qualimap rnaseq qc

inputSamplesFileExamples.tsv

@@ -1 +1,3 @@
-oss://chinese-quartet/quartet-test-data/WEGENE_T7/Quartet_DNA_BGI_T7_WGE_LCL5_1_20191105_R1.fastq.gz	oss://chinese-quartet/quartet-test-data/WEGENE_T7/Quartet_DNA_BGI_T7_WGE_LCL5_1_20191105_R2.fastq.gz	oss://pgx-result/renluyao/quality_control/20191223_wegeneT7_sentieon/0214dda2-9408-4bc2-9e7e-322e18d488ad/call-Dedup/Quartet_DNA_BGI_T7_WGE_LCL8_1_20191105.sorted.deduped.bam	oss://pgx-result/renluyao/quality_control/20191223_wegeneT7_sentieon/0214dda2-9408-4bc2-9e7e-322e18d488ad/call-Dedup/Quartet_DNA_BGI_T7_WGE_LCL8_1_20191105.sorted.deduped.bam.bai
+oss://pgx-source-data/wholebloodRNAseq_DEMO/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_3_20190710_CleanData_R1_0.5Mcut.fastq.gz	oss://pgx-source-data/wholebloodRNAseq_DEMO/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_3_20190710_CleanData_R2_0.5Mcut.fastq.gz	oss://choppy-cromwell-result/test-choppy/RNAseq_0p5M_20200209/30523014-5772-4bdc-b3b9-d6688a152573/call-samtools/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_3_20190710_CleanData_R1_0.sorted.bam	oss://choppy-cromwell-result/test-choppy/RNAseq_0p5M_20200209/30523014-5772-4bdc-b3b9-d6688a152573/call-samtools/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_3_20190710_CleanData_R1_0.sorted.bam.bai
+oss://pgx-source-data/wholebloodRNAseq_DEMO/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_1_20190710_CleanData_R1_0.5Mcut.fastq.gz	oss://pgx-source-data/wholebloodRNAseq_DEMO/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_1_20190710_CleanData_R2_0.5Mcut.fastq.gz	oss://choppy-cromwell-result/test-choppy/RNAseq_0p5M_20200209/4302d90f-1a84-40a1-8f56-99bb3652fade/call-samtools/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_1_20190710_CleanData_R1_0.sorted.bam	oss://choppy-cromwell-result/test-choppy/RNAseq_0p5M_20200209/4302d90f-1a84-40a1-8f56-99bb3652fade/call-samtools/Quartet_RNA_ILM_NovaSeq_RiboZero_FDU_F7_1_20190710_CleanData_R1_0.sorted.bam.bai
+oss://pgx-source-data/wholebloodRNAseq_DEMO/Quartet_RNA_ILM_HiSeq4000_RiboZero_UTS_BLD8_1_20161209_CleanData_R1_0.5Mcut.fastq.gz	oss://pgx-source-data/wholebloodRNAseq_DEMO/Quartet_RNA_ILM_HiSeq4000_RiboZero_UTS_BLD8_1_20161209_CleanData_R2_0.5Mcut.fastq.gz	oss://choppy-cromwell-result/test-choppy/RNAseq_0p5M_20200209/76162f0f-e580-4a1b-8932-33ea5dad9ba3/call-samtools/Quartet_RNA_ILM_HiSeq4000_RiboZero_UTS_BLD8_1_20161209_CleanData_R1_0.sorted.bam	oss://choppy-cromwell-result/test-choppy/RNAseq_0p5M_20200209/76162f0f-e580-4a1b-8932-33ea5dad9ba3/call-samtools/Quartet_RNA_ILM_HiSeq4000_RiboZero_UTS_BLD8_1_20161209_CleanData_R1_0.sorted.bam.bai

inputs

@@ -1,19 +1,24 @@
 {
-  "{{ project_name }}.qualimap.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/qualimap:2.0.0",
-  "{{ project_name }}.qualimap.cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
   "{{ project_name }}.fastqc.disk_size": "150",
+  "{{ project_name }}.gtf": "oss://pgx-reference-data/reference/annotation/Homo_sapiens.GRCh38.93.gtf",
   "{{ project_name }}.fastqscreen.cluster_config": "OnDemand bcs.b2.3xlarge img-ubuntu-vpc",
   "{{ project_name }}.fastqc.cluster_config": "OnDemand bcs.b2.3xlarge img-ubuntu-vpc",
+  "{{ project_name }}.qualimapBAMqc.disk_size": "500",
   "{{ project_name }}.fastqc.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqc:v0.11.5",
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
   "{{ project_name }}.fastqscreen.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqscreen:0.12.0",
+  "{{ project_name }}.qualimapRNAseq.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/qualimap:2.0.0",
   "{{ project_name }}.screen_ref_dir": "oss://pgx-reference-data/fastq_screen_reference/",
   "{{ project_name }}.fastq_screen_conf": "oss://pgx-reference-data/fastq_screen_reference/fastq_screen.conf",
   "{{ project_name }}.multiqc.cluster_config": "OnDemand bcs.b2.3xlarge img-ubuntu-vpc",
-  "{{ project_name }}.qualimap.disk_size": "500",
   "{{ project_name }}.multiqc.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/multiqc:v1.8",
+  "{{ project_name }}.qualimapRNAseq.disk_size": "500",
+  "{{ project_name }}.qualimapBAMqc.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/qualimap:2.0.0",
+  "{{ project_name }}.qualimapBAMqc.cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
+  "{{ project_name }}.qualimapRNAseq.cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
   "{{ project_name }}.fastqscreen.disk_size": "100",
   "{{ project_name }}.multiqc.disk_size": "100",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
 }
+

tasks/multiqc.wdl

@@ -6,7 +6,8 @@ task multiqc {
 	Array[File] txt1
 	Array[File] txt2
 
-	Array[File] zip
+	Array[File] bamqc_zip
+	Array[File] rnaseq_zip
 
 	String docker
 	String cluster_config
@@ -21,11 +22,16 @@ task multiqc {
 
 		cp ${sep=" " read1_zip} ${sep=" " read2_zip} /cromwell_root/tmp/fastqc
 		cp ${sep=" " txt1} ${sep=" " txt2} /cromwell_root/tmp/fastqscreen
-		for i in ${sep=" " zip}
+		for i in ${sep=" " bamqc_zip}
 		do
 		  tar -zxvf $i -C /cromwell_root/tmp/bamqc
 		done
 
+		for i in ${sep=" " rnaseq_zip}
+		do
+		  tar -zxvf $i -C /cromwell_root/tmp/rnaseq
+		done
+
 		multiqc /cromwell_root/tmp/
 	
 	>>>

tasks/qualimap.wdl → tasks/qualimapBAMqc.wdl

@@ -1,4 +1,4 @@
-task qualimap {
+task qualimapBAMqc {
 	File bam
 	File bai
 	String bamname = basename(bam,".bam")
@@ -10,8 +10,8 @@ task qualimap {
 		set -o pipefail
 		set -e
 		nt=$(nproc)
-		/opt/qualimap/qualimap bamqc -bam ${bam} -outformat PDF:HTML -nt $nt -outdir ${bamname} --java-mem-size=32G 
-		tar -zcvf ${bamname}_qualimap.zip ${bamname}
+		/opt/qualimap/qualimap bamqc -bam ${bam} -outformat PDF:HTML -nt $nt -outdir ${bamname}_bamqc --java-mem-size=32G 
+		tar -zcvf ${bamname}_bamqc_qualimap.zip ${bamname}_bamqc
 	>>>
 
 	runtime {
@@ -22,6 +22,6 @@ task qualimap {
 	}
 
 	output {
-		File zip = "${bamname}_qualimap.zip"
+		File bamqc_zip = "${bamname}_bamqc_qualimap.zip"
 	}
 }

tasks/qualimapRNAseq.wdl

@@ -0,0 +1,28 @@
+task qualimapRNAseq {
+	File bam
+	File bai
+	File gtf
+	String bamname = basename(bam,".bam")
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		/opt/qualimap/qualimap rnaseq -bam ${bam} -outformat HTML -outdir ${bamname}_RNAseq -gtf ${gtf} -pe --java-mem-size=10G
+		tar -zcvf ${bamname}_RNAseq_qualimap.zip ${bamname}_RNAseq
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File rnaseq_zip = "${bamname}_RNAseq_qualimap.zip"
+	}
+}

workflow.wdl

@@ -1,6 +1,7 @@
 import "./tasks/fastqc.wdl" as fastqc
 import "./tasks/fastqscreen.wdl" as fastqscreen
-import "./tasks/qualimap.wdl" as qualimap
+import "./tasks/qualimapBAMqc.wdl" as qualimapBAMqc
+import "./tasks/qualimapRNAseq.wdl" as qualimapRNAseq
 import "./tasks/multiqc.wdl" as multiqc
 
 workflow {{ project_name }} {
@@ -10,6 +11,7 @@ workflow {{ project_name }} {
 	File screen_ref_dir
 	File fastq_screen_conf
 	File ref_dir
+	File gtf
 	String fasta
 
 	scatter (sample in inputSamples) {
@@ -27,12 +29,19 @@ workflow {{ project_name }} {
 			fastq_screen_conf=fastq_screen_conf
 		}
 
-		call qualimap.qualimap as qualimap {
+		call qualimapBAMqc.qualimapBAMqc as qualimapBAMqc {
 			input:
 			bam=sample[2],
 			bai=sample[3]
 		}
 
+		call qualimapRNAseq.qualimapRNAseq as qualimapRNAseq {
+			input:
+			bam=sample[2],
+			bai=sample[3],
+			gtf=gtf		
+		}
+
 	}
 
 	call multiqc.multiqc as multiqc {
@@ -41,7 +50,8 @@ workflow {{ project_name }} {
 		read2_zip=fastqc.read2_zip,
 		txt1=fastqscreen.txt1,
 		txt2=fastqscreen.txt2,
-		zip=qualimap.zip
+		bamqc_zip=qualimapBAMqc.bamqc_zip,
+		rnaseq_zip=qualimapRNAseq.rnaseq_zip
 	}
 
 }