add-fastqc-fastqcreen

defaults

@@ -2,6 +2,12 @@
     "idx": "oss://pgx-reference-data/reference/hisat2/grch38_snp_tran/", 
     "gtf": "oss://pgx-reference-data/reference/tophat2/annotation/gencode.v22.annotation.gtf",
     "idx_prefix": "genome_snp_tran",
+    "screen_ref_dir": "oss://pgx-reference-data/fastq_screen_reference/",
+    "fastq_screen_conf": "oss://pgx-reference-data/fastq_screen_reference/fastq_screen.conf",
+    "fastqscreen_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqscreen:0.12.0",
+    "fastqscreen_cluster": "OnDemand bcs.b2.3xlarge img-ubuntu-vpc",
+    "fastqc_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqc:v0.11.5",
+    "fastqc_cluster": "OnDemand bcs.b2.3xlarge img-ubuntu-vpc",
     "hisat2_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/hisat2:v2.1.0-2",
     "hisat2_cluster": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
     "samtools_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/samtools:v1.3.1",
@@ -9,5 +15,5 @@
     "stringtie_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/stringtie:v1.3.4",
     "stringtie_cluster": "OnDemand bcs.a2.large img-ubuntu-vpc",
     "ballgown_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/pgx-ballgown:0.0.1",
-    "ballgown_cluster": "OnDemand bcs.a2.large img-ubuntu-vpc"
+    "ballgown_cluster": "OnDemand bcs.b2.large img-ubuntu-vpc"
 }

inputs

@@ -1,9 +1,15 @@
 {
     "{{ project_name }}.read1": "{{ read1 }}",
     "{{ project_name }}.read2": "{{ read2 }}",
+    "{{ project_name }}.screen_ref_dir": "{{ screen_ref_dir }}",
+    "{{ project_name }}.fastq_screen_conf": "{{ fastq_screen_conf }}",
     "{{ project_name }}.idx": "{{ idx }}",
     "{{ project_name }}.gtf": "{{ gtf }}",
     "{{ project_name }}.idx_prefix": "{{ idx_prefix }}",
+    "{{ project_name }}.fastqscreen_docker": "{{ fastqscreen_docker }}",
+    "{{ project_name }}.fastqscreen_cluster": "{{ fastqscreen_cluster }}",
+    "{{ project_name }}.fastqc_cluster": "{{ fastqc_cluster }}",
+    "{{ project_name }}.fastqc_docker": "{{ fastqc_docker }}",
     "{{ project_name }}.hisat2_docker": "{{ hisat2_docker }}",
     "{{ project_name }}.hisat2_cluster": "{{ hisat2_cluster }}",
     "{{ project_name }}.samtools_docker": "{{ samtools_docker }}",

tasks/ballgown.wdl

@@ -4,6 +4,7 @@ task ballgown {
     Array[File] ballgown
     String docker
     String cluster
+    String disk_size
 
     command <<<
       mkdir -p /cromwell_root/tmp/${base}
@@ -15,7 +16,7 @@ task ballgown {
       docker: docker
       cluster: cluster
       systemDisk: "cloud_ssd 40"
-      dataDisk: "cloud_ssd 150 /cromwell_root/"
+      dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
     }
     
     output {

tasks/fastqc.wdl

@@ -0,0 +1,28 @@
+task fastqc {
+	File read1
+	File read2
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		fastqc -t $nt -o ./ ${read1}
+		fastqc -t $nt -o ./ ${read2}
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File read1_html = sub(basename(read1), "\\.(fastq|fq)\\.gz$", "_fastqc.html")
+		File read1_zip = sub(basename(read1), "\\.(fastq|fq)\\.gz$", "_fastqc.zip")
+		File read2_html = sub(basename(read2), "\\.(fastq|fq)\\.gz$", "_fastqc.html")
+		File read2_zip = sub(basename(read2), "\\.(fastq|fq)\\.gz$", "_fastqc.zip")
+	}
+}

tasks/fastqscreen.wdl

@@ -0,0 +1,36 @@
+task fastq_screen {
+	File read1
+	File read2
+	File screen_ref_dir
+	File fastq_screen_conf
+	String read1name = basename(read1,".fastq.gz")
+	String read2name = basename(read2,".fastq.gz")
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		mkdir -p /cromwell_root/tmp
+		cp -r ${screen_ref_dir} /cromwell_root/tmp/
+		fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${read1}
+		fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${read2}
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File png1 = "${read1name}_screen.png"
+		File txt1 = "${read1name}_screen.txt"
+		File html1 = "${read1name}_screen.html"
+		File png2 = "${read2name}_screen.png"
+		File txt2 = "${read2name}_screen.txt"
+		File html2 = "${read2name}_screen.html"
+	}
+}

tasks/hisat2.wdl

@@ -6,9 +6,11 @@ task hisat2 {
    String base = sub(basename(read_1P),"\\.\\S+$", "")
    String docker
    String cluster
+   String disk_size
+   
 
    command {
-   	 nt=$(nproc)
+     nt=$(nproc)
      hisat2 -t -p $nt -x ${idx}/${idx_prefix} -1 ${read_1P} -2 ${read_2P} -S ${base}.sam  --un-conc-gz ${base}_un.fq.gz
    }
    
@@ -16,7 +18,7 @@ task hisat2 {
 		docker: docker 
 		cluster: cluster
 		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd 200 /cromwell_root/"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
    }
 
    output {

tasks/samtools.wdl

@@ -7,6 +7,7 @@ task samtools {
     String viral_samstats = base + ".viral.samstats"
     String docker
     String cluster
+    String disk_size
 
     command <<<
        set -o pipefail
@@ -21,7 +22,7 @@ task samtools {
        docker: docker
        cluster: cluster
        systemDisk: "cloud_ssd 40"
-       dataDisk: "cloud_ssd 200 /cromwell_root/"
+       dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
     }
 
     output {

tasks/stringtie.wdl

@@ -4,6 +4,7 @@ task stringtie {
     String docker
     String base = basename(bam, ".sorted.bam")
     String cluster
+    String disk_size
 
     command <<<
       nt=$(nproc)
@@ -15,7 +16,7 @@ task stringtie {
       docker: docker
       cluster: cluster
       systemDisk: "cloud_ssd 40"
-      dataDisk: "cloud_ssd 150 /cromwell_root/"
+      dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
     }
     
     output {

workflow.wdl

@@ -1,3 +1,5 @@
+import "./tasks/fastqc.wdl" as fastqc
+import "./tasks/fastqscreen.wdl" as fastqscreen
 import "./tasks/hisat2.wdl" as hisat2
 import "./tasks/samtools.wdl" as samtools
 import "./tasks/stringtie.wdl" as stringtie
@@ -10,6 +12,10 @@ workflow {{ project_name }} {
     File idx
 	String idx_prefix
     File gtf
+    String fastqc_docker
+    String fastqc_cluster
+	String fastqscreen_docker
+    String fastqscreen_cluster
 	String hisat2_docker
 	String hisat2_cluster
 	String stringtie_docker
@@ -20,6 +26,24 @@ workflow {{ project_name }} {
 	String ballgown_cluster
 	
 	
+	call fastqc.fastqc as fastqc {
+		input:
+		read1=read1,
+		read2=read2,
+		docker = fastqc_docker,
+		cluster = fastqc_cluster
+		}
+			
+	call fastqscreen.fastqscreen as fastqscreen {
+		input:
+		read1=read1,
+		read2=read2,
+		docker = fastqscreen_docker,
+		cluster = fastqscreen_cluster,
+		screen_ref_dir=screen_ref_dir,
+		fastq_screen_conf=fastq_screen_conf
+		}	
+	
 	call hisat2.hisat2 as hisat2 {
 		input: 
 		docker = hisat2_docker,