Merge pull request #536 from FriederikeHanssen/step_md

Add step markduplicates & allow BAM input for all steps
nf-core · May 12, 2022 · b76d09d · b76d09d
2 parents 3bcf3bb + e044d9b
commit b76d09d
Show file tree

Hide file tree

Showing 30 changed files with 2,671 additions and 2,095 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -40,9 +40,12 @@ jobs:
           - "gatk4_spark"
           - "haplotypecaller"
           - "manta"
+          - "markduplicates"
           - "mutect2"
           - "msisensorpro"
           # - 'save_bam_mapped'
+          - "prepare_recalibration"
+          - "recalibrate"
           - "variantcalling_channel"
           - "skip_markduplicates"
           - "strelka"

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -23,6 +23,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#512](https://github.com/nf-core/sarek/pull/512), [#531](https://github.com/nf-core/sarek/pull/531), [#537](https://github.com/nf-core/sarek/pull/537) - Subway map for pipeline
 - [#522](https://github.com/nf-core/sarek/pull/522) - Add QC for vcf files & MultiQC
 - [#533](https://github.com/nf-core/sarek/pull/533) - Add param `--only_paired_variant_calling` to allow skipping of germline variantcalling for paired samples
+- [#536](https://github.com/nf-core/sarek/pull/536) - Add `--step markduplicates` to start from duplicate marking, `--step prepare_recalibration` now ONLY starts at process `BaseRecalibrator` & adding `bam` and `cram` input support for `--step` `markduplicates`, `prepare_recalibration`, `recalibrate`, and `variant_calling`
 - [#538](https://github.com/nf-core/sarek/pull/538) - Add param `--seq_platform`, default: `ILLUMINA`
 
 ### Changed

diff --git a/conf/modules.config b/conf/modules.config
@@ -91,7 +91,7 @@ process {
     }
 
     withName: 'TABIX_DBSNP' {
-        ext.when         = { !params.dbsnp_tbi && params.dbsnp && (params.step == "mapping" || params.step == "prepare_recalibration") || params.tools && (params.tools.contains('controlfreec') || params.tools.contains('haplotypecaller') || params.tools.contains('mutect2')) }
+        ext.when         = { !params.dbsnp_tbi && params.dbsnp && (params.step == "mapping" || params.step == "markduplicates" || params.step == "prepare_recalibration") || params.tools && (params.tools.contains('controlfreec') || params.tools.contains('haplotypecaller') || params.tools.contains('mutect2')) }
         publishDir       = [
             enabled: params.save_reference,
             mode: params.publish_dir_mode,
@@ -111,7 +111,7 @@ process {
     }
 
     withName: 'TABIX_KNOWN_INDELS' {
-        ext.when         = { !params.known_indels_tbi && params.known_indels && (params.step == 'mapping' || params.step == 'prepare_recalibration') }
+        ext.when         = { !params.known_indels_tbi && params.known_indels && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration') }
         publishDir       = [
             enabled: params.save_reference,
             mode: params.publish_dir_mode,
@@ -294,6 +294,32 @@ process {
 
 // MARKDUPLICATES
 
+    withName: 'SAMTOOLS_CRAMTOBAM'{
+        ext.args = "-b"
+    }
+
+    withName: 'SAMTOOLS_BAMTOCRAM.*' {
+        // BAM provided for step Markduplicates either run through MD or Convert -> then saved as md.cram
+        // BAM files provided for step prepare_recal are converted and run through BQSR -> then saved as md.cram
+        // BAM files provided for step recal are converted and run through BQSR II -> then saved as md.cram
+        ext.args = "-C"
+        ext.prefix       = { "${meta.id}.md" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/preprocessing/${meta.id}/markduplicates" },
+            pattern: "*{cram,crai}"
+        ]
+    }
+
+    withName: 'SAMTOOLS_BAMTOCRAM_VARIANTCALLING' {
+        ext.prefix       = { "${meta.id}.recal" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/preprocessing/${meta.id}/recalibrated" },
+            pattern: "*{cram,crai}"
+        ]
+    }
+
     withName: 'GATK4_ESTIMATELIBRARYCOMPLEXITY|GATK4_MARKDUPLICATES' {
         ext.prefix       = { "${meta.id}.md" }
         publishDir       = [
@@ -325,15 +351,6 @@ process {
         ext.when         = { !(params.skip_tools && params.skip_tools.contains('markduplicates')) }
     }
 
-    withName: 'SAMTOOLS_BAMTOCRAM' {
-        ext.prefix       = { "${meta.id}.md" }
-        publishDir       = [
-            mode: params.publish_dir_mode,
-            path: { "${params.outdir}/preprocessing/${meta.id}/markduplicates" },
-            pattern: "*{cram,crai}"
-        ]
-    }
-
     withName: 'INDEX_MARKDUPLICATES' {
         publishDir       = [
             mode: params.publish_dir_mode,
@@ -408,17 +425,6 @@ process {
         ]
     }
 
-    withName: 'QUALIMAP_BAMQC' {
-        ext.args         = '--paint-chromosome-limits --genome-gc-distr HUMAN -skip-duplicated --skip-dup-mode 0 -outformat HTML'
-        ext.prefix       = { "${meta.id}.mapped" }
-        ext.when         = { !(params.skip_tools && params.skip_tools.contains('bamqc')) }
-        publishDir       = [
-            mode: params.publish_dir_mode,
-            path: { "${params.outdir}/reports/qualimap/${meta.id}" },
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
     withName: 'SAMTOOLS_STATS' {
         ext.when         = { !(params.skip_tools && params.skip_tools.contains('samtools')) }
         publishDir       = [
@@ -439,7 +445,7 @@ process {
 
     withName: 'QUALIMAP_BAMQCCRAM' {
         ext.args         = '--paint-chromosome-limits --genome-gc-distr HUMAN -skip-duplicated --skip-dup-mode 0 -outformat HTML'
-        ext.prefix       = { "${meta.id}.recal" }
+        ext.prefix       = { "${meta.id}.mapped" }
         ext.when         = { !(params.skip_tools && params.skip_tools.contains('bamqc')) }
         publishDir       = [
             mode: params.publish_dir_mode,
@@ -448,6 +454,10 @@ process {
         ]
     }
 
+    withName: 'NFCORE_SAREK:SAREK:CRAM_QC:QUALIMAP_BAMQCCRAM' {
+        ext.prefix       = { "${meta.id}.recal" }
+    }
+
     withName: 'NFCORE_SAREK:SAREK:CRAM_QC:SAMTOOLS_STATS' {
         ext.when         = { !(params.skip_tools && params.skip_tools.contains('samtools')) }
         publishDir       = [

diff --git a/conf/test.config b/conf/test.config
@@ -55,13 +55,36 @@ profiles {
     pair {
         params.input               = "${baseDir}/tests/csv/3.0/fastq_pair.csv"
     }
-    prepare_recalibration {
-        params.input               = "${baseDir}/tests/csv/3.0/mapped_single.csv"
+    markduplicates_bam {
+        params.input               = "${baseDir}/tests/csv/3.0/mapped_single_bam.csv"
+        params.step                = 'markduplicates'
+    }
+    markduplicates_cram {
+        params.input               = "${baseDir}/tests/csv/3.0/mapped_single_cram.csv"
+        params.step                = 'markduplicates'
+    }
+    prepare_recalibration_bam {
+        params.input               = "${baseDir}/tests/csv/3.0/mapped_single_bam.csv"
+        params.step                = 'prepare_recalibration'
+    }
+    prepare_recalibration_cram {
+        params.input               = "${baseDir}/tests/csv/3.0/mapped_single_cram.csv"
         params.step                = 'prepare_recalibration'
     }
+    recalibrate_bam {
+        params.input               = "${baseDir}/tests/csv/3.0/prepare_recalibration_single_bam.csv"
+        params.step                = 'recalibrate'
+    }
+    recalibrate_cram {
+        params.input               = "${baseDir}/tests/csv/3.0/prepare_recalibration_single_cram.csv"
+        params.step                = 'recalibrate'
+    }
     save_bam_mapped {
         params.save_bam_mapped     = true
     }
+    skip_bqsr {
+        params.skip_tools          = "baserecalibrator"
+    }
     skip_markduplicates {
         params.skip_tools          = "markduplicates"
     }
@@ -70,8 +93,9 @@ profiles {
         params.save_split_fastqs   = true
     }
     targeted {
-        params.intervals           = "${params.genomes_base}/data/genomics/homo_sapiens/genome/multi_intervals.bed"
-        params.wes                 = true
+        params.intervals               = "${params.genomes_base}/data/genomics/homo_sapiens/genome/genome.multi_intervals.bed"
+        params.wes                     = true
+        params.nucleotides_per_second  = 20
     }
     tools {
         params.input               = "${baseDir}/tests/csv/3.0/recalibrated.csv"
@@ -85,7 +109,6 @@ profiles {
         params.wes                 = true
         params.genome              = 'WBcel235'
         params.vep_genome          = 'WBcel235'
-        //params.vep_cache           =
     }
     tools_germline {
         params.input               = "${baseDir}/tests/csv/3.0/recalibrated_germline.csv"

diff --git a/docs/images/sarek_subway.png b/docs/images/sarek_subway.png