first commit

inputs

@@ -0,0 +1,41 @@
+{
+    "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
+    "{{ project_name }}.sample_id": "{{ sample_id }}",
+    "{{ project_name }}.read1": "{{ read1 }}",
+    "{{ project_name }}.read2": "{{ read2 }}",
+    "{{ project_name }}.idx": "oss://pgx-reference-data/reference/hisat2/grch38_snp_tran/",
+    "{{ project_name }}.gtf": "oss://pgx-reference-data/reference/annotation/Homo_sapiens.GRCh38.93.gtf",
+    "{{ project_name }}.idx_prefix": "genome_snp_tran",
+    "{{ project_name }}.hisat2.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/hisat2:v2.1.0-2",
+    "{{ project_name }}.hisat2.cluster": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+    "{{ project_name }}.samtools.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/samtools:v1.3.1",
+    "{{ project_name }}.samtools.cluster": "OnDemand bcs.a2.large img-ubuntu-vpc",
+    "{{ project_name }}.stringtie.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/stringtie:v1.3.4",
+    "{{ project_name }}.stringtie.cluster": "OnDemand bcs.a2.large img-ubuntu-vpc",
+    "{{ project_name }}.fastp.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastp:0.19.6",
+    "{{ project_name }}.fastp.cluster": "OnDemand bcs.a2.large img-ubuntu-vpc",
+    "{{ project_name }}.adapter_sequence": "{{ adapter_sequence  }}",
+    "{{ project_name }}.adapter_sequence_r2": "{{ adapter_sequence_r2 }}",
+    "{{ 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 }}.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 }}.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/fastp.wdl

@@ -0,0 +1,30 @@
+task fastp {
+    String sample_id
+    File read1
+    File read2
+    String adapter_sequence
+    String adapter_sequence_r2
+    String docker
+    String cluster
+
+   command <<<
+     fastp --thread 4 -l 50 -q 20 -u 20 --adapter_sequence ${adapter_sequence} --adapter_sequence_r2 ${adapter_sequence_r2} --detect_adapter_for_pe -i  ${read1} -I ${read2} -o ${sample_id}_R1.fastq.gz -O ${sample_id}_R2.fastq.gz -j ${sample_id}.json -h ${sample_id}.html
+   >>>
+   
+   runtime { 
+		docker: docker 
+		cluster: cluster
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd 200 /cromwell_root/"
+   }
+
+   output {
+      File json = "${sample_id}.json"
+      File report = "${sample_id}.html"
+      File Trim_R1 = "${sample_id}_R1.fastq.gz"
+      File Trim_R2 = "${sample_id}_R2.fastq.gz"
+   }
+}
+
+
+

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

@@ -0,0 +1,27 @@
+task hisat2 {
+   File idx
+   File Trim_R1
+   File Trim_R2
+   String idx_prefix
+   String sample_id
+   String docker
+   String cluster
+
+   command <<<
+   	 nt=$(nproc)
+     hisat2 -t -p $nt -x ${idx}/${idx_prefix} -1 ${Trim_R1} -2 ${Trim_R2} -S ${sample_id}.sam  --un-conc-gz ${sample_id}_un.fq.gz
+   >>>
+   
+   runtime { 
+		docker: docker 
+		cluster: cluster
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd 200 /cromwell_root/"
+   }
+
+   output {
+      File sam = "${sample_id}.sam"
+      File unmapread_1p = "${sample_id}_un.fq.1.gz"
+      File unmapread_2p = "${sample_id}_un.fq.2.gz"
+   }
+}

tasks/multiqc.wdl

@@ -0,0 +1,51 @@
+task multiqc {
+
+	Array[File] read1_zip
+	Array[File] read2_zip
+
+	Array[File] txt1
+	Array[File] txt2
+
+	Array[File] bamqc_zip
+	Array[File] rnaseq_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/bamqc
+		mkdir -p /cromwell_root/tmp/rnaseq
+
+		cp ${sep=" " read1_zip} ${sep=" " read2_zip} /cromwell_root/tmp/fastqc
+		cp ${sep=" " txt1} ${sep=" " txt2} /cromwell_root/tmp/fastqscreen
+		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/
+	
+	>>>
+
+	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/*")
+	}
+}

tasks/qualimapBAMqc.wdl

@@ -0,0 +1,26 @@
+task qualimapBAMqc {
+	File bam
+	String bamname = basename(bam,".bam")
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		/opt/qualimap/qualimap bamqc -bam ${bam} -outformat PDF:HTML -nt $nt -outdir ${bamname}_bamqc --java-mem-size=32G 
+		tar -zcvf ${bamname}_bamqc_qualimap.zip ${bamname}_bamqc
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File bamqc_zip = "${bamname}_bamqc_qualimap.zip"
+	}
+}

tasks/samtools.wdl

@@ -0,0 +1,34 @@
+task samtools {
+    File sam
+    String sample_id
+    String bam = sample_id + ".bam"
+    String sorted_bam = sample_id + ".sorted.bam"
+    String sorted_bam_index = sample_id + ".sorted.bam.bai"
+    String ins_size = sample_id + ".ins_size"
+    String docker
+    String cluster
+
+    command <<<
+       set -o pipefail
+       set -e
+       /opt/conda/bin/samtools view -bS ${sam} > ${bam}
+       /opt/conda/bin/samtools sort -m 1000000000 ${bam} -o ${sorted_bam}
+       /opt/conda/bin/samtools index ${sorted_bam}
+       /opt/conda/bin/samtools stats -i 8000 ${sorted_bam} |grep ^IS|cut -f 2- > ${sample_id}.ins_size
+    >>>
+
+    runtime {
+       docker: docker
+       cluster: cluster
+       systemDisk: "cloud_ssd 40"
+       dataDisk: "cloud_ssd 200 /cromwell_root/"
+    }
+
+    output {
+      File out_bam = sorted_bam
+      File out_bam_index = sorted_bam_index
+      File out_ins_size = ins_size
+    }
+
+}
+

tasks/stringtie.wdl

@@ -0,0 +1,27 @@
+task stringtie {
+    File bam
+    File gtf
+    String docker
+    String sample_id
+    String cluster
+
+    command <<<
+      nt=$(nproc)
+      mkdir ballgown
+      /opt/conda/bin/stringtie -e -B -p $nt -G ${gtf} -o ballgown/${sample_id}/${sample_id}.gtf -C ${sample_id}.cov.ref.gtf -A ${sample_id}.gene.abundance.txt ${bam} -g ${sample_id}_genecount.csv
+    >>>
+    
+    runtime {
+      docker: docker
+      cluster: cluster
+      systemDisk: "cloud_ssd 40"
+      dataDisk: "cloud_ssd 150 /cromwell_root/"
+    }
+    
+    output {
+      File covered_transcripts = "${sample_id}.cov.ref.gtf"
+      File gene_abundance = "${sample_id}.gene.abundance.txt"
+      Array[File] ballgown = ["ballgown/${sample_id}/${sample_id}.gtf", "ballgown/${sample_id}/e2t.ctab", "ballgown/${sample_id}/e_data.ctab", "ballgown/${sample_id}/i2t.ctab", "ballgown/${sample_id}/i_data.ctab", "ballgown/${sample_id}/t_data.ctab"]
+      File genecount = "{sample_id}_genecount.csv"
+    }
+}

workflow.wdl

@@ -0,0 +1,91 @@
+import "./tasks/fastp.wdl" as fastp
+import "./tasks/hisat2.wdl" as hisat2
+import "./tasks/fastqc.wdl" as fastqc
+import "./tasks/multiqc.wdl" as multiqc
+import "./tasks/samtools.wdl" as samtools
+import "./tasks/fastqscreen.wdl" as fastqscreen
+import "./tasks/qualimapBAMqc.wdl" as qualimapBAMqc
+import "./tasks/stringtie.wdl" as stringtie
+
+
+workflow {{ project_name }} {
+	File inputSamplesFile
+	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
+	File screen_ref_dir
+	File fastq_screen_conf
+	File gtf
+	String fasta
+    	String sample_id
+	File read1
+	File read2
+    	File idx
+	String adapter_sequence
+    	String adapter_sequence_r2
+	String idx_prefix
+    	File gtf
+
+
+	scatter (quartet in inputSamples){
+
+		call fastp.fastp as fastp {
+			input: 
+            		sample_id=quartet[2],
+		    read1=quartet[0], 
+		    read2=quartet[1], 
+		    adapter_sequence=quartet[3], 
+		    adapter_sequence_r2=quartet[4]
+		}
+
+		call fastqc.fastqc as fastqc {
+		    input:
+		    read1=fastp.Trim_R1, 
+		    read2=fastp.Trim_R2
+		}
+
+		call fastqscreen.fastqscreen as fastqscreen {
+            input:
+            read1=fastp.Trim_R1, 
+		    read2=fastp.Trim_R2,
+			screen_ref_dir=screen_ref_dir,
+			fastq_screen_conf=fastq_screen_conf
+		}
+
+		call hisat2.hisat2 as hisat2 {
+			input: 
+		    sample_id=quartet[2],
+		    idx=idx, 
+		    idx_prefix=idx_prefix, 
+		    Trim_R1=fastp.Trim_R1, 
+		    Trim_R2=fastp.Trim_R2
+		}
+
+        call samtools.samtools as samtools {
+            input: 
+		    sample_id=quartet[2],
+		    sam = hisat2.sam 
+            }
+        
+        call qualimapBAMqc.qualimapBAMqc as qualimapBAMqc {
+			input:
+			bam= samtools.out_bam
+		}
+
+
+        call stringtie.stringtie as stringtie {
+              input: 
+		    sample_id=quartet[2],
+            		gtf = gtf, 
+		    bam = samtools.out_bam
+	}
+}
+
+
+	call multiqc.multiqc as multiqc {
+		input:
+		read1_zip=fastqc.read1_zip,
+		read2_zip=fastqc.read2_zip,
+		txt1=fastqscreen.txt1,
+		txt2=fastqscreen.txt2,
+		rnaseq_zip=qualimapRNAseq.rnaseq_zip
+	}
+}