second commit

defaults

@@ -0,0 +1,8 @@
+{   
+    "STAR_INDEX_DIR":"oss://pgx-reference-data/reference/arriba/STAR_index_hg38_GENCODE37",
+    "ASSEMBLY_FA":"oss://pgx-reference-data/reference/arriba/hg38.fa",
+    "ANNOTATION_GTF":"oss://pgx-reference-data/reference/arriba/GENCODE37.gtf"
+    "arriba_docker":"registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/arriba:2.1.0",
+    "arriba_cluster":"OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+    "disk_size":"200"
+}

inputs

@@ -0,0 +1,11 @@
+{
+    "{{ project_name }}.fastq1": "{{ fastq1 }}",
+    "{{ project_name }}.fastq2": "{{ fastq2 }}",
+    "{{ project_name }}.sample_id": "{{ sample_id }}",
+    "{{ project_name }}.arriba_docker": "{{ arriba_docker }}",
+    "{{ project_name }}.STAR_INDEX_DIR": "{{ STAR_INDEX_DIR }}",
+    "{{ project_name }}.ASSEMBLY_FA": "{{ ASSEMBLY_FA }}",
+    "{{ project_name }}.ANNOTATION_GTF": "{{ ANNOTATION_GTF }}",
+    "{{ project_name }}.arriba_cluster": "{{ arriba_cluster }}",
+    "{{ project_name }}.disk_size": "{{ disk_size }}"
+}

tasks/arriba.wdl

@@ -0,0 +1,67 @@
+task arriba{
+    String sample_id
+    File fastq1
+    File fastq2
+    File STAR_INDEX_DIR
+    File ASSEMBLY_FA
+    File ANNOTATION_GTF
+
+    String docker
+    String cluster
+    String disk_size
+
+    command <<<
+	
+        set -o pipefail
+        set -e
+
+        mkdir ./output/
+        STAR \
+            --runThreadN 4 \
+            --genomeDir ${STAR_INDEX_DIR} \
+            --genomeLoad NoSharedMemory \
+            --readFilesIn ${fastq1} ${fastq2} \
+            --readFilesCommand zcat \
+            --outStd BAM_Unsorted \
+            --outSAMtype BAM Unsorted \
+            --outSAMunmapped Within \
+            --outBAMcompression 0 \
+            --outFilterMultimapNmax 50 \
+            --peOverlapNbasesMin 10 \
+            --alignSplicedMateMapLminOverLmate 0.5 \
+            --alignSJstitchMismatchNmax 5 -1 5 5 \
+            --chimSegmentMin 10 \
+            --chimOutType WithinBAM HardClip \
+            --chimJunctionOverhangMin 10 \
+            --chimScoreDropMax 30 \
+            --chimScoreJunctionNonGTAG 0 \
+            --chimScoreSeparation 1 \
+            --chimSegmentReadGapMax 3 \
+            --chimMultimapNmax 50 |tee ./output/${sample_id}.Aligned.out.bam |/arriba_v2.1.0/arriba \
+            -x /dev/stdin \
+            -o ./output/${sample_id}_fusions.tsv -O ./output/${sample_id}_fusions.discarded.tsv \
+            -a ${ASSEMBLY_FA} \
+            -g ${ANNOTATION_GTF} \
+            -b /arriba_v2.1.0/database/blacklist_hg38_GRCh38_v2.1.0.tsv.gz \
+            -k /arriba_v2.1.0/database/known_fusions_hg38_GRCh38_v2.1.0.tsv.gz \
+            -t /arriba_v2.1.0/database/known_fusions_hg38_GRCh38_v2.1.0.tsv.gz \
+            -p /arriba_v2.1.0/database/protein_domains_hg38_GRCh38_v2.1.0.gff3
+
+
+    >>>
+	
+    runtime {
+        docker : docker
+        cluster : cluster
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {
+        Array[File] arriba_result=glob("./output/*.tsv")
+        Array[File] arriba_bam=glob("./output/*.bam")
+    }
+
+}
+
+

workflow.wdl

@@ -0,0 +1,30 @@
+import "./tasks/arriba.wdl" as arriba
+
+workflow run_arriba {
+    String sample_id
+    File fastq1
+    File fastq2
+    File STAR_INDEX_DIR
+    File ASSEMBLY_FA
+    File ANNOTATION_GTF
+
+    String arriba_docker
+    String arriba_cluster
+    String disk_size
+
+        call arriba.arriba as arriba {
+                input:	
+                sample_id=sample_id,
+                fastq1=fastq1,
+                fastq2=fastq2,
+                STAR_INDEX_DIR=STAR_INDEX_DIR,
+                ASSEMBLY_FA=ASSEMBLY_FA,
+                ANNOTATION_GTF= ANNOTATION_GTF,
+                docker=arriba_docker,
+                cluster=arriba_cluster,
+                disk_size=disk_size
+        }
+
+
+}	
+