first commit

defaults

@@ -0,0 +1,13 @@
+{
+  "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",
+  "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",
+  "samtools_cluster": "OnDemand bcs.a2.large img-ubuntu-vpc",
+  "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",
+}

inputs

@@ -0,0 +1,15 @@
+{
+    "{{ project_name }}.read1": "{{ read1 }}",
+    "{{ project_name }}.read2": "{{ read2 }}",
+    "{{ project_name }}.idx": "{{ idx }}",
+    "{{ project_name }}.gtf": "{{ gtf }}",
+    "{{ project_name }}.idx_prefix": "{{ idx_prefix }}",
+    "{{ project_name }}.hisat2.docker": "{{ hisat2_docker }}",
+    "{{ project_name }}.hisat2.cluster": "{{ hisat2_cluster }}",
+    "{{ project_name }}.samtools.docker": "{{ samtools_docker }}",
+    "{{ project_name }}.samtools.cluster": "{{ samtools_cluster }}",
+    "{{ project_name }}.stringtie.docker": "{{ stringtie_docker }}",
+    "{{ project_name }}.stringtie.cluster": "{{ stringtie_cluster }}"
+    "{{ project_name }}.ballgown.docker": "{{ ballgown_docker }}",
+    "{{ project_name }}.ballgown.cluster": "{{ ballgown_cluster }}"
+}

readme.md

@@ -0,0 +1,23 @@
+> Author: Jun Shang
+>
+> Email: shangjunv@163.com
+>
+> Last Updates: 25/02/2020
+
+#### Requirements
+
+- choppy
+- Ali-Cloud
+
+```
+$ source activate choppy/open-choppy-env
+$ choppy install junshang/rna-seq-pair-end-viral
+$ choppy apps
+```
+
+#### quick start
+
+```
+$ choppy samples junshang/rna-seq-pair-end-viral-latest > samples.csv
+$ choppy batch junshang/rna-seq-pair-end-viral-latest samples.csv -p Your_project_name
+```

tasks/ballgown.wdl

@@ -0,0 +1,24 @@
+task ballgown {
+    File ballgown
+    File gene_abundance
+    String base = basename(gene_abundance, ".gene.abundance.txt")
+    String docker
+    String cluster
+
+    command <<<
+      mkdir /cromwell_root/tmp/
+      cp -r ${ballgown} /cromwell_root/tmp/
+      Rscript /usr/bin/ballgown.R /cromwell_root/tmp/ballgown/ ${base}.txt
+    >>>
+    
+    runtime {
+      docker: docker
+      cluster: cluster
+      systemDisk: "cloud_ssd 40"
+      dataDisk: "cloud_ssd 150 /cromwell_root/"
+    }
+    
+    output {
+      File mat_expression = "${base}.txt"
+    }
+}

tasks/hisat2.wdl

@@ -0,0 +1,27 @@
+task hisat2 {
+   File idx
+   File read_1P
+   File read_2P
+   String idx_prefix
+   String base = sub(basename(read_1P),"\\.\\S+$", "")
+   String docker
+   String cluster
+
+   command {
+   	 nt=$(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
+   }
+   
+   runtime { 
+		docker: docker 
+		cluster: cluster
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd 200 /cromwell_root/"
+   }
+
+   output {
+      File sam = base + ".sam"
+      File unmapread_1p = base + "_un.fq.1.gz"
+      File unmapread_2p = base + "_un.fq.2.gz"
+   }
+}

tasks/samtools.wdl

@@ -0,0 +1,34 @@
+task samtools {
+    File sam
+    String base = basename(sam, ".sam")
+    String bam = base + ".bam"
+    String sorted_bam = base + ".sorted.bam"
+    String sorted_bam_index = base + ".sorted.bam.bai"
+    String viral_samstats = base + ".viral.samstats"
+    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 ${sorted_bam} > ${viral_samstats}
+    >>>
+
+    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_viral_samstats = viral_samstats
+    }
+
+}
+

tasks/stringtie.wdl

@@ -0,0 +1,26 @@
+task stringtie {
+    File bam
+    File gtf
+    String docker
+    String base = basename(bam, ".sorted.bam")
+    String cluster
+
+    command <<<
+      nt=$(nproc)
+      mkdir ballgown
+      /opt/conda/bin/stringtie -e -B -p $nt -G ${gtf} -o ballgown/${base}/${base}.gtf -C ${base}.cov.ref.gtf -A ${base}.gene.abundance.txt ${bam}
+    >>>
+    
+    runtime {
+      docker: docker
+      cluster: cluster
+      systemDisk: "cloud_ssd 40"
+      dataDisk: "cloud_ssd 150 /cromwell_root/"
+    }
+    
+    output {
+      File covered_transcripts = "${base}.cov.ref.gtf"
+      File gene_abundance = "${base}.gene.abundance.txt"
+      Array[File] ballgown = ["ballgown/${base}/${base}.gtf", "ballgown/${base}/e2t.ctab", "ballgown/${base}/e_data.ctab", "ballgown/${base}/i2t.ctab", "ballgown/${base}/i_data.ctab", "ballgown/${base}/t_data.ctab"]
+    }
+}

workflow.wdl

@@ -0,0 +1,35 @@
+import "./tasks/hisat2.wdl" as hisat2
+import "./tasks/samtools.wdl" as samtools
+import "./tasks/stringtie.wdl" as stringtie
+import "./tasks/ballgown.wdl" as ballgown
+
+workflow {{ project_name }} {
+
+	File read1
+	File read2
+    File idx
+	String idx_prefix
+    File gtf
+	
+	
+	call hisat2.hisat2 as hisat2 {
+		input: idx=idx, idx_prefix=idx_prefix, read_1P=read1, read_2P=read2
+	}
+
+    all samtools.samtools as samtools {
+        input: sam = hisat2.sam
+	}
+
+    call stringtie.stringtie as stringtie {
+        input: gtf = gtf, bam = samtools.out_bam
+	}   
+
+	call ballgown.ballgown as ballgown {
+		input: ballgown = stringtie.ballgown
+	}
+
+        
+	
+}
+
+