Merge pull request #42 from UMCUGenetics/develop

v0.2.0

BWA-Mapping/bwa-0.7.17_samtools-1.9/Mapping.nf

@@ -1,27 +1,25 @@
 
 
 process BWAMapping {
-    tag {"BWA_Mem ${sample_id} - ${rg_id}"}
+    tag {"BWA Mem ${sample_id} - ${rg_id}"}
     label 'BWA_0_7_17'
     label 'BWA_0_7_17_Mem'
     clusterOptions = workflow.profile == "sge" ? "-l h_vmem=${params.mem}" : ""
     container = 'library://sawibo/default/bioinf-tools:bwa-0.7.17_samtools-1.9'
-
+    shell = ['/bin/bash', '-euo', 'pipefail']
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple (sample_id, rg_id, path(fastq))
 
     output:
-    tuple sample_id, rg_id, file("${rg_id}_sorted.bam"),file("${rg_id}_sorted.bai")
+        tuple (sample_id, rg_id, path("${rg_id}_sorted.bam"),path("${rg_id}_sorted.bai"), emit: mapped_bams)
 
     script:
+        def barcode = rg_id.split('_')[1]
+        def bwa_readgroup = "\"@RG\\tID:${rg_id}\\tSM:${sample_id}\\tPL:ILLUMINA\\tLB:${sample_id}\\tPU:${barcode}\""
 
-    def barcode = rg_id.split('_')[1]
-    def bwa_readgroup = "\"@RG\\tID:${rg_id}\\tSM:${sample_id}\\tPL:ILLUMINA\\tLB:${sample_id}\\tPU:${barcode}\""
-
-    """
-    set -o pipefail
-    bwa mem $params.optional -t ${task.cpus} -R $bwa_readgroup $params.genome_fasta $fastq | \
-    samtools sort > ${rg_id}_sorted.bam
-    samtools index ${rg_id}_sorted.bam ${rg_id}_sorted.bai
-    """
+        """
+        bwa mem $params.optional -t ${task.cpus} -R $bwa_readgroup $params.genome_fasta $fastq | \
+        samtools sort > ${rg_id}_sorted.bam
+        samtools index ${rg_id}_sorted.bam ${rg_id}_sorted.bai
+        """
 }

BWA/0.7.17/BWASW.nf

@@ -6,13 +6,13 @@ process BWASW {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple(sample_id, rg_id, path(fastq))
 
     output:
-    tuple sample_id, rg_id, file("${fastq[0].simpleName}.sam")
+        tuple(sample_id, rg_id, path("${fastq[0].simpleName}.sam"), emit: sam_file)
 
     script:
-    """
-    bwa bwasw -t ${task.cpus} ${params.optional} ${params.genome} ${fastq} > ${fastq[0].simpleName}.sam
-    """
+        """
+        bwa bwasw -t ${task.cpus} ${params.optional} ${params.genome} ${fastq} > ${fastq[0].simpleName}.sam
+        """
 }

BWA/0.7.17/Index.nf

@@ -10,16 +10,14 @@ process Index {
     storeDir = index_loc
 
     input:
-    file(fasta)
+        path(fasta)
 
     output:
-
-    file("${fasta}.{alt,amb,ann,bwt,pac,sa}")
+        path("${fasta}.{alt,amb,ann,bwt,pac,sa}", emit: bwa_index)
 
 
     script:
-    """
-    bwa index $params.optional $fasta
-    """
-
+        """
+        bwa index $params.optional $fasta
+        """
 }

BWA/0.7.17/MEM.nf

@@ -6,16 +6,16 @@ process MEM {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple(sample_id, rg_id, path(fastq))
 
     output:
-    tuple sample_id, rg_id, file("${fastq[0].simpleName}.sam")
+        tuple(sample_id, rg_id, path("${fastq[0].simpleName}.sam"), emit: sam_file)
 
     script:
-    def barcode = rg_id.split('_')[1]
-    def readgroup = "\"@RG\\tID:${rg_id}\\tSM:${sample_id}\\tPL:ILLUMINA\\tLB:${sample_id}\\tPU:${barcode}\""
+        def barcode = rg_id.split('_')[1]
+        def readgroup = "\"@RG\\tID:${rg_id}\\tSM:${sample_id}\\tPL:ILLUMINA\\tLB:${sample_id}\\tPU:${barcode}\""
 
-    """
-    bwa mem -t ${task.cpus} -R ${readgroup} ${params.optional} ${params.genome} ${fastq}  > ${fastq[0].simpleName}.sam
-    """
+        """
+        bwa mem -t ${task.cpus} -R ${readgroup} ${params.optional} ${params.genome} ${fastq} > ${fastq[0].simpleName}.sam
+        """
 }

ControlFREEC/11.5/AssessSignificance.nf

@@ -0,0 +1,18 @@
+process AssessSignificance {
+    tag {"Control Freec AssessSignificance ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_AssessSignificance'
+    container = 'library://sawibo/default/bioinf-tools:freec11.5'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(ratio_file), path(cnv_file))
+
+    output:
+        tuple(sample_id, path("${cnv_file.name}.p.value.txt"), emit: cnv_pvalue)
+
+    script:
+        """
+        cat /bin/assess_significance.R | R --slave --args ${cnv_file} ${ratio_file}
+        """
+}

ControlFREEC/11.5/Freec.nf

@@ -0,0 +1,36 @@
+process Freec {
+    tag {"Control Freec ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_Freec'
+    //TODO: upload to singularity library
+    container = 'library://sawibo/default/bioinf-tools:freec11.5'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(bam_file), path(bai_file))
+
+    output:
+        tuple(sample_id, path("${bam_file.name}_ratio.txt"), path("${bam_file.name}_CNVs"), emit: cnv)
+        tuple(sample_id, path("${bam_file.name}_sample.cpn"), path("${bam_file.name}_ratio.BedGraph"), path("${bam_file.name}_info.txt"), emit: other)
+
+    script:
+        def config = "${sample_id}.config"
+        """
+        touch ${config}
+        echo "[general]" >> ${config}
+        echo "chrLenFile = ${params.chr_len_file}" >> ${config}
+        echo "chrFiles = ${params.chr_files}" >> ${config}
+        echo "gemMappabilityFile = ${params.gem_mappability_file}" >> ${config}
+        echo "ploidy = ${params.ploidy}" >> ${config}
+        echo "window = ${params.window}" >> ${config}
+        echo "telocentromeric = ${params.telocentromeric}" >> ${config}
+        echo "BedGraphOutput=TRUE" >> ${config}
+        echo "maxThreads=${task.cpus}" >> ${config}
+
+        echo "[sample]" >> ${config}
+        echo "inputFormat = BAM" >> ${config}
+        echo "mateFile = ${bam_file}" >> ${config}
+
+        freec -conf ${config}
+        """
+}

ControlFREEC/11.5/MakeGraph.nf

@@ -0,0 +1,18 @@
+process MakeGraph {
+    tag {"Control Freec MakeGraph ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_MakeGraph'
+    container = 'library://sawibo/default/bioinf-tools:freec11.5'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(ratio_file), path(cnv_file))
+
+    output:
+        tuple(sample_id, path("${ratio_file.name}.png"), path("${ratio_file.name}.log2.png"), emit: ratio_png)
+
+    script:
+        """
+        cat /bin/makeGraph.R | R --slave --args ${params.ploidy} ${ratio_file}
+        """
+}

ControlFREEC/11.5/MakeKaryotype.nf

@@ -0,0 +1,18 @@
+process MakeKaryotype {
+    tag {"Control Freec MakeKaryotype ${sample_id}"}
+    label 'ControlFreec_11_5'
+    label 'ControlFreec_11_5_MakeKaryotype'
+    container = 'library://sawibo/default/bioinf-tools:freec11.5'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(ratio_file), path(cnv_file))
+
+    output:
+        tuple(sample_id, path("*_karyotype.pdf"), emit: karyotype_pdf)
+
+    script:
+        """
+        cat /bin/makeKaryotype.R | R --slave --args ${params.ploidy} ${params.maxlevel} ${params.telocentromeric} ${ratio_file}
+        """
+}

FastQC/0.11.5/FastQC.nf

@@ -1,18 +1,18 @@
 process FastQC {
     tag {"FastQC ${sample_id} - ${rg_id}"}
-    label 'FASTQC_0_11_5'
+    label 'FastQC_0_11_5'
     clusterOptions = workflow.profile == "sge" ? "-l h_vmem=${params.mem}" : ""
     container = 'library://sawibo/default/bioinf-tools:fastqc-0.11.5'
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple (sample_id, rg_id, path(fastq) )
 
     output:
-    file "*_fastqc.{zip,html}"
+        path("*_fastqc.{zip,html}", emit: fastqc_reports)
 
     script:
-    """
-    fastqc ${params.optional} -t ${task.cpus} $fastq
-    """
+        """
+        fastqc ${params.optional} -t ${task.cpus} $fastq
+        """
 }

FastQC/0.11.8/FastQC.nf

@@ -5,13 +5,13 @@ process FastQC {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple sample_id, rg_id, file(fastq: "*")
+        tuple(sample_id, rg_id, path(fastq))
 
     output:
-    file "*_fastqc.{zip,html}"
+        path("*_fastqc.{zip,html}", emit: report)
 
     script:
-    """
-    fastqc ${params.optional} -t ${task.cpus} ${fastq}
-    """
+        """
+        fastqc ${params.optional} -t ${task.cpus} ${fastq}
+        """
 }

Fastp/0.14.1/Fastp.nf

@@ -0,0 +1,25 @@
+process Fastp {
+    tag {"Fastp ${sample_id} - ${rg_id}"}
+    label 'Fastp_0_14_1'
+    container = 'quay.io/biocontainers/fastp:0.14.1--0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, rg_id, path(fastq_files))
+
+    output:
+        tuple(sample_id, rg_id, path("*.fastq.gz"), emit: fastqs_cleaned)
+        path("${sample_id}_fastp.json", emit: qc_report)
+
+    script:
+        //adapted from https://github.com/nf-core/eager/blob/master/LICENSE, Copyright (c) Alexander Peltzer, Stephen Clayton, James A. Fellows Yates, Maxime Borry
+        if (params.singleEnd) {
+            """
+            fastp --in1 ${fastq_files[0]} --out1 "${fastq_files[0].simpleName}.trim.fastq.gz" -j ${sample_id}_fastp.json ${params.optional}
+            """
+        } else {
+            """
+            fastp --in1 ${fastq_files[0]} --in2 ${fastq_files[1]} --out1 "${fastq_files[0].simpleName}.trim.fastq.gz" --out2 "${fastq_files[1].simpleName}.trim.fastq.gz" -j ${sample_id}_fastp.json ${params.optional}
+            """
+        }
+}

Fastp/0.20.1/Fastp.nf

@@ -0,0 +1,25 @@
+process Fastp {
+    tag {"Fastp ${sample_id} - ${rg_id}"}
+    label 'Fastp_0_20_1'
+    container = 'quay.io/biocontainers/fastp:0.20.1--h8b12597_0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, rg_id, path(fastq_files))
+
+    output:
+        tuple(sample_id, rg_id, path("*.fastq.gz"), emit: fastqs_cleaned)
+        path("${sample_id}_fastp.json", emit: qc_report)
+
+    script:
+        //adapted from https://github.com/nf-core/eager/blob/master/LICENSE, Copyright (c) Alexander Peltzer, Stephen Clayton, James A. Fellows Yates, Maxime Borry
+        if (params.singleEnd) {
+            """
+            fastp --in1 ${fastq_files[0]} --out1 "${fastq_files[0].simpleName}_trim.fastq.gz" -j ${sample_id}_fastp.json ${params.optional}
+            """
+        } else {
+            """
+            fastp --in1 ${fastq_files[0]} --in2 ${fastq_files[1]} --out1 "${fastq_files[0].simpleName}_trim.fastq.gz" --out2 "${fastq_files[1].simpleName}_trim.fastq.gz" -j ${sample_id}_fastp.json ${params.optional}
+            """
+        }
+}

GATK/3.8-1-0-gf15c1c3ef/BaseRecalibrator.nf

@@ -0,0 +1,33 @@
+process BaseRecalibrator {
+    tag {"GATK BaseRecalibrator ${sample_id} - ${chr}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_BaseRecalibrator'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(bam_file), path(bai_file), chr)
+
+    output:
+        tuple(sample_id, path("${bam_file.baseName}.bqsr.${chr}.bam"), path("${bam_file.baseName}.bqsr.${chr}.bai"), emit: bam_file)
+
+    script:
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar $params.gatk_path -T BaseRecalibrator \
+        --num_cpu_threads_per_data_thread ${task.cpus} \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --intervals ${chr} \
+        --out ${bam_file.baseName}.bqsr.${chr}.table \
+        ${params.optional_bqsr}
+
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T PrintReads \
+        --num_cpu_threads_per_data_thread ${task.cpus} \
+        --reference_sequence ${params.genome} \
+        --input_file ${bam_file} \
+        --BQSR ${bam_file.baseName}.bqsr.${chr}.table \
+        --intervals ${chr} \
+        --out ${bam_file.baseName}.bqsr.${chr}.bam \
+        ${params.optional_pr}
+        """
+}

GATK/3.8-1-0-gf15c1c3ef/CatVariants.nf

@@ -0,0 +1,19 @@
+process CatVariantsGVCF {
+    tag {"GATK CatVariantsGVCF ${sample_id}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_CatVariantsGVCF'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(gvcf_files), path(gvcf_idx_files))
+
+    output:
+        tuple(sample_id, path("${sample_id}.g.vcf.gz"), path("${sample_id}.g.vcf.gz.tbi"), emit:vcf_file)
+
+    script:
+        def input_files = gvcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -cp ${params.gatk_path} org.broadinstitute.gatk.tools.CatVariants --reference ${params.genome} -V ${input_files} --outputFile ${sample_id}.g.vcf.gz ${params.optional}
+        """
+}

GATK/3.8-1-0-gf15c1c3ef/CombineVariants.nf

@@ -6,14 +6,34 @@ process CombineVariants {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-    tuple val(analysis_id), file(vcf_files), file(vcf_idx_files)
+        tuple(analysis_id, path(vcf_files), path(vcf_idx_files))
 
     output:
-    tuple val(analysis_id), file("${analysis_id}.vcf"), file("${analysis_id}.vcf.idx")
+        tuple(analysis_id, path("${analysis_id}.vcf"), path("${analysis_id}.vcf.idx"), emit:vcf_file)
 
     script:
-    def input_files = vcf_files.collect{"$it"}.join(" -V ")
-    """
-    java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T CombineVariants --reference_sequence ${params.genome} -V ${input_files} --out ${analysis_id}.vcf ${params.optional}
-    """
+        def input_files = vcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T CombineVariants --reference_sequence ${params.genome} -V ${input_files} --out ${analysis_id}.vcf ${params.optional}
+        """
+}
+
+process CombineVariantsGVCF {
+    tag {"GATK CombineVariantsGVCF ${sample_id}"}
+    label 'GATK_3_8_1_0_gf15c1c3ef'
+    label 'GATK_3_8_1_0_gf15c1c3ef_CombineVariantsGVCF'
+    container = 'quay.io/biocontainers/gatk:3.8--py27_1'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(vcf_files), path(vcf_idx_files))
+
+    output:
+        tuple(sample_id, path("${sample_id}.g.vcf"), path("${sample_id}.g.vcf.idx"), emit:vcf_file)
+
+    script:
+        def input_files = vcf_files.collect{"$it"}.join(" -V ")
+        """
+        java -Xmx${task.memory.toGiga()-4}G -jar ${params.gatk_path} -T CombineVariants --reference_sequence ${params.genome} -V ${input_files} --out ${sample_id}.g.vcf ${params.optional}
+        """
 }