multiqc

inputs

@@ -11,11 +11,13 @@
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
   "{{ project_name }}.fastqscreen.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqscreen:0.12.0",
   "{{ project_name }}.screen_ref_dir": "oss://pgx-reference-data/fastq_screen_reference/",
-  "{{ project_name }}.rtg.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.fastq_screen_conf": "oss://pgx-reference-data/fastq_screen_reference/fastq_screen.conf",
+  "{{ project_name }}.multiqc.cluster_config": "OnDemand ecs.sn1ne.4xlarge img-ubuntu-vpc",
+  "{{ project_name }}.multiqc.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/multiqc:v1.8",
   "{{ project_name }}.bamqc.cluster_config": "OnDemand ecs.sn1ne.8xlarge img-ubuntu-vpc",
   "{{ project_name }}.fastqscreen.disk_size": "100",
   "{{ project_name }}.bamqc.disk_size": "500",
+  "{{ project_name }}.multiqc.disk_size": "100",
   "{{ project_name }}.bamqc.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/qualimap:2.0.0",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
 }

tasks/bamqc.wdl

@@ -1,6 +1,7 @@
 task bamqc {
 	File bam
 	File bai
+	String bamname = basename(bam,".bam")
 	String docker
 	String cluster_config
 	String disk_size
@@ -10,6 +11,7 @@ task bamqc {
 		set -e
 		nt=$(nproc)
 		/opt/qualimap/qualimap bamqc -bam ${bam} -outformat PDF:HTML -nt $nt -outdir result --java-mem-size=32G 
+		tar -zcvf ${bamname}_qualimap.zip ./result
 	>>>
 
 	runtime {
@@ -20,9 +22,12 @@ task bamqc {
 	}
 
 	output {
+		File zip = "${bamname}_qualimap.zip"
 		File genome_result = "result/genome_results.txt"
 		File pdf = "result/report.pdf"
-		Array[File] png = glob("reuslt/images_qualimapReport/*.png")
-		Array[File] txt = glob("result/raw_data_qualimapReport/*.txt")
+		File coverage = "result/raw_data_qualimapReport/coverage_histogram.txt"
+		File insert_size = "result/raw_data_qualimapReport/insert_size_histogram.txt"
+		File genome_fraction = "result/raw_data_qualimapReport/genome_fraction_coverage.txt"
+		File gc_dist = "result/raw_data_qualimapReport/mapped_reads_gc-content_distribution.txt"
 	}
 }

tasks/multiqc.wdl

@@ -0,0 +1,50 @@
+task multiqc {
+
+	Array[File] read1_zip
+	Array[File] read2_zip
+
+	Array[File] txt1
+	Array[File] txt2
+
+	Array[File] genome_result
+	Array[File] coverage
+	Array[File] insert_size
+	Array[File] genome_fraction
+	Array[File] gc_dist
+
+	Array[File] summary
+
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		mkdir -p /cromwell_root/tmp/fastqc
+		mkdir -p /cromwell_root/tmp/fastqscreen
+		mkdir -p /cromwell_root/tmp/bamqc
+		mkdir -p /cromwell_root/tmp/benchmark
+
+		cp ${sep=" " read1_zip} ${sep=" " read2_zip} /cromwell_root/tmp/fastqc
+		cp ${sep=" " txt1} ${sep=" " txt2} /cromwell_root/tmp/fastqscreen
+		cp ${sep=" " genome_result} ${sep=" " coverage} ${sep=" " insert_size} ${sep=" " genome_fraction} ${sep=" " gc_dist} /cromwell_root/tmp/bamqc
+		cp ${sep=" " summary} /cromwell_root/tmp/benchmark
+
+		multiqc /cromwell_root/tmp/
+		ls > filelist
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File filelist = "filelist"
+		File multiqc_html = "multiqc_report.html"
+		Array[File] multiqc_txt = glob("multiqc_data/*")
+	}
+}

workflow.wdl

@@ -2,8 +2,9 @@ import "./tasks/fastqc.wdl" as fastqc
 import "./tasks/fastqscreen.wdl" as fastqscreen
 import "./tasks/bamqc.wdl" as bamqc
 import "./tasks/benchmark.wdl" as benchmark
+import "./tasks/multiqc.wdl" as multiqc
 
-workflow {{ project_name }} {
+workflow project_name {
 
 	File inputSamplesFile
 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
@@ -43,6 +44,19 @@ workflow {{ project_name }} {
 			fasta=fasta
 		}
 	}
+	call multiqc.multiqc as multiqc {
+		input:
+		read1_zip=fastqc.read1_zip,
+		read2_zip=fastqc.read2_zip,
+		txt1=fastqscreen.txt1,
+		txt2=fastqscreen.txt2,
+		genome_result=bamqc.genome_result,
+		coverage=bamqc.coverage,
+		insert_size=bamqc.insert_size,
+		genome_fraction=bamqc.genome_fraction,
+		gc_dist=bamqc.gc_dist,
+		summary=benchmark.summary
+	}
 
 }