_shortdna.config' }
}
// Load nf-core custom profiles from different Institutions
From ead8adaa77eb37d0cb5c15e9dd8b2e1ade42431d Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 7 Mar 2025 11:09:55 +0100
Subject: [PATCH 04/24] adding test_humanpopgen
---
conf/test_humanpopgen.config | 57 ++++++++++++++++++++++++++++++++++++
nextflow.config | 25 ++++++++--------
2 files changed, 70 insertions(+), 12 deletions(-)
create mode 100644 conf/test_humanpopgen.config
diff --git a/conf/test_humanpopgen.config b/conf/test_humanpopgen.config
new file mode 100644
index 00000000..e3a0da7f
--- /dev/null
+++ b/conf/test_humanpopgen.config
@@ -0,0 +1,57 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/eager -profile test_humanpopgen,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+ resourceLimits = [
+ cpus: 4,
+ memory: '15.GB',
+ time: '1.h'
+ ]
+}
+
+params {
+ config_profile_name = 'Test human popgen profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
+ // Input data
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
+
+ // Genome references
+ fasta = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
+
+ // Mapping
+ mapping_tool = 'bowtie2'
+
+ // BAM filtering
+ run_bamfiltering = true
+ bamfiltering_minreadlength = 30
+ bamfiltering_mappingquality = 37
+
+ // Damage
+ damagecalculation_tool = 'mapdamage'
+ run_mapdamage_rescaling = true
+ run_trim_bam = true
+
+ // Contamination
+ run_mtnucratio = true
+ run_contamination_estimation_angsd = true
+
+ // Genotyping
+ genotyping_tool = 'pileupcaller'
+ genotyping_pileupcaller_bedfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
+ genotyping_pileupcaller_snpfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K_covered_in_JK2067_downsampled_s0.1.numeric_chromosomes.snp'
+
+ //Sex Determination
+ run_sexdeterrmine = true
+ sexdeterrmine_bedfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
+
+}
diff --git a/nextflow.config b/nextflow.config
index 1e96ef98..0762b42d 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -384,18 +384,19 @@ profiles {
test_full {
includeConfig 'conf/test_full.config'
}
- test { includeConfig 'conf/test.config' }
- test_full { includeConfig 'conf/test_full.config' }
- test_nothing { includeConfig 'conf/test_nothing.config' }
- test_humanbam { includeConfig 'conf/test_humanbam.config' }
- test_multiref { includeConfig 'conf/test_multiref.config' }
- test_kraken2 { includeConfig 'conf/test_kraken2.config' }
- test_malt { includeConfig 'conf/test_malt.config' }
- test_krakenuniq { includeConfig 'conf/test_krakenuniq.config'}
- test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
- test_modern { includeConfig 'conf/test_modern.config' }
- test_microbial { includeConfig 'conf/test_microbial.config' }
- test_shortdna { includeConfig 'conf/test_shortdna.config' }
+ test { includeConfig 'conf/test.config' }
+ test_full { includeConfig 'conf/test_full.config' }
+ test_nothing { includeConfig 'conf/test_nothing.config' }
+ test_humanbam { includeConfig 'conf/test_humanbam.config' }
+ test_multiref { includeConfig 'conf/test_multiref.config' }
+ test_kraken2 { includeConfig 'conf/test_kraken2.config' }
+ test_malt { includeConfig 'conf/test_malt.config' }
+ test_krakenuniq { includeConfig 'conf/test_krakenuniq.config' }
+ test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
+ test_modern { includeConfig 'conf/test_modern.config' }
+ test_microbial { includeConfig 'conf/test_microbial.config' }
+ test_shortdna { includeConfig 'conf/test_shortdna.config' }
+ test_humanpopgen { includeConfig 'conf/test_humanpopgen.config' }
}
// Load nf-core custom profiles from different Institutions
From 66aafdf4bbe1026dc0e06ff014caeb4d78bb68aa Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 7 Mar 2025 11:33:29 +0100
Subject: [PATCH 05/24] adding test default
---
conf/test_default.config | 67 ++++++++++++++++++++++++++++++++++++++++
nextflow.config | 1 +
2 files changed, 68 insertions(+)
create mode 100644 conf/test_default.config
diff --git a/conf/test_default.config b/conf/test_default.config
new file mode 100644
index 00000000..39a141ea
--- /dev/null
+++ b/conf/test_default.config
@@ -0,0 +1,67 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/eager -profile test_default,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+ resourceLimits = [
+ cpus: 4,
+ memory: '15.GB',
+ time: '1.h'
+ ]
+}
+
+// TO DO: Change name to test.config once migration is complete.
+params {
+ config_profile_name = 'Test profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
+ // Input data
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
+
+ // Genome references
+ fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
+
+ // Preprocessing
+ preprocessing_tool = 'adapterremoval'
+
+ // Sharding FASTQ
+ run_fastq_sharding = true
+ fastq_shard_size = 5000
+
+ // Mapping
+ mapping_tool = 'bwaaln'
+ skip_qualimap = false
+
+ // BAM filtering
+ run_bamfiltering = true
+ bamfiltering_minreadlength = 30
+ bamfiltering_mappingquality = 37
+ deduplication_tool = 'markduplicates'
+
+ // PreSeq
+ mapstats_preseq_mode = 'c_curve'
+
+ // Damage calculation
+ damagecalculation_tool = 'damageprofiler'
+
+ // Genotyping
+ genotyping_tool = 'ug'
+
+ // Map Stats
+ run_bedtools_coverage = true
+ mapstats_bedtools_featurefile = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.gff3'
+
+ // Metagenomic screening
+ run_metagenomics = true
+ metagenomics_profiling_tool = 'metaphlan'
+ metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/metaphlan/metaphlan4_database.tar.gz'
+ metagenomics_run_postprocessing = true
+}
diff --git a/nextflow.config b/nextflow.config
index 0762b42d..1d565018 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -393,6 +393,7 @@ profiles {
test_malt { includeConfig 'conf/test_malt.config' }
test_krakenuniq { includeConfig 'conf/test_krakenuniq.config' }
test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
+ test_default { includeConfig 'conf/test_default.config' }
test_modern { includeConfig 'conf/test_modern.config' }
test_microbial { includeConfig 'conf/test_microbial.config' }
test_shortdna { includeConfig 'conf/test_shortdna.config' }
From 2689873ed3ef43f8760e6d489d6bca4af5c1ab24 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 7 Mar 2025 11:59:33 +0100
Subject: [PATCH 06/24] minor updates
---
conf/test_default.config | 4 ----
conf/test_humanpopgen.config | 2 +-
conf/test_microbial.config | 4 ++--
conf/test_modern.config | 5 -----
conf/test_shortdna.config | 5 -----
5 files changed, 3 insertions(+), 17 deletions(-)
diff --git a/conf/test_default.config b/conf/test_default.config
index 39a141ea..fbd211c5 100644
--- a/conf/test_default.config
+++ b/conf/test_default.config
@@ -55,10 +55,6 @@ params {
// Genotyping
genotyping_tool = 'ug'
- // Map Stats
- run_bedtools_coverage = true
- mapstats_bedtools_featurefile = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.gff3'
-
// Metagenomic screening
run_metagenomics = true
metagenomics_profiling_tool = 'metaphlan'
diff --git a/conf/test_humanpopgen.config b/conf/test_humanpopgen.config
index e3a0da7f..da2efa16 100644
--- a/conf/test_humanpopgen.config
+++ b/conf/test_humanpopgen.config
@@ -30,6 +30,7 @@ params {
// Mapping
mapping_tool = 'bowtie2'
+ convert_inputbam = true
// BAM filtering
run_bamfiltering = true
@@ -38,7 +39,6 @@ params {
// Damage
damagecalculation_tool = 'mapdamage'
- run_mapdamage_rescaling = true
run_trim_bam = true
// Contamination
diff --git a/conf/test_microbial.config b/conf/test_microbial.config
index 48842532..0c25d5d5 100644
--- a/conf/test_microbial.config
+++ b/conf/test_microbial.config
@@ -45,10 +45,10 @@ params {
run_metagenomics = true
metagenomics_profiling_tool = 'krakenuniq'
metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/krakenuniq/testdb-krakenuniq.tar.gz'
+ run_host_removal = true
- // Manioulate Damage
+ // Manipulate Damage
run_mapdamage_rescaling = true
- run_pmd_filtering = true
// Genotyping
genotyping_tool = 'freebayes'
diff --git a/conf/test_modern.config b/conf/test_modern.config
index 5add473c..beee31c3 100644
--- a/conf/test_modern.config
+++ b/conf/test_modern.config
@@ -37,11 +37,6 @@ params {
// Mapping
mapping_tool = 'bwamem'
- // BAM filtering
- run_bamfiltering = true
- bamfiltering_minreadlength = 30
- bamfiltering_mappingquality = 37
-
// Metagenomics
run_metagenomics = true
metagenomics_complexity_tool = 'prinseq'
diff --git a/conf/test_shortdna.config b/conf/test_shortdna.config
index c1079fdd..672cb7f3 100644
--- a/conf/test_shortdna.config
+++ b/conf/test_shortdna.config
@@ -28,15 +28,10 @@ params {
// Genome references
fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
-
- // Preprocessing
- sequencing_qc_tool = 'falco'
-
// Mapping
// TO DO: Change when mapAD is there.
// mapping_tool = 'mapad'
-
// Metagenomics
run_metagenomics = true
metagenomics_complexity_tool = 'bbduk'
From 981cd92d51108f49024a11934aff6016a798bfc5 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 14 Mar 2025 11:57:57 +0100
Subject: [PATCH 07/24] finnished v1 test configs
---
conf/test_default.config | 1 +
conf/test_humanpopgen.config | 5 +++++
subworkflows/local/utils_nfcore_eager_pipeline/main.nf | 2 +-
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/conf/test_default.config b/conf/test_default.config
index fbd211c5..a7403317 100644
--- a/conf/test_default.config
+++ b/conf/test_default.config
@@ -51,6 +51,7 @@ params {
// Damage calculation
damagecalculation_tool = 'damageprofiler'
+ skip_qualimap = false
// Genotyping
genotyping_tool = 'ug'
diff --git a/conf/test_humanpopgen.config b/conf/test_humanpopgen.config
index da2efa16..bd55ae97 100644
--- a/conf/test_humanpopgen.config
+++ b/conf/test_humanpopgen.config
@@ -16,6 +16,11 @@ process {
memory: '15.GB',
time: '1.h'
]
+
+ // To avoid pipeline failure due to not having X reads and to not have overcrowded datasets in the test
+ withName: ANGSD_CONTAMINATION {
+ errorStrategy = { task.exitStatus in [134] ? 'ignore' : 'finish' }
+ }
}
params {
diff --git a/subworkflows/local/utils_nfcore_eager_pipeline/main.nf b/subworkflows/local/utils_nfcore_eager_pipeline/main.nf
index 0fcf7be6..5cfe596f 100644
--- a/subworkflows/local/utils_nfcore_eager_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_eager_pipeline/main.nf
@@ -215,7 +215,7 @@ def validateInputParameters() {
if ( !params.fasta && !params.fasta_sheet ) { exit 1, "[nf-core/eager] ERROR: Neither FASTA file --fasta nor reference sheet --fasta_sheet have been provided."}
if ( params.fasta && params.fasta_sheet ) { exit 1, "[nf-core/eager] ERROR: A FASTA file --fasta and a reference sheet --fasta_sheet have been provided. These parameters are mutually exclusive."}
if ( params.preprocessing_adapterlist && params.preprocessing_skipadaptertrim ) { log.warn("[nf-core/eager] WARNING: --preprocessing_skipadaptertrim will override --preprocessing_adapterlist. Adapter trimming will be skipped!") }
- if ( params.deduplication_tool == 'dedup' && ! params.preprocessing_excludeunmerged ) { exit 1, "[nf-core/eager] ERROR: Dedup can only be used on collapsed (i.e. merged) PE reads. For all other cases, please set --deduplication_tool to 'markduplicates'."}
+ if ( params.deduplication_tool == 'dedup' && ! params.preprocessing_excludeunmerged ) { exit 1, "[nf-core/eager] ERROR: Dedup can only be used on collapsed (i.e. merged) PE reads without singletons. If you want to use Dedup, please provide --preprocessing_excludeunmerged. For all other cases, please set --deduplication_tool to 'markduplicates'."}
if ( params.bamfiltering_retainunmappedgenomicbam && params.bamfiltering_mappingquality > 0 ) { exit 1, ("[nf-core/eager] ERROR: You cannot both retain unmapped reads and perform quality filtering, as unmapped reads have a mapping quality of 0. Pick one or the other functionality.") }
if ( params.genotyping_source == 'trimmed' && ! params.run_trim_bam ) { exit 1, ("[nf-core/eager] ERROR: --genotyping_source cannot be 'trimmed' unless BAM trimming is turned on with `--run_trim_bam`.") }
if ( params.genotyping_source == 'pmd' && ! params.run_pmd_filtering ) { exit 1, ("[nf-core/eager] ERROR: --genotyping_source cannot be 'pmd' unless PMD-filtering is ran.") }
From 3597d6f441569c07e031bf90d2e46d61dd279c80 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 14 Mar 2025 11:58:50 +0100
Subject: [PATCH 08/24] finnished but error with mapDamage --rescale. Mixing
different references
---
conf/test_microbial.config | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/conf/test_microbial.config b/conf/test_microbial.config
index 0c25d5d5..269c4fc7 100644
--- a/conf/test_microbial.config
+++ b/conf/test_microbial.config
@@ -23,7 +23,7 @@ params {
config_profile_description = 'Minimal test dataset to check pipeline function'
// Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_PE_only.tsv'
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_PE_only_v3.tsv'
// Genome references
fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
@@ -31,6 +31,7 @@ params {
// Preprocessing
sequencing_qc_tool = 'falco'
+ preprocessing_excludeunmerged = true
// Mapping
mapping_tool = 'circularmapper'
From 67bde36da42d0ad3191e99476672a02e569a4200 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Mon, 24 Mar 2025 14:14:39 +0100
Subject: [PATCH 09/24] removing old profiles
---
conf/test_default.config | 64 -------------------------------------
conf/test_humanbam.config | 55 -------------------------------
conf/test_kraken2.config | 35 --------------------
conf/test_krakenuniq.config | 36 ---------------------
conf/test_malt.config | 36 ---------------------
conf/test_metaphlan.config | 37 ---------------------
conf/test_multiref.config | 39 ----------------------
conf/test_nothing.config | 48 ----------------------------
8 files changed, 350 deletions(-)
delete mode 100644 conf/test_default.config
delete mode 100644 conf/test_humanbam.config
delete mode 100644 conf/test_kraken2.config
delete mode 100644 conf/test_krakenuniq.config
delete mode 100644 conf/test_malt.config
delete mode 100644 conf/test_metaphlan.config
delete mode 100644 conf/test_multiref.config
delete mode 100644 conf/test_nothing.config
diff --git a/conf/test_default.config b/conf/test_default.config
deleted file mode 100644
index a7403317..00000000
--- a/conf/test_default.config
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_default,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-// TO DO: Change name to test.config once migration is complete.
-params {
- config_profile_name = 'Test profile'
- config_profile_description = 'Minimal test dataset to check pipeline function'
-
- // Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
-
- // Preprocessing
- preprocessing_tool = 'adapterremoval'
-
- // Sharding FASTQ
- run_fastq_sharding = true
- fastq_shard_size = 5000
-
- // Mapping
- mapping_tool = 'bwaaln'
- skip_qualimap = false
-
- // BAM filtering
- run_bamfiltering = true
- bamfiltering_minreadlength = 30
- bamfiltering_mappingquality = 37
- deduplication_tool = 'markduplicates'
-
- // PreSeq
- mapstats_preseq_mode = 'c_curve'
-
- // Damage calculation
- damagecalculation_tool = 'damageprofiler'
- skip_qualimap = false
-
- // Genotyping
- genotyping_tool = 'ug'
-
- // Metagenomic screening
- run_metagenomics = true
- metagenomics_profiling_tool = 'metaphlan'
- metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/metaphlan/metaphlan4_database.tar.gz'
- metagenomics_run_postprocessing = true
-}
diff --git a/conf/test_humanbam.config b/conf/test_humanbam.config
deleted file mode 100644
index 21c35179..00000000
--- a/conf/test_humanbam.config
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_tsv_humanbam,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-params {
- config_profile_name = 'Human BAM test profile'
- config_profile_description = 'Minimal test dataset to check pipeline function'
-
- // Input data
- // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
- // TODO nf-core: Give any required params for the test so that command line flags are not needed
- input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
-
- // Contamination estimation
- contamination_estimation_angsd_mapq = 0
- contamination_estimation_angsd_minq = 0
-
- // Qualimap
- snpcapture_bed = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
-
- // TODO Reactivate sexDet and genotyping params when those steps get implemented.
- // //Sex Determination
- sexdeterrmine_bedfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
- // // Genotyping
- genotyping_pileupcaller_bedfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
- genotyping_pileupcaller_snpfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K_covered_in_JK2067_downsampled_s0.1.numeric_chromosomes.snp'
-
-
- // BAM filtering
- run_bamfiltering = true
- bamfiltering_minreadlength = 30
- bamfiltering_mappingquality = 37
-
- // Metagenomic screening
- run_metagenomics = false
-}
diff --git a/conf/test_kraken2.config b/conf/test_kraken2.config
deleted file mode 100644
index b976d179..00000000
--- a/conf/test_kraken2.config
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test for
- metagenomics krakenuniq.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_krakenuniq,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-params {
- config_profile_name = 'Kraken2 test profile'
- config_profile_description = 'Minimal test dataset to check the metagenomics kraken2 pipeline function'
-
- // Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
-
- // Metagenomics
- run_metagenomics = true
- metagenomics_profiling_tool = 'kraken2'
- metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/kraken/eager_test.tar.gz'
-}
diff --git a/conf/test_krakenuniq.config b/conf/test_krakenuniq.config
deleted file mode 100644
index 5b25c1d6..00000000
--- a/conf/test_krakenuniq.config
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test for
- metagenomics krakenuniq.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_krakenuniq,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-params {
- config_profile_name = 'KrakenUniq test profile'
- config_profile_description = 'Minimal test dataset to check the metagenomics krakenuniq pipeline function'
-
- // Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
-
- // Metagenomics
- run_metagenomics = true
- metagenomics_profiling_tool = 'krakenuniq'
- metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/krakenuniq/testdb-krakenuniq.tar.gz'
-}
diff --git a/conf/test_malt.config b/conf/test_malt.config
deleted file mode 100644
index 43b905cc..00000000
--- a/conf/test_malt.config
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test for
- metagenomics malt.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_malt,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-params {
- config_profile_name = 'MALT test profile'
- config_profile_description = 'Minimal test dataset to check the metagenomics MALT pipeline function'
-
- // Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
-
- // Metagenomics
- run_metagenomics = true
- metagenomics_profiling_tool = 'malt'
- metagenomics_profiling_database = params.pipelines_testdata_base_path + '/eager/databases/malt/eager_test.tar.gz'
-}
diff --git a/conf/test_metaphlan.config b/conf/test_metaphlan.config
deleted file mode 100644
index 85343cb7..00000000
--- a/conf/test_metaphlan.config
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test for
- metagenomics krakenuniq.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_krakenuniq,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-params {
- config_profile_name = 'MetaPhlAn4 test profile'
- config_profile_description = 'Minimal test dataset to check the metagenomics metaphlan4 pipeline function'
-
- // Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
-
- // Metagenomics
- run_metagenomics = true
- metagenomics_profiling_tool = 'metaphlan'
- metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/metaphlan/metaphlan4_database.tar.gz'
- metagenomics_run_postprocessing = true
-}
diff --git a/conf/test_multiref.config b/conf/test_multiref.config
deleted file mode 100644
index 6917a1a6..00000000
--- a/conf/test_multiref.config
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test.
-
- Use as follows:
- fasta_sheet = 'https://github.com/nf-core/test-datasets/raw/eager/reference/reference_sheet_multiref.csv'
- nextflow run nf-core/eager -profile test_multiref,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-params {
- config_profile_name = 'Test profile'
- config_profile_description = 'Minimal test dataset to check pipeline function'
-
- // Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_multilane_multilib.tsv'
-
- // Genome references
- fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
-
- // BAM filtering
- run_bamfiltering = true
- bamfiltering_minreadlength = 30
- bamfiltering_mappingquality = 37
-
- // Metagenomics
- run_metagenomics = false
-}
diff --git a/conf/test_nothing.config b/conf/test_nothing.config
deleted file mode 100644
index a16745b6..00000000
--- a/conf/test_nothing.config
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Nextflow config file for running minimal tests
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Defines input files and everything required to run a fast and simple pipeline test.
-
- Use as follows:
- nextflow run nf-core/eager -profile test_nothing,<docker/singularity> --outdir <OUTDIR>
-
-----------------------------------------------------------------------------------------
-*/
-
-process {
- resourceLimits = [
- cpus: 4,
- memory: '15.GB',
- time: '1.h'
- ]
-}
-
-params {
- config_profile_name = 'Test profile'
- config_profile_description = 'Minimal test dataset to check pipeline function'
-
- // Input data
- // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
- // TODO nf-core: Give any required params for the test so that command line flags are not needed
- input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
-
- // Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
-
- skip_preprocessing = true
- skip_deduplication = true
- skip_qualimap = true
- skip_damagecalculation = true
- mapstats_skip_preseq = true
-
- run_fastq_sharding = false
- run_bamfiltering = false
- run_bedtools_coverage = false
- run_metagenomics = false
- run_contamination_estimation_angsd = false
- run_mtnucratio = false
- run_mapdamage_rescaling = false
- run_pmd_filtering = false
- run_trim_bam = false
-}
From 56a3ab51dc7687ca4347b5baa604cb21e746d405 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Mon, 24 Mar 2025 14:50:15 +0100
Subject: [PATCH 10/24] replacing test.config
---
conf/test.config | 50 ++++++++++++++++++++++++++++++++----------------
1 file changed, 34 insertions(+), 16 deletions(-)
diff --git a/conf/test.config b/conf/test.config
index e358134a..b9f6b7eb 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -5,7 +5,7 @@
Defines input files and everything required to run a fast and simple pipeline test.
Use as follows:
- nextflow run nf-core/eager -profile test,<docker/singularity> --outdir <OUTDIR>
+ nextflow run nf-core/eager -profile test_default,<docker/singularity> --outdir <OUTDIR>
----------------------------------------------------------------------------------------
*/
@@ -18,31 +18,49 @@ process {
]
}
+// TO DO: Change name to test.config once migration is complete.
params {
- config_profile_name = 'Test profile'
- config_profile_description = 'Minimal test dataset to check pipeline function'
+ config_profile_name = 'Test profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
// Input data
- // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
- // TODO nf-core: Give any required params for the test so that command line flags are not needed
- input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
// Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
+ fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
+
+ // Preprocessing
+ preprocessing_tool = 'adapterremoval'
// Sharding FASTQ
- run_fastq_sharding = true
- fastq_shard_size = 5000
+ run_fastq_sharding = true
+ fastq_shard_size = 5000
+
+ // Mapping
+ mapping_tool = 'bwaaln'
+ skip_qualimap = false
// BAM filtering
- run_bamfiltering = true
- bamfiltering_minreadlength = 30
- bamfiltering_mappingquality = 37
+ run_bamfiltering = true
+ bamfiltering_minreadlength = 30
+ bamfiltering_mappingquality = 37
+ deduplication_tool = 'markduplicates'
+
+ // PreSeq
+ mapstats_preseq_mode = 'c_curve'
+
+ // Damage calculation
+ damagecalculation_tool = 'damageprofiler'
+ skip_qualimap = false
- // Map Stats
- run_bedtools_coverage = true
- mapstats_bedtools_featurefile = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.gff3'
+ // Genotyping
+ run_genotyping = true
+ genotyping_source = 'raw'
+ genotyping_tool = 'ug'
// Metagenomic screening
- run_metagenomics = false
+ run_metagenomics = true
+ metagenomics_profiling_tool = 'metaphlan'
+ metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/metaphlan/metaphlan4_database.tar.gz'
+ metagenomics_run_postprocessing = true
}
From ff452d91a85e09bb7678f5c07204391f3cd53946 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Mon, 24 Mar 2025 14:50:32 +0100
Subject: [PATCH 11/24] replacing nothing to minimal
---
conf/test_minimal.config | 48 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 48 insertions(+)
create mode 100644 conf/test_minimal.config
diff --git a/conf/test_minimal.config b/conf/test_minimal.config
new file mode 100644
index 00000000..a16745b6
--- /dev/null
+++ b/conf/test_minimal.config
@@ -0,0 +1,48 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/eager -profile test_nothing,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+ resourceLimits = [
+ cpus: 4,
+ memory: '15.GB',
+ time: '1.h'
+ ]
+}
+
+params {
+ config_profile_name = 'Test profile'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
+ // Input data
+ // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
+ // TODO nf-core: Give any required params for the test so that command line flags are not needed
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
+
+ // Genome references
+ fasta = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
+
+ skip_preprocessing = true
+ skip_deduplication = true
+ skip_qualimap = true
+ skip_damagecalculation = true
+ mapstats_skip_preseq = true
+
+ run_fastq_sharding = false
+ run_bamfiltering = false
+ run_bedtools_coverage = false
+ run_metagenomics = false
+ run_contamination_estimation_angsd = false
+ run_mtnucratio = false
+ run_mapdamage_rescaling = false
+ run_pmd_filtering = false
+ run_trim_bam = false
+}
From dd12a5b7aa3788fa4bbd92cf9ef17a66946eed2e Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Mon, 24 Mar 2025 14:50:47 +0100
Subject: [PATCH 12/24] adding genotyping source
---
conf/test_humanpopgen.config | 2 ++
conf/test_microbial.config | 7 +++++++
conf/test_modern.config | 2 ++
conf/test_shortdna.config | 2 ++
4 files changed, 13 insertions(+)
diff --git a/conf/test_humanpopgen.config b/conf/test_humanpopgen.config
index bd55ae97..9368bdc6 100644
--- a/conf/test_humanpopgen.config
+++ b/conf/test_humanpopgen.config
@@ -52,6 +52,8 @@ params {
// Genotyping
genotyping_tool = 'pileupcaller'
+ run_genotyping = true
+ genotyping_source = 'trimmed'
genotyping_pileupcaller_bedfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
genotyping_pileupcaller_snpfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K_covered_in_JK2067_downsampled_s0.1.numeric_chromosomes.snp'
diff --git a/conf/test_microbial.config b/conf/test_microbial.config
index 269c4fc7..dd9eec06 100644
--- a/conf/test_microbial.config
+++ b/conf/test_microbial.config
@@ -28,6 +28,8 @@ params {
// Genome references
fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
+ // Host Removal
+ run_host_removal = true
// Preprocessing
sequencing_qc_tool = 'falco'
@@ -51,7 +53,12 @@ params {
// Manipulate Damage
run_mapdamage_rescaling = true
+ // Bedtools coverage
+ run_bedtools_coverage = true
+
// Genotyping
+ run_genotyping = true
+ genotyping_source = 'rescaled'
genotyping_tool = 'freebayes'
diff --git a/conf/test_modern.config b/conf/test_modern.config
index beee31c3..3494098b 100644
--- a/conf/test_modern.config
+++ b/conf/test_modern.config
@@ -45,6 +45,8 @@ params {
metagenomics_run_postprocessing = true
// Genotyping
+ run_genotyping = true
+ genotyping_source = 'raw'
genotyping_tool = 'hc'
}
diff --git a/conf/test_shortdna.config b/conf/test_shortdna.config
index 672cb7f3..2a1af8de 100644
--- a/conf/test_shortdna.config
+++ b/conf/test_shortdna.config
@@ -45,6 +45,8 @@ params {
run_pmd_filtering = true
// Genotyping
+ run_genotyping = true
+ genotyping_source = 'pmd'
genotyping_tool = 'angsd'
From 2c0bb13a59fd26b548c2c812acf4b631400a33b4 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Mon, 24 Mar 2025 14:58:53 +0100
Subject: [PATCH 13/24] update nextflow.config
---
nextflow.config | 9 +--------
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/nextflow.config b/nextflow.config
index 1d565018..d63a9fb3 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -386,14 +386,7 @@ profiles {
}
test { includeConfig 'conf/test.config' }
test_full { includeConfig 'conf/test_full.config' }
- test_nothing { includeConfig 'conf/test_nothing.config' }
- test_humanbam { includeConfig 'conf/test_humanbam.config' }
- test_multiref { includeConfig 'conf/test_multiref.config' }
- test_kraken2 { includeConfig 'conf/test_kraken2.config' }
- test_malt { includeConfig 'conf/test_malt.config' }
- test_krakenuniq { includeConfig 'conf/test_krakenuniq.config' }
- test_metaphlan { includeConfig 'conf/test_metaphlan.config' }
- test_default { includeConfig 'conf/test_default.config' }
+ test_minimal { includeConfig 'conf/test_minimal.config' }
test_modern { includeConfig 'conf/test_modern.config' }
test_microbial { includeConfig 'conf/test_microbial.config' }
test_shortdna { includeConfig 'conf/test_shortdna.config' }
From 57809e50a6d1f358c9262497dd721287830f37a8 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Tue, 25 Mar 2025 08:04:23 +0100
Subject: [PATCH 14/24] Update conf/test.config
---
conf/test.config | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/conf/test.config b/conf/test.config
index b9f6b7eb..e5d5c7eb 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -5,7 +5,7 @@
Defines input files and everything required to run a fast and simple pipeline test.
Use as follows:
- nextflow run nf-core/eager -profile test_default,<docker/singularity> --outdir <OUTDIR>
+ nextflow run nf-core/eager -profile test,<docker/singularity> --outdir <OUTDIR>
----------------------------------------------------------------------------------------
*/
From 636e5d550182daf567c04a407df8d9f40a254298 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Tue, 25 Mar 2025 08:05:23 +0100
Subject: [PATCH 15/24] Update conf/test.config
---
conf/test.config | 1 -
1 file changed, 1 deletion(-)
diff --git a/conf/test.config b/conf/test.config
index e5d5c7eb..81ec0bb9 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -18,7 +18,6 @@ process {
]
}
-// TO DO: Change name to test.config once migration is complete.
params {
config_profile_name = 'Test profile'
config_profile_description = 'Minimal test dataset to check pipeline function'
From b08e6ac5835643e36d24935690955d08063dc006 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Tue, 25 Mar 2025 08:45:22 +0000
Subject: [PATCH 16/24] Move kraken2 to humanpopgen
---
conf/test_humanpopgen.config | 12 +++++++++---
conf/test_modern.config | 12 ++----------
2 files changed, 11 insertions(+), 13 deletions(-)
diff --git a/conf/test_humanpopgen.config b/conf/test_humanpopgen.config
index 9368bdc6..11605769 100644
--- a/conf/test_humanpopgen.config
+++ b/conf/test_humanpopgen.config
@@ -14,12 +14,12 @@ process {
resourceLimits = [
cpus: 4,
memory: '15.GB',
- time: '1.h'
+ time: '1.h',
]
// To avoid pipeline failure due to not having X reads and to not have overcrowded datasets in the test
withName: ANGSD_CONTAMINATION {
- errorStrategy = { task.exitStatus in [134] ? 'ignore' : 'finish' }
+ errorStrategy = { task.exitStatus in [134] ? 'ignore' : 'finish' }
}
}
@@ -35,7 +35,7 @@ params {
// Mapping
mapping_tool = 'bowtie2'
- convert_inputbam = true
+ convert_inputbam = true
// BAM filtering
run_bamfiltering = true
@@ -61,4 +61,10 @@ params {
run_sexdeterrmine = true
sexdeterrmine_bedfile = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
+ // Metagenomics
+ run_metagenomics = true
+ metagenomics_complexity_tool = 'prinseq'
+ metagenomics_profiling_tool = 'kraken2'
+ metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/kraken/eager_test.tar.gz'
+ metagenomics_run_postprocessing = true
}
diff --git a/conf/test_modern.config b/conf/test_modern.config
index 3494098b..f958dd69 100644
--- a/conf/test_modern.config
+++ b/conf/test_modern.config
@@ -14,7 +14,7 @@ process {
resourceLimits = [
cpus: 4,
memory: '15.GB',
- time: '1.h'
+ time: '1.h',
]
}
@@ -32,21 +32,13 @@ params {
// Preprocessing
sequencing_qc_tool = 'falco'
preprocessing_tool = 'fastp'
- convert_inputbam = true
+ convert_inputbam = false
// Mapping
mapping_tool = 'bwamem'
- // Metagenomics
- run_metagenomics = true
- metagenomics_complexity_tool = 'prinseq'
- metagenomics_profiling_tool = 'kraken2'
- metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/kraken/eager_test.tar.gz'
- metagenomics_run_postprocessing = true
-
// Genotyping
run_genotyping = true
genotyping_source = 'raw'
genotyping_tool = 'hc'
-
}
From ccf180ca34b58acd99c3a75089b2334a4c488767 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Tue, 25 Mar 2025 10:26:12 +0100
Subject: [PATCH 17/24] removing fastp
---
conf/test_microbial.config | 1 +
1 file changed, 1 insertion(+)
diff --git a/conf/test_microbial.config b/conf/test_microbial.config
index dd9eec06..27fbb4a6 100644
--- a/conf/test_microbial.config
+++ b/conf/test_microbial.config
@@ -33,6 +33,7 @@ params {
// Preprocessing
sequencing_qc_tool = 'falco'
+ preprocessing_tool = 'fastp'
preprocessing_excludeunmerged = true
// Mapping
From b1bba769dc52f7a8f3c3b595db9050eb34b479bd Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Tue, 25 Mar 2025 10:26:38 +0100
Subject: [PATCH 18/24] adding fastp and changing input and fasta
---
conf/test_modern.config | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/conf/test_modern.config b/conf/test_modern.config
index f958dd69..84b6923e 100644
--- a/conf/test_modern.config
+++ b/conf/test_modern.config
@@ -23,15 +23,14 @@ params {
config_profile_description = 'Minimal test dataset to check pipeline function'
// Input data
- input = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
+ input = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/mammooth_design_bam_v3.tsv'
// Genome references
- fasta = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
+ fasta = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
// Preprocessing
sequencing_qc_tool = 'falco'
- preprocessing_tool = 'fastp'
convert_inputbam = false
// Mapping
From 52df92bb34c44ca490899113eafaeaf9c3a06b9a Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Tue, 25 Mar 2025 11:33:33 +0100
Subject: [PATCH 19/24] excluding fasta
---
subworkflows/local/genotype.nf | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/subworkflows/local/genotype.nf b/subworkflows/local/genotype.nf
index a674bf85..fc5a723b 100644
--- a/subworkflows/local/genotype.nf
+++ b/subworkflows/local/genotype.nf
@@ -393,17 +393,17 @@ workflow GENOTYPE {
addNewMetaFromAttributes( it, "id" , "reference" , false )
} // RESULT: [ [combination_meta], [ref_meta], fasta, fai, dict, dbsnp ]
+ // TO DO: Module fails if we don't give the fai but the fasta. However is not specified atm. Re-add fasta once this issue is solved.
ch_input_for_angsd = ch_bams_for_multimap
.combine( ch_fasta_for_multimap , by:0 )
.multiMap {
ignore_me, meta, bam, bai, ref_meta, fasta, fai, dict, dbsnp ->
bam: [ meta, bam ]
- fasta: [ ref_meta, fasta ]
}
ANGSD_GL(
ch_input_for_angsd.bam,
- ch_input_for_angsd.fasta,
+ [[], []], // No fasta file
[[], []], // No errors file
)
ch_angsd_genotype_likelihoods = ANGSD_GL.out.genotype_likelihood
From 22433a9a08bf9f5caa82fba76d050f01a703a7a0 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Tue, 25 Mar 2025 14:11:44 +0000
Subject: [PATCH 20/24] Deactivate rescaling, fix freebayes problem
---
conf/modules.config | 825 +++++++++++-------------
conf/test_microbial.config | 11 +-
subworkflows/local/manipulate_damage.nf | 248 ++++---
workflows/eager.nf | 18 +-
4 files changed, 502 insertions(+), 600 deletions(-)
diff --git a/conf/modules.config b/conf/modules.config
index daf87aee..c102e4b9 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -15,15 +15,15 @@ process {
publishDir = [
path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
mode: params.publish_dir_mode,
- saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
]
- withName: 'MULTIQC' {
- ext.args = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
+ withName: MULTIQC {
+ ext.args = { params.multiqc_title ? "--title \"${params.multiqc_title}\"" : '' }
publishDir = [
path: { "${params.outdir}/multiqc" },
mode: params.publish_dir_mode,
- saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
]
}
@@ -31,7 +31,7 @@ process {
// CONVERT INPUT BAM
//
withName: SAMTOOLS_CONVERT_BAM_INPUT {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
enabled: false
@@ -39,7 +39,7 @@ process {
}
withName: CAT_FASTQ_CONVERTED_BAM {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
enabled: false
@@ -50,12 +50,11 @@ process {
// READ PREPROCESSING
//
withName: FASTQC {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = '--quiet'
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = '--quiet'
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/preprocessing/fastqc_raw/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -64,12 +63,11 @@ process {
}
withName: FASTQC_PROCESSED {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = '--quiet'
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = '--quiet'
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/preprocessing/fastqc_processed/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -78,12 +76,11 @@ process {
}
withName: FALCO {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = '--quiet'
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = '--quiet'
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/preprocessing/falco_raw/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -92,12 +89,11 @@ process {
}
withName: FALCO_PROCESSED {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = '--quiet'
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = '--quiet'
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/preprocessing/falco_processed/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -106,71 +102,61 @@ process {
}
withName: FASTP_SINGLE {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.args = [
- // TRIMMING OPTIONS
params.preprocessing_trim5p != 0 ? "--trim_front1 ${params.preprocessing_trim5p}" : "",
params.preprocessing_trim3p != 0 ? "--trim_tail1 ${params.preprocessing_trim3p}" : "",
- params.preprocessing_skipadaptertrim ? "--disable_adapter_trimming" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter_sequence ${params.preprocessing_adapter1}" : "", // adding adapter list happens at module input channel level
- // FILTERING OPTIONS
+ params.preprocessing_skipadaptertrim ? "--disable_adapter_trimming" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter_sequence ${params.preprocessing_adapter1}" : "",
"--length_required ${params.preprocessing_minlength}",
- params.preprocessing_fastp_complexityfilter ? "--low_complexity_filter --complexity_threshold ${params.preprocessing_fastp_complexityfilter_threshold}" : ""
+ params.preprocessing_fastp_complexityfilter ? "--low_complexity_filter --complexity_threshold ${params.preprocessing_fastp_complexityfilter_threshold}" : "",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // data
path: { "${params.outdir}/preprocessing/fastp/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.preprocessing_savepreprocessedreads
+ enabled: params.preprocessing_savepreprocessedreads,
],
[
- //stats
path: { "${params.outdir}/preprocessing/fastp/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.{log,html,json}'
- ]
+ pattern: '*.{log,html,json}',
+ ],
]
}
withName: FASTP_PAIRED {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.args = [
- // COLLAPSING OPTIONS - option to retain singletons
params.preprocessing_excludeunmerged ? "" : "--include_unmerged",
- // TRIMMING OPTIONS
params.preprocessing_trim5p != 0 ? "--trim_front1 ${params.preprocessing_trim5p} --trim_front2 ${params.preprocessing_trim5p}" : "",
params.preprocessing_trim3p != 0 ? "--trim_tail1 ${params.preprocessing_trim3p} --trim_tail2 ${params.preprocessing_trim3p}" : "",
- params.preprocessing_skipadaptertrim ? "--disable_adapter_trimming" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter_sequence ${params.preprocessing_adapter1}" : "", // adding adapter list happens at module input channel level
- params.preprocessing_skipadaptertrim ? "" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter2 ? "--adapter_sequence_r2 ${params.preprocessing_adapter2}" : "", // adding adapter list happens at module input channel level
- // FILTERING OPTIONS--disable_adapter_trimming
+ params.preprocessing_skipadaptertrim ? "--disable_adapter_trimming" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter_sequence ${params.preprocessing_adapter1}" : "",
+ params.preprocessing_skipadaptertrim ? "" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter2 ? "--adapter_sequence_r2 ${params.preprocessing_adapter2}" : "",
"--length_required ${params.preprocessing_minlength}",
- params.preprocessing_fastp_complexityfilter ? "--low_complexity_filter --complexity_threshold ${params.preprocessing_fastp_complexityfilter_threshold}" : ""
+ params.preprocessing_fastp_complexityfilter ? "--low_complexity_filter --complexity_threshold ${params.preprocessing_fastp_complexityfilter_threshold}" : "",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // data
path: { "${params.outdir}/preprocessing/fastp/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.preprocessing_savepreprocessedreads
+ enabled: params.preprocessing_savepreprocessedreads,
],
[
- // stats
path: { "${params.outdir}/preprocessing/fastp/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.{log,html,json}'
- ]
+ pattern: '*.{log,html,json}',
+ ],
]
}
withName: ADAPTERREMOVAL_SINGLE {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.args = [
- // trimming options - note: adding adapter list happens at module input channel level
- params.preprocessing_skipadaptertrim ? "--adapter1 ''" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter1 ${params.preprocessing_adapter1}" : "", // adding adapter list happens at module input channel level
+ params.preprocessing_skipadaptertrim ? "--adapter1 ''" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter1 ${params.preprocessing_adapter1}" : "",
params.preprocessing_skipadaptertrim ? "--adapter2 ''" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter2 ? "--adapter2 ${params.preprocessing_adapter2}" : "",
"--minadapteroverlap ${params.preprocessing_adapterremoval_adapteroverlap}",
params.preprocessing_adapterremoval_preserve5p ? "--preserve5p" : "",
@@ -179,33 +165,28 @@ process {
!params.preprocessing_adapterremoval_skipqualitytrimming ? "--trimqualities --minquality ${params.preprocessing_adapterremoval_trimbasequalitymin}" : "",
!params.preprocessing_adapterremoval_skipntrimming ? "--trimns" : "",
"--qualitymax ${params.preprocessing_adapterremoval_qualitymax}",
- // filtering options
- "--minlength ${params.preprocessing_minlength}"
+ "--minlength ${params.preprocessing_minlength}",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // data
path: { "${params.outdir}/preprocessing/adapterremoval/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.preprocessing_savepreprocessedreads
+ enabled: params.preprocessing_savepreprocessedreads,
],
[
- // stats
path: { "${params.outdir}/preprocessing/adapterremoval/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.settings'
- ]
+ pattern: '*.settings',
+ ],
]
}
withName: ADAPTERREMOVAL_PAIRED {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.args = [
- // COLLAPSING OPTIONS
params.preprocessing_skippairmerging ? "" : "--collapse",
- // TRIMMING OPTIONS - note: adding adapter list happens at module input channel level
params.preprocessing_skipadaptertrim ? "--adapter1 ''" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter1 ? "--adapter1 ${params.preprocessing_adapter1}" : "",
params.preprocessing_skipadaptertrim ? "--adapter2 ''" : params.preprocessing_adapterlist ? "" : params.preprocessing_adapter2 ? "--adapter2 ${params.preprocessing_adapter2}" : "",
"--minadapteroverlap ${params.preprocessing_adapterremoval_adapteroverlap}",
@@ -215,39 +196,35 @@ process {
!params.preprocessing_adapterremoval_skipqualitytrimming ? "--trimqualities --minquality ${params.preprocessing_adapterremoval_trimbasequalitymin}" : "",
!params.preprocessing_adapterremoval_skipntrimming ? "--trimns" : "",
"--qualitymax ${params.preprocessing_adapterremoval_qualitymax}",
- // FILTERING OPTIONS
- "--minlength ${params.preprocessing_minlength}"
+ "--minlength ${params.preprocessing_minlength}",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
[
- // data
path: { "${params.outdir}/preprocessing/adapterremoval/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.preprocessing_savepreprocessedreads
+ enabled: params.preprocessing_savepreprocessedreads,
],
[
- // stats
path: { "${params.outdir}/preprocessing/adapterremoval/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.settings'
- ]
+ pattern: '*.settings',
+ ],
]
}
withName: CAT_FASTQ_ADAPTERREMOVAL {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
- [
- // data
- path: { "${params.outdir}/preprocessing/adapterremoval/data/" },
- mode: params.publish_dir_mode,
- pattern: '*.fastq.gz',
- enabled: params.preprocessing_savepreprocessedreads
- ]
+ [
+ path: { "${params.outdir}/preprocessing/adapterremoval/data/" },
+ mode: params.publish_dir_mode,
+ pattern: '*.fastq.gz',
+ enabled: params.preprocessing_savepreprocessedreads,
]
+ ]
}
@@ -257,11 +234,10 @@ process {
withName: GUNZIP_FASTA {
publishDir = [
[
- // data
path: { "${params.outdir}/references/fasta/data/" },
mode: params.publish_dir_mode,
pattern: '*.{fasta,fna,fas,fa}',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -275,11 +251,10 @@ process {
withName: SAMTOOLS_FAIDX {
publishDir = [
[
- // data
path: { "${params.outdir}/references/fasta/data/" },
mode: params.publish_dir_mode,
pattern: '*.fai',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -287,11 +262,10 @@ process {
withName: PICARD_CREATESEQUENCEDICTIONARY {
publishDir = [
[
- // data
path: { "${params.outdir}/references/fasta/data/" },
mode: params.publish_dir_mode,
pattern: '*.dict',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -299,11 +273,10 @@ process {
withName: BOWTIE2_BUILD {
publishDir = [
[
- // data
path: { "${params.outdir}/references/bowtie2/data/" },
mode: params.publish_dir_mode,
pattern: 'bowtie2',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -311,11 +284,10 @@ process {
withName: BWA_INDEX {
publishDir = [
[
- // data
path: { "${params.outdir}/references/bwa/data/" },
mode: params.publish_dir_mode,
pattern: 'bwa',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -324,24 +296,22 @@ process {
withName: GUNZIP_ELONGATED_FASTA {
publishDir = [
[
- // data
path: { "${params.outdir}/references/fasta/data/" },
mode: params.publish_dir_mode,
pattern: '*_*[0-9].{fasta,fna,fas,fa}',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
withName: CIRCULARMAPPER_CIRCULARGENERATOR {
- tag = { "${meta.id}_${params.fasta_circularmapper_elongationfactor}" }
+ tag = { "${meta.id}_${params.fasta_circularmapper_elongationfactor}" }
publishDir = [
[
- // data
path: { "${params.outdir}/references/fasta/data/" },
mode: params.publish_dir_mode,
pattern: '*_*[0-9].fasta',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -349,11 +319,10 @@ process {
withName: BWA_INDEX_CIRCULARISED {
publishDir = [
[
- // data
path: { "${params.outdir}/references/bwa/data/" },
mode: params.publish_dir_mode,
pattern: 'bwa',
- enabled: params.save_reference
+ enabled: params.save_reference,
]
]
}
@@ -361,24 +330,20 @@ process {
//
// BAM INPUT
//
- withName: 'SAMTOOLS_FLAGSTATS_BAM_INPUT' {
- // NOTE This step becomes obsolete once a lane-merging step is added for input BAMs.
- // TODO Once a lane-merging step is added for input BAMs, the lane should be dropped from this tag.
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ withName: SAMTOOLS_FLAGSTATS_BAM_INPUT {
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.lane}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/mapping/bam_input/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
withName: SAMTOOLS_INDEX_BAM_INPUT {
- // NOTE This step becomes obsolete once a lane-merging step is added for input BAMs.
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
enabled: false
]
@@ -388,105 +353,98 @@ process {
// BAM FILTERING
//
withName: FILTER_BAM_FRAGMENT_LENGTH {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = "-l ${params.bamfiltering_minreadlength}"
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = "-l ${params.bamfiltering_minreadlength}"
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/read_filtering/filtered_bams/data/" },
mode: params.publish_dir_mode,
pattern: '*.filtered.bam',
- enabled: params.bamfiltering_savefilteredbams
+ enabled: params.bamfiltering_savefilteredbams,
]
]
}
withName: SAMTOOLS_VIEW_BAM_FILTERING {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = [
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = [
"-q ${params.bamfiltering_mappingquality}",
params.bamfiltering_retainunmappedgenomicbam ? '' : "-F ${params.bamfiltering_genomicbamfilterflag}",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_filtered" }
publishDir = [
[
- // data
path: { "${params.outdir}/read_filtering/filtered_bams/data/" },
mode: params.publish_dir_mode,
pattern: '*.bam',
- enabled: params.bamfiltering_savefilteredbams
+ enabled: params.bamfiltering_savefilteredbams,
]
]
}
withName: 'SAMTOOLS_LENGTH_FILTER_INDEX|SAMTOOLS_FILTER_INDEX' {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_filtered" }
publishDir = [
[
- // data
path: { "${params.outdir}/read_filtering/filtered_bams/data/" },
mode: params.publish_dir_mode,
pattern: '*.{bai,csi}',
- enabled: params.bamfiltering_savefilteredbams
+ enabled: params.bamfiltering_savefilteredbams,
]
]
}
withName: SAMTOOLS_FLAGSTAT_FILTERED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_filtered" }
publishDir = [
[
- // stats
path: { "${params.outdir}/read_filtering/filtered_bams/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
withName: SAMTOOLS_FASTQ_SAVEBAMFILTERINGREADS {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_bamfiltering_fastq" }
publishDir = [
[
- // data
path: { "${params.outdir}/read_filtering/fastq/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.bamfiltering_generatefastq
+ enabled: params.bamfiltering_generatefastq,
]
]
}
withName: SAMTOOLS_FASTQ_METAGENOMICS {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = [
- params.metagenomics_input == 'mapped' ? '-F 4': '',
- params.metagenomics_input == 'unmapped' ? '-f 4': '',
- // 'all' is left then with NO -F or -f flag, therefore all reads get sent to fastq
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = [
+ params.metagenomics_input == 'mapped' ? '-F 4' : '',
+ params.metagenomics_input == 'unmapped' ? '-f 4' : '',
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_metagenomics_fastq_${params.metagenomics_input}" }
publishDir = [
[
- // data
path: { "${params.outdir}/read_filtering/fastq/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.metagenomics_input_savefastq
+ enabled: params.metagenomics_input_savefastq,
]
]
}
- withName: 'CAT_FASTQ_METAGENOMICS' {
- tag = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
+ withName: CAT_FASTQ_METAGENOMICS {
+ tag = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- enabled: false // NO publishing of concatenated fastq files for metagenomics, only outputs from SAMTOOLS_FASTQ_METAGENOMICS
+ enabled: false
]
]
}
@@ -495,9 +453,9 @@ process {
// SHARDING FASTQS
//
withName: SEQKIT_SPLIT2 {
- tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
ext.prefix = "out"
- ext.args = "-s ${params.fastq_shard_size}"
+ ext.args = "-s ${params.fastq_shard_size}"
publishDir = [
enabled: false
]
@@ -507,8 +465,8 @@ process {
// READ MAPPING
//
withName: BWA_ALN {
- tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = { "-n ${params.mapping_bwaaln_n} -k ${params.mapping_bwaaln_k} -l ${params.mapping_bwaaln_l} -o ${params.mapping_bwaaln_o}" }
+ tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = { "-n ${params.mapping_bwaaln_n} -k ${params.mapping_bwaaln_k} -l ${params.mapping_bwaaln_l} -o ${params.mapping_bwaaln_o}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.id_index}" }
publishDir = [
enabled: false
@@ -516,21 +474,22 @@ process {
}
withName: 'BWA_SAMSE|BWA_SAMPE' {
- tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = {
+ tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = {
se_pe_string = meta.single_end ? "SE" : "PE"
[
"-r '@RG\\tID:ILLUMINA-${meta.sample_id}_${meta.library_id}\\tSM:${meta.sample_id}\\tLB:${meta.library_id}\\tPL:illumina\\tPU:ILLUMINA-${meta.library_id}-${meta.strandedness}_stranded-${se_pe_string}'"
- ].join(' ').trim() }
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.id_index}" }
publishDir = [
enabled: false
]
}
- withName: ".*MAP:FASTQ_ALIGN_BWAALN:SAMTOOLS_INDEX" {
- tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ withName: '.*MAP:FASTQ_ALIGN_BWAALN:SAMTOOLS_INDEX' {
+ tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
@@ -538,14 +497,15 @@ process {
}
withName: BWA_MEM {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = {
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = {
se_pe_string = meta.single_end ? "SE" : "PE"
[
"-k ${params.mapping_bwamem_k}",
"-r ${params.mapping_bwamem_r}",
- "-R '@RG\\tID:ILLUMINA-${meta.sample_id}_${meta.library_id}\\tSM:${meta.sample_id}\\tLB:${meta.library_id}\\tPL:illumina\\tPU:ILLUMINA-${meta.library_id}-${meta.strandedness}_stranded-${se_pe_string}'"
- ].join(' ').trim() }
+ "-R '@RG\\tID:ILLUMINA-${meta.sample_id}_${meta.library_id}\\tSM:${meta.sample_id}\\tLB:${meta.library_id}\\tPL:illumina\\tPU:ILLUMINA-${meta.library_id}-${meta.strandedness}_stranded-${se_pe_string}'",
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
@@ -553,8 +513,8 @@ process {
}
withName: BOWTIE2_ALIGN {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = {
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = {
se_pe_string = meta.single_end ? "SE" : "PE"
[
"-N ${params.mapping_bowtie2_n}",
@@ -567,8 +527,9 @@ process {
"--rg LB:${meta.library_id}",
"--rg PL:illumina",
"--rg PU:ILLUMINA-${meta.sample_id}_${meta.library_id}-${meta.strandedness}_stranded-${se_pe_string}",
- "${params.mapping_bowtie2_alignmode}" == 'local' ? "--local --${params.mapping_bowtie2_sensitivity}-local" : ( "${params.mapping_bowtie2_alignmode}" == 'end-to-end' ? "--end-to-end --${params.mapping_bowtie2_sensitivity}" : "" )
- ].join(' ').trim()}
+ "${params.mapping_bowtie2_alignmode}" == 'local' ? "--local --${params.mapping_bowtie2_sensitivity}-local" : ("${params.mapping_bowtie2_alignmode}" == 'end-to-end' ? "--end-to-end --${params.mapping_bowtie2_sensitivity}" : ""),
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
@@ -576,8 +537,8 @@ process {
}
withName: 'SAMTOOLS_INDEX_MEM|SAMTOOLS_INDEX_BT2' {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
@@ -585,50 +546,47 @@ process {
}
withName: SAMTOOLS_MERGE_LANES {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
enabled: false
]
- ext.args = { params.run_fastq_sharding ? "-c -p" : "" }
+ ext.args = { params.run_fastq_sharding ? "-c -p" : "" }
}
withName: SAMTOOLS_SORT_MERGED_LANES {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_sorted" }
publishDir = [
[
- // data
path: { "${params.outdir}/mapping/${params.mapping_tool}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bam}'
+ pattern: '*.{bam}',
]
]
}
withName: SAMTOOLS_INDEX_MERGED_LANES {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/mapping/${params.mapping_tool}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
]
}
withName: SAMTOOLS_FLAGSTAT_MERGED_LANES {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_sorted" }
publishDir = [
[
- // stats
path: { "${params.outdir}/mapping/${params.mapping_tool}/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
@@ -636,26 +594,26 @@ process {
// Circular mapping
// Configuration for BWA_ALN and BWA_SAMSE/SAMPE is the same as for the non-circular mapping
withName: CIRCULARMAPPER_REALIGNSAMFILE {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = { params.mapping_circularmapper_circularfilter ? "-f true -x true" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = { params.mapping_circularmapper_circularfilter ? "-f true -x true" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
]
}
- withName: ".*MAP:CIRCULARMAPPER:FASTQ_ALIGN_BWAALN_ELONGATED:SAMTOOLS_INDEX" {
- tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ withName: '.*MAP:CIRCULARMAPPER:FASTQ_ALIGN_BWAALN_ELONGATED:SAMTOOLS_INDEX' {
+ tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
]
}
- withName: ".*MAP:CIRCULARMAPPER:SAMTOOLS_INDEX_REALIGNED" {
- tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ withName: '.*MAP:CIRCULARMAPPER:SAMTOOLS_INDEX_REALIGNED' {
+ tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
publishDir = [
enabled: false
@@ -666,11 +624,11 @@ process {
// DEDUPLICATION
//
withName: PICARD_MARKDUPLICATES {
- tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
- ext.args = [
+ tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = [
"--REMOVE_DUPLICATES",
"--VALIDATION_STRINGENCY SILENT",
- "--ASSUME_SORTED"
+ "--ASSUME_SORTED",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_${meta.genomic_region}_MarkDuplicates" }
publishDir = [
@@ -679,8 +637,8 @@ process {
}
withName: DEDUP {
- tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
- ext.args = "--merged"
+ tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = "--merged"
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_${meta.genomic_region}_DeDup" }
publishDir = [
enabled: false
@@ -688,31 +646,30 @@ process {
}
withName: SAMTOOLS_MERGE_DEDUPPED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
enabled: false
]
}
- withName: ".*DEDUPLICATE:BUILD_INTERVALS" {
+ withName: '.*DEDUPLICATE:BUILD_INTERVALS' {
publishDir = [
enabled: false
]
}
// Overwrite default SWF tag and prefix
- withName: ".*BAM_SPLIT_BY_REGION:SAMTOOLS_VIEW" {
- tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
+ withName: '.*BAM_SPLIT_BY_REGION:SAMTOOLS_VIEW' {
+ tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_${meta.genomic_region}_dedupped" }
publishDir = [
enabled: false
]
}
- withName: ".*BAM_SPLIT_BY_REGION:SAMTOOLS_INDEX" {
- // The BAM_SPLIT_BY_REGION SWF only works with bais, so `params.fasta_largeref` should not be passed to it.
- tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
+ withName: '.*BAM_SPLIT_BY_REGION:SAMTOOLS_INDEX' {
+ tag = { "${meta.reference}:${meta.genomic_region}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_${meta.genomic_region}_dedupped" }
publishDir = [
enabled: false
@@ -720,41 +677,38 @@ process {
}
withName: SAMTOOLS_SORT_DEDUPPED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_dedupped" }
publishDir = [
[
- // data
path: { "${params.outdir}/deduplication/${params.deduplication_tool}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.bam'
+ pattern: '*.bam',
]
]
}
withName: SAMTOOLS_INDEX_DEDUPPED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_dedupped" }
publishDir = [
[
- // data
path: { "${params.outdir}/deduplication/${params.deduplication_tool}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
]
}
withName: SAMTOOLS_FLAGSTAT_DEDUPPED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_dedupped" }
publishDir = [
[
- // stats
path: { "${params.outdir}/deduplication/${params.deduplication_tool}/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
@@ -763,17 +717,18 @@ process {
// HOST REMOVAL
//
withName: HOST_REMOVAL {
- tag = { "${meta.reference}|${meta_fastqs.sample_id}_${meta_fastqs.library_id}_L${meta_fastqs.lane}" }
- ext.args = {[
- "-m ${params.host_removal_mode}",
- "${meta_fastqs.single_end}" == false && "${params.preprocessing_skippairmerging}" == false ? "-merged" : ""
- ].join(' ').trim()}
+ tag = { "${meta.reference}|${meta_fastqs.sample_id}_${meta_fastqs.library_id}_L${meta_fastqs.lane}" }
+ ext.args = {
+ [
+ "-m ${params.host_removal_mode}",
+ "${meta_fastqs.single_end}" == false && "${params.preprocessing_skippairmerging}" == false ? "-merged" : "",
+ ].join(' ').trim()
+ }
publishDir = [
[
- // data
path: { "${params.outdir}/read_filtering/host_removal/data/" },
mode: params.publish_dir_mode,
- pattern: '*.fq.gz'
+ pattern: '*.fq.gz',
]
]
}
@@ -782,25 +737,23 @@ process {
// AUTHENTICATION
//
withName: ENDORSPY {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/endorspy/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.json'
+ pattern: '*.json',
]
]
}
withName: PRESEQ_CCURVE {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = "-B -s ${params.mapstats_preseq_stepsize}"
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = "-B -s ${params.mapstats_preseq_stepsize}"
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/preseq/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -809,7 +762,7 @@ process {
}
withName: PRESEQ_LCEXTRAP {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.args = [
"-B",
"-s ${params.mapstats_preseq_stepsize}",
@@ -817,12 +770,11 @@ process {
"-x ${params.mapstats_preseq_terms}",
"-n ${params.mapstats_preseq_bootstrap}",
"-c ${params.mapstats_preseq_cval}",
- params.mapstats_preseq_defects_mode ? '-D' : ''
+ params.mapstats_preseq_defects_mode ? '-D' : '',
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/preseq/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -831,19 +783,18 @@ process {
}
withName: SAMTOOLS_VIEW_GENOME {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}" }
publishDir = [
enabled: false
]
}
withName: BEDTOOLS_COVERAGE_DEPTH {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = '-mean -nonamecheck'
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = '-mean -nonamecheck'
ext.prefix = { "${meta.sample_id}_${meta.reference}_depth" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/bedtools/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -852,12 +803,11 @@ process {
}
withName: BEDTOOLS_COVERAGE_BREADTH {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = '-nonamecheck'
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = '-nonamecheck'
ext.prefix = { "${meta.sample_id}_${meta.reference}_breadth" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/bedtools/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -867,12 +817,12 @@ process {
withName: ANGSD_DOCOUNTS {
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = [
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = [
"-iCounts 1",
"-r ${params.contamination_estimation_angsd_chrom_name}:${params.contamination_estimation_angsd_range_from}-${params.contamination_estimation_angsd_range_to}",
"-minMapQ ${params.contamination_estimation_angsd_mapq}",
- "-minQ ${params.contamination_estimation_angsd_minq}"
+ "-minQ ${params.contamination_estimation_angsd_minq}",
].join(' ').trim()
publishDir = [
enabled: false
@@ -880,14 +830,13 @@ process {
}
withName: ANGSD_CONTAMINATION {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
- path: { "${params.outdir}/authentication/angsd_nuclear_contamination/stats/"},
+ path: { "${params.outdir}/authentication/angsd_nuclear_contamination/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.txt'
+ pattern: '*.txt',
]
]
}
@@ -895,26 +844,24 @@ process {
withName: PRINT_CONTAMINATION_ANGSD {
publishDir = [
[
- // stats
- path: { "${params.outdir}/authentication/angsd_nuclear_contamination/stats/"},
+ path: { "${params.outdir}/authentication/angsd_nuclear_contamination/stats/" },
mode: params.publish_dir_mode,
- pattern: 'nuclear_contamination*'
+ pattern: 'nuclear_contamination*',
]
]
}
withName: MTNUCRATIO {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
publishDir = [
enabled: false
]
}
withName: 'QUALIMAP_BAMQC_WITHBED|QUALIMAP_BAMQC_NOBED' {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/qualimap/stats/${meta.reference}/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -923,19 +870,19 @@ process {
}
withName: BBMAP_BBDUK {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { "entropymask=f entropy=${params.metagenomics_complexity_entropy}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { "entropymask=f entropy=${params.metagenomics_complexity_entropy}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_complexity" }
publishDir = [
path: { "${params.outdir}/metagenomics/complexity_filter/bbduk/" },
mode: params.publish_dir_mode,
pattern: '*.{fastq.gz,log}',
- enabled: params.metagenomics_complexity_savefastq
+ enabled: params.metagenomics_complexity_savefastq,
]
}
withName: MALT_RUN {
- ext.args = [
+ ext.args = [
"-m ${params.metagenomics_malt_mode}",
"-at ${params.metagenomics_malt_alignmentmode}",
"-top ${params.metagenomics_malt_toppercent}",
@@ -943,12 +890,12 @@ process {
"-mq ${params.metagenomics_malt_maxqueries}",
"--memoryMode ${params.metagenomics_malt_memorymode}",
params.metagenomics_malt_minsupportmode == "percent" ? "-supp ${params.metagenomics_malt_minsupportpercent}" : "-sup ${params.metagenomics_malt_minsupportreads}",
- params.metagenomics_malt_savereads ? "--alignments ./" : ""
+ params.metagenomics_malt_savereads ? "--alignments ./" : "",
].join(' ').trim()
publishDir = [
path: { "${params.outdir}/metagenomics/profiling/malt/" },
mode: params.publish_dir_mode,
- pattern: '*.{rma6,log,sam.gz}'
+ pattern: '*.{rma6,log,sam.gz}',
]
ext.prefix = { "${meta.label}_${meta.id}-run" }
}
@@ -958,29 +905,29 @@ process {
publishDir = [
path: { "${params.outdir}/metagenomics/profiling/malt/" },
mode: params.publish_dir_mode,
- pattern: '*.{log}'
+ pattern: '*.{log}',
]
}
withName: KRAKEN2_KRAKEN2 {
- tag = { "${meta.sample_id}|single_end_mode_${meta.single_end}" }
- ext.args = [
+ tag = { "${meta.sample_id}|single_end_mode_${meta.single_end}" }
+ ext.args = [
params.metagenomics_kraken2_saveminimizers ? "--report-minimizer-data" : ""
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
path: { "${params.outdir}/metagenomics/profiling/kraken2/" },
mode: params.publish_dir_mode,
- pattern: '*.{txt,fastq.gz}'
+ pattern: '*.{txt,fastq.gz}',
]
}
withName: KRAKENUNIQ_PRELOADEDKRAKENUNIQ {
- tag = { "single_end_mode_${meta.single_end}" }
+ tag = { "single_end_mode_${meta.single_end}" }
publishDir = [
path: { "${params.outdir}/metagenomics/profiling/krakenuniq/" },
mode: params.publish_dir_mode,
- pattern: '*.{txt,fastq.gz}'
+ pattern: '*.{txt,fastq.gz}',
]
ext.prefix = { "${meta.single_end}" }
}
@@ -989,13 +936,13 @@ process {
publishDir = [
path: { "${params.outdir}/metagenomics/profiling/metaphlan/" },
mode: params.publish_dir_mode,
- pattern: '*.{biom,txt}'
+ pattern: '*.{biom,txt}',
]
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
}
withName: MALTEXTRACT {
- ext.args = [
+ ext.args = [
"-f ${params.metagenomics_maltextract_filter}",
"-a ${params.metagenomics_maltextract_toppercent}",
"--minPI ${params.metagenomics_maltextract_minpercentidentity}",
@@ -1004,53 +951,53 @@ process {
params.metagenomics_maltextract_duplicateremovaloff ? "--dupRemOff" : "",
params.metagenomics_maltextract_matches ? "--matches" : "",
params.metagenomics_maltextract_megansummary ? "--meganSummary" : "",
- params.metagenomics_maltextract_usetopalignment ? "--useTopAlignment" : "",
+ params.metagenomics_maltextract_usetopalignment ? "--useTopAlignment" : "",
{ meta.strandedness } == "single" ? '--singleStranded' : '',
].join(' ').trim()
publishDir = [
path: { "${params.outdir}/metagenomics/postprocessing/maltextract/" },
mode: params.publish_dir_mode,
pattern: 'results',
- saveAs: { "${meta.id}" }
+ saveAs: { "${meta.id}" },
]
}
withName: MEGAN_RMA2INFO {
- tag = {"${meta.id}"}
- ext.args = "-c2c Taxonomy"
+ tag = { "${meta.id}" }
+ ext.args = "-c2c Taxonomy"
ext.prefix = { "${meta.id}" }
publishDir = [
path: { "${params.outdir}/metagenomics/postprocessing/megan_summaries/" },
mode: params.publish_dir_mode,
- pattern: '*.{txt.gz,megan}'
+ pattern: '*.{txt.gz,megan}',
]
}
withName: AMPS {
- publishDir = [
+ publishDir = [
path: { "${params.outdir}/metagenomics/postprocessing/maltextract/" },
mode: params.publish_dir_mode,
- pattern: 'results'
+ pattern: 'results',
]
- errorStrategy = 'ignore' // required as it fails the run for low reads: https://github.com/rhuebler/HOPS/issues/9
+ errorStrategy = 'ignore'
}
withName: TAXPASTA_MERGE {
publishDir = [
path: { "${params.outdir}/metagenomics/postprocessing/taxpasta/" },
mode: params.publish_dir_mode,
- pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}'
+ pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}',
]
- ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}_taxpasta_table.tsv" }
+ ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}_taxpasta_table.tsv" }
}
withName: TAXPASTA_STANDARDISE {
publishDir = [
path: { "${params.outdir}/metagenomics/postprocessing/taxpasta/" },
mode: params.publish_dir_mode,
- pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}'
+ pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}',
]
- ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}taxpasta_table.tsv" }
+ ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}taxpasta_table.tsv" }
}
//
@@ -1058,7 +1005,7 @@ process {
//
withName: 'QUALIMAP_BAMQC_WITHBED|QUALIMAP_BAMQC_NOBED' {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}" }
publishDir = [
path: { "${params.outdir}/mapstats/qualimap/${meta.reference}/" },
mode: params.publish_dir_mode,
@@ -1070,16 +1017,15 @@ process {
// DAMAGE CALCULATION
//
withName: DAMAGEPROFILER {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.args = [
"-l ${params.damagecalculation_damageprofiler_length}",
"-t ${params.damagecalculation_xaxis}",
- "-yaxis_dp_max ${params.damagecalculation_yaxis}"
+ "-yaxis_dp_max ${params.damagecalculation_yaxis}",
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/damageprofiler/stats/" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
@@ -1088,40 +1034,40 @@ process {
}
withName: CALCULATE_MAPDAMAGE2 {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { [
- "--no-stats",
- "-y ${params.damagecalculation_yaxis}",
- params.damagecalculation_mapdamage_downsample != 0 ? "-n ${params.damagecalculation_mapdamage_downsample} --downsample-seed=1" : "",
- { meta.strandedness } == "single" ? '--single-stranded' : '',
- "-m ${params.damagecalculation_xaxis}"
- ].join(' ').trim() }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = {
+ [
+ "--no-stats",
+ "-y ${params.damagecalculation_yaxis}",
+ params.damagecalculation_mapdamage_downsample != 0 ? "-n ${params.damagecalculation_mapdamage_downsample} --downsample-seed=1" : "",
+ { meta.strandedness } == "single" ? '--single-stranded' : '',
+ "-m ${params.damagecalculation_xaxis}",
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/mapdamage2/stats/" },
mode: params.publish_dir_mode,
- pattern: 'results_*/*'
+ pattern: 'results_*/*',
]
]
}
withName: SAMTOOLS_DEPTH_SEXDETERRMINE {
- tag = { "${meta1.reference}|${meta1.sample_id}" }
+ tag = { "${meta1.reference}|${meta1.sample_id}" }
ext.prefix = { "${meta2.id}_samtoolsdepth" }
- ext.args = '-aa -q30 -Q30 -H'
+ ext.args = '-aa -q30 -Q30 -H'
publishDir = [
enabled: false
]
}
withName: SEXDETERRMINE {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.reference}_sexdeterrmine" }
publishDir = [
[
- // stats
path: { "${params.outdir}/authentication/sexdeterrmine/stats/" },
mode: params.publish_dir_mode,
pattern: '*{_sexdeterrmine}*',
@@ -1136,125 +1082,119 @@ process {
ext.prefix = { "${meta.id}.masked" }
publishDir = [
[
- // data
path: { "${params.outdir}/references/masked_reference/data/" },
mode: params.publish_dir_mode,
- pattern: '*.masked.fa'
+ pattern: '*.masked.fa',
]
]
}
withName: MAPDAMAGE2 {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { [
- "--rescale",
- // "--rescale-out=${task.ext.prefix}.bam", // This doesn't work, because the output is expected to be in the mapdamage results dir.
- "--seq-length=${params.damage_manipulation_rescale_seqlength}",
- params.damage_manipulation_rescale_length_3p != 0 ? "--rescale-length-3p=${params.damage_manipulation_rescale_length_3p}" : "",
- params.damage_manipulation_rescale_length_5p != 0 ? "--rescale-length-5p=${params.damage_manipulation_rescale_length_5p}" : "",
- { meta.strandedness } == "single" ? '--single-stranded' : ''
- ].join(' ').trim() }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = {
+ [
+ "--rescale",
+ "--seq-length=${params.damage_manipulation_rescale_seqlength}",
+ params.damage_manipulation_rescale_length_3p != 0 ? "--rescale-length-3p=${params.damage_manipulation_rescale_length_3p}" : "",
+ params.damage_manipulation_rescale_length_5p != 0 ? "--rescale-length-5p=${params.damage_manipulation_rescale_length_5p}" : "",
+ { meta.strandedness } == "single" ? '--single-stranded' : '',
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_rescaled" }
publishDir = [
[
- // data
path: { "${params.outdir}/damage_manipulation/mapdamage2/data/" },
mode: params.publish_dir_mode,
pattern: 'result*/*.rescaled.bam',
- saveAs: { "${meta.sample_id}_${meta.library_id}_${meta.reference}_rescaled.bam" } // Needed to save the bam directly in the output dir instead of within the mapdamage results dir.
+ saveAs: { "${meta.sample_id}_${meta.library_id}_${meta.reference}_rescaled.bam" },
],
[
- // stats
path: { "${params.outdir}/damage_manipulation/mapdamage2/stats/" },
mode: params.publish_dir_mode,
- pattern: 'results_*/Stats_out_MCMC_*'
- ]
+ pattern: 'results_*/Stats_out_MCMC_*',
+ ],
]
}
withName: SAMTOOLS_INDEX_DAMAGE_RESCALED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
publishDir = [
[
- // stats
path: { "${params.outdir}/damage_manipulation/mapdamage2/data/" },
mode: params.publish_dir_mode,
pattern: '*.{bai,csi}',
- saveAs: { "${meta.sample_id}_${meta.library_id}_${meta.reference}_rescaled.bam.bai" } // ext.prefix cannot be used here, so rename for publishing instead.
+ saveAs: { "${meta.sample_id}_${meta.library_id}_${meta.reference}_rescaled.bam.bai" },
]
]
}
withName: PMDTOOLS_FILTER {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args2 = {[
- "${meta.damage_treatment}" == 'none' ? '--UDGminus' : "${meta.damage_treatment}" == 'half' ? '--UDGhalf' : '--UDGplus' ,
- "${meta.strandedness}" == 'single' ? '--ss' : ''
- ].join(' ').trim()}
- ext.args3 = { "-h" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args2 = {
+ [
+ "${meta.damage_treatment}" == 'none' ? '--UDGminus' : "${meta.damage_treatment}" == 'half' ? '--UDGhalf' : '--UDGplus',
+ "${meta.strandedness}" == 'single' ? '--ss' : '',
+ ].join(' ').trim()
+ }
+ ext.args3 = { "-h" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_pmdfiltered" }
publishDir = [
[
- // data
path: { "${params.outdir}/damage_manipulation/pmdtools/data/" },
mode: params.publish_dir_mode,
- pattern: '*_pmdfiltered.bam'
+ pattern: '*_pmdfiltered.bam',
]
]
}
withName: SAMTOOLS_INDEX_DAMAGE_FILTERED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
publishDir = [
[
- // data
path: { "${params.outdir}/damage_manipulation/pmdtools/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
]
}
withName: SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_pmdfiltered" }
publishDir = [
[
- // stats
path: { "${params.outdir}/damage_manipulation/pmdtools/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
withName: BAMUTIL_TRIMBAM {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = [
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = [
params.damage_manipulation_bamutils_softclip ? '-c' : ''
].join(' ').trim()
ext.prefix = { params.run_pmd_filtering ? "${meta.sample_id}_${meta.library_id}_${meta.reference}_pmdfiltered_trimmed" : "${meta.sample_id}_${meta.library_id}_${meta.reference}_trimmed" }
publishDir = [
[
- // data
path: { "${params.outdir}/damage_manipulation/bamutils_trimbam/data/" },
mode: params.publish_dir_mode,
- pattern: '*_trimmed.bam'
+ pattern: '*_trimmed.bam',
]
]
}
withName: SAMTOOLS_INDEX_DAMAGE_TRIMMED {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
publishDir = [
[
- // data
path: { "${params.outdir}/damage_manipulation/bamutils_trimbam/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
]
}
@@ -1263,55 +1203,50 @@ process {
// METAGENOMIC SCREENING
//
withName: PRINSEQPLUSPLUS {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = [
- params.metagenomics_prinseq_mode == 'dust' ? "-lc_dust=${params.metagenomics_prinseq_dustscore}" : "-lc_entropy=${params.metagenomics_complexity_entropy}",
- "-trim_qual_left=0 -trim_qual_left=0 -trim_qual_window=0 -trim_qual_step=0",
- ].join(' ').trim()
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = [
+ params.metagenomics_prinseq_mode == 'dust' ? "-lc_dust=${params.metagenomics_prinseq_dustscore}" : "-lc_entropy=${params.metagenomics_complexity_entropy}",
+ "-trim_qual_left=0 -trim_qual_left=0 -trim_qual_window=0 -trim_qual_step=0",
+ ].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_complexity" }
publishDir = [
[
- // data
path: { "${params.outdir}/metagenomics/prinseq/data/" },
mode: params.publish_dir_mode,
pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz}',
- enabled: params.metagenomics_complexity_savefastq
+ enabled: params.metagenomics_complexity_savefastq,
],
[
- // stats
path: { "${params.outdir}/metagenomics/prinseq/stats/" },
mode: params.publish_dir_mode,
pattern: '*log',
- enabled: params.metagenomics_complexity_savefastq
- ]
+ enabled: params.metagenomics_complexity_savefastq,
+ ],
]
}
withName: BBMAP_BBDUK {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { "entropymask=f entropy=${params.metagenomics_complexity_entropy}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { "entropymask=f entropy=${params.metagenomics_complexity_entropy}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_complexity" }
publishDir = [
[
- // data
path: { "${params.outdir}/metagenomics/bbduk/data/" },
mode: params.publish_dir_mode,
pattern: '*.fastq.gz',
- enabled: params.metagenomics_complexity_savefastq
+ enabled: params.metagenomics_complexity_savefastq,
],
[
- // stats
path: { "${params.outdir}/metagenomics/bbduk/stats/" },
mode: params.publish_dir_mode,
pattern: '*.log',
- enabled: params.metagenomics_complexity_savefastq
- ]
+ enabled: params.metagenomics_complexity_savefastq,
+ ],
]
}
withName: MALT_RUN {
- // TODO needs a tag
- ext.args = [
+ ext.args = [
"-m ${params.metagenomics_malt_mode}",
"-at ${params.metagenomics_malt_alignmentmode}",
"-top ${params.metagenomics_malt_toppercent}",
@@ -1319,34 +1254,30 @@ process {
"-mq ${params.metagenomics_malt_maxqueries}",
"--memoryMode ${params.metagenomics_malt_memorymode}",
params.metagenomics_malt_minsupportmode == "percent" ? "-supp ${params.metagenomics_malt_minsupportpercent}" : "-sup ${params.metagenomics_malt_minsupportreads}",
- params.metagenomics_malt_savereads ? "--alignments ./" : ""
+ params.metagenomics_malt_savereads ? "--alignments ./" : "",
].join(' ').trim()
ext.prefix = { "${meta.label}_${meta.id}-run" }
publishDir = [
[
- // data
path: { "${params.outdir}/metagenomics/malt/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{rma6,sam.gz}'
+ pattern: '*.{rma6,sam.gz}',
],
[
- // stats
path: { "${params.outdir}/metagenomics/malt/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.log'
- ]
+ pattern: '*.log',
+ ],
]
}
withName: CAT_CAT_MALT {
- // TODO needs a tag
ext.prefix = { "${meta.id}_runtime_log_concatenated.log" }
publishDir = [
[
- // stats
path: { "${params.outdir}/metagenomics/malt/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.log'
+ pattern: '*.log',
]
]
}
@@ -1358,40 +1289,36 @@ process {
}
withName: KRAKEN2_KRAKEN2 {
- ext.args = [
+ ext.args = [
params.metagenomics_kraken2_saveminimizers ? "--report-minimizer-data" : ""
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/metagenomics/kraken2/data/" },
mode: params.publish_dir_mode,
- pattern: '*.fastq.gz'
+ pattern: '*.fastq.gz',
],
[
- // stats
path: { "${params.outdir}/metagenomics/kraken2/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.txt'
- ]
+ pattern: '*.txt',
+ ],
]
}
withName: KRAKENUNIQ_PRELOADEDKRAKENUNIQ {
publishDir = [
[
- // data
path: { "${params.outdir}/metagenomics/krakenuniq/data/" },
mode: params.publish_dir_mode,
- pattern: '*.fastq.gz'
+ pattern: '*.fastq.gz',
],
[
- // stats
path: { "${params.outdir}/metagenomics/krakenuniq/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.txt'
- ]
+ pattern: '*.txt',
+ ],
]
}
@@ -1399,17 +1326,15 @@ process {
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/metagenomics/metaphlan/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.{biom,txt}'
+ pattern: '*.{biom,txt}',
]
]
}
withName: MALTEXTRACT {
- // TODO needs a tag
- ext.args = [
+ ext.args = [
"-f ${params.metagenomics_maltextract_filter}",
"-a ${params.metagenomics_maltextract_toppercent}",
"--minPI ${params.metagenomics_maltextract_minpercentidentity}",
@@ -1418,63 +1343,59 @@ process {
params.metagenomics_maltextract_duplicateremovaloff ? "--dupRemOff" : "",
params.metagenomics_maltextract_matches ? "--matches" : "",
params.metagenomics_maltextract_megansummary ? "--meganSummary" : "",
- params.metagenomics_maltextract_usetopalignment ? "--useTopAlignment" : "",
+ params.metagenomics_maltextract_usetopalignment ? "--useTopAlignment" : "",
{ meta.strandedness } == "single" ? '--singleStranded' : '',
].join(' ').trim()
publishDir = [
[
- // stats
path: { "${params.outdir}/metagenomics/maltextract/stats/" },
mode: params.publish_dir_mode,
pattern: 'results',
- saveAs: { "${meta.id}" }
+ saveAs: { "${meta.id}" },
]
]
}
withName: MEGAN_RMA2INFO {
- tag = {"${meta.id}"}
- ext.args = "-c2c Taxonomy"
+ tag = { "${meta.id}" }
+ ext.args = "-c2c Taxonomy"
ext.prefix = { "${meta.id}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/metagenomics/megan_summaries/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.{txt.gz,megan}'
+ pattern: '*.{txt.gz,megan}',
]
]
}
withName: AMPS {
- publishDir = [
+ publishDir = [
path: { "${params.outdir}/metagenomics/amps/stats/" },
mode: params.publish_dir_mode,
- pattern: 'results'
+ pattern: 'results',
]
- errorStrategy = 'ignore' // required as it fails the run for low reads: https://github.com/rhuebler/HOPS/issues/9
+ errorStrategy = 'ignore'
}
withName: TAXPASTA_MERGE {
- ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}_taxpasta_table.tsv" }
+ ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}_taxpasta_table.tsv" }
publishDir = [
[
- // stats
path: { "${params.outdir}/metagenomics/taxpasta/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}'
+ pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}',
]
]
}
withName: TAXPASTA_STANDARDISE {
- ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}taxpasta_table.tsv" }
+ ext.args = { "--profiler ${meta.profiler} --output ${meta.profiler}taxpasta_table.tsv" }
publishDir = [
[
- // stats
path: { "${params.outdir}/metagenomics/taxpasta/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}'
+ pattern: '*.{csv,tsv,ods,xlsx,arrow,parquet,biom}',
]
]
}
@@ -1482,98 +1403,92 @@ process {
//
// LIBRARY MERGE
//
- withName: ".*MERGE_LIBRARIES:SAMTOOLS_MERGE_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ withName: '.*MERGE_LIBRARIES:SAMTOOLS_MERGE_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}_unsorted" }
publishDir = [
enabled: false
]
}
- withName: ".*MERGE_LIBRARIES:SAMTOOLS_SORT_MERGED_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ withName: '.*MERGE_LIBRARIES:SAMTOOLS_SORT_MERGED_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/final_bams/raw/data/" },
mode: params.publish_dir_mode,
- pattern: '*.bam'
+ pattern: '*.bam',
]
]
}
- withName: ".*MERGE_LIBRARIES:SAMTOOLS_INDEX_MERGED_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ withName: '.*MERGE_LIBRARIES:SAMTOOLS_INDEX_MERGED_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/final_bams/raw/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
]
}
- withName: ".*MERGE_LIBRARIES:SAMTOOLS_FLAGSTAT_MERGED_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ withName: '.*MERGE_LIBRARIES:SAMTOOLS_FLAGSTAT_MERGED_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/final_bams/raw/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
- withName: ".*MERGE_LIBRARIES:SAMTOOLS_MERGE_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ withName: '.*MERGE_LIBRARIES:SAMTOOLS_MERGE_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}_unsorted" }
publishDir = [
enabled: false
]
}
- withName: ".*MERGE_LIBRARIES_GENOTYPING:SAMTOOLS_SORT_MERGED_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ withName: '.*MERGE_LIBRARIES_GENOTYPING:SAMTOOLS_SORT_MERGED_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/final_bams/${params.genotyping_source}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.bam'
+ pattern: '*.bam',
]
]
}
- withName: ".*MERGE_LIBRARIES_GENOTYPING:SAMTOOLS_INDEX_MERGED_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ withName: '.*MERGE_LIBRARIES_GENOTYPING:SAMTOOLS_INDEX_MERGED_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/final_bams/${params.genotyping_source}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
]
}
- withName: ".*MERGE_LIBRARIES_GENOTYPING:SAMTOOLS_FLAGSTAT_MERGED_LIBRARIES" {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ withName: '.*MERGE_LIBRARIES_GENOTYPING:SAMTOOLS_FLAGSTAT_MERGED_LIBRARIES' {
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/final_bams/${params.genotyping_source}/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
]
}
@@ -1582,8 +1497,8 @@ process {
// GENOTYPING
//
withName: SAMTOOLS_MPILEUP_PILEUPCALLER {
- tag = { "${meta.reference}|${meta.strandedness}" }
- ext.args = [
+ tag = { "${meta.reference}|${meta.strandedness}" }
+ ext.args = [
"-B",
"-q ${params.genotyping_pileupcaller_min_base_quality}",
"-Q ${params.genotyping_pileupcaller_min_map_quality}",
@@ -1595,26 +1510,28 @@ process {
}
withName: SEQUENCETOOLS_PILEUPCALLER {
- tag = { "${meta.reference}|${meta.strandedness}" }
- ext.args = {[
- "--${params.genotyping_pileupcaller_method}",
- params.genotyping_pileupcaller_transitions_mode == "SkipTransitions" ? "--skipTransitions" : params.genotyping_pileupcaller_transitions_mode == "TransitionsMissing" ? "--transitionsMissing" : "",
- "${meta.strandedness}" == 'single' ? "--singleStrandMode" : "" ,
- "--sampleNames", meta.sample_id.join(","),
- "-e pileupcaller.${meta.strandedness}.${meta.reference}"
- ].join(' ').trim() }
+ tag = { "${meta.reference}|${meta.strandedness}" }
+ ext.args = {
+ [
+ "--${params.genotyping_pileupcaller_method}",
+ params.genotyping_pileupcaller_transitions_mode == "SkipTransitions" ? "--skipTransitions" : params.genotyping_pileupcaller_transitions_mode == "TransitionsMissing" ? "--transitionsMissing" : "",
+ "${meta.strandedness}" == 'single' ? "--singleStrandMode" : "",
+ "--sampleNames",
+ meta.sample_id.join(","),
+ "-e pileupcaller.${meta.strandedness}.${meta.reference}",
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.strandedness}_${meta.reference}" }
publishDir = [
- enabled: false // Not published because the output goes through COLLECT_GENOTYPES
+ enabled: false
]
}
withName: COLLECT_GENOTYPES {
- tag = { "${meta.reference}" }
+ tag = { "${meta.reference}" }
ext.prefix = { "pileupcaller_genotypes_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/pileupcaller/data/" },
mode: params.publish_dir_mode,
pattern: '*.{geno,snp,ind}',
@@ -1623,12 +1540,11 @@ process {
}
withName: EIGENSTRATDATABASETOOLS_EIGENSTRATSNPCOVERAGE {
- tag = { "${meta.reference}" }
- ext.args = { "-j ${prefix}.json" }
+ tag = { "${meta.reference}" }
+ ext.args = { "-j ${prefix}.json" }
ext.prefix = { "pileupcaller_genotypes_${meta.reference}_coverage" }
publishDir = [
[
- // stats
path: { "${params.outdir}/genotyping/pileupcaller/stats/" },
mode: params.publish_dir_mode,
pattern: '*.tsv',
@@ -1637,9 +1553,9 @@ process {
}
withName: GATK_REALIGNERTARGETCREATOR {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = [
- params.genotyping_gatk_ug_defaultbasequalities > 0 ? "--defaultBaseQualities ${params.genotyping_gatk_ug_defaultbasequalities}" : "", // Empty string since GATK complains if its default of -1 is provided.
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = [
+ params.genotyping_gatk_ug_defaultbasequalities > 0 ? "--defaultBaseQualities ${params.genotyping_gatk_ug_defaultbasequalities}" : ""
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.reference}_realigntarget" }
publishDir = [
@@ -1648,14 +1564,13 @@ process {
}
withName: GATK_INDELREALIGNER {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = [
- params.genotyping_gatk_ug_defaultbasequalities > 0 ? "--defaultBaseQualities ${params.genotyping_gatk_ug_defaultbasequalities}" : "", // Empty string since GATK complains if its default of -1 is provided.
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = [
+ params.genotyping_gatk_ug_defaultbasequalities > 0 ? "--defaultBaseQualities ${params.genotyping_gatk_ug_defaultbasequalities}" : ""
].join(' ').trim()
ext.prefix = { "${meta.sample_id}_${meta.reference}_realigned" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/gatk_ug/data/" },
mode: params.publish_dir_mode,
pattern: '*.{bam,bai}',
@@ -1665,19 +1580,20 @@ process {
}
withName: GATK_UNIFIEDGENOTYPER {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = {[
- "--sample_ploidy ${meta2.ploidy}",
- "-stand_call_conf ${params.genotyping_gatk_call_conf}",
- "-dcov ${params.genotyping_gatk_ug_downsample}",
- "--output_mode ${params.genotyping_gatk_ug_out_mode}",
- "--genotype_likelihoods_model ${params.genotyping_gatk_ug_genotype_mode}",
- params.genotyping_gatk_ug_defaultbasequalities > 0 ? "--defaultBaseQualities ${params.genotyping_gatk_ug_defaultbasequalities}" : "", // Empty string since GATK complains if its default of -1 is provided.
- ].join(' ').trim() }
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = {
+ [
+ "--sample_ploidy ${meta2.ploidy}",
+ "-stand_call_conf ${params.genotyping_gatk_call_conf}",
+ "-dcov ${params.genotyping_gatk_ug_downsample}",
+ "--output_mode ${params.genotyping_gatk_ug_out_mode}",
+ "--genotype_likelihoods_model ${params.genotyping_gatk_ug_genotype_mode}",
+ params.genotyping_gatk_ug_defaultbasequalities > 0 ? "--defaultBaseQualities ${params.genotyping_gatk_ug_defaultbasequalities}" : "",
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/gatk_ug/data/" },
mode: params.publish_dir_mode,
pattern: '*.vcf.gz',
@@ -1686,12 +1602,11 @@ process {
}
withName: BCFTOOLS_INDEX_UG {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = "--tbi" //tbi indices for consistency with GATK HC
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = "--tbi"
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/gatk_ug/data/" },
mode: params.publish_dir_mode,
pattern: '*.vcf.gz.tbi',
@@ -1700,18 +1615,18 @@ process {
}
withName: GATK4_HAPLOTYPECALLER {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = {[
- // Option names have changed from underscore_separated to hyphen-separated in GATK4
- "--sample-ploidy ${meta2.ploidy}",
- "-stand-call-conf ${params.genotyping_gatk_call_conf}",
- "--output-mode ${params.genotyping_gatk_hc_out_mode}",
- "--emit-ref-confidence ${params.genotyping_gatk_hc_emitrefconf}",
- ].join(' ').trim() }
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = {
+ [
+ "--sample-ploidy ${meta2.ploidy}",
+ "-stand-call-conf ${params.genotyping_gatk_call_conf}",
+ "--output-mode ${params.genotyping_gatk_hc_out_mode}",
+ "--emit-ref-confidence ${params.genotyping_gatk_hc_emitrefconf}",
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/gatk_hc/data/" },
mode: params.publish_dir_mode,
pattern: '*.{vcf.gz,vcf.gz.tbi}',
@@ -1720,16 +1635,17 @@ process {
}
withName: FREEBAYES {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = {[
- "-p ${ref_meta.ploidy}",
- "-C ${params.genotyping_freebayes_min_alternate_count}",
- params.genotyping_freebayes_skip_coverage != 0 ? "-g ${params.genotyping_freebayes_skip_coverage}" : "",
- ].join(' ').trim() }
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = {
+ [
+ ref_meta.ploidy ? "-p ${ref_meta.ploidy}" : '',
+ "-C ${params.genotyping_freebayes_min_alternate_count}",
+ params.genotyping_freebayes_skip_coverage != 0 ? "-g ${params.genotyping_freebayes_skip_coverage}" : "",
+ ].join(' ').trim()
+ }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/freebayes/data/" },
mode: params.publish_dir_mode,
pattern: '*.vcf.gz',
@@ -1738,12 +1654,11 @@ process {
}
withName: BCFTOOLS_INDEX_FREEBAYES {
- tag = { "${meta.reference}|${meta.sample_id}" }
- ext.args = "--tbi" //tbi indices for consistency with GATK HC
+ tag = { "${meta.reference}|${meta.sample_id}" }
+ ext.args = "--tbi"
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/freebayes/data/" },
mode: params.publish_dir_mode,
pattern: '*.vcf.gz.tbi',
@@ -1752,11 +1667,10 @@ process {
}
withName: BCFTOOLS_STATS_GENOTYPING {
- tag = { "${meta.reference}|${meta.sample_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}" }
ext.prefix = { "${meta.sample_id}_${meta.reference}" }
publishDir = [
[
- // stats
path: { "${params.outdir}/genotyping/bcftools/stats/" },
mode: params.publish_dir_mode,
pattern: '*.txt',
@@ -1765,12 +1679,12 @@ process {
}
withName: ANGSD_GL {
- tag = { "${meta.reference}" }
- ext.args = {
+ tag = { "${meta.reference}" }
+ ext.args = {
gl_model = params.genotyping_angsd_glmodel == 'samtools' ? 1 : params.genotyping_angsd_glmodel == 'gatk' ? 2 : params.genotyping_angsd_glmodel == 'soapsnp' ? 3 : 4
gl_format = params.genotyping_angsd_glformat == 'binary' ? 1 : params.genotyping_angsd_glformat == 'beagle_binary' ? 2 : params.genotyping_angsd_glformat == 'binary_three' ? 3 : 4
[
- ( gl_format == 2 || gl_format == 3 ) ? '-doMajorMinor 1': '',
+ gl_format == 2 || gl_format == 3 ? '-doMajorMinor 1' : '',
"-GL ${gl_model}",
"-doGlf ${gl_format}",
].join(' ').trim()
@@ -1778,7 +1692,6 @@ process {
ext.prefix = { "angsd_${meta.reference}" }
publishDir = [
[
- // data
path: { "${params.outdir}/genotyping/angsd/data/" },
mode: params.publish_dir_mode,
pattern: '*.{glf,beagle}.gz',
diff --git a/conf/test_microbial.config b/conf/test_microbial.config
index dd9eec06..4c45e5db 100644
--- a/conf/test_microbial.config
+++ b/conf/test_microbial.config
@@ -14,7 +14,7 @@ process {
resourceLimits = [
cpus: 4,
memory: '15.GB',
- time: '1.h'
+ time: '1.h',
]
}
@@ -29,7 +29,7 @@ params {
fasta_sheet = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
// Host Removal
- run_host_removal = true
+ run_host_removal = true
// Preprocessing
sequencing_qc_tool = 'falco'
@@ -50,16 +50,11 @@ params {
metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/krakenuniq/testdb-krakenuniq.tar.gz'
run_host_removal = true
- // Manipulate Damage
- run_mapdamage_rescaling = true
-
// Bedtools coverage
run_bedtools_coverage = true
// Genotyping
run_genotyping = true
- genotyping_source = 'rescaled'
+ genotyping_source = 'raw'
genotyping_tool = 'freebayes'
-
-
}
diff --git a/subworkflows/local/manipulate_damage.nf b/subworkflows/local/manipulate_damage.nf
index bc8d96cb..4b8b8e7d 100644
--- a/subworkflows/local/manipulate_damage.nf
+++ b/subworkflows/local/manipulate_damage.nf
@@ -2,177 +2,171 @@
// Calculate PMD scores, trim, or rescale DNA damage from mapped reads.
//
-include { addNewMetaFromAttributes } from '../../subworkflows/local/utils_nfcore_eager_pipeline/main'
+include { addNewMetaFromAttributes } from '../../subworkflows/local/utils_nfcore_eager_pipeline/main'
-include { BEDTOOLS_MASKFASTA } from '../../modules/nf-core/bedtools/maskfasta/main'
-include { MAPDAMAGE2 } from '../../modules/nf-core/mapdamage2/main'
-include { PMDTOOLS_FILTER } from '../../modules/nf-core/pmdtools/filter/main'
-include { BAMUTIL_TRIMBAM } from '../../modules/nf-core/bamutil/trimbam/main'
-include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DAMAGE_RESCALED } from '../../modules/nf-core/samtools/index/main'
-include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DAMAGE_FILTERED } from '../../modules/nf-core/samtools/index/main'
-include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DAMAGE_TRIMMED } from '../../modules/nf-core/samtools/index/main'
-include { SAMTOOLS_FLAGSTAT as SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED } from '../../modules/nf-core/samtools/flagstat/main'
+include { BEDTOOLS_MASKFASTA } from '../../modules/nf-core/bedtools/maskfasta/main'
+include { MAPDAMAGE2 } from '../../modules/nf-core/mapdamage2/main'
+include { PMDTOOLS_FILTER } from '../../modules/nf-core/pmdtools/filter/main'
+include { BAMUTIL_TRIMBAM } from '../../modules/nf-core/bamutil/trimbam/main'
+include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DAMAGE_RESCALED } from '../../modules/nf-core/samtools/index/main'
+include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DAMAGE_FILTERED } from '../../modules/nf-core/samtools/index/main'
+include { SAMTOOLS_INDEX as SAMTOOLS_INDEX_DAMAGE_TRIMMED } from '../../modules/nf-core/samtools/index/main'
+include { SAMTOOLS_FLAGSTAT as SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED } from '../../modules/nf-core/samtools/flagstat/main'
// TODO: Add required channels and channel manipulations for reference-dependent bed masking before pmdtools. Requires multi-ref support before implementation.
workflow MANIPULATE_DAMAGE {
take:
- ch_bam_bai // [ [ meta ], bam , bai ]
- ch_fasta // [ [ meta ], fasta ]
- ch_pmd_masking // [ [ meta ], masked_fasta, bed_for_masking ]
+ ch_bam_bai // [ [ meta ], bam , bai ]
+ ch_fasta // [ [ meta ], fasta ]
+ ch_fasta_elongated // [ [ meta ], fasta ]
+ ch_pmd_masking // [ [ meta ], masked_fasta, bed_for_masking ]
main:
- ch_versions = Channel.empty()
- ch_rescaled_bams = Channel.empty()
- ch_pmd_filtered_bams = Channel.empty()
- ch_trimmed_bams = Channel.empty()
- ch_pmd_filtered_flagstat = Channel.empty() // Only run flagstat on pmd filtered bam, since rescaling and trimming does not change the number of reads
+ ch_versions = Channel.empty()
+ ch_rescaled_bams = Channel.empty()
+ ch_pmd_filtered_bams = Channel.empty()
+ ch_trimmed_bams = Channel.empty()
+ ch_pmd_filtered_flagstat = Channel.empty()
+ // Only run flagstat on pmd filtered bam, since rescaling and trimming does not change the number of reads
// Ensure correct reference is associated with each bam_bai pair
- ch_refs = ch_fasta
- .map {
+ if (params.run_mapdamage_rescaling) {
+ ch_refs = ch_fasta_elongated.map {
// Prepend a new meta that contains the meta.id value as the new_meta.reference attribute
- addNewMetaFromAttributes( it, "id" , "reference" , false )
+ addNewMetaFromAttributes(it, "id", "reference", false)
}
+ }
+ else {
+ ch_refs = ch_fasta.map {
+ // Prepend a new meta that contains the meta.id value as the new_meta.reference attribute
+ addNewMetaFromAttributes(it, "id", "reference", false)
+ }
+ }
+
ch_input_for_damage_manipulation = ch_bam_bai
.map {
// Prepend a new meta that contains the meta.reference value as the new_meta.reference attribute
- addNewMetaFromAttributes( it, "reference" , "reference" , false )
+ addNewMetaFromAttributes(it, "reference", "reference", false)
}
- .combine( ch_refs, by: 0 ) // [ [combine_meta], [meta], bam, bai, [ref_meta], fasta ]
-
- if ( params.run_mapdamage_rescaling ) {
- ch_mapdamage_prep = ch_input_for_damage_manipulation
- .branch {
- ignore_me, meta, bam, bai, ref_meta, fasta ->
- skip: meta.damage_treatment == 'full'
- no_skip: true
- }
+ .combine(ch_refs, by: 0)
+ // [ [combine_meta], [meta], bam, bai, [ref_meta], fasta ]
- ch_skip_rescale = ch_mapdamage_prep.skip
- .map {
- ignore_me, meta, bam, bai, ref_meta, fasta ->
- [ meta, bam, bai ]
- }
+ if (params.run_mapdamage_rescaling) {
+ ch_mapdamage_prep = ch_input_for_damage_manipulation.branch { ignore_me, meta, bam, bai, ref_meta, fasta ->
+ skip: meta.damage_treatment == 'full'
+ no_skip: true
+ }
- ch_mapdamage_input = ch_mapdamage_prep.no_skip
- .multiMap {
- ignore_me, meta, bam, bai, ref_meta, fasta ->
- bam: [ meta, bam ]
- fasta: fasta
- }
+ ch_skip_rescale = ch_mapdamage_prep.skip.map { ignore_me, meta, bam, bai, ref_meta, fasta ->
+ [meta, bam, bai]
+ }
+
+ ch_mapdamage_input = ch_mapdamage_prep.no_skip.multiMap { ignore_me, meta, bam, bai, ref_meta, fasta ->
+ bam: [meta, bam]
+ fasta: fasta
+ }
- MAPDAMAGE2( ch_mapdamage_input.bam, ch_mapdamage_input.fasta )
- ch_versions = ch_versions.mix( MAPDAMAGE2.out.versions.first() )
+ MAPDAMAGE2(ch_mapdamage_input.bam, ch_mapdamage_input.fasta)
+ ch_versions = ch_versions.mix(MAPDAMAGE2.out.versions.first())
- SAMTOOLS_INDEX_DAMAGE_RESCALED( MAPDAMAGE2.out.rescaled )
- ch_versions = ch_versions.mix( SAMTOOLS_INDEX_DAMAGE_RESCALED.out.versions.first() )
+ SAMTOOLS_INDEX_DAMAGE_RESCALED(MAPDAMAGE2.out.rescaled)
+ ch_versions = ch_versions.mix(SAMTOOLS_INDEX_DAMAGE_RESCALED.out.versions.first())
ch_rescaled_index = params.fasta_largeref ? SAMTOOLS_INDEX_DAMAGE_RESCALED.out.csi : SAMTOOLS_INDEX_DAMAGE_RESCALED.out.bai
// TODO When adding library-level data merging pre-genotyping, make sure that rescaled bams are not merged in any way as the underlying damage model could differ between libraries
- ch_rescaled_bams = MAPDAMAGE2.out.rescaled.join(ch_rescaled_index)
- .mix(ch_skip_rescale) // Should these be mixed actually, or excluded? Might not make sense to take rescaled and non-rescaled bams togetehr for anything downstream.
+ ch_rescaled_bams = MAPDAMAGE2.out.rescaled
+ .join(ch_rescaled_index)
+ .mix(ch_skip_rescale)
}
- if ( params.run_pmd_filtering ) {
+ if (params.run_pmd_filtering) {
ch_masking_prep = ch_pmd_masking
- .combine( ch_fasta, by: 0 ) // [ [meta], masked_fasta, bed, fasta ]
- .branch {
- meta, masked_fasta, bed, fasta ->
- alreadymasked: masked_fasta != ""
- tobemasked: masked_fasta == "" && bed != ""
- nomasking: masked_fasta == "" && bed == ""
- }
-
- ch_masking_input = ch_masking_prep.tobemasked
- .multiMap{
- meta, masked_fasta, bed, fasta ->
- bed: [ meta, bed ]
- fasta: fasta
- }
-
- BEDTOOLS_MASKFASTA( ch_masking_input.bed, ch_masking_input.fasta )
+ .combine(ch_fasta, by: 0)
+ .branch { meta, masked_fasta, bed, fasta ->
+ alreadymasked: masked_fasta != ""
+ tobemasked: masked_fasta == "" && bed != ""
+ nomasking: masked_fasta == "" && bed == ""
+ }
+
+ ch_masking_input = ch_masking_prep.tobemasked.multiMap { meta, masked_fasta, bed, fasta ->
+ bed: [meta, bed]
+ fasta: fasta
+ }
+
+ BEDTOOLS_MASKFASTA(ch_masking_input.bed, ch_masking_input.fasta)
ch_masking_output = BEDTOOLS_MASKFASTA.out.fasta
- ch_versions = ch_versions.mix( BEDTOOLS_MASKFASTA.out.versions.first() )
-
- ch_already_masked = ch_masking_prep.alreadymasked
- .map {
- meta, masked_fasta, bed, fasta ->
- [ meta, masked_fasta ]
- }
-
- ch_no_masking = ch_masking_prep.nomasking
- .map {
- meta, masked_fasta, bed, fasta ->
- [ meta, fasta ]
- }
-
- ch_pmd_fastas = ch_masking_output.mix( ch_already_masked, ch_no_masking )
- .map {
- // Prepend a new meta that contains the meta.id value as the new_meta.reference attribute
- addNewMetaFromAttributes( it, "id" , "reference" , false )
- }
+ ch_versions = ch_versions.mix(BEDTOOLS_MASKFASTA.out.versions.first())
+
+ ch_already_masked = ch_masking_prep.alreadymasked.map { meta, masked_fasta, bed, fasta ->
+ [meta, masked_fasta]
+ }
+
+ ch_no_masking = ch_masking_prep.nomasking.map { meta, masked_fasta, bed, fasta ->
+ [meta, fasta]
+ }
+
+ ch_pmd_fastas = ch_masking_output
+ .mix(ch_already_masked, ch_no_masking)
+ .map {
+ // Prepend a new meta that contains the meta.id value as the new_meta.reference attribute
+ addNewMetaFromAttributes(it, "id", "reference", false)
+ }
ch_pmdtools_input = ch_bam_bai
- .map { addNewMetaFromAttributes( it, "reference" , "reference" , false ) }
- .combine( ch_pmd_fastas, by: 0 ) // [ [combine_meta], [meta], bam, bai, [ref_meta] fasta ]
- .multiMap {
- combine_meta, meta, bam, bai, ref_meta, fasta ->
- bam: [ meta, bam, bai ]
- fasta: fasta
- }
-
- PMDTOOLS_FILTER( ch_pmdtools_input.bam, params.damage_manipulation_pmdtools_threshold, ch_pmdtools_input.fasta )
- ch_versions = ch_versions.mix( PMDTOOLS_FILTER.out.versions.first() )
-
- SAMTOOLS_INDEX_DAMAGE_FILTERED( PMDTOOLS_FILTER.out.bam )
- ch_versions = ch_versions.mix( SAMTOOLS_INDEX_DAMAGE_FILTERED.out.versions.first() )
+ .map { addNewMetaFromAttributes(it, "reference", "reference", false) }
+ .combine(ch_pmd_fastas, by: 0)
+ .multiMap { combine_meta, meta, bam, bai, ref_meta, fasta ->
+ bam: [meta, bam, bai]
+ fasta: fasta
+ }
+
+ PMDTOOLS_FILTER(ch_pmdtools_input.bam, params.damage_manipulation_pmdtools_threshold, ch_pmdtools_input.fasta)
+ ch_versions = ch_versions.mix(PMDTOOLS_FILTER.out.versions.first())
+
+ SAMTOOLS_INDEX_DAMAGE_FILTERED(PMDTOOLS_FILTER.out.bam)
+ ch_versions = ch_versions.mix(SAMTOOLS_INDEX_DAMAGE_FILTERED.out.versions.first())
ch_filtered_index = params.fasta_largeref ? SAMTOOLS_INDEX_DAMAGE_FILTERED.out.csi : SAMTOOLS_INDEX_DAMAGE_FILTERED.out.bai
- ch_pmd_filtered_bams = PMDTOOLS_FILTER.out.bam.join( ch_filtered_index )
+ ch_pmd_filtered_bams = PMDTOOLS_FILTER.out.bam.join(ch_filtered_index)
- SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED( ch_pmd_filtered_bams )
+ SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED(ch_pmd_filtered_bams)
ch_pmd_filtered_flagstat = SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED.out.flagstat
- ch_versions = ch_versions.mix( SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED.out.versions.first() )
+ ch_versions = ch_versions.mix(SAMTOOLS_FLAGSTAT_DAMAGE_FILTERED.out.versions.first())
}
- if ( params.run_trim_bam ) {
- if ( params.run_pmd_filtering ) {
- ch_to_trim = ch_pmd_filtered_bams
- .map{
- meta, bam, bai ->
- [ meta, bam ]
- }
- } else {
- ch_to_trim = ch_bam_bai
- .map {
- meta, bam, bai ->
- [ meta, bam ]
- }
+ if (params.run_trim_bam) {
+ if (params.run_pmd_filtering) {
+ ch_to_trim = ch_pmd_filtered_bams.map { meta, bam, bai ->
+ [meta, bam]
+ }
}
-
- ch_trimbam_input = ch_to_trim
- .map {
- meta, bam ->
- trim_left = meta.strandedness == 'single' ? ( meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_single_stranded_none_udg_left : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_single_stranded_half_udg_left : 0 ) : ( meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_double_stranded_none_udg_left : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_double_stranded_half_udg_left : 0 )
- trim_right = meta.strandedness == 'single' ? ( meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_single_stranded_none_udg_right : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_single_stranded_half_udg_right : 0 ) : ( meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_double_stranded_none_udg_right : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_double_stranded_half_udg_right : 0 )
- [ meta, bam, trim_left, trim_right ]
+ else {
+ ch_to_trim = ch_bam_bai.map { meta, bam, bai ->
+ [meta, bam]
}
+ }
+
+ ch_trimbam_input = ch_to_trim.map { meta, bam ->
+ def trim_left = meta.strandedness == 'single' ? (meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_single_stranded_none_udg_left : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_single_stranded_half_udg_left : 0) : (meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_double_stranded_none_udg_left : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_double_stranded_half_udg_left : 0)
+ def trim_right = meta.strandedness == 'single' ? (meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_single_stranded_none_udg_right : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_single_stranded_half_udg_right : 0) : (meta.damage_treatment == 'none' ? params.damage_manipulation_bamutils_trim_double_stranded_none_udg_right : meta.damage_treatment == 'half' ? params.damage_manipulation_bamutils_trim_double_stranded_half_udg_right : 0)
+ [meta, bam, trim_left, trim_right]
+ }
- BAMUTIL_TRIMBAM( ch_trimbam_input )
- ch_versions = ch_versions.mix( BAMUTIL_TRIMBAM.out.versions.first() )
+ BAMUTIL_TRIMBAM(ch_trimbam_input)
+ ch_versions = ch_versions.mix(BAMUTIL_TRIMBAM.out.versions.first())
- SAMTOOLS_INDEX_DAMAGE_TRIMMED( BAMUTIL_TRIMBAM.out.bam )
- ch_versions = ch_versions.mix( SAMTOOLS_INDEX_DAMAGE_TRIMMED.out.versions.first() )
+ SAMTOOLS_INDEX_DAMAGE_TRIMMED(BAMUTIL_TRIMBAM.out.bam)
+ ch_versions = ch_versions.mix(SAMTOOLS_INDEX_DAMAGE_TRIMMED.out.versions.first())
ch_trimmed_index = params.fasta_largeref ? SAMTOOLS_INDEX_DAMAGE_TRIMMED.out.csi : SAMTOOLS_INDEX_DAMAGE_TRIMMED.out.bai
- ch_trimmed_bams = BAMUTIL_TRIMBAM.out.bam.join( ch_trimmed_index )
+ ch_trimmed_bams = BAMUTIL_TRIMBAM.out.bam.join(ch_trimmed_index)
}
emit:
- rescaled = ch_rescaled_bams // [ meta, bam, bai ]
- filtered = ch_pmd_filtered_bams // [ meta, bam, bai ]
- trimmed = ch_trimmed_bams // [ meta, bam, bai ]
+ rescaled = ch_rescaled_bams // [ meta, bam, bai ]
+ filtered = ch_pmd_filtered_bams // [ meta, bam, bai ]
+ trimmed = ch_trimmed_bams // [ meta, bam, bai ]
flagstat = ch_pmd_filtered_flagstat // [ meta, flagstat ]
versions = ch_versions
}
diff --git a/workflows/eager.nf b/workflows/eager.nf
index dd98a790..104e4057 100644
--- a/workflows/eager.nf
+++ b/workflows/eager.nf
@@ -433,9 +433,9 @@ workflow EAGER {
ch_versions = ch_versions.mix(PRESEQ_CCURVE.out.versions)
}
else if (!params.mapstats_skip_preseq && params.mapstats_preseq_mode == 'lc_extrap') {
- PRESEQ_LCEXTRAP(ch_reads_for_deduplication.map { [it[0], it[1]] })
- ch_multiqc_files = ch_multiqc_files.mix(PRESEQ_LCEXTRAP.out.lc_extrap.collect { it[1] }.ifEmpty([]))
- ch_versions = ch_versions.mix(PRESEQ_LCEXTRAP.out.versions)
+ PRESEQ_LCEXTRAP(ch_reads_for_deduplication.map { [it[0], it[1]] })
+ ch_multiqc_files = ch_multiqc_files.mix(PRESEQ_LCEXTRAP.out.lc_extrap.collect { it[1] }.ifEmpty([]))
+ ch_versions = ch_versions.mix(PRESEQ_LCEXTRAP.out.versions)
}
//
@@ -525,7 +525,7 @@ workflow EAGER {
//
if (params.run_mapdamage_rescaling || params.run_pmd_filtering || params.run_trim_bam) {
- MANIPULATE_DAMAGE(ch_dedupped_bams, ch_fasta_for_deduplication.fasta, REFERENCE_INDEXING.out.pmd_masking)
+ MANIPULATE_DAMAGE(ch_dedupped_bams, ch_fasta_for_deduplication.fasta, REFERENCE_INDEXING.out.reference, REFERENCE_INDEXING.out.pmd_masking)
ch_multiqc_files = ch_multiqc_files.mix(MANIPULATE_DAMAGE.out.flagstat.collect { it[1] }.ifEmpty([]))
ch_versions = ch_versions.mix(MANIPULATE_DAMAGE.out.versions)
ch_bams_for_library_merge = params.genotyping_source == 'rescaled' ? MANIPULATE_DAMAGE.out.rescaled : params.genotyping_source == 'pmd' ? MANIPULATE_DAMAGE.out.filtered : params.genotyping_source == 'trimmed' ? MANIPULATE_DAMAGE.out.trimmed : ch_merged_dedup_bams
@@ -552,7 +552,7 @@ workflow EAGER {
ch_bams_for_genotyping,
ch_reference_for_genotyping,
REFERENCE_INDEXING.out.pileupcaller_bed_snp.ifEmpty([[], [], []]),
- REFERENCE_INDEXING.out.dbsnp.ifEmpty([[], []])
+ REFERENCE_INDEXING.out.dbsnp.ifEmpty([[], []]),
)
ch_versions = ch_versions.mix(GENOTYPE.out.versions)
@@ -565,9 +565,9 @@ workflow EAGER {
softwareVersionsToYAML(ch_versions)
.collectFile(
storeDir: "${params.outdir}/pipeline_info",
- name: 'nf_core_' + 'eager_software_' + 'mqc_' + 'versions.yml',
+ name: 'nf_core_' + 'eager_software_' + 'mqc_' + 'versions.yml',
sort: true,
- newLine: true
+ newLine: true,
)
.set { ch_collated_versions }
@@ -605,7 +605,7 @@ workflow EAGER {
ch_multiqc_files = ch_multiqc_files.mix(
ch_methods_description.collectFile(
name: 'methods_description_mqc.yaml',
- sort: true
+ sort: true,
)
)
@@ -619,7 +619,7 @@ workflow EAGER {
ch_multiqc_custom_config.toList(),
ch_multiqc_logo.toList(),
[],
- []
+ [],
)
emit:
From 89262a279ecb20f104f886ba7a94882cbd122374 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 28 Mar 2025 10:25:51 +0100
Subject: [PATCH 21/24] Update conf/modules.config
Co-authored-by: Ian Light-Maka <86308592+ilight1542@users.noreply.github.com>
---
conf/modules.config | 2 ++
1 file changed, 2 insertions(+)
diff --git a/conf/modules.config b/conf/modules.config
index c102e4b9..4cce66c0 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1619,6 +1619,8 @@ process {
ext.args = {
[
"--sample-ploidy ${meta2.ploidy}",
+ " ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
+
"-stand-call-conf ${params.genotyping_gatk_call_conf}",
"--output-mode ${params.genotyping_gatk_hc_out_mode}",
"--emit-ref-confidence ${params.genotyping_gatk_hc_emitrefconf}",
From 04c75a174cb1fe63013060a9641099f12d0550e4 Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 28 Mar 2025 10:25:58 +0100
Subject: [PATCH 22/24] Update conf/modules.config
Co-authored-by: Ian Light-Maka <86308592+ilight1542@users.noreply.github.com>
---
conf/modules.config | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/conf/modules.config b/conf/modules.config
index 4cce66c0..3e91fe13 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1583,7 +1583,9 @@ process {
tag = { "${meta.reference}|${meta.sample_id}" }
ext.args = {
[
- "--sample_ploidy ${meta2.ploidy}",
+ "--sample-ploidy ${meta2.ploidy}",
+ " ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
+
"-stand_call_conf ${params.genotyping_gatk_call_conf}",
"-dcov ${params.genotyping_gatk_ug_downsample}",
"--output_mode ${params.genotyping_gatk_ug_out_mode}",
From 13bc21a2c213b540d6d75d8ebd9cae17113abfcc Mon Sep 17 00:00:00 2001
From: Judith Ballesteros <judith.vballesteros@gmail.com>
Date: Fri, 28 Mar 2025 11:32:32 +0100
Subject: [PATCH 23/24] Update conf/modules.config
Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>
---
conf/modules.config | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/conf/modules.config b/conf/modules.config
index cc96d02f..21a34e65 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -1617,7 +1617,7 @@ process {
ext.args = {
[
"--sample-ploidy ${meta2.ploidy}",
- " ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
+ ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
"-stand_call_conf ${params.genotyping_gatk_call_conf}",
"-dcov ${params.genotyping_gatk_ug_downsample}",
From 396fd258ec32aada46cec4b16df5d38b695dd532 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Fri, 28 Mar 2025 10:49:42 +0000
Subject: [PATCH 24/24] And for haplotypecaller
---
conf/modules.config | 31 +++++++++++++------------------
1 file changed, 13 insertions(+), 18 deletions(-)
diff --git a/conf/modules.config b/conf/modules.config
index cc96d02f..e9d1b05f 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -331,17 +331,17 @@ process {
// BAM INPUT
//
-
+
withName: SAMTOOLS_INDEX_BAM_INPUT {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
publishDir = [
enabled: false
]
}
withName: SAMTOOLS_MERGE_LANES_BAMINPUT {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.run_fastq_sharding ? "-c -p" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.run_fastq_sharding ? "-c -p" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
enabled: false
@@ -349,36 +349,33 @@ process {
}
withName: SAMTOOLS_SORT_MERGED_LANES_BAMINPUT {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_sorted" }
publishDir = [
- // data
path: { "${params.outdir}/mapping/${params.mapping_tool}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bam}'
+ pattern: '*.{bam}',
]
}
withName: SAMTOOLS_INDEX_MERGED_LANES_BAMINPUT {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
- ext.args = { params.fasta_largeref ? "-c" : "" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ ext.args = { params.fasta_largeref ? "-c" : "" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
publishDir = [
- // data
path: { "${params.outdir}/mapping/${params.mapping_tool}/data/" },
mode: params.publish_dir_mode,
- pattern: '*.{bai,csi}'
+ pattern: '*.{bai,csi}',
]
}
withName: SAMTOOLS_FLAGSTAT_MERGED_LANES_BAMINPUT {
- tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+ tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}_sorted" }
publishDir = [
- // stats
path: { "${params.outdir}/mapping/bam_input/stats/" },
mode: params.publish_dir_mode,
- pattern: '*.flagstat'
+ pattern: '*.flagstat',
]
}
@@ -1617,8 +1614,7 @@ process {
ext.args = {
[
"--sample-ploidy ${meta2.ploidy}",
- " ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
-
+ ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
"-stand_call_conf ${params.genotyping_gatk_call_conf}",
"-dcov ${params.genotyping_gatk_ug_downsample}",
"--output_mode ${params.genotyping_gatk_ug_out_mode}",
@@ -1654,8 +1650,7 @@ process {
ext.args = {
[
"--sample-ploidy ${meta2.ploidy}",
- " ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
-
+ ref_meta.ploidy ? "--sample-ploidy ${ref_meta.ploidy}" : "--sample-ploidy 2",
"-stand-call-conf ${params.genotyping_gatk_call_conf}",
"--output-mode ${params.genotyping_gatk_hc_out_mode}",
"--emit-ref-confidence ${params.genotyping_gatk_hc_emitrefconf}",