Feature/gatk4.2

GATK/4.2.1.0/GenotypeGvcfs.nf

@@ -0,0 +1,63 @@
+process GenotypeGVCFs {
+    tag {"GATK GenotypeGVCFs ${analysis_id} - ${interval_file.baseName}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_GenotypeGVCFs'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(analysis_id, path(gvcf_files), path(gvcf_idx_files), path(interval_file))
+
+    output:
+        tuple(
+            analysis_id,
+            path("${analysis_id}_${interval_file.baseName}${ext_vcf}"),
+            path("${analysis_id}_${interval_file.baseName}${ext_vcf}${ext_vcf_index}"),
+            emit:vcf_file
+        )
+
+    script:
+        def input_files = gvcf_files.collect{"$it"}.join(" --variant ")
+        ext_vcf = params.compress || gvcf_files.getExtension() == ".gz" ? ".vcf.gz" : ".vcf"
+        ext_vcf_index = params.compress || gvcf_files.getExtension() == ".gz" ? ".tbi" : ".idx"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" GenotypeGVCFs \
+        --reference ${params.genome} \
+        --variant $input_files \
+        --output ${analysis_id}_${interval_file.baseName}${ext_vcf} \
+        --intervals ${interval_file} \
+        ${params.optional}
+        """
+}
+
+process GenotypeGVCF {
+    tag {"GATK GenotypeGVCF ${sample_id} - ${interval_file.baseName}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_GenotypeGVCF'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(sample_id, path(gvcf_files), path(gvcf_idx_files), path(interval_file))
+
+    output:
+        tuple(
+            val(sample_id),
+            path("${sample_id}_${interval_file.baseName}${ext_vcf}"),
+            path("${sample_id}_${interval_file.baseName}${ext_vcf}${ext_vcf_index}"),
+            emit: vcf_file
+        )
+
+    script:
+        def input_files = gvcf_files.collect{"$it"}.join(" --variant ")
+        ext_vcf = params.compress || gvcf_files.getExtension() == ".gz" ? ".vcf.gz" : ".vcf"
+        ext_vcf_index = params.compress || gvcf_files.getExtension() == ".gz" ? ".tbi" : ".idx"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" GenotypeGVCFs \
+        --reference ${params.genome} \
+        --variant $input_files \
+        --output ${sample_id}_${interval_file.baseName}${ext_vcf} \
+        --intervals ${interval_file} \
+        ${params.optional}
+        """
+}

GATK/4.2.1.0/HaplotypeCaller.nf

@@ -0,0 +1,71 @@
+process HaplotypeCaller {
+    tag {"GATK HaplotypeCaller ${analysis_id} - ${interval_file.baseName}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_HaplotypeCaller'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(analysis_id, path(bam_files), path(bai_files), path(interval_file))
+
+    output:
+        tuple(
+            val(analysis_id),
+            path("${analysis_id}.${interval_file.baseName}${ext_vcf}"),
+            path("${analysis_id}.${interval_file.baseName}${ext_vcf}${ext_vcf_index}"),
+            emit: vcf_file
+        )
+
+    script:
+        def input_files = bam_files.collect{"$it"}.join(" --input ")
+        ext_vcf = ".vcf"
+        ext_vcf_index = ".idx"
+        if( params.compress )
+            ext_vcf = ".vcf.gz"
+            ext_vcf_index = ".tbi"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" HaplotypeCaller \
+        --reference ${params.genome} \
+        --input ${input_files} \
+        --intervals ${interval_file} \
+        --output ${analysis_id}.${interval_file.baseName}${ext_vcf} \
+        ${params.optional}
+        """
+}
+
+process HaplotypeCallerGVCF {
+    tag {"GATK HaplotypeCallerGVCF ${sample_id} - ${interval_file.baseName}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_HaplotypeCallerGVCF'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+    params.emit_ref_confidence = 'GVCF'
+
+    input:
+        tuple(sample_id, path(bam_file), path(bai_file), path(interval_file))
+
+    output:
+        tuple(
+            val(sample_id),
+            path("${sample_id}_${interval_file.baseName}${ext_gvcf}"),
+            path("${sample_id}_${interval_file.baseName}${ext_gvcf}${ext_gvcf_index}"),
+            path(interval_file),
+            emit: vcf_file
+        )
+
+    script:
+        ext_gvcf = ".g.vcf"
+        ext_gvcf_index = ".idx"
+        if( params.compress )
+            ext_gvcf = ".g.vcf.gz"
+            ext_gvcf_index = ".tbi"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" HaplotypeCaller \
+        --reference ${params.genome} \
+        --input ${bam_file} \
+        --intervals ${interval_file} \
+        --output ${sample_id}_${interval_file.baseName}${ext_gvcf} \
+        --emit-ref-confidence ${params.emit_ref_confidence} \
+        ${params.optional}
+        """
+}

GATK/4.2.1.0/MergeVcfs.nf

@@ -0,0 +1,50 @@
+process MergeVcfs {
+    tag {"GATK MergeVcfs ${output_name}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_MergeVcfs'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(output_name, path(vcf_files), path(vcf_idx_files))
+
+    output:
+        tuple(output_name, path("${output_name}${ext_vcf}"), path("${output_name}${ext_vcf}${ext_vcf_index}"), emit:vcf_file)
+
+    script:
+        def input_files = vcf_files.collect{"$it"}.join(" --INPUT ")
+        ext_vcf = ".vcf"
+        ext_vcf_index = ".idx"
+        if( params.compress )
+            ext_vcf = ".vcf.gz"
+            ext_vcf_index = ".tbi"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" MergeVcfs --INPUT ${input_files} --OUTPUT ${output_name}${ext_vcf}
+        """
+}
+
+
+process MergeGvcfs {
+    tag {"GATK MergeGvcfs ${output_name}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_MergeGvcfs'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(output_name, path(vcf_files), path(vcf_idx_files))
+
+    output:
+        tuple(output_name, path("${output_name}${ext_gvcf}"), path("${output_name}${ext_gvcf}${ext_gvcf_index}"), emit:vcf_file)
+
+    script:
+        def input_files = vcf_files.collect{"$it"}.join(" --INPUT ")
+        ext_gvcf = ".g.vcf"
+        ext_gvcf_index = ".idx"
+        if( params.compress )
+            ext_gvcf = ".g.vcf.gz"
+            ext_gvcf_index = ".tbi"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" MergeVcfs --INPUT ${input_files} --OUTPUT ${output_name}${ext_gvcf}
+        """
+}

GATK/4.2.1.0/SelectVariants.nf

@@ -0,0 +1,30 @@
+process SelectVariantsSample {
+    tag {"GATK SelectVariantsSample ${analysis_id} - ${sample_id}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_SelectVariantsSample'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(analysis_id, path(vcf_file), path(vcf_idx_file), sample_id)
+
+    output:
+        tuple(
+            sample_id,
+            path("${sample_id}_${vcf_file.baseName}${ext_vcf}"),
+            path("${sample_id}_${vcf_file.baseName}${ext_vcf}${ext_vcf_index}"),
+            emit: vcf_file
+        )
+
+    script:
+        ext_vcf = params.compress || vcf_file.getExtension() == ".gz" ? ".vcf.gz" : ".vcf"
+        ext_vcf_index = params.compress || vcf_file.getExtension() == ".gz" ? ".tbi" : ".idx"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" SelectVariants \
+        --reference ${params.genome} \
+        --variant ${vcf_file} \
+        --output ${sample_id}_${vcf_file.baseName}${ext_vcf} \
+        --sample-name ${sample_id} \
+        ${params.optional}
+        """
+}

GATK/4.2.1.0/VariantFiltration.nf

@@ -0,0 +1,26 @@
+process VariantFiltrationSnpIndel {
+    tag {"GATK VariantFiltrationSnpIndel ${analysis_id}"}
+    label 'GATK_4_2_1_0'
+    label 'GATK_4_2_1_0_VariantFiltrationSnpIndel'
+    container = 'broadinstitute/gatk:4.2.1.0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple(analysis_id, path(vcf_file), path(vcf_idx_file))
+
+    output:
+        tuple(analysis_id, path("${vcf_file.baseName}.filter${ext_vcf}"), path("${vcf_file.baseName}.filter${ext_vcf}${ext_vcf_index}"), emit: vcf_file)
+
+    script:
+        ext_vcf = params.compress || vcf_file.getExtension() == ".gz" ? ".vcf.gz" : ".vcf"
+        ext_vcf_index = params.compress || vcf_file.getExtension() == ".gz" ? ".tbi" : ".idx"
+        """
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" SelectVariants --reference ${params.genome} --variant $vcf_file --output ${vcf_file.baseName}.snp${ext_vcf} --select-type-to-exclude INDEL
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" SelectVariants --reference ${params.genome} --variant $vcf_file --output ${vcf_file.baseName}.indel${ext_vcf} --select-type-to-include INDEL
+
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" VariantFiltration --reference ${params.genome} --variant ${vcf_file.baseName}.snp${ext_vcf} --output ${vcf_file.baseName}.snp_filter${ext_vcf} ${params.snp_filter} ${params.snp_cluster}
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" VariantFiltration --reference ${params.genome} --variant ${vcf_file.baseName}.indel${ext_vcf} --output ${vcf_file.baseName}.indel_filter${ext_vcf} ${params.indel_filter}
+
+        gatk --java-options "-Xmx${task.memory.toGiga()-4}G" MergeVcfs --INPUT ${vcf_file.baseName}.snp_filter${ext_vcf} --INPUT ${vcf_file.baseName}.indel_filter${ext_vcf} --OUTPUT ${vcf_file.baseName}.filter${ext_vcf}
+        """
+}