chromosome breaks

inputs

@@ -1,12 +1,15 @@
 {
-  "{{ project_name }}.Dedup_bam": "{{ Dedup_bam }}",
   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
+  "{{ project_name }}.dedup_bam_index": "{{ dedup_bam_index }}",
   "{{ project_name }}.disk_size": "500",
-  "{{ project_name }}.ref_fa_fai": "GRCh38.d1.vd1.fa.fai",
-  "{{ project_name }}.FBdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/freebayes:1.3.1",
+  "{{ project_name }}.mapper": "{{ mapper }}",
+  "{{ project_name }}.sample_name": "{{ sample_name }}",
   "{{ project_name }}.half_read_length": "{{ half_read_length }}",
+  "{{ project_name }}.breakChromo.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/samtools:v1.3.1",
+  "{{ project_name }}.dedup_bam": "{{ dedup_bam }}",
+  "{{ project_name }}.chromosomes": "Array[String] (optional, default = [\"chr1\", \"chr2\", \"chr3\", \"chr4\", \"chr5\", \"chr6\", \"chr7\", \"chr8\", \"chr9\", \"chr10\", \"chr11\", \"chr12\", \"chr13\", \"chr14\", \"chr15\", \"chr16\", \"chr17\", \"chr18\", \"chr19\", \"chr20\", \"chr21\", \"chr22\", \"chrX\"])",
   "{{ project_name }}.cluster_config": "OnDemand bcs.es.c.8xlarge img-ubuntu-vpc",
-  "{{ project_name }}.Dedup_bam_index": "{{ Dedup_bam_index }}",
-  "{{ project_name }}.sample": "{{ sample }}",
+  "{{ project_name }}.concatVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
+  "{{ project_name }}.freebayes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/freebayes:1.3.1",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
-}
+}

tasks/Freebayes.wdl

@@ -1,13 +1,13 @@
-task Freebayes {
+task freebayes {
 
     File ref_dir
-    File ref_fa_fai
 	File fasta
-	File Dedup_bam
-	File Dedup_bam_index
+	File chr_bam
+	File chr_bam_bai
+	String chromosome
 	String half_read_length
-	String sample
-	String FBdocker
+	String sample_name
+	String docker
 	String cluster_config
 	String disk_size
 
@@ -15,18 +15,16 @@ task Freebayes {
 		set -o pipefail
 		set -e	
 		nt=$(nproc)
-		/opt/freebayes/scripts/freebayes-parallel <(/opt/freebayes/scripts/fasta_generate_regions.py ${ref_dir}/${ref_fa_fai} 100000) $nt -f ${ref_dir}/${fasta} --genotype-qualities -F 0.05 --max-complex-gap ${half_read_length} ${Dedup_bam} > ${sample}_fb.vcf
-		cat ${sample}_fb.vcf | grep '#' > header
-		cat ${sample}_fb.vcf | grep -v '#' | grep -v '0/0' | cat header - > ${sample}_fb.filtered.vcf
+		freebayes -f ${ref_dir}/${fasta} --genotype-qualities --max-complex-gap ${half_read_length} ${chr_bam} > ${sample_name}_${chromosome}_fb.vcf
 	>>>
 
 	runtime {
-		docker:FBdocker
+		docker: docker
     	cluster: cluster_config
     	systemDisk: "cloud_ssd 40"
     	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File filtered = "${sample}_fb.filtered.vcf"
+		File vcf = "${sample_name}_${chromosome}_fb.vcf"
 	}
 }

tasks/FreebayesParallel.wdl

@@ -0,0 +1,33 @@
+
+task Freebayes {
+
+    File ref_dir
+    File ref_fa_fai
+	File fasta
+	File Dedup_bam
+	File Dedup_bam_index
+	String half_read_length
+	String sample
+	String FBdocker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e	
+		nt=$(nproc)
+		/opt/freebayes/scripts/freebayes-parallel <(/opt/freebayes/scripts/fasta_generate_regions.py ${ref_dir}/${ref_fa_fai} 100000) $nt -f ${ref_dir}/${fasta} --genotype-qualities -F 0.05 --max-complex-gap ${half_read_length} ${Dedup_bam} > ${sample}_fb.vcf
+		cat ${sample}_fb.vcf | grep '#' > header
+		cat ${sample}_fb.vcf | grep -v '#' | grep -v '0/0' | cat header - > ${sample}_fb.filtered.vcf
+	>>>
+
+	runtime {
+		docker:FBdocker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File filtered = "${sample}_fb.filtered.vcf"
+	}
+}

tasks/breakChromo.wdl

@@ -0,0 +1,28 @@
+task breakChromo {
+	File dedup_bam
+	File dedup_bam_index
+	String chromosome
+	String sample_name
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e	
+		nt=$(nproc)
+		/opt/conda/bin/samtools view -@ $nt -hb ${dedup_bam} ${chromosome} > ${sample_name}_${chromosome}.bam
+		/opt/conda/bin/samtools index ${sample_name}_${chromosome}.bam
+	>>>
+
+	runtime {
+		docker: docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File chr_bam = "${sample_name}_${chromosome}.bam"
+		File chr_bam_bai = "samtools index ${sample_name}_${chromosome}.bam.bai"
+	}
+}

tasks/concatVCF.wdl

@@ -0,0 +1,25 @@
+task concatVCF {
+
+    Array[File] vcf
+    String mapper
+    String sample_name
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e	
+		/opt/hall-lab/bcftools-1.9/bin/bcftools concat -a ${sep=" " vcf} > ${sample_name}.${mapper}.fb.vcf
+	>>>
+
+	runtime {
+		docker: docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File filtered = "${sample_name}.${mapper}.fb.vcf"
+	}
+}

workflow.wdl

@@ -1,31 +1,49 @@
-import "./tasks/Freebayes.wdl" as Freebayes
-
+import "./tasks/breakChromo.wdl" as breakChromo
+import "./tasks/freebayes.wdl" as freebayes
+import "./tasks/concatVCF.wdl" as concatVCF
 
 workflow {{ project_name }} {
-
-	String sample
-	String FBdocker
-	File ref_fa_fai
-	File fasta
-	File Dedup_bam
-	File Dedup_bam_index
+	File dedup_bam
+	File dedup_bam_index
+	Array[String] chromosomes = ["chr1" , "chr2" , "chr3" , "chr4" , "chr5" , "chr6" , "chr7" , "chr8" , "chr9" , "chr10" , "chr11" , "chr12" , "chr13" , "chr14" , "chr15" , "chr16" , "chr17" , "chr18" , "chr19" , "chr20" , "chr21" , "chr22" , "chrX"]
 	File ref_dir
+	String mapper
+	String fasta
 	String half_read_length
+	String sample_name
 	String disk_size
 	String cluster_config
-
-	call Freebayes.Freebayes as Freebayes {
+	scatter (chromosome in chromosomes){
+		call breakChromo.breakChromo as breakChromo {
+			input:
+			dedup_bam=dedup_bam,
+			dedup_bam_index=dedup_bam_index,
+			chromosome=chromosome,
+			sample_name=sample_name,
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call freebayes.freebayes as freebayes {
+			input:
+			ref_dir=ref_dir,
+			fasta=fasta,
+			chr_bam=breakChromo.chr_bam,
+			chr_bam_bai=breakChromo.chr_bam_bai,
+			chromosome=chromosome,
+			half_read_length=half_read_length,
+			sample_name=sample_name,
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+	}
+	call concatVCF.concatVCF as concatVCF{
 		input:
-		fasta=fasta,
-		ref_dir=ref_dir,
-		Dedup_bam=Dedup_bam,
-		Dedup_bam_index=Dedup_bam_index,
-		sample=sample,
-		half_read_length=half_read_length,
-		FBdocker=FBdocker,
+		vcf=freebayes.vcf,
+		mapper=mapper,
+		sample_name=sample_name,
 		cluster_config=cluster_config,
-		disk_size=disk_size,
-		ref_fa_fai=ref_fa_fai
-	}
+		disk_size=disk_size
 	}
 
+}
+