commit

inputs

@@ -0,0 +1,18 @@
+{
+  "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
+  "{{ project_name }}.ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+  "{{ project_name }}.dbsnp": "dbsnp_146.hg38.vcf",
+  "{{ project_name }}.SENTIEON_INSTALL_DIR": "/opt/sentieon-genomics",
+  "{{ project_name }}.dbmills_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+  "{{ project_name }}.db_mills": "Mills_and_1000G_gold_standard.indels.hg38.vcf",
+  "{{ project_name }}.cluster_config": "{{ cluster if cluster != '' else 'OnDemand ecs.sn1ne.8xlarge img-ubuntu-vpc' }}",
+  "{{ project_name }}.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/sentieon-genomics:v2018.08.01",
+  "{{ project_name }}.dbsnp_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+  "{{ project_name }}.sample": "{{ sample_name }}",
+  "{{ project_name }}.disk_size": "{{ 200 }}", 
+  "{{ project_name }}.hardfiltration_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/gatk:v2019.01",
+  "{{ project_name }}.annovar_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/annovar:v2018.04",
+  "{{ project_name }}.recaled_bam_file": "{{ recaled_bam }}",
+  "{{ project_name }}.database": "oss://chinese-quartet/quartet-storage-data/reference_data/annovar_hg38/",
+  "{{ project_name }}.recaled_bam_index": "{{ recaled_bam_index }}"
+}

tasks/Annovar.wdl

@@ -0,0 +1,28 @@
+task Annovar {
+
+	File vcf_file
+	File database
+	String sample
+	String docker
+	String cluster_config
+	String disk_size
+
+
+	command <<<
+		nt=$(nproc)
+		/installations/annovar/table_annovar.pl ${vcf_file} ${database} -buildver hg38 -out ${sample} -remove -protocol refGene,ensGene,ljb26_all,dbnsfp35c,intervar_20180118,cosmic70,exac03,gnomad30_genome,1000g2015aug_all,clinvar_20190305,gnomad211_genome -operation g,g,f,f,f,f,f,f,f,f,f -nastring . -vcfinput -thread $nt
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File avinput = "${sample}.avinput"
+		File multianno_txt = "${sample}.hg19_multianno.txt"
+		File multianno_vcf = "${sample}.hg19_multianno.vcf"
+
+	}
+}

tasks/Haplotyper.wdl

@@ -0,0 +1,38 @@
+task Haplotyper {
+	
+	
+    File ref_dir
+    File dbsnp_dir
+
+	String SENTIEON_INSTALL_DIR
+	String fasta
+	File recaled_bam
+	File recaled_bam_index
+	String dbsnp
+	String sample
+	String docker
+	String cluster_config
+	String disk_size
+
+command <<<
+		set -o pipefail
+		set -e
+		export SENTIEON_LICENSE=192.168.0.55:8990
+		nt=$(nproc)	
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${recaled_bam} --algo Haplotyper -d ${dbsnp_dir}/${dbsnp} ${sample}_hc.vcf
+	>>>
+	
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File vcf = "${sample}_hc.vcf"
+		File vcf_idx = "${sample}_hc.vcf.idx"
+	}
+}
+
+

tasks/Hardfiltration.wdl

@@ -0,0 +1,36 @@
+task Hardfiltration {
+	
+	File vcf_file
+	File vcf_index
+	String sample
+	String docker
+	String disk_size
+	String cluster_config
+	
+
+	command <<<
+		set -o pipefail
+		set -e
+		java -Dsamjdk.use_async_io_read_samtools=false -Dsamjdk.use_async_io_write_samtools=true -Dsamjdk.use_async_io_write_tribble=false -Dsamjdk.compression_level=2 -Xmx32G -jar /gatk/gatk-package-4.1.0.0-local.jar VariantFiltration -V ${vcf_file} -O ${sample}_hc_filtered.vcf --filter-expression "QD<2.0" --filter-name "LowQD" --filter-expression "MQ<40.0" --filter-name "LowMQ" --filter-expression "FS>60.0" --filter-name "FisherStrandBias" --filter-expression "HaplotypeScore>13.0" --filter-name "HighHapScore" --filter-expression "MQRankSum<-12.5" --filter-name "LowMQRankSum" --filter-expression "ReadPosRankSum<-8.0" --filter-name "LowReadPosRankSum" --cluster-size 3 --cluster-window-size 100 --filter-expression "MQ0 >= 4 && ((MQ0/(1.0*DP))>0.1)" --filter-name "HARD_TO_VALIDATE" --filter-expression "DP < 5" --filter-name "LowCoverage" --filter-expression "QUAL < 30.0" --filter-name "VeryLowQual" --filter-expression "QUAL > 30.0 && QUAL < 50.0" --filter-name "LowQual" 
+		cat ${sample}_hc_filtered.vcf |grep "#" > ${sample}_hc_filtered.vcf.header.tmp
+		cat ${sample}_hc_filtered.vcf |grep PASS > ${sample}_hc_filtered.vcf.tmp
+		cat ${sample}_hc_filtered.vcf.header.tmp ${sample}_hc_filtered.vcf.tmp > ${sample}_hc_PASS.vcf
+		>>>
+
+		runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File raw_vcf = "${sample}_hc_filtered.vcf"
+		File pass_vcf = "${sample}_hc_PASS.vcf"
+	}
+}
+
+
+
+
+

workflow.wdl

@@ -0,0 +1,56 @@
+import "./tasks/Haplotyper.wdl" as Haplotyper
+import "./tasks/Hardfiltration.wdl" as Hardfiltration
+import "./tasks/Annovar.wdl" as Annovar
+
+workflow {{ project_name }} {
+
+	String SENTIEON_INSTALL_DIR
+	String sample
+	String docker
+	
+	String fasta
+	File ref_dir
+	File dbmills_dir
+	String db_mills
+	File dbsnp_dir
+	String dbsnp
+	String disk_size
+	String cluster_config
+
+	File recaled_bam
+	File database
+	File recaled_bam_index
+
+	call Haplotyper.Haplotyper as Haplotyper {
+		input:
+		SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+		fasta=fasta,
+		ref_dir=ref_dir,
+		recaled_bam=recaled_bam,
+		recaled_bam_index=recaled_bam_index,
+		dbsnp=dbsnp,
+		dbsnp_dir=dbsnp_dir,
+		sample=sample,
+		docker=docker,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+	call Hardfiltration.Hardfiltration  as Hardfiltration {
+		input:
+		docker=hardfiltration_docker,
+		sample=sample,
+		vcf_index=Haplotyper.vcf_index,
+		disk_size=disk_size,
+		vcf_file=Haplotyper.vcf_file,
+		cluster_config=cluster_config
+	}
+	call Annovar.Annovar as Annovar {
+		input:
+		docker=annovar_docker,
+		database=database,
+		vcf_file=Hardfiltration.pass_vcf,
+		sample=sample,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+}