recovery multiqc

tasks/extract_tables.wdl

@@ -0,0 +1,41 @@
+task extract_tables {
+
+	File quality_yield_summary
+	File wgs_metrics_summary
+	File aln_metrics_summary
+	File is_metrics_summary
+	File hap
+	File fastqc
+	File fastqscreen
+
+
+	String project
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+
+		python /opt/extract_tables.py -quality ${quality_yield_summary} -depth ${wgs_metrics_summary} -aln ${aln_metrics_summary} -is ${is_metrics_summary} -fastqc ${fastqc} -fastqscreen ${fastqscreen} -hap ${hap} -project ${project}
+
+		cat variants.calling.qc.txt | cut -f12- | grep -v 'SNV' | awk '{for(i=1;i<=NF;i++) {sum[i] += $i; sumsq[i] += ($i)^2}} 
+          END {for (i=1;i<=NF;i++) {
+          printf "%f %f \n", sum[i]/NR, sqrt((sumsq[i]-sum[i]^2/NR)/NR)}
+         }' >> reference_datasets_aver-std.txt
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File pre_alignment = "pre_alignment.txt"
+		File post_alignment = "post_alignment.txt"
+		File variant_calling = "variants.calling.qc.txt"
+		File precision_recall = "reference_datasets_aver-std.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] summary
+
+	Array[File] zip
+
+	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/benchmark
+
+		cp ${sep=" " read1_zip} ${sep=" " read2_zip} /cromwell_root/tmp/fastqc
+		cp ${sep=" " txt1} ${sep=" " txt2} /cromwell_root/tmp/fastqscreen
+		cp ${sep=" " summary} /cromwell_root/tmp/benchmark
+
+		multiqc /cromwell_root/tmp/
+
+		cat multiqc_data/multiqc_general_stats.txt > multiqc_general_stats.txt
+		cat multiqc_data/multiqc_fastq_screen.txt > multiqc_fastq_screen.txt
+		cat multiqc_data/multiqc_happy_data.json > multiqc_happy_data.json
+	
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File multiqc_html = "multiqc_report.html"
+		Array[File] multiqc_txt = glob("multiqc_data/*")
+		File fastqc = "multiqc_general_stats.txt"
+		File fastqscreen = "multiqc_fastq_screen.txt"
+		File hap = "multiqc_happy_data.json"
+	}
+}

workflow.wdl

@@ -9,7 +9,9 @@ import "./tasks/Haplotyper_gVCF.wdl" as Haplotyper_gVCF
 import "./tasks/GVCFtyper.wdl" as GVCFtyper
 import "./tasks/split_gvcf_files.wdl" as split_gvcf_files
 import "./tasks/benchmark.wdl" as benchmark
+import "./tasks/multiqc.wdl" as multiqc
 import "./tasks/merge_sentieon_metrics.wdl" as merge_sentieon_metrics
+import "./tasks/extract_tables.wdl" as extract_tables
 import "./tasks/mendelian.wdl" as mendelian
 import "./tasks/merge_mendelian.wdl" as merge_mendelian
 import "./tasks/quartet_mendelian.wdl" as quartet_mendelian
@@ -220,6 +222,19 @@ workflow {{ project_name }} {
 
 	}
 
+	call multiqc.multiqc as multiqc {
+		input:
+		read1_zip=fastqc.read1_zip,
+		read2_zip=fastqc.read2_zip,
+		txt1=fastqscreen.txt1,
+		txt2=fastqscreen.txt2,
+		summary=benchmark.summary,
+		zip=qualimap.zip,
+		docker=MULTIQCdocker,
+		cluster_config=SMALLcluster_config,
+		disk_size=disk_size
+	}
+
 	call merge_sentieon_metrics.merge_sentieon_metrics as merge_sentieon_metrics {
 		input:
 		quality_yield_header=sentieon.quality_yield_header,
@@ -234,6 +249,21 @@ workflow {{ project_name }} {
 		docker=MULTIQCdocker,
 		cluster_config=SMALLcluster_config,
 		disk_size=disk_size	
+	}
+
+	call extract_tables.extract_tables as extract_tables {
+		input:
+		quality_yield_summary=merge_sentieon_metrics.quality_yield_summary,
+		wgs_metrics_summary=merge_sentieon_metrics.wgs_metrics_summary,
+		aln_metrics_summary=merge_sentieon_metrics.aln_metrics_summary,
+		is_metrics_summary=merge_sentieon_metrics.is_metrics_summary,
+		fastqc=multiqc.fastqc,
+		fastqscreen=multiqc.fastqscreen,
+		hap=multiqc.hap,
+		project=project,
+		docker=DIYdocker,
+		cluster_config=SMALLcluster_config,
+		disk_size=disk_size
 	}	
 
 	Boolean sister_tag = read_boolean(split_gvcf_files.sister_tag)